{"current_steps": 10, "total_steps": 25209, "loss": 1.6512, "lr": 4.9977515176118345e-05, "epoch": 0.0011900511722004047, "percentage": 0.04, "elapsed_time": "0:01:13", "remaining_time": "2 days, 3:43:52", "throughput": 45692.5, "total_tokens": 3376896} {"current_steps": 20, "total_steps": 25209, "loss": 0.893, "lr": 4.9952567580506e-05, "epoch": 0.0023801023444008093, "percentage": 0.08, "elapsed_time": "0:02:30", "remaining_time": "2 days, 4:28:55", "throughput": 44945.81, "total_tokens": 6742528} {"current_steps": 30, "total_steps": 25209, "loss": 0.745, "lr": 4.992765730738634e-05, "epoch": 0.003570153516601214, "percentage": 0.12, "elapsed_time": "0:03:27", "remaining_time": "2 days, 0:24:50", "throughput": 48610.2, "total_tokens": 10094464} {"current_steps": 40, "total_steps": 25209, "loss": 0.7023, "lr": 4.9902784263792476e-05, "epoch": 0.004760204688801619, "percentage": 0.16, "elapsed_time": "0:04:20", "remaining_time": "1 day, 21:29:25", "throughput": 51190.68, "total_tokens": 13323136} {"current_steps": 50, "total_steps": 25209, "loss": 0.6658, "lr": 4.987794835708133e-05, "epoch": 0.005950255861002023, "percentage": 0.2, "elapsed_time": "0:05:17", "remaining_time": "1 day, 20:24:20", "throughput": 52803.12, "total_tokens": 16775552} {"current_steps": 60, "total_steps": 25209, "loss": 0.6464, "lr": 4.985314949493234e-05, "epoch": 0.007140307033202428, "percentage": 0.24, "elapsed_time": "0:06:10", "remaining_time": "1 day, 19:08:59", "throughput": 54178.91, "total_tokens": 20078976} {"current_steps": 70, "total_steps": 25209, "loss": 0.6292, "lr": 4.982838758534584e-05, "epoch": 0.008330358205402833, "percentage": 0.28, "elapsed_time": "0:07:19", "remaining_time": "1 day, 19:51:32", "throughput": 53238.63, "total_tokens": 23406592} {"current_steps": 80, "total_steps": 25209, "loss": 0.619, "lr": 4.980366253664179e-05, "epoch": 0.009520409377603237, "percentage": 0.32, "elapsed_time": "0:08:55", "remaining_time": "1 day, 22:43:09", "throughput": 50028.26, "total_tokens": 26787328} {"current_steps": 90, "total_steps": 25209, "loss": 0.6069, "lr": 4.977897425745825e-05, "epoch": 0.010710460549803642, "percentage": 0.36, "elapsed_time": "0:09:54", "remaining_time": "1 day, 22:04:56", "throughput": 50808.13, "total_tokens": 30200320} {"current_steps": 100, "total_steps": 25209, "loss": 0.5992, "lr": 4.975432265674997e-05, "epoch": 0.011900511722004046, "percentage": 0.4, "elapsed_time": "0:12:38", "remaining_time": "2 days, 4:55:48", "throughput": 44194.01, "total_tokens": 33538176} {"current_steps": 110, "total_steps": 25209, "loss": 0.5905, "lr": 4.972970764378705e-05, "epoch": 0.01309056289420445, "percentage": 0.44, "elapsed_time": "0:15:19", "remaining_time": "2 days, 10:16:06", "throughput": 40173.92, "total_tokens": 36933120} {"current_steps": 120, "total_steps": 25209, "loss": 0.5816, "lr": 4.970512912815344e-05, "epoch": 0.014280614066404856, "percentage": 0.48, "elapsed_time": "0:18:35", "remaining_time": "2 days, 16:46:49", "throughput": 36171.11, "total_tokens": 40346496} {"current_steps": 130, "total_steps": 25209, "loss": 0.5805, "lr": 4.968058701974564e-05, "epoch": 0.01547066523860526, "percentage": 0.52, "elapsed_time": "0:20:59", "remaining_time": "2 days, 19:28:08", "throughput": 34677.19, "total_tokens": 43660032} {"current_steps": 140, "total_steps": 25209, "loss": 0.5679, "lr": 4.96560812287712e-05, "epoch": 0.016660716410805666, "percentage": 0.56, "elapsed_time": "0:24:01", "remaining_time": "2 days, 23:42:15", "throughput": 32616.08, "total_tokens": 47018624} {"current_steps": 150, "total_steps": 25209, "loss": 0.5627, "lr": 4.963161166574748e-05, "epoch": 0.01785076758300607, "percentage": 0.6, "elapsed_time": "0:26:52", "remaining_time": "3 days, 2:49:18", "throughput": 31254.37, "total_tokens": 50392832} {"current_steps": 160, "total_steps": 25209, "loss": 0.5576, "lr": 4.960717824150013e-05, "epoch": 0.019040818755206475, "percentage": 0.63, "elapsed_time": "0:29:25", "remaining_time": "3 days, 4:46:59", "throughput": 30409.84, "total_tokens": 53692416} {"current_steps": 170, "total_steps": 25209, "loss": 0.5547, "lr": 4.9582780867161893e-05, "epoch": 0.02023086992740688, "percentage": 0.67, "elapsed_time": "0:31:41", "remaining_time": "3 days, 5:48:17", "throughput": 29965.4, "total_tokens": 56985088} {"current_steps": 180, "total_steps": 25209, "loss": 0.5497, "lr": 4.955841945417105e-05, "epoch": 0.021420921099607283, "percentage": 0.71, "elapsed_time": "0:33:14", "remaining_time": "3 days, 5:01:56", "throughput": 30254.98, "total_tokens": 60339456} {"current_steps": 190, "total_steps": 25209, "loss": 0.5485, "lr": 4.953409391427024e-05, "epoch": 0.022610972271807687, "percentage": 0.75, "elapsed_time": "0:34:08", "remaining_time": "3 days, 2:55:16", "throughput": 31069.17, "total_tokens": 63638656} {"current_steps": 200, "total_steps": 25209, "loss": 0.5454, "lr": 4.950980415950502e-05, "epoch": 0.02380102344400809, "percentage": 0.79, "elapsed_time": "0:35:05", "remaining_time": "3 days, 1:08:10", "throughput": 31838.78, "total_tokens": 67038592} {"current_steps": 210, "total_steps": 25209, "loss": 0.5409, "lr": 4.9485550102222575e-05, "epoch": 0.024991074616208496, "percentage": 0.83, "elapsed_time": "0:35:58", "remaining_time": "2 days, 23:22:58", "throughput": 32579.64, "total_tokens": 70329856} {"current_steps": 220, "total_steps": 25209, "loss": 0.5329, "lr": 4.946133165507037e-05, "epoch": 0.0261811257884089, "percentage": 0.87, "elapsed_time": "0:36:54", "remaining_time": "2 days, 21:51:59", "throughput": 33250.42, "total_tokens": 73628032} {"current_steps": 230, "total_steps": 25209, "loss": 0.5348, "lr": 4.943714873099483e-05, "epoch": 0.027371176960609308, "percentage": 0.91, "elapsed_time": "0:37:52", "remaining_time": "2 days, 20:33:37", "throughput": 33852.37, "total_tokens": 76934016} {"current_steps": 240, "total_steps": 25209, "loss": 0.5257, "lr": 4.9413001243240024e-05, "epoch": 0.028561228132809712, "percentage": 0.95, "elapsed_time": "0:38:48", "remaining_time": "2 days, 19:17:19", "throughput": 34462.19, "total_tokens": 80241152} {"current_steps": 250, "total_steps": 25209, "loss": 0.5285, "lr": 4.938888910534637e-05, "epoch": 0.029751279305010116, "percentage": 0.99, "elapsed_time": "0:39:44", "remaining_time": "2 days, 18:08:26", "throughput": 35043.95, "total_tokens": 83579008} {"current_steps": 260, "total_steps": 25209, "loss": 0.5278, "lr": 4.936481223114932e-05, "epoch": 0.03094133047721052, "percentage": 1.03, "elapsed_time": "0:40:38", "remaining_time": "2 days, 17:00:11", "throughput": 35605.81, "total_tokens": 86831616} {"current_steps": 270, "total_steps": 25209, "loss": 0.5204, "lr": 4.934077053477808e-05, "epoch": 0.03213138164941092, "percentage": 1.07, "elapsed_time": "0:41:34", "remaining_time": "2 days, 15:59:50", "throughput": 36168.5, "total_tokens": 90215040} {"current_steps": 280, "total_steps": 25209, "loss": 0.5208, "lr": 4.931676393065431e-05, "epoch": 0.03332143282161133, "percentage": 1.11, "elapsed_time": "0:42:28", "remaining_time": "2 days, 15:02:04", "throughput": 36708.44, "total_tokens": 93562368} {"current_steps": 290, "total_steps": 25209, "loss": 0.5213, "lr": 4.929279233349088e-05, "epoch": 0.03451148399381174, "percentage": 1.15, "elapsed_time": "0:43:22", "remaining_time": "2 days, 14:06:38", "throughput": 37226.85, "total_tokens": 96870912} {"current_steps": 300, "total_steps": 25209, "loss": 0.5127, "lr": 4.926885565829051e-05, "epoch": 0.03570153516601214, "percentage": 1.19, "elapsed_time": "0:44:28", "remaining_time": "2 days, 13:32:17", "throughput": 37548.01, "total_tokens": 100184320} {"current_steps": 310, "total_steps": 25209, "loss": 0.5169, "lr": 4.924495382034461e-05, "epoch": 0.036891586338212545, "percentage": 1.23, "elapsed_time": "0:47:00", "remaining_time": "2 days, 14:56:12", "throughput": 36675.81, "total_tokens": 103458688} {"current_steps": 320, "total_steps": 25209, "loss": 0.509, "lr": 4.9221086735231975e-05, "epoch": 0.03808163751041295, "percentage": 1.27, "elapsed_time": "0:48:47", "remaining_time": "2 days, 15:14:29", "throughput": 36462.48, "total_tokens": 106731648} {"current_steps": 330, "total_steps": 25209, "loss": 0.5075, "lr": 4.919725431881751e-05, "epoch": 0.039271688682613354, "percentage": 1.31, "elapsed_time": "0:50:27", "remaining_time": "2 days, 15:23:30", "throughput": 36367.68, "total_tokens": 110086272} {"current_steps": 340, "total_steps": 25209, "loss": 0.5124, "lr": 4.917345648725101e-05, "epoch": 0.04046173985481376, "percentage": 1.35, "elapsed_time": "0:52:23", "remaining_time": "2 days, 15:52:23", "throughput": 36080.86, "total_tokens": 113427456} {"current_steps": 350, "total_steps": 25209, "loss": 0.5071, "lr": 4.914969315696596e-05, "epoch": 0.04165179102701416, "percentage": 1.39, "elapsed_time": "0:53:49", "remaining_time": "2 days, 15:42:32", "throughput": 36159.84, "total_tokens": 116765312} {"current_steps": 360, "total_steps": 25209, "loss": 0.5065, "lr": 4.912596424467818e-05, "epoch": 0.042841842199214566, "percentage": 1.43, "elapsed_time": "0:55:14", "remaining_time": "2 days, 15:32:38", "throughput": 36205.69, "total_tokens": 119990784} {"current_steps": 370, "total_steps": 25209, "loss": 0.5025, "lr": 4.910226966738475e-05, "epoch": 0.04403189337141497, "percentage": 1.47, "elapsed_time": "0:56:09", "remaining_time": "2 days, 14:49:38", "throughput": 36585.38, "total_tokens": 123261312} {"current_steps": 380, "total_steps": 25209, "loss": 0.4989, "lr": 4.9078609342362666e-05, "epoch": 0.045221944543615375, "percentage": 1.51, "elapsed_time": "0:56:59", "remaining_time": "2 days, 14:03:30", "throughput": 37003.47, "total_tokens": 126523520} {"current_steps": 390, "total_steps": 25209, "loss": 0.4957, "lr": 4.905498318716775e-05, "epoch": 0.04641199571581578, "percentage": 1.55, "elapsed_time": "0:57:54", "remaining_time": "2 days, 13:25:12", "throughput": 37399.56, "total_tokens": 129945088} {"current_steps": 400, "total_steps": 25209, "loss": 0.4997, "lr": 4.9031391119633295e-05, "epoch": 0.04760204688801618, "percentage": 1.59, "elapsed_time": "0:58:48", "remaining_time": "2 days, 12:47:18", "throughput": 37792.38, "total_tokens": 133345792} {"current_steps": 410, "total_steps": 25209, "loss": 0.4958, "lr": 4.9007833057869e-05, "epoch": 0.04879209806021659, "percentage": 1.63, "elapsed_time": "0:59:53", "remaining_time": "2 days, 12:22:22", "throughput": 38074.81, "total_tokens": 136814720} {"current_steps": 420, "total_steps": 25209, "loss": 0.4956, "lr": 4.898430892025967e-05, "epoch": 0.04998214923241699, "percentage": 1.67, "elapsed_time": "1:00:43", "remaining_time": "2 days, 11:44:32", "throughput": 38435.12, "total_tokens": 140056576} {"current_steps": 430, "total_steps": 25209, "loss": 0.4909, "lr": 4.896081862546415e-05, "epoch": 0.051172200404617396, "percentage": 1.71, "elapsed_time": "1:01:39", "remaining_time": "2 days, 11:13:16", "throughput": 38766.14, "total_tokens": 143422848} {"current_steps": 440, "total_steps": 25209, "loss": 0.4863, "lr": 4.8937362092414e-05, "epoch": 0.0523622515768178, "percentage": 1.75, "elapsed_time": "1:02:47", "remaining_time": "2 days, 10:54:22", "throughput": 38990.4, "total_tokens": 146881152} {"current_steps": 450, "total_steps": 25209, "loss": 0.4864, "lr": 4.891393924031244e-05, "epoch": 0.053552302749018205, "percentage": 1.79, "elapsed_time": "1:03:46", "remaining_time": "2 days, 10:28:41", "throughput": 39241.04, "total_tokens": 150146944} {"current_steps": 460, "total_steps": 25209, "loss": 0.486, "lr": 4.8890549988633095e-05, "epoch": 0.054742353921218616, "percentage": 1.82, "elapsed_time": "1:04:54", "remaining_time": "2 days, 10:12:16", "throughput": 39443.46, "total_tokens": 153615744} {"current_steps": 470, "total_steps": 25209, "loss": 0.4857, "lr": 4.8867194257118907e-05, "epoch": 0.05593240509341902, "percentage": 1.86, "elapsed_time": "1:05:57", "remaining_time": "2 days, 9:52:06", "throughput": 39676.65, "total_tokens": 157034880} {"current_steps": 480, "total_steps": 25209, "loss": 0.4832, "lr": 4.884387196578093e-05, "epoch": 0.057122456265619424, "percentage": 1.9, "elapsed_time": "1:06:56", "remaining_time": "2 days, 9:28:43", "throughput": 39947.62, "total_tokens": 160448256} {"current_steps": 490, "total_steps": 25209, "loss": 0.48, "lr": 4.882058303489718e-05, "epoch": 0.05831250743781983, "percentage": 1.94, "elapsed_time": "1:07:45", "remaining_time": "2 days, 8:58:36", "throughput": 40262.55, "total_tokens": 163707136} {"current_steps": 500, "total_steps": 25209, "loss": 0.4834, "lr": 4.8797327385011496e-05, "epoch": 0.05950255861002023, "percentage": 1.98, "elapsed_time": "1:08:38", "remaining_time": "2 days, 8:32:22", "throughput": 40555.63, "total_tokens": 167040128} {"current_steps": 510, "total_steps": 25209, "loss": 0.4774, "lr": 4.8774104936932425e-05, "epoch": 0.06069260978222064, "percentage": 2.02, "elapsed_time": "1:09:39", "remaining_time": "2 days, 8:13:11", "throughput": 40778.76, "total_tokens": 170418944} {"current_steps": 520, "total_steps": 25209, "loss": 0.4789, "lr": 4.8750915611732076e-05, "epoch": 0.06188266095442104, "percentage": 2.06, "elapsed_time": "1:10:55", "remaining_time": "2 days, 8:07:20", "throughput": 40822.42, "total_tokens": 173714560} {"current_steps": 530, "total_steps": 25209, "loss": 0.4803, "lr": 4.8727759330744986e-05, "epoch": 0.06307271212662144, "percentage": 2.1, "elapsed_time": "1:12:56", "remaining_time": "2 days, 8:36:37", "throughput": 40455.32, "total_tokens": 177060736} {"current_steps": 540, "total_steps": 25209, "loss": 0.4762, "lr": 4.870463601556696e-05, "epoch": 0.06426276329882184, "percentage": 2.14, "elapsed_time": "1:14:39", "remaining_time": "2 days, 8:50:26", "throughput": 40280.35, "total_tokens": 180424960} {"current_steps": 550, "total_steps": 25209, "loss": 0.473, "lr": 4.8681545588054075e-05, "epoch": 0.06545281447102225, "percentage": 2.18, "elapsed_time": "1:16:02", "remaining_time": "2 days, 8:49:11", "throughput": 40283.49, "total_tokens": 183787520} {"current_steps": 560, "total_steps": 25209, "loss": 0.4767, "lr": 4.8658487970321404e-05, "epoch": 0.06664286564322267, "percentage": 2.22, "elapsed_time": "1:17:34", "remaining_time": "2 days, 8:54:11", "throughput": 40224.61, "total_tokens": 187205632} {"current_steps": 570, "total_steps": 25209, "loss": 0.4754, "lr": 4.863546308474209e-05, "epoch": 0.06783291681542307, "percentage": 2.26, "elapsed_time": "1:19:05", "remaining_time": "2 days, 8:58:29", "throughput": 40145.89, "total_tokens": 190492800} {"current_steps": 580, "total_steps": 25209, "loss": 0.4702, "lr": 4.86124708539461e-05, "epoch": 0.06902296798762347, "percentage": 2.3, "elapsed_time": "1:20:27", "remaining_time": "2 days, 8:56:18", "throughput": 40153.15, "total_tokens": 193824640} {"current_steps": 590, "total_steps": 25209, "loss": 0.4675, "lr": 4.8589511200819216e-05, "epoch": 0.07021301915982388, "percentage": 2.34, "elapsed_time": "1:21:26", "remaining_time": "2 days, 8:38:18", "throughput": 40383.44, "total_tokens": 197332608} {"current_steps": 600, "total_steps": 25209, "loss": 0.4688, "lr": 4.8566584048501926e-05, "epoch": 0.07140307033202428, "percentage": 2.38, "elapsed_time": "1:22:19", "remaining_time": "2 days, 8:16:24", "throughput": 40629.63, "total_tokens": 200681344} {"current_steps": 610, "total_steps": 25209, "loss": 0.4719, "lr": 4.854368932038835e-05, "epoch": 0.07259312150422469, "percentage": 2.42, "elapsed_time": "1:23:09", "remaining_time": "2 days, 7:53:27", "throughput": 40877.92, "total_tokens": 203960320} {"current_steps": 620, "total_steps": 25209, "loss": 0.4696, "lr": 4.8520826940125144e-05, "epoch": 0.07378317267642509, "percentage": 2.46, "elapsed_time": "1:23:59", "remaining_time": "2 days, 7:31:18", "throughput": 41131.83, "total_tokens": 207298304} {"current_steps": 630, "total_steps": 25209, "loss": 0.4669, "lr": 4.849799683161046e-05, "epoch": 0.0749732238486255, "percentage": 2.5, "elapsed_time": "1:24:50", "remaining_time": "2 days, 7:10:03", "throughput": 41375.53, "total_tokens": 210623744} {"current_steps": 640, "total_steps": 25209, "loss": 0.4672, "lr": 4.8475198918992835e-05, "epoch": 0.0761632750208259, "percentage": 2.54, "elapsed_time": "1:25:41", "remaining_time": "2 days, 6:49:40", "throughput": 41609.0, "total_tokens": 213935744} {"current_steps": 650, "total_steps": 25209, "loss": 0.4677, "lr": 4.845243312667023e-05, "epoch": 0.0773533261930263, "percentage": 2.58, "elapsed_time": "1:26:34", "remaining_time": "2 days, 6:30:54", "throughput": 41841.68, "total_tokens": 217336064} {"current_steps": 660, "total_steps": 25209, "loss": 0.4671, "lr": 4.842969937928884e-05, "epoch": 0.07854337736522671, "percentage": 2.62, "elapsed_time": "1:27:25", "remaining_time": "2 days, 6:11:51", "throughput": 42064.13, "total_tokens": 220650368} {"current_steps": 670, "total_steps": 25209, "loss": 0.4651, "lr": 4.840699760174217e-05, "epoch": 0.07973342853742711, "percentage": 2.66, "elapsed_time": "1:28:17", "remaining_time": "2 days, 5:53:40", "throughput": 42286.88, "total_tokens": 224011776} {"current_steps": 680, "total_steps": 25209, "loss": 0.4659, "lr": 4.8384327719169906e-05, "epoch": 0.08092347970962752, "percentage": 2.7, "elapsed_time": "1:29:10", "remaining_time": "2 days, 5:36:41", "throughput": 42488.91, "total_tokens": 227334912} {"current_steps": 690, "total_steps": 25209, "loss": 0.4612, "lr": 4.836168965695694e-05, "epoch": 0.08211353088182792, "percentage": 2.74, "elapsed_time": "1:30:06", "remaining_time": "2 days, 5:21:41", "throughput": 42684.14, "total_tokens": 230751104} {"current_steps": 700, "total_steps": 25209, "loss": 0.4582, "lr": 4.8339083340732304e-05, "epoch": 0.08330358205402832, "percentage": 2.78, "elapsed_time": "1:31:16", "remaining_time": "2 days, 5:15:31", "throughput": 42767.72, "total_tokens": 234197888} {"current_steps": 710, "total_steps": 25209, "loss": 0.4613, "lr": 4.8316508696368154e-05, "epoch": 0.08449363322622873, "percentage": 2.82, "elapsed_time": "1:32:09", "remaining_time": "2 days, 4:59:49", "throughput": 42953.81, "total_tokens": 237501312} {"current_steps": 720, "total_steps": 25209, "loss": 0.4629, "lr": 4.8293965649978714e-05, "epoch": 0.08568368439842913, "percentage": 2.86, "elapsed_time": "1:33:01", "remaining_time": "2 days, 4:43:49", "throughput": 43147.8, "total_tokens": 240814720} {"current_steps": 730, "total_steps": 25209, "loss": 0.4612, "lr": 4.8271454127919364e-05, "epoch": 0.08687373557062954, "percentage": 2.9, "elapsed_time": "1:33:52", "remaining_time": "2 days, 4:27:48", "throughput": 43348.02, "total_tokens": 244150144} {"current_steps": 740, "total_steps": 25209, "loss": 0.4555, "lr": 4.824897405678549e-05, "epoch": 0.08806378674282994, "percentage": 2.94, "elapsed_time": "1:34:47", "remaining_time": "2 days, 4:14:34", "throughput": 43528.94, "total_tokens": 247584000} {"current_steps": 750, "total_steps": 25209, "loss": 0.4563, "lr": 4.8226525363411576e-05, "epoch": 0.08925383791503035, "percentage": 2.98, "elapsed_time": "1:35:40", "remaining_time": "2 days, 4:00:09", "throughput": 43721.21, "total_tokens": 250981888} {"current_steps": 760, "total_steps": 25209, "loss": 0.4557, "lr": 4.820410797487017e-05, "epoch": 0.09044388908723075, "percentage": 3.01, "elapsed_time": "1:36:30", "remaining_time": "2 days, 3:44:38", "throughput": 43922.27, "total_tokens": 254330880} {"current_steps": 770, "total_steps": 25209, "loss": 0.4551, "lr": 4.818172181847091e-05, "epoch": 0.09163394025943115, "percentage": 3.05, "elapsed_time": "1:37:21", "remaining_time": "2 days, 3:29:47", "throughput": 44115.66, "total_tokens": 257680384} {"current_steps": 780, "total_steps": 25209, "loss": 0.4551, "lr": 4.81593668217595e-05, "epoch": 0.09282399143163156, "percentage": 3.09, "elapsed_time": "1:38:14", "remaining_time": "2 days, 3:16:37", "throughput": 44291.75, "total_tokens": 261058560} {"current_steps": 790, "total_steps": 25209, "loss": 0.4582, "lr": 4.813704291251675e-05, "epoch": 0.09401404260383196, "percentage": 3.13, "elapsed_time": "1:39:03", "remaining_time": "2 days, 3:01:59", "throughput": 44471.19, "total_tokens": 264321408} {"current_steps": 800, "total_steps": 25209, "loss": 0.4542, "lr": 4.811475001875759e-05, "epoch": 0.09520409377603237, "percentage": 3.17, "elapsed_time": "1:39:58", "remaining_time": "2 days, 2:50:16", "throughput": 44639.12, "total_tokens": 267760768} {"current_steps": 810, "total_steps": 25209, "loss": 0.453, "lr": 4.8092488068730105e-05, "epoch": 0.09639414494823277, "percentage": 3.21, "elapsed_time": "1:40:49", "remaining_time": "2 days, 2:37:01", "throughput": 44811.65, "total_tokens": 271083136} {"current_steps": 820, "total_steps": 25209, "loss": 0.4518, "lr": 4.807025699091452e-05, "epoch": 0.09758419612043318, "percentage": 3.25, "elapsed_time": "1:41:40", "remaining_time": "2 days, 2:24:08", "throughput": 44977.37, "total_tokens": 274390144} {"current_steps": 830, "total_steps": 25209, "loss": 0.4505, "lr": 4.8048056714022325e-05, "epoch": 0.09877424729263358, "percentage": 3.29, "elapsed_time": "1:42:36", "remaining_time": "2 days, 2:13:52", "throughput": 45129.39, "total_tokens": 277842432} {"current_steps": 840, "total_steps": 25209, "loss": 0.4498, "lr": 4.802588716699519e-05, "epoch": 0.09996429846483398, "percentage": 3.33, "elapsed_time": "1:43:26", "remaining_time": "2 days, 2:01:01", "throughput": 45297.47, "total_tokens": 281149312} {"current_steps": 850, "total_steps": 25209, "loss": 0.4507, "lr": 4.8003748279004156e-05, "epoch": 0.10115434963703439, "percentage": 3.37, "elapsed_time": "1:44:17", "remaining_time": "2 days, 1:48:33", "throughput": 45472.99, "total_tokens": 284528128} {"current_steps": 860, "total_steps": 25209, "loss": 0.4467, "lr": 4.798163997944854e-05, "epoch": 0.10234440080923479, "percentage": 3.41, "elapsed_time": "1:45:12", "remaining_time": "2 days, 1:38:33", "throughput": 45613.69, "total_tokens": 287918720} {"current_steps": 870, "total_steps": 25209, "loss": 0.4502, "lr": 4.79595621979551e-05, "epoch": 0.1035344519814352, "percentage": 3.45, "elapsed_time": "1:46:07", "remaining_time": "2 days, 1:28:46", "throughput": 45753.66, "total_tokens": 291320704} {"current_steps": 880, "total_steps": 25209, "loss": 0.4508, "lr": 4.793751486437702e-05, "epoch": 0.1047245031536356, "percentage": 3.49, "elapsed_time": "1:46:57", "remaining_time": "2 days, 1:17:08", "throughput": 45910.1, "total_tokens": 294639232} {"current_steps": 890, "total_steps": 25209, "loss": 0.4517, "lr": 4.7915497908793064e-05, "epoch": 0.105914554325836, "percentage": 3.53, "elapsed_time": "1:47:48", "remaining_time": "2 days, 1:05:44", "throughput": 46063.23, "total_tokens": 297951616} {"current_steps": 900, "total_steps": 25209, "loss": 0.4495, "lr": 4.7893511261506516e-05, "epoch": 0.10710460549803641, "percentage": 3.57, "elapsed_time": "1:48:42", "remaining_time": "2 days, 0:56:11", "throughput": 46202.31, "total_tokens": 301352832} {"current_steps": 910, "total_steps": 25209, "loss": 0.4478, "lr": 4.787155485304435e-05, "epoch": 0.10829465667023681, "percentage": 3.61, "elapsed_time": "1:49:31", "remaining_time": "2 days, 0:44:24", "throughput": 46357.39, "total_tokens": 304621824} {"current_steps": 920, "total_steps": 25209, "loss": 0.4426, "lr": 4.784962861415629e-05, "epoch": 0.10948470784243723, "percentage": 3.65, "elapsed_time": "1:50:23", "remaining_time": "2 days, 0:34:35", "throughput": 46502.93, "total_tokens": 308026112} {"current_steps": 930, "total_steps": 25209, "loss": 0.452, "lr": 4.7827732475813884e-05, "epoch": 0.11067475901463764, "percentage": 3.69, "elapsed_time": "1:51:15", "remaining_time": "2 days, 0:24:36", "throughput": 46646.96, "total_tokens": 311396480} {"current_steps": 940, "total_steps": 25209, "loss": 0.4487, "lr": 4.7805866369209576e-05, "epoch": 0.11186481018683804, "percentage": 3.73, "elapsed_time": "1:52:11", "remaining_time": "2 days, 0:16:47", "throughput": 46753.04, "total_tokens": 314741376} {"current_steps": 950, "total_steps": 25209, "loss": 0.4479, "lr": 4.778403022575583e-05, "epoch": 0.11305486135903844, "percentage": 3.77, "elapsed_time": "1:53:12", "remaining_time": "2 days, 0:10:40", "throughput": 46836.67, "total_tokens": 318116736} {"current_steps": 960, "total_steps": 25209, "loss": 0.4478, "lr": 4.7762223977084195e-05, "epoch": 0.11424491253123885, "percentage": 3.81, "elapsed_time": "1:54:12", "remaining_time": "2 days, 0:04:41", "throughput": 46915.53, "total_tokens": 321472896} {"current_steps": 970, "total_steps": 25209, "loss": 0.444, "lr": 4.774044755504444e-05, "epoch": 0.11543496370343925, "percentage": 3.85, "elapsed_time": "1:55:03", "remaining_time": "1 day, 23:55:05", "throughput": 47048.65, "total_tokens": 324793600} {"current_steps": 980, "total_steps": 25209, "loss": 0.4466, "lr": 4.7718700891703616e-05, "epoch": 0.11662501487563966, "percentage": 3.89, "elapsed_time": "1:55:57", "remaining_time": "1 day, 23:46:48", "throughput": 47173.09, "total_tokens": 328197888} {"current_steps": 990, "total_steps": 25209, "loss": 0.4374, "lr": 4.7696983919345215e-05, "epoch": 0.11781506604784006, "percentage": 3.93, "elapsed_time": "1:56:48", "remaining_time": "1 day, 23:37:31", "throughput": 47301.31, "total_tokens": 331507712} {"current_steps": 1000, "total_steps": 25209, "loss": 0.4461, "lr": 4.7675296570468216e-05, "epoch": 0.11900511722004047, "percentage": 3.97, "elapsed_time": "1:57:39", "remaining_time": "1 day, 23:28:12", "throughput": 47433.23, "total_tokens": 334834304} {"current_steps": 1010, "total_steps": 25209, "loss": 0.4428, "lr": 4.76536387777863e-05, "epoch": 0.12019516839224087, "percentage": 4.01, "elapsed_time": "1:58:34", "remaining_time": "1 day, 23:21:10", "throughput": 47527.1, "total_tokens": 338154112} {"current_steps": 1020, "total_steps": 25209, "loss": 0.4434, "lr": 4.7632010474226915e-05, "epoch": 0.12138521956444127, "percentage": 4.05, "elapsed_time": "1:59:34", "remaining_time": "1 day, 23:15:34", "throughput": 47600.76, "total_tokens": 341497984} {"current_steps": 1030, "total_steps": 25209, "loss": 0.443, "lr": 4.761041159293035e-05, "epoch": 0.12257527073664168, "percentage": 4.09, "elapsed_time": "2:00:25", "remaining_time": "1 day, 23:07:00", "throughput": 47721.35, "total_tokens": 344818944} {"current_steps": 1040, "total_steps": 25209, "loss": 0.4382, "lr": 4.7588842067249e-05, "epoch": 0.12376532190884208, "percentage": 4.13, "elapsed_time": "2:01:16", "remaining_time": "1 day, 22:58:13", "throughput": 47846.0, "total_tokens": 348135424} {"current_steps": 1050, "total_steps": 25209, "loss": 0.4398, "lr": 4.756730183074637e-05, "epoch": 0.12495537308104249, "percentage": 4.17, "elapsed_time": "2:02:09", "remaining_time": "1 day, 22:50:46", "throughput": 47963.95, "total_tokens": 351561984} {"current_steps": 1060, "total_steps": 25209, "loss": 0.4403, "lr": 4.7545790817196314e-05, "epoch": 0.12614542425324288, "percentage": 4.2, "elapsed_time": "2:02:59", "remaining_time": "1 day, 22:41:55", "throughput": 48097.26, "total_tokens": 354923520} {"current_steps": 1070, "total_steps": 25209, "loss": 0.4362, "lr": 4.752430896058212e-05, "epoch": 0.1273354754254433, "percentage": 4.24, "elapsed_time": "2:03:49", "remaining_time": "1 day, 22:33:28", "throughput": 48214.11, "total_tokens": 358206976} {"current_steps": 1080, "total_steps": 25209, "loss": 0.4402, "lr": 4.750285619509567e-05, "epoch": 0.12852552659764369, "percentage": 4.28, "elapsed_time": "2:04:40", "remaining_time": "1 day, 22:25:36", "throughput": 48325.64, "total_tokens": 361521792} {"current_steps": 1090, "total_steps": 25209, "loss": 0.437, "lr": 4.7481432455136644e-05, "epoch": 0.1297155777698441, "percentage": 4.32, "elapsed_time": "2:05:33", "remaining_time": "1 day, 22:18:08", "throughput": 48442.94, "total_tokens": 364925696} {"current_steps": 1100, "total_steps": 25209, "loss": 0.4384, "lr": 4.7460037675311584e-05, "epoch": 0.1309056289420445, "percentage": 4.36, "elapsed_time": "2:06:24", "remaining_time": "1 day, 22:10:36", "throughput": 48557.42, "total_tokens": 368293888} {"current_steps": 1110, "total_steps": 25209, "loss": 0.4383, "lr": 4.7438671790433126e-05, "epoch": 0.1320956801142449, "percentage": 4.4, "elapsed_time": "2:07:21", "remaining_time": "1 day, 22:04:56", "throughput": 48637.04, "total_tokens": 371644672} {"current_steps": 1120, "total_steps": 25209, "loss": 0.4389, "lr": 4.741733473551915e-05, "epoch": 0.13328573128644533, "percentage": 4.44, "elapsed_time": "2:08:11", "remaining_time": "1 day, 21:57:11", "throughput": 48746.99, "total_tokens": 374944128} {"current_steps": 1130, "total_steps": 25209, "loss": 0.4383, "lr": 4.7396026445791966e-05, "epoch": 0.13447578245864572, "percentage": 4.48, "elapsed_time": "2:09:01", "remaining_time": "1 day, 21:49:22", "throughput": 48873.34, "total_tokens": 378353152} {"current_steps": 1140, "total_steps": 25209, "loss": 0.4372, "lr": 4.737474685667742e-05, "epoch": 0.13566583363084614, "percentage": 4.52, "elapsed_time": "2:09:53", "remaining_time": "1 day, 21:42:15", "throughput": 48977.12, "total_tokens": 381679872} {"current_steps": 1150, "total_steps": 25209, "loss": 0.4355, "lr": 4.7353495903804165e-05, "epoch": 0.13685588480304653, "percentage": 4.56, "elapsed_time": "2:10:47", "remaining_time": "1 day, 21:36:06", "throughput": 49055.73, "total_tokens": 384941824} {"current_steps": 1160, "total_steps": 25209, "loss": 0.4379, "lr": 4.733227352300277e-05, "epoch": 0.13804593597524695, "percentage": 4.6, "elapsed_time": "2:11:40", "remaining_time": "1 day, 21:29:51", "throughput": 49157.29, "total_tokens": 388365568} {"current_steps": 1170, "total_steps": 25209, "loss": 0.4361, "lr": 4.731107965030496e-05, "epoch": 0.13923598714744734, "percentage": 4.64, "elapsed_time": "2:12:29", "remaining_time": "1 day, 21:22:21", "throughput": 49271.57, "total_tokens": 391708544} {"current_steps": 1180, "total_steps": 25209, "loss": 0.4328, "lr": 4.728991422194278e-05, "epoch": 0.14042603831964776, "percentage": 4.68, "elapsed_time": "2:13:24", "remaining_time": "1 day, 21:16:40", "throughput": 49358.36, "total_tokens": 395089408} {"current_steps": 1190, "total_steps": 25209, "loss": 0.4306, "lr": 4.726877717434773e-05, "epoch": 0.14161608949184815, "percentage": 4.72, "elapsed_time": "2:14:16", "remaining_time": "1 day, 21:10:21", "throughput": 49454.31, "total_tokens": 398450944} {"current_steps": 1200, "total_steps": 25209, "loss": 0.4334, "lr": 4.724766844415013e-05, "epoch": 0.14280614066404856, "percentage": 4.76, "elapsed_time": "2:15:05", "remaining_time": "1 day, 21:02:54", "throughput": 49566.38, "total_tokens": 401768832} {"current_steps": 1210, "total_steps": 25209, "loss": 0.4329, "lr": 4.722658796817813e-05, "epoch": 0.14399619183624895, "percentage": 4.8, "elapsed_time": "2:15:55", "remaining_time": "1 day, 20:55:46", "throughput": 49664.12, "total_tokens": 405013120} {"current_steps": 1220, "total_steps": 25209, "loss": 0.4322, "lr": 4.7205535683457044e-05, "epoch": 0.14518624300844937, "percentage": 4.84, "elapsed_time": "2:16:41", "remaining_time": "1 day, 20:47:56", "throughput": 49777.14, "total_tokens": 408271872} {"current_steps": 1230, "total_steps": 25209, "loss": 0.4341, "lr": 4.7184511527208484e-05, "epoch": 0.14637629418064976, "percentage": 4.88, "elapsed_time": "2:17:30", "remaining_time": "1 day, 20:40:39", "throughput": 49886.93, "total_tokens": 411578368} {"current_steps": 1240, "total_steps": 25209, "loss": 0.4314, "lr": 4.7163515436849644e-05, "epoch": 0.14756634535285018, "percentage": 4.92, "elapsed_time": "2:18:21", "remaining_time": "1 day, 20:34:28", "throughput": 49985.3, "total_tokens": 414958592} {"current_steps": 1250, "total_steps": 25209, "loss": 0.4322, "lr": 4.714254734999245e-05, "epoch": 0.14875639652505057, "percentage": 4.96, "elapsed_time": "2:19:12", "remaining_time": "1 day, 20:28:07", "throughput": 50082.96, "total_tokens": 418301056} {"current_steps": 1260, "total_steps": 25209, "loss": 0.4305, "lr": 4.712160720444284e-05, "epoch": 0.149946447697251, "percentage": 5.0, "elapsed_time": "2:20:03", "remaining_time": "1 day, 20:22:03", "throughput": 50169.03, "total_tokens": 421587456} {"current_steps": 1270, "total_steps": 25209, "loss": 0.4296, "lr": 4.710069493819992e-05, "epoch": 0.15113649886945138, "percentage": 5.04, "elapsed_time": "2:20:50", "remaining_time": "1 day, 20:14:53", "throughput": 50276.96, "total_tokens": 424879360} {"current_steps": 1280, "total_steps": 25209, "loss": 0.4317, "lr": 4.70798104894553e-05, "epoch": 0.1523265500416518, "percentage": 5.08, "elapsed_time": "2:21:41", "remaining_time": "1 day, 20:08:55", "throughput": 50369.72, "total_tokens": 428227456} {"current_steps": 1290, "total_steps": 25209, "loss": 0.428, "lr": 4.705895379659219e-05, "epoch": 0.1535166012138522, "percentage": 5.12, "elapsed_time": "2:22:30", "remaining_time": "1 day, 20:02:19", "throughput": 50469.66, "total_tokens": 431533952} {"current_steps": 1300, "total_steps": 25209, "loss": 0.4267, "lr": 4.7038124798184766e-05, "epoch": 0.1547066523860526, "percentage": 5.16, "elapsed_time": "2:23:22", "remaining_time": "1 day, 19:56:56", "throughput": 50555.57, "total_tokens": 434913408} {"current_steps": 1310, "total_steps": 25209, "loss": 0.4238, "lr": 4.7017323432997304e-05, "epoch": 0.155896703558253, "percentage": 5.2, "elapsed_time": "2:24:15", "remaining_time": "1 day, 19:51:42", "throughput": 50643.11, "total_tokens": 438328832} {"current_steps": 1320, "total_steps": 25209, "loss": 0.4276, "lr": 4.6996549639983506e-05, "epoch": 0.15708675473045342, "percentage": 5.24, "elapsed_time": "2:25:09", "remaining_time": "1 day, 19:47:04", "throughput": 50723.73, "total_tokens": 441783936} {"current_steps": 1330, "total_steps": 25209, "loss": 0.4262, "lr": 4.697580335828569e-05, "epoch": 0.1582768059026538, "percentage": 5.28, "elapsed_time": "2:26:18", "remaining_time": "1 day, 19:46:48", "throughput": 50702.19, "total_tokens": 445082496} {"current_steps": 1340, "total_steps": 25209, "loss": 0.4294, "lr": 4.6955084527234076e-05, "epoch": 0.15946685707485422, "percentage": 5.32, "elapsed_time": "2:27:20", "remaining_time": "1 day, 19:44:28", "throughput": 50722.26, "total_tokens": 448396416} {"current_steps": 1350, "total_steps": 25209, "loss": 0.4269, "lr": 4.6934393086346034e-05, "epoch": 0.16065690824705461, "percentage": 5.36, "elapsed_time": "2:28:13", "remaining_time": "1 day, 19:39:38", "throughput": 50792.67, "total_tokens": 451727616} {"current_steps": 1360, "total_steps": 25209, "loss": 0.429, "lr": 4.6913728975325324e-05, "epoch": 0.16184695941925503, "percentage": 5.39, "elapsed_time": "2:29:07", "remaining_time": "1 day, 19:35:10", "throughput": 50865.0, "total_tokens": 455135104} {"current_steps": 1370, "total_steps": 25209, "loss": 0.4271, "lr": 4.6893092134061393e-05, "epoch": 0.16303701059145542, "percentage": 5.43, "elapsed_time": "2:29:57", "remaining_time": "1 day, 19:29:17", "throughput": 50955.52, "total_tokens": 458457216} {"current_steps": 1380, "total_steps": 25209, "loss": 0.4279, "lr": 4.687248250262859e-05, "epoch": 0.16422706176365584, "percentage": 5.47, "elapsed_time": "2:30:49", "remaining_time": "1 day, 19:24:28", "throughput": 51032.01, "total_tokens": 461836032} {"current_steps": 1390, "total_steps": 25209, "loss": 0.4253, "lr": 4.685190002128548e-05, "epoch": 0.16541711293585623, "percentage": 5.51, "elapsed_time": "2:31:40", "remaining_time": "1 day, 19:19:05", "throughput": 51118.56, "total_tokens": 465202176} {"current_steps": 1400, "total_steps": 25209, "loss": 0.4274, "lr": 4.6831344630474114e-05, "epoch": 0.16660716410805665, "percentage": 5.55, "elapsed_time": "2:32:34", "remaining_time": "1 day, 19:14:49", "throughput": 51186.0, "total_tokens": 468595840} {"current_steps": 1410, "total_steps": 25209, "loss": 0.432, "lr": 4.6810816270819276e-05, "epoch": 0.16779721528025704, "percentage": 5.59, "elapsed_time": "2:33:25", "remaining_time": "1 day, 19:09:44", "throughput": 51265.67, "total_tokens": 471947136} {"current_steps": 1420, "total_steps": 25209, "loss": 0.4236, "lr": 4.679031488312777e-05, "epoch": 0.16898726645245746, "percentage": 5.63, "elapsed_time": "2:34:12", "remaining_time": "1 day, 19:03:31", "throughput": 51362.88, "total_tokens": 475253376} {"current_steps": 1430, "total_steps": 25209, "loss": 0.4286, "lr": 4.6769840408387717e-05, "epoch": 0.17017731762465785, "percentage": 5.67, "elapsed_time": "2:35:03", "remaining_time": "1 day, 18:58:20", "throughput": 51449.94, "total_tokens": 478650624} {"current_steps": 1440, "total_steps": 25209, "loss": 0.4264, "lr": 4.674939278776787e-05, "epoch": 0.17136736879685827, "percentage": 5.71, "elapsed_time": "2:35:56", "remaining_time": "1 day, 18:53:58", "throughput": 51522.68, "total_tokens": 482064256} {"current_steps": 1450, "total_steps": 25209, "loss": 0.4245, "lr": 4.672897196261683e-05, "epoch": 0.17255741996905866, "percentage": 5.75, "elapsed_time": "2:36:53", "remaining_time": "1 day, 18:50:41", "throughput": 51568.75, "total_tokens": 485431936} {"current_steps": 1460, "total_steps": 25209, "loss": 0.4242, "lr": 4.670857787446238e-05, "epoch": 0.17374747114125907, "percentage": 5.79, "elapsed_time": "2:37:43", "remaining_time": "1 day, 18:45:45", "throughput": 51642.37, "total_tokens": 488742016} {"current_steps": 1470, "total_steps": 25209, "loss": 0.427, "lr": 4.668821046501082e-05, "epoch": 0.1749375223134595, "percentage": 5.83, "elapsed_time": "2:38:33", "remaining_time": "1 day, 18:40:32", "throughput": 51722.27, "total_tokens": 492057216} {"current_steps": 1480, "total_steps": 25209, "loss": 0.4219, "lr": 4.6667869676146194e-05, "epoch": 0.17612757348565988, "percentage": 5.87, "elapsed_time": "2:39:24", "remaining_time": "1 day, 18:35:52", "throughput": 51796.27, "total_tokens": 495419392} {"current_steps": 1490, "total_steps": 25209, "loss": 0.4261, "lr": 4.6647555449929645e-05, "epoch": 0.1773176246578603, "percentage": 5.91, "elapsed_time": "2:40:16", "remaining_time": "1 day, 18:31:17", "throughput": 51869.74, "total_tokens": 498786048} {"current_steps": 1500, "total_steps": 25209, "loss": 0.4194, "lr": 4.662726772859869e-05, "epoch": 0.1785076758300607, "percentage": 5.95, "elapsed_time": "2:41:06", "remaining_time": "1 day, 18:26:21", "throughput": 51946.4, "total_tokens": 502117120} {"current_steps": 1510, "total_steps": 25209, "loss": 0.4229, "lr": 4.660700645456655e-05, "epoch": 0.1796977270022611, "percentage": 5.99, "elapsed_time": "2:42:00", "remaining_time": "1 day, 18:22:34", "throughput": 52009.99, "total_tokens": 505542272} {"current_steps": 1520, "total_steps": 25209, "loss": 0.4241, "lr": 4.658677157042149e-05, "epoch": 0.1808877781744615, "percentage": 6.03, "elapsed_time": "2:42:51", "remaining_time": "1 day, 18:18:07", "throughput": 52083.06, "total_tokens": 508929152} {"current_steps": 1530, "total_steps": 25209, "loss": 0.4245, "lr": 4.656656301892605e-05, "epoch": 0.18207782934666192, "percentage": 6.07, "elapsed_time": "2:43:38", "remaining_time": "1 day, 18:12:28", "throughput": 52166.31, "total_tokens": 512169728} {"current_steps": 1540, "total_steps": 25209, "loss": 0.4232, "lr": 4.6546380743016465e-05, "epoch": 0.1832678805188623, "percentage": 6.11, "elapsed_time": "2:44:30", "remaining_time": "1 day, 18:08:24", "throughput": 52225.49, "total_tokens": 515490560} {"current_steps": 1550, "total_steps": 25209, "loss": 0.4212, "lr": 4.652622468580193e-05, "epoch": 0.18445793169106273, "percentage": 6.15, "elapsed_time": "2:45:21", "remaining_time": "1 day, 18:03:58", "throughput": 52296.8, "total_tokens": 518855936} {"current_steps": 1560, "total_steps": 25209, "loss": 0.4208, "lr": 4.650609479056392e-05, "epoch": 0.18564798286326312, "percentage": 6.19, "elapsed_time": "2:46:10", "remaining_time": "1 day, 17:59:06", "throughput": 52375.46, "total_tokens": 522199808} {"current_steps": 1570, "total_steps": 25209, "loss": 0.4236, "lr": 4.648599100075556e-05, "epoch": 0.18683803403546353, "percentage": 6.23, "elapsed_time": "2:47:01", "remaining_time": "1 day, 17:54:53", "throughput": 52443.03, "total_tokens": 525568512} {"current_steps": 1580, "total_steps": 25209, "loss": 0.4224, "lr": 4.6465913260000945e-05, "epoch": 0.18802808520766393, "percentage": 6.27, "elapsed_time": "2:47:51", "remaining_time": "1 day, 17:50:27", "throughput": 52506.13, "total_tokens": 528841088} {"current_steps": 1590, "total_steps": 25209, "loss": 0.4212, "lr": 4.644586151209444e-05, "epoch": 0.18921813637986434, "percentage": 6.31, "elapsed_time": "2:48:48", "remaining_time": "1 day, 17:47:35", "throughput": 52547.77, "total_tokens": 532226944} {"current_steps": 1600, "total_steps": 25209, "loss": 0.4203, "lr": 4.6425835701000084e-05, "epoch": 0.19040818755206473, "percentage": 6.35, "elapsed_time": "2:49:38", "remaining_time": "1 day, 17:43:08", "throughput": 52616.16, "total_tokens": 535549312} {"current_steps": 1610, "total_steps": 25209, "loss": 0.4221, "lr": 4.640583577085084e-05, "epoch": 0.19159823872426515, "percentage": 6.39, "elapsed_time": "2:50:29", "remaining_time": "1 day, 17:39:06", "throughput": 52686.26, "total_tokens": 538970496} {"current_steps": 1620, "total_steps": 25209, "loss": 0.4186, "lr": 4.638586166594806e-05, "epoch": 0.19278828989646554, "percentage": 6.43, "elapsed_time": "2:51:23", "remaining_time": "1 day, 17:35:32", "throughput": 52742.18, "total_tokens": 542349824} {"current_steps": 1630, "total_steps": 25209, "loss": 0.4209, "lr": 4.6365913330760726e-05, "epoch": 0.19397834106866596, "percentage": 6.47, "elapsed_time": "2:52:11", "remaining_time": "1 day, 17:30:47", "throughput": 52809.85, "total_tokens": 545588096} {"current_steps": 1640, "total_steps": 25209, "loss": 0.4227, "lr": 4.6345990709924855e-05, "epoch": 0.19516839224086635, "percentage": 6.51, "elapsed_time": "2:53:00", "remaining_time": "1 day, 17:26:24", "throughput": 52880.11, "total_tokens": 548932608} {"current_steps": 1650, "total_steps": 25209, "loss": 0.4201, "lr": 4.632609374824284e-05, "epoch": 0.19635844341306677, "percentage": 6.55, "elapsed_time": "2:53:49", "remaining_time": "1 day, 17:21:52", "throughput": 52949.52, "total_tokens": 552231808} {"current_steps": 1660, "total_steps": 25209, "loss": 0.4168, "lr": 4.630622239068285e-05, "epoch": 0.19754849458526716, "percentage": 6.58, "elapsed_time": "2:54:39", "remaining_time": "1 day, 17:17:44", "throughput": 53017.84, "total_tokens": 555604608} {"current_steps": 1670, "total_steps": 25209, "loss": 0.421, "lr": 4.628637658237808e-05, "epoch": 0.19873854575746758, "percentage": 6.62, "elapsed_time": "2:55:29", "remaining_time": "1 day, 17:13:32", "throughput": 53080.82, "total_tokens": 558904192} {"current_steps": 1680, "total_steps": 25209, "loss": 0.4164, "lr": 4.626655626862625e-05, "epoch": 0.19992859692966797, "percentage": 6.66, "elapsed_time": "2:56:26", "remaining_time": "1 day, 17:11:06", "throughput": 53113.97, "total_tokens": 562287744} {"current_steps": 1690, "total_steps": 25209, "loss": 0.4202, "lr": 4.624676139488888e-05, "epoch": 0.20111864810186839, "percentage": 6.7, "elapsed_time": "2:57:20", "remaining_time": "1 day, 17:07:55", "throughput": 53166.13, "total_tokens": 565700352} {"current_steps": 1700, "total_steps": 25209, "loss": 0.4149, "lr": 4.6226991906790686e-05, "epoch": 0.20230869927406878, "percentage": 6.74, "elapsed_time": "2:58:15", "remaining_time": "1 day, 17:04:59", "throughput": 53224.24, "total_tokens": 569235968} {"current_steps": 1710, "total_steps": 25209, "loss": 0.4188, "lr": 4.620724775011897e-05, "epoch": 0.2034987504462692, "percentage": 6.78, "elapsed_time": "2:59:08", "remaining_time": "1 day, 17:01:40", "throughput": 53282.8, "total_tokens": 572685696} {"current_steps": 1720, "total_steps": 25209, "loss": 0.4235, "lr": 4.618752887082297e-05, "epoch": 0.20468880161846958, "percentage": 6.82, "elapsed_time": "2:59:58", "remaining_time": "1 day, 16:57:44", "throughput": 53346.18, "total_tokens": 576043264} {"current_steps": 1730, "total_steps": 25209, "loss": 0.4147, "lr": 4.616783521501325e-05, "epoch": 0.20587885279067, "percentage": 6.86, "elapsed_time": "3:00:53", "remaining_time": "1 day, 16:55:03", "throughput": 53395.32, "total_tokens": 579538688} {"current_steps": 1740, "total_steps": 25209, "loss": 0.4182, "lr": 4.614816672896108e-05, "epoch": 0.2070689039628704, "percentage": 6.9, "elapsed_time": "3:01:46", "remaining_time": "1 day, 16:51:43", "throughput": 53448.88, "total_tokens": 582929920} {"current_steps": 1750, "total_steps": 25209, "loss": 0.4143, "lr": 4.612852335909782e-05, "epoch": 0.2082589551350708, "percentage": 6.94, "elapsed_time": "3:02:55", "remaining_time": "1 day, 16:52:04", "throughput": 53429.14, "total_tokens": 586397696} {"current_steps": 1760, "total_steps": 25209, "loss": 0.4172, "lr": 4.6108905052014323e-05, "epoch": 0.2094490063072712, "percentage": 6.98, "elapsed_time": "3:04:09", "remaining_time": "1 day, 16:53:31", "throughput": 53381.46, "total_tokens": 589822208} {"current_steps": 1770, "total_steps": 25209, "loss": 0.4135, "lr": 4.608931175446027e-05, "epoch": 0.21063905747947162, "percentage": 7.02, "elapsed_time": "3:05:29", "remaining_time": "1 day, 16:56:24", "throughput": 53287.78, "total_tokens": 593081344} {"current_steps": 1780, "total_steps": 25209, "loss": 0.4132, "lr": 4.606974341334367e-05, "epoch": 0.211829108651672, "percentage": 7.06, "elapsed_time": "3:06:42", "remaining_time": "1 day, 16:57:25", "throughput": 53245.22, "total_tokens": 596456832} {"current_steps": 1790, "total_steps": 25209, "loss": 0.4159, "lr": 4.605019997573011e-05, "epoch": 0.21301915982387243, "percentage": 7.1, "elapsed_time": "3:07:54", "remaining_time": "1 day, 16:58:29", "throughput": 53193.21, "total_tokens": 599737344} {"current_steps": 1800, "total_steps": 25209, "loss": 0.4156, "lr": 4.603068138884229e-05, "epoch": 0.21420921099607282, "percentage": 7.14, "elapsed_time": "3:09:02", "remaining_time": "1 day, 16:58:31", "throughput": 53164.76, "total_tokens": 603028992} {"current_steps": 1810, "total_steps": 25209, "loss": 0.4127, "lr": 4.6011187600059345e-05, "epoch": 0.21539926216827324, "percentage": 7.18, "elapsed_time": "3:10:25", "remaining_time": "1 day, 17:01:49", "throughput": 53070.1, "total_tokens": 606373120} {"current_steps": 1820, "total_steps": 25209, "loss": 0.4119, "lr": 4.599171855691629e-05, "epoch": 0.21658931334047363, "percentage": 7.22, "elapsed_time": "3:11:37", "remaining_time": "1 day, 17:02:41", "throughput": 53030.88, "total_tokens": 609746048} {"current_steps": 1830, "total_steps": 25209, "loss": 0.418, "lr": 4.597227420710335e-05, "epoch": 0.21777936451267405, "percentage": 7.26, "elapsed_time": "3:12:51", "remaining_time": "1 day, 17:03:47", "throughput": 52985.64, "total_tokens": 613110912} {"current_steps": 1840, "total_steps": 25209, "loss": 0.4165, "lr": 4.595285449846551e-05, "epoch": 0.21896941568487446, "percentage": 7.3, "elapsed_time": "3:14:02", "remaining_time": "1 day, 17:04:31", "throughput": 52944.73, "total_tokens": 616429824} {"current_steps": 1850, "total_steps": 25209, "loss": 0.4164, "lr": 4.593345937900178e-05, "epoch": 0.22015946685707485, "percentage": 7.34, "elapsed_time": "3:15:23", "remaining_time": "1 day, 17:07:08", "throughput": 52862.18, "total_tokens": 619738112} {"current_steps": 1860, "total_steps": 25209, "loss": 0.4138, "lr": 4.591408879686472e-05, "epoch": 0.22134951802927527, "percentage": 7.38, "elapsed_time": "3:16:30", "remaining_time": "1 day, 17:06:43", "throughput": 52840.21, "total_tokens": 622988160} {"current_steps": 1870, "total_steps": 25209, "loss": 0.4176, "lr": 4.5894742700359775e-05, "epoch": 0.22253956920147566, "percentage": 7.42, "elapsed_time": "3:17:41", "remaining_time": "1 day, 17:07:20", "throughput": 52800.99, "total_tokens": 626298880} {"current_steps": 1880, "total_steps": 25209, "loss": 0.419, "lr": 4.587542103794477e-05, "epoch": 0.22372962037367608, "percentage": 7.46, "elapsed_time": "3:18:40", "remaining_time": "1 day, 17:05:24", "throughput": 52821.58, "total_tokens": 629670656} {"current_steps": 1890, "total_steps": 25209, "loss": 0.4177, "lr": 4.5856123758229247e-05, "epoch": 0.22491967154587647, "percentage": 7.5, "elapsed_time": "3:19:31", "remaining_time": "1 day, 17:01:40", "throughput": 52881.3, "total_tokens": 633045760} {"current_steps": 1900, "total_steps": 25209, "loss": 0.4097, "lr": 4.5836850809973993e-05, "epoch": 0.2261097227180769, "percentage": 7.54, "elapsed_time": "3:20:23", "remaining_time": "1 day, 16:58:18", "throughput": 52936.76, "total_tokens": 636465536} {"current_steps": 1910, "total_steps": 25209, "loss": 0.4135, "lr": 4.5817602142090385e-05, "epoch": 0.22729977389027728, "percentage": 7.58, "elapsed_time": "3:21:12", "remaining_time": "1 day, 16:54:19", "throughput": 53003.74, "total_tokens": 639862400} {"current_steps": 1920, "total_steps": 25209, "loss": 0.4163, "lr": 4.579837770363989e-05, "epoch": 0.2284898250624777, "percentage": 7.62, "elapsed_time": "3:21:59", "remaining_time": "1 day, 16:50:04", "throughput": 53063.97, "total_tokens": 643101696} {"current_steps": 1930, "total_steps": 25209, "loss": 0.4147, "lr": 4.57791774438334e-05, "epoch": 0.2296798762346781, "percentage": 7.66, "elapsed_time": "3:22:52", "remaining_time": "1 day, 16:46:57", "throughput": 53113.34, "total_tokens": 646507904} {"current_steps": 1940, "total_steps": 25209, "loss": 0.4144, "lr": 4.576000131203078e-05, "epoch": 0.2308699274068785, "percentage": 7.7, "elapsed_time": "3:23:44", "remaining_time": "1 day, 16:43:40", "throughput": 53160.2, "total_tokens": 649836672} {"current_steps": 1950, "total_steps": 25209, "loss": 0.4092, "lr": 4.574084925774023e-05, "epoch": 0.2320599785790789, "percentage": 7.74, "elapsed_time": "3:24:43", "remaining_time": "1 day, 16:41:56", "throughput": 53172.76, "total_tokens": 653158656} {"current_steps": 1960, "total_steps": 25209, "loss": 0.408, "lr": 4.5721721230617795e-05, "epoch": 0.23325002975127931, "percentage": 7.78, "elapsed_time": "3:25:40", "remaining_time": "1 day, 16:39:42", "throughput": 53196.36, "total_tokens": 656481152} {"current_steps": 1970, "total_steps": 25209, "loss": 0.4146, "lr": 4.57026171804667e-05, "epoch": 0.2344400809234797, "percentage": 7.81, "elapsed_time": "3:26:34", "remaining_time": "1 day, 16:36:47", "throughput": 53239.83, "total_tokens": 659865984} {"current_steps": 1980, "total_steps": 25209, "loss": 0.411, "lr": 4.568353705723692e-05, "epoch": 0.23563013209568012, "percentage": 7.85, "elapsed_time": "3:27:25", "remaining_time": "1 day, 16:33:29", "throughput": 53290.5, "total_tokens": 663233920} {"current_steps": 1990, "total_steps": 25209, "loss": 0.4142, "lr": 4.566448081102455e-05, "epoch": 0.2368201832678805, "percentage": 7.89, "elapsed_time": "3:28:16", "remaining_time": "1 day, 16:30:10", "throughput": 53336.39, "total_tokens": 666532224} {"current_steps": 2000, "total_steps": 25209, "loss": 0.415, "lr": 4.564544839207128e-05, "epoch": 0.23801023444008093, "percentage": 7.93, "elapsed_time": "3:29:13", "remaining_time": "1 day, 16:27:59", "throughput": 53370.65, "total_tokens": 669998464} {"current_steps": 2010, "total_steps": 25209, "loss": 0.4133, "lr": 4.562643975076387e-05, "epoch": 0.23920028561228132, "percentage": 7.97, "elapsed_time": "3:30:07", "remaining_time": "1 day, 16:25:11", "throughput": 53410.6, "total_tokens": 673364352} {"current_steps": 2020, "total_steps": 25209, "loss": 0.4097, "lr": 4.560745483763357e-05, "epoch": 0.24039033678448174, "percentage": 8.01, "elapsed_time": "3:31:04", "remaining_time": "1 day, 16:23:04", "throughput": 53436.89, "total_tokens": 676752256} {"current_steps": 2030, "total_steps": 25209, "loss": 0.4121, "lr": 4.5588493603355595e-05, "epoch": 0.24158038795668213, "percentage": 8.05, "elapsed_time": "3:32:37", "remaining_time": "1 day, 16:27:45", "throughput": 53306.55, "total_tokens": 680044416} {"current_steps": 2040, "total_steps": 25209, "loss": 0.4121, "lr": 4.556955599874859e-05, "epoch": 0.24277043912888255, "percentage": 8.09, "elapsed_time": "3:34:22", "remaining_time": "1 day, 16:34:47", "throughput": 53135.25, "total_tokens": 683468928} {"current_steps": 2050, "total_steps": 25209, "loss": 0.4104, "lr": 4.555064197477409e-05, "epoch": 0.24396049030108294, "percentage": 8.13, "elapsed_time": "3:36:00", "remaining_time": "1 day, 16:40:17", "throughput": 52991.08, "total_tokens": 686800256} {"current_steps": 2060, "total_steps": 25209, "loss": 0.409, "lr": 4.5531751482536e-05, "epoch": 0.24515054147328336, "percentage": 8.17, "elapsed_time": "3:37:29", "remaining_time": "1 day, 16:44:03", "throughput": 52886.46, "total_tokens": 690147456} {"current_steps": 2070, "total_steps": 25209, "loss": 0.4147, "lr": 4.5512884473280024e-05, "epoch": 0.24634059264548375, "percentage": 8.21, "elapsed_time": "3:39:06", "remaining_time": "1 day, 16:49:15", "throughput": 52747.8, "total_tokens": 693453056} {"current_steps": 2080, "total_steps": 25209, "loss": 0.4129, "lr": 4.549404089839322e-05, "epoch": 0.24753064381768417, "percentage": 8.25, "elapsed_time": "3:40:44", "remaining_time": "1 day, 16:54:35", "throughput": 52607.64, "total_tokens": 696762880} {"current_steps": 2090, "total_steps": 25209, "loss": 0.4074, "lr": 4.547522070940335e-05, "epoch": 0.24872069498988456, "percentage": 8.29, "elapsed_time": "3:41:54", "remaining_time": "1 day, 16:54:42", "throughput": 52582.54, "total_tokens": 700118144} {"current_steps": 2100, "total_steps": 25209, "loss": 0.4087, "lr": 4.545642385797848e-05, "epoch": 0.24991074616208497, "percentage": 8.33, "elapsed_time": "3:43:26", "remaining_time": "1 day, 16:58:51", "throughput": 52464.04, "total_tokens": 703369216} {"current_steps": 2110, "total_steps": 25209, "loss": 0.4075, "lr": 4.543765029592637e-05, "epoch": 0.25110079733428536, "percentage": 8.37, "elapsed_time": "3:44:51", "remaining_time": "1 day, 17:01:40", "throughput": 52381.05, "total_tokens": 706717184} {"current_steps": 2120, "total_steps": 25209, "loss": 0.4061, "lr": 4.541889997519403e-05, "epoch": 0.25229084850648575, "percentage": 8.41, "elapsed_time": "3:46:25", "remaining_time": "1 day, 17:06:00", "throughput": 52268.84, "total_tokens": 710100736} {"current_steps": 2130, "total_steps": 25209, "loss": 0.4059, "lr": 4.5400172847867095e-05, "epoch": 0.2534808996786862, "percentage": 8.45, "elapsed_time": "3:48:15", "remaining_time": "1 day, 17:13:10", "throughput": 52094.81, "total_tokens": 713447680} {"current_steps": 2140, "total_steps": 25209, "loss": 0.4055, "lr": 4.5381468866169466e-05, "epoch": 0.2546709508508866, "percentage": 8.49, "elapsed_time": "3:49:52", "remaining_time": "1 day, 17:18:00", "throughput": 51966.82, "total_tokens": 716744704} {"current_steps": 2150, "total_steps": 25209, "loss": 0.4076, "lr": 4.5362787982462616e-05, "epoch": 0.255861002023087, "percentage": 8.53, "elapsed_time": "3:51:07", "remaining_time": "1 day, 17:18:45", "throughput": 51925.65, "total_tokens": 720054784} {"current_steps": 2160, "total_steps": 25209, "loss": 0.4101, "lr": 4.5344130149245275e-05, "epoch": 0.25705105319528737, "percentage": 8.57, "elapsed_time": "3:52:22", "remaining_time": "1 day, 17:19:40", "throughput": 51887.02, "total_tokens": 723446144} {"current_steps": 2170, "total_steps": 25209, "loss": 0.4057, "lr": 4.5325495319152715e-05, "epoch": 0.2582411043674878, "percentage": 8.61, "elapsed_time": "3:53:21", "remaining_time": "1 day, 17:17:31", "throughput": 51904.94, "total_tokens": 726733440} {"current_steps": 2180, "total_steps": 25209, "loss": 0.4105, "lr": 4.530688344495644e-05, "epoch": 0.2594311555396882, "percentage": 8.65, "elapsed_time": "3:54:15", "remaining_time": "1 day, 17:14:39", "throughput": 51945.3, "total_tokens": 730117888} {"current_steps": 2190, "total_steps": 25209, "loss": 0.4069, "lr": 4.528829447956357e-05, "epoch": 0.2606212067118886, "percentage": 8.69, "elapsed_time": "3:55:04", "remaining_time": "1 day, 17:10:52", "throughput": 52001.13, "total_tokens": 733454720} {"current_steps": 2200, "total_steps": 25209, "loss": 0.406, "lr": 4.526972837601633e-05, "epoch": 0.261811257884089, "percentage": 8.73, "elapsed_time": "3:56:00", "remaining_time": "1 day, 17:08:17", "throughput": 52033.26, "total_tokens": 736805120} {"current_steps": 2210, "total_steps": 25209, "loss": 0.4092, "lr": 4.525118508749165e-05, "epoch": 0.26300130905628943, "percentage": 8.77, "elapsed_time": "3:56:50", "remaining_time": "1 day, 17:04:43", "throughput": 52082.18, "total_tokens": 740100992} {"current_steps": 2220, "total_steps": 25209, "loss": 0.41, "lr": 4.5232664567300546e-05, "epoch": 0.2641913602284898, "percentage": 8.81, "elapsed_time": "3:57:38", "remaining_time": "1 day, 17:00:55", "throughput": 52139.46, "total_tokens": 743443968} {"current_steps": 2230, "total_steps": 25209, "loss": 0.4067, "lr": 4.521416676888773e-05, "epoch": 0.2653814114006902, "percentage": 8.85, "elapsed_time": "3:58:29", "remaining_time": "1 day, 16:57:37", "throughput": 52191.72, "total_tokens": 746863232} {"current_steps": 2240, "total_steps": 25209, "loss": 0.4081, "lr": 4.519569164583107e-05, "epoch": 0.26657146257289066, "percentage": 8.89, "elapsed_time": "3:59:18", "remaining_time": "1 day, 16:53:53", "throughput": 52245.69, "total_tokens": 750175744} {"current_steps": 2250, "total_steps": 25209, "loss": 0.4034, "lr": 4.517723915184109e-05, "epoch": 0.26776151374509105, "percentage": 8.93, "elapsed_time": "4:00:10", "remaining_time": "1 day, 16:50:49", "throughput": 52292.39, "total_tokens": 753584256} {"current_steps": 2260, "total_steps": 25209, "loss": 0.4082, "lr": 4.5158809240760506e-05, "epoch": 0.26895156491729144, "percentage": 8.97, "elapsed_time": "4:00:59", "remaining_time": "1 day, 16:47:10", "throughput": 52343.22, "total_tokens": 756867712} {"current_steps": 2270, "total_steps": 25209, "loss": 0.4057, "lr": 4.514040186656375e-05, "epoch": 0.27014161608949183, "percentage": 9.0, "elapsed_time": "4:01:51", "remaining_time": "1 day, 16:44:03", "throughput": 52390.98, "total_tokens": 760273792} {"current_steps": 2280, "total_steps": 25209, "loss": 0.4079, "lr": 4.512201698335644e-05, "epoch": 0.2713316672616923, "percentage": 9.04, "elapsed_time": "4:02:43", "remaining_time": "1 day, 16:41:02", "throughput": 52433.38, "total_tokens": 763634176} {"current_steps": 2290, "total_steps": 25209, "loss": 0.407, "lr": 4.510365454537496e-05, "epoch": 0.27252171843389267, "percentage": 9.08, "elapsed_time": "4:03:34", "remaining_time": "1 day, 16:37:48", "throughput": 52481.24, "total_tokens": 766997376} {"current_steps": 2300, "total_steps": 25209, "loss": 0.4094, "lr": 4.5085314506985945e-05, "epoch": 0.27371176960609306, "percentage": 9.12, "elapsed_time": "4:04:24", "remaining_time": "1 day, 16:34:29", "throughput": 52527.84, "total_tokens": 770317696} {"current_steps": 2310, "total_steps": 25209, "loss": 0.4062, "lr": 4.50669968226858e-05, "epoch": 0.27490182077829345, "percentage": 9.16, "elapsed_time": "4:05:15", "remaining_time": "1 day, 16:31:18", "throughput": 52577.67, "total_tokens": 773728000} {"current_steps": 2320, "total_steps": 25209, "loss": 0.4043, "lr": 4.504870144710027e-05, "epoch": 0.2760918719504939, "percentage": 9.2, "elapsed_time": "4:06:06", "remaining_time": "1 day, 16:28:02", "throughput": 52624.68, "total_tokens": 777063680} {"current_steps": 2330, "total_steps": 25209, "loss": 0.4055, "lr": 4.5030428334983884e-05, "epoch": 0.2772819231226943, "percentage": 9.24, "elapsed_time": "4:07:06", "remaining_time": "1 day, 16:26:30", "throughput": 52634.06, "total_tokens": 780401792} {"current_steps": 2340, "total_steps": 25209, "loss": 0.4069, "lr": 4.501217744121959e-05, "epoch": 0.2784719742948947, "percentage": 9.28, "elapsed_time": "4:08:08", "remaining_time": "1 day, 16:25:01", "throughput": 52642.42, "total_tokens": 783740928} {"current_steps": 2350, "total_steps": 25209, "loss": 0.4032, "lr": 4.499394872081821e-05, "epoch": 0.27966202546709507, "percentage": 9.32, "elapsed_time": "4:08:57", "remaining_time": "1 day, 16:21:36", "throughput": 52693.83, "total_tokens": 787089920} {"current_steps": 2360, "total_steps": 25209, "loss": 0.3996, "lr": 4.4975742128918e-05, "epoch": 0.2808520766392955, "percentage": 9.36, "elapsed_time": "4:09:45", "remaining_time": "1 day, 16:18:04", "throughput": 52743.22, "total_tokens": 790372992} {"current_steps": 2370, "total_steps": 25209, "loss": 0.4041, "lr": 4.495755762078418e-05, "epoch": 0.2820421278114959, "percentage": 9.4, "elapsed_time": "4:10:36", "remaining_time": "1 day, 16:14:57", "throughput": 52788.91, "total_tokens": 793735936} {"current_steps": 2380, "total_steps": 25209, "loss": 0.4042, "lr": 4.49393951518085e-05, "epoch": 0.2832321789836963, "percentage": 9.44, "elapsed_time": "4:11:23", "remaining_time": "1 day, 16:11:18", "throughput": 52842.06, "total_tokens": 797028096} {"current_steps": 2390, "total_steps": 25209, "loss": 0.4048, "lr": 4.4921254677508716e-05, "epoch": 0.2844222301558967, "percentage": 9.48, "elapsed_time": "4:12:12", "remaining_time": "1 day, 16:08:02", "throughput": 52889.76, "total_tokens": 800367104} {"current_steps": 2400, "total_steps": 25209, "loss": 0.4026, "lr": 4.490313615352821e-05, "epoch": 0.28561228132809713, "percentage": 9.52, "elapsed_time": "4:13:01", "remaining_time": "1 day, 16:04:43", "throughput": 52939.5, "total_tokens": 803714688} {"current_steps": 2410, "total_steps": 25209, "loss": 0.4017, "lr": 4.48850395356355e-05, "epoch": 0.2868023325002975, "percentage": 9.56, "elapsed_time": "4:13:50", "remaining_time": "1 day, 16:01:20", "throughput": 52992.22, "total_tokens": 807081856} {"current_steps": 2420, "total_steps": 25209, "loss": 0.4033, "lr": 4.486696477972375e-05, "epoch": 0.2879923836724979, "percentage": 9.6, "elapsed_time": "4:14:39", "remaining_time": "1 day, 15:58:03", "throughput": 53040.52, "total_tokens": 810415744} {"current_steps": 2430, "total_steps": 25209, "loss": 0.4024, "lr": 4.484891184181041e-05, "epoch": 0.2891824348446983, "percentage": 9.64, "elapsed_time": "4:15:25", "remaining_time": "1 day, 15:54:22", "throughput": 53092.48, "total_tokens": 813670272} {"current_steps": 2440, "total_steps": 25209, "loss": 0.4048, "lr": 4.483088067803662e-05, "epoch": 0.29037248601689875, "percentage": 9.68, "elapsed_time": "4:16:15", "remaining_time": "1 day, 15:51:14", "throughput": 53141.66, "total_tokens": 817063168} {"current_steps": 2450, "total_steps": 25209, "loss": 0.4014, "lr": 4.481287124466697e-05, "epoch": 0.29156253718909914, "percentage": 9.72, "elapsed_time": "4:17:05", "remaining_time": "1 day, 15:48:16", "throughput": 53184.88, "total_tokens": 820422272} {"current_steps": 2460, "total_steps": 25209, "loss": 0.4014, "lr": 4.479488349808885e-05, "epoch": 0.2927525883612995, "percentage": 9.76, "elapsed_time": "4:17:55", "remaining_time": "1 day, 15:45:14", "throughput": 53229.27, "total_tokens": 823774208} {"current_steps": 2470, "total_steps": 25209, "loss": 0.4041, "lr": 4.4776917394812114e-05, "epoch": 0.2939426395334999, "percentage": 9.8, "elapsed_time": "4:18:43", "remaining_time": "1 day, 15:41:47", "throughput": 53277.81, "total_tokens": 827042688} {"current_steps": 2480, "total_steps": 25209, "loss": 0.4031, "lr": 4.475897289146862e-05, "epoch": 0.29513269070570036, "percentage": 9.84, "elapsed_time": "4:19:32", "remaining_time": "1 day, 15:38:38", "throughput": 53323.04, "total_tokens": 830359936} {"current_steps": 2490, "total_steps": 25209, "loss": 0.3995, "lr": 4.4741049944811806e-05, "epoch": 0.29632274187790075, "percentage": 9.88, "elapsed_time": "4:20:29", "remaining_time": "1 day, 15:36:41", "throughput": 53344.32, "total_tokens": 833721984} {"current_steps": 2500, "total_steps": 25209, "loss": 0.4025, "lr": 4.472314851171621e-05, "epoch": 0.29751279305010114, "percentage": 9.92, "elapsed_time": "4:21:22", "remaining_time": "1 day, 15:34:13", "throughput": 53371.0, "total_tokens": 836988288} {"current_steps": 2510, "total_steps": 25209, "loss": 0.406, "lr": 4.4705268549177084e-05, "epoch": 0.29870284422230153, "percentage": 9.96, "elapsed_time": "4:22:12", "remaining_time": "1 day, 15:31:11", "throughput": 53415.36, "total_tokens": 840331392} {"current_steps": 2520, "total_steps": 25209, "loss": 0.4015, "lr": 4.468741001430989e-05, "epoch": 0.299892895394502, "percentage": 10.0, "elapsed_time": "4:23:01", "remaining_time": "1 day, 15:28:08", "throughput": 53459.12, "total_tokens": 843654144} {"current_steps": 2530, "total_steps": 25209, "loss": 0.3991, "lr": 4.466957286434997e-05, "epoch": 0.30108294656670237, "percentage": 10.04, "elapsed_time": "4:23:51", "remaining_time": "1 day, 15:25:13", "throughput": 53505.5, "total_tokens": 847070464} {"current_steps": 2540, "total_steps": 25209, "loss": 0.4037, "lr": 4.4651757056652e-05, "epoch": 0.30227299773890276, "percentage": 10.08, "elapsed_time": "4:24:42", "remaining_time": "1 day, 15:22:29", "throughput": 53546.97, "total_tokens": 850464768} {"current_steps": 2550, "total_steps": 25209, "loss": 0.3976, "lr": 4.463396254868968e-05, "epoch": 0.30346304891110315, "percentage": 10.12, "elapsed_time": "4:25:33", "remaining_time": "1 day, 15:19:43", "throughput": 53586.01, "total_tokens": 853813760} {"current_steps": 2560, "total_steps": 25209, "loss": 0.3983, "lr": 4.461618929805519e-05, "epoch": 0.3046531000833036, "percentage": 10.16, "elapsed_time": "4:26:22", "remaining_time": "1 day, 15:16:42", "throughput": 53632.48, "total_tokens": 857189248} {"current_steps": 2570, "total_steps": 25209, "loss": 0.3993, "lr": 4.459843726245888e-05, "epoch": 0.305843151255504, "percentage": 10.19, "elapsed_time": "4:27:12", "remaining_time": "1 day, 15:13:47", "throughput": 53677.05, "total_tokens": 860562304} {"current_steps": 2580, "total_steps": 25209, "loss": 0.4028, "lr": 4.458070639972875e-05, "epoch": 0.3070332024277044, "percentage": 10.23, "elapsed_time": "4:28:01", "remaining_time": "1 day, 15:10:50", "throughput": 53722.28, "total_tokens": 863941248} {"current_steps": 2590, "total_steps": 25209, "loss": 0.3973, "lr": 4.456299666781007e-05, "epoch": 0.3082232535999048, "percentage": 10.27, "elapsed_time": "4:28:48", "remaining_time": "1 day, 15:07:29", "throughput": 53768.0, "total_tokens": 867173120} {"current_steps": 2600, "total_steps": 25209, "loss": 0.3976, "lr": 4.4545308024764984e-05, "epoch": 0.3094133047721052, "percentage": 10.31, "elapsed_time": "4:29:35", "remaining_time": "1 day, 15:04:21", "throughput": 53812.21, "total_tokens": 870461312} {"current_steps": 2610, "total_steps": 25209, "loss": 0.3985, "lr": 4.452764042877207e-05, "epoch": 0.3106033559443056, "percentage": 10.35, "elapsed_time": "4:30:26", "remaining_time": "1 day, 15:01:42", "throughput": 53849.8, "total_tokens": 873814272} {"current_steps": 2620, "total_steps": 25209, "loss": 0.3995, "lr": 4.45099938381259e-05, "epoch": 0.311793407116506, "percentage": 10.39, "elapsed_time": "4:31:17", "remaining_time": "1 day, 14:59:01", "throughput": 53886.39, "total_tokens": 877139328} {"current_steps": 2630, "total_steps": 25209, "loss": 0.3982, "lr": 4.449236821123667e-05, "epoch": 0.31298345828870644, "percentage": 10.43, "elapsed_time": "4:32:08", "remaining_time": "1 day, 14:56:26", "throughput": 53922.54, "total_tokens": 880494592} {"current_steps": 2640, "total_steps": 25209, "loss": 0.3989, "lr": 4.447476350662976e-05, "epoch": 0.31417350946090683, "percentage": 10.47, "elapsed_time": "4:33:01", "remaining_time": "1 day, 14:54:01", "throughput": 53954.73, "total_tokens": 883846400} {"current_steps": 2650, "total_steps": 25209, "loss": 0.3992, "lr": 4.4457179682945346e-05, "epoch": 0.3153635606331072, "percentage": 10.51, "elapsed_time": "4:33:48", "remaining_time": "1 day, 14:50:55", "throughput": 54000.6, "total_tokens": 887167616} {"current_steps": 2660, "total_steps": 25209, "loss": 0.3999, "lr": 4.443961669893798e-05, "epoch": 0.3165536118053076, "percentage": 10.55, "elapsed_time": "4:34:36", "remaining_time": "1 day, 14:47:56", "throughput": 54046.96, "total_tokens": 890530816} {"current_steps": 2670, "total_steps": 25209, "loss": 0.4001, "lr": 4.4422074513476155e-05, "epoch": 0.31774366297750806, "percentage": 10.59, "elapsed_time": "4:35:27", "remaining_time": "1 day, 14:45:17", "throughput": 54088.24, "total_tokens": 893938816} {"current_steps": 2680, "total_steps": 25209, "loss": 0.3948, "lr": 4.4404553085541955e-05, "epoch": 0.31893371414970845, "percentage": 10.63, "elapsed_time": "4:36:17", "remaining_time": "1 day, 14:42:34", "throughput": 54128.87, "total_tokens": 897310976} {"current_steps": 2690, "total_steps": 25209, "loss": 0.4024, "lr": 4.438705237423063e-05, "epoch": 0.32012376532190884, "percentage": 10.67, "elapsed_time": "4:37:06", "remaining_time": "1 day, 14:39:46", "throughput": 54169.67, "total_tokens": 900653184} {"current_steps": 2700, "total_steps": 25209, "loss": 0.3984, "lr": 4.436957233875017e-05, "epoch": 0.32131381649410923, "percentage": 10.71, "elapsed_time": "4:38:01", "remaining_time": "1 day, 14:37:50", "throughput": 54191.56, "total_tokens": 904014208} {"current_steps": 2710, "total_steps": 25209, "loss": 0.3976, "lr": 4.4352112938420956e-05, "epoch": 0.3225038676663097, "percentage": 10.75, "elapsed_time": "4:38:51", "remaining_time": "1 day, 14:35:05", "throughput": 54233.34, "total_tokens": 907385728} {"current_steps": 2720, "total_steps": 25209, "loss": 0.3989, "lr": 4.433467413267529e-05, "epoch": 0.32369391883851006, "percentage": 10.79, "elapsed_time": "4:39:44", "remaining_time": "1 day, 14:32:50", "throughput": 54265.19, "total_tokens": 910789504} {"current_steps": 2730, "total_steps": 25209, "loss": 0.3954, "lr": 4.431725588105708e-05, "epoch": 0.32488397001071045, "percentage": 10.83, "elapsed_time": "4:40:35", "remaining_time": "1 day, 14:30:25", "throughput": 54304.88, "total_tokens": 914255360} {"current_steps": 2740, "total_steps": 25209, "loss": 0.3995, "lr": 4.4299858143221377e-05, "epoch": 0.32607402118291084, "percentage": 10.87, "elapsed_time": "4:41:26", "remaining_time": "1 day, 14:27:54", "throughput": 54343.92, "total_tokens": 917674496} {"current_steps": 2750, "total_steps": 25209, "loss": 0.3958, "lr": 4.4282480878934065e-05, "epoch": 0.3272640723551113, "percentage": 10.91, "elapsed_time": "4:42:16", "remaining_time": "1 day, 14:25:22", "throughput": 54383.65, "total_tokens": 921091712} {"current_steps": 2760, "total_steps": 25209, "loss": 0.4029, "lr": 4.4265124048071346e-05, "epoch": 0.3284541235273117, "percentage": 10.95, "elapsed_time": "4:43:07", "remaining_time": "1 day, 14:22:54", "throughput": 54418.09, "total_tokens": 924448896} {"current_steps": 2770, "total_steps": 25209, "loss": 0.397, "lr": 4.4247787610619477e-05, "epoch": 0.32964417469951207, "percentage": 10.99, "elapsed_time": "4:44:00", "remaining_time": "1 day, 14:20:37", "throughput": 54450.58, "total_tokens": 927848832} {"current_steps": 2780, "total_steps": 25209, "loss": 0.4, "lr": 4.42304715266743e-05, "epoch": 0.33083422587171246, "percentage": 11.03, "elapsed_time": "4:44:51", "remaining_time": "1 day, 14:18:12", "throughput": 54477.5, "total_tokens": 931092096} {"current_steps": 2790, "total_steps": 25209, "loss": 0.3952, "lr": 4.421317575644092e-05, "epoch": 0.3320242770439129, "percentage": 11.07, "elapsed_time": "4:46:01", "remaining_time": "1 day, 14:18:18", "throughput": 54453.1, "total_tokens": 934477568} {"current_steps": 2800, "total_steps": 25209, "loss": 0.3987, "lr": 4.419590026023325e-05, "epoch": 0.3332143282161133, "percentage": 11.11, "elapsed_time": "4:47:12", "remaining_time": "1 day, 14:18:38", "throughput": 54415.68, "total_tokens": 937736320} {"current_steps": 2810, "total_steps": 25209, "loss": 0.3949, "lr": 4.417864499847368e-05, "epoch": 0.3344043793883137, "percentage": 11.15, "elapsed_time": "4:48:13", "remaining_time": "1 day, 14:17:25", "throughput": 54421.62, "total_tokens": 941113984} {"current_steps": 2820, "total_steps": 25209, "loss": 0.3941, "lr": 4.4161409931692676e-05, "epoch": 0.3355944305605141, "percentage": 11.19, "elapsed_time": "4:49:20", "remaining_time": "1 day, 14:17:07", "throughput": 54410.01, "total_tokens": 944559616} {"current_steps": 2830, "total_steps": 25209, "loss": 0.394, "lr": 4.414419502052841e-05, "epoch": 0.3367844817327145, "percentage": 11.23, "elapsed_time": "4:50:09", "remaining_time": "1 day, 14:14:29", "throughput": 54444.42, "total_tokens": 947840768} {"current_steps": 2840, "total_steps": 25209, "loss": 0.3969, "lr": 4.412700022572637e-05, "epoch": 0.3379745329049149, "percentage": 11.27, "elapsed_time": "4:51:01", "remaining_time": "1 day, 14:12:10", "throughput": 54473.95, "total_tokens": 951176064} {"current_steps": 2850, "total_steps": 25209, "loss": 0.3963, "lr": 4.410982550813902e-05, "epoch": 0.3391645840771153, "percentage": 11.31, "elapsed_time": "4:51:53", "remaining_time": "1 day, 14:09:57", "throughput": 54506.63, "total_tokens": 954600320} {"current_steps": 2860, "total_steps": 25209, "loss": 0.3946, "lr": 4.409267082872535e-05, "epoch": 0.3403546352493157, "percentage": 11.35, "elapsed_time": "4:52:43", "remaining_time": "1 day, 14:07:26", "throughput": 54544.97, "total_tokens": 957994368} {"current_steps": 2870, "total_steps": 25209, "loss": 0.3919, "lr": 4.407553614855059e-05, "epoch": 0.34154468642151614, "percentage": 11.38, "elapsed_time": "4:53:35", "remaining_time": "1 day, 14:05:08", "throughput": 54580.59, "total_tokens": 961440000} {"current_steps": 2880, "total_steps": 25209, "loss": 0.396, "lr": 4.405842142878579e-05, "epoch": 0.34273473759371653, "percentage": 11.42, "elapsed_time": "4:54:21", "remaining_time": "1 day, 14:02:15", "throughput": 54619.93, "total_tokens": 964696960} {"current_steps": 2890, "total_steps": 25209, "loss": 0.3922, "lr": 4.404132663070745e-05, "epoch": 0.3439247887659169, "percentage": 11.46, "elapsed_time": "4:55:10", "remaining_time": "1 day, 13:59:34", "throughput": 54658.26, "total_tokens": 968020224} {"current_steps": 2900, "total_steps": 25209, "loss": 0.3962, "lr": 4.402425171569716e-05, "epoch": 0.3451148399381173, "percentage": 11.5, "elapsed_time": "4:56:00", "remaining_time": "1 day, 13:57:07", "throughput": 54696.45, "total_tokens": 971437184} {"current_steps": 2910, "total_steps": 25209, "loss": 0.3942, "lr": 4.400719664524127e-05, "epoch": 0.34630489111031776, "percentage": 11.54, "elapsed_time": "4:56:51", "remaining_time": "1 day, 13:54:50", "throughput": 54728.1, "total_tokens": 974807808} {"current_steps": 2920, "total_steps": 25209, "loss": 0.3927, "lr": 4.399016138093044e-05, "epoch": 0.34749494228251815, "percentage": 11.58, "elapsed_time": "4:57:41", "remaining_time": "1 day, 13:52:23", "throughput": 54762.26, "total_tokens": 978155136} {"current_steps": 2930, "total_steps": 25209, "loss": 0.3891, "lr": 4.397314588445937e-05, "epoch": 0.34868499345471854, "percentage": 11.62, "elapsed_time": "4:58:29", "remaining_time": "1 day, 13:49:37", "throughput": 54800.99, "total_tokens": 981441408} {"current_steps": 2940, "total_steps": 25209, "loss": 0.3963, "lr": 4.395615011762637e-05, "epoch": 0.349875044626919, "percentage": 11.66, "elapsed_time": "4:59:16", "remaining_time": "1 day, 13:46:49", "throughput": 54841.47, "total_tokens": 984744192} {"current_steps": 2950, "total_steps": 25209, "loss": 0.3951, "lr": 4.3939174042333057e-05, "epoch": 0.3510650957991194, "percentage": 11.7, "elapsed_time": "5:00:06", "remaining_time": "1 day, 13:44:29", "throughput": 54872.48, "total_tokens": 988082304} {"current_steps": 2960, "total_steps": 25209, "loss": 0.3945, "lr": 4.3922217620583904e-05, "epoch": 0.35225514697131977, "percentage": 11.74, "elapsed_time": "5:00:56", "remaining_time": "1 day, 13:42:00", "throughput": 54905.58, "total_tokens": 991386880} {"current_steps": 2970, "total_steps": 25209, "loss": 0.3933, "lr": 4.3905280814486025e-05, "epoch": 0.35344519814352016, "percentage": 11.78, "elapsed_time": "5:01:46", "remaining_time": "1 day, 13:39:41", "throughput": 54938.46, "total_tokens": 994758656} {"current_steps": 2980, "total_steps": 25209, "loss": 0.3957, "lr": 4.388836358624867e-05, "epoch": 0.3546352493157206, "percentage": 11.82, "elapsed_time": "5:02:35", "remaining_time": "1 day, 13:37:06", "throughput": 54976.56, "total_tokens": 998106368} {"current_steps": 2990, "total_steps": 25209, "loss": 0.3969, "lr": 4.3871465898182976e-05, "epoch": 0.355825300487921, "percentage": 11.86, "elapsed_time": "5:03:24", "remaining_time": "1 day, 13:34:36", "throughput": 55011.45, "total_tokens": 1001433344} {"current_steps": 3000, "total_steps": 25209, "loss": 0.4002, "lr": 4.385458771270156e-05, "epoch": 0.3570153516601214, "percentage": 11.9, "elapsed_time": "5:04:12", "remaining_time": "1 day, 13:31:59", "throughput": 55048.7, "total_tokens": 1004752128} {"current_steps": 3010, "total_steps": 25209, "loss": 0.3921, "lr": 4.3837728992318205e-05, "epoch": 0.3582054028323218, "percentage": 11.94, "elapsed_time": "5:05:00", "remaining_time": "1 day, 13:29:28", "throughput": 55082.53, "total_tokens": 1008044288} {"current_steps": 3020, "total_steps": 25209, "loss": 0.3958, "lr": 4.382088969964746e-05, "epoch": 0.3593954540045222, "percentage": 11.98, "elapsed_time": "5:05:48", "remaining_time": "1 day, 13:26:51", "throughput": 55118.97, "total_tokens": 1011343232} {"current_steps": 3030, "total_steps": 25209, "loss": 0.3914, "lr": 4.380406979740436e-05, "epoch": 0.3605855051767226, "percentage": 12.02, "elapsed_time": "5:06:38", "remaining_time": "1 day, 13:24:31", "throughput": 55152.81, "total_tokens": 1014712704} {"current_steps": 3040, "total_steps": 25209, "loss": 0.393, "lr": 4.3787269248403994e-05, "epoch": 0.361775556348923, "percentage": 12.06, "elapsed_time": "5:07:27", "remaining_time": "1 day, 13:22:05", "throughput": 55187.57, "total_tokens": 1018059136} {"current_steps": 3050, "total_steps": 25209, "loss": 0.3901, "lr": 4.377048801556126e-05, "epoch": 0.3629656075211234, "percentage": 12.1, "elapsed_time": "5:08:14", "remaining_time": "1 day, 13:19:30", "throughput": 55225.4, "total_tokens": 1021391104} {"current_steps": 3060, "total_steps": 25209, "loss": 0.4004, "lr": 4.3753726061890446e-05, "epoch": 0.36415565869332384, "percentage": 12.14, "elapsed_time": "5:09:04", "remaining_time": "1 day, 13:17:12", "throughput": 55257.78, "total_tokens": 1024754816} {"current_steps": 3070, "total_steps": 25209, "loss": 0.3937, "lr": 4.373698335050488e-05, "epoch": 0.3653457098655242, "percentage": 12.18, "elapsed_time": "5:09:55", "remaining_time": "1 day, 13:14:57", "throughput": 55285.82, "total_tokens": 1028053504} {"current_steps": 3080, "total_steps": 25209, "loss": 0.3941, "lr": 4.372025984461667e-05, "epoch": 0.3665357610377246, "percentage": 12.22, "elapsed_time": "5:11:04", "remaining_time": "1 day, 13:15:02", "throughput": 55255.68, "total_tokens": 1031340416} {"current_steps": 3090, "total_steps": 25209, "loss": 0.3934, "lr": 4.370355550753629e-05, "epoch": 0.367725812209925, "percentage": 12.26, "elapsed_time": "5:12:12", "remaining_time": "1 day, 13:14:49", "throughput": 55235.74, "total_tokens": 1034683136} {"current_steps": 3100, "total_steps": 25209, "loss": 0.3938, "lr": 4.368687030267226e-05, "epoch": 0.36891586338212545, "percentage": 12.3, "elapsed_time": "5:13:15", "remaining_time": "1 day, 13:14:08", "throughput": 55223.82, "total_tokens": 1037960320} {"current_steps": 3110, "total_steps": 25209, "loss": 0.3936, "lr": 4.367020419353081e-05, "epoch": 0.37010591455432584, "percentage": 12.34, "elapsed_time": "5:14:18", "remaining_time": "1 day, 13:13:23", "throughput": 55213.61, "total_tokens": 1041240576} {"current_steps": 3120, "total_steps": 25209, "loss": 0.3941, "lr": 4.365355714371558e-05, "epoch": 0.37129596572652623, "percentage": 12.38, "elapsed_time": "5:15:12", "remaining_time": "1 day, 13:11:35", "throughput": 55230.84, "total_tokens": 1044541568} {"current_steps": 3130, "total_steps": 25209, "loss": 0.392, "lr": 4.3636929116927235e-05, "epoch": 0.3724860168987266, "percentage": 12.42, "elapsed_time": "5:15:59", "remaining_time": "1 day, 13:08:59", "throughput": 55266.81, "total_tokens": 1047826944} {"current_steps": 3140, "total_steps": 25209, "loss": 0.393, "lr": 4.362032007696314e-05, "epoch": 0.37367606807092707, "percentage": 12.46, "elapsed_time": "5:16:46", "remaining_time": "1 day, 13:06:24", "throughput": 55304.52, "total_tokens": 1051148672} {"current_steps": 3150, "total_steps": 25209, "loss": 0.3922, "lr": 4.360372998771707e-05, "epoch": 0.37486611924312746, "percentage": 12.5, "elapsed_time": "5:17:35", "remaining_time": "1 day, 13:04:02", "throughput": 55336.19, "total_tokens": 1054459008} {"current_steps": 3160, "total_steps": 25209, "loss": 0.3879, "lr": 4.358715881317884e-05, "epoch": 0.37605617041532785, "percentage": 12.54, "elapsed_time": "5:18:25", "remaining_time": "1 day, 13:01:46", "throughput": 55372.06, "total_tokens": 1057890944} {"current_steps": 3170, "total_steps": 25209, "loss": 0.3909, "lr": 4.357060651743399e-05, "epoch": 0.37724622158752824, "percentage": 12.57, "elapsed_time": "5:19:12", "remaining_time": "1 day, 12:59:17", "throughput": 55410.15, "total_tokens": 1061264256} {"current_steps": 3180, "total_steps": 25209, "loss": 0.3888, "lr": 4.3554073064663454e-05, "epoch": 0.3784362727597287, "percentage": 12.61, "elapsed_time": "5:19:58", "remaining_time": "1 day, 12:56:37", "throughput": 55451.9, "total_tokens": 1064611840} {"current_steps": 3190, "total_steps": 25209, "loss": 0.3913, "lr": 4.353755841914325e-05, "epoch": 0.3796263239319291, "percentage": 12.65, "elapsed_time": "5:20:47", "remaining_time": "1 day, 12:54:16", "throughput": 55488.04, "total_tokens": 1068006016} {"current_steps": 3200, "total_steps": 25209, "loss": 0.3935, "lr": 4.3521062545244116e-05, "epoch": 0.38081637510412947, "percentage": 12.69, "elapsed_time": "5:21:35", "remaining_time": "1 day, 12:51:53", "throughput": 55521.02, "total_tokens": 1071327488} {"current_steps": 3210, "total_steps": 25209, "loss": 0.3925, "lr": 4.350458540743126e-05, "epoch": 0.38200642627632986, "percentage": 12.73, "elapsed_time": "5:22:22", "remaining_time": "1 day, 12:49:16", "throughput": 55555.35, "total_tokens": 1074553728} {"current_steps": 3220, "total_steps": 25209, "loss": 0.3884, "lr": 4.3488126970263955e-05, "epoch": 0.3831964774485303, "percentage": 12.77, "elapsed_time": "5:23:10", "remaining_time": "1 day, 12:46:54", "throughput": 55590.39, "total_tokens": 1077915520} {"current_steps": 3230, "total_steps": 25209, "loss": 0.3904, "lr": 4.347168719839527e-05, "epoch": 0.3843865286207307, "percentage": 12.81, "elapsed_time": "5:23:57", "remaining_time": "1 day, 12:44:27", "throughput": 55624.42, "total_tokens": 1081215744} {"current_steps": 3240, "total_steps": 25209, "loss": 0.3937, "lr": 4.345526605657173e-05, "epoch": 0.3855765797929311, "percentage": 12.85, "elapsed_time": "5:24:46", "remaining_time": "1 day, 12:42:09", "throughput": 55657.35, "total_tokens": 1084566528} {"current_steps": 3250, "total_steps": 25209, "loss": 0.3927, "lr": 4.343886350963304e-05, "epoch": 0.3867666309651315, "percentage": 12.89, "elapsed_time": "5:25:36", "remaining_time": "1 day, 12:40:02", "throughput": 55688.86, "total_tokens": 1087982592} {"current_steps": 3260, "total_steps": 25209, "loss": 0.3914, "lr": 4.3422479522511697e-05, "epoch": 0.3879566821373319, "percentage": 12.93, "elapsed_time": "5:26:24", "remaining_time": "1 day, 12:37:40", "throughput": 55720.4, "total_tokens": 1091273088} {"current_steps": 3270, "total_steps": 25209, "loss": 0.3896, "lr": 4.340611406023272e-05, "epoch": 0.3891467333095323, "percentage": 12.97, "elapsed_time": "5:27:12", "remaining_time": "1 day, 12:35:14", "throughput": 55754.27, "total_tokens": 1094571776} {"current_steps": 3280, "total_steps": 25209, "loss": 0.3875, "lr": 4.338976708791336e-05, "epoch": 0.3903367844817327, "percentage": 13.01, "elapsed_time": "5:28:03", "remaining_time": "1 day, 12:33:17", "throughput": 55783.04, "total_tokens": 1098004352} {"current_steps": 3290, "total_steps": 25209, "loss": 0.3907, "lr": 4.337343857076272e-05, "epoch": 0.3915268356539331, "percentage": 13.05, "elapsed_time": "5:28:52", "remaining_time": "1 day, 12:31:02", "throughput": 55815.73, "total_tokens": 1101369472} {"current_steps": 3300, "total_steps": 25209, "loss": 0.3884, "lr": 4.33571284740815e-05, "epoch": 0.39271688682613354, "percentage": 13.09, "elapsed_time": "5:29:42", "remaining_time": "1 day, 12:28:59", "throughput": 55847.19, "total_tokens": 1104807168} {"current_steps": 3310, "total_steps": 25209, "loss": 0.3899, "lr": 4.3340836763261675e-05, "epoch": 0.39390693799833393, "percentage": 13.13, "elapsed_time": "5:30:32", "remaining_time": "1 day, 12:26:53", "throughput": 55875.98, "total_tokens": 1108170368} {"current_steps": 3320, "total_steps": 25209, "loss": 0.3916, "lr": 4.332456340378618e-05, "epoch": 0.3950969891705343, "percentage": 13.17, "elapsed_time": "5:31:20", "remaining_time": "1 day, 12:24:32", "throughput": 55906.26, "total_tokens": 1111436672} {"current_steps": 3330, "total_steps": 25209, "loss": 0.3901, "lr": 4.3308308361228586e-05, "epoch": 0.39628704034273476, "percentage": 13.21, "elapsed_time": "5:32:08", "remaining_time": "1 day, 12:22:12", "throughput": 55939.76, "total_tokens": 1114772992} {"current_steps": 3340, "total_steps": 25209, "loss": 0.389, "lr": 4.329207160125282e-05, "epoch": 0.39747709151493515, "percentage": 13.25, "elapsed_time": "5:32:57", "remaining_time": "1 day, 12:20:04", "throughput": 55972.71, "total_tokens": 1118188288} {"current_steps": 3350, "total_steps": 25209, "loss": 0.392, "lr": 4.327585308961287e-05, "epoch": 0.39866714268713555, "percentage": 13.29, "elapsed_time": "5:33:47", "remaining_time": "1 day, 12:17:57", "throughput": 56004.71, "total_tokens": 1121608704} {"current_steps": 3360, "total_steps": 25209, "loss": 0.3886, "lr": 4.325965279215243e-05, "epoch": 0.39985719385933594, "percentage": 13.33, "elapsed_time": "5:34:34", "remaining_time": "1 day, 12:15:40", "throughput": 56037.78, "total_tokens": 1124952064} {"current_steps": 3370, "total_steps": 25209, "loss": 0.3903, "lr": 4.3243470674804686e-05, "epoch": 0.4010472450315364, "percentage": 13.37, "elapsed_time": "5:35:22", "remaining_time": "1 day, 12:13:22", "throughput": 56071.63, "total_tokens": 1128305152} {"current_steps": 3380, "total_steps": 25209, "loss": 0.3911, "lr": 4.3227306703591904e-05, "epoch": 0.40223729620373677, "percentage": 13.41, "elapsed_time": "5:36:11", "remaining_time": "1 day, 12:11:10", "throughput": 56100.19, "total_tokens": 1131604608} {"current_steps": 3390, "total_steps": 25209, "loss": 0.389, "lr": 4.32111608446252e-05, "epoch": 0.40342734737593716, "percentage": 13.45, "elapsed_time": "5:36:58", "remaining_time": "1 day, 12:08:53", "throughput": 56132.72, "total_tokens": 1134932992} {"current_steps": 3400, "total_steps": 25209, "loss": 0.3861, "lr": 4.319503306410426e-05, "epoch": 0.40461739854813755, "percentage": 13.49, "elapsed_time": "5:37:49", "remaining_time": "1 day, 12:06:57", "throughput": 56161.92, "total_tokens": 1138382848} {"current_steps": 3410, "total_steps": 25209, "loss": 0.3855, "lr": 4.317892332831699e-05, "epoch": 0.405807449720338, "percentage": 13.53, "elapsed_time": "5:38:36", "remaining_time": "1 day, 12:04:37", "throughput": 56194.58, "total_tokens": 1141681024} {"current_steps": 3420, "total_steps": 25209, "loss": 0.3863, "lr": 4.316283160363922e-05, "epoch": 0.4069975008925384, "percentage": 13.57, "elapsed_time": "5:39:26", "remaining_time": "1 day, 12:02:33", "throughput": 56220.94, "total_tokens": 1145000320} {"current_steps": 3430, "total_steps": 25209, "loss": 0.3865, "lr": 4.314675785653447e-05, "epoch": 0.4081875520647388, "percentage": 13.61, "elapsed_time": "5:41:08", "remaining_time": "1 day, 12:06:07", "throughput": 56102.39, "total_tokens": 1148342656} {"current_steps": 3440, "total_steps": 25209, "loss": 0.3857, "lr": 4.3130702053553606e-05, "epoch": 0.40937760323693917, "percentage": 13.65, "elapsed_time": "5:43:38", "remaining_time": "1 day, 12:14:39", "throughput": 55854.39, "total_tokens": 1151647616} {"current_steps": 3450, "total_steps": 25209, "loss": 0.3897, "lr": 4.3114664161334546e-05, "epoch": 0.4105676544091396, "percentage": 13.69, "elapsed_time": "5:45:55", "remaining_time": "1 day, 12:21:41", "throughput": 55645.85, "total_tokens": 1154932608} {"current_steps": 3460, "total_steps": 25209, "loss": 0.3871, "lr": 4.3098644146601984e-05, "epoch": 0.41175770558134, "percentage": 13.73, "elapsed_time": "5:46:51", "remaining_time": "1 day, 12:20:14", "throughput": 55661.88, "total_tokens": 1158379904} {"current_steps": 3470, "total_steps": 25209, "loss": 0.3848, "lr": 4.30826419761671e-05, "epoch": 0.4129477567535404, "percentage": 13.76, "elapsed_time": "5:47:41", "remaining_time": "1 day, 12:18:13", "throughput": 55686.81, "total_tokens": 1161703680} {"current_steps": 3480, "total_steps": 25209, "loss": 0.3886, "lr": 4.30666576169273e-05, "epoch": 0.4141378079257408, "percentage": 13.8, "elapsed_time": "5:48:29", "remaining_time": "1 day, 12:15:58", "throughput": 55718.15, "total_tokens": 1165038848} {"current_steps": 3490, "total_steps": 25209, "loss": 0.3915, "lr": 4.305069103586585e-05, "epoch": 0.41532785909794123, "percentage": 13.84, "elapsed_time": "5:49:37", "remaining_time": "1 day, 12:15:49", "throughput": 55693.9, "total_tokens": 1168340864} {"current_steps": 3500, "total_steps": 25209, "loss": 0.389, "lr": 4.303474220005164e-05, "epoch": 0.4165179102701416, "percentage": 13.88, "elapsed_time": "5:51:14", "remaining_time": "1 day, 12:18:38", "throughput": 55596.62, "total_tokens": 1171691392} {"current_steps": 3510, "total_steps": 25209, "loss": 0.3895, "lr": 4.3018811076638944e-05, "epoch": 0.417707961442342, "percentage": 13.92, "elapsed_time": "5:53:33", "remaining_time": "1 day, 12:25:40", "throughput": 55395.38, "total_tokens": 1175107072} {"current_steps": 3520, "total_steps": 25209, "loss": 0.3895, "lr": 4.300289763286704e-05, "epoch": 0.4188980126145424, "percentage": 13.96, "elapsed_time": "5:57:21", "remaining_time": "1 day, 12:41:57", "throughput": 54958.73, "total_tokens": 1178421120} {"current_steps": 3530, "total_steps": 25209, "loss": 0.3867, "lr": 4.298700183606e-05, "epoch": 0.42008806378674285, "percentage": 14.0, "elapsed_time": "5:59:53", "remaining_time": "1 day, 12:50:13", "throughput": 54725.81, "total_tokens": 1181722752} {"current_steps": 3540, "total_steps": 25209, "loss": 0.385, "lr": 4.297112365362637e-05, "epoch": 0.42127811495894324, "percentage": 14.04, "elapsed_time": "6:03:12", "remaining_time": "1 day, 13:03:13", "throughput": 54380.65, "total_tokens": 1185068928} {"current_steps": 3550, "total_steps": 25209, "loss": 0.3881, "lr": 4.295526305305891e-05, "epoch": 0.42246816613114363, "percentage": 14.08, "elapsed_time": "6:08:15", "remaining_time": "1 day, 13:26:47", "throughput": 53781.29, "total_tokens": 1188321024} {"current_steps": 3560, "total_steps": 25209, "loss": 0.3891, "lr": 4.293942000193429e-05, "epoch": 0.423658217303344, "percentage": 14.12, "elapsed_time": "6:10:50", "remaining_time": "1 day, 13:35:07", "throughput": 53555.83, "total_tokens": 1191623936} {"current_steps": 3570, "total_steps": 25209, "loss": 0.3872, "lr": 4.2923594467912866e-05, "epoch": 0.42484826847554447, "percentage": 14.16, "elapsed_time": "6:13:15", "remaining_time": "1 day, 13:42:29", "throughput": 53357.67, "total_tokens": 1194994432} {"current_steps": 3580, "total_steps": 25209, "loss": 0.3857, "lr": 4.290778641873832e-05, "epoch": 0.42603831964774486, "percentage": 14.2, "elapsed_time": "6:14:49", "remaining_time": "1 day, 13:44:35", "throughput": 53282.37, "total_tokens": 1198317312} {"current_steps": 3590, "total_steps": 25209, "loss": 0.3871, "lr": 4.2891995822237455e-05, "epoch": 0.42722837081994525, "percentage": 14.24, "elapsed_time": "6:16:51", "remaining_time": "1 day, 13:49:29", "throughput": 53146.98, "total_tokens": 1201755776} {"current_steps": 3600, "total_steps": 25209, "loss": 0.3875, "lr": 4.28762226463199e-05, "epoch": 0.42841842199214564, "percentage": 14.28, "elapsed_time": "6:17:55", "remaining_time": "1 day, 13:48:30", "throughput": 53147.67, "total_tokens": 1205158784} {"current_steps": 3610, "total_steps": 25209, "loss": 0.3867, "lr": 4.286046685897781e-05, "epoch": 0.4296084731643461, "percentage": 14.32, "elapsed_time": "6:19:03", "remaining_time": "1 day, 13:47:59", "throughput": 53136.21, "total_tokens": 1208529920} {"current_steps": 3620, "total_steps": 25209, "loss": 0.3876, "lr": 4.284472842828562e-05, "epoch": 0.4307985243365465, "percentage": 14.36, "elapsed_time": "6:19:57", "remaining_time": "1 day, 13:46:01", "throughput": 53157.49, "total_tokens": 1211875712} {"current_steps": 3630, "total_steps": 25209, "loss": 0.3893, "lr": 4.282900732239977e-05, "epoch": 0.43198857550874686, "percentage": 14.4, "elapsed_time": "6:20:49", "remaining_time": "1 day, 13:43:52", "throughput": 53182.85, "total_tokens": 1215206144} {"current_steps": 3640, "total_steps": 25209, "loss": 0.3857, "lr": 4.281330350955845e-05, "epoch": 0.43317862668094725, "percentage": 14.44, "elapsed_time": "6:21:43", "remaining_time": "1 day, 13:41:53", "throughput": 53208.69, "total_tokens": 1218648064} {"current_steps": 3650, "total_steps": 25209, "loss": 0.3866, "lr": 4.279761695808125e-05, "epoch": 0.4343686778531477, "percentage": 14.48, "elapsed_time": "6:22:33", "remaining_time": "1 day, 13:39:36", "throughput": 53236.58, "total_tokens": 1221968256} {"current_steps": 3660, "total_steps": 25209, "loss": 0.3899, "lr": 4.278194763636904e-05, "epoch": 0.4355587290253481, "percentage": 14.52, "elapsed_time": "6:23:34", "remaining_time": "1 day, 13:38:24", "throughput": 53243.36, "total_tokens": 1225382656} {"current_steps": 3670, "total_steps": 25209, "loss": 0.3853, "lr": 4.276629551290354e-05, "epoch": 0.4367487801975485, "percentage": 14.56, "elapsed_time": "6:24:37", "remaining_time": "1 day, 13:37:23", "throughput": 53239.81, "total_tokens": 1228667008} {"current_steps": 3680, "total_steps": 25209, "loss": 0.3839, "lr": 4.2750660556247175e-05, "epoch": 0.4379388313697489, "percentage": 14.6, "elapsed_time": "6:25:35", "remaining_time": "1 day, 13:35:47", "throughput": 53252.12, "total_tokens": 1232004992} {"current_steps": 3690, "total_steps": 25209, "loss": 0.3878, "lr": 4.273504273504274e-05, "epoch": 0.4391288825419493, "percentage": 14.64, "elapsed_time": "6:26:24", "remaining_time": "1 day, 13:33:25", "throughput": 53283.4, "total_tokens": 1235352576} {"current_steps": 3700, "total_steps": 25209, "loss": 0.382, "lr": 4.271944201801317e-05, "epoch": 0.4403189337141497, "percentage": 14.68, "elapsed_time": "6:27:14", "remaining_time": "1 day, 13:31:07", "throughput": 53313.03, "total_tokens": 1238695424} {"current_steps": 3710, "total_steps": 25209, "loss": 0.3862, "lr": 4.270385837396127e-05, "epoch": 0.4415089848863501, "percentage": 14.72, "elapsed_time": "6:28:02", "remaining_time": "1 day, 13:28:42", "throughput": 53344.75, "total_tokens": 1242024960} {"current_steps": 3720, "total_steps": 25209, "loss": 0.3836, "lr": 4.268829177176945e-05, "epoch": 0.44269903605855054, "percentage": 14.76, "elapsed_time": "6:28:51", "remaining_time": "1 day, 13:26:16", "throughput": 53377.5, "total_tokens": 1245371264} {"current_steps": 3730, "total_steps": 25209, "loss": 0.3851, "lr": 4.2672742180399455e-05, "epoch": 0.44388908723075093, "percentage": 14.8, "elapsed_time": "6:29:38", "remaining_time": "1 day, 13:23:46", "throughput": 53411.02, "total_tokens": 1248690048} {"current_steps": 3740, "total_steps": 25209, "loss": 0.3876, "lr": 4.265720956889213e-05, "epoch": 0.4450791384029513, "percentage": 14.84, "elapsed_time": "6:30:28", "remaining_time": "1 day, 13:21:29", "throughput": 53443.36, "total_tokens": 1252109312} {"current_steps": 3750, "total_steps": 25209, "loss": 0.3837, "lr": 4.2641693906367113e-05, "epoch": 0.4462691895751517, "percentage": 14.88, "elapsed_time": "6:31:18", "remaining_time": "1 day, 13:19:14", "throughput": 53473.77, "total_tokens": 1255494528} {"current_steps": 3760, "total_steps": 25209, "loss": 0.3858, "lr": 4.2626195162022646e-05, "epoch": 0.44745924074735216, "percentage": 14.92, "elapsed_time": "6:32:07", "remaining_time": "1 day, 13:16:50", "throughput": 53507.78, "total_tokens": 1258881792} {"current_steps": 3770, "total_steps": 25209, "loss": 0.3869, "lr": 4.2610713305135255e-05, "epoch": 0.44864929191955255, "percentage": 14.95, "elapsed_time": "6:32:54", "remaining_time": "1 day, 13:14:21", "throughput": 53540.37, "total_tokens": 1262186240} {"current_steps": 3780, "total_steps": 25209, "loss": 0.3799, "lr": 4.2595248305059546e-05, "epoch": 0.44983934309175294, "percentage": 14.99, "elapsed_time": "6:33:43", "remaining_time": "1 day, 13:12:00", "throughput": 53570.44, "total_tokens": 1265497728} {"current_steps": 3790, "total_steps": 25209, "loss": 0.387, "lr": 4.2579800131227916e-05, "epoch": 0.45102939426395333, "percentage": 15.03, "elapsed_time": "6:34:30", "remaining_time": "1 day, 13:09:33", "throughput": 53602.39, "total_tokens": 1268804864} {"current_steps": 3800, "total_steps": 25209, "loss": 0.3852, "lr": 4.256436875315028e-05, "epoch": 0.4522194454361538, "percentage": 15.07, "elapsed_time": "6:35:16", "remaining_time": "1 day, 13:07:00", "throughput": 53635.31, "total_tokens": 1272067840} {"current_steps": 3810, "total_steps": 25209, "loss": 0.3856, "lr": 4.2548954140413895e-05, "epoch": 0.45340949660835417, "percentage": 15.11, "elapsed_time": "6:36:10", "remaining_time": "1 day, 13:05:05", "throughput": 53660.65, "total_tokens": 1275520768} {"current_steps": 3820, "total_steps": 25209, "loss": 0.3811, "lr": 4.253355626268302e-05, "epoch": 0.45459954778055456, "percentage": 15.15, "elapsed_time": "6:37:00", "remaining_time": "1 day, 13:02:56", "throughput": 53688.95, "total_tokens": 1278899328} {"current_steps": 3830, "total_steps": 25209, "loss": 0.389, "lr": 4.2518175089698716e-05, "epoch": 0.45578959895275495, "percentage": 15.19, "elapsed_time": "6:37:51", "remaining_time": "1 day, 13:00:48", "throughput": 53715.45, "total_tokens": 1282248576} {"current_steps": 3840, "total_steps": 25209, "loss": 0.3869, "lr": 4.25028105912786e-05, "epoch": 0.4569796501249554, "percentage": 15.23, "elapsed_time": "6:38:39", "remaining_time": "1 day, 12:58:28", "throughput": 53748.86, "total_tokens": 1285651712} {"current_steps": 3850, "total_steps": 25209, "loss": 0.386, "lr": 4.2487462737316565e-05, "epoch": 0.4581697012971558, "percentage": 15.27, "elapsed_time": "6:39:27", "remaining_time": "1 day, 12:56:05", "throughput": 53780.09, "total_tokens": 1288960768} {"current_steps": 3860, "total_steps": 25209, "loss": 0.383, "lr": 4.2472131497782555e-05, "epoch": 0.4593597524693562, "percentage": 15.31, "elapsed_time": "6:40:15", "remaining_time": "1 day, 12:53:47", "throughput": 53808.64, "total_tokens": 1292256768} {"current_steps": 3870, "total_steps": 25209, "loss": 0.386, "lr": 4.245681684272231e-05, "epoch": 0.46054980364155657, "percentage": 15.35, "elapsed_time": "6:41:03", "remaining_time": "1 day, 12:51:25", "throughput": 53839.11, "total_tokens": 1295558528} {"current_steps": 3880, "total_steps": 25209, "loss": 0.3832, "lr": 4.244151874225712e-05, "epoch": 0.461739854813757, "percentage": 15.39, "elapsed_time": "6:41:51", "remaining_time": "1 day, 12:49:05", "throughput": 53868.89, "total_tokens": 1298868608} {"current_steps": 3890, "total_steps": 25209, "loss": 0.3863, "lr": 4.2426237166583596e-05, "epoch": 0.4629299059859574, "percentage": 15.43, "elapsed_time": "6:42:40", "remaining_time": "1 day, 12:46:53", "throughput": 53898.19, "total_tokens": 1302230144} {"current_steps": 3900, "total_steps": 25209, "loss": 0.3882, "lr": 4.241097208597339e-05, "epoch": 0.4641199571581578, "percentage": 15.47, "elapsed_time": "6:43:30", "remaining_time": "1 day, 12:44:43", "throughput": 53927.31, "total_tokens": 1305619840} {"current_steps": 3910, "total_steps": 25209, "loss": 0.3836, "lr": 4.2395723470773005e-05, "epoch": 0.4653100083303582, "percentage": 15.51, "elapsed_time": "6:44:22", "remaining_time": "1 day, 12:42:43", "throughput": 53951.71, "total_tokens": 1308985216} {"current_steps": 3920, "total_steps": 25209, "loss": 0.3821, "lr": 4.238049129140347e-05, "epoch": 0.46650005950255863, "percentage": 15.55, "elapsed_time": "6:45:08", "remaining_time": "1 day, 12:40:16", "throughput": 53983.46, "total_tokens": 1312259584} {"current_steps": 3930, "total_steps": 25209, "loss": 0.3811, "lr": 4.236527551836022e-05, "epoch": 0.467690110674759, "percentage": 15.59, "elapsed_time": "6:45:58", "remaining_time": "1 day, 12:38:06", "throughput": 54012.72, "total_tokens": 1315643648} {"current_steps": 3940, "total_steps": 25209, "loss": 0.3835, "lr": 4.235007612221274e-05, "epoch": 0.4688801618469594, "percentage": 15.63, "elapsed_time": "6:46:47", "remaining_time": "1 day, 12:35:55", "throughput": 54040.02, "total_tokens": 1318966912} {"current_steps": 3950, "total_steps": 25209, "loss": 0.3863, "lr": 4.2334893073604386e-05, "epoch": 0.4700702130191598, "percentage": 15.67, "elapsed_time": "6:47:36", "remaining_time": "1 day, 12:33:46", "throughput": 54067.41, "total_tokens": 1322304640} {"current_steps": 3960, "total_steps": 25209, "loss": 0.3888, "lr": 4.231972634325214e-05, "epoch": 0.47126026419136025, "percentage": 15.71, "elapsed_time": "6:48:24", "remaining_time": "1 day, 12:31:29", "throughput": 54097.84, "total_tokens": 1325650688} {"current_steps": 3970, "total_steps": 25209, "loss": 0.3852, "lr": 4.230457590194635e-05, "epoch": 0.47245031536356064, "percentage": 15.75, "elapsed_time": "6:49:14", "remaining_time": "1 day, 12:29:22", "throughput": 54126.22, "total_tokens": 1329027712} {"current_steps": 3980, "total_steps": 25209, "loss": 0.3821, "lr": 4.228944172055053e-05, "epoch": 0.473640366535761, "percentage": 15.79, "elapsed_time": "6:50:06", "remaining_time": "1 day, 12:27:30", "throughput": 54150.17, "total_tokens": 1332463360} {"current_steps": 3990, "total_steps": 25209, "loss": 0.3824, "lr": 4.22743237700011e-05, "epoch": 0.4748304177079614, "percentage": 15.83, "elapsed_time": "6:50:56", "remaining_time": "1 day, 12:25:23", "throughput": 54177.3, "total_tokens": 1335816704} {"current_steps": 4000, "total_steps": 25209, "loss": 0.3819, "lr": 4.225922202130716e-05, "epoch": 0.47602046888016186, "percentage": 15.87, "elapsed_time": "6:51:47", "remaining_time": "1 day, 12:23:24", "throughput": 54205.79, "total_tokens": 1339279360} {"current_steps": 4010, "total_steps": 25209, "loss": 0.3816, "lr": 4.224413644555024e-05, "epoch": 0.47721052005236225, "percentage": 15.91, "elapsed_time": "6:52:34", "remaining_time": "1 day, 12:21:07", "throughput": 54234.19, "total_tokens": 1342564736} {"current_steps": 4020, "total_steps": 25209, "loss": 0.3789, "lr": 4.222906701388411e-05, "epoch": 0.47840057122456264, "percentage": 15.95, "elapsed_time": "6:53:23", "remaining_time": "1 day, 12:18:55", "throughput": 54264.34, "total_tokens": 1345929472} {"current_steps": 4030, "total_steps": 25209, "loss": 0.3841, "lr": 4.2214013697534466e-05, "epoch": 0.47959062239676303, "percentage": 15.99, "elapsed_time": "6:54:10", "remaining_time": "1 day, 12:16:37", "throughput": 54293.57, "total_tokens": 1349219584} {"current_steps": 4040, "total_steps": 25209, "loss": 0.3884, "lr": 4.219897646779882e-05, "epoch": 0.4807806735689635, "percentage": 16.03, "elapsed_time": "6:54:59", "remaining_time": "1 day, 12:14:30", "throughput": 54322.26, "total_tokens": 1352604544} {"current_steps": 4050, "total_steps": 25209, "loss": 0.3801, "lr": 4.2183955296046145e-05, "epoch": 0.48197072474116387, "percentage": 16.07, "elapsed_time": "6:55:47", "remaining_time": "1 day, 12:12:14", "throughput": 54354.38, "total_tokens": 1355980288} {"current_steps": 4060, "total_steps": 25209, "loss": 0.3824, "lr": 4.2168950153716746e-05, "epoch": 0.48316077591336426, "percentage": 16.11, "elapsed_time": "6:56:36", "remaining_time": "1 day, 12:10:09", "throughput": 54380.18, "total_tokens": 1359311360} {"current_steps": 4070, "total_steps": 25209, "loss": 0.3827, "lr": 4.215396101232197e-05, "epoch": 0.4843508270855647, "percentage": 16.15, "elapsed_time": "6:57:22", "remaining_time": "1 day, 12:07:47", "throughput": 54410.39, "total_tokens": 1362578560} {"current_steps": 4080, "total_steps": 25209, "loss": 0.3825, "lr": 4.213898784344398e-05, "epoch": 0.4855408782577651, "percentage": 16.18, "elapsed_time": "6:58:12", "remaining_time": "1 day, 12:05:48", "throughput": 54436.22, "total_tokens": 1365966976} {"current_steps": 4090, "total_steps": 25209, "loss": 0.3823, "lr": 4.21240306187356e-05, "epoch": 0.4867309294299655, "percentage": 16.22, "elapsed_time": "6:59:00", "remaining_time": "1 day, 12:03:36", "throughput": 54465.28, "total_tokens": 1369307776} {"current_steps": 4100, "total_steps": 25209, "loss": 0.3802, "lr": 4.2109089309919967e-05, "epoch": 0.4879209806021659, "percentage": 16.26, "elapsed_time": "6:59:49", "remaining_time": "1 day, 12:01:30", "throughput": 54494.02, "total_tokens": 1372692352} {"current_steps": 4110, "total_steps": 25209, "loss": 0.3823, "lr": 4.2094163888790445e-05, "epoch": 0.4891110317743663, "percentage": 16.3, "elapsed_time": "7:00:43", "remaining_time": "1 day, 11:59:50", "throughput": 54514.96, "total_tokens": 1376160768} {"current_steps": 4120, "total_steps": 25209, "loss": 0.3836, "lr": 4.2079254327210294e-05, "epoch": 0.4903010829465667, "percentage": 16.34, "elapsed_time": "7:01:31", "remaining_time": "1 day, 11:57:38", "throughput": 54543.65, "total_tokens": 1379485184} {"current_steps": 4130, "total_steps": 25209, "loss": 0.3795, "lr": 4.206436059711249e-05, "epoch": 0.4914911341187671, "percentage": 16.38, "elapsed_time": "7:02:18", "remaining_time": "1 day, 11:55:24", "throughput": 54570.53, "total_tokens": 1382734848} {"current_steps": 4140, "total_steps": 25209, "loss": 0.3775, "lr": 4.20494826704995e-05, "epoch": 0.4926811852909675, "percentage": 16.42, "elapsed_time": "7:03:07", "remaining_time": "1 day, 11:53:17", "throughput": 54601.16, "total_tokens": 1386161152} {"current_steps": 4150, "total_steps": 25209, "loss": 0.3831, "lr": 4.203462051944307e-05, "epoch": 0.49387123646316794, "percentage": 16.46, "elapsed_time": "7:03:57", "remaining_time": "1 day, 11:51:20", "throughput": 54626.35, "total_tokens": 1389544320} {"current_steps": 4160, "total_steps": 25209, "loss": 0.3831, "lr": 4.201977411608398e-05, "epoch": 0.49506128763536833, "percentage": 16.5, "elapsed_time": "7:04:44", "remaining_time": "1 day, 11:49:07", "throughput": 54656.04, "total_tokens": 1392877696} {"current_steps": 4170, "total_steps": 25209, "loss": 0.3812, "lr": 4.200494343263185e-05, "epoch": 0.4962513388075687, "percentage": 16.54, "elapsed_time": "7:05:34", "remaining_time": "1 day, 11:47:07", "throughput": 54681.56, "total_tokens": 1396244736} {"current_steps": 4180, "total_steps": 25209, "loss": 0.3778, "lr": 4.1990128441364914e-05, "epoch": 0.4974413899797691, "percentage": 16.58, "elapsed_time": "7:06:21", "remaining_time": "1 day, 11:44:58", "throughput": 54710.39, "total_tokens": 1399594368} {"current_steps": 4190, "total_steps": 25209, "loss": 0.3825, "lr": 4.197532911462977e-05, "epoch": 0.49863144115196956, "percentage": 16.62, "elapsed_time": "7:07:10", "remaining_time": "1 day, 11:42:53", "throughput": 54738.42, "total_tokens": 1402956672} {"current_steps": 4200, "total_steps": 25209, "loss": 0.3842, "lr": 4.196054542484125e-05, "epoch": 0.49982149232416995, "percentage": 16.66, "elapsed_time": "7:07:53", "remaining_time": "1 day, 11:40:22", "throughput": 54773.09, "total_tokens": 1406218880} {"current_steps": 4210, "total_steps": 25209, "loss": 0.381, "lr": 4.1945777344482084e-05, "epoch": 0.5010115434963703, "percentage": 16.7, "elapsed_time": "7:08:47", "remaining_time": "1 day, 11:38:45", "throughput": 54791.01, "total_tokens": 1409635072} {"current_steps": 4220, "total_steps": 25209, "loss": 0.379, "lr": 4.19310248461028e-05, "epoch": 0.5022015946685707, "percentage": 16.74, "elapsed_time": "7:09:48", "remaining_time": "1 day, 11:37:45", "throughput": 54792.78, "total_tokens": 1413037952} {"current_steps": 4230, "total_steps": 25209, "loss": 0.3816, "lr": 4.1916287902321405e-05, "epoch": 0.5033916458407711, "percentage": 16.78, "elapsed_time": "7:10:38", "remaining_time": "1 day, 11:35:46", "throughput": 54816.31, "total_tokens": 1416359680} {"current_steps": 4240, "total_steps": 25209, "loss": 0.3826, "lr": 4.190156648582328e-05, "epoch": 0.5045816970129715, "percentage": 16.82, "elapsed_time": "7:11:29", "remaining_time": "1 day, 11:33:54", "throughput": 54839.8, "total_tokens": 1419750656} {"current_steps": 4250, "total_steps": 25209, "loss": 0.3824, "lr": 4.188686056936087e-05, "epoch": 0.505771748185172, "percentage": 16.86, "elapsed_time": "7:12:17", "remaining_time": "1 day, 11:31:52", "throughput": 54867.89, "total_tokens": 1423148032} {"current_steps": 4260, "total_steps": 25209, "loss": 0.379, "lr": 4.187217012575352e-05, "epoch": 0.5069617993573724, "percentage": 16.9, "elapsed_time": "7:13:07", "remaining_time": "1 day, 11:29:58", "throughput": 54891.9, "total_tokens": 1426528640} {"current_steps": 4270, "total_steps": 25209, "loss": 0.3817, "lr": 4.185749512788727e-05, "epoch": 0.5081518505295728, "percentage": 16.94, "elapsed_time": "7:14:01", "remaining_time": "1 day, 11:28:18", "throughput": 54912.39, "total_tokens": 1429979392} {"current_steps": 4280, "total_steps": 25209, "loss": 0.3749, "lr": 4.184283554871462e-05, "epoch": 0.5093419017017732, "percentage": 16.98, "elapsed_time": "7:14:50", "remaining_time": "1 day, 11:26:20", "throughput": 54936.85, "total_tokens": 1433323904} {"current_steps": 4290, "total_steps": 25209, "loss": 0.3766, "lr": 4.1828191361254344e-05, "epoch": 0.5105319528739736, "percentage": 17.02, "elapsed_time": "7:15:36", "remaining_time": "1 day, 11:24:06", "throughput": 54967.38, "total_tokens": 1436641280} {"current_steps": 4300, "total_steps": 25209, "loss": 0.3834, "lr": 4.181356253859127e-05, "epoch": 0.511722004046174, "percentage": 17.06, "elapsed_time": "7:16:22", "remaining_time": "1 day, 11:21:53", "throughput": 54995.37, "total_tokens": 1439915520} {"current_steps": 4310, "total_steps": 25209, "loss": 0.3813, "lr": 4.179894905387606e-05, "epoch": 0.5129120552183744, "percentage": 17.1, "elapsed_time": "7:17:12", "remaining_time": "1 day, 11:20:00", "throughput": 55018.58, "total_tokens": 1443279744} {"current_steps": 4320, "total_steps": 25209, "loss": 0.3791, "lr": 4.178435088032502e-05, "epoch": 0.5141021063905747, "percentage": 17.14, "elapsed_time": "7:18:00", "remaining_time": "1 day, 11:17:56", "throughput": 55047.52, "total_tokens": 1446673664} {"current_steps": 4330, "total_steps": 25209, "loss": 0.3773, "lr": 4.176976799121989e-05, "epoch": 0.5152921575627752, "percentage": 17.18, "elapsed_time": "7:18:48", "remaining_time": "1 day, 11:15:55", "throughput": 55074.1, "total_tokens": 1450031616} {"current_steps": 4340, "total_steps": 25209, "loss": 0.3787, "lr": 4.1755200359907657e-05, "epoch": 0.5164822087349756, "percentage": 17.22, "elapsed_time": "7:19:38", "remaining_time": "1 day, 11:14:02", "throughput": 55096.12, "total_tokens": 1453360640} {"current_steps": 4350, "total_steps": 25209, "loss": 0.3805, "lr": 4.174064795980028e-05, "epoch": 0.517672259907176, "percentage": 17.26, "elapsed_time": "7:20:25", "remaining_time": "1 day, 11:11:55", "throughput": 55125.86, "total_tokens": 1456736256} {"current_steps": 4360, "total_steps": 25209, "loss": 0.382, "lr": 4.17261107643746e-05, "epoch": 0.5188623110793764, "percentage": 17.3, "elapsed_time": "7:21:12", "remaining_time": "1 day, 11:09:49", "throughput": 55151.59, "total_tokens": 1460012160} {"current_steps": 4370, "total_steps": 25209, "loss": 0.3758, "lr": 4.171158874717204e-05, "epoch": 0.5200523622515768, "percentage": 17.34, "elapsed_time": "7:21:59", "remaining_time": "1 day, 11:07:41", "throughput": 55179.32, "total_tokens": 1463319808} {"current_steps": 4380, "total_steps": 25209, "loss": 0.3753, "lr": 4.169708188179844e-05, "epoch": 0.5212424134237772, "percentage": 17.37, "elapsed_time": "7:22:47", "remaining_time": "1 day, 11:05:40", "throughput": 55201.8, "total_tokens": 1466568704} {"current_steps": 4390, "total_steps": 25209, "loss": 0.3816, "lr": 4.1682590141923846e-05, "epoch": 0.5224324645959776, "percentage": 17.41, "elapsed_time": "7:23:35", "remaining_time": "1 day, 11:03:41", "throughput": 55227.88, "total_tokens": 1469930112} {"current_steps": 4400, "total_steps": 25209, "loss": 0.3783, "lr": 4.1668113501282335e-05, "epoch": 0.523622515768178, "percentage": 17.45, "elapsed_time": "7:24:22", "remaining_time": "1 day, 11:01:37", "throughput": 55254.42, "total_tokens": 1473242752} {"current_steps": 4410, "total_steps": 25209, "loss": 0.3808, "lr": 4.165365193367178e-05, "epoch": 0.5248125669403785, "percentage": 17.49, "elapsed_time": "7:25:10", "remaining_time": "1 day, 10:59:36", "throughput": 55279.13, "total_tokens": 1476542976} {"current_steps": 4420, "total_steps": 25209, "loss": 0.3805, "lr": 4.163920541295369e-05, "epoch": 0.5260026181125789, "percentage": 17.53, "elapsed_time": "7:26:01", "remaining_time": "1 day, 10:57:48", "throughput": 55299.86, "total_tokens": 1479890816} {"current_steps": 4430, "total_steps": 25209, "loss": 0.381, "lr": 4.1624773913052946e-05, "epoch": 0.5271926692847793, "percentage": 17.57, "elapsed_time": "7:26:50", "remaining_time": "1 day, 10:55:53", "throughput": 55324.45, "total_tokens": 1483254400} {"current_steps": 4440, "total_steps": 25209, "loss": 0.381, "lr": 4.161035740795769e-05, "epoch": 0.5283827204569796, "percentage": 17.61, "elapsed_time": "7:27:40", "remaining_time": "1 day, 10:54:07", "throughput": 55343.81, "total_tokens": 1486589696} {"current_steps": 4450, "total_steps": 25209, "loss": 0.3773, "lr": 4.1595955871719055e-05, "epoch": 0.52957277162918, "percentage": 17.65, "elapsed_time": "7:28:29", "remaining_time": "1 day, 10:52:11", "throughput": 55368.08, "total_tokens": 1489933184} {"current_steps": 4460, "total_steps": 25209, "loss": 0.3812, "lr": 4.158156927845101e-05, "epoch": 0.5307628228013804, "percentage": 17.69, "elapsed_time": "7:29:31", "remaining_time": "1 day, 10:51:18", "throughput": 55364.5, "total_tokens": 1493264640} {"current_steps": 4470, "total_steps": 25209, "loss": 0.3776, "lr": 4.156719760233016e-05, "epoch": 0.5319528739735808, "percentage": 17.73, "elapsed_time": "7:30:20", "remaining_time": "1 day, 10:49:26", "throughput": 55388.55, "total_tokens": 1496649344} {"current_steps": 4480, "total_steps": 25209, "loss": 0.3783, "lr": 4.155284081759552e-05, "epoch": 0.5331429251457813, "percentage": 17.77, "elapsed_time": "7:31:14", "remaining_time": "1 day, 10:47:52", "throughput": 55402.17, "total_tokens": 1499970176} {"current_steps": 4490, "total_steps": 25209, "loss": 0.38, "lr": 4.1538498898548356e-05, "epoch": 0.5343329763179817, "percentage": 17.81, "elapsed_time": "7:32:16", "remaining_time": "1 day, 10:47:00", "throughput": 55402.07, "total_tokens": 1503417728} {"current_steps": 4500, "total_steps": 25209, "loss": 0.381, "lr": 4.1524171819552e-05, "epoch": 0.5355230274901821, "percentage": 17.85, "elapsed_time": "7:33:04", "remaining_time": "1 day, 10:45:03", "throughput": 55426.74, "total_tokens": 1506753792} {"current_steps": 4510, "total_steps": 25209, "loss": 0.3787, "lr": 4.15098595550316e-05, "epoch": 0.5367130786623825, "percentage": 17.89, "elapsed_time": "7:34:11", "remaining_time": "1 day, 10:44:33", "throughput": 55417.01, "total_tokens": 1510201216} {"current_steps": 4520, "total_steps": 25209, "loss": 0.3819, "lr": 4.1495562079474e-05, "epoch": 0.5379031298345829, "percentage": 17.93, "elapsed_time": "7:35:01", "remaining_time": "1 day, 10:42:45", "throughput": 55439.46, "total_tokens": 1513594368} {"current_steps": 4530, "total_steps": 25209, "loss": 0.3804, "lr": 4.148127936742749e-05, "epoch": 0.5390931810067833, "percentage": 17.97, "elapsed_time": "7:35:59", "remaining_time": "1 day, 10:41:34", "throughput": 55449.13, "total_tokens": 1517075328} {"current_steps": 4540, "total_steps": 25209, "loss": 0.3793, "lr": 4.146701139350166e-05, "epoch": 0.5402832321789837, "percentage": 18.01, "elapsed_time": "7:36:59", "remaining_time": "1 day, 10:40:28", "throughput": 55451.51, "total_tokens": 1520425856} {"current_steps": 4550, "total_steps": 25209, "loss": 0.379, "lr": 4.1452758132367196e-05, "epoch": 0.541473283351184, "percentage": 18.05, "elapsed_time": "7:38:20", "remaining_time": "1 day, 10:41:05", "throughput": 55407.26, "total_tokens": 1523746176} {"current_steps": 4560, "total_steps": 25209, "loss": 0.3825, "lr": 4.1438519558755656e-05, "epoch": 0.5426633345233846, "percentage": 18.09, "elapsed_time": "7:39:16", "remaining_time": "1 day, 10:39:43", "throughput": 55416.53, "total_tokens": 1527083008} {"current_steps": 4570, "total_steps": 25209, "loss": 0.3756, "lr": 4.1424295647459336e-05, "epoch": 0.543853385695585, "percentage": 18.13, "elapsed_time": "7:40:11", "remaining_time": "1 day, 10:38:17", "throughput": 55430.37, "total_tokens": 1530498688} {"current_steps": 4580, "total_steps": 25209, "loss": 0.3756, "lr": 4.141008637333106e-05, "epoch": 0.5450434368677853, "percentage": 18.17, "elapsed_time": "7:41:11", "remaining_time": "1 day, 10:37:17", "throughput": 55432.13, "total_tokens": 1533901184} {"current_steps": 4590, "total_steps": 25209, "loss": 0.3792, "lr": 4.1395891711283974e-05, "epoch": 0.5462334880399857, "percentage": 18.21, "elapsed_time": "7:44:34", "remaining_time": "1 day, 10:46:57", "throughput": 55146.5, "total_tokens": 1537186304} {"current_steps": 4600, "total_steps": 25209, "loss": 0.3798, "lr": 4.1381711636291395e-05, "epoch": 0.5474235392121861, "percentage": 18.25, "elapsed_time": "7:47:36", "remaining_time": "1 day, 10:54:58", "throughput": 54908.69, "total_tokens": 1540531712} {"current_steps": 4610, "total_steps": 25209, "loss": 0.3787, "lr": 4.1367546123386604e-05, "epoch": 0.5486135903843865, "percentage": 18.29, "elapsed_time": "7:51:56", "remaining_time": "1 day, 11:08:47", "throughput": 54521.43, "total_tokens": 1543860608} {"current_steps": 4620, "total_steps": 25209, "loss": 0.3777, "lr": 4.1353395147662673e-05, "epoch": 0.5498036415565869, "percentage": 18.33, "elapsed_time": "7:54:18", "remaining_time": "1 day, 11:13:43", "throughput": 54369.05, "total_tokens": 1547241344} {"current_steps": 4630, "total_steps": 25209, "loss": 0.3777, "lr": 4.133925868427225e-05, "epoch": 0.5509936927287873, "percentage": 18.37, "elapsed_time": "7:56:18", "remaining_time": "1 day, 11:17:02", "throughput": 54257.76, "total_tokens": 1550593792} {"current_steps": 4640, "total_steps": 25209, "loss": 0.3787, "lr": 4.132513670842744e-05, "epoch": 0.5521837439009878, "percentage": 18.41, "elapsed_time": "7:58:35", "remaining_time": "1 day, 11:21:37", "throughput": 54113.17, "total_tokens": 1553913216} {"current_steps": 4650, "total_steps": 25209, "loss": 0.3749, "lr": 4.1311029195399534e-05, "epoch": 0.5533737950731882, "percentage": 18.45, "elapsed_time": "8:01:46", "remaining_time": "1 day, 11:30:03", "throughput": 53871.58, "total_tokens": 1557234432} {"current_steps": 4660, "total_steps": 25209, "loss": 0.3753, "lr": 4.129693612051892e-05, "epoch": 0.5545638462453886, "percentage": 18.49, "elapsed_time": "8:04:21", "remaining_time": "1 day, 11:35:51", "throughput": 53697.45, "total_tokens": 1560531712} {"current_steps": 4670, "total_steps": 25209, "loss": 0.3763, "lr": 4.1282857459174826e-05, "epoch": 0.555753897417589, "percentage": 18.53, "elapsed_time": "8:08:33", "remaining_time": "1 day, 11:48:41", "throughput": 53348.74, "total_tokens": 1563820416} {"current_steps": 4680, "total_steps": 25209, "loss": 0.3751, "lr": 4.1268793186815184e-05, "epoch": 0.5569439485897894, "percentage": 18.56, "elapsed_time": "8:11:20", "remaining_time": "1 day, 11:55:17", "throughput": 53157.79, "total_tokens": 1567120128} {"current_steps": 4690, "total_steps": 25209, "loss": 0.378, "lr": 4.1254743278946456e-05, "epoch": 0.5581339997619897, "percentage": 18.6, "elapsed_time": "8:12:44", "remaining_time": "1 day, 11:55:46", "throughput": 53117.96, "total_tokens": 1570412160} {"current_steps": 4700, "total_steps": 25209, "loss": 0.3815, "lr": 4.1240707711133394e-05, "epoch": 0.5593240509341901, "percentage": 18.64, "elapsed_time": "8:13:41", "remaining_time": "1 day, 11:54:14", "throughput": 53132.96, "total_tokens": 1573853440} {"current_steps": 4710, "total_steps": 25209, "loss": 0.3768, "lr": 4.122668645899893e-05, "epoch": 0.5605141021063905, "percentage": 18.68, "elapsed_time": "8:14:35", "remaining_time": "1 day, 11:52:32", "throughput": 53147.53, "total_tokens": 1577153792} {"current_steps": 4720, "total_steps": 25209, "loss": 0.3769, "lr": 4.1212679498223975e-05, "epoch": 0.561704153278591, "percentage": 18.72, "elapsed_time": "8:15:29", "remaining_time": "1 day, 11:50:50", "throughput": 53162.51, "total_tokens": 1580468352} {"current_steps": 4730, "total_steps": 25209, "loss": 0.3781, "lr": 4.1198686804547215e-05, "epoch": 0.5628942044507914, "percentage": 18.76, "elapsed_time": "8:16:24", "remaining_time": "1 day, 11:49:12", "throughput": 53178.95, "total_tokens": 1583884416} {"current_steps": 4740, "total_steps": 25209, "loss": 0.3801, "lr": 4.118470835376499e-05, "epoch": 0.5640842556229918, "percentage": 18.8, "elapsed_time": "8:17:17", "remaining_time": "1 day, 11:47:29", "throughput": 53194.73, "total_tokens": 1587211136} {"current_steps": 4750, "total_steps": 25209, "loss": 0.3763, "lr": 4.117074412173107e-05, "epoch": 0.5652743067951922, "percentage": 18.84, "elapsed_time": "8:18:10", "remaining_time": "1 day, 11:45:42", "throughput": 53213.07, "total_tokens": 1590558080} {"current_steps": 4760, "total_steps": 25209, "loss": 0.3762, "lr": 4.115679408435648e-05, "epoch": 0.5664643579673926, "percentage": 18.88, "elapsed_time": "8:19:04", "remaining_time": "1 day, 11:44:00", "throughput": 53227.08, "total_tokens": 1593847552} {"current_steps": 4770, "total_steps": 25209, "loss": 0.3782, "lr": 4.114285821760937e-05, "epoch": 0.567654409139593, "percentage": 18.92, "elapsed_time": "8:19:58", "remaining_time": "1 day, 11:42:19", "throughput": 53243.48, "total_tokens": 1597207168} {"current_steps": 4780, "total_steps": 25209, "loss": 0.3744, "lr": 4.11289364975148e-05, "epoch": 0.5688444603117934, "percentage": 18.96, "elapsed_time": "8:20:52", "remaining_time": "1 day, 11:40:40", "throughput": 53259.77, "total_tokens": 1600597120} {"current_steps": 4790, "total_steps": 25209, "loss": 0.3756, "lr": 4.111502890015456e-05, "epoch": 0.5700345114839939, "percentage": 19.0, "elapsed_time": "8:21:47", "remaining_time": "1 day, 11:39:04", "throughput": 53277.14, "total_tokens": 1604049152} {"current_steps": 4800, "total_steps": 25209, "loss": 0.374, "lr": 4.1101135401667056e-05, "epoch": 0.5712245626561943, "percentage": 19.04, "elapsed_time": "8:22:41", "remaining_time": "1 day, 11:37:24", "throughput": 53289.25, "total_tokens": 1607306496} {"current_steps": 4810, "total_steps": 25209, "loss": 0.3788, "lr": 4.108725597824708e-05, "epoch": 0.5724146138283946, "percentage": 19.08, "elapsed_time": "8:23:36", "remaining_time": "1 day, 11:35:48", "throughput": 53304.1, "total_tokens": 1610687744} {"current_steps": 4820, "total_steps": 25209, "loss": 0.3805, "lr": 4.107339060614564e-05, "epoch": 0.573604665000595, "percentage": 19.12, "elapsed_time": "8:24:45", "remaining_time": "1 day, 11:35:11", "throughput": 53293.43, "total_tokens": 1614034432} {"current_steps": 4830, "total_steps": 25209, "loss": 0.3751, "lr": 4.1059539261669825e-05, "epoch": 0.5747947161727954, "percentage": 19.16, "elapsed_time": "8:25:41", "remaining_time": "1 day, 11:33:38", "throughput": 53305.93, "total_tokens": 1617384832} {"current_steps": 4840, "total_steps": 25209, "loss": 0.3759, "lr": 4.104570192118262e-05, "epoch": 0.5759847673449958, "percentage": 19.2, "elapsed_time": "8:26:37", "remaining_time": "1 day, 11:32:07", "throughput": 53317.24, "total_tokens": 1620712064} {"current_steps": 4850, "total_steps": 25209, "loss": 0.3762, "lr": 4.1031878561102714e-05, "epoch": 0.5771748185171962, "percentage": 19.24, "elapsed_time": "8:27:34", "remaining_time": "1 day, 11:30:37", "throughput": 53329.55, "total_tokens": 1624098944} {"current_steps": 4860, "total_steps": 25209, "loss": 0.3737, "lr": 4.1018069157904385e-05, "epoch": 0.5783648696893966, "percentage": 19.28, "elapsed_time": "8:28:48", "remaining_time": "1 day, 11:30:23", "throughput": 53310.31, "total_tokens": 1627482624} {"current_steps": 4870, "total_steps": 25209, "loss": 0.3754, "lr": 4.100427368811727e-05, "epoch": 0.5795549208615971, "percentage": 19.32, "elapsed_time": "8:30:04", "remaining_time": "1 day, 11:30:17", "throughput": 53290.57, "total_tokens": 1630943104} {"current_steps": 4880, "total_steps": 25209, "loss": 0.377, "lr": 4.099049212832622e-05, "epoch": 0.5807449720337975, "percentage": 19.36, "elapsed_time": "8:31:27", "remaining_time": "1 day, 11:30:36", "throughput": 53253.66, "total_tokens": 1634211712} {"current_steps": 4890, "total_steps": 25209, "loss": 0.376, "lr": 4.0976724455171155e-05, "epoch": 0.5819350232059979, "percentage": 19.4, "elapsed_time": "8:33:32", "remaining_time": "1 day, 11:33:52", "throughput": 53148.45, "total_tokens": 1637631104} {"current_steps": 4900, "total_steps": 25209, "loss": 0.3771, "lr": 4.096297064534688e-05, "epoch": 0.5831250743781983, "percentage": 19.44, "elapsed_time": "8:36:29", "remaining_time": "1 day, 11:40:42", "throughput": 52953.7, "total_tokens": 1641014656} {"current_steps": 4910, "total_steps": 25209, "loss": 0.3797, "lr": 4.0949230675602904e-05, "epoch": 0.5843151255503987, "percentage": 19.48, "elapsed_time": "8:38:38", "remaining_time": "1 day, 11:44:09", "throughput": 52839.9, "total_tokens": 1644278400} {"current_steps": 4920, "total_steps": 25209, "loss": 0.3724, "lr": 4.09355045227433e-05, "epoch": 0.585505176722599, "percentage": 19.52, "elapsed_time": "8:40:33", "remaining_time": "1 day, 11:46:39", "throughput": 52752.71, "total_tokens": 1647638912} {"current_steps": 4930, "total_steps": 25209, "loss": 0.3765, "lr": 4.092179216362654e-05, "epoch": 0.5866952278947994, "percentage": 19.56, "elapsed_time": "8:42:02", "remaining_time": "1 day, 11:47:22", "throughput": 52704.61, "total_tokens": 1650850432} {"current_steps": 4940, "total_steps": 25209, "loss": 0.3777, "lr": 4.090809357516532e-05, "epoch": 0.5878852790669998, "percentage": 19.6, "elapsed_time": "8:43:34", "remaining_time": "1 day, 11:48:13", "throughput": 52655.25, "total_tokens": 1654119680} {"current_steps": 4950, "total_steps": 25209, "loss": 0.3721, "lr": 4.089440873432638e-05, "epoch": 0.5890753302392003, "percentage": 19.64, "elapsed_time": "8:45:07", "remaining_time": "1 day, 11:49:12", "throughput": 52606.24, "total_tokens": 1657506944} {"current_steps": 4960, "total_steps": 25209, "loss": 0.3731, "lr": 4.088073761813037e-05, "epoch": 0.5902653814114007, "percentage": 19.68, "elapsed_time": "8:46:55", "remaining_time": "1 day, 11:51:07", "throughput": 52529.11, "total_tokens": 1660717312} {"current_steps": 4970, "total_steps": 25209, "loss": 0.3766, "lr": 4.086708020365172e-05, "epoch": 0.5914554325836011, "percentage": 19.72, "elapsed_time": "8:48:29", "remaining_time": "1 day, 11:52:09", "throughput": 52478.73, "total_tokens": 1664085760} {"current_steps": 4980, "total_steps": 25209, "loss": 0.3742, "lr": 4.0853436468018354e-05, "epoch": 0.5926454837558015, "percentage": 19.75, "elapsed_time": "8:50:00", "remaining_time": "1 day, 11:52:53", "throughput": 52436.23, "total_tokens": 1667478656} {"current_steps": 4990, "total_steps": 25209, "loss": 0.3741, "lr": 4.0839806388411686e-05, "epoch": 0.5938355349280019, "percentage": 19.79, "elapsed_time": "8:51:13", "remaining_time": "1 day, 11:52:26", "throughput": 52420.81, "total_tokens": 1670816512} {"current_steps": 5000, "total_steps": 25209, "loss": 0.3725, "lr": 4.0826189942066346e-05, "epoch": 0.5950255861002023, "percentage": 19.83, "elapsed_time": "8:52:18", "remaining_time": "1 day, 11:51:29", "throughput": 52419.18, "total_tokens": 1674195968} {"current_steps": 5000, "total_steps": 25209, "eval_loss": 0.33721470832824707, "epoch": 0.5950255861002023, "percentage": 19.83, "elapsed_time": "8:52:20", "remaining_time": "1 day, 11:51:35", "throughput": 52416.7, "total_tokens": 1674195968} {"current_steps": 5010, "total_steps": 25209, "loss": 0.3727, "lr": 4.081258710627008e-05, "epoch": 0.5962156372724027, "percentage": 19.87, "elapsed_time": "8:53:37", "remaining_time": "1 day, 11:51:25", "throughput": 52396.9, "total_tokens": 1677606528} {"current_steps": 5020, "total_steps": 25209, "loss": 0.3743, "lr": 4.0798997858363557e-05, "epoch": 0.5974056884446031, "percentage": 19.91, "elapsed_time": "8:54:31", "remaining_time": "1 day, 11:49:44", "throughput": 52413.47, "total_tokens": 1680999936} {"current_steps": 5030, "total_steps": 25209, "loss": 0.3759, "lr": 4.078542217574024e-05, "epoch": 0.5985957396168036, "percentage": 19.95, "elapsed_time": "8:55:26", "remaining_time": "1 day, 11:48:01", "throughput": 52430.58, "total_tokens": 1684394880} {"current_steps": 5040, "total_steps": 25209, "loss": 0.3745, "lr": 4.0771860035846196e-05, "epoch": 0.599785790789004, "percentage": 19.99, "elapsed_time": "8:56:16", "remaining_time": "1 day, 11:46:04", "throughput": 52449.3, "total_tokens": 1687647104} {"current_steps": 5050, "total_steps": 25209, "loss": 0.3723, "lr": 4.0758311416179965e-05, "epoch": 0.6009758419612043, "percentage": 20.03, "elapsed_time": "8:57:08", "remaining_time": "1 day, 11:44:14", "throughput": 52468.61, "total_tokens": 1691007744} {"current_steps": 5060, "total_steps": 25209, "loss": 0.3733, "lr": 4.0744776294292386e-05, "epoch": 0.6021658931334047, "percentage": 20.07, "elapsed_time": "8:58:17", "remaining_time": "1 day, 11:43:30", "throughput": 52461.92, "total_tokens": 1694402560} {"current_steps": 5070, "total_steps": 25209, "loss": 0.3711, "lr": 4.073125464778646e-05, "epoch": 0.6033559443056051, "percentage": 20.11, "elapsed_time": "9:00:10", "remaining_time": "1 day, 11:45:41", "throughput": 52384.0, "total_tokens": 1697804416} {"current_steps": 5080, "total_steps": 25209, "loss": 0.3752, "lr": 4.071774645431717e-05, "epoch": 0.6045459954778055, "percentage": 20.15, "elapsed_time": "9:02:02", "remaining_time": "1 day, 11:47:45", "throughput": 52304.45, "total_tokens": 1701053824} {"current_steps": 5090, "total_steps": 25209, "loss": 0.3765, "lr": 4.070425169159135e-05, "epoch": 0.6057360466500059, "percentage": 20.19, "elapsed_time": "9:03:30", "remaining_time": "1 day, 11:48:17", "throughput": 52270.07, "total_tokens": 1704553216} {"current_steps": 5100, "total_steps": 25209, "loss": 0.3763, "lr": 4.069077033736751e-05, "epoch": 0.6069260978222063, "percentage": 20.23, "elapsed_time": "9:04:20", "remaining_time": "1 day, 11:46:20", "throughput": 52289.11, "total_tokens": 1707809792} {"current_steps": 5110, "total_steps": 25209, "loss": 0.3759, "lr": 4.06773023694557e-05, "epoch": 0.6081161489944068, "percentage": 20.27, "elapsed_time": "9:05:15", "remaining_time": "1 day, 11:44:37", "throughput": 52306.6, "total_tokens": 1711220736} {"current_steps": 5120, "total_steps": 25209, "loss": 0.3742, "lr": 4.066384776571732e-05, "epoch": 0.6093062001666072, "percentage": 20.31, "elapsed_time": "9:06:08", "remaining_time": "1 day, 11:42:51", "throughput": 52322.97, "total_tokens": 1714541952} {"current_steps": 5130, "total_steps": 25209, "loss": 0.3725, "lr": 4.065040650406504e-05, "epoch": 0.6104962513388076, "percentage": 20.35, "elapsed_time": "9:07:02", "remaining_time": "1 day, 11:41:09", "throughput": 52337.83, "total_tokens": 1717878272} {"current_steps": 5140, "total_steps": 25209, "loss": 0.3763, "lr": 4.0636978562462576e-05, "epoch": 0.611686302511008, "percentage": 20.39, "elapsed_time": "9:07:55", "remaining_time": "1 day, 11:39:20", "throughput": 52356.72, "total_tokens": 1721237120} {"current_steps": 5150, "total_steps": 25209, "loss": 0.3759, "lr": 4.062356391892456e-05, "epoch": 0.6128763536832084, "percentage": 20.43, "elapsed_time": "9:08:42", "remaining_time": "1 day, 11:37:10", "throughput": 52380.03, "total_tokens": 1724468992} {"current_steps": 5160, "total_steps": 25209, "loss": 0.3774, "lr": 4.0610162551516395e-05, "epoch": 0.6140664048554088, "percentage": 20.47, "elapsed_time": "9:09:39", "remaining_time": "1 day, 11:35:40", "throughput": 52391.27, "total_tokens": 1727836160} {"current_steps": 5170, "total_steps": 25209, "loss": 0.374, "lr": 4.059677443835412e-05, "epoch": 0.6152564560276091, "percentage": 20.51, "elapsed_time": "9:10:33", "remaining_time": "1 day, 11:33:57", "throughput": 52409.36, "total_tokens": 1731246720} {"current_steps": 5180, "total_steps": 25209, "loss": 0.3713, "lr": 4.058339955760423e-05, "epoch": 0.6164465071998096, "percentage": 20.55, "elapsed_time": "9:11:25", "remaining_time": "1 day, 11:32:08", "throughput": 52426.21, "total_tokens": 1734552960} {"current_steps": 5190, "total_steps": 25209, "loss": 0.3763, "lr": 4.0570037887483535e-05, "epoch": 0.61763655837201, "percentage": 20.59, "elapsed_time": "9:12:16", "remaining_time": "1 day, 11:30:14", "throughput": 52445.98, "total_tokens": 1737875584} {"current_steps": 5200, "total_steps": 25209, "loss": 0.3681, "lr": 4.0556689406259025e-05, "epoch": 0.6188266095442104, "percentage": 20.63, "elapsed_time": "9:13:08", "remaining_time": "1 day, 11:28:24", "throughput": 52465.61, "total_tokens": 1741239680} {"current_steps": 5210, "total_steps": 25209, "loss": 0.3708, "lr": 4.054335409224771e-05, "epoch": 0.6200166607164108, "percentage": 20.67, "elapsed_time": "9:14:01", "remaining_time": "1 day, 11:26:40", "throughput": 52482.05, "total_tokens": 1744587136} {"current_steps": 5220, "total_steps": 25209, "loss": 0.3698, "lr": 4.053003192381646e-05, "epoch": 0.6212067118886112, "percentage": 20.71, "elapsed_time": "9:14:57", "remaining_time": "1 day, 11:25:05", "throughput": 52499.14, "total_tokens": 1748081152} {"current_steps": 5230, "total_steps": 25209, "loss": 0.3773, "lr": 4.051672287938189e-05, "epoch": 0.6223967630608116, "percentage": 20.75, "elapsed_time": "9:15:50", "remaining_time": "1 day, 11:23:20", "throughput": 52514.69, "total_tokens": 1751379584} {"current_steps": 5240, "total_steps": 25209, "loss": 0.3693, "lr": 4.050342693741019e-05, "epoch": 0.623586814233012, "percentage": 20.79, "elapsed_time": "9:17:44", "remaining_time": "1 day, 11:25:30", "throughput": 52436.57, "total_tokens": 1754775808} {"current_steps": 5250, "total_steps": 25209, "loss": 0.3759, "lr": 4.049014407641699e-05, "epoch": 0.6247768654052124, "percentage": 20.83, "elapsed_time": "9:19:15", "remaining_time": "1 day, 11:26:08", "throughput": 52393.44, "total_tokens": 1758093056} {"current_steps": 5260, "total_steps": 25209, "loss": 0.371, "lr": 4.047687427496717e-05, "epoch": 0.6259669165774129, "percentage": 20.87, "elapsed_time": "9:20:28", "remaining_time": "1 day, 11:25:38", "throughput": 52380.8, "total_tokens": 1761485952} {"current_steps": 5270, "total_steps": 25209, "loss": 0.3722, "lr": 4.046361751167479e-05, "epoch": 0.6271569677496133, "percentage": 20.91, "elapsed_time": "9:21:32", "remaining_time": "1 day, 11:24:35", "throughput": 52382.43, "total_tokens": 1764894080} {"current_steps": 5280, "total_steps": 25209, "loss": 0.3677, "lr": 4.045037376520292e-05, "epoch": 0.6283470189218137, "percentage": 20.94, "elapsed_time": "9:22:34", "remaining_time": "1 day, 11:23:22", "throughput": 52388.64, "total_tokens": 1768336896} {"current_steps": 5290, "total_steps": 25209, "loss": 0.3728, "lr": 4.043714301426344e-05, "epoch": 0.629537070094014, "percentage": 20.98, "elapsed_time": "9:23:30", "remaining_time": "1 day, 11:21:49", "throughput": 52401.22, "total_tokens": 1771697280} {"current_steps": 5300, "total_steps": 25209, "loss": 0.3763, "lr": 4.042392523761696e-05, "epoch": 0.6307271212662144, "percentage": 21.02, "elapsed_time": "9:24:53", "remaining_time": "1 day, 11:21:59", "throughput": 52370.27, "total_tokens": 1775032832} {"current_steps": 5310, "total_steps": 25209, "loss": 0.3728, "lr": 4.041072041407267e-05, "epoch": 0.6319171724384148, "percentage": 21.06, "elapsed_time": "9:25:54", "remaining_time": "1 day, 11:20:42", "throughput": 52375.41, "total_tokens": 1778374656} {"current_steps": 5320, "total_steps": 25209, "loss": 0.3698, "lr": 4.039752852248815e-05, "epoch": 0.6331072236106152, "percentage": 21.1, "elapsed_time": "9:28:22", "remaining_time": "1 day, 11:24:53", "throughput": 52247.15, "total_tokens": 1781767040} {"current_steps": 5330, "total_steps": 25209, "loss": 0.3733, "lr": 4.0384349541769286e-05, "epoch": 0.6342972747828156, "percentage": 21.14, "elapsed_time": "9:30:41", "remaining_time": "1 day, 11:28:27", "throughput": 52133.9, "total_tokens": 1785121408} {"current_steps": 5340, "total_steps": 25209, "loss": 0.3721, "lr": 4.037118345087011e-05, "epoch": 0.6354873259550161, "percentage": 21.18, "elapsed_time": "9:31:57", "remaining_time": "1 day, 11:28:09", "throughput": 52116.74, "total_tokens": 1788533248} {"current_steps": 5350, "total_steps": 25209, "loss": 0.3733, "lr": 4.0358030228792636e-05, "epoch": 0.6366773771272165, "percentage": 21.22, "elapsed_time": "9:32:58", "remaining_time": "1 day, 11:26:53", "throughput": 52119.2, "total_tokens": 1791804672} {"current_steps": 5360, "total_steps": 25209, "loss": 0.3715, "lr": 4.034488985458673e-05, "epoch": 0.6378674282994169, "percentage": 21.26, "elapsed_time": "9:34:04", "remaining_time": "1 day, 11:25:53", "throughput": 52118.91, "total_tokens": 1795208064} {"current_steps": 5370, "total_steps": 25209, "loss": 0.3725, "lr": 4.033176230735001e-05, "epoch": 0.6390574794716173, "percentage": 21.3, "elapsed_time": "9:35:09", "remaining_time": "1 day, 11:24:54", "throughput": 52118.21, "total_tokens": 1798597120} {"current_steps": 5380, "total_steps": 25209, "loss": 0.3685, "lr": 4.0318647566227626e-05, "epoch": 0.6402475306438177, "percentage": 21.34, "elapsed_time": "9:36:07", "remaining_time": "1 day, 11:23:23", "throughput": 52129.08, "total_tokens": 1801952000} {"current_steps": 5390, "total_steps": 25209, "loss": 0.3738, "lr": 4.0305545610412205e-05, "epoch": 0.6414375818160181, "percentage": 21.38, "elapsed_time": "9:37:04", "remaining_time": "1 day, 11:21:54", "throughput": 52139.3, "total_tokens": 1805296640} {"current_steps": 5400, "total_steps": 25209, "loss": 0.3749, "lr": 4.029245641914365e-05, "epoch": 0.6426276329882185, "percentage": 21.42, "elapsed_time": "9:38:07", "remaining_time": "1 day, 11:20:46", "throughput": 52139.96, "total_tokens": 1808623616} {"current_steps": 5410, "total_steps": 25209, "loss": 0.3742, "lr": 4.027937997170904e-05, "epoch": 0.6438176841604188, "percentage": 21.46, "elapsed_time": "9:38:59", "remaining_time": "1 day, 11:18:57", "throughput": 52156.85, "total_tokens": 1811913728} {"current_steps": 5420, "total_steps": 25209, "loss": 0.3731, "lr": 4.026631624744247e-05, "epoch": 0.6450077353326193, "percentage": 21.5, "elapsed_time": "9:39:58", "remaining_time": "1 day, 11:17:34", "throughput": 52163.11, "total_tokens": 1815224192} {"current_steps": 5430, "total_steps": 25209, "loss": 0.3718, "lr": 4.025326522572493e-05, "epoch": 0.6461977865048197, "percentage": 21.54, "elapsed_time": "9:40:52", "remaining_time": "1 day, 11:15:52", "throughput": 52179.13, "total_tokens": 1818581248} {"current_steps": 5440, "total_steps": 25209, "loss": 0.372, "lr": 4.024022688598415e-05, "epoch": 0.6473878376770201, "percentage": 21.58, "elapsed_time": "9:41:45", "remaining_time": "1 day, 11:14:07", "throughput": 52196.01, "total_tokens": 1821934208} {"current_steps": 5450, "total_steps": 25209, "loss": 0.3681, "lr": 4.0227201207694494e-05, "epoch": 0.6485778888492205, "percentage": 21.62, "elapsed_time": "9:42:41", "remaining_time": "1 day, 11:12:34", "throughput": 52208.93, "total_tokens": 1825316224} {"current_steps": 5460, "total_steps": 25209, "loss": 0.3662, "lr": 4.021418817037677e-05, "epoch": 0.6497679400214209, "percentage": 21.66, "elapsed_time": "9:43:38", "remaining_time": "1 day, 11:11:01", "throughput": 52219.63, "total_tokens": 1828637312} {"current_steps": 5470, "total_steps": 25209, "loss": 0.3704, "lr": 4.0201187753598174e-05, "epoch": 0.6509579911936213, "percentage": 21.7, "elapsed_time": "9:44:32", "remaining_time": "1 day, 11:09:23", "throughput": 52230.82, "total_tokens": 1831879040} {"current_steps": 5480, "total_steps": 25209, "loss": 0.373, "lr": 4.018819993697208e-05, "epoch": 0.6521480423658217, "percentage": 21.74, "elapsed_time": "9:45:30", "remaining_time": "1 day, 11:07:56", "throughput": 52241.08, "total_tokens": 1835256448} {"current_steps": 5490, "total_steps": 25209, "loss": 0.3682, "lr": 4.017522470015793e-05, "epoch": 0.6533380935380221, "percentage": 21.78, "elapsed_time": "9:46:24", "remaining_time": "1 day, 11:06:14", "throughput": 52256.61, "total_tokens": 1838599296} {"current_steps": 5500, "total_steps": 25209, "loss": 0.3684, "lr": 4.0162262022861144e-05, "epoch": 0.6545281447102226, "percentage": 21.82, "elapsed_time": "9:47:19", "remaining_time": "1 day, 11:04:39", "throughput": 52270.61, "total_tokens": 1841989632} {"current_steps": 5510, "total_steps": 25209, "loss": 0.3726, "lr": 4.0149311884832906e-05, "epoch": 0.655718195882423, "percentage": 21.86, "elapsed_time": "9:48:13", "remaining_time": "1 day, 11:02:59", "throughput": 52283.71, "total_tokens": 1845277696} {"current_steps": 5520, "total_steps": 25209, "loss": 0.3726, "lr": 4.0136374265870116e-05, "epoch": 0.6569082470546234, "percentage": 21.9, "elapsed_time": "9:49:08", "remaining_time": "1 day, 11:01:24", "throughput": 52299.18, "total_tokens": 1848718336} {"current_steps": 5530, "total_steps": 25209, "loss": 0.3736, "lr": 4.0123449145815174e-05, "epoch": 0.6580982982268238, "percentage": 21.94, "elapsed_time": "9:50:04", "remaining_time": "1 day, 10:59:48", "throughput": 52312.56, "total_tokens": 1852080512} {"current_steps": 5540, "total_steps": 25209, "loss": 0.3692, "lr": 4.011053650455592e-05, "epoch": 0.6592883493990241, "percentage": 21.98, "elapsed_time": "9:50:57", "remaining_time": "1 day, 10:58:07", "throughput": 52328.59, "total_tokens": 1855446528} {"current_steps": 5550, "total_steps": 25209, "loss": 0.372, "lr": 4.0097636322025466e-05, "epoch": 0.6604784005712245, "percentage": 22.02, "elapsed_time": "9:52:00", "remaining_time": "1 day, 10:56:59", "throughput": 52331.55, "total_tokens": 1858845312} {"current_steps": 5560, "total_steps": 25209, "loss": 0.3709, "lr": 4.008474857820206e-05, "epoch": 0.6616684517434249, "percentage": 22.06, "elapsed_time": "9:53:09", "remaining_time": "1 day, 10:56:14", "throughput": 52324.86, "total_tokens": 1862231296} {"current_steps": 5570, "total_steps": 25209, "loss": 0.3746, "lr": 4.007187325310899e-05, "epoch": 0.6628585029156254, "percentage": 22.1, "elapsed_time": "9:54:27", "remaining_time": "1 day, 10:55:57", "throughput": 52304.87, "total_tokens": 1865565952} {"current_steps": 5580, "total_steps": 25209, "loss": 0.3705, "lr": 4.00590103268144e-05, "epoch": 0.6640485540878258, "percentage": 22.13, "elapsed_time": "9:56:22", "remaining_time": "1 day, 10:57:53", "throughput": 52230.69, "total_tokens": 1868941696} {"current_steps": 5590, "total_steps": 25209, "loss": 0.3697, "lr": 4.004615977943124e-05, "epoch": 0.6652386052600262, "percentage": 22.17, "elapsed_time": "9:57:54", "remaining_time": "1 day, 10:58:28", "throughput": 52188.94, "total_tokens": 1872275712} {"current_steps": 5600, "total_steps": 25209, "loss": 0.3661, "lr": 4.0033321591117025e-05, "epoch": 0.6664286564322266, "percentage": 22.21, "elapsed_time": "9:58:45", "remaining_time": "1 day, 10:56:36", "throughput": 52207.33, "total_tokens": 1875574016} {"current_steps": 5610, "total_steps": 25209, "loss": 0.3741, "lr": 4.002049574207381e-05, "epoch": 0.667618707604427, "percentage": 22.25, "elapsed_time": "9:59:40", "remaining_time": "1 day, 10:54:59", "throughput": 52221.9, "total_tokens": 1878947712} {"current_steps": 5620, "total_steps": 25209, "loss": 0.3704, "lr": 4.000768221254803e-05, "epoch": 0.6688087587766274, "percentage": 22.29, "elapsed_time": "10:00:33", "remaining_time": "1 day, 10:53:16", "throughput": 52239.49, "total_tokens": 1882347776} {"current_steps": 5630, "total_steps": 25209, "loss": 0.3676, "lr": 3.999488098283034e-05, "epoch": 0.6699988099488278, "percentage": 22.33, "elapsed_time": "10:01:27", "remaining_time": "1 day, 10:51:39", "throughput": 52253.26, "total_tokens": 1885703168} {"current_steps": 5640, "total_steps": 25209, "loss": 0.3724, "lr": 3.9982092033255506e-05, "epoch": 0.6711888611210282, "percentage": 22.37, "elapsed_time": "10:02:21", "remaining_time": "1 day, 10:49:57", "throughput": 52269.1, "total_tokens": 1889058048} {"current_steps": 5650, "total_steps": 25209, "loss": 0.3691, "lr": 3.996931534420232e-05, "epoch": 0.6723789122932287, "percentage": 22.41, "elapsed_time": "10:03:13", "remaining_time": "1 day, 10:48:15", "throughput": 52285.18, "total_tokens": 1892408960} {"current_steps": 5660, "total_steps": 25209, "loss": 0.3676, "lr": 3.995655089609339e-05, "epoch": 0.673568963465429, "percentage": 22.45, "elapsed_time": "10:04:08", "remaining_time": "1 day, 10:46:37", "throughput": 52298.68, "total_tokens": 1895734784} {"current_steps": 5670, "total_steps": 25209, "loss": 0.3655, "lr": 3.994379866939511e-05, "epoch": 0.6747590146376294, "percentage": 22.49, "elapsed_time": "10:05:02", "remaining_time": "1 day, 10:45:01", "throughput": 52312.97, "total_tokens": 1899115136} {"current_steps": 5680, "total_steps": 25209, "loss": 0.3683, "lr": 3.993105864461745e-05, "epoch": 0.6759490658098298, "percentage": 22.53, "elapsed_time": "10:05:57", "remaining_time": "1 day, 10:43:24", "throughput": 52324.68, "total_tokens": 1902389760} {"current_steps": 5690, "total_steps": 25209, "loss": 0.3657, "lr": 3.9918330802313866e-05, "epoch": 0.6771391169820302, "percentage": 22.57, "elapsed_time": "10:06:52", "remaining_time": "1 day, 10:41:49", "throughput": 52340.02, "total_tokens": 1905836928} {"current_steps": 5700, "total_steps": 25209, "loss": 0.368, "lr": 3.9905615123081206e-05, "epoch": 0.6783291681542306, "percentage": 22.61, "elapsed_time": "10:07:45", "remaining_time": "1 day, 10:40:07", "throughput": 52356.11, "total_tokens": 1909188096} {"current_steps": 5710, "total_steps": 25209, "loss": 0.3667, "lr": 3.989291158755953e-05, "epoch": 0.679519219326431, "percentage": 22.65, "elapsed_time": "10:08:35", "remaining_time": "1 day, 10:38:17", "throughput": 52373.61, "total_tokens": 1912468224} {"current_steps": 5720, "total_steps": 25209, "loss": 0.3702, "lr": 3.988022017643201e-05, "epoch": 0.6807092704986314, "percentage": 22.69, "elapsed_time": "10:09:26", "remaining_time": "1 day, 10:36:29", "throughput": 52389.94, "total_tokens": 1915732992} {"current_steps": 5730, "total_steps": 25209, "loss": 0.369, "lr": 3.9867540870424826e-05, "epoch": 0.6818993216708319, "percentage": 22.73, "elapsed_time": "10:10:19", "remaining_time": "1 day, 10:34:48", "throughput": 52405.6, "total_tokens": 1919088768} {"current_steps": 5740, "total_steps": 25209, "loss": 0.3712, "lr": 3.985487365030702e-05, "epoch": 0.6830893728430323, "percentage": 22.77, "elapsed_time": "10:11:14", "remaining_time": "1 day, 10:33:11", "throughput": 52421.25, "total_tokens": 1922500224} {"current_steps": 5750, "total_steps": 25209, "loss": 0.3712, "lr": 3.984221849689036e-05, "epoch": 0.6842794240152327, "percentage": 22.81, "elapsed_time": "10:12:02", "remaining_time": "1 day, 10:31:14", "throughput": 52440.45, "total_tokens": 1925727872} {"current_steps": 5760, "total_steps": 25209, "loss": 0.3693, "lr": 3.982957539102927e-05, "epoch": 0.6854694751874331, "percentage": 22.85, "elapsed_time": "10:12:53", "remaining_time": "1 day, 10:29:27", "throughput": 52458.0, "total_tokens": 1929053056} {"current_steps": 5770, "total_steps": 25209, "loss": 0.3723, "lr": 3.981694431362065e-05, "epoch": 0.6866595263596335, "percentage": 22.89, "elapsed_time": "10:13:41", "remaining_time": "1 day, 10:27:30", "throughput": 52477.49, "total_tokens": 1932299392} {"current_steps": 5780, "total_steps": 25209, "loss": 0.3675, "lr": 3.9804325245603786e-05, "epoch": 0.6878495775318338, "percentage": 22.93, "elapsed_time": "10:14:34", "remaining_time": "1 day, 10:25:50", "throughput": 52491.86, "total_tokens": 1935612544} {"current_steps": 5790, "total_steps": 25209, "loss": 0.3701, "lr": 3.9791718167960226e-05, "epoch": 0.6890396287040342, "percentage": 22.97, "elapsed_time": "10:15:22", "remaining_time": "1 day, 10:23:54", "throughput": 52510.88, "total_tokens": 1938845568} {"current_steps": 5800, "total_steps": 25209, "loss": 0.3683, "lr": 3.9779123061713665e-05, "epoch": 0.6902296798762346, "percentage": 23.01, "elapsed_time": "10:16:14", "remaining_time": "1 day, 10:22:09", "throughput": 52527.45, "total_tokens": 1942157184} {"current_steps": 5810, "total_steps": 25209, "loss": 0.3729, "lr": 3.976653990792979e-05, "epoch": 0.6914197310484351, "percentage": 23.05, "elapsed_time": "10:17:03", "remaining_time": "1 day, 10:20:17", "throughput": 52545.04, "total_tokens": 1945401216} {"current_steps": 5820, "total_steps": 25209, "loss": 0.3683, "lr": 3.9753968687716206e-05, "epoch": 0.6926097822206355, "percentage": 23.09, "elapsed_time": "10:18:00", "remaining_time": "1 day, 10:18:51", "throughput": 52553.56, "total_tokens": 1948713472} {"current_steps": 5830, "total_steps": 25209, "loss": 0.3724, "lr": 3.974140938222232e-05, "epoch": 0.6937998333928359, "percentage": 23.13, "elapsed_time": "10:19:33", "remaining_time": "1 day, 10:19:26", "throughput": 52510.93, "total_tokens": 1952040320} {"current_steps": 5840, "total_steps": 25209, "loss": 0.3715, "lr": 3.972886197263915e-05, "epoch": 0.6949898845650363, "percentage": 23.17, "elapsed_time": "10:21:52", "remaining_time": "1 day, 10:22:30", "throughput": 52405.31, "total_tokens": 1955360768} {"current_steps": 5850, "total_steps": 25209, "loss": 0.3645, "lr": 3.97163264401993e-05, "epoch": 0.6961799357372367, "percentage": 23.21, "elapsed_time": "10:24:03", "remaining_time": "1 day, 10:25:07", "throughput": 52313.28, "total_tokens": 1958770688} {"current_steps": 5860, "total_steps": 25209, "loss": 0.3662, "lr": 3.970380276617677e-05, "epoch": 0.6973699869094371, "percentage": 23.25, "elapsed_time": "10:26:47", "remaining_time": "1 day, 10:29:34", "throughput": 52174.16, "total_tokens": 1962131328} {"current_steps": 5870, "total_steps": 25209, "loss": 0.3665, "lr": 3.96912909318869e-05, "epoch": 0.6985600380816375, "percentage": 23.29, "elapsed_time": "10:28:05", "remaining_time": "1 day, 10:29:17", "throughput": 52152.39, "total_tokens": 1965407104} {"current_steps": 5880, "total_steps": 25209, "loss": 0.3717, "lr": 3.96787909186862e-05, "epoch": 0.699750089253838, "percentage": 23.33, "elapsed_time": "10:29:56", "remaining_time": "1 day, 10:30:44", "throughput": 52088.72, "total_tokens": 1968745600} {"current_steps": 5890, "total_steps": 25209, "loss": 0.3675, "lr": 3.9666302707972244e-05, "epoch": 0.7009401404260384, "percentage": 23.36, "elapsed_time": "10:31:18", "remaining_time": "1 day, 10:30:38", "throughput": 52062.88, "total_tokens": 1972039936} {"current_steps": 5900, "total_steps": 25209, "loss": 0.3653, "lr": 3.965382628118358e-05, "epoch": 0.7021301915982388, "percentage": 23.4, "elapsed_time": "10:32:41", "remaining_time": "1 day, 10:30:36", "throughput": 52037.58, "total_tokens": 1975410560} {"current_steps": 5910, "total_steps": 25209, "loss": 0.3726, "lr": 3.964136161979959e-05, "epoch": 0.7033202427704391, "percentage": 23.44, "elapsed_time": "10:33:57", "remaining_time": "1 day, 10:30:10", "throughput": 52021.26, "total_tokens": 1978751872} {"current_steps": 5920, "total_steps": 25209, "loss": 0.3715, "lr": 3.9628908705340406e-05, "epoch": 0.7045102939426395, "percentage": 23.48, "elapsed_time": "10:35:31", "remaining_time": "1 day, 10:30:43", "throughput": 51980.36, "total_tokens": 1982101120} {"current_steps": 5930, "total_steps": 25209, "loss": 0.368, "lr": 3.961646751936673e-05, "epoch": 0.7057003451148399, "percentage": 23.52, "elapsed_time": "10:36:49", "remaining_time": "1 day, 10:30:22", "throughput": 51962.06, "total_tokens": 1985447296} {"current_steps": 5940, "total_steps": 25209, "loss": 0.3753, "lr": 3.960403804347979e-05, "epoch": 0.7068903962870403, "percentage": 23.56, "elapsed_time": "10:38:00", "remaining_time": "1 day, 10:29:39", "throughput": 51951.88, "total_tokens": 1988742528} {"current_steps": 5950, "total_steps": 25209, "loss": 0.3661, "lr": 3.959162025932119e-05, "epoch": 0.7080804474592407, "percentage": 23.6, "elapsed_time": "10:39:21", "remaining_time": "1 day, 10:29:29", "throughput": 51930.2, "total_tokens": 1992131072} {"current_steps": 5960, "total_steps": 25209, "loss": 0.3677, "lr": 3.95792141485728e-05, "epoch": 0.7092704986314412, "percentage": 23.64, "elapsed_time": "10:40:29", "remaining_time": "1 day, 10:28:35", "throughput": 51926.75, "total_tokens": 1995511936} {"current_steps": 5970, "total_steps": 25209, "loss": 0.3691, "lr": 3.956681969295664e-05, "epoch": 0.7104605498036416, "percentage": 23.68, "elapsed_time": "10:41:20", "remaining_time": "1 day, 10:26:47", "throughput": 51944.55, "total_tokens": 1998845184} {"current_steps": 5980, "total_steps": 25209, "loss": 0.3658, "lr": 3.955443687423479e-05, "epoch": 0.711650600975842, "percentage": 23.72, "elapsed_time": "10:42:11", "remaining_time": "1 day, 10:25:01", "throughput": 51962.1, "total_tokens": 2002195712} {"current_steps": 5990, "total_steps": 25209, "loss": 0.3671, "lr": 3.954206567420924e-05, "epoch": 0.7128406521480424, "percentage": 23.76, "elapsed_time": "10:43:03", "remaining_time": "1 day, 10:23:14", "throughput": 51980.66, "total_tokens": 2005570560} {"current_steps": 6000, "total_steps": 25209, "loss": 0.3712, "lr": 3.952970607472179e-05, "epoch": 0.7140307033202428, "percentage": 23.8, "elapsed_time": "10:43:55", "remaining_time": "1 day, 10:21:29", "throughput": 51997.53, "total_tokens": 2008925056} {"current_steps": 6010, "total_steps": 25209, "loss": 0.3687, "lr": 3.951735805765399e-05, "epoch": 0.7152207544924432, "percentage": 23.84, "elapsed_time": "10:44:47", "remaining_time": "1 day, 10:19:47", "throughput": 52016.46, "total_tokens": 2012391040} {"current_steps": 6020, "total_steps": 25209, "loss": 0.368, "lr": 3.950502160492692e-05, "epoch": 0.7164108056646435, "percentage": 23.88, "elapsed_time": "10:45:38", "remaining_time": "1 day, 10:17:58", "throughput": 52033.96, "total_tokens": 2015691776} {"current_steps": 6030, "total_steps": 25209, "loss": 0.3682, "lr": 3.9492696698501205e-05, "epoch": 0.7176008568368439, "percentage": 23.92, "elapsed_time": "10:46:29", "remaining_time": "1 day, 10:16:15", "throughput": 52051.66, "total_tokens": 2019078784} {"current_steps": 6040, "total_steps": 25209, "loss": 0.3672, "lr": 3.9480383320376784e-05, "epoch": 0.7187909080090444, "percentage": 23.96, "elapsed_time": "10:47:18", "remaining_time": "1 day, 10:14:20", "throughput": 52071.19, "total_tokens": 2022359552} {"current_steps": 6050, "total_steps": 25209, "loss": 0.3718, "lr": 3.94680814525929e-05, "epoch": 0.7199809591812448, "percentage": 24.0, "elapsed_time": "10:48:20", "remaining_time": "1 day, 10:13:08", "throughput": 52075.56, "total_tokens": 2025757312} {"current_steps": 6060, "total_steps": 25209, "loss": 0.3684, "lr": 3.945579107722792e-05, "epoch": 0.7211710103534452, "percentage": 24.04, "elapsed_time": "10:49:14", "remaining_time": "1 day, 10:11:32", "throughput": 52088.59, "total_tokens": 2029086208} {"current_steps": 6070, "total_steps": 25209, "loss": 0.3693, "lr": 3.9443512176399276e-05, "epoch": 0.7223610615256456, "percentage": 24.08, "elapsed_time": "10:50:44", "remaining_time": "1 day, 10:11:48", "throughput": 52054.52, "total_tokens": 2032438400} {"current_steps": 6080, "total_steps": 25209, "loss": 0.3706, "lr": 3.9431244732263307e-05, "epoch": 0.723551112697846, "percentage": 24.12, "elapsed_time": "10:52:40", "remaining_time": "1 day, 10:13:26", "throughput": 51987.77, "total_tokens": 2035857408} {"current_steps": 6090, "total_steps": 25209, "loss": 0.3661, "lr": 3.941898872701519e-05, "epoch": 0.7247411638700464, "percentage": 24.16, "elapsed_time": "10:54:25", "remaining_time": "1 day, 10:14:29", "throughput": 51937.33, "total_tokens": 2039322624} {"current_steps": 6100, "total_steps": 25209, "loss": 0.3661, "lr": 3.940674414288882e-05, "epoch": 0.7259312150422468, "percentage": 24.2, "elapsed_time": "10:55:20", "remaining_time": "1 day, 10:12:56", "throughput": 51948.08, "total_tokens": 2042634368} {"current_steps": 6110, "total_steps": 25209, "loss": 0.3687, "lr": 3.939451096215668e-05, "epoch": 0.7271212662144472, "percentage": 24.24, "elapsed_time": "10:56:16", "remaining_time": "1 day, 10:11:26", "throughput": 51958.5, "total_tokens": 2045957632} {"current_steps": 6120, "total_steps": 25209, "loss": 0.3691, "lr": 3.938228916712978e-05, "epoch": 0.7283113173866477, "percentage": 24.28, "elapsed_time": "10:57:06", "remaining_time": "1 day, 10:09:37", "throughput": 51977.52, "total_tokens": 2049316352} {"current_steps": 6130, "total_steps": 25209, "loss": 0.3731, "lr": 3.937007874015748e-05, "epoch": 0.7295013685588481, "percentage": 24.32, "elapsed_time": "10:58:01", "remaining_time": "1 day, 10:08:02", "throughput": 51991.9, "total_tokens": 2052719744} {"current_steps": 6140, "total_steps": 25209, "loss": 0.3707, "lr": 3.935787966362748e-05, "epoch": 0.7306914197310485, "percentage": 24.36, "elapsed_time": "10:59:08", "remaining_time": "1 day, 10:07:06", "throughput": 51987.13, "total_tokens": 2056026752} {"current_steps": 6150, "total_steps": 25209, "loss": 0.3657, "lr": 3.9345691919965595e-05, "epoch": 0.7318814709032488, "percentage": 24.4, "elapsed_time": "11:00:02", "remaining_time": "1 day, 10:05:29", "throughput": 52001.41, "total_tokens": 2059387392} {"current_steps": 6160, "total_steps": 25209, "loss": 0.3678, "lr": 3.9333515491635764e-05, "epoch": 0.7330715220754492, "percentage": 24.44, "elapsed_time": "11:00:50", "remaining_time": "1 day, 10:03:35", "throughput": 52021.06, "total_tokens": 2062681088} {"current_steps": 6170, "total_steps": 25209, "loss": 0.3713, "lr": 3.932135036113987e-05, "epoch": 0.7342615732476496, "percentage": 24.48, "elapsed_time": "11:01:40", "remaining_time": "1 day, 10:01:44", "throughput": 52039.6, "total_tokens": 2065988864} {"current_steps": 6180, "total_steps": 25209, "loss": 0.3673, "lr": 3.930919651101764e-05, "epoch": 0.73545162441985, "percentage": 24.52, "elapsed_time": "11:02:31", "remaining_time": "1 day, 9:59:58", "throughput": 52056.61, "total_tokens": 2069305984} {"current_steps": 6190, "total_steps": 25209, "loss": 0.3663, "lr": 3.9297053923846576e-05, "epoch": 0.7366416755920504, "percentage": 24.55, "elapsed_time": "11:03:22", "remaining_time": "1 day, 9:58:14", "throughput": 52073.55, "total_tokens": 2072648704} {"current_steps": 6200, "total_steps": 25209, "loss": 0.3668, "lr": 3.928492258224183e-05, "epoch": 0.7378317267642509, "percentage": 24.59, "elapsed_time": "11:04:10", "remaining_time": "1 day, 9:56:20", "throughput": 52093.39, "total_tokens": 2075948544} {"current_steps": 6210, "total_steps": 25209, "loss": 0.3653, "lr": 3.927280246885609e-05, "epoch": 0.7390217779364513, "percentage": 24.63, "elapsed_time": "11:04:59", "remaining_time": "1 day, 9:54:30", "throughput": 52111.94, "total_tokens": 2079263360} {"current_steps": 6220, "total_steps": 25209, "loss": 0.367, "lr": 3.9260693566379486e-05, "epoch": 0.7402118291086517, "percentage": 24.67, "elapsed_time": "11:05:54", "remaining_time": "1 day, 9:52:56", "throughput": 52125.5, "total_tokens": 2082646400} {"current_steps": 6230, "total_steps": 25209, "loss": 0.3652, "lr": 3.924859585753948e-05, "epoch": 0.7414018802808521, "percentage": 24.71, "elapsed_time": "11:06:45", "remaining_time": "1 day, 9:51:11", "throughput": 52142.72, "total_tokens": 2085982080} {"current_steps": 6240, "total_steps": 25209, "loss": 0.3697, "lr": 3.923650932510079e-05, "epoch": 0.7425919314530525, "percentage": 24.75, "elapsed_time": "11:07:36", "remaining_time": "1 day, 9:49:27", "throughput": 52159.43, "total_tokens": 2089323648} {"current_steps": 6250, "total_steps": 25209, "loss": 0.3644, "lr": 3.9224433951865215e-05, "epoch": 0.7437819826252529, "percentage": 24.79, "elapsed_time": "11:08:25", "remaining_time": "1 day, 9:47:38", "throughput": 52178.28, "total_tokens": 2092655872} {"current_steps": 6260, "total_steps": 25209, "loss": 0.3669, "lr": 3.921236972067165e-05, "epoch": 0.7449720337974532, "percentage": 24.83, "elapsed_time": "11:09:16", "remaining_time": "1 day, 9:45:53", "throughput": 52195.87, "total_tokens": 2096009600} {"current_steps": 6270, "total_steps": 25209, "loss": 0.3672, "lr": 3.920031661439585e-05, "epoch": 0.7461620849696537, "percentage": 24.87, "elapsed_time": "11:10:05", "remaining_time": "1 day, 9:44:03", "throughput": 52216.37, "total_tokens": 2099390080} {"current_steps": 6280, "total_steps": 25209, "loss": 0.3723, "lr": 3.918827461595045e-05, "epoch": 0.7473521361418541, "percentage": 24.91, "elapsed_time": "11:10:56", "remaining_time": "1 day, 9:42:19", "throughput": 52234.46, "total_tokens": 2102765184} {"current_steps": 6290, "total_steps": 25209, "loss": 0.3689, "lr": 3.9176243708284746e-05, "epoch": 0.7485421873140545, "percentage": 24.95, "elapsed_time": "11:11:47", "remaining_time": "1 day, 9:40:37", "throughput": 52250.75, "total_tokens": 2106118144} {"current_steps": 6300, "total_steps": 25209, "loss": 0.3659, "lr": 3.9164223874384715e-05, "epoch": 0.7497322384862549, "percentage": 24.99, "elapsed_time": "11:12:38", "remaining_time": "1 day, 9:38:51", "throughput": 52268.12, "total_tokens": 2109441664} {"current_steps": 6310, "total_steps": 25209, "loss": 0.3618, "lr": 3.91522150972728e-05, "epoch": 0.7509222896584553, "percentage": 25.03, "elapsed_time": "11:13:29", "remaining_time": "1 day, 9:37:11", "throughput": 52283.8, "total_tokens": 2112783616} {"current_steps": 6320, "total_steps": 25209, "loss": 0.3642, "lr": 3.9140217360007896e-05, "epoch": 0.7521123408306557, "percentage": 25.07, "elapsed_time": "11:14:20", "remaining_time": "1 day, 9:35:27", "throughput": 52300.45, "total_tokens": 2116112640} {"current_steps": 6330, "total_steps": 25209, "loss": 0.3683, "lr": 3.912823064568521e-05, "epoch": 0.7533023920028561, "percentage": 25.11, "elapsed_time": "11:15:09", "remaining_time": "1 day, 9:33:39", "throughput": 52318.11, "total_tokens": 2119395712} {"current_steps": 6340, "total_steps": 25209, "loss": 0.3681, "lr": 3.9116254937436155e-05, "epoch": 0.7544924431750565, "percentage": 25.15, "elapsed_time": "11:16:10", "remaining_time": "1 day, 9:32:24", "throughput": 52323.62, "total_tokens": 2122774528} {"current_steps": 6350, "total_steps": 25209, "loss": 0.3661, "lr": 3.910429021842825e-05, "epoch": 0.755682494347257, "percentage": 25.19, "elapsed_time": "11:17:12", "remaining_time": "1 day, 9:31:13", "throughput": 52324.82, "total_tokens": 2126064128} {"current_steps": 6360, "total_steps": 25209, "loss": 0.3678, "lr": 3.9092336471865084e-05, "epoch": 0.7568725455194574, "percentage": 25.23, "elapsed_time": "11:18:35", "remaining_time": "1 day, 9:31:06", "throughput": 52303.14, "total_tokens": 2129535616} {"current_steps": 6370, "total_steps": 25209, "loss": 0.3637, "lr": 3.908039368098611e-05, "epoch": 0.7580625966916578, "percentage": 25.27, "elapsed_time": "11:19:51", "remaining_time": "1 day, 9:30:40", "throughput": 52287.68, "total_tokens": 2132917504} {"current_steps": 6380, "total_steps": 25209, "loss": 0.3662, "lr": 3.9068461829066633e-05, "epoch": 0.7592526478638582, "percentage": 25.31, "elapsed_time": "11:20:47", "remaining_time": "1 day, 9:29:10", "throughput": 52300.4, "total_tokens": 2136317184} {"current_steps": 6390, "total_steps": 25209, "loss": 0.37, "lr": 3.9056540899417656e-05, "epoch": 0.7604426990360585, "percentage": 25.35, "elapsed_time": "11:21:34", "remaining_time": "1 day, 9:27:18", "throughput": 52319.49, "total_tokens": 2139599872} {"current_steps": 6400, "total_steps": 25209, "loss": 0.3667, "lr": 3.904463087538585e-05, "epoch": 0.7616327502082589, "percentage": 25.39, "elapsed_time": "11:22:29", "remaining_time": "1 day, 9:25:48", "throughput": 52333.44, "total_tokens": 2143053056} {"current_steps": 6410, "total_steps": 25209, "loss": 0.3674, "lr": 3.903273174035336e-05, "epoch": 0.7628228013804593, "percentage": 25.43, "elapsed_time": "11:23:20", "remaining_time": "1 day, 9:24:03", "throughput": 52351.34, "total_tokens": 2146404864} {"current_steps": 6420, "total_steps": 25209, "loss": 0.3663, "lr": 3.902084347773779e-05, "epoch": 0.7640128525526597, "percentage": 25.47, "elapsed_time": "11:24:13", "remaining_time": "1 day, 9:22:27", "throughput": 52366.65, "total_tokens": 2149808640} {"current_steps": 6430, "total_steps": 25209, "loss": 0.3638, "lr": 3.900896607099207e-05, "epoch": 0.7652029037248602, "percentage": 25.51, "elapsed_time": "11:25:05", "remaining_time": "1 day, 9:20:49", "throughput": 52382.27, "total_tokens": 2153194880} {"current_steps": 6440, "total_steps": 25209, "loss": 0.3638, "lr": 3.899709950360437e-05, "epoch": 0.7663929548970606, "percentage": 25.55, "elapsed_time": "11:25:56", "remaining_time": "1 day, 9:19:08", "throughput": 52399.09, "total_tokens": 2156562432} {"current_steps": 6450, "total_steps": 25209, "loss": 0.3643, "lr": 3.8985243759097997e-05, "epoch": 0.767583006069261, "percentage": 25.59, "elapsed_time": "11:26:46", "remaining_time": "1 day, 9:17:22", "throughput": 52416.4, "total_tokens": 2159876096} {"current_steps": 6460, "total_steps": 25209, "loss": 0.3646, "lr": 3.897339882103129e-05, "epoch": 0.7687730572414614, "percentage": 25.63, "elapsed_time": "11:27:40", "remaining_time": "1 day, 9:15:50", "throughput": 52432.09, "total_tokens": 2163360640} {"current_steps": 6470, "total_steps": 25209, "loss": 0.3641, "lr": 3.8961564672997544e-05, "epoch": 0.7699631084136618, "percentage": 25.67, "elapsed_time": "11:28:32", "remaining_time": "1 day, 9:14:11", "throughput": 52448.4, "total_tokens": 2166752256} {"current_steps": 6480, "total_steps": 25209, "loss": 0.3671, "lr": 3.8949741298624924e-05, "epoch": 0.7711531595858622, "percentage": 25.71, "elapsed_time": "11:29:23", "remaining_time": "1 day, 9:12:33", "throughput": 52464.89, "total_tokens": 2170156544} {"current_steps": 6490, "total_steps": 25209, "loss": 0.3685, "lr": 3.8937928681576305e-05, "epoch": 0.7723432107580626, "percentage": 25.74, "elapsed_time": "11:30:14", "remaining_time": "1 day, 9:10:51", "throughput": 52481.9, "total_tokens": 2173513344} {"current_steps": 6500, "total_steps": 25209, "loss": 0.3673, "lr": 3.8926126805549276e-05, "epoch": 0.773533261930263, "percentage": 25.78, "elapsed_time": "11:31:04", "remaining_time": "1 day, 9:09:06", "throughput": 52499.24, "total_tokens": 2176829696} {"current_steps": 6510, "total_steps": 25209, "loss": 0.3639, "lr": 3.891433565427596e-05, "epoch": 0.7747233131024635, "percentage": 25.82, "elapsed_time": "11:31:51", "remaining_time": "1 day, 9:07:14", "throughput": 52518.53, "total_tokens": 2180103040} {"current_steps": 6520, "total_steps": 25209, "loss": 0.3695, "lr": 3.8902555211522964e-05, "epoch": 0.7759133642746638, "percentage": 25.86, "elapsed_time": "11:32:44", "remaining_time": "1 day, 9:05:41", "throughput": 52534.34, "total_tokens": 2183566464} {"current_steps": 6530, "total_steps": 25209, "loss": 0.3639, "lr": 3.889078546109127e-05, "epoch": 0.7771034154468642, "percentage": 25.9, "elapsed_time": "11:33:33", "remaining_time": "1 day, 9:03:54", "throughput": 52551.71, "total_tokens": 2186844928} {"current_steps": 6540, "total_steps": 25209, "loss": 0.3647, "lr": 3.887902638681616e-05, "epoch": 0.7782934666190646, "percentage": 25.94, "elapsed_time": "11:34:27", "remaining_time": "1 day, 9:02:24", "throughput": 52565.91, "total_tokens": 2190316160} {"current_steps": 6550, "total_steps": 25209, "loss": 0.362, "lr": 3.886727797256707e-05, "epoch": 0.779483517791265, "percentage": 25.98, "elapsed_time": "11:35:20", "remaining_time": "1 day, 9:00:49", "throughput": 52580.31, "total_tokens": 2193680768} {"current_steps": 6560, "total_steps": 25209, "loss": 0.3659, "lr": 3.88555402022476e-05, "epoch": 0.7806735689634654, "percentage": 26.02, "elapsed_time": "11:36:13", "remaining_time": "1 day, 8:59:14", "throughput": 52594.84, "total_tokens": 2197057792} {"current_steps": 6570, "total_steps": 25209, "loss": 0.3647, "lr": 3.884381305979528e-05, "epoch": 0.7818636201356658, "percentage": 26.06, "elapsed_time": "11:37:03", "remaining_time": "1 day, 8:57:33", "throughput": 52607.56, "total_tokens": 2200250112} {"current_steps": 6580, "total_steps": 25209, "loss": 0.3684, "lr": 3.883209652918163e-05, "epoch": 0.7830536713078662, "percentage": 26.1, "elapsed_time": "11:37:54", "remaining_time": "1 day, 8:55:52", "throughput": 52620.85, "total_tokens": 2203462912} {"current_steps": 6590, "total_steps": 25209, "loss": 0.3667, "lr": 3.8820390594411935e-05, "epoch": 0.7842437224800667, "percentage": 26.14, "elapsed_time": "11:38:45", "remaining_time": "1 day, 8:54:14", "throughput": 52635.86, "total_tokens": 2206801920} {"current_steps": 6600, "total_steps": 25209, "loss": 0.3625, "lr": 3.880869523952524e-05, "epoch": 0.7854337736522671, "percentage": 26.18, "elapsed_time": "11:39:34", "remaining_time": "1 day, 8:52:28", "throughput": 52653.0, "total_tokens": 2210078592} {"current_steps": 6610, "total_steps": 25209, "loss": 0.3592, "lr": 3.879701044859422e-05, "epoch": 0.7866238248244675, "percentage": 26.22, "elapsed_time": "11:40:25", "remaining_time": "1 day, 8:50:49", "throughput": 52669.63, "total_tokens": 2213457152} {"current_steps": 6620, "total_steps": 25209, "loss": 0.3627, "lr": 3.87853362057251e-05, "epoch": 0.7878138759966679, "percentage": 26.26, "elapsed_time": "11:41:15", "remaining_time": "1 day, 8:49:07", "throughput": 52686.09, "total_tokens": 2216778112} {"current_steps": 6630, "total_steps": 25209, "loss": 0.3626, "lr": 3.8773672495057576e-05, "epoch": 0.7890039271688682, "percentage": 26.3, "elapsed_time": "11:42:15", "remaining_time": "1 day, 8:47:55", "throughput": 52688.04, "total_tokens": 2220058496} {"current_steps": 6640, "total_steps": 25209, "loss": 0.3636, "lr": 3.8762019300764674e-05, "epoch": 0.7901939783410686, "percentage": 26.34, "elapsed_time": "11:43:08", "remaining_time": "1 day, 8:46:22", "throughput": 52700.87, "total_tokens": 2223382400} {"current_steps": 6650, "total_steps": 25209, "loss": 0.37, "lr": 3.875037660705273e-05, "epoch": 0.791384029513269, "percentage": 26.38, "elapsed_time": "11:44:23", "remaining_time": "1 day, 8:45:51", "throughput": 52687.72, "total_tokens": 2226792576} {"current_steps": 6660, "total_steps": 25209, "loss": 0.3623, "lr": 3.873874439816127e-05, "epoch": 0.7925740806854695, "percentage": 26.42, "elapsed_time": "11:45:47", "remaining_time": "1 day, 8:45:43", "throughput": 52662.47, "total_tokens": 2230119808} {"current_steps": 6670, "total_steps": 25209, "loss": 0.3677, "lr": 3.872712265836289e-05, "epoch": 0.7937641318576699, "percentage": 26.46, "elapsed_time": "11:46:51", "remaining_time": "1 day, 8:44:40", "throughput": 52661.98, "total_tokens": 2233453824} {"current_steps": 6680, "total_steps": 25209, "loss": 0.3661, "lr": 3.8715511371963225e-05, "epoch": 0.7949541830298703, "percentage": 26.5, "elapsed_time": "11:47:39", "remaining_time": "1 day, 8:42:54", "throughput": 52679.52, "total_tokens": 2236748800} {"current_steps": 6690, "total_steps": 25209, "loss": 0.3625, "lr": 3.87039105233008e-05, "epoch": 0.7961442342020707, "percentage": 26.54, "elapsed_time": "11:48:29", "remaining_time": "1 day, 8:41:14", "throughput": 52696.72, "total_tokens": 2240135808} {"current_steps": 6700, "total_steps": 25209, "loss": 0.3591, "lr": 3.8692320096746975e-05, "epoch": 0.7973342853742711, "percentage": 26.58, "elapsed_time": "11:49:18", "remaining_time": "1 day, 8:39:29", "throughput": 52715.46, "total_tokens": 2243494016} {"current_steps": 6710, "total_steps": 25209, "loss": 0.3673, "lr": 3.868074007670589e-05, "epoch": 0.7985243365464715, "percentage": 26.62, "elapsed_time": "11:50:06", "remaining_time": "1 day, 8:37:43", "throughput": 52733.22, "total_tokens": 2246791552} {"current_steps": 6720, "total_steps": 25209, "loss": 0.3653, "lr": 3.866917044761428e-05, "epoch": 0.7997143877186719, "percentage": 26.66, "elapsed_time": "11:50:57", "remaining_time": "1 day, 8:36:04", "throughput": 52750.34, "total_tokens": 2250175232} {"current_steps": 6730, "total_steps": 25209, "loss": 0.3656, "lr": 3.8657611193941486e-05, "epoch": 0.8009044388908723, "percentage": 26.7, "elapsed_time": "11:51:53", "remaining_time": "1 day, 8:34:41", "throughput": 52761.42, "total_tokens": 2253628160} {"current_steps": 6740, "total_steps": 25209, "loss": 0.3659, "lr": 3.8646062300189315e-05, "epoch": 0.8020944900630728, "percentage": 26.74, "elapsed_time": "11:52:47", "remaining_time": "1 day, 8:33:10", "throughput": 52776.33, "total_tokens": 2257093376} {"current_steps": 6750, "total_steps": 25209, "loss": 0.3636, "lr": 3.8634523750891984e-05, "epoch": 0.8032845412352732, "percentage": 26.78, "elapsed_time": "11:53:38", "remaining_time": "1 day, 8:31:33", "throughput": 52791.64, "total_tokens": 2260449024} {"current_steps": 6760, "total_steps": 25209, "loss": 0.3636, "lr": 3.862299553061597e-05, "epoch": 0.8044745924074735, "percentage": 26.82, "elapsed_time": "11:54:29", "remaining_time": "1 day, 8:29:55", "throughput": 52807.73, "total_tokens": 2263820672} {"current_steps": 6770, "total_steps": 25209, "loss": 0.365, "lr": 3.861147762396e-05, "epoch": 0.8056646435796739, "percentage": 26.86, "elapsed_time": "11:55:20", "remaining_time": "1 day, 8:28:20", "throughput": 52820.99, "total_tokens": 2267113344} {"current_steps": 6780, "total_steps": 25209, "loss": 0.3678, "lr": 3.859997001555494e-05, "epoch": 0.8068546947518743, "percentage": 26.9, "elapsed_time": "11:56:09", "remaining_time": "1 day, 8:26:37", "throughput": 52837.68, "total_tokens": 2270410112} {"current_steps": 6790, "total_steps": 25209, "loss": 0.366, "lr": 3.8588472690063676e-05, "epoch": 0.8080447459240747, "percentage": 26.93, "elapsed_time": "11:57:01", "remaining_time": "1 day, 8:25:03", "throughput": 52854.03, "total_tokens": 2273877632} {"current_steps": 6800, "total_steps": 25209, "loss": 0.3629, "lr": 3.857698563218106e-05, "epoch": 0.8092347970962751, "percentage": 26.97, "elapsed_time": "11:57:50", "remaining_time": "1 day, 8:23:19", "throughput": 52873.14, "total_tokens": 2277250560} {"current_steps": 6810, "total_steps": 25209, "loss": 0.3639, "lr": 3.8565508826633836e-05, "epoch": 0.8104248482684755, "percentage": 27.01, "elapsed_time": "11:58:43", "remaining_time": "1 day, 8:21:50", "throughput": 52887.09, "total_tokens": 2280690688} {"current_steps": 6820, "total_steps": 25209, "loss": 0.3631, "lr": 3.855404225818049e-05, "epoch": 0.811614899440676, "percentage": 27.05, "elapsed_time": "11:59:32", "remaining_time": "1 day, 8:20:06", "throughput": 52904.69, "total_tokens": 2284003456} {"current_steps": 6830, "total_steps": 25209, "loss": 0.3647, "lr": 3.8542585911611286e-05, "epoch": 0.8128049506128764, "percentage": 27.09, "elapsed_time": "12:00:19", "remaining_time": "1 day, 8:18:19", "throughput": 52921.78, "total_tokens": 2287234560} {"current_steps": 6840, "total_steps": 25209, "loss": 0.3658, "lr": 3.853113977174803e-05, "epoch": 0.8139950017850768, "percentage": 27.13, "elapsed_time": "12:01:06", "remaining_time": "1 day, 8:16:34", "throughput": 52939.55, "total_tokens": 2290531584} {"current_steps": 6850, "total_steps": 25209, "loss": 0.3602, "lr": 3.851970382344411e-05, "epoch": 0.8151850529572772, "percentage": 27.17, "elapsed_time": "12:01:56", "remaining_time": "1 day, 8:14:54", "throughput": 52955.5, "total_tokens": 2293844736} {"current_steps": 6860, "total_steps": 25209, "loss": 0.3623, "lr": 3.850827805158433e-05, "epoch": 0.8163751041294776, "percentage": 27.21, "elapsed_time": "12:02:42", "remaining_time": "1 day, 8:13:03", "throughput": 52972.8, "total_tokens": 2297007872} {"current_steps": 6870, "total_steps": 25209, "loss": 0.3648, "lr": 3.8496862441084896e-05, "epoch": 0.817565155301678, "percentage": 27.25, "elapsed_time": "12:03:33", "remaining_time": "1 day, 8:11:28", "throughput": 52987.99, "total_tokens": 2300383104} {"current_steps": 6880, "total_steps": 25209, "loss": 0.3678, "lr": 3.848545697689328e-05, "epoch": 0.8187552064738783, "percentage": 27.29, "elapsed_time": "12:04:22", "remaining_time": "1 day, 8:09:47", "throughput": 53005.95, "total_tokens": 2303752960} {"current_steps": 6890, "total_steps": 25209, "loss": 0.3639, "lr": 3.8474061643988136e-05, "epoch": 0.8199452576460787, "percentage": 27.33, "elapsed_time": "12:05:11", "remaining_time": "1 day, 8:08:07", "throughput": 53021.83, "total_tokens": 2307049856} {"current_steps": 6900, "total_steps": 25209, "loss": 0.3684, "lr": 3.846267642737925e-05, "epoch": 0.8211353088182792, "percentage": 27.37, "elapsed_time": "12:06:02", "remaining_time": "1 day, 8:06:31", "throughput": 53038.91, "total_tokens": 2310494720} {"current_steps": 6910, "total_steps": 25209, "loss": 0.3627, "lr": 3.8451301312107455e-05, "epoch": 0.8223253599904796, "percentage": 27.41, "elapsed_time": "12:06:54", "remaining_time": "1 day, 8:05:00", "throughput": 53053.52, "total_tokens": 2313921408} {"current_steps": 6920, "total_steps": 25209, "loss": 0.3649, "lr": 3.843993628324451e-05, "epoch": 0.82351541116268, "percentage": 27.45, "elapsed_time": "12:07:47", "remaining_time": "1 day, 8:03:30", "throughput": 53067.99, "total_tokens": 2317362688} {"current_steps": 6930, "total_steps": 25209, "loss": 0.3647, "lr": 3.8428581325893034e-05, "epoch": 0.8247054623348804, "percentage": 27.49, "elapsed_time": "12:08:47", "remaining_time": "1 day, 8:02:18", "throughput": 53074.22, "total_tokens": 2320811136} {"current_steps": 6940, "total_steps": 25209, "loss": 0.359, "lr": 3.8417236425186484e-05, "epoch": 0.8258955135070808, "percentage": 27.53, "elapsed_time": "12:09:36", "remaining_time": "1 day, 8:00:36", "throughput": 53091.03, "total_tokens": 2324115712} {"current_steps": 6950, "total_steps": 25209, "loss": 0.3617, "lr": 3.840590156628895e-05, "epoch": 0.8270855646792812, "percentage": 27.57, "elapsed_time": "12:10:38", "remaining_time": "1 day, 7:59:33", "throughput": 53089.9, "total_tokens": 2327404288} {"current_steps": 6960, "total_steps": 25209, "loss": 0.3632, "lr": 3.8394576734395205e-05, "epoch": 0.8282756158514816, "percentage": 27.61, "elapsed_time": "12:11:55", "remaining_time": "1 day, 7:59:06", "throughput": 53074.17, "total_tokens": 2330787584} {"current_steps": 6970, "total_steps": 25209, "loss": 0.3609, "lr": 3.838326191473054e-05, "epoch": 0.829465667023682, "percentage": 27.65, "elapsed_time": "12:13:05", "remaining_time": "1 day, 7:58:19", "throughput": 53065.43, "total_tokens": 2334086656} {"current_steps": 6980, "total_steps": 25209, "loss": 0.3628, "lr": 3.837195709255069e-05, "epoch": 0.8306557181958825, "percentage": 27.69, "elapsed_time": "12:14:06", "remaining_time": "1 day, 7:57:12", "throughput": 53066.58, "total_tokens": 2337396864} {"current_steps": 6990, "total_steps": 25209, "loss": 0.3635, "lr": 3.8360662253141796e-05, "epoch": 0.8318457693680829, "percentage": 27.73, "elapsed_time": "12:14:58", "remaining_time": "1 day, 7:55:40", "throughput": 53080.1, "total_tokens": 2340772096} {"current_steps": 7000, "total_steps": 25209, "loss": 0.3609, "lr": 3.834937738182029e-05, "epoch": 0.8330358205402832, "percentage": 27.77, "elapsed_time": "12:15:51", "remaining_time": "1 day, 7:54:11", "throughput": 53093.11, "total_tokens": 2344166144} {"current_steps": 7010, "total_steps": 25209, "loss": 0.3667, "lr": 3.833810246393281e-05, "epoch": 0.8342258717124836, "percentage": 27.81, "elapsed_time": "12:16:42", "remaining_time": "1 day, 7:52:37", "throughput": 53106.21, "total_tokens": 2347443968} {"current_steps": 7020, "total_steps": 25209, "loss": 0.3609, "lr": 3.832683748485616e-05, "epoch": 0.835415922884684, "percentage": 27.85, "elapsed_time": "12:17:36", "remaining_time": "1 day, 7:51:10", "throughput": 53117.85, "total_tokens": 2350820736} {"current_steps": 7030, "total_steps": 25209, "loss": 0.3628, "lr": 3.8315582429997184e-05, "epoch": 0.8366059740568844, "percentage": 27.89, "elapsed_time": "12:18:25", "remaining_time": "1 day, 7:49:30", "throughput": 53131.71, "total_tokens": 2354031872} {"current_steps": 7040, "total_steps": 25209, "loss": 0.363, "lr": 3.830433728479272e-05, "epoch": 0.8377960252290848, "percentage": 27.93, "elapsed_time": "12:19:17", "remaining_time": "1 day, 7:47:59", "throughput": 53145.66, "total_tokens": 2357426176} {"current_steps": 7050, "total_steps": 25209, "loss": 0.3619, "lr": 3.829310203470948e-05, "epoch": 0.8389860764012853, "percentage": 27.97, "elapsed_time": "12:20:10", "remaining_time": "1 day, 7:46:30", "throughput": 53157.39, "total_tokens": 2360750976} {"current_steps": 7060, "total_steps": 25209, "loss": 0.3628, "lr": 3.828187666524403e-05, "epoch": 0.8401761275734857, "percentage": 28.01, "elapsed_time": "12:21:00", "remaining_time": "1 day, 7:44:53", "throughput": 53173.89, "total_tokens": 2364130944} {"current_steps": 7070, "total_steps": 25209, "loss": 0.3651, "lr": 3.827066116192266e-05, "epoch": 0.8413661787456861, "percentage": 28.05, "elapsed_time": "12:21:52", "remaining_time": "1 day, 7:43:22", "throughput": 53188.6, "total_tokens": 2367566464} {"current_steps": 7080, "total_steps": 25209, "loss": 0.3604, "lr": 3.825945551030135e-05, "epoch": 0.8425562299178865, "percentage": 28.09, "elapsed_time": "12:22:42", "remaining_time": "1 day, 7:41:46", "throughput": 53205.12, "total_tokens": 2370960128} {"current_steps": 7090, "total_steps": 25209, "loss": 0.3613, "lr": 3.824825969596561e-05, "epoch": 0.8437462810900869, "percentage": 28.12, "elapsed_time": "12:23:33", "remaining_time": "1 day, 7:40:13", "throughput": 53219.93, "total_tokens": 2374342144} {"current_steps": 7100, "total_steps": 25209, "loss": 0.3674, "lr": 3.823707370453054e-05, "epoch": 0.8449363322622873, "percentage": 28.16, "elapsed_time": "12:24:26", "remaining_time": "1 day, 7:38:43", "throughput": 53233.59, "total_tokens": 2377733760} {"current_steps": 7110, "total_steps": 25209, "loss": 0.3623, "lr": 3.8225897521640614e-05, "epoch": 0.8461263834344876, "percentage": 28.2, "elapsed_time": "12:25:13", "remaining_time": "1 day, 7:37:00", "throughput": 53250.21, "total_tokens": 2380986624} {"current_steps": 7120, "total_steps": 25209, "loss": 0.3649, "lr": 3.8214731132969675e-05, "epoch": 0.847316434606688, "percentage": 28.24, "elapsed_time": "12:26:02", "remaining_time": "1 day, 7:35:23", "throughput": 53266.07, "total_tokens": 2384326272} {"current_steps": 7130, "total_steps": 25209, "loss": 0.3575, "lr": 3.820357452422084e-05, "epoch": 0.8485064857788885, "percentage": 28.28, "elapsed_time": "12:26:55", "remaining_time": "1 day, 7:33:54", "throughput": 53279.08, "total_tokens": 2387717888} {"current_steps": 7140, "total_steps": 25209, "loss": 0.3612, "lr": 3.8192427681126445e-05, "epoch": 0.8496965369510889, "percentage": 28.32, "elapsed_time": "12:27:45", "remaining_time": "1 day, 7:32:19", "throughput": 53295.51, "total_tokens": 2391115392} {"current_steps": 7150, "total_steps": 25209, "loss": 0.3634, "lr": 3.818129058944793e-05, "epoch": 0.8508865881232893, "percentage": 28.36, "elapsed_time": "12:28:36", "remaining_time": "1 day, 7:30:48", "throughput": 53308.84, "total_tokens": 2394468608} {"current_steps": 7160, "total_steps": 25209, "loss": 0.3618, "lr": 3.817016323497578e-05, "epoch": 0.8520766392954897, "percentage": 28.4, "elapsed_time": "12:29:28", "remaining_time": "1 day, 7:29:15", "throughput": 53321.99, "total_tokens": 2397786240} {"current_steps": 7170, "total_steps": 25209, "loss": 0.362, "lr": 3.8159045603529455e-05, "epoch": 0.8532666904676901, "percentage": 28.44, "elapsed_time": "12:30:19", "remaining_time": "1 day, 7:27:45", "throughput": 53336.15, "total_tokens": 2401176704} {"current_steps": 7180, "total_steps": 25209, "loss": 0.3611, "lr": 3.8147937680957334e-05, "epoch": 0.8544567416398905, "percentage": 28.48, "elapsed_time": "12:31:06", "remaining_time": "1 day, 7:26:01", "throughput": 53354.02, "total_tokens": 2404464000} {"current_steps": 7190, "total_steps": 25209, "loss": 0.3645, "lr": 3.813683945313658e-05, "epoch": 0.8556467928120909, "percentage": 28.52, "elapsed_time": "12:31:55", "remaining_time": "1 day, 7:24:23", "throughput": 53369.88, "total_tokens": 2407789952} {"current_steps": 7200, "total_steps": 25209, "loss": 0.3596, "lr": 3.812575090597313e-05, "epoch": 0.8568368439842913, "percentage": 28.56, "elapsed_time": "12:32:46", "remaining_time": "1 day, 7:22:52", "throughput": 53383.47, "total_tokens": 2411138176} {"current_steps": 7210, "total_steps": 25209, "loss": 0.3566, "lr": 3.811467202540156e-05, "epoch": 0.8580268951564918, "percentage": 28.6, "elapsed_time": "12:33:36", "remaining_time": "1 day, 7:21:18", "throughput": 53399.44, "total_tokens": 2414540544} {"current_steps": 7220, "total_steps": 25209, "loss": 0.3615, "lr": 3.810360279738507e-05, "epoch": 0.8592169463286922, "percentage": 28.64, "elapsed_time": "12:34:26", "remaining_time": "1 day, 7:19:44", "throughput": 53414.98, "total_tokens": 2417928192} {"current_steps": 7230, "total_steps": 25209, "loss": 0.3539, "lr": 3.809254320791535e-05, "epoch": 0.8604069975008926, "percentage": 28.68, "elapsed_time": "12:35:21", "remaining_time": "1 day, 7:18:22", "throughput": 53424.93, "total_tokens": 2421318144} {"current_steps": 7240, "total_steps": 25209, "loss": 0.359, "lr": 3.808149324301256e-05, "epoch": 0.861597048673093, "percentage": 28.72, "elapsed_time": "12:36:14", "remaining_time": "1 day, 7:16:54", "throughput": 53434.62, "total_tokens": 2424551552} {"current_steps": 7250, "total_steps": 25209, "loss": 0.3588, "lr": 3.807045288872522e-05, "epoch": 0.8627870998452933, "percentage": 28.76, "elapsed_time": "12:37:23", "remaining_time": "1 day, 7:16:09", "throughput": 53427.2, "total_tokens": 2427939072} {"current_steps": 7260, "total_steps": 25209, "loss": 0.359, "lr": 3.805942213113015e-05, "epoch": 0.8639771510174937, "percentage": 28.8, "elapsed_time": "12:38:32", "remaining_time": "1 day, 7:15:22", "throughput": 53419.58, "total_tokens": 2431278592} {"current_steps": 7270, "total_steps": 25209, "loss": 0.3606, "lr": 3.8048400956332385e-05, "epoch": 0.8651672021896941, "percentage": 28.84, "elapsed_time": "12:39:39", "remaining_time": "1 day, 7:14:28", "throughput": 53415.41, "total_tokens": 2434627072} {"current_steps": 7280, "total_steps": 25209, "loss": 0.3601, "lr": 3.803738935046512e-05, "epoch": 0.8663572533618945, "percentage": 28.88, "elapsed_time": "12:40:56", "remaining_time": "1 day, 7:14:01", "throughput": 53397.19, "total_tokens": 2437934080} {"current_steps": 7290, "total_steps": 25209, "loss": 0.3635, "lr": 3.802638729968962e-05, "epoch": 0.867547304534095, "percentage": 28.92, "elapsed_time": "12:41:52", "remaining_time": "1 day, 7:12:41", "throughput": 53406.82, "total_tokens": 2441347712} {"current_steps": 7300, "total_steps": 25209, "loss": 0.3646, "lr": 3.8015394790195145e-05, "epoch": 0.8687373557062954, "percentage": 28.96, "elapsed_time": "12:42:40", "remaining_time": "1 day, 7:11:02", "throughput": 53423.19, "total_tokens": 2444647296} {"current_steps": 7310, "total_steps": 25209, "loss": 0.3615, "lr": 3.800441180819891e-05, "epoch": 0.8699274068784958, "percentage": 29.0, "elapsed_time": "12:43:29", "remaining_time": "1 day, 7:09:28", "throughput": 53439.66, "total_tokens": 2448055552} {"current_steps": 7320, "total_steps": 25209, "loss": 0.3592, "lr": 3.7993438339945965e-05, "epoch": 0.8711174580506962, "percentage": 29.04, "elapsed_time": "12:44:20", "remaining_time": "1 day, 7:07:56", "throughput": 53453.69, "total_tokens": 2451416960} {"current_steps": 7330, "total_steps": 25209, "loss": 0.3631, "lr": 3.798247437170914e-05, "epoch": 0.8723075092228966, "percentage": 29.08, "elapsed_time": "12:45:10", "remaining_time": "1 day, 7:06:22", "throughput": 53468.52, "total_tokens": 2454762112} {"current_steps": 7340, "total_steps": 25209, "loss": 0.3635, "lr": 3.797151988978901e-05, "epoch": 0.873497560395097, "percentage": 29.12, "elapsed_time": "12:46:01", "remaining_time": "1 day, 7:04:50", "throughput": 53482.74, "total_tokens": 2458123008} {"current_steps": 7350, "total_steps": 25209, "loss": 0.3578, "lr": 3.796057488051377e-05, "epoch": 0.8746876115672974, "percentage": 29.16, "elapsed_time": "12:46:47", "remaining_time": "1 day, 7:03:09", "throughput": 53499.45, "total_tokens": 2461396224} {"current_steps": 7360, "total_steps": 25209, "loss": 0.3588, "lr": 3.794963933023918e-05, "epoch": 0.8758776627394979, "percentage": 29.2, "elapsed_time": "12:47:33", "remaining_time": "1 day, 7:01:27", "throughput": 53517.2, "total_tokens": 2464680192} {"current_steps": 7370, "total_steps": 25209, "loss": 0.3593, "lr": 3.79387132253485e-05, "epoch": 0.8770677139116982, "percentage": 29.24, "elapsed_time": "12:48:22", "remaining_time": "1 day, 6:59:50", "throughput": 53531.95, "total_tokens": 2467965696} {"current_steps": 7380, "total_steps": 25209, "loss": 0.3663, "lr": 3.792779655225243e-05, "epoch": 0.8782577650838986, "percentage": 29.28, "elapsed_time": "12:49:13", "remaining_time": "1 day, 6:58:20", "throughput": 53544.7, "total_tokens": 2471281920} {"current_steps": 7390, "total_steps": 25209, "loss": 0.3619, "lr": 3.791688929738902e-05, "epoch": 0.879447816256099, "percentage": 29.31, "elapsed_time": "12:50:04", "remaining_time": "1 day, 6:56:49", "throughput": 53558.84, "total_tokens": 2474663424} {"current_steps": 7400, "total_steps": 25209, "loss": 0.3574, "lr": 3.79059914472236e-05, "epoch": 0.8806378674282994, "percentage": 29.35, "elapsed_time": "12:50:55", "remaining_time": "1 day, 6:55:19", "throughput": 53571.53, "total_tokens": 2477969280} {"current_steps": 7410, "total_steps": 25209, "loss": 0.3652, "lr": 3.7895102988248716e-05, "epoch": 0.8818279186004998, "percentage": 29.39, "elapsed_time": "12:51:46", "remaining_time": "1 day, 6:53:50", "throughput": 53585.75, "total_tokens": 2481387904} {"current_steps": 7420, "total_steps": 25209, "loss": 0.3593, "lr": 3.7884223906984064e-05, "epoch": 0.8830179697727002, "percentage": 29.43, "elapsed_time": "12:52:37", "remaining_time": "1 day, 6:52:20", "throughput": 53599.36, "total_tokens": 2484755712} {"current_steps": 7430, "total_steps": 25209, "loss": 0.3617, "lr": 3.787335418997641e-05, "epoch": 0.8842080209449006, "percentage": 29.47, "elapsed_time": "12:53:31", "remaining_time": "1 day, 6:50:55", "throughput": 53612.19, "total_tokens": 2488197504} {"current_steps": 7440, "total_steps": 25209, "loss": 0.3576, "lr": 3.786249382379952e-05, "epoch": 0.8853980721171011, "percentage": 29.51, "elapsed_time": "12:54:23", "remaining_time": "1 day, 6:49:30", "throughput": 53622.93, "total_tokens": 2491530112} {"current_steps": 7450, "total_steps": 25209, "loss": 0.3639, "lr": 3.785164279505411e-05, "epoch": 0.8865881232893015, "percentage": 29.55, "elapsed_time": "12:55:14", "remaining_time": "1 day, 6:47:58", "throughput": 53638.71, "total_tokens": 2494958208} {"current_steps": 7460, "total_steps": 25209, "loss": 0.3607, "lr": 3.7840801090367744e-05, "epoch": 0.8877781744615019, "percentage": 29.59, "elapsed_time": "12:56:02", "remaining_time": "1 day, 6:46:22", "throughput": 53653.66, "total_tokens": 2498249728} {"current_steps": 7470, "total_steps": 25209, "loss": 0.3607, "lr": 3.782996869639479e-05, "epoch": 0.8889682256337023, "percentage": 29.63, "elapsed_time": "12:56:54", "remaining_time": "1 day, 6:44:55", "throughput": 53664.43, "total_tokens": 2501551744} {"current_steps": 7480, "total_steps": 25209, "loss": 0.3599, "lr": 3.7819145599816354e-05, "epoch": 0.8901582768059026, "percentage": 29.67, "elapsed_time": "12:57:45", "remaining_time": "1 day, 6:43:26", "throughput": 53677.61, "total_tokens": 2504908160} {"current_steps": 7490, "total_steps": 25209, "loss": 0.3564, "lr": 3.780833178734018e-05, "epoch": 0.891348327978103, "percentage": 29.71, "elapsed_time": "12:58:40", "remaining_time": "1 day, 6:42:06", "throughput": 53688.4, "total_tokens": 2508365568} {"current_steps": 7500, "total_steps": 25209, "loss": 0.3588, "lr": 3.77975272457006e-05, "epoch": 0.8925383791503034, "percentage": 29.75, "elapsed_time": "12:59:30", "remaining_time": "1 day, 6:40:33", "throughput": 53704.1, "total_tokens": 2511741696} {"current_steps": 7510, "total_steps": 25209, "loss": 0.3598, "lr": 3.778673196165851e-05, "epoch": 0.8937284303225038, "percentage": 29.79, "elapsed_time": "13:00:17", "remaining_time": "1 day, 6:38:56", "throughput": 53721.13, "total_tokens": 2515101056} {"current_steps": 7520, "total_steps": 25209, "loss": 0.3575, "lr": 3.7775945922001186e-05, "epoch": 0.8949184814947043, "percentage": 29.83, "elapsed_time": "13:01:15", "remaining_time": "1 day, 6:37:42", "throughput": 53728.77, "total_tokens": 2518550016} {"current_steps": 7530, "total_steps": 25209, "loss": 0.3568, "lr": 3.776516911354236e-05, "epoch": 0.8961085326669047, "percentage": 29.87, "elapsed_time": "13:02:06", "remaining_time": "1 day, 6:36:13", "throughput": 53741.83, "total_tokens": 2521900672} {"current_steps": 7540, "total_steps": 25209, "loss": 0.3575, "lr": 3.775440152312205e-05, "epoch": 0.8972985838391051, "percentage": 29.91, "elapsed_time": "13:03:10", "remaining_time": "1 day, 6:35:16", "throughput": 53738.36, "total_tokens": 2525199104} {"current_steps": 7550, "total_steps": 25209, "loss": 0.361, "lr": 3.774364313760652e-05, "epoch": 0.8984886350113055, "percentage": 29.95, "elapsed_time": "13:04:21", "remaining_time": "1 day, 6:34:34", "throughput": 53729.57, "total_tokens": 2528610432} {"current_steps": 7560, "total_steps": 25209, "loss": 0.3591, "lr": 3.7732893943888224e-05, "epoch": 0.8996786861835059, "percentage": 29.99, "elapsed_time": "13:05:32", "remaining_time": "1 day, 6:33:51", "throughput": 53720.75, "total_tokens": 2531985920} {"current_steps": 7570, "total_steps": 25209, "loss": 0.3627, "lr": 3.772215392888574e-05, "epoch": 0.9008687373557063, "percentage": 30.03, "elapsed_time": "13:06:27", "remaining_time": "1 day, 6:32:33", "throughput": 53728.75, "total_tokens": 2535351808} {"current_steps": 7580, "total_steps": 25209, "loss": 0.3612, "lr": 3.771142307954368e-05, "epoch": 0.9020587885279067, "percentage": 30.07, "elapsed_time": "13:07:17", "remaining_time": "1 day, 6:31:00", "throughput": 53744.22, "total_tokens": 2538726528} {"current_steps": 7590, "total_steps": 25209, "loss": 0.3576, "lr": 3.770070138283264e-05, "epoch": 0.903248839700107, "percentage": 30.11, "elapsed_time": "13:08:08", "remaining_time": "1 day, 6:29:32", "throughput": 53758.97, "total_tokens": 2542161152} {"current_steps": 7600, "total_steps": 25209, "loss": 0.3632, "lr": 3.768998882574915e-05, "epoch": 0.9044388908723076, "percentage": 30.15, "elapsed_time": "13:08:56", "remaining_time": "1 day, 6:27:58", "throughput": 53774.89, "total_tokens": 2545532416} {"current_steps": 7610, "total_steps": 25209, "loss": 0.3588, "lr": 3.767928539531557e-05, "epoch": 0.905628942044508, "percentage": 30.19, "elapsed_time": "13:09:44", "remaining_time": "1 day, 6:26:21", "throughput": 53790.7, "total_tokens": 2548838912} {"current_steps": 7620, "total_steps": 25209, "loss": 0.3615, "lr": 3.7668591078580055e-05, "epoch": 0.9068189932167083, "percentage": 30.23, "elapsed_time": "13:10:32", "remaining_time": "1 day, 6:24:47", "throughput": 53806.19, "total_tokens": 2552178048} {"current_steps": 7630, "total_steps": 25209, "loss": 0.3615, "lr": 3.765790586261647e-05, "epoch": 0.9080090443889087, "percentage": 30.27, "elapsed_time": "13:11:23", "remaining_time": "1 day, 6:23:18", "throughput": 53819.64, "total_tokens": 2555537664} {"current_steps": 7640, "total_steps": 25209, "loss": 0.3622, "lr": 3.7647229734524326e-05, "epoch": 0.9091990955611091, "percentage": 30.31, "elapsed_time": "13:12:13", "remaining_time": "1 day, 6:21:48", "throughput": 53833.26, "total_tokens": 2558897280} {"current_steps": 7650, "total_steps": 25209, "loss": 0.3599, "lr": 3.7636562681428744e-05, "epoch": 0.9103891467333095, "percentage": 30.35, "elapsed_time": "13:13:03", "remaining_time": "1 day, 6:20:18", "throughput": 53847.29, "total_tokens": 2562244864} {"current_steps": 7660, "total_steps": 25209, "loss": 0.3589, "lr": 3.7625904690480346e-05, "epoch": 0.9115791979055099, "percentage": 30.39, "elapsed_time": "13:13:49", "remaining_time": "1 day, 6:18:38", "throughput": 53864.49, "total_tokens": 2565524992} {"current_steps": 7670, "total_steps": 25209, "loss": 0.3603, "lr": 3.7615255748855224e-05, "epoch": 0.9127692490777103, "percentage": 30.43, "elapsed_time": "13:14:38", "remaining_time": "1 day, 6:17:05", "throughput": 53879.44, "total_tokens": 2568870272} {"current_steps": 7680, "total_steps": 25209, "loss": 0.3591, "lr": 3.7604615843754845e-05, "epoch": 0.9139593002499108, "percentage": 30.47, "elapsed_time": "13:15:27", "remaining_time": "1 day, 6:15:34", "throughput": 53894.22, "total_tokens": 2572246912} {"current_steps": 7690, "total_steps": 25209, "loss": 0.3578, "lr": 3.759398496240601e-05, "epoch": 0.9151493514221112, "percentage": 30.5, "elapsed_time": "13:16:16", "remaining_time": "1 day, 6:14:02", "throughput": 53909.84, "total_tokens": 2575619840} {"current_steps": 7700, "total_steps": 25209, "loss": 0.3579, "lr": 3.7583363092060815e-05, "epoch": 0.9163394025943116, "percentage": 30.54, "elapsed_time": "13:17:06", "remaining_time": "1 day, 6:12:32", "throughput": 53925.02, "total_tokens": 2579056512} {"current_steps": 7710, "total_steps": 25209, "loss": 0.3586, "lr": 3.757275021999649e-05, "epoch": 0.917529453766512, "percentage": 30.58, "elapsed_time": "13:17:54", "remaining_time": "1 day, 6:10:57", "throughput": 53940.57, "total_tokens": 2582366720} {"current_steps": 7720, "total_steps": 25209, "loss": 0.3581, "lr": 3.7562146333515445e-05, "epoch": 0.9187195049387124, "percentage": 30.62, "elapsed_time": "13:18:45", "remaining_time": "1 day, 6:09:31", "throughput": 53954.34, "total_tokens": 2585797248} {"current_steps": 7730, "total_steps": 25209, "loss": 0.3601, "lr": 3.7551551419945167e-05, "epoch": 0.9199095561109127, "percentage": 30.66, "elapsed_time": "13:19:35", "remaining_time": "1 day, 6:08:01", "throughput": 53969.21, "total_tokens": 2589200128} {"current_steps": 7740, "total_steps": 25209, "loss": 0.3549, "lr": 3.7540965466638104e-05, "epoch": 0.9210996072831131, "percentage": 30.7, "elapsed_time": "13:20:25", "remaining_time": "1 day, 6:06:31", "throughput": 53984.28, "total_tokens": 2592595584} {"current_steps": 7750, "total_steps": 25209, "loss": 0.3627, "lr": 3.753038846097172e-05, "epoch": 0.9222896584553136, "percentage": 30.74, "elapsed_time": "13:21:15", "remaining_time": "1 day, 6:05:03", "throughput": 53998.17, "total_tokens": 2595997824} {"current_steps": 7760, "total_steps": 25209, "loss": 0.3593, "lr": 3.751982039034827e-05, "epoch": 0.923479709627514, "percentage": 30.78, "elapsed_time": "13:22:04", "remaining_time": "1 day, 6:03:32", "throughput": 54011.46, "total_tokens": 2599294720} {"current_steps": 7770, "total_steps": 25209, "loss": 0.3596, "lr": 3.75092612421949e-05, "epoch": 0.9246697607997144, "percentage": 30.82, "elapsed_time": "13:22:53", "remaining_time": "1 day, 6:02:01", "throughput": 54025.87, "total_tokens": 2602637568} {"current_steps": 7780, "total_steps": 25209, "loss": 0.3632, "lr": 3.7498711003963475e-05, "epoch": 0.9258598119719148, "percentage": 30.86, "elapsed_time": "13:23:41", "remaining_time": "1 day, 6:00:27", "throughput": 54041.18, "total_tokens": 2605950592} {"current_steps": 7790, "total_steps": 25209, "loss": 0.361, "lr": 3.748816966313058e-05, "epoch": 0.9270498631441152, "percentage": 30.9, "elapsed_time": "13:24:31", "remaining_time": "1 day, 5:58:59", "throughput": 54054.93, "total_tokens": 2609335424} {"current_steps": 7800, "total_steps": 25209, "loss": 0.3597, "lr": 3.7477637207197374e-05, "epoch": 0.9282399143163156, "percentage": 30.94, "elapsed_time": "13:25:18", "remaining_time": "1 day, 5:57:22", "throughput": 54071.78, "total_tokens": 2612645504} {"current_steps": 7810, "total_steps": 25209, "loss": 0.3633, "lr": 3.7467113623689666e-05, "epoch": 0.929429965488516, "percentage": 30.98, "elapsed_time": "13:26:07", "remaining_time": "1 day, 5:55:52", "throughput": 54086.9, "total_tokens": 2616058752} {"current_steps": 7820, "total_steps": 25209, "loss": 0.3625, "lr": 3.745659890015768e-05, "epoch": 0.9306200166607164, "percentage": 31.02, "elapsed_time": "13:26:57", "remaining_time": "1 day, 5:54:23", "throughput": 54101.51, "total_tokens": 2619449472} {"current_steps": 7830, "total_steps": 25209, "loss": 0.3659, "lr": 3.744609302417615e-05, "epoch": 0.9318100678329169, "percentage": 31.06, "elapsed_time": "13:27:50", "remaining_time": "1 day, 5:53:02", "throughput": 54110.2, "total_tokens": 2622743552} {"current_steps": 7840, "total_steps": 25209, "loss": 0.3593, "lr": 3.7435595983344175e-05, "epoch": 0.9330001190051173, "percentage": 31.1, "elapsed_time": "13:28:40", "remaining_time": "1 day, 5:51:34", "throughput": 54122.63, "total_tokens": 2626076416} {"current_steps": 7850, "total_steps": 25209, "loss": 0.3595, "lr": 3.7425107765285155e-05, "epoch": 0.9341901701773176, "percentage": 31.14, "elapsed_time": "13:29:40", "remaining_time": "1 day, 5:50:27", "throughput": 54127.08, "total_tokens": 2629504384} {"current_steps": 7860, "total_steps": 25209, "loss": 0.3611, "lr": 3.741462835764676e-05, "epoch": 0.935380221349518, "percentage": 31.18, "elapsed_time": "13:30:39", "remaining_time": "1 day, 5:49:20", "throughput": 54128.79, "total_tokens": 2632810240} {"current_steps": 7870, "total_steps": 25209, "loss": 0.3559, "lr": 3.740415774810088e-05, "epoch": 0.9365702725217184, "percentage": 31.22, "elapsed_time": "13:31:49", "remaining_time": "1 day, 5:48:35", "throughput": 54120.6, "total_tokens": 2636178560} {"current_steps": 7880, "total_steps": 25209, "loss": 0.3591, "lr": 3.739369592434351e-05, "epoch": 0.9377603236939188, "percentage": 31.26, "elapsed_time": "13:33:00", "remaining_time": "1 day, 5:47:52", "throughput": 54111.09, "total_tokens": 2639539200} {"current_steps": 7890, "total_steps": 25209, "loss": 0.3593, "lr": 3.738324287409473e-05, "epoch": 0.9389503748661192, "percentage": 31.3, "elapsed_time": "13:34:03", "remaining_time": "1 day, 5:46:53", "throughput": 54110.56, "total_tokens": 2642934528} {"current_steps": 7900, "total_steps": 25209, "loss": 0.3595, "lr": 3.7372798585098644e-05, "epoch": 0.9401404260383196, "percentage": 31.34, "elapsed_time": "13:34:58", "remaining_time": "1 day, 5:45:36", "throughput": 54117.18, "total_tokens": 2646224000} {"current_steps": 7910, "total_steps": 25209, "loss": 0.3568, "lr": 3.736236304512331e-05, "epoch": 0.9413304772105201, "percentage": 31.38, "elapsed_time": "13:35:47", "remaining_time": "1 day, 5:44:06", "throughput": 54129.44, "total_tokens": 2649477376} {"current_steps": 7920, "total_steps": 25209, "loss": 0.3591, "lr": 3.735193624196067e-05, "epoch": 0.9425205283827205, "percentage": 31.42, "elapsed_time": "13:36:35", "remaining_time": "1 day, 5:42:35", "throughput": 54143.56, "total_tokens": 2652813824} {"current_steps": 7930, "total_steps": 25209, "loss": 0.3557, "lr": 3.7341518163426514e-05, "epoch": 0.9437105795549209, "percentage": 31.46, "elapsed_time": "13:37:31", "remaining_time": "1 day, 5:41:19", "throughput": 54152.41, "total_tokens": 2656237824} {"current_steps": 7940, "total_steps": 25209, "loss": 0.3586, "lr": 3.73311087973604e-05, "epoch": 0.9449006307271213, "percentage": 31.5, "elapsed_time": "13:38:24", "remaining_time": "1 day, 5:39:58", "throughput": 54161.62, "total_tokens": 2659559936} {"current_steps": 7950, "total_steps": 25209, "loss": 0.3616, "lr": 3.732070813162561e-05, "epoch": 0.9460906818993217, "percentage": 31.54, "elapsed_time": "13:39:16", "remaining_time": "1 day, 5:38:36", "throughput": 54174.06, "total_tokens": 2663019264} {"current_steps": 7960, "total_steps": 25209, "loss": 0.362, "lr": 3.731031615410908e-05, "epoch": 0.947280733071522, "percentage": 31.58, "elapsed_time": "13:40:03", "remaining_time": "1 day, 5:37:02", "throughput": 54188.32, "total_tokens": 2666267520} {"current_steps": 7970, "total_steps": 25209, "loss": 0.3595, "lr": 3.729993285272132e-05, "epoch": 0.9484707842437224, "percentage": 31.62, "elapsed_time": "13:40:52", "remaining_time": "1 day, 5:35:33", "throughput": 54203.38, "total_tokens": 2669675392} {"current_steps": 7980, "total_steps": 25209, "loss": 0.3585, "lr": 3.7289558215396414e-05, "epoch": 0.9496608354159228, "percentage": 31.66, "elapsed_time": "13:41:43", "remaining_time": "1 day, 5:34:07", "throughput": 54216.38, "total_tokens": 2673050880} {"current_steps": 7990, "total_steps": 25209, "loss": 0.3562, "lr": 3.727919223009191e-05, "epoch": 0.9508508865881233, "percentage": 31.7, "elapsed_time": "13:42:33", "remaining_time": "1 day, 5:32:40", "throughput": 54230.52, "total_tokens": 2676462464} {"current_steps": 8000, "total_steps": 25209, "loss": 0.3586, "lr": 3.726883488478877e-05, "epoch": 0.9520409377603237, "percentage": 31.73, "elapsed_time": "13:43:22", "remaining_time": "1 day, 5:31:10", "throughput": 54244.16, "total_tokens": 2679796352} {"current_steps": 8010, "total_steps": 25209, "loss": 0.3606, "lr": 3.7258486167491323e-05, "epoch": 0.9532309889325241, "percentage": 31.77, "elapsed_time": "13:44:14", "remaining_time": "1 day, 5:29:48", "throughput": 54256.3, "total_tokens": 2683228160} {"current_steps": 8020, "total_steps": 25209, "loss": 0.3553, "lr": 3.724814606622721e-05, "epoch": 0.9544210401047245, "percentage": 31.81, "elapsed_time": "13:45:05", "remaining_time": "1 day, 5:28:23", "throughput": 54269.05, "total_tokens": 2686627456} {"current_steps": 8030, "total_steps": 25209, "loss": 0.3581, "lr": 3.7237814569047294e-05, "epoch": 0.9556110912769249, "percentage": 31.85, "elapsed_time": "13:45:53", "remaining_time": "1 day, 5:26:53", "throughput": 54282.79, "total_tokens": 2689928320} {"current_steps": 8040, "total_steps": 25209, "loss": 0.3602, "lr": 3.7227491664025656e-05, "epoch": 0.9568011424491253, "percentage": 31.89, "elapsed_time": "13:46:45", "remaining_time": "1 day, 5:25:29", "throughput": 54295.35, "total_tokens": 2693335552} {"current_steps": 8050, "total_steps": 25209, "loss": 0.3586, "lr": 3.721717733925948e-05, "epoch": 0.9579911936213257, "percentage": 31.93, "elapsed_time": "13:47:33", "remaining_time": "1 day, 5:23:59", "throughput": 54310.05, "total_tokens": 2696684288} {"current_steps": 8060, "total_steps": 25209, "loss": 0.3605, "lr": 3.720687158286904e-05, "epoch": 0.9591812447935261, "percentage": 31.97, "elapsed_time": "13:48:21", "remaining_time": "1 day, 5:22:27", "throughput": 54325.13, "total_tokens": 2700030336} {"current_steps": 8070, "total_steps": 25209, "loss": 0.3573, "lr": 3.719657438299762e-05, "epoch": 0.9603712959657266, "percentage": 32.01, "elapsed_time": "13:49:08", "remaining_time": "1 day, 5:20:54", "throughput": 54340.77, "total_tokens": 2703347840} {"current_steps": 8080, "total_steps": 25209, "loss": 0.358, "lr": 3.7186285727811446e-05, "epoch": 0.961561347137927, "percentage": 32.05, "elapsed_time": "13:49:57", "remaining_time": "1 day, 5:19:28", "throughput": 54355.48, "total_tokens": 2706793600} {"current_steps": 8090, "total_steps": 25209, "loss": 0.3605, "lr": 3.717600560549967e-05, "epoch": 0.9627513983101273, "percentage": 32.09, "elapsed_time": "13:50:44", "remaining_time": "1 day, 5:17:54", "throughput": 54370.73, "total_tokens": 2710094592} {"current_steps": 8100, "total_steps": 25209, "loss": 0.362, "lr": 3.716573400427426e-05, "epoch": 0.9639414494823277, "percentage": 32.13, "elapsed_time": "13:51:32", "remaining_time": "1 day, 5:16:23", "throughput": 54385.34, "total_tokens": 2713411968} {"current_steps": 8110, "total_steps": 25209, "loss": 0.3599, "lr": 3.7155470912370004e-05, "epoch": 0.9651315006545281, "percentage": 32.17, "elapsed_time": "13:52:22", "remaining_time": "1 day, 5:14:58", "throughput": 54398.85, "total_tokens": 2716827904} {"current_steps": 8120, "total_steps": 25209, "loss": 0.3587, "lr": 3.714521631804439e-05, "epoch": 0.9663215518267285, "percentage": 32.21, "elapsed_time": "13:53:10", "remaining_time": "1 day, 5:13:27", "throughput": 54413.48, "total_tokens": 2720149888} {"current_steps": 8130, "total_steps": 25209, "loss": 0.3581, "lr": 3.713497020957759e-05, "epoch": 0.9675116029989289, "percentage": 32.25, "elapsed_time": "13:53:59", "remaining_time": "1 day, 5:12:00", "throughput": 54427.56, "total_tokens": 2723547776} {"current_steps": 8140, "total_steps": 25209, "loss": 0.3583, "lr": 3.712473257527238e-05, "epoch": 0.9687016541711294, "percentage": 32.29, "elapsed_time": "13:54:51", "remaining_time": "1 day, 5:10:37", "throughput": 54439.61, "total_tokens": 2726952448} {"current_steps": 8150, "total_steps": 25209, "loss": 0.359, "lr": 3.711450340345412e-05, "epoch": 0.9698917053433298, "percentage": 32.33, "elapsed_time": "13:55:43", "remaining_time": "1 day, 5:09:17", "throughput": 54449.7, "total_tokens": 2730321408} {"current_steps": 8160, "total_steps": 25209, "loss": 0.3602, "lr": 3.710428268247067e-05, "epoch": 0.9710817565155302, "percentage": 32.37, "elapsed_time": "13:56:40", "remaining_time": "1 day, 5:08:06", "throughput": 54452.06, "total_tokens": 2733528704} {"current_steps": 8170, "total_steps": 25209, "loss": 0.3548, "lr": 3.709407040069233e-05, "epoch": 0.9722718076877306, "percentage": 32.41, "elapsed_time": "13:57:40", "remaining_time": "1 day, 5:07:00", "throughput": 54452.74, "total_tokens": 2736801280} {"current_steps": 8180, "total_steps": 25209, "loss": 0.3541, "lr": 3.708386654651179e-05, "epoch": 0.973461858859931, "percentage": 32.45, "elapsed_time": "13:58:38", "remaining_time": "1 day, 5:05:52", "throughput": 54456.83, "total_tokens": 2740203008} {"current_steps": 8190, "total_steps": 25209, "loss": 0.3524, "lr": 3.707367110834409e-05, "epoch": 0.9746519100321314, "percentage": 32.49, "elapsed_time": "13:59:44", "remaining_time": "1 day, 5:05:00", "throughput": 54452.94, "total_tokens": 2743590528} {"current_steps": 8200, "total_steps": 25209, "loss": 0.3537, "lr": 3.7063484074626555e-05, "epoch": 0.9758419612043318, "percentage": 32.53, "elapsed_time": "14:00:35", "remaining_time": "1 day, 5:03:37", "throughput": 54465.16, "total_tokens": 2746994176} {"current_steps": 8210, "total_steps": 25209, "loss": 0.3554, "lr": 3.7053305433818725e-05, "epoch": 0.9770320123765321, "percentage": 32.57, "elapsed_time": "14:01:26", "remaining_time": "1 day, 5:02:12", "throughput": 54476.97, "total_tokens": 2750329344} {"current_steps": 8220, "total_steps": 25209, "loss": 0.3599, "lr": 3.704313517440232e-05, "epoch": 0.9782220635487326, "percentage": 32.61, "elapsed_time": "14:02:11", "remaining_time": "1 day, 5:00:38", "throughput": 54492.14, "total_tokens": 2753573248} {"current_steps": 8230, "total_steps": 25209, "loss": 0.3592, "lr": 3.703297328488118e-05, "epoch": 0.979412114720933, "percentage": 32.65, "elapsed_time": "14:03:01", "remaining_time": "1 day, 4:59:11", "throughput": 54505.3, "total_tokens": 2756934912} {"current_steps": 8240, "total_steps": 25209, "loss": 0.3592, "lr": 3.70228197537812e-05, "epoch": 0.9806021658931334, "percentage": 32.69, "elapsed_time": "14:03:51", "remaining_time": "1 day, 4:57:47", "throughput": 54518.78, "total_tokens": 2760355840} {"current_steps": 8250, "total_steps": 25209, "loss": 0.3537, "lr": 3.7012674569650305e-05, "epoch": 0.9817922170653338, "percentage": 32.73, "elapsed_time": "14:04:40", "remaining_time": "1 day, 4:56:20", "throughput": 54531.6, "total_tokens": 2763686912} {"current_steps": 8260, "total_steps": 25209, "loss": 0.3621, "lr": 3.700253772105835e-05, "epoch": 0.9829822682375342, "percentage": 32.77, "elapsed_time": "14:05:27", "remaining_time": "1 day, 4:54:50", "throughput": 54546.51, "total_tokens": 2767026816} {"current_steps": 8270, "total_steps": 25209, "loss": 0.353, "lr": 3.699240919659711e-05, "epoch": 0.9841723194097346, "percentage": 32.81, "elapsed_time": "14:06:14", "remaining_time": "1 day, 4:53:18", "throughput": 54560.5, "total_tokens": 2770289664} {"current_steps": 8280, "total_steps": 25209, "loss": 0.3606, "lr": 3.698228898488019e-05, "epoch": 0.985362370581935, "percentage": 32.85, "elapsed_time": "14:07:05", "remaining_time": "1 day, 4:51:56", "throughput": 54572.85, "total_tokens": 2773700992} {"current_steps": 8290, "total_steps": 25209, "loss": 0.3583, "lr": 3.6972177074543e-05, "epoch": 0.9865524217541354, "percentage": 32.89, "elapsed_time": "14:07:56", "remaining_time": "1 day, 4:50:34", "throughput": 54583.99, "total_tokens": 2777057536} {"current_steps": 8300, "total_steps": 25209, "loss": 0.3543, "lr": 3.69620734542427e-05, "epoch": 0.9877424729263359, "percentage": 32.92, "elapsed_time": "14:08:45", "remaining_time": "1 day, 4:49:06", "throughput": 54596.1, "total_tokens": 2780328320} {"current_steps": 8310, "total_steps": 25209, "loss": 0.3563, "lr": 3.695197811265811e-05, "epoch": 0.9889325240985363, "percentage": 32.96, "elapsed_time": "14:09:37", "remaining_time": "1 day, 4:47:46", "throughput": 54604.23, "total_tokens": 2783599744} {"current_steps": 8320, "total_steps": 25209, "loss": 0.3581, "lr": 3.6941891038489694e-05, "epoch": 0.9901225752707367, "percentage": 33.0, "elapsed_time": "14:10:28", "remaining_time": "1 day, 4:46:23", "throughput": 54614.27, "total_tokens": 2786870528} {"current_steps": 8330, "total_steps": 25209, "loss": 0.3559, "lr": 3.693181222045952e-05, "epoch": 0.991312626442937, "percentage": 33.04, "elapsed_time": "14:11:22", "remaining_time": "1 day, 4:45:07", "throughput": 54621.36, "total_tokens": 2790171008} {"current_steps": 8340, "total_steps": 25209, "loss": 0.3592, "lr": 3.692174164731113e-05, "epoch": 0.9925026776151374, "percentage": 33.08, "elapsed_time": "14:12:09", "remaining_time": "1 day, 4:43:38", "throughput": 54634.5, "total_tokens": 2793451264} {"current_steps": 8350, "total_steps": 25209, "loss": 0.36, "lr": 3.6911679307809595e-05, "epoch": 0.9936927287873378, "percentage": 33.12, "elapsed_time": "14:13:01", "remaining_time": "1 day, 4:42:17", "throughput": 54645.27, "total_tokens": 2796824320} {"current_steps": 8360, "total_steps": 25209, "loss": 0.3564, "lr": 3.690162519074137e-05, "epoch": 0.9948827799595382, "percentage": 33.16, "elapsed_time": "14:13:52", "remaining_time": "1 day, 4:40:55", "throughput": 54657.81, "total_tokens": 2800242560} {"current_steps": 8370, "total_steps": 25209, "loss": 0.3558, "lr": 3.689157928491431e-05, "epoch": 0.9960728311317386, "percentage": 33.2, "elapsed_time": "14:14:42", "remaining_time": "1 day, 4:39:30", "throughput": 54669.42, "total_tokens": 2803560192} {"current_steps": 8380, "total_steps": 25209, "loss": 0.3526, "lr": 3.6881541579157566e-05, "epoch": 0.9972628823039391, "percentage": 33.24, "elapsed_time": "14:15:31", "remaining_time": "1 day, 4:38:05", "throughput": 54682.9, "total_tokens": 2806937728} {"current_steps": 8390, "total_steps": 25209, "loss": 0.3601, "lr": 3.687151206232154e-05, "epoch": 0.9984529334761395, "percentage": 33.28, "elapsed_time": "14:16:24", "remaining_time": "1 day, 4:36:46", "throughput": 54693.88, "total_tokens": 2810393856} {"current_steps": 8400, "total_steps": 25209, "loss": 0.3601, "lr": 3.686149072327788e-05, "epoch": 0.9996429846483399, "percentage": 33.32, "elapsed_time": "14:17:14", "remaining_time": "1 day, 4:35:24", "throughput": 54706.72, "total_tokens": 2813815296} {"current_steps": 8410, "total_steps": 25209, "loss": 0.3452, "lr": 3.685147755091937e-05, "epoch": 1.0008330358205402, "percentage": 33.36, "elapsed_time": "14:18:05", "remaining_time": "1 day, 4:34:02", "throughput": 54718.71, "total_tokens": 2817225344} {"current_steps": 8420, "total_steps": 25209, "loss": 0.3379, "lr": 3.684147253415992e-05, "epoch": 1.0020230869927407, "percentage": 33.4, "elapsed_time": "14:18:54", "remaining_time": "1 day, 4:32:36", "throughput": 54733.49, "total_tokens": 2820643584} {"current_steps": 8430, "total_steps": 25209, "loss": 0.3397, "lr": 3.683147566193448e-05, "epoch": 1.0032131381649412, "percentage": 33.44, "elapsed_time": "14:19:44", "remaining_time": "1 day, 4:31:13", "throughput": 54746.38, "total_tokens": 2824062336} {"current_steps": 8440, "total_steps": 25209, "loss": 0.3406, "lr": 3.6821486923199025e-05, "epoch": 1.0044031893371415, "percentage": 33.48, "elapsed_time": "14:20:32", "remaining_time": "1 day, 4:29:46", "throughput": 54758.7, "total_tokens": 2827339136} {"current_steps": 8450, "total_steps": 25209, "loss": 0.3432, "lr": 3.681150630693046e-05, "epoch": 1.005593240509342, "percentage": 33.52, "elapsed_time": "14:21:27", "remaining_time": "1 day, 4:28:32", "throughput": 54765.92, "total_tokens": 2830702976} {"current_steps": 8460, "total_steps": 25209, "loss": 0.3403, "lr": 3.6801533802126615e-05, "epoch": 1.0067832916815422, "percentage": 33.56, "elapsed_time": "14:22:28", "remaining_time": "1 day, 4:27:31", "throughput": 54769.19, "total_tokens": 2834240768} {"current_steps": 8470, "total_steps": 25209, "loss": 0.3386, "lr": 3.679156939780617e-05, "epoch": 1.0079733428537427, "percentage": 33.6, "elapsed_time": "14:23:28", "remaining_time": "1 day, 4:26:28", "throughput": 54769.84, "total_tokens": 2837563776} {"current_steps": 8480, "total_steps": 25209, "loss": 0.3349, "lr": 3.6781613083008594e-05, "epoch": 1.009163394025943, "percentage": 33.64, "elapsed_time": "14:24:34", "remaining_time": "1 day, 4:25:36", "throughput": 54766.65, "total_tokens": 2841009408} {"current_steps": 8490, "total_steps": 25209, "loss": 0.3399, "lr": 3.677166484679412e-05, "epoch": 1.0103534451981435, "percentage": 33.68, "elapsed_time": "14:25:29", "remaining_time": "1 day, 4:24:22", "throughput": 54772.06, "total_tokens": 2844289792} {"current_steps": 8500, "total_steps": 25209, "loss": 0.3421, "lr": 3.676172467824368e-05, "epoch": 1.011543496370344, "percentage": 33.72, "elapsed_time": "14:26:17", "remaining_time": "1 day, 4:22:55", "throughput": 54783.67, "total_tokens": 2847522560} {"current_steps": 8510, "total_steps": 25209, "loss": 0.3388, "lr": 3.675179256645885e-05, "epoch": 1.0127335475425443, "percentage": 33.76, "elapsed_time": "14:27:08", "remaining_time": "1 day, 4:21:33", "throughput": 54795.61, "total_tokens": 2850912000} {"current_steps": 8520, "total_steps": 25209, "loss": 0.337, "lr": 3.674186850056181e-05, "epoch": 1.0139235987147448, "percentage": 33.8, "elapsed_time": "14:27:55", "remaining_time": "1 day, 4:20:05", "throughput": 54810.14, "total_tokens": 2854256896} {"current_steps": 8530, "total_steps": 25209, "loss": 0.3405, "lr": 3.67319524696953e-05, "epoch": 1.015113649886945, "percentage": 33.84, "elapsed_time": "14:28:42", "remaining_time": "1 day, 4:18:37", "throughput": 54824.91, "total_tokens": 2857616000} {"current_steps": 8540, "total_steps": 25209, "loss": 0.3394, "lr": 3.6722044463022536e-05, "epoch": 1.0163037010591456, "percentage": 33.88, "elapsed_time": "14:29:32", "remaining_time": "1 day, 4:17:14", "throughput": 54836.96, "total_tokens": 2861003264} {"current_steps": 8550, "total_steps": 25209, "loss": 0.3426, "lr": 3.6712144469727214e-05, "epoch": 1.0174937522313459, "percentage": 33.92, "elapsed_time": "14:30:22", "remaining_time": "1 day, 4:15:51", "throughput": 54849.65, "total_tokens": 2864394880} {"current_steps": 8560, "total_steps": 25209, "loss": 0.336, "lr": 3.67022524790134e-05, "epoch": 1.0186838034035464, "percentage": 33.96, "elapsed_time": "14:31:11", "remaining_time": "1 day, 4:14:26", "throughput": 54862.91, "total_tokens": 2867750784} {"current_steps": 8570, "total_steps": 25209, "loss": 0.3407, "lr": 3.6692368480105546e-05, "epoch": 1.0198738545757469, "percentage": 34.0, "elapsed_time": "14:31:59", "remaining_time": "1 day, 4:13:00", "throughput": 54875.15, "total_tokens": 2871054464} {"current_steps": 8580, "total_steps": 25209, "loss": 0.3359, "lr": 3.6682492462248374e-05, "epoch": 1.0210639057479471, "percentage": 34.04, "elapsed_time": "14:32:48", "remaining_time": "1 day, 4:11:36", "throughput": 54887.94, "total_tokens": 2874423424} {"current_steps": 8590, "total_steps": 25209, "loss": 0.3379, "lr": 3.667262441470689e-05, "epoch": 1.0222539569201476, "percentage": 34.08, "elapsed_time": "14:33:35", "remaining_time": "1 day, 4:10:07", "throughput": 54902.23, "total_tokens": 2877731712} {"current_steps": 8600, "total_steps": 25209, "loss": 0.3396, "lr": 3.6662764326766255e-05, "epoch": 1.023444008092348, "percentage": 34.11, "elapsed_time": "14:34:23", "remaining_time": "1 day, 4:08:41", "throughput": 54916.3, "total_tokens": 2881094656} {"current_steps": 8610, "total_steps": 25209, "loss": 0.3424, "lr": 3.665291218773185e-05, "epoch": 1.0246340592645484, "percentage": 34.15, "elapsed_time": "14:35:11", "remaining_time": "1 day, 4:07:15", "throughput": 54929.64, "total_tokens": 2884445952} {"current_steps": 8620, "total_steps": 25209, "loss": 0.3397, "lr": 3.664306798692912e-05, "epoch": 1.0258241104367487, "percentage": 34.19, "elapsed_time": "14:36:01", "remaining_time": "1 day, 4:05:53", "throughput": 54943.75, "total_tokens": 2887927680} {"current_steps": 8630, "total_steps": 25209, "loss": 0.3377, "lr": 3.6633231713703576e-05, "epoch": 1.0270141616089492, "percentage": 34.23, "elapsed_time": "14:36:52", "remaining_time": "1 day, 4:04:32", "throughput": 54954.65, "total_tokens": 2891291008} {"current_steps": 8640, "total_steps": 25209, "loss": 0.3388, "lr": 3.6623403357420745e-05, "epoch": 1.0282042127811495, "percentage": 34.27, "elapsed_time": "14:37:41", "remaining_time": "1 day, 4:03:08", "throughput": 54967.96, "total_tokens": 2894676480} {"current_steps": 8650, "total_steps": 25209, "loss": 0.3438, "lr": 3.661358290746611e-05, "epoch": 1.02939426395335, "percentage": 34.31, "elapsed_time": "14:38:31", "remaining_time": "1 day, 4:01:47", "throughput": 54980.36, "total_tokens": 2898084480} {"current_steps": 8660, "total_steps": 25209, "loss": 0.3351, "lr": 3.6603770353245056e-05, "epoch": 1.0305843151255505, "percentage": 34.35, "elapsed_time": "14:39:18", "remaining_time": "1 day, 4:00:19", "throughput": 54993.86, "total_tokens": 2901378048} {"current_steps": 8670, "total_steps": 25209, "loss": 0.3427, "lr": 3.659396568418286e-05, "epoch": 1.0317743662977508, "percentage": 34.39, "elapsed_time": "14:40:07", "remaining_time": "1 day, 3:58:55", "throughput": 55006.74, "total_tokens": 2904746880} {"current_steps": 8680, "total_steps": 25209, "loss": 0.3377, "lr": 3.658416888972459e-05, "epoch": 1.0329644174699513, "percentage": 34.43, "elapsed_time": "14:40:55", "remaining_time": "1 day, 3:57:30", "throughput": 55019.1, "total_tokens": 2908061440} {"current_steps": 8690, "total_steps": 25209, "loss": 0.3385, "lr": 3.6574379959335106e-05, "epoch": 1.0341544686421515, "percentage": 34.47, "elapsed_time": "14:41:41", "remaining_time": "1 day, 3:56:00", "throughput": 55034.9, "total_tokens": 2911405312} {"current_steps": 8700, "total_steps": 25209, "loss": 0.3414, "lr": 3.6564598882498976e-05, "epoch": 1.035344519814352, "percentage": 34.51, "elapsed_time": "14:42:28", "remaining_time": "1 day, 3:54:35", "throughput": 55048.04, "total_tokens": 2914736000} {"current_steps": 8710, "total_steps": 25209, "loss": 0.3407, "lr": 3.655482564872043e-05, "epoch": 1.0365345709865523, "percentage": 34.55, "elapsed_time": "14:43:21", "remaining_time": "1 day, 3:53:17", "throughput": 55058.04, "total_tokens": 2918141312} {"current_steps": 8720, "total_steps": 25209, "loss": 0.339, "lr": 3.654506024752336e-05, "epoch": 1.0377246221587528, "percentage": 34.59, "elapsed_time": "14:44:09", "remaining_time": "1 day, 3:51:53", "throughput": 55070.73, "total_tokens": 2921475840} {"current_steps": 8730, "total_steps": 25209, "loss": 0.3385, "lr": 3.653530266845121e-05, "epoch": 1.0389146733309533, "percentage": 34.63, "elapsed_time": "14:45:01", "remaining_time": "1 day, 3:50:36", "throughput": 55081.0, "total_tokens": 2924890624} {"current_steps": 8740, "total_steps": 25209, "loss": 0.3393, "lr": 3.652555290106696e-05, "epoch": 1.0401047245031536, "percentage": 34.67, "elapsed_time": "14:45:51", "remaining_time": "1 day, 3:49:14", "throughput": 55092.53, "total_tokens": 2928246016} {"current_steps": 8750, "total_steps": 25209, "loss": 0.3357, "lr": 3.6515810934953084e-05, "epoch": 1.0412947756753541, "percentage": 34.71, "elapsed_time": "14:46:40", "remaining_time": "1 day, 3:47:51", "throughput": 55105.13, "total_tokens": 2931614336} {"current_steps": 8760, "total_steps": 25209, "loss": 0.3424, "lr": 3.650607675971151e-05, "epoch": 1.0424848268475544, "percentage": 34.75, "elapsed_time": "14:47:29", "remaining_time": "1 day, 3:46:29", "throughput": 55117.1, "total_tokens": 2934969984} {"current_steps": 8770, "total_steps": 25209, "loss": 0.3395, "lr": 3.649635036496351e-05, "epoch": 1.043674878019755, "percentage": 34.79, "elapsed_time": "14:48:24", "remaining_time": "1 day, 3:45:17", "throughput": 55125.15, "total_tokens": 2938427264} {"current_steps": 8780, "total_steps": 25209, "loss": 0.3393, "lr": 3.6486631740349746e-05, "epoch": 1.0448649291919552, "percentage": 34.83, "elapsed_time": "14:49:12", "remaining_time": "1 day, 3:43:51", "throughput": 55138.73, "total_tokens": 2941775104} {"current_steps": 8790, "total_steps": 25209, "loss": 0.3432, "lr": 3.647692087553018e-05, "epoch": 1.0460549803641557, "percentage": 34.87, "elapsed_time": "14:50:05", "remaining_time": "1 day, 3:42:36", "throughput": 55148.32, "total_tokens": 2945203072} {"current_steps": 8800, "total_steps": 25209, "loss": 0.3407, "lr": 3.6467217760184005e-05, "epoch": 1.047245031536356, "percentage": 34.91, "elapsed_time": "14:50:57", "remaining_time": "1 day, 3:41:20", "throughput": 55157.16, "total_tokens": 2948576896} {"current_steps": 8810, "total_steps": 25209, "loss": 0.3385, "lr": 3.6457522384009625e-05, "epoch": 1.0484350827085565, "percentage": 34.95, "elapsed_time": "14:51:51", "remaining_time": "1 day, 3:40:06", "throughput": 55164.11, "total_tokens": 2951905664} {"current_steps": 8820, "total_steps": 25209, "loss": 0.3357, "lr": 3.644783473672462e-05, "epoch": 1.049625133880757, "percentage": 34.99, "elapsed_time": "14:52:46", "remaining_time": "1 day, 3:38:54", "throughput": 55169.2, "total_tokens": 2955195008} {"current_steps": 8830, "total_steps": 25209, "loss": 0.3386, "lr": 3.643815480806568e-05, "epoch": 1.0508151850529572, "percentage": 35.03, "elapsed_time": "14:53:39", "remaining_time": "1 day, 3:37:39", "throughput": 55177.36, "total_tokens": 2958569088} {"current_steps": 8840, "total_steps": 25209, "loss": 0.3378, "lr": 3.6428482587788555e-05, "epoch": 1.0520052362251577, "percentage": 35.07, "elapsed_time": "14:54:27", "remaining_time": "1 day, 3:36:16", "throughput": 55189.94, "total_tokens": 2961931776} {"current_steps": 8850, "total_steps": 25209, "loss": 0.3393, "lr": 3.641881806566803e-05, "epoch": 1.053195287397358, "percentage": 35.11, "elapsed_time": "14:55:17", "remaining_time": "1 day, 3:34:56", "throughput": 55201.49, "total_tokens": 2965312256} {"current_steps": 8860, "total_steps": 25209, "loss": 0.3353, "lr": 3.640916123149788e-05, "epoch": 1.0543853385695585, "percentage": 35.15, "elapsed_time": "14:56:07", "remaining_time": "1 day, 3:33:34", "throughput": 55212.16, "total_tokens": 2968617088} {"current_steps": 8870, "total_steps": 25209, "loss": 0.3371, "lr": 3.639951207509079e-05, "epoch": 1.0555753897417588, "percentage": 35.19, "elapsed_time": "14:56:55", "remaining_time": "1 day, 3:32:10", "throughput": 55226.14, "total_tokens": 2972012672} {"current_steps": 8880, "total_steps": 25209, "loss": 0.3432, "lr": 3.6389870586278333e-05, "epoch": 1.0567654409139593, "percentage": 35.23, "elapsed_time": "14:57:44", "remaining_time": "1 day, 3:30:49", "throughput": 55237.77, "total_tokens": 2975375616} {"current_steps": 8890, "total_steps": 25209, "loss": 0.3397, "lr": 3.6380236754910965e-05, "epoch": 1.0579554920861598, "percentage": 35.27, "elapsed_time": "14:58:32", "remaining_time": "1 day, 3:29:25", "throughput": 55251.07, "total_tokens": 2978744064} {"current_steps": 8900, "total_steps": 25209, "loss": 0.3384, "lr": 3.6370610570857897e-05, "epoch": 1.05914554325836, "percentage": 35.3, "elapsed_time": "14:59:20", "remaining_time": "1 day, 3:28:00", "throughput": 55263.62, "total_tokens": 2982048896} {"current_steps": 8910, "total_steps": 25209, "loss": 0.3381, "lr": 3.6360992024007114e-05, "epoch": 1.0603355944305606, "percentage": 35.34, "elapsed_time": "15:00:08", "remaining_time": "1 day, 3:26:37", "throughput": 55276.14, "total_tokens": 2985382400} {"current_steps": 8920, "total_steps": 25209, "loss": 0.3418, "lr": 3.6351381104265304e-05, "epoch": 1.0615256456027609, "percentage": 35.38, "elapsed_time": "15:00:56", "remaining_time": "1 day, 3:25:14", "throughput": 55289.98, "total_tokens": 2988793088} {"current_steps": 8930, "total_steps": 25209, "loss": 0.3437, "lr": 3.634177780155783e-05, "epoch": 1.0627156967749614, "percentage": 35.42, "elapsed_time": "15:01:47", "remaining_time": "1 day, 3:23:54", "throughput": 55300.36, "total_tokens": 2992142464} {"current_steps": 8940, "total_steps": 25209, "loss": 0.3383, "lr": 3.633218210582867e-05, "epoch": 1.0639057479471616, "percentage": 35.46, "elapsed_time": "15:02:35", "remaining_time": "1 day, 3:22:32", "throughput": 55311.99, "total_tokens": 2995474176} {"current_steps": 8950, "total_steps": 25209, "loss": 0.3366, "lr": 3.6322594007040376e-05, "epoch": 1.0650957991193621, "percentage": 35.5, "elapsed_time": "15:03:29", "remaining_time": "1 day, 3:21:20", "throughput": 55321.76, "total_tokens": 2998986368} {"current_steps": 8960, "total_steps": 25209, "loss": 0.338, "lr": 3.631301349517403e-05, "epoch": 1.0662858502915626, "percentage": 35.54, "elapsed_time": "15:04:15", "remaining_time": "1 day, 3:19:53", "throughput": 55335.32, "total_tokens": 3002270464} {"current_steps": 8970, "total_steps": 25209, "loss": 0.3356, "lr": 3.6303440560229216e-05, "epoch": 1.067475901463763, "percentage": 35.58, "elapsed_time": "15:05:04", "remaining_time": "1 day, 3:18:30", "throughput": 55348.15, "total_tokens": 3005628544} {"current_steps": 8980, "total_steps": 25209, "loss": 0.3381, "lr": 3.629387519222395e-05, "epoch": 1.0686659526359634, "percentage": 35.62, "elapsed_time": "15:05:52", "remaining_time": "1 day, 3:17:08", "throughput": 55359.72, "total_tokens": 3008949504} {"current_steps": 8990, "total_steps": 25209, "loss": 0.3413, "lr": 3.628431738119464e-05, "epoch": 1.0698560038081637, "percentage": 35.66, "elapsed_time": "15:06:42", "remaining_time": "1 day, 3:15:47", "throughput": 55371.5, "total_tokens": 3012335488} {"current_steps": 9000, "total_steps": 25209, "loss": 0.3403, "lr": 3.62747671171961e-05, "epoch": 1.0710460549803642, "percentage": 35.7, "elapsed_time": "15:07:28", "remaining_time": "1 day, 3:14:21", "throughput": 55384.94, "total_tokens": 3015605888} {"current_steps": 9010, "total_steps": 25209, "loss": 0.3376, "lr": 3.626522439030138e-05, "epoch": 1.0722361061525645, "percentage": 35.74, "elapsed_time": "15:08:14", "remaining_time": "1 day, 3:12:54", "throughput": 55399.05, "total_tokens": 3018917632} {"current_steps": 9020, "total_steps": 25209, "loss": 0.3388, "lr": 3.6255689190601863e-05, "epoch": 1.073426157324765, "percentage": 35.78, "elapsed_time": "15:09:00", "remaining_time": "1 day, 3:11:28", "throughput": 55411.51, "total_tokens": 3022153984} {"current_steps": 9030, "total_steps": 25209, "loss": 0.3376, "lr": 3.624616150820714e-05, "epoch": 1.0746162084969653, "percentage": 35.82, "elapsed_time": "15:09:46", "remaining_time": "1 day, 3:10:02", "throughput": 55424.76, "total_tokens": 3025463168} {"current_steps": 9040, "total_steps": 25209, "loss": 0.3393, "lr": 3.623664133324499e-05, "epoch": 1.0758062596691658, "percentage": 35.86, "elapsed_time": "15:10:33", "remaining_time": "1 day, 3:08:38", "throughput": 55438.28, "total_tokens": 3028813312} {"current_steps": 9050, "total_steps": 25209, "loss": 0.343, "lr": 3.622712865586131e-05, "epoch": 1.0769963108413663, "percentage": 35.9, "elapsed_time": "15:11:21", "remaining_time": "1 day, 3:07:15", "throughput": 55451.01, "total_tokens": 3032158592} {"current_steps": 9060, "total_steps": 25209, "loss": 0.338, "lr": 3.621762346622014e-05, "epoch": 1.0781863620135665, "percentage": 35.94, "elapsed_time": "15:12:08", "remaining_time": "1 day, 3:05:50", "throughput": 55463.8, "total_tokens": 3035439872} {"current_steps": 9070, "total_steps": 25209, "loss": 0.3414, "lr": 3.620812575450352e-05, "epoch": 1.079376413185767, "percentage": 35.98, "elapsed_time": "15:12:57", "remaining_time": "1 day, 3:04:30", "throughput": 55473.46, "total_tokens": 3038716800} {"current_steps": 9080, "total_steps": 25209, "loss": 0.3379, "lr": 3.6198635510911556e-05, "epoch": 1.0805664643579673, "percentage": 36.02, "elapsed_time": "15:13:45", "remaining_time": "1 day, 3:03:08", "throughput": 55484.75, "total_tokens": 3042003200} {"current_steps": 9090, "total_steps": 25209, "loss": 0.3435, "lr": 3.618915272566228e-05, "epoch": 1.0817565155301678, "percentage": 36.06, "elapsed_time": "15:14:32", "remaining_time": "1 day, 3:01:44", "throughput": 55496.93, "total_tokens": 3045279616} {"current_steps": 9100, "total_steps": 25209, "loss": 0.3409, "lr": 3.6179677388991694e-05, "epoch": 1.082946566702368, "percentage": 36.1, "elapsed_time": "15:15:22", "remaining_time": "1 day, 3:00:24", "throughput": 55508.24, "total_tokens": 3048639232} {"current_steps": 9110, "total_steps": 25209, "loss": 0.3439, "lr": 3.617020949115366e-05, "epoch": 1.0841366178745686, "percentage": 36.14, "elapsed_time": "15:16:18", "remaining_time": "1 day, 2:59:17", "throughput": 55510.87, "total_tokens": 3051912192} {"current_steps": 9120, "total_steps": 25209, "loss": 0.3396, "lr": 3.6160749022419886e-05, "epoch": 1.085326669046769, "percentage": 36.18, "elapsed_time": "15:17:08", "remaining_time": "1 day, 2:57:57", "throughput": 55520.66, "total_tokens": 3055199488} {"current_steps": 9130, "total_steps": 25209, "loss": 0.3411, "lr": 3.6151295973079887e-05, "epoch": 1.0865167202189694, "percentage": 36.22, "elapsed_time": "15:17:59", "remaining_time": "1 day, 2:56:40", "throughput": 55530.51, "total_tokens": 3058578048} {"current_steps": 9140, "total_steps": 25209, "loss": 0.3376, "lr": 3.6141850333440934e-05, "epoch": 1.08770677139117, "percentage": 36.26, "elapsed_time": "15:18:50", "remaining_time": "1 day, 2:55:24", "throughput": 55541.35, "total_tokens": 3062010112} {"current_steps": 9150, "total_steps": 25209, "loss": 0.3373, "lr": 3.613241209382803e-05, "epoch": 1.0888968225633702, "percentage": 36.3, "elapsed_time": "15:19:38", "remaining_time": "1 day, 2:54:02", "throughput": 55554.9, "total_tokens": 3065419136} {"current_steps": 9160, "total_steps": 25209, "loss": 0.3363, "lr": 3.6122981244583834e-05, "epoch": 1.0900868737355707, "percentage": 36.34, "elapsed_time": "15:20:26", "remaining_time": "1 day, 2:52:41", "throughput": 55566.57, "total_tokens": 3068768768} {"current_steps": 9170, "total_steps": 25209, "loss": 0.3362, "lr": 3.6113557776068644e-05, "epoch": 1.091276924907771, "percentage": 36.38, "elapsed_time": "15:21:16", "remaining_time": "1 day, 2:51:22", "throughput": 55579.09, "total_tokens": 3072201344} {"current_steps": 9180, "total_steps": 25209, "loss": 0.3416, "lr": 3.6104141678660386e-05, "epoch": 1.0924669760799715, "percentage": 36.42, "elapsed_time": "15:21:59", "remaining_time": "1 day, 2:49:51", "throughput": 55594.12, "total_tokens": 3075422976} {"current_steps": 9190, "total_steps": 25209, "loss": 0.3381, "lr": 3.6094732942754487e-05, "epoch": 1.093657027252172, "percentage": 36.46, "elapsed_time": "15:22:46", "remaining_time": "1 day, 2:48:28", "throughput": 55606.31, "total_tokens": 3078722176} {"current_steps": 9200, "total_steps": 25209, "loss": 0.3384, "lr": 3.60853315587639e-05, "epoch": 1.0948470784243722, "percentage": 36.49, "elapsed_time": "15:23:34", "remaining_time": "1 day, 2:47:08", "throughput": 55618.45, "total_tokens": 3082093184} {"current_steps": 9210, "total_steps": 25209, "loss": 0.3393, "lr": 3.607593751711909e-05, "epoch": 1.0960371295965727, "percentage": 36.53, "elapsed_time": "15:24:22", "remaining_time": "1 day, 2:45:46", "throughput": 55631.27, "total_tokens": 3085460352} {"current_steps": 9220, "total_steps": 25209, "loss": 0.3404, "lr": 3.60665508082679e-05, "epoch": 1.097227180768773, "percentage": 36.57, "elapsed_time": "15:25:12", "remaining_time": "1 day, 2:44:27", "throughput": 55642.6, "total_tokens": 3088848000} {"current_steps": 9230, "total_steps": 25209, "loss": 0.3377, "lr": 3.6057171422675585e-05, "epoch": 1.0984172319409735, "percentage": 36.61, "elapsed_time": "15:26:02", "remaining_time": "1 day, 2:43:09", "throughput": 55654.41, "total_tokens": 3092272640} {"current_steps": 9240, "total_steps": 25209, "loss": 0.3349, "lr": 3.604779935082474e-05, "epoch": 1.0996072831131738, "percentage": 36.65, "elapsed_time": "15:26:51", "remaining_time": "1 day, 2:41:50", "throughput": 55665.38, "total_tokens": 3095626624} {"current_steps": 9250, "total_steps": 25209, "loss": 0.3372, "lr": 3.603843458321526e-05, "epoch": 1.1007973342853743, "percentage": 36.69, "elapsed_time": "15:27:41", "remaining_time": "1 day, 2:40:32", "throughput": 55675.77, "total_tokens": 3098992640} {"current_steps": 9260, "total_steps": 25209, "loss": 0.3412, "lr": 3.6029077110364355e-05, "epoch": 1.1019873854575746, "percentage": 36.73, "elapsed_time": "15:28:30", "remaining_time": "1 day, 2:39:12", "throughput": 55687.8, "total_tokens": 3102375040} {"current_steps": 9270, "total_steps": 25209, "loss": 0.3411, "lr": 3.60197269228064e-05, "epoch": 1.103177436629775, "percentage": 36.77, "elapsed_time": "15:29:16", "remaining_time": "1 day, 2:37:48", "throughput": 55700.41, "total_tokens": 3105668736} {"current_steps": 9280, "total_steps": 25209, "loss": 0.34, "lr": 3.601038401109299e-05, "epoch": 1.1043674878019756, "percentage": 36.81, "elapsed_time": "15:30:05", "remaining_time": "1 day, 2:36:28", "throughput": 55711.54, "total_tokens": 3108995072} {"current_steps": 9290, "total_steps": 25209, "loss": 0.338, "lr": 3.6001048365792846e-05, "epoch": 1.1055575389741759, "percentage": 36.85, "elapsed_time": "15:30:52", "remaining_time": "1 day, 2:35:07", "throughput": 55723.61, "total_tokens": 3112320000} {"current_steps": 9300, "total_steps": 25209, "loss": 0.3411, "lr": 3.599171997749182e-05, "epoch": 1.1067475901463764, "percentage": 36.89, "elapsed_time": "15:31:41", "remaining_time": "1 day, 2:33:47", "throughput": 55734.97, "total_tokens": 3115675904} {"current_steps": 9310, "total_steps": 25209, "loss": 0.3377, "lr": 3.598239883679281e-05, "epoch": 1.1079376413185766, "percentage": 36.93, "elapsed_time": "15:32:31", "remaining_time": "1 day, 2:32:30", "throughput": 55744.5, "total_tokens": 3118989184} {"current_steps": 9320, "total_steps": 25209, "loss": 0.3377, "lr": 3.597308493431576e-05, "epoch": 1.1091276924907771, "percentage": 36.97, "elapsed_time": "15:33:24", "remaining_time": "1 day, 2:31:18", "throughput": 55750.52, "total_tokens": 3122301440} {"current_steps": 9330, "total_steps": 25209, "loss": 0.3388, "lr": 3.596377826069758e-05, "epoch": 1.1103177436629774, "percentage": 37.01, "elapsed_time": "15:34:13", "remaining_time": "1 day, 2:29:58", "throughput": 55759.72, "total_tokens": 3125517696} {"current_steps": 9340, "total_steps": 25209, "loss": 0.3397, "lr": 3.5954478806592155e-05, "epoch": 1.111507794835178, "percentage": 37.05, "elapsed_time": "15:35:03", "remaining_time": "1 day, 2:28:41", "throughput": 55770.67, "total_tokens": 3128918912} {"current_steps": 9350, "total_steps": 25209, "loss": 0.3395, "lr": 3.594518656267024e-05, "epoch": 1.1126978460073782, "percentage": 37.09, "elapsed_time": "15:35:58", "remaining_time": "1 day, 2:27:33", "throughput": 55776.66, "total_tokens": 3132332928} {"current_steps": 9360, "total_steps": 25209, "loss": 0.34, "lr": 3.5935901519619496e-05, "epoch": 1.1138878971795787, "percentage": 37.13, "elapsed_time": "15:36:48", "remaining_time": "1 day, 2:26:16", "throughput": 55785.12, "total_tokens": 3135623552} {"current_steps": 9370, "total_steps": 25209, "loss": 0.3419, "lr": 3.5926623668144385e-05, "epoch": 1.1150779483517792, "percentage": 37.17, "elapsed_time": "15:37:36", "remaining_time": "1 day, 2:24:56", "throughput": 55795.61, "total_tokens": 3138877056} {"current_steps": 9380, "total_steps": 25209, "loss": 0.3428, "lr": 3.5917352998966194e-05, "epoch": 1.1162679995239795, "percentage": 37.21, "elapsed_time": "15:38:24", "remaining_time": "1 day, 2:23:34", "throughput": 55808.07, "total_tokens": 3142224640} {"current_steps": 9390, "total_steps": 25209, "loss": 0.3381, "lr": 3.5908089502822914e-05, "epoch": 1.11745805069618, "percentage": 37.25, "elapsed_time": "15:39:13", "remaining_time": "1 day, 2:22:17", "throughput": 55818.49, "total_tokens": 3145579904} {"current_steps": 9400, "total_steps": 25209, "loss": 0.3424, "lr": 3.589883317046929e-05, "epoch": 1.1186481018683803, "percentage": 37.29, "elapsed_time": "15:40:08", "remaining_time": "1 day, 2:21:08", "throughput": 55824.46, "total_tokens": 3148969088} {"current_steps": 9410, "total_steps": 25209, "loss": 0.343, "lr": 3.5889583992676715e-05, "epoch": 1.1198381530405808, "percentage": 37.33, "elapsed_time": "15:41:02", "remaining_time": "1 day, 2:19:57", "throughput": 55829.1, "total_tokens": 3152224384} {"current_steps": 9420, "total_steps": 25209, "loss": 0.3363, "lr": 3.5880341960233244e-05, "epoch": 1.1210282042127813, "percentage": 37.37, "elapsed_time": "15:42:00", "remaining_time": "1 day, 2:18:55", "throughput": 55829.85, "total_tokens": 3155548032} {"current_steps": 9430, "total_steps": 25209, "loss": 0.3383, "lr": 3.58711070639435e-05, "epoch": 1.1222182553849815, "percentage": 37.41, "elapsed_time": "15:43:13", "remaining_time": "1 day, 2:18:15", "throughput": 55816.61, "total_tokens": 3158834048} {"current_steps": 9440, "total_steps": 25209, "loss": 0.3392, "lr": 3.586187929462869e-05, "epoch": 1.123408306557182, "percentage": 37.45, "elapsed_time": "15:44:12", "remaining_time": "1 day, 2:17:14", "throughput": 55818.46, "total_tokens": 3162257408} {"current_steps": 9450, "total_steps": 25209, "loss": 0.3385, "lr": 3.585265864312651e-05, "epoch": 1.1245983577293823, "percentage": 37.49, "elapsed_time": "15:45:04", "remaining_time": "1 day, 2:16:01", "throughput": 55825.3, "total_tokens": 3165541248} {"current_steps": 9460, "total_steps": 25209, "loss": 0.3375, "lr": 3.584344510029118e-05, "epoch": 1.1257884089015828, "percentage": 37.53, "elapsed_time": "15:45:50", "remaining_time": "1 day, 2:14:37", "throughput": 55836.49, "total_tokens": 3168732032} {"current_steps": 9470, "total_steps": 25209, "loss": 0.3405, "lr": 3.583423865699333e-05, "epoch": 1.126978460073783, "percentage": 37.57, "elapsed_time": "15:46:35", "remaining_time": "1 day, 2:13:12", "throughput": 55849.8, "total_tokens": 3172002432} {"current_steps": 9480, "total_steps": 25209, "loss": 0.3395, "lr": 3.5825039304119994e-05, "epoch": 1.1281685112459836, "percentage": 37.61, "elapsed_time": "15:47:30", "remaining_time": "1 day, 2:12:04", "throughput": 55853.58, "total_tokens": 3175283712} {"current_steps": 9490, "total_steps": 25209, "loss": 0.3384, "lr": 3.581584703257461e-05, "epoch": 1.1293585624181839, "percentage": 37.65, "elapsed_time": "15:48:31", "remaining_time": "1 day, 2:11:07", "throughput": 55853.22, "total_tokens": 3178710016} {"current_steps": 9500, "total_steps": 25209, "loss": 0.3359, "lr": 3.580666183327689e-05, "epoch": 1.1305486135903844, "percentage": 37.68, "elapsed_time": "15:49:22", "remaining_time": "1 day, 2:09:51", "throughput": 55864.15, "total_tokens": 3182137600} {"current_steps": 9510, "total_steps": 25209, "loss": 0.3326, "lr": 3.5797483697162906e-05, "epoch": 1.131738664762585, "percentage": 37.72, "elapsed_time": "15:50:15", "remaining_time": "1 day, 2:08:39", "throughput": 55872.3, "total_tokens": 3185566848} {"current_steps": 9520, "total_steps": 25209, "loss": 0.3402, "lr": 3.5788312615184936e-05, "epoch": 1.1329287159347852, "percentage": 37.76, "elapsed_time": "15:51:01", "remaining_time": "1 day, 2:07:17", "throughput": 55884.51, "total_tokens": 3188846720} {"current_steps": 9530, "total_steps": 25209, "loss": 0.3358, "lr": 3.5779148578311476e-05, "epoch": 1.1341187671069857, "percentage": 37.8, "elapsed_time": "15:51:49", "remaining_time": "1 day, 2:05:57", "throughput": 55896.15, "total_tokens": 3192193792} {"current_steps": 9540, "total_steps": 25209, "loss": 0.3394, "lr": 3.5769991577527236e-05, "epoch": 1.135308818279186, "percentage": 37.84, "elapsed_time": "15:52:39", "remaining_time": "1 day, 2:04:41", "throughput": 55906.21, "total_tokens": 3195572992} {"current_steps": 9550, "total_steps": 25209, "loss": 0.3406, "lr": 3.5760841603833034e-05, "epoch": 1.1364988694513865, "percentage": 37.88, "elapsed_time": "15:53:28", "remaining_time": "1 day, 2:03:23", "throughput": 55917.66, "total_tokens": 3198940672} {"current_steps": 9560, "total_steps": 25209, "loss": 0.3353, "lr": 3.5751698648245814e-05, "epoch": 1.1376889206235867, "percentage": 37.92, "elapsed_time": "15:54:15", "remaining_time": "1 day, 2:02:03", "throughput": 55929.65, "total_tokens": 3202288000} {"current_steps": 9570, "total_steps": 25209, "loss": 0.3389, "lr": 3.574256270179857e-05, "epoch": 1.1388789717957872, "percentage": 37.96, "elapsed_time": "15:55:04", "remaining_time": "1 day, 2:00:44", "throughput": 55939.37, "total_tokens": 3205562752} {"current_steps": 9580, "total_steps": 25209, "loss": 0.3403, "lr": 3.573343375554037e-05, "epoch": 1.1400690229679875, "percentage": 38.0, "elapsed_time": "15:55:51", "remaining_time": "1 day, 1:59:24", "throughput": 55952.33, "total_tokens": 3208960128} {"current_steps": 9590, "total_steps": 25209, "loss": 0.3381, "lr": 3.572431180053621e-05, "epoch": 1.141259074140188, "percentage": 38.04, "elapsed_time": "15:56:38", "remaining_time": "1 day, 1:58:03", "throughput": 55964.12, "total_tokens": 3212259584} {"current_steps": 9600, "total_steps": 25209, "loss": 0.3361, "lr": 3.571519682786711e-05, "epoch": 1.1424491253123885, "percentage": 38.08, "elapsed_time": "15:57:27", "remaining_time": "1 day, 1:56:45", "throughput": 55975.21, "total_tokens": 3215620736} {"current_steps": 9610, "total_steps": 25209, "loss": 0.3401, "lr": 3.570608882862996e-05, "epoch": 1.1436391764845888, "percentage": 38.12, "elapsed_time": "15:58:16", "remaining_time": "1 day, 1:55:29", "throughput": 55985.27, "total_tokens": 3218978048} {"current_steps": 9620, "total_steps": 25209, "loss": 0.3397, "lr": 3.569698779393757e-05, "epoch": 1.1448292276567893, "percentage": 38.16, "elapsed_time": "15:59:06", "remaining_time": "1 day, 1:54:13", "throughput": 55995.63, "total_tokens": 3222365824} {"current_steps": 9630, "total_steps": 25209, "loss": 0.3405, "lr": 3.568789371491859e-05, "epoch": 1.1460192788289896, "percentage": 38.2, "elapsed_time": "15:59:54", "remaining_time": "1 day, 1:52:54", "throughput": 56007.27, "total_tokens": 3225720960} {"current_steps": 9640, "total_steps": 25209, "loss": 0.3385, "lr": 3.567880658271748e-05, "epoch": 1.14720933000119, "percentage": 38.24, "elapsed_time": "16:00:41", "remaining_time": "1 day, 1:51:32", "throughput": 56020.02, "total_tokens": 3229052160} {"current_steps": 9650, "total_steps": 25209, "loss": 0.3386, "lr": 3.566972638849445e-05, "epoch": 1.1483993811733906, "percentage": 38.28, "elapsed_time": "16:01:30", "remaining_time": "1 day, 1:50:16", "throughput": 56030.99, "total_tokens": 3232459648} {"current_steps": 9660, "total_steps": 25209, "loss": 0.3395, "lr": 3.566065312342551e-05, "epoch": 1.1495894323455909, "percentage": 38.32, "elapsed_time": "16:02:18", "remaining_time": "1 day, 1:48:58", "throughput": 56041.51, "total_tokens": 3235774592} {"current_steps": 9670, "total_steps": 25209, "loss": 0.3374, "lr": 3.565158677870231e-05, "epoch": 1.1507794835177914, "percentage": 38.36, "elapsed_time": "16:03:09", "remaining_time": "1 day, 1:47:43", "throughput": 56050.09, "total_tokens": 3239115264} {"current_steps": 9680, "total_steps": 25209, "loss": 0.3414, "lr": 3.564252734553221e-05, "epoch": 1.1519695346899916, "percentage": 38.4, "elapsed_time": "16:03:55", "remaining_time": "1 day, 1:46:21", "throughput": 56062.82, "total_tokens": 3242422144} {"current_steps": 9690, "total_steps": 25209, "loss": 0.3359, "lr": 3.563347481513818e-05, "epoch": 1.1531595858621921, "percentage": 38.44, "elapsed_time": "16:04:43", "remaining_time": "1 day, 1:45:03", "throughput": 56073.22, "total_tokens": 3245732096} {"current_steps": 9700, "total_steps": 25209, "loss": 0.3377, "lr": 3.56244291787588e-05, "epoch": 1.1543496370343924, "percentage": 38.48, "elapsed_time": "16:05:34", "remaining_time": "1 day, 1:43:50", "throughput": 56083.75, "total_tokens": 3249204736} {"current_steps": 9710, "total_steps": 25209, "loss": 0.3387, "lr": 3.5615390427648216e-05, "epoch": 1.155539688206593, "percentage": 38.52, "elapsed_time": "16:06:18", "remaining_time": "1 day, 1:42:25", "throughput": 56097.02, "total_tokens": 3252433408} {"current_steps": 9720, "total_steps": 25209, "loss": 0.3418, "lr": 3.5606358553076075e-05, "epoch": 1.1567297393787932, "percentage": 38.56, "elapsed_time": "16:07:06", "remaining_time": "1 day, 1:41:06", "throughput": 56107.79, "total_tokens": 3255731328} {"current_steps": 9730, "total_steps": 25209, "loss": 0.3397, "lr": 3.5597333546327526e-05, "epoch": 1.1579197905509937, "percentage": 38.6, "elapsed_time": "16:07:51", "remaining_time": "1 day, 1:39:43", "throughput": 56120.7, "total_tokens": 3259006848} {"current_steps": 9740, "total_steps": 25209, "loss": 0.3455, "lr": 3.5588315398703186e-05, "epoch": 1.1591098417231942, "percentage": 38.64, "elapsed_time": "16:08:39", "remaining_time": "1 day, 1:38:24", "throughput": 56132.06, "total_tokens": 3262348672} {"current_steps": 9750, "total_steps": 25209, "loss": 0.3379, "lr": 3.557930410151907e-05, "epoch": 1.1602998928953945, "percentage": 38.68, "elapsed_time": "16:09:26", "remaining_time": "1 day, 1:37:05", "throughput": 56141.98, "total_tokens": 3265599616} {"current_steps": 9760, "total_steps": 25209, "loss": 0.3381, "lr": 3.5570299646106606e-05, "epoch": 1.161489944067595, "percentage": 38.72, "elapsed_time": "16:10:18", "remaining_time": "1 day, 1:35:54", "throughput": 56148.47, "total_tokens": 3268901760} {"current_steps": 9770, "total_steps": 25209, "loss": 0.3422, "lr": 3.556130202381253e-05, "epoch": 1.1626799952397953, "percentage": 38.76, "elapsed_time": "16:11:18", "remaining_time": "1 day, 1:34:53", "throughput": 56148.8, "total_tokens": 3272242816} {"current_steps": 9780, "total_steps": 25209, "loss": 0.3349, "lr": 3.555231122599892e-05, "epoch": 1.1638700464119958, "percentage": 38.8, "elapsed_time": "16:12:10", "remaining_time": "1 day, 1:33:43", "throughput": 56156.89, "total_tokens": 3275675776} {"current_steps": 9790, "total_steps": 25209, "loss": 0.3407, "lr": 3.554332724404313e-05, "epoch": 1.165060097584196, "percentage": 38.84, "elapsed_time": "16:12:56", "remaining_time": "1 day, 1:32:21", "throughput": 56169.33, "total_tokens": 3278974464} {"current_steps": 9800, "total_steps": 25209, "loss": 0.3389, "lr": 3.553435006933777e-05, "epoch": 1.1662501487563965, "percentage": 38.88, "elapsed_time": "16:13:46", "remaining_time": "1 day, 1:31:06", "throughput": 56178.65, "total_tokens": 3282321792} {"current_steps": 9810, "total_steps": 25209, "loss": 0.3405, "lr": 3.5525379693290626e-05, "epoch": 1.1674401999285968, "percentage": 38.91, "elapsed_time": "16:14:35", "remaining_time": "1 day, 1:29:49", "throughput": 56188.73, "total_tokens": 3285640192} {"current_steps": 9820, "total_steps": 25209, "loss": 0.3373, "lr": 3.551641610732469e-05, "epoch": 1.1686302511007973, "percentage": 38.95, "elapsed_time": "16:15:23", "remaining_time": "1 day, 1:28:32", "throughput": 56199.19, "total_tokens": 3288973568} {"current_steps": 9830, "total_steps": 25209, "loss": 0.3388, "lr": 3.55074593028781e-05, "epoch": 1.1698203022729978, "percentage": 38.99, "elapsed_time": "16:16:11", "remaining_time": "1 day, 1:27:14", "throughput": 56210.36, "total_tokens": 3292317568} {"current_steps": 9840, "total_steps": 25209, "loss": 0.336, "lr": 3.5498509271404065e-05, "epoch": 1.171010353445198, "percentage": 39.03, "elapsed_time": "16:16:58", "remaining_time": "1 day, 1:25:55", "throughput": 56221.68, "total_tokens": 3295629312} {"current_steps": 9850, "total_steps": 25209, "loss": 0.3393, "lr": 3.5489566004370893e-05, "epoch": 1.1722004046173986, "percentage": 39.07, "elapsed_time": "16:17:45", "remaining_time": "1 day, 1:24:36", "throughput": 56232.28, "total_tokens": 3298888192} {"current_steps": 9860, "total_steps": 25209, "loss": 0.3382, "lr": 3.548062949326194e-05, "epoch": 1.1733904557895989, "percentage": 39.11, "elapsed_time": "16:18:33", "remaining_time": "1 day, 1:23:18", "throughput": 56243.98, "total_tokens": 3302279424} {"current_steps": 9870, "total_steps": 25209, "loss": 0.3386, "lr": 3.547169972957554e-05, "epoch": 1.1745805069617994, "percentage": 39.15, "elapsed_time": "16:19:23", "remaining_time": "1 day, 1:22:03", "throughput": 56254.21, "total_tokens": 3305667328} {"current_steps": 9880, "total_steps": 25209, "loss": 0.3357, "lr": 3.5462776704825e-05, "epoch": 1.1757705581339997, "percentage": 39.19, "elapsed_time": "16:20:08", "remaining_time": "1 day, 1:20:42", "throughput": 56265.24, "total_tokens": 3308892928} {"current_steps": 9890, "total_steps": 25209, "loss": 0.3367, "lr": 3.5453860410538594e-05, "epoch": 1.1769606093062002, "percentage": 39.23, "elapsed_time": "16:20:56", "remaining_time": "1 day, 1:19:24", "throughput": 56276.41, "total_tokens": 3312215552} {"current_steps": 9900, "total_steps": 25209, "loss": 0.3368, "lr": 3.5444950838259455e-05, "epoch": 1.1781506604784004, "percentage": 39.27, "elapsed_time": "16:21:46", "remaining_time": "1 day, 1:18:10", "throughput": 56286.36, "total_tokens": 3315622400} {"current_steps": 9910, "total_steps": 25209, "loss": 0.3343, "lr": 3.543604797954563e-05, "epoch": 1.179340711650601, "percentage": 39.31, "elapsed_time": "16:22:36", "remaining_time": "1 day, 1:16:57", "throughput": 56296.58, "total_tokens": 3319072640} {"current_steps": 9920, "total_steps": 25209, "loss": 0.335, "lr": 3.542715182596996e-05, "epoch": 1.1805307628228014, "percentage": 39.35, "elapsed_time": "16:23:24", "remaining_time": "1 day, 1:15:40", "throughput": 56307.99, "total_tokens": 3322450432} {"current_steps": 9930, "total_steps": 25209, "loss": 0.3372, "lr": 3.5418262369120115e-05, "epoch": 1.1817208139950017, "percentage": 39.39, "elapsed_time": "16:24:17", "remaining_time": "1 day, 1:14:29", "throughput": 56316.94, "total_tokens": 3325922944} {"current_steps": 9940, "total_steps": 25209, "loss": 0.337, "lr": 3.5409379600598526e-05, "epoch": 1.1829108651672022, "percentage": 39.43, "elapsed_time": "16:25:04", "remaining_time": "1 day, 1:13:11", "throughput": 56327.43, "total_tokens": 3329222656} {"current_steps": 9950, "total_steps": 25209, "loss": 0.3359, "lr": 3.540050351202235e-05, "epoch": 1.1841009163394025, "percentage": 39.47, "elapsed_time": "16:25:56", "remaining_time": "1 day, 1:12:01", "throughput": 56336.74, "total_tokens": 3332707200} {"current_steps": 9960, "total_steps": 25209, "loss": 0.3367, "lr": 3.539163409502347e-05, "epoch": 1.185290967511603, "percentage": 39.51, "elapsed_time": "16:26:47", "remaining_time": "1 day, 1:10:48", "throughput": 56347.88, "total_tokens": 3336215296} {"current_steps": 9970, "total_steps": 25209, "loss": 0.3391, "lr": 3.5382771341248416e-05, "epoch": 1.1864810186838035, "percentage": 39.55, "elapsed_time": "16:27:35", "remaining_time": "1 day, 1:09:30", "throughput": 56359.1, "total_tokens": 3339572096} {"current_steps": 9980, "total_steps": 25209, "loss": 0.3366, "lr": 3.537391524235835e-05, "epoch": 1.1876710698560038, "percentage": 39.59, "elapsed_time": "16:28:23", "remaining_time": "1 day, 1:08:13", "throughput": 56370.4, "total_tokens": 3342946944} {"current_steps": 9990, "total_steps": 25209, "loss": 0.3351, "lr": 3.5365065790029055e-05, "epoch": 1.1888611210282043, "percentage": 39.63, "elapsed_time": "16:29:10", "remaining_time": "1 day, 1:06:56", "throughput": 56381.98, "total_tokens": 3346309888} {"current_steps": 10000, "total_steps": 25209, "loss": 0.3376, "lr": 3.535622297595087e-05, "epoch": 1.1900511722004046, "percentage": 39.67, "elapsed_time": "16:29:59", "remaining_time": "1 day, 1:05:41", "throughput": 56391.34, "total_tokens": 3349634688} {"current_steps": 10000, "total_steps": 25209, "eval_loss": 0.3330932855606079, "epoch": 1.1900511722004046, "percentage": 39.67, "elapsed_time": "16:30:00", "remaining_time": "1 day, 1:05:42", "throughput": 56390.39, "total_tokens": 3349634688} {"current_steps": 10010, "total_steps": 25209, "loss": 0.3396, "lr": 3.534738679182869e-05, "epoch": 1.191241223372605, "percentage": 39.71, "elapsed_time": "16:31:01", "remaining_time": "1 day, 1:04:45", "throughput": 56389.84, "total_tokens": 3353023744} {"current_steps": 10020, "total_steps": 25209, "loss": 0.3419, "lr": 3.533855722938188e-05, "epoch": 1.1924312745448054, "percentage": 39.75, "elapsed_time": "16:31:51", "remaining_time": "1 day, 1:03:32", "throughput": 56398.61, "total_tokens": 3356384128} {"current_steps": 10030, "total_steps": 25209, "loss": 0.3398, "lr": 3.5329734280344325e-05, "epoch": 1.1936213257170059, "percentage": 39.79, "elapsed_time": "16:32:41", "remaining_time": "1 day, 1:02:17", "throughput": 56408.12, "total_tokens": 3359748992} {"current_steps": 10040, "total_steps": 25209, "loss": 0.3383, "lr": 3.5320917936464294e-05, "epoch": 1.1948113768892061, "percentage": 39.83, "elapsed_time": "16:33:31", "remaining_time": "1 day, 1:01:04", "throughput": 56416.06, "total_tokens": 3363049088} {"current_steps": 10050, "total_steps": 25209, "loss": 0.3359, "lr": 3.5312108189504505e-05, "epoch": 1.1960014280614066, "percentage": 39.87, "elapsed_time": "16:34:22", "remaining_time": "1 day, 0:59:52", "throughput": 56423.43, "total_tokens": 3366347264} {"current_steps": 10060, "total_steps": 25209, "loss": 0.3404, "lr": 3.530330503124204e-05, "epoch": 1.1971914792336071, "percentage": 39.91, "elapsed_time": "16:35:10", "remaining_time": "1 day, 0:58:36", "throughput": 56433.68, "total_tokens": 3369686784} {"current_steps": 10070, "total_steps": 25209, "loss": 0.3365, "lr": 3.5294508453468325e-05, "epoch": 1.1983815304058074, "percentage": 39.95, "elapsed_time": "16:36:00", "remaining_time": "1 day, 0:57:23", "throughput": 56441.16, "total_tokens": 3372970624} {"current_steps": 10080, "total_steps": 25209, "loss": 0.3385, "lr": 3.528571844798908e-05, "epoch": 1.199571581578008, "percentage": 39.99, "elapsed_time": "16:36:50", "remaining_time": "1 day, 0:56:08", "throughput": 56451.03, "total_tokens": 3376350720} {"current_steps": 10090, "total_steps": 25209, "loss": 0.3338, "lr": 3.527693500662431e-05, "epoch": 1.2007616327502082, "percentage": 40.03, "elapsed_time": "16:37:39", "remaining_time": "1 day, 0:54:53", "throughput": 56460.02, "total_tokens": 3379649408} {"current_steps": 10100, "total_steps": 25209, "loss": 0.3386, "lr": 3.5268158121208294e-05, "epoch": 1.2019516839224087, "percentage": 40.07, "elapsed_time": "16:38:25", "remaining_time": "1 day, 0:53:34", "throughput": 56471.7, "total_tokens": 3382961280} {"current_steps": 10110, "total_steps": 25209, "loss": 0.3362, "lr": 3.525938778358949e-05, "epoch": 1.203141735094609, "percentage": 40.1, "elapsed_time": "16:39:18", "remaining_time": "1 day, 0:52:26", "throughput": 56478.66, "total_tokens": 3386363648} {"current_steps": 10120, "total_steps": 25209, "loss": 0.3384, "lr": 3.5250623985630537e-05, "epoch": 1.2043317862668095, "percentage": 40.14, "elapsed_time": "16:40:06", "remaining_time": "1 day, 0:51:10", "throughput": 56488.63, "total_tokens": 3389699072} {"current_steps": 10130, "total_steps": 25209, "loss": 0.3374, "lr": 3.524186671920826e-05, "epoch": 1.2055218374390098, "percentage": 40.18, "elapsed_time": "16:40:55", "remaining_time": "1 day, 0:49:55", "throughput": 56499.4, "total_tokens": 3393094528} {"current_steps": 10140, "total_steps": 25209, "loss": 0.3392, "lr": 3.523311597621358e-05, "epoch": 1.2067118886112103, "percentage": 40.22, "elapsed_time": "16:41:45", "remaining_time": "1 day, 0:48:43", "throughput": 56507.06, "total_tokens": 3396406528} {"current_steps": 10150, "total_steps": 25209, "loss": 0.3373, "lr": 3.5224371748551505e-05, "epoch": 1.2079019397834108, "percentage": 40.26, "elapsed_time": "16:42:33", "remaining_time": "1 day, 0:47:26", "throughput": 56516.91, "total_tokens": 3399708416} {"current_steps": 10160, "total_steps": 25209, "loss": 0.3359, "lr": 3.521563402814109e-05, "epoch": 1.209091990955611, "percentage": 40.3, "elapsed_time": "16:43:24", "remaining_time": "1 day, 0:46:15", "throughput": 56526.45, "total_tokens": 3403164928} {"current_steps": 10170, "total_steps": 25209, "loss": 0.3398, "lr": 3.5206902806915436e-05, "epoch": 1.2102820421278115, "percentage": 40.34, "elapsed_time": "16:44:10", "remaining_time": "1 day, 0:44:55", "throughput": 56538.5, "total_tokens": 3406459136} {"current_steps": 10180, "total_steps": 25209, "loss": 0.3397, "lr": 3.5198178076821644e-05, "epoch": 1.2114720933000118, "percentage": 40.38, "elapsed_time": "16:44:57", "remaining_time": "1 day, 0:43:38", "throughput": 56549.0, "total_tokens": 3409750656} {"current_steps": 10190, "total_steps": 25209, "loss": 0.3371, "lr": 3.5189459829820743e-05, "epoch": 1.2126621444722123, "percentage": 40.42, "elapsed_time": "16:45:47", "remaining_time": "1 day, 0:42:25", "throughput": 56558.73, "total_tokens": 3413179392} {"current_steps": 10200, "total_steps": 25209, "loss": 0.3397, "lr": 3.5180748057887714e-05, "epoch": 1.2138521956444128, "percentage": 40.46, "elapsed_time": "16:46:35", "remaining_time": "1 day, 0:41:10", "throughput": 56568.83, "total_tokens": 3416504960} {"current_steps": 10210, "total_steps": 25209, "loss": 0.3386, "lr": 3.517204275301144e-05, "epoch": 1.215042246816613, "percentage": 40.5, "elapsed_time": "16:47:23", "remaining_time": "1 day, 0:39:53", "throughput": 56579.26, "total_tokens": 3419823872} {"current_steps": 10220, "total_steps": 25209, "loss": 0.3382, "lr": 3.5163343907194676e-05, "epoch": 1.2162322979888136, "percentage": 40.54, "elapsed_time": "16:48:12", "remaining_time": "1 day, 0:38:40", "throughput": 56589.44, "total_tokens": 3423234048} {"current_steps": 10230, "total_steps": 25209, "loss": 0.3379, "lr": 3.5154651512453995e-05, "epoch": 1.2174223491610139, "percentage": 40.58, "elapsed_time": "16:49:01", "remaining_time": "1 day, 0:37:25", "throughput": 56599.37, "total_tokens": 3426588288} {"current_steps": 10240, "total_steps": 25209, "loss": 0.3347, "lr": 3.514596556081981e-05, "epoch": 1.2186124003332144, "percentage": 40.62, "elapsed_time": "16:49:46", "remaining_time": "1 day, 0:36:06", "throughput": 56610.55, "total_tokens": 3429848960} {"current_steps": 10250, "total_steps": 25209, "loss": 0.335, "lr": 3.513728604433628e-05, "epoch": 1.2198024515054147, "percentage": 40.66, "elapsed_time": "16:50:35", "remaining_time": "1 day, 0:34:51", "throughput": 56621.72, "total_tokens": 3433259904} {"current_steps": 10260, "total_steps": 25209, "loss": 0.342, "lr": 3.5128612955061334e-05, "epoch": 1.2209925026776152, "percentage": 40.7, "elapsed_time": "16:51:22", "remaining_time": "1 day, 0:33:35", "throughput": 56632.54, "total_tokens": 3436602368} {"current_steps": 10270, "total_steps": 25209, "loss": 0.3387, "lr": 3.5119946285066595e-05, "epoch": 1.2221825538498154, "percentage": 40.74, "elapsed_time": "16:52:13", "remaining_time": "1 day, 0:32:25", "throughput": 56641.84, "total_tokens": 3440081280} {"current_steps": 10280, "total_steps": 25209, "loss": 0.3411, "lr": 3.511128602643739e-05, "epoch": 1.223372605022016, "percentage": 40.78, "elapsed_time": "16:53:02", "remaining_time": "1 day, 0:31:11", "throughput": 56651.03, "total_tokens": 3443409664} {"current_steps": 10290, "total_steps": 25209, "loss": 0.3387, "lr": 3.510263217127269e-05, "epoch": 1.2245626561942164, "percentage": 40.82, "elapsed_time": "16:53:51", "remaining_time": "1 day, 0:29:56", "throughput": 56660.44, "total_tokens": 3446725248} {"current_steps": 10300, "total_steps": 25209, "loss": 0.3385, "lr": 3.50939847116851e-05, "epoch": 1.2257527073664167, "percentage": 40.86, "elapsed_time": "16:54:41", "remaining_time": "1 day, 0:28:44", "throughput": 56668.38, "total_tokens": 3450055168} {"current_steps": 10310, "total_steps": 25209, "loss": 0.3354, "lr": 3.508534363980081e-05, "epoch": 1.2269427585386172, "percentage": 40.9, "elapsed_time": "16:55:28", "remaining_time": "1 day, 0:27:27", "throughput": 56678.47, "total_tokens": 3453319296} {"current_steps": 10320, "total_steps": 25209, "loss": 0.3388, "lr": 3.507670894775958e-05, "epoch": 1.2281328097108175, "percentage": 40.94, "elapsed_time": "16:56:16", "remaining_time": "1 day, 0:26:12", "throughput": 56688.35, "total_tokens": 3456655104} {"current_steps": 10330, "total_steps": 25209, "loss": 0.3378, "lr": 3.506808062771471e-05, "epoch": 1.229322860883018, "percentage": 40.98, "elapsed_time": "16:57:06", "remaining_time": "1 day, 0:25:00", "throughput": 56696.92, "total_tokens": 3459994112} {"current_steps": 10340, "total_steps": 25209, "loss": 0.3354, "lr": 3.505945867183298e-05, "epoch": 1.2305129120552183, "percentage": 41.02, "elapsed_time": "16:57:54", "remaining_time": "1 day, 0:23:45", "throughput": 56707.42, "total_tokens": 3463366528} {"current_steps": 10350, "total_steps": 25209, "loss": 0.3344, "lr": 3.505084307229468e-05, "epoch": 1.2317029632274188, "percentage": 41.06, "elapsed_time": "16:58:45", "remaining_time": "1 day, 0:22:35", "throughput": 56715.19, "total_tokens": 3466750336} {"current_steps": 10360, "total_steps": 25209, "loss": 0.3349, "lr": 3.5042233821293525e-05, "epoch": 1.232893014399619, "percentage": 41.1, "elapsed_time": "16:59:32", "remaining_time": "1 day, 0:21:18", "throughput": 56727.46, "total_tokens": 3470139392} {"current_steps": 10370, "total_steps": 25209, "loss": 0.3396, "lr": 3.503363091103664e-05, "epoch": 1.2340830655718196, "percentage": 41.14, "elapsed_time": "17:00:20", "remaining_time": "1 day, 0:20:04", "throughput": 56737.14, "total_tokens": 3473493376} {"current_steps": 10380, "total_steps": 25209, "loss": 0.3406, "lr": 3.5025034333744545e-05, "epoch": 1.23527311674402, "percentage": 41.18, "elapsed_time": "17:01:10", "remaining_time": "1 day, 0:18:52", "throughput": 56745.99, "total_tokens": 3476882816} {"current_steps": 10390, "total_steps": 25209, "loss": 0.3382, "lr": 3.501644408165112e-05, "epoch": 1.2364631679162204, "percentage": 41.22, "elapsed_time": "17:02:00", "remaining_time": "1 day, 0:17:39", "throughput": 56754.42, "total_tokens": 3480208512} {"current_steps": 10400, "total_steps": 25209, "loss": 0.3415, "lr": 3.500786014700357e-05, "epoch": 1.2376532190884209, "percentage": 41.26, "elapsed_time": "17:02:53", "remaining_time": "1 day, 0:16:32", "throughput": 56759.81, "total_tokens": 3483553024} {"current_steps": 10410, "total_steps": 25209, "loss": 0.3383, "lr": 3.499928252206237e-05, "epoch": 1.2388432702606211, "percentage": 41.29, "elapsed_time": "17:03:52", "remaining_time": "1 day, 0:15:33", "throughput": 56759.63, "total_tokens": 3486881280} {"current_steps": 10420, "total_steps": 25209, "loss": 0.3382, "lr": 3.499071119910131e-05, "epoch": 1.2400333214328216, "percentage": 41.33, "elapsed_time": "17:04:43", "remaining_time": "1 day, 0:14:22", "throughput": 56768.53, "total_tokens": 3490301952} {"current_steps": 10430, "total_steps": 25209, "loss": 0.3393, "lr": 3.498214617040739e-05, "epoch": 1.2412233726050221, "percentage": 41.37, "elapsed_time": "17:05:30", "remaining_time": "1 day, 0:13:07", "throughput": 56778.2, "total_tokens": 3493595520} {"current_steps": 10440, "total_steps": 25209, "loss": 0.3376, "lr": 3.49735874282808e-05, "epoch": 1.2424134237772224, "percentage": 41.41, "elapsed_time": "17:06:17", "remaining_time": "1 day, 0:11:50", "throughput": 56789.34, "total_tokens": 3496940672} {"current_steps": 10450, "total_steps": 25209, "loss": 0.3379, "lr": 3.4965034965034965e-05, "epoch": 1.243603474949423, "percentage": 41.45, "elapsed_time": "17:07:09", "remaining_time": "1 day, 0:10:42", "throughput": 56797.94, "total_tokens": 3500435200} {"current_steps": 10460, "total_steps": 25209, "loss": 0.3361, "lr": 3.495648877299642e-05, "epoch": 1.2447935261216232, "percentage": 41.49, "elapsed_time": "17:07:56", "remaining_time": "1 day, 0:09:26", "throughput": 56809.39, "total_tokens": 3503811584} {"current_steps": 10470, "total_steps": 25209, "loss": 0.3411, "lr": 3.494794884450483e-05, "epoch": 1.2459835772938237, "percentage": 41.53, "elapsed_time": "17:08:48", "remaining_time": "1 day, 0:08:17", "throughput": 56815.99, "total_tokens": 3507155456} {"current_steps": 10480, "total_steps": 25209, "loss": 0.3391, "lr": 3.4939415171912954e-05, "epoch": 1.247173628466024, "percentage": 41.57, "elapsed_time": "17:09:38", "remaining_time": "1 day, 0:07:05", "throughput": 56824.91, "total_tokens": 3510530304} {"current_steps": 10490, "total_steps": 25209, "loss": 0.3348, "lr": 3.4930887747586616e-05, "epoch": 1.2483636796382245, "percentage": 41.61, "elapsed_time": "17:10:23", "remaining_time": "1 day, 0:05:47", "throughput": 56835.86, "total_tokens": 3513816064} {"current_steps": 10500, "total_steps": 25209, "loss": 0.3374, "lr": 3.492236656390469e-05, "epoch": 1.2495537308104248, "percentage": 41.65, "elapsed_time": "17:11:10", "remaining_time": "1 day, 0:04:31", "throughput": 56846.21, "total_tokens": 3517103872} {"current_steps": 10510, "total_steps": 25209, "loss": 0.338, "lr": 3.4913851613259034e-05, "epoch": 1.2507437819826253, "percentage": 41.69, "elapsed_time": "17:11:59", "remaining_time": "1 day, 0:03:19", "throughput": 56855.98, "total_tokens": 3520517760} {"current_steps": 10520, "total_steps": 25209, "loss": 0.3397, "lr": 3.490534288805452e-05, "epoch": 1.2519338331548258, "percentage": 41.73, "elapsed_time": "17:12:48", "remaining_time": "1 day, 0:02:05", "throughput": 56866.46, "total_tokens": 3523920000} {"current_steps": 10530, "total_steps": 25209, "loss": 0.3416, "lr": 3.489684038070891e-05, "epoch": 1.253123884327026, "percentage": 41.77, "elapsed_time": "17:13:33", "remaining_time": "1 day, 0:00:48", "throughput": 56878.02, "total_tokens": 3527219968} {"current_steps": 10540, "total_steps": 25209, "loss": 0.3386, "lr": 3.488834408365296e-05, "epoch": 1.2543139354992265, "percentage": 41.81, "elapsed_time": "17:14:23", "remaining_time": "23:59:36", "throughput": 56886.37, "total_tokens": 3530546944} {"current_steps": 10550, "total_steps": 25209, "loss": 0.3398, "lr": 3.487985398933027e-05, "epoch": 1.2555039866714268, "percentage": 41.85, "elapsed_time": "17:15:11", "remaining_time": "23:58:22", "throughput": 56895.66, "total_tokens": 3533870848} {"current_steps": 10560, "total_steps": 25209, "loss": 0.3381, "lr": 3.4871370090197324e-05, "epoch": 1.2566940378436273, "percentage": 41.89, "elapsed_time": "17:16:00", "remaining_time": "23:57:10", "throughput": 56904.47, "total_tokens": 3537229696} {"current_steps": 10570, "total_steps": 25209, "loss": 0.339, "lr": 3.486289237872343e-05, "epoch": 1.2578840890158276, "percentage": 41.93, "elapsed_time": "17:16:46", "remaining_time": "23:55:53", "throughput": 56915.54, "total_tokens": 3540508928} {"current_steps": 10580, "total_steps": 25209, "loss": 0.3375, "lr": 3.485442084739075e-05, "epoch": 1.259074140188028, "percentage": 41.97, "elapsed_time": "17:17:34", "remaining_time": "23:54:38", "throughput": 56924.69, "total_tokens": 3543789952} {"current_steps": 10590, "total_steps": 25209, "loss": 0.3423, "lr": 3.484595548869416e-05, "epoch": 1.2602641913602284, "percentage": 42.01, "elapsed_time": "17:18:19", "remaining_time": "23:53:21", "throughput": 56935.22, "total_tokens": 3547052288} {"current_steps": 10600, "total_steps": 25209, "loss": 0.3346, "lr": 3.4837496295141335e-05, "epoch": 1.2614542425324289, "percentage": 42.05, "elapsed_time": "17:19:08", "remaining_time": "23:52:09", "throughput": 56944.2, "total_tokens": 3550381184} {"current_steps": 10610, "total_steps": 25209, "loss": 0.3381, "lr": 3.482904325925266e-05, "epoch": 1.2626442937046294, "percentage": 42.09, "elapsed_time": "17:19:55", "remaining_time": "23:50:53", "throughput": 56954.83, "total_tokens": 3553720064} {"current_steps": 10620, "total_steps": 25209, "loss": 0.3374, "lr": 3.482059637356124e-05, "epoch": 1.2638343448768297, "percentage": 42.13, "elapsed_time": "17:20:44", "remaining_time": "23:49:41", "throughput": 56964.34, "total_tokens": 3557116928} {"current_steps": 10630, "total_steps": 25209, "loss": 0.3349, "lr": 3.481215563061281e-05, "epoch": 1.2650243960490302, "percentage": 42.17, "elapsed_time": "17:21:33", "remaining_time": "23:48:30", "throughput": 56973.65, "total_tokens": 3560507264} {"current_steps": 10640, "total_steps": 25209, "loss": 0.3403, "lr": 3.4803721022965785e-05, "epoch": 1.2662144472212304, "percentage": 42.21, "elapsed_time": "17:22:20", "remaining_time": "23:47:15", "throughput": 56983.21, "total_tokens": 3563775104} {"current_steps": 10650, "total_steps": 25209, "loss": 0.3405, "lr": 3.479529254319117e-05, "epoch": 1.267404498393431, "percentage": 42.25, "elapsed_time": "17:23:10", "remaining_time": "23:46:03", "throughput": 56992.76, "total_tokens": 3567182976} {"current_steps": 10660, "total_steps": 25209, "loss": 0.3369, "lr": 3.478687018387257e-05, "epoch": 1.2685945495656314, "percentage": 42.29, "elapsed_time": "17:23:58", "remaining_time": "23:44:51", "throughput": 57002.14, "total_tokens": 3570555648} {"current_steps": 10670, "total_steps": 25209, "loss": 0.336, "lr": 3.477845393760616e-05, "epoch": 1.2697846007378317, "percentage": 42.33, "elapsed_time": "17:24:46", "remaining_time": "23:43:36", "throughput": 57012.91, "total_tokens": 3573920000} {"current_steps": 10680, "total_steps": 25209, "loss": 0.3348, "lr": 3.4770043797000614e-05, "epoch": 1.270974651910032, "percentage": 42.37, "elapsed_time": "17:25:30", "remaining_time": "23:42:18", "throughput": 57024.46, "total_tokens": 3577191680} {"current_steps": 10690, "total_steps": 25209, "loss": 0.3365, "lr": 3.4761639754677146e-05, "epoch": 1.2721647030822325, "percentage": 42.41, "elapsed_time": "17:26:18", "remaining_time": "23:41:04", "throughput": 57033.32, "total_tokens": 3580463616} {"current_steps": 10700, "total_steps": 25209, "loss": 0.3416, "lr": 3.4753241803269435e-05, "epoch": 1.273354754254433, "percentage": 42.45, "elapsed_time": "17:27:05", "remaining_time": "23:39:49", "throughput": 57042.65, "total_tokens": 3583720704} {"current_steps": 10710, "total_steps": 25209, "loss": 0.3387, "lr": 3.474484993542361e-05, "epoch": 1.2745448054266333, "percentage": 42.48, "elapsed_time": "17:27:55", "remaining_time": "23:38:40", "throughput": 57050.23, "total_tokens": 3587082496} {"current_steps": 10720, "total_steps": 25209, "loss": 0.3361, "lr": 3.473646414379822e-05, "epoch": 1.2757348565988338, "percentage": 42.52, "elapsed_time": "17:28:43", "remaining_time": "23:37:26", "throughput": 57060.3, "total_tokens": 3590426496} {"current_steps": 10730, "total_steps": 25209, "loss": 0.3407, "lr": 3.472808442106422e-05, "epoch": 1.276924907771034, "percentage": 42.56, "elapsed_time": "17:29:31", "remaining_time": "23:36:13", "throughput": 57068.97, "total_tokens": 3593731328} {"current_steps": 10740, "total_steps": 25209, "loss": 0.3358, "lr": 3.4719710759904936e-05, "epoch": 1.2781149589432346, "percentage": 42.6, "elapsed_time": "17:30:27", "remaining_time": "23:35:11", "throughput": 57071.96, "total_tokens": 3597107584} {"current_steps": 10750, "total_steps": 25209, "loss": 0.3386, "lr": 3.471134315301603e-05, "epoch": 1.279305010115435, "percentage": 42.64, "elapsed_time": "17:31:15", "remaining_time": "23:33:58", "throughput": 57080.48, "total_tokens": 3600387456} {"current_steps": 10760, "total_steps": 25209, "loss": 0.3378, "lr": 3.470298159310549e-05, "epoch": 1.2804950612876353, "percentage": 42.68, "elapsed_time": "17:32:09", "remaining_time": "23:32:52", "throughput": 57086.59, "total_tokens": 3603826816} {"current_steps": 10770, "total_steps": 25209, "loss": 0.337, "lr": 3.4694626072893585e-05, "epoch": 1.2816851124598359, "percentage": 42.72, "elapsed_time": "17:32:58", "remaining_time": "23:31:42", "throughput": 57096.03, "total_tokens": 3607268864} {"current_steps": 10780, "total_steps": 25209, "loss": 0.3389, "lr": 3.468627658511285e-05, "epoch": 1.2828751636320361, "percentage": 42.76, "elapsed_time": "17:33:47", "remaining_time": "23:30:29", "throughput": 57106.09, "total_tokens": 3610663424} {"current_steps": 10790, "total_steps": 25209, "loss": 0.3367, "lr": 3.467793312250806e-05, "epoch": 1.2840652148042366, "percentage": 42.8, "elapsed_time": "17:34:36", "remaining_time": "23:29:18", "throughput": 57114.51, "total_tokens": 3614026112} {"current_steps": 10800, "total_steps": 25209, "loss": 0.3359, "lr": 3.466959567783619e-05, "epoch": 1.285255265976437, "percentage": 42.84, "elapsed_time": "17:35:25", "remaining_time": "23:28:06", "throughput": 57123.04, "total_tokens": 3617346944} {"current_steps": 10810, "total_steps": 25209, "loss": 0.3341, "lr": 3.466126424386642e-05, "epoch": 1.2864453171486374, "percentage": 42.88, "elapsed_time": "17:36:13", "remaining_time": "23:26:54", "throughput": 57132.55, "total_tokens": 3620715648} {"current_steps": 10820, "total_steps": 25209, "loss": 0.3381, "lr": 3.4652938813380056e-05, "epoch": 1.2876353683208377, "percentage": 42.92, "elapsed_time": "17:37:01", "remaining_time": "23:25:40", "throughput": 57143.97, "total_tokens": 3624129920} {"current_steps": 10830, "total_steps": 25209, "loss": 0.3373, "lr": 3.464461937917057e-05, "epoch": 1.2888254194930382, "percentage": 42.96, "elapsed_time": "17:37:51", "remaining_time": "23:24:31", "throughput": 57152.14, "total_tokens": 3627541632} {"current_steps": 10840, "total_steps": 25209, "loss": 0.3392, "lr": 3.4636305934043525e-05, "epoch": 1.2900154706652387, "percentage": 43.0, "elapsed_time": "17:38:37", "remaining_time": "23:23:16", "throughput": 57162.47, "total_tokens": 3630824704} {"current_steps": 10850, "total_steps": 25209, "loss": 0.3377, "lr": 3.4627998470816544e-05, "epoch": 1.291205521837439, "percentage": 43.04, "elapsed_time": "17:39:28", "remaining_time": "23:22:06", "throughput": 57170.25, "total_tokens": 3634201088} {"current_steps": 10860, "total_steps": 25209, "loss": 0.3363, "lr": 3.4619696982319334e-05, "epoch": 1.2923955730096395, "percentage": 43.08, "elapsed_time": "17:40:15", "remaining_time": "23:20:52", "throughput": 57180.1, "total_tokens": 3637512576} {"current_steps": 10870, "total_steps": 25209, "loss": 0.3395, "lr": 3.461140146139361e-05, "epoch": 1.2935856241818398, "percentage": 43.12, "elapsed_time": "17:41:04", "remaining_time": "23:19:42", "throughput": 57188.58, "total_tokens": 3640883456} {"current_steps": 10880, "total_steps": 25209, "loss": 0.3402, "lr": 3.460311190089309e-05, "epoch": 1.2947756753540403, "percentage": 43.16, "elapsed_time": "17:41:51", "remaining_time": "23:18:27", "throughput": 57198.17, "total_tokens": 3644163456} {"current_steps": 10890, "total_steps": 25209, "loss": 0.336, "lr": 3.459482829368348e-05, "epoch": 1.2959657265262408, "percentage": 43.2, "elapsed_time": "17:42:41", "remaining_time": "23:17:18", "throughput": 57205.82, "total_tokens": 3647513856} {"current_steps": 10900, "total_steps": 25209, "loss": 0.3373, "lr": 3.4586550632642425e-05, "epoch": 1.297155777698441, "percentage": 43.24, "elapsed_time": "17:43:31", "remaining_time": "23:16:08", "throughput": 57213.56, "total_tokens": 3650888192} {"current_steps": 10910, "total_steps": 25209, "loss": 0.3395, "lr": 3.457827891065949e-05, "epoch": 1.2983458288706413, "percentage": 43.28, "elapsed_time": "17:44:25", "remaining_time": "23:15:04", "throughput": 57216.26, "total_tokens": 3654167680} {"current_steps": 10920, "total_steps": 25209, "loss": 0.3348, "lr": 3.457001312063614e-05, "epoch": 1.2995358800428418, "percentage": 43.32, "elapsed_time": "17:45:17", "remaining_time": "23:13:56", "throughput": 57224.06, "total_tokens": 3657608064} {"current_steps": 10930, "total_steps": 25209, "loss": 0.3391, "lr": 3.45617532554857e-05, "epoch": 1.3007259312150423, "percentage": 43.36, "elapsed_time": "17:46:02", "remaining_time": "23:12:40", "throughput": 57235.59, "total_tokens": 3660921984} {"current_steps": 10940, "total_steps": 25209, "loss": 0.3355, "lr": 3.455349930813339e-05, "epoch": 1.3019159823872426, "percentage": 43.4, "elapsed_time": "17:46:51", "remaining_time": "23:11:30", "throughput": 57243.7, "total_tokens": 3664283136} {"current_steps": 10950, "total_steps": 25209, "loss": 0.3346, "lr": 3.45452512715162e-05, "epoch": 1.303106033559443, "percentage": 43.44, "elapsed_time": "17:47:39", "remaining_time": "23:10:17", "throughput": 57253.07, "total_tokens": 3667607424} {"current_steps": 10960, "total_steps": 25209, "loss": 0.3361, "lr": 3.4537009138582935e-05, "epoch": 1.3042960847316434, "percentage": 43.48, "elapsed_time": "17:48:27", "remaining_time": "23:09:06", "throughput": 57263.17, "total_tokens": 3671023616} {"current_steps": 10970, "total_steps": 25209, "loss": 0.3367, "lr": 3.4528772902294174e-05, "epoch": 1.3054861359038439, "percentage": 43.52, "elapsed_time": "17:49:14", "remaining_time": "23:07:52", "throughput": 57273.05, "total_tokens": 3674348416} {"current_steps": 10980, "total_steps": 25209, "loss": 0.3381, "lr": 3.452054255562222e-05, "epoch": 1.3066761870760444, "percentage": 43.56, "elapsed_time": "17:50:05", "remaining_time": "23:06:44", "throughput": 57280.94, "total_tokens": 3677757696} {"current_steps": 10990, "total_steps": 25209, "loss": 0.3348, "lr": 3.451231809155115e-05, "epoch": 1.3078662382482447, "percentage": 43.6, "elapsed_time": "17:50:54", "remaining_time": "23:05:32", "throughput": 57289.87, "total_tokens": 3681106816} {"current_steps": 11000, "total_steps": 25209, "loss": 0.3397, "lr": 3.450409950307666e-05, "epoch": 1.309056289420445, "percentage": 43.64, "elapsed_time": "17:51:45", "remaining_time": "23:04:24", "throughput": 57297.99, "total_tokens": 3684565504} {"current_steps": 11010, "total_steps": 25209, "loss": 0.3415, "lr": 3.449588678320619e-05, "epoch": 1.3102463405926454, "percentage": 43.67, "elapsed_time": "17:52:32", "remaining_time": "23:03:12", "throughput": 57307.05, "total_tokens": 3687872896} {"current_steps": 11020, "total_steps": 25209, "loss": 0.3377, "lr": 3.4487679924958767e-05, "epoch": 1.311436391764846, "percentage": 43.71, "elapsed_time": "17:53:20", "remaining_time": "23:02:00", "throughput": 57316.61, "total_tokens": 3691228544} {"current_steps": 11030, "total_steps": 25209, "loss": 0.3385, "lr": 3.4479478921365076e-05, "epoch": 1.3126264429370462, "percentage": 43.75, "elapsed_time": "17:54:10", "remaining_time": "23:00:50", "throughput": 57325.82, "total_tokens": 3694654976} {"current_steps": 11040, "total_steps": 25209, "loss": 0.3374, "lr": 3.447128376546738e-05, "epoch": 1.3138164941092467, "percentage": 43.79, "elapsed_time": "17:54:58", "remaining_time": "22:59:39", "throughput": 57334.6, "total_tokens": 3698009856} {"current_steps": 11050, "total_steps": 25209, "loss": 0.334, "lr": 3.4463094450319505e-05, "epoch": 1.315006545281447, "percentage": 43.83, "elapsed_time": "17:55:53", "remaining_time": "22:58:36", "throughput": 57338.48, "total_tokens": 3701413760} {"current_steps": 11060, "total_steps": 25209, "loss": 0.3328, "lr": 3.4454910968986855e-05, "epoch": 1.3161965964536475, "percentage": 43.87, "elapsed_time": "17:56:42", "remaining_time": "22:57:25", "throughput": 57346.34, "total_tokens": 3704701440} {"current_steps": 11070, "total_steps": 25209, "loss": 0.3378, "lr": 3.4446733314546336e-05, "epoch": 1.317386647625848, "percentage": 43.91, "elapsed_time": "17:57:28", "remaining_time": "22:56:11", "throughput": 57355.75, "total_tokens": 3707977472} {"current_steps": 11080, "total_steps": 25209, "loss": 0.3367, "lr": 3.443856148008633e-05, "epoch": 1.3185766987980483, "percentage": 43.95, "elapsed_time": "17:58:17", "remaining_time": "22:55:00", "throughput": 57364.2, "total_tokens": 3711318144} {"current_steps": 11090, "total_steps": 25209, "loss": 0.3322, "lr": 3.443039545870672e-05, "epoch": 1.3197667499702488, "percentage": 43.99, "elapsed_time": "17:59:05", "remaining_time": "22:53:49", "throughput": 57374.12, "total_tokens": 3714700544} {"current_steps": 11100, "total_steps": 25209, "loss": 0.3375, "lr": 3.442223524351883e-05, "epoch": 1.320956801142449, "percentage": 44.03, "elapsed_time": "17:59:52", "remaining_time": "22:52:36", "throughput": 57384.04, "total_tokens": 3718042240} {"current_steps": 11110, "total_steps": 25209, "loss": 0.3367, "lr": 3.44140808276454e-05, "epoch": 1.3221468523146496, "percentage": 44.07, "elapsed_time": "18:00:43", "remaining_time": "22:51:28", "throughput": 57391.96, "total_tokens": 3721480064} {"current_steps": 11120, "total_steps": 25209, "loss": 0.3368, "lr": 3.4405932204220575e-05, "epoch": 1.32333690348685, "percentage": 44.11, "elapsed_time": "18:01:31", "remaining_time": "22:50:17", "throughput": 57400.46, "total_tokens": 3724795520} {"current_steps": 11130, "total_steps": 25209, "loss": 0.3329, "lr": 3.4397789366389876e-05, "epoch": 1.3245269546590503, "percentage": 44.15, "elapsed_time": "18:02:19", "remaining_time": "22:49:05", "throughput": 57409.86, "total_tokens": 3728144896} {"current_steps": 11140, "total_steps": 25209, "loss": 0.3353, "lr": 3.438965230731016e-05, "epoch": 1.3257170058312506, "percentage": 44.19, "elapsed_time": "18:03:06", "remaining_time": "22:47:52", "throughput": 57420.47, "total_tokens": 3731546624} {"current_steps": 11150, "total_steps": 25209, "loss": 0.3402, "lr": 3.438152102014964e-05, "epoch": 1.3269070570034511, "percentage": 44.23, "elapsed_time": "18:03:53", "remaining_time": "22:46:41", "throughput": 57429.2, "total_tokens": 3734848768} {"current_steps": 11160, "total_steps": 25209, "loss": 0.3342, "lr": 3.437339549808778e-05, "epoch": 1.3280971081756516, "percentage": 44.27, "elapsed_time": "18:04:42", "remaining_time": "22:45:30", "throughput": 57437.97, "total_tokens": 3738229888} {"current_steps": 11170, "total_steps": 25209, "loss": 0.3366, "lr": 3.43652757343154e-05, "epoch": 1.329287159347852, "percentage": 44.31, "elapsed_time": "18:05:30", "remaining_time": "22:44:19", "throughput": 57447.62, "total_tokens": 3741584256} {"current_steps": 11180, "total_steps": 25209, "loss": 0.3348, "lr": 3.435716172203449e-05, "epoch": 1.3304772105200524, "percentage": 44.35, "elapsed_time": "18:06:19", "remaining_time": "22:43:09", "throughput": 57455.28, "total_tokens": 3744931712} {"current_steps": 11190, "total_steps": 25209, "loss": 0.341, "lr": 3.434905345445833e-05, "epoch": 1.3316672616922527, "percentage": 44.39, "elapsed_time": "18:07:06", "remaining_time": "22:41:57", "throughput": 57464.46, "total_tokens": 3748228352} {"current_steps": 11200, "total_steps": 25209, "loss": 0.3369, "lr": 3.4340950924811374e-05, "epoch": 1.3328573128644532, "percentage": 44.43, "elapsed_time": "18:07:53", "remaining_time": "22:40:44", "throughput": 57474.9, "total_tokens": 3751577344} {"current_steps": 11210, "total_steps": 25209, "loss": 0.3332, "lr": 3.433285412632927e-05, "epoch": 1.3340473640366537, "percentage": 44.47, "elapsed_time": "18:08:38", "remaining_time": "22:39:29", "throughput": 57486.14, "total_tokens": 3754931840} {"current_steps": 11220, "total_steps": 25209, "loss": 0.3397, "lr": 3.4324763052258835e-05, "epoch": 1.335237415208854, "percentage": 44.51, "elapsed_time": "18:09:27", "remaining_time": "22:38:19", "throughput": 57494.09, "total_tokens": 3758232192} {"current_steps": 11230, "total_steps": 25209, "loss": 0.3373, "lr": 3.4316677695858003e-05, "epoch": 1.3364274663810543, "percentage": 44.55, "elapsed_time": "18:10:13", "remaining_time": "22:37:05", "throughput": 57503.81, "total_tokens": 3761510912} {"current_steps": 11240, "total_steps": 25209, "loss": 0.3361, "lr": 3.430859805039583e-05, "epoch": 1.3376175175532548, "percentage": 44.59, "elapsed_time": "18:11:00", "remaining_time": "22:35:54", "throughput": 57513.13, "total_tokens": 3764850816} {"current_steps": 11250, "total_steps": 25209, "loss": 0.3356, "lr": 3.430052410915246e-05, "epoch": 1.3388075687254553, "percentage": 44.63, "elapsed_time": "18:11:47", "remaining_time": "22:34:42", "throughput": 57522.05, "total_tokens": 3768144640} {"current_steps": 11260, "total_steps": 25209, "loss": 0.3363, "lr": 3.4292455865419086e-05, "epoch": 1.3399976198976555, "percentage": 44.67, "elapsed_time": "18:12:33", "remaining_time": "22:33:28", "throughput": 57532.72, "total_tokens": 3771460224} {"current_steps": 11270, "total_steps": 25209, "loss": 0.3391, "lr": 3.4284393312497973e-05, "epoch": 1.341187671069856, "percentage": 44.71, "elapsed_time": "18:13:23", "remaining_time": "22:32:19", "throughput": 57540.6, "total_tokens": 3774860160} {"current_steps": 11280, "total_steps": 25209, "loss": 0.3331, "lr": 3.427633644370238e-05, "epoch": 1.3423777222420563, "percentage": 44.75, "elapsed_time": "18:14:12", "remaining_time": "22:31:10", "throughput": 57548.73, "total_tokens": 3778219648} {"current_steps": 11290, "total_steps": 25209, "loss": 0.3353, "lr": 3.4268285252356564e-05, "epoch": 1.3435677734142568, "percentage": 44.79, "elapsed_time": "18:14:58", "remaining_time": "22:29:57", "throughput": 57559.94, "total_tokens": 3781596544} {"current_steps": 11300, "total_steps": 25209, "loss": 0.3356, "lr": 3.426023973179575e-05, "epoch": 1.3447578245864573, "percentage": 44.83, "elapsed_time": "18:15:47", "remaining_time": "22:28:47", "throughput": 57568.08, "total_tokens": 3784938752} {"current_steps": 11310, "total_steps": 25209, "loss": 0.3348, "lr": 3.425219987536614e-05, "epoch": 1.3459478757586576, "percentage": 44.86, "elapsed_time": "18:16:33", "remaining_time": "22:27:34", "throughput": 57578.04, "total_tokens": 3788243072} {"current_steps": 11320, "total_steps": 25209, "loss": 0.3375, "lr": 3.4244165676424815e-05, "epoch": 1.347137926930858, "percentage": 44.9, "elapsed_time": "18:17:17", "remaining_time": "22:26:18", "throughput": 57587.76, "total_tokens": 3791430016} {"current_steps": 11330, "total_steps": 25209, "loss": 0.3359, "lr": 3.423613712833979e-05, "epoch": 1.3483279781030584, "percentage": 44.94, "elapsed_time": "18:18:04", "remaining_time": "22:25:06", "throughput": 57597.94, "total_tokens": 3794790400} {"current_steps": 11340, "total_steps": 25209, "loss": 0.3372, "lr": 3.422811422448995e-05, "epoch": 1.3495180292752589, "percentage": 44.98, "elapsed_time": "18:18:47", "remaining_time": "22:23:50", "throughput": 57608.8, "total_tokens": 3798017280} {"current_steps": 11350, "total_steps": 25209, "loss": 0.3387, "lr": 3.422009695826503e-05, "epoch": 1.3507080804474592, "percentage": 45.02, "elapsed_time": "18:19:34", "remaining_time": "22:22:39", "throughput": 57618.21, "total_tokens": 3801359232} {"current_steps": 11360, "total_steps": 25209, "loss": 0.3356, "lr": 3.4212085323065626e-05, "epoch": 1.3518981316196597, "percentage": 45.06, "elapsed_time": "18:20:23", "remaining_time": "22:21:29", "throughput": 57626.07, "total_tokens": 3804695040} {"current_steps": 11370, "total_steps": 25209, "loss": 0.3323, "lr": 3.4204079312303103e-05, "epoch": 1.35308818279186, "percentage": 45.1, "elapsed_time": "18:21:14", "remaining_time": "22:20:22", "throughput": 57633.58, "total_tokens": 3808112512} {"current_steps": 11380, "total_steps": 25209, "loss": 0.3346, "lr": 3.419607891939964e-05, "epoch": 1.3542782339640604, "percentage": 45.14, "elapsed_time": "18:22:09", "remaining_time": "22:19:20", "throughput": 57637.92, "total_tokens": 3811576832} {"current_steps": 11390, "total_steps": 25209, "loss": 0.3334, "lr": 3.4188084137788166e-05, "epoch": 1.355468285136261, "percentage": 45.18, "elapsed_time": "18:23:04", "remaining_time": "22:18:18", "throughput": 57642.27, "total_tokens": 3815023872} {"current_steps": 11400, "total_steps": 25209, "loss": 0.3339, "lr": 3.418009496091238e-05, "epoch": 1.3566583363084612, "percentage": 45.22, "elapsed_time": "18:23:51", "remaining_time": "22:17:06", "throughput": 57651.98, "total_tokens": 3818354432} {"current_steps": 11410, "total_steps": 25209, "loss": 0.3393, "lr": 3.417211138222666e-05, "epoch": 1.3578483874806617, "percentage": 45.26, "elapsed_time": "18:24:34", "remaining_time": "22:15:50", "throughput": 57662.95, "total_tokens": 3821555456} {"current_steps": 11420, "total_steps": 25209, "loss": 0.3386, "lr": 3.416413339519612e-05, "epoch": 1.359038438652862, "percentage": 45.3, "elapsed_time": "18:25:25", "remaining_time": "22:14:43", "throughput": 57670.3, "total_tokens": 3824990848} {"current_steps": 11430, "total_steps": 25209, "loss": 0.3387, "lr": 3.4156160993296524e-05, "epoch": 1.3602284898250625, "percentage": 45.34, "elapsed_time": "18:26:10", "remaining_time": "22:13:30", "throughput": 57679.27, "total_tokens": 3828219264} {"current_steps": 11440, "total_steps": 25209, "loss": 0.337, "lr": 3.4148194170014295e-05, "epoch": 1.361418540997263, "percentage": 45.38, "elapsed_time": "18:26:59", "remaining_time": "22:12:21", "throughput": 57688.54, "total_tokens": 3831631616} {"current_steps": 11450, "total_steps": 25209, "loss": 0.3324, "lr": 3.4140232918846484e-05, "epoch": 1.3626085921694633, "percentage": 45.42, "elapsed_time": "18:27:44", "remaining_time": "22:11:08", "throughput": 57698.77, "total_tokens": 3834939776} {"current_steps": 11460, "total_steps": 25209, "loss": 0.3332, "lr": 3.4132277233300753e-05, "epoch": 1.3637986433416636, "percentage": 45.46, "elapsed_time": "18:28:31", "remaining_time": "22:09:56", "throughput": 57707.91, "total_tokens": 3838259072} {"current_steps": 11470, "total_steps": 25209, "loss": 0.3404, "lr": 3.4124327106895356e-05, "epoch": 1.364988694513864, "percentage": 45.5, "elapsed_time": "18:29:17", "remaining_time": "22:08:43", "throughput": 57717.8, "total_tokens": 3841540864} {"current_steps": 11480, "total_steps": 25209, "loss": 0.3373, "lr": 3.4116382533159097e-05, "epoch": 1.3661787456860646, "percentage": 45.54, "elapsed_time": "18:30:05", "remaining_time": "22:07:34", "throughput": 57725.84, "total_tokens": 3844872448} {"current_steps": 11490, "total_steps": 25209, "loss": 0.3413, "lr": 3.4108443505631335e-05, "epoch": 1.3673687968582648, "percentage": 45.58, "elapsed_time": "18:30:53", "remaining_time": "22:06:24", "throughput": 57734.98, "total_tokens": 3848248064} {"current_steps": 11500, "total_steps": 25209, "loss": 0.3387, "lr": 3.410051001786192e-05, "epoch": 1.3685588480304653, "percentage": 45.62, "elapsed_time": "18:31:40", "remaining_time": "22:05:13", "throughput": 57744.87, "total_tokens": 3851628544} {"current_steps": 11510, "total_steps": 25209, "loss": 0.3331, "lr": 3.409258206341124e-05, "epoch": 1.3697488992026656, "percentage": 45.66, "elapsed_time": "18:32:30", "remaining_time": "22:04:05", "throughput": 57752.66, "total_tokens": 3855018880} {"current_steps": 11520, "total_steps": 25209, "loss": 0.3386, "lr": 3.4084659635850134e-05, "epoch": 1.3709389503748661, "percentage": 45.7, "elapsed_time": "18:33:14", "remaining_time": "22:02:51", "throughput": 57763.72, "total_tokens": 3858320768} {"current_steps": 11530, "total_steps": 25209, "loss": 0.3373, "lr": 3.40767427287599e-05, "epoch": 1.3721290015470666, "percentage": 45.74, "elapsed_time": "18:34:01", "remaining_time": "22:01:39", "throughput": 57772.92, "total_tokens": 3861616512} {"current_steps": 11540, "total_steps": 25209, "loss": 0.3351, "lr": 3.406883133573224e-05, "epoch": 1.373319052719267, "percentage": 45.78, "elapsed_time": "18:34:49", "remaining_time": "22:00:30", "throughput": 57781.31, "total_tokens": 3864981632} {"current_steps": 11550, "total_steps": 25209, "loss": 0.3358, "lr": 3.406092545036932e-05, "epoch": 1.3745091038914674, "percentage": 45.82, "elapsed_time": "18:35:36", "remaining_time": "21:59:18", "throughput": 57789.83, "total_tokens": 3868234112} {"current_steps": 11560, "total_steps": 25209, "loss": 0.3368, "lr": 3.405302506628365e-05, "epoch": 1.3756991550636677, "percentage": 45.86, "elapsed_time": "18:36:25", "remaining_time": "21:58:10", "throughput": 57797.66, "total_tokens": 3871607680} {"current_steps": 11570, "total_steps": 25209, "loss": 0.3358, "lr": 3.404513017709813e-05, "epoch": 1.3768892062358682, "percentage": 45.9, "elapsed_time": "18:37:11", "remaining_time": "21:56:58", "throughput": 57807.12, "total_tokens": 3874921088} {"current_steps": 11580, "total_steps": 25209, "loss": 0.3362, "lr": 3.403724077644598e-05, "epoch": 1.3780792574080685, "percentage": 45.94, "elapsed_time": "18:38:01", "remaining_time": "21:55:50", "throughput": 57815.22, "total_tokens": 3878303872} {"current_steps": 11590, "total_steps": 25209, "loss": 0.3327, "lr": 3.402935685797077e-05, "epoch": 1.379269308580269, "percentage": 45.98, "elapsed_time": "18:38:49", "remaining_time": "21:54:42", "throughput": 57823.36, "total_tokens": 3881679616} {"current_steps": 11600, "total_steps": 25209, "loss": 0.3389, "lr": 3.4021478415326355e-05, "epoch": 1.3804593597524693, "percentage": 46.02, "elapsed_time": "18:39:37", "remaining_time": "21:53:32", "throughput": 57831.71, "total_tokens": 3884996992} {"current_steps": 11610, "total_steps": 25209, "loss": 0.3391, "lr": 3.401360544217687e-05, "epoch": 1.3816494109246698, "percentage": 46.05, "elapsed_time": "18:40:26", "remaining_time": "21:52:24", "throughput": 57839.86, "total_tokens": 3888397696} {"current_steps": 11620, "total_steps": 25209, "loss": 0.3346, "lr": 3.400573793219672e-05, "epoch": 1.3828394620968703, "percentage": 46.09, "elapsed_time": "18:41:17", "remaining_time": "21:51:17", "throughput": 57847.88, "total_tokens": 3891834624} {"current_steps": 11630, "total_steps": 25209, "loss": 0.3344, "lr": 3.3997875879070546e-05, "epoch": 1.3840295132690705, "percentage": 46.13, "elapsed_time": "18:42:04", "remaining_time": "21:50:06", "throughput": 57856.67, "total_tokens": 3895145088} {"current_steps": 11640, "total_steps": 25209, "loss": 0.3298, "lr": 3.399001927649318e-05, "epoch": 1.385219564441271, "percentage": 46.17, "elapsed_time": "18:42:52", "remaining_time": "21:48:57", "throughput": 57866.16, "total_tokens": 3898588672} {"current_steps": 11650, "total_steps": 25209, "loss": 0.3354, "lr": 3.398216811816968e-05, "epoch": 1.3864096156134713, "percentage": 46.21, "elapsed_time": "18:43:39", "remaining_time": "21:47:47", "throughput": 57875.25, "total_tokens": 3901945856} {"current_steps": 11660, "total_steps": 25209, "loss": 0.3354, "lr": 3.397432239781527e-05, "epoch": 1.3875996667856718, "percentage": 46.25, "elapsed_time": "18:44:24", "remaining_time": "21:46:33", "throughput": 57884.53, "total_tokens": 3905131264} {"current_steps": 11670, "total_steps": 25209, "loss": 0.3325, "lr": 3.396648210915531e-05, "epoch": 1.3887897179578723, "percentage": 46.29, "elapsed_time": "18:45:12", "remaining_time": "21:45:24", "throughput": 57892.27, "total_tokens": 3908441088} {"current_steps": 11680, "total_steps": 25209, "loss": 0.3322, "lr": 3.3958647245925315e-05, "epoch": 1.3899797691300726, "percentage": 46.33, "elapsed_time": "18:46:04", "remaining_time": "21:44:20", "throughput": 57898.87, "total_tokens": 3911909632} {"current_steps": 11690, "total_steps": 25209, "loss": 0.3349, "lr": 3.3950817801870885e-05, "epoch": 1.3911698203022729, "percentage": 46.37, "elapsed_time": "18:46:56", "remaining_time": "21:43:15", "throughput": 57905.04, "total_tokens": 3915323776} {"current_steps": 11700, "total_steps": 25209, "loss": 0.3398, "lr": 3.3942993770747735e-05, "epoch": 1.3923598714744734, "percentage": 46.41, "elapsed_time": "18:47:47", "remaining_time": "21:42:09", "throughput": 57910.97, "total_tokens": 3918664576} {"current_steps": 11710, "total_steps": 25209, "loss": 0.3363, "lr": 3.3935175146321626e-05, "epoch": 1.3935499226466739, "percentage": 46.45, "elapsed_time": "18:48:40", "remaining_time": "21:41:06", "throughput": 57916.84, "total_tokens": 3922163072} {"current_steps": 11720, "total_steps": 25209, "loss": 0.3373, "lr": 3.392736192236839e-05, "epoch": 1.3947399738188742, "percentage": 46.49, "elapsed_time": "18:49:29", "remaining_time": "21:39:59", "throughput": 57925.21, "total_tokens": 3925589248} {"current_steps": 11730, "total_steps": 25209, "loss": 0.3316, "lr": 3.391955409267387e-05, "epoch": 1.3959300249910747, "percentage": 46.53, "elapsed_time": "18:50:19", "remaining_time": "21:38:52", "throughput": 57932.69, "total_tokens": 3928981888} {"current_steps": 11740, "total_steps": 25209, "loss": 0.3374, "lr": 3.3911751651033896e-05, "epoch": 1.397120076163275, "percentage": 46.57, "elapsed_time": "18:51:08", "remaining_time": "21:37:43", "throughput": 57941.43, "total_tokens": 3932402688} {"current_steps": 11750, "total_steps": 25209, "loss": 0.336, "lr": 3.3903954591254334e-05, "epoch": 1.3983101273354754, "percentage": 46.61, "elapsed_time": "18:51:55", "remaining_time": "21:36:33", "throughput": 57950.27, "total_tokens": 3935692928} {"current_steps": 11760, "total_steps": 25209, "loss": 0.3372, "lr": 3.389616290715097e-05, "epoch": 1.399500178507676, "percentage": 46.65, "elapsed_time": "18:52:44", "remaining_time": "21:35:25", "throughput": 57957.06, "total_tokens": 3938997248} {"current_steps": 11770, "total_steps": 25209, "loss": 0.3378, "lr": 3.388837659254955e-05, "epoch": 1.4006902296798762, "percentage": 46.69, "elapsed_time": "18:53:32", "remaining_time": "21:34:16", "throughput": 57964.05, "total_tokens": 3942283264} {"current_steps": 11780, "total_steps": 25209, "loss": 0.3396, "lr": 3.3880595641285746e-05, "epoch": 1.4018802808520767, "percentage": 46.73, "elapsed_time": "18:54:20", "remaining_time": "21:33:08", "throughput": 57973.35, "total_tokens": 3945723392} {"current_steps": 11790, "total_steps": 25209, "loss": 0.3356, "lr": 3.387282004720513e-05, "epoch": 1.403070332024277, "percentage": 46.77, "elapsed_time": "18:55:05", "remaining_time": "21:31:55", "throughput": 57984.27, "total_tokens": 3949039104} {"current_steps": 11800, "total_steps": 25209, "loss": 0.3316, "lr": 3.386504980416316e-05, "epoch": 1.4042603831964775, "percentage": 46.81, "elapsed_time": "18:55:53", "remaining_time": "21:30:47", "throughput": 57992.91, "total_tokens": 3952442112} {"current_steps": 11810, "total_steps": 25209, "loss": 0.3355, "lr": 3.385728490602515e-05, "epoch": 1.4054504343686778, "percentage": 46.85, "elapsed_time": "18:56:42", "remaining_time": "21:29:38", "throughput": 58000.89, "total_tokens": 3955789952} {"current_steps": 11820, "total_steps": 25209, "loss": 0.3402, "lr": 3.384952534666625e-05, "epoch": 1.4066404855408783, "percentage": 46.89, "elapsed_time": "18:57:30", "remaining_time": "21:28:30", "throughput": 58009.39, "total_tokens": 3959189760} {"current_steps": 11830, "total_steps": 25209, "loss": 0.3424, "lr": 3.3841771119971455e-05, "epoch": 1.4078305367130786, "percentage": 46.93, "elapsed_time": "18:58:19", "remaining_time": "21:27:22", "throughput": 58017.15, "total_tokens": 3962556800} {"current_steps": 11840, "total_steps": 25209, "loss": 0.338, "lr": 3.383402221983554e-05, "epoch": 1.409020587885279, "percentage": 46.97, "elapsed_time": "18:59:07", "remaining_time": "21:26:13", "throughput": 58025.13, "total_tokens": 3965856896} {"current_steps": 11850, "total_steps": 25209, "loss": 0.332, "lr": 3.3826278640163064e-05, "epoch": 1.4102106390574796, "percentage": 47.01, "elapsed_time": "18:59:55", "remaining_time": "21:25:04", "throughput": 58034.16, "total_tokens": 3969268608} {"current_steps": 11860, "total_steps": 25209, "loss": 0.3363, "lr": 3.3818540374868354e-05, "epoch": 1.4114006902296798, "percentage": 47.05, "elapsed_time": "19:00:43", "remaining_time": "21:23:56", "throughput": 58041.63, "total_tokens": 3972557696} {"current_steps": 11870, "total_steps": 25209, "loss": 0.336, "lr": 3.381080741787547e-05, "epoch": 1.4125907414018803, "percentage": 47.09, "elapsed_time": "19:01:31", "remaining_time": "21:22:48", "throughput": 58050.34, "total_tokens": 3975983104} {"current_steps": 11880, "total_steps": 25209, "loss": 0.3374, "lr": 3.38030797631182e-05, "epoch": 1.4137807925740806, "percentage": 47.13, "elapsed_time": "19:02:18", "remaining_time": "21:21:38", "throughput": 58059.94, "total_tokens": 3979338240} {"current_steps": 11890, "total_steps": 25209, "loss": 0.3358, "lr": 3.379535740454003e-05, "epoch": 1.4149708437462811, "percentage": 47.17, "elapsed_time": "19:03:06", "remaining_time": "21:20:29", "throughput": 58067.5, "total_tokens": 3982647424} {"current_steps": 11900, "total_steps": 25209, "loss": 0.3344, "lr": 3.3787640336094126e-05, "epoch": 1.4161608949184816, "percentage": 47.21, "elapsed_time": "19:03:55", "remaining_time": "21:19:21", "throughput": 58074.76, "total_tokens": 3985973376} {"current_steps": 11910, "total_steps": 25209, "loss": 0.3342, "lr": 3.3779928551743325e-05, "epoch": 1.417350946090682, "percentage": 47.25, "elapsed_time": "19:04:42", "remaining_time": "21:18:12", "throughput": 58084.4, "total_tokens": 3989366016} {"current_steps": 11920, "total_steps": 25209, "loss": 0.3341, "lr": 3.3772222045460084e-05, "epoch": 1.4185409972628822, "percentage": 47.28, "elapsed_time": "19:05:31", "remaining_time": "21:17:04", "throughput": 58091.85, "total_tokens": 3992721920} {"current_steps": 11930, "total_steps": 25209, "loss": 0.3374, "lr": 3.37645208112265e-05, "epoch": 1.4197310484350827, "percentage": 47.32, "elapsed_time": "19:06:17", "remaining_time": "21:15:54", "throughput": 58100.82, "total_tokens": 3996007936} {"current_steps": 11940, "total_steps": 25209, "loss": 0.3297, "lr": 3.3756824843034255e-05, "epoch": 1.4209210996072832, "percentage": 47.36, "elapsed_time": "19:07:03", "remaining_time": "21:14:44", "throughput": 58109.69, "total_tokens": 3999316736} {"current_steps": 11950, "total_steps": 25209, "loss": 0.3356, "lr": 3.374913413488464e-05, "epoch": 1.4221111507794835, "percentage": 47.4, "elapsed_time": "19:07:51", "remaining_time": "21:13:36", "throughput": 58117.44, "total_tokens": 4002658304} {"current_steps": 11960, "total_steps": 25209, "loss": 0.3347, "lr": 3.374144868078848e-05, "epoch": 1.423301201951684, "percentage": 47.44, "elapsed_time": "19:08:41", "remaining_time": "21:12:29", "throughput": 58123.25, "total_tokens": 4005936512} {"current_steps": 11970, "total_steps": 25209, "loss": 0.3392, "lr": 3.373376847476615e-05, "epoch": 1.4244912531238842, "percentage": 47.48, "elapsed_time": "19:09:28", "remaining_time": "21:11:20", "throughput": 58131.36, "total_tokens": 4009249664} {"current_steps": 11980, "total_steps": 25209, "loss": 0.3371, "lr": 3.3726093510847566e-05, "epoch": 1.4256813042960848, "percentage": 47.52, "elapsed_time": "19:10:15", "remaining_time": "21:10:10", "throughput": 58140.08, "total_tokens": 4012550144} {"current_steps": 11990, "total_steps": 25209, "loss": 0.3414, "lr": 3.371842378307212e-05, "epoch": 1.4268713554682853, "percentage": 47.56, "elapsed_time": "19:11:06", "remaining_time": "21:09:05", "throughput": 58146.35, "total_tokens": 4015955712} {"current_steps": 12000, "total_steps": 25209, "loss": 0.3343, "lr": 3.371075928548872e-05, "epoch": 1.4280614066404855, "percentage": 47.6, "elapsed_time": "19:11:52", "remaining_time": "21:07:56", "throughput": 58155.19, "total_tokens": 4019274240} {"current_steps": 12010, "total_steps": 25209, "loss": 0.3351, "lr": 3.37031000121557e-05, "epoch": 1.4292514578126858, "percentage": 47.64, "elapsed_time": "19:12:40", "remaining_time": "21:06:46", "throughput": 58162.83, "total_tokens": 4022542464} {"current_steps": 12020, "total_steps": 25209, "loss": 0.3343, "lr": 3.369544595714088e-05, "epoch": 1.4304415089848863, "percentage": 47.68, "elapsed_time": "19:13:31", "remaining_time": "21:05:42", "throughput": 58168.99, "total_tokens": 4025936256} {"current_steps": 12030, "total_steps": 25209, "loss": 0.3355, "lr": 3.368779711452148e-05, "epoch": 1.4316315601570868, "percentage": 47.72, "elapsed_time": "19:14:21", "remaining_time": "21:04:36", "throughput": 58175.88, "total_tokens": 4029340928} {"current_steps": 12040, "total_steps": 25209, "loss": 0.3366, "lr": 3.368015347838413e-05, "epoch": 1.432821611329287, "percentage": 47.76, "elapsed_time": "19:15:11", "remaining_time": "21:03:30", "throughput": 58182.39, "total_tokens": 4032694272} {"current_steps": 12050, "total_steps": 25209, "loss": 0.3341, "lr": 3.3672515042824855e-05, "epoch": 1.4340116625014876, "percentage": 47.8, "elapsed_time": "19:15:56", "remaining_time": "21:02:19", "throughput": 58191.31, "total_tokens": 4035933312} {"current_steps": 12060, "total_steps": 25209, "loss": 0.3331, "lr": 3.366488180194904e-05, "epoch": 1.4352017136736879, "percentage": 47.84, "elapsed_time": "19:16:43", "remaining_time": "21:01:10", "throughput": 58200.31, "total_tokens": 4039298688} {"current_steps": 12070, "total_steps": 25209, "loss": 0.3305, "lr": 3.365725374987143e-05, "epoch": 1.4363917648458884, "percentage": 47.88, "elapsed_time": "19:17:31", "remaining_time": "21:00:02", "throughput": 58208.18, "total_tokens": 4042665344} {"current_steps": 12080, "total_steps": 25209, "loss": 0.3342, "lr": 3.36496308807161e-05, "epoch": 1.4375818160180889, "percentage": 47.92, "elapsed_time": "19:18:22", "remaining_time": "20:58:57", "throughput": 58215.08, "total_tokens": 4046084480} {"current_steps": 12090, "total_steps": 25209, "loss": 0.3372, "lr": 3.3642013188616426e-05, "epoch": 1.4387718671902892, "percentage": 47.96, "elapsed_time": "19:19:06", "remaining_time": "20:57:46", "throughput": 58223.47, "total_tokens": 4049263360} {"current_steps": 12100, "total_steps": 25209, "loss": 0.3382, "lr": 3.3634400667715074e-05, "epoch": 1.4399619183624897, "percentage": 48.0, "elapsed_time": "19:19:53", "remaining_time": "20:56:36", "throughput": 58231.89, "total_tokens": 4052558464} {"current_steps": 12110, "total_steps": 25209, "loss": 0.33, "lr": 3.3626793312164013e-05, "epoch": 1.44115196953469, "percentage": 48.04, "elapsed_time": "19:20:42", "remaining_time": "20:55:29", "throughput": 58238.87, "total_tokens": 4055877376} {"current_steps": 12120, "total_steps": 25209, "loss": 0.3364, "lr": 3.361919111612443e-05, "epoch": 1.4423420207068904, "percentage": 48.08, "elapsed_time": "19:21:30", "remaining_time": "20:54:22", "throughput": 58246.33, "total_tokens": 4059237248} {"current_steps": 12130, "total_steps": 25209, "loss": 0.3352, "lr": 3.361159407376678e-05, "epoch": 1.443532071879091, "percentage": 48.12, "elapsed_time": "19:22:14", "remaining_time": "20:53:10", "throughput": 58256.41, "total_tokens": 4062486784} {"current_steps": 12140, "total_steps": 25209, "loss": 0.3361, "lr": 3.3604002179270685e-05, "epoch": 1.4447221230512912, "percentage": 48.16, "elapsed_time": "19:23:02", "remaining_time": "20:52:02", "throughput": 58264.07, "total_tokens": 4065799168} {"current_steps": 12150, "total_steps": 25209, "loss": 0.3337, "lr": 3.359641542682504e-05, "epoch": 1.4459121742234915, "percentage": 48.2, "elapsed_time": "19:23:53", "remaining_time": "20:50:58", "throughput": 58269.99, "total_tokens": 4069221376} {"current_steps": 12160, "total_steps": 25209, "loss": 0.3298, "lr": 3.3588833810627854e-05, "epoch": 1.447102225395692, "percentage": 48.24, "elapsed_time": "19:24:44", "remaining_time": "20:49:53", "throughput": 58276.33, "total_tokens": 4072607104} {"current_steps": 12170, "total_steps": 25209, "loss": 0.3325, "lr": 3.358125732488632e-05, "epoch": 1.4482922765678925, "percentage": 48.28, "elapsed_time": "19:25:33", "remaining_time": "20:48:47", "throughput": 58283.08, "total_tokens": 4075938432} {"current_steps": 12180, "total_steps": 25209, "loss": 0.3345, "lr": 3.357368596381679e-05, "epoch": 1.4494823277400928, "percentage": 48.32, "elapsed_time": "19:26:23", "remaining_time": "20:47:42", "throughput": 58290.32, "total_tokens": 4079380736} {"current_steps": 12190, "total_steps": 25209, "loss": 0.3379, "lr": 3.356611972164471e-05, "epoch": 1.4506723789122933, "percentage": 48.36, "elapsed_time": "19:27:08", "remaining_time": "20:46:30", "throughput": 58300.38, "total_tokens": 4082678912} {"current_steps": 12200, "total_steps": 25209, "loss": 0.3348, "lr": 3.355855859260466e-05, "epoch": 1.4518624300844936, "percentage": 48.4, "elapsed_time": "19:27:58", "remaining_time": "20:45:26", "throughput": 58307.2, "total_tokens": 4086109312} {"current_steps": 12210, "total_steps": 25209, "loss": 0.3324, "lr": 3.3551002570940285e-05, "epoch": 1.453052481256694, "percentage": 48.44, "elapsed_time": "19:28:47", "remaining_time": "20:44:19", "throughput": 58314.52, "total_tokens": 4089451264} {"current_steps": 12220, "total_steps": 25209, "loss": 0.3348, "lr": 3.354345165090431e-05, "epoch": 1.4542425324288946, "percentage": 48.47, "elapsed_time": "19:29:37", "remaining_time": "20:43:13", "throughput": 58321.0, "total_tokens": 4092794880} {"current_steps": 12230, "total_steps": 25209, "loss": 0.3378, "lr": 3.3535905826758515e-05, "epoch": 1.4554325836010948, "percentage": 48.51, "elapsed_time": "19:30:25", "remaining_time": "20:42:05", "throughput": 58329.21, "total_tokens": 4096173184} {"current_steps": 12240, "total_steps": 25209, "loss": 0.333, "lr": 3.352836509277369e-05, "epoch": 1.4566226347732951, "percentage": 48.55, "elapsed_time": "19:31:12", "remaining_time": "20:40:58", "throughput": 58337.83, "total_tokens": 4099560064} {"current_steps": 12250, "total_steps": 25209, "loss": 0.3357, "lr": 3.352082944322966e-05, "epoch": 1.4578126859454956, "percentage": 48.59, "elapsed_time": "19:31:59", "remaining_time": "20:39:49", "throughput": 58347.02, "total_tokens": 4102923648} {"current_steps": 12260, "total_steps": 25209, "loss": 0.3324, "lr": 3.351329887241524e-05, "epoch": 1.4590027371176961, "percentage": 48.63, "elapsed_time": "19:32:46", "remaining_time": "20:38:40", "throughput": 58355.12, "total_tokens": 4106220672} {"current_steps": 12270, "total_steps": 25209, "loss": 0.3311, "lr": 3.3505773374628225e-05, "epoch": 1.4601927882898964, "percentage": 48.67, "elapsed_time": "19:33:37", "remaining_time": "20:37:36", "throughput": 58361.5, "total_tokens": 4109655808} {"current_steps": 12280, "total_steps": 25209, "loss": 0.3358, "lr": 3.3498252944175354e-05, "epoch": 1.461382839462097, "percentage": 48.71, "elapsed_time": "19:34:25", "remaining_time": "20:36:29", "throughput": 58369.52, "total_tokens": 4113014784} {"current_steps": 12290, "total_steps": 25209, "loss": 0.3374, "lr": 3.3490737575372326e-05, "epoch": 1.4625728906342972, "percentage": 48.75, "elapsed_time": "19:35:13", "remaining_time": "20:35:21", "throughput": 58377.87, "total_tokens": 4116401664} {"current_steps": 12300, "total_steps": 25209, "loss": 0.3411, "lr": 3.348322726254375e-05, "epoch": 1.4637629418064977, "percentage": 48.79, "elapsed_time": "19:35:57", "remaining_time": "20:34:10", "throughput": 58386.89, "total_tokens": 4119622016} {"current_steps": 12310, "total_steps": 25209, "loss": 0.3366, "lr": 3.347572200002315e-05, "epoch": 1.4649529929786982, "percentage": 48.83, "elapsed_time": "19:36:47", "remaining_time": "20:33:06", "throughput": 58393.4, "total_tokens": 4123020416} {"current_steps": 12320, "total_steps": 25209, "loss": 0.3365, "lr": 3.3468221782152924e-05, "epoch": 1.4661430441508985, "percentage": 48.87, "elapsed_time": "19:37:37", "remaining_time": "20:32:00", "throughput": 58399.94, "total_tokens": 4126383488} {"current_steps": 12330, "total_steps": 25209, "loss": 0.3331, "lr": 3.346072660328435e-05, "epoch": 1.467333095323099, "percentage": 48.91, "elapsed_time": "19:38:27", "remaining_time": "20:30:55", "throughput": 58406.64, "total_tokens": 4129781760} {"current_steps": 12340, "total_steps": 25209, "loss": 0.3389, "lr": 3.345323645777756e-05, "epoch": 1.4685231464952992, "percentage": 48.95, "elapsed_time": "19:39:14", "remaining_time": "20:29:47", "throughput": 58414.62, "total_tokens": 4133115008} {"current_steps": 12350, "total_steps": 25209, "loss": 0.3357, "lr": 3.34457513400015e-05, "epoch": 1.4697131976674997, "percentage": 48.99, "elapsed_time": "19:40:00", "remaining_time": "20:28:38", "throughput": 58423.57, "total_tokens": 4136421632} {"current_steps": 12360, "total_steps": 25209, "loss": 0.3333, "lr": 3.343827124433396e-05, "epoch": 1.4709032488397, "percentage": 49.03, "elapsed_time": "19:40:48", "remaining_time": "20:27:30", "throughput": 58431.79, "total_tokens": 4139777024} {"current_steps": 12370, "total_steps": 25209, "loss": 0.3313, "lr": 3.343079616516151e-05, "epoch": 1.4720933000119005, "percentage": 49.07, "elapsed_time": "19:41:36", "remaining_time": "20:26:24", "throughput": 58439.21, "total_tokens": 4143117696} {"current_steps": 12380, "total_steps": 25209, "loss": 0.3349, "lr": 3.3423326096879495e-05, "epoch": 1.4732833511841008, "percentage": 49.11, "elapsed_time": "19:42:28", "remaining_time": "20:25:21", "throughput": 58445.49, "total_tokens": 4146609024} {"current_steps": 12390, "total_steps": 25209, "loss": 0.3341, "lr": 3.341586103389203e-05, "epoch": 1.4744734023563013, "percentage": 49.15, "elapsed_time": "19:43:19", "remaining_time": "20:24:17", "throughput": 58452.08, "total_tokens": 4150065536} {"current_steps": 12400, "total_steps": 25209, "loss": 0.3357, "lr": 3.3408400970611995e-05, "epoch": 1.4756634535285018, "percentage": 49.19, "elapsed_time": "19:44:06", "remaining_time": "20:23:09", "throughput": 58460.07, "total_tokens": 4153357824} {"current_steps": 12410, "total_steps": 25209, "loss": 0.3356, "lr": 3.340094590146095e-05, "epoch": 1.476853504700702, "percentage": 49.23, "elapsed_time": "19:44:55", "remaining_time": "20:22:03", "throughput": 58467.65, "total_tokens": 4156771712} {"current_steps": 12420, "total_steps": 25209, "loss": 0.3319, "lr": 3.3393495820869215e-05, "epoch": 1.4780435558729026, "percentage": 49.27, "elapsed_time": "19:45:43", "remaining_time": "20:20:57", "throughput": 58474.9, "total_tokens": 4160113280} {"current_steps": 12430, "total_steps": 25209, "loss": 0.333, "lr": 3.338605072327576e-05, "epoch": 1.4792336070451029, "percentage": 49.31, "elapsed_time": "19:46:31", "remaining_time": "20:19:50", "throughput": 58483.34, "total_tokens": 4163522816} {"current_steps": 12440, "total_steps": 25209, "loss": 0.3364, "lr": 3.337861060312827e-05, "epoch": 1.4804236582173034, "percentage": 49.35, "elapsed_time": "19:47:18", "remaining_time": "20:18:42", "throughput": 58491.31, "total_tokens": 4166811008} {"current_steps": 12450, "total_steps": 25209, "loss": 0.3338, "lr": 3.337117545488306e-05, "epoch": 1.4816137093895039, "percentage": 49.39, "elapsed_time": "19:48:05", "remaining_time": "20:17:34", "throughput": 58498.84, "total_tokens": 4170123264} {"current_steps": 12460, "total_steps": 25209, "loss": 0.3315, "lr": 3.33637452730051e-05, "epoch": 1.4828037605617042, "percentage": 49.43, "elapsed_time": "19:48:51", "remaining_time": "20:16:25", "throughput": 58507.54, "total_tokens": 4173407232} {"current_steps": 12470, "total_steps": 25209, "loss": 0.3389, "lr": 3.335632005196796e-05, "epoch": 1.4839938117339044, "percentage": 49.47, "elapsed_time": "19:49:36", "remaining_time": "20:15:16", "throughput": 58516.83, "total_tokens": 4176731264} {"current_steps": 12480, "total_steps": 25209, "loss": 0.3385, "lr": 3.334889978625383e-05, "epoch": 1.485183862906105, "percentage": 49.51, "elapsed_time": "19:50:22", "remaining_time": "20:14:07", "throughput": 58525.54, "total_tokens": 4180024576} {"current_steps": 12490, "total_steps": 25209, "loss": 0.3329, "lr": 3.3341484470353515e-05, "epoch": 1.4863739140783054, "percentage": 49.55, "elapsed_time": "19:51:11", "remaining_time": "20:13:01", "throughput": 58532.45, "total_tokens": 4183388544} {"current_steps": 12500, "total_steps": 25209, "loss": 0.337, "lr": 3.333407409876635e-05, "epoch": 1.4875639652505057, "percentage": 49.59, "elapsed_time": "19:51:58", "remaining_time": "20:11:54", "throughput": 58539.39, "total_tokens": 4186675968} {"current_steps": 12510, "total_steps": 25209, "loss": 0.3337, "lr": 3.332666866600024e-05, "epoch": 1.4887540164227062, "percentage": 49.63, "elapsed_time": "19:52:47", "remaining_time": "20:10:48", "throughput": 58547.09, "total_tokens": 4190066176} {"current_steps": 12520, "total_steps": 25209, "loss": 0.3374, "lr": 3.331926816657162e-05, "epoch": 1.4899440675949065, "percentage": 49.66, "elapsed_time": "19:53:38", "remaining_time": "20:09:45", "throughput": 58553.21, "total_tokens": 4193511040} {"current_steps": 12530, "total_steps": 25209, "loss": 0.3351, "lr": 3.331187259500546e-05, "epoch": 1.491134118767107, "percentage": 49.7, "elapsed_time": "19:54:23", "remaining_time": "20:08:35", "throughput": 58561.84, "total_tokens": 4196725632} {"current_steps": 12540, "total_steps": 25209, "loss": 0.3389, "lr": 3.3304481945835235e-05, "epoch": 1.4923241699393075, "percentage": 49.74, "elapsed_time": "19:55:10", "remaining_time": "20:07:28", "throughput": 58569.56, "total_tokens": 4200074112} {"current_steps": 12550, "total_steps": 25209, "loss": 0.3349, "lr": 3.329709621360288e-05, "epoch": 1.4935142211115078, "percentage": 49.78, "elapsed_time": "19:56:00", "remaining_time": "20:06:23", "throughput": 58575.77, "total_tokens": 4203430528} {"current_steps": 12560, "total_steps": 25209, "loss": 0.3381, "lr": 3.328971539285882e-05, "epoch": 1.4947042722837083, "percentage": 49.82, "elapsed_time": "19:56:46", "remaining_time": "20:05:15", "throughput": 58583.77, "total_tokens": 4206724224} {"current_steps": 12570, "total_steps": 25209, "loss": 0.3371, "lr": 3.3282339478161935e-05, "epoch": 1.4958943234559086, "percentage": 49.86, "elapsed_time": "19:57:34", "remaining_time": "20:04:09", "throughput": 58591.01, "total_tokens": 4210032768} {"current_steps": 12580, "total_steps": 25209, "loss": 0.3377, "lr": 3.327496846407953e-05, "epoch": 1.497084374628109, "percentage": 49.9, "elapsed_time": "19:58:21", "remaining_time": "20:03:01", "throughput": 58598.95, "total_tokens": 4213371392} {"current_steps": 12590, "total_steps": 25209, "loss": 0.3341, "lr": 3.3267602345187304e-05, "epoch": 1.4982744258003093, "percentage": 49.94, "elapsed_time": "19:59:11", "remaining_time": "20:01:56", "throughput": 58605.0, "total_tokens": 4216704128} {"current_steps": 12600, "total_steps": 25209, "loss": 0.3392, "lr": 3.326024111606942e-05, "epoch": 1.4994644769725098, "percentage": 49.98, "elapsed_time": "19:59:58", "remaining_time": "20:00:50", "throughput": 58612.76, "total_tokens": 4220049664} {"current_steps": 12610, "total_steps": 25209, "loss": 0.3348, "lr": 3.325288477131839e-05, "epoch": 1.5006545281447101, "percentage": 50.02, "elapsed_time": "20:00:45", "remaining_time": "19:59:42", "throughput": 58620.98, "total_tokens": 4223395584} {"current_steps": 12620, "total_steps": 25209, "loss": 0.3325, "lr": 3.324553330553507e-05, "epoch": 1.5018445793169106, "percentage": 50.06, "elapsed_time": "20:01:36", "remaining_time": "19:58:39", "throughput": 58627.48, "total_tokens": 4226821504} {"current_steps": 12630, "total_steps": 25209, "loss": 0.3342, "lr": 3.323818671332871e-05, "epoch": 1.5030346304891111, "percentage": 50.1, "elapsed_time": "20:02:24", "remaining_time": "19:57:33", "throughput": 58635.71, "total_tokens": 4230258816} {"current_steps": 12640, "total_steps": 25209, "loss": 0.3321, "lr": 3.323084498931687e-05, "epoch": 1.5042246816613114, "percentage": 50.14, "elapsed_time": "20:03:15", "remaining_time": "19:56:29", "throughput": 58640.93, "total_tokens": 4233586944} {"current_steps": 12650, "total_steps": 25209, "loss": 0.3386, "lr": 3.322350812812545e-05, "epoch": 1.5054147328335117, "percentage": 50.18, "elapsed_time": "20:04:03", "remaining_time": "19:55:23", "throughput": 58647.55, "total_tokens": 4236886912} {"current_steps": 12660, "total_steps": 25209, "loss": 0.3304, "lr": 3.321617612438862e-05, "epoch": 1.5066047840057122, "percentage": 50.22, "elapsed_time": "20:04:50", "remaining_time": "19:54:16", "throughput": 58655.64, "total_tokens": 4240260096} {"current_steps": 12670, "total_steps": 25209, "loss": 0.3333, "lr": 3.320884897274886e-05, "epoch": 1.5077948351779127, "percentage": 50.26, "elapsed_time": "20:05:36", "remaining_time": "19:53:08", "throughput": 58663.44, "total_tokens": 4243496192} {"current_steps": 12680, "total_steps": 25209, "loss": 0.3327, "lr": 3.320152666785692e-05, "epoch": 1.5089848863501132, "percentage": 50.3, "elapsed_time": "20:06:27", "remaining_time": "19:52:05", "throughput": 58669.47, "total_tokens": 4246939264} {"current_steps": 12690, "total_steps": 25209, "loss": 0.3292, "lr": 3.319420920437179e-05, "epoch": 1.5101749375223135, "percentage": 50.34, "elapsed_time": "20:07:15", "remaining_time": "19:50:59", "throughput": 58676.98, "total_tokens": 4250321792} {"current_steps": 12700, "total_steps": 25209, "loss": 0.3345, "lr": 3.31868965769607e-05, "epoch": 1.5113649886945137, "percentage": 50.38, "elapsed_time": "20:08:05", "remaining_time": "19:49:55", "throughput": 58682.76, "total_tokens": 4253644928} {"current_steps": 12710, "total_steps": 25209, "loss": 0.3358, "lr": 3.317958878029911e-05, "epoch": 1.5125550398667142, "percentage": 50.42, "elapsed_time": "20:08:54", "remaining_time": "19:48:50", "throughput": 58690.19, "total_tokens": 4257051904} {"current_steps": 12720, "total_steps": 25209, "loss": 0.3337, "lr": 3.3172285809070665e-05, "epoch": 1.5137450910389147, "percentage": 50.46, "elapsed_time": "20:09:45", "remaining_time": "19:47:47", "throughput": 58695.47, "total_tokens": 4260428160} {"current_steps": 12730, "total_steps": 25209, "loss": 0.3355, "lr": 3.3164987657967214e-05, "epoch": 1.514935142211115, "percentage": 50.5, "elapsed_time": "20:10:34", "remaining_time": "19:46:41", "throughput": 58703.55, "total_tokens": 4263874944} {"current_steps": 12740, "total_steps": 25209, "loss": 0.3353, "lr": 3.315769432168877e-05, "epoch": 1.5161251933833155, "percentage": 50.54, "elapsed_time": "20:11:19", "remaining_time": "19:45:33", "throughput": 58711.88, "total_tokens": 4267174656} {"current_steps": 12750, "total_steps": 25209, "loss": 0.3352, "lr": 3.315040579494349e-05, "epoch": 1.5173152445555158, "percentage": 50.58, "elapsed_time": "20:12:05", "remaining_time": "19:44:26", "throughput": 58719.92, "total_tokens": 4270463616} {"current_steps": 12760, "total_steps": 25209, "loss": 0.3333, "lr": 3.31431220724477e-05, "epoch": 1.5185052957277163, "percentage": 50.62, "elapsed_time": "20:12:54", "remaining_time": "19:43:20", "throughput": 58727.11, "total_tokens": 4273826944} {"current_steps": 12770, "total_steps": 25209, "loss": 0.3373, "lr": 3.3135843148925834e-05, "epoch": 1.5196953468999168, "percentage": 50.66, "elapsed_time": "20:13:43", "remaining_time": "19:42:16", "throughput": 58734.29, "total_tokens": 4277259264} {"current_steps": 12780, "total_steps": 25209, "loss": 0.3348, "lr": 3.3128569019110414e-05, "epoch": 1.520885398072117, "percentage": 50.7, "elapsed_time": "20:14:31", "remaining_time": "19:41:10", "throughput": 58741.57, "total_tokens": 4280589824} {"current_steps": 12790, "total_steps": 25209, "loss": 0.3382, "lr": 3.312129967774207e-05, "epoch": 1.5220754492443174, "percentage": 50.74, "elapsed_time": "20:15:18", "remaining_time": "19:40:03", "throughput": 58749.59, "total_tokens": 4283917824} {"current_steps": 12800, "total_steps": 25209, "loss": 0.3346, "lr": 3.311403511956952e-05, "epoch": 1.5232655004165179, "percentage": 50.78, "elapsed_time": "20:16:01", "remaining_time": "19:38:52", "throughput": 58758.59, "total_tokens": 4287104768} {"current_steps": 12810, "total_steps": 25209, "loss": 0.3367, "lr": 3.310677533934952e-05, "epoch": 1.5244555515887184, "percentage": 50.82, "elapsed_time": "20:16:51", "remaining_time": "19:37:48", "throughput": 58764.07, "total_tokens": 4290426368} {"current_steps": 12820, "total_steps": 25209, "loss": 0.3361, "lr": 3.309952033184686e-05, "epoch": 1.5256456027609189, "percentage": 50.85, "elapsed_time": "20:17:39", "remaining_time": "19:36:42", "throughput": 58771.42, "total_tokens": 4293785856} {"current_steps": 12830, "total_steps": 25209, "loss": 0.3289, "lr": 3.309227009183439e-05, "epoch": 1.5268356539331192, "percentage": 50.89, "elapsed_time": "20:18:31", "remaining_time": "19:35:41", "throughput": 58776.82, "total_tokens": 4297245824} {"current_steps": 12840, "total_steps": 25209, "loss": 0.3363, "lr": 3.308502461409295e-05, "epoch": 1.5280257051053194, "percentage": 50.93, "elapsed_time": "20:19:19", "remaining_time": "19:34:36", "throughput": 58783.72, "total_tokens": 4300601600} {"current_steps": 12850, "total_steps": 25209, "loss": 0.3302, "lr": 3.3077783893411386e-05, "epoch": 1.52921575627752, "percentage": 50.97, "elapsed_time": "20:20:08", "remaining_time": "19:33:31", "throughput": 58790.62, "total_tokens": 4303996160} {"current_steps": 12860, "total_steps": 25209, "loss": 0.3346, "lr": 3.30705479245865e-05, "epoch": 1.5304058074497204, "percentage": 51.01, "elapsed_time": "20:20:56", "remaining_time": "19:32:25", "throughput": 58797.61, "total_tokens": 4307326848} {"current_steps": 12870, "total_steps": 25209, "loss": 0.3345, "lr": 3.3063316702423094e-05, "epoch": 1.5315958586219207, "percentage": 51.05, "elapsed_time": "20:21:42", "remaining_time": "19:31:18", "throughput": 58805.1, "total_tokens": 4310568320} {"current_steps": 12880, "total_steps": 25209, "loss": 0.3348, "lr": 3.305609022173388e-05, "epoch": 1.532785909794121, "percentage": 51.09, "elapsed_time": "20:22:29", "remaining_time": "19:30:11", "throughput": 58812.75, "total_tokens": 4313896448} {"current_steps": 12890, "total_steps": 25209, "loss": 0.3326, "lr": 3.304886847733954e-05, "epoch": 1.5339759609663215, "percentage": 51.13, "elapsed_time": "20:23:16", "remaining_time": "19:29:04", "throughput": 58820.24, "total_tokens": 4317174528} {"current_steps": 12900, "total_steps": 25209, "loss": 0.3354, "lr": 3.304165146406865e-05, "epoch": 1.535166012138522, "percentage": 51.17, "elapsed_time": "20:24:02", "remaining_time": "19:27:57", "throughput": 58828.17, "total_tokens": 4320459008} {"current_steps": 12910, "total_steps": 25209, "loss": 0.3306, "lr": 3.30344391767577e-05, "epoch": 1.5363560633107225, "percentage": 51.21, "elapsed_time": "20:24:52", "remaining_time": "19:26:54", "throughput": 58833.63, "total_tokens": 4323831424} {"current_steps": 12920, "total_steps": 25209, "loss": 0.3344, "lr": 3.302723161025104e-05, "epoch": 1.5375461144829228, "percentage": 51.25, "elapsed_time": "20:25:41", "remaining_time": "19:25:49", "throughput": 58839.55, "total_tokens": 4327146880} {"current_steps": 12930, "total_steps": 25209, "loss": 0.3289, "lr": 3.302002875940093e-05, "epoch": 1.538736165655123, "percentage": 51.29, "elapsed_time": "20:26:33", "remaining_time": "19:24:47", "throughput": 58844.58, "total_tokens": 4330550144} {"current_steps": 12940, "total_steps": 25209, "loss": 0.3324, "lr": 3.3012830619067466e-05, "epoch": 1.5399262168273236, "percentage": 51.33, "elapsed_time": "20:27:21", "remaining_time": "19:23:42", "throughput": 58851.68, "total_tokens": 4333905920} {"current_steps": 12950, "total_steps": 25209, "loss": 0.3348, "lr": 3.300563718411857e-05, "epoch": 1.541116267999524, "percentage": 51.37, "elapsed_time": "20:28:08", "remaining_time": "19:22:36", "throughput": 58859.77, "total_tokens": 4337293312} {"current_steps": 12960, "total_steps": 25209, "loss": 0.3341, "lr": 3.299844844943e-05, "epoch": 1.5423063191717243, "percentage": 51.41, "elapsed_time": "20:28:54", "remaining_time": "19:21:29", "throughput": 58868.0, "total_tokens": 4340611456} {"current_steps": 12970, "total_steps": 25209, "loss": 0.3333, "lr": 3.299126440988535e-05, "epoch": 1.5434963703439248, "percentage": 51.45, "elapsed_time": "20:29:41", "remaining_time": "19:20:23", "throughput": 58875.1, "total_tokens": 4343920256} {"current_steps": 12980, "total_steps": 25209, "loss": 0.3335, "lr": 3.298408506037596e-05, "epoch": 1.5446864215161251, "percentage": 51.49, "elapsed_time": "20:30:32", "remaining_time": "19:19:20", "throughput": 58881.56, "total_tokens": 4347354752} {"current_steps": 12990, "total_steps": 25209, "loss": 0.3342, "lr": 3.297691039580097e-05, "epoch": 1.5458764726883256, "percentage": 51.53, "elapsed_time": "20:31:19", "remaining_time": "19:18:14", "throughput": 58889.68, "total_tokens": 4350760448} {"current_steps": 13000, "total_steps": 25209, "loss": 0.3318, "lr": 3.29697404110673e-05, "epoch": 1.5470665238605261, "percentage": 51.57, "elapsed_time": "20:32:11", "remaining_time": "19:17:12", "throughput": 58894.78, "total_tokens": 4354175872} {"current_steps": 13010, "total_steps": 25209, "loss": 0.3337, "lr": 3.2962575101089594e-05, "epoch": 1.5482565750327264, "percentage": 51.61, "elapsed_time": "20:33:05", "remaining_time": "19:16:13", "throughput": 58897.8, "total_tokens": 4357580288} {"current_steps": 13020, "total_steps": 25209, "loss": 0.3352, "lr": 3.295541446079024e-05, "epoch": 1.5494466262049267, "percentage": 51.65, "elapsed_time": "20:33:51", "remaining_time": "19:15:06", "throughput": 58905.76, "total_tokens": 4360872832} {"current_steps": 13030, "total_steps": 25209, "loss": 0.3347, "lr": 3.2948258485099336e-05, "epoch": 1.5506366773771272, "percentage": 51.69, "elapsed_time": "20:34:40", "remaining_time": "19:14:02", "throughput": 58912.18, "total_tokens": 4364245376} {"current_steps": 13040, "total_steps": 25209, "loss": 0.3302, "lr": 3.29411071689547e-05, "epoch": 1.5518267285493277, "percentage": 51.73, "elapsed_time": "20:35:33", "remaining_time": "19:13:01", "throughput": 58915.82, "total_tokens": 4367628288} {"current_steps": 13050, "total_steps": 25209, "loss": 0.3315, "lr": 3.2933960507301826e-05, "epoch": 1.5530167797215282, "percentage": 51.77, "elapsed_time": "20:36:18", "remaining_time": "19:11:54", "throughput": 58923.38, "total_tokens": 4370867328} {"current_steps": 13060, "total_steps": 25209, "loss": 0.3324, "lr": 3.292681849509387e-05, "epoch": 1.5542068308937285, "percentage": 51.81, "elapsed_time": "20:37:07", "remaining_time": "19:10:49", "throughput": 58929.89, "total_tokens": 4374203904} {"current_steps": 13070, "total_steps": 25209, "loss": 0.3333, "lr": 3.291968112729166e-05, "epoch": 1.5553968820659287, "percentage": 51.85, "elapsed_time": "20:37:55", "remaining_time": "19:09:44", "throughput": 58936.28, "total_tokens": 4377513216} {"current_steps": 13080, "total_steps": 25209, "loss": 0.3337, "lr": 3.291254839886367e-05, "epoch": 1.5565869332381292, "percentage": 51.89, "elapsed_time": "20:38:42", "remaining_time": "19:08:39", "throughput": 58942.64, "total_tokens": 4380782592} {"current_steps": 13090, "total_steps": 25209, "loss": 0.3363, "lr": 3.2905420304785995e-05, "epoch": 1.5577769844103297, "percentage": 51.93, "elapsed_time": "20:39:32", "remaining_time": "19:07:35", "throughput": 58948.97, "total_tokens": 4384183424} {"current_steps": 13100, "total_steps": 25209, "loss": 0.3356, "lr": 3.289829684004235e-05, "epoch": 1.55896703558253, "percentage": 51.97, "elapsed_time": "20:40:25", "remaining_time": "19:06:34", "throughput": 58953.31, "total_tokens": 4387610496} {"current_steps": 13110, "total_steps": 25209, "loss": 0.332, "lr": 3.289117799962402e-05, "epoch": 1.5601570867547303, "percentage": 52.01, "elapsed_time": "20:41:14", "remaining_time": "19:05:31", "throughput": 58959.72, "total_tokens": 4390996992} {"current_steps": 13120, "total_steps": 25209, "loss": 0.337, "lr": 3.2884063778529914e-05, "epoch": 1.5613471379269308, "percentage": 52.04, "elapsed_time": "20:42:06", "remaining_time": "19:04:29", "throughput": 58962.44, "total_tokens": 4394259328} {"current_steps": 13130, "total_steps": 25209, "loss": 0.3353, "lr": 3.28769541717665e-05, "epoch": 1.5625371890991313, "percentage": 52.08, "elapsed_time": "20:42:58", "remaining_time": "19:03:28", "throughput": 58966.71, "total_tokens": 4397656832} {"current_steps": 13140, "total_steps": 25209, "loss": 0.3354, "lr": 3.2869849174347775e-05, "epoch": 1.5637272402713318, "percentage": 52.12, "elapsed_time": "20:43:50", "remaining_time": "19:02:27", "throughput": 58972.26, "total_tokens": 4401114496} {"current_steps": 13150, "total_steps": 25209, "loss": 0.3365, "lr": 3.2862748781295294e-05, "epoch": 1.564917291443532, "percentage": 52.16, "elapsed_time": "20:44:41", "remaining_time": "19:01:25", "throughput": 58977.59, "total_tokens": 4404519424} {"current_steps": 13160, "total_steps": 25209, "loss": 0.3328, "lr": 3.2855652987638146e-05, "epoch": 1.5661073426157324, "percentage": 52.2, "elapsed_time": "20:45:30", "remaining_time": "19:00:21", "throughput": 58983.51, "total_tokens": 4407866880} {"current_steps": 13170, "total_steps": 25209, "loss": 0.335, "lr": 3.284856178841291e-05, "epoch": 1.5672973937879329, "percentage": 52.24, "elapsed_time": "20:46:17", "remaining_time": "18:59:15", "throughput": 58991.05, "total_tokens": 4411178368} {"current_steps": 13180, "total_steps": 25209, "loss": 0.3331, "lr": 3.284147517866367e-05, "epoch": 1.5684874449601334, "percentage": 52.28, "elapsed_time": "20:47:03", "remaining_time": "18:58:08", "throughput": 58999.34, "total_tokens": 4414516864} {"current_steps": 13190, "total_steps": 25209, "loss": 0.3363, "lr": 3.2834393153441976e-05, "epoch": 1.5696774961323336, "percentage": 52.32, "elapsed_time": "20:47:51", "remaining_time": "18:57:04", "throughput": 59005.42, "total_tokens": 4417846272} {"current_steps": 13200, "total_steps": 25209, "loss": 0.3316, "lr": 3.282731570780689e-05, "epoch": 1.570867547304534, "percentage": 52.36, "elapsed_time": "20:48:42", "remaining_time": "18:56:02", "throughput": 59010.78, "total_tokens": 4421228416} {"current_steps": 13210, "total_steps": 25209, "loss": 0.3373, "lr": 3.2820242836824875e-05, "epoch": 1.5720575984767344, "percentage": 52.4, "elapsed_time": "20:49:32", "remaining_time": "18:54:59", "throughput": 59016.23, "total_tokens": 4424595968} {"current_steps": 13220, "total_steps": 25209, "loss": 0.3336, "lr": 3.2813174535569854e-05, "epoch": 1.573247649648935, "percentage": 52.44, "elapsed_time": "20:50:19", "remaining_time": "18:53:54", "throughput": 59023.18, "total_tokens": 4427899776} {"current_steps": 13230, "total_steps": 25209, "loss": 0.3324, "lr": 3.280611079912318e-05, "epoch": 1.5744377008211354, "percentage": 52.48, "elapsed_time": "20:51:07", "remaining_time": "18:52:49", "throughput": 59029.75, "total_tokens": 4431226752} {"current_steps": 13240, "total_steps": 25209, "loss": 0.3347, "lr": 3.279905162257358e-05, "epoch": 1.5756277519933357, "percentage": 52.52, "elapsed_time": "20:51:55", "remaining_time": "18:51:44", "throughput": 59036.02, "total_tokens": 4434505984} {"current_steps": 13250, "total_steps": 25209, "loss": 0.3378, "lr": 3.279199700101723e-05, "epoch": 1.576817803165536, "percentage": 52.56, "elapsed_time": "20:52:42", "remaining_time": "18:50:38", "throughput": 59043.58, "total_tokens": 4437843584} {"current_steps": 13260, "total_steps": 25209, "loss": 0.3337, "lr": 3.2784946929557644e-05, "epoch": 1.5780078543377365, "percentage": 52.6, "elapsed_time": "20:53:27", "remaining_time": "18:49:31", "throughput": 59051.44, "total_tokens": 4441120000} {"current_steps": 13270, "total_steps": 25209, "loss": 0.3324, "lr": 3.277790140330571e-05, "epoch": 1.579197905509937, "percentage": 52.64, "elapsed_time": "20:54:16", "remaining_time": "18:48:27", "throughput": 59057.39, "total_tokens": 4444437888} {"current_steps": 13280, "total_steps": 25209, "loss": 0.3321, "lr": 3.277086041737968e-05, "epoch": 1.5803879566821375, "percentage": 52.68, "elapsed_time": "20:55:02", "remaining_time": "18:47:21", "throughput": 59065.44, "total_tokens": 4447760128} {"current_steps": 13290, "total_steps": 25209, "loss": 0.3349, "lr": 3.276382396690513e-05, "epoch": 1.5815780078543378, "percentage": 52.72, "elapsed_time": "20:55:51", "remaining_time": "18:46:18", "throughput": 59071.28, "total_tokens": 4451114496} {"current_steps": 13300, "total_steps": 25209, "loss": 0.3314, "lr": 3.275679204701496e-05, "epoch": 1.582768059026538, "percentage": 52.76, "elapsed_time": "20:56:41", "remaining_time": "18:45:15", "throughput": 59077.45, "total_tokens": 4454526976} {"current_steps": 13310, "total_steps": 25209, "loss": 0.3299, "lr": 3.274976465284939e-05, "epoch": 1.5839581101987386, "percentage": 52.8, "elapsed_time": "20:57:29", "remaining_time": "18:44:11", "throughput": 59084.96, "total_tokens": 4457938560} {"current_steps": 13320, "total_steps": 25209, "loss": 0.3329, "lr": 3.274274177955593e-05, "epoch": 1.585148161370939, "percentage": 52.84, "elapsed_time": "20:58:18", "remaining_time": "18:43:07", "throughput": 59091.01, "total_tokens": 4461310464} {"current_steps": 13330, "total_steps": 25209, "loss": 0.3281, "lr": 3.273572342228937e-05, "epoch": 1.5863382125431393, "percentage": 52.88, "elapsed_time": "20:59:08", "remaining_time": "18:42:04", "throughput": 59098.12, "total_tokens": 4464765568} {"current_steps": 13340, "total_steps": 25209, "loss": 0.3326, "lr": 3.272870957621176e-05, "epoch": 1.5875282637153396, "percentage": 52.92, "elapsed_time": "20:59:56", "remaining_time": "18:41:00", "throughput": 59106.03, "total_tokens": 4468226304} {"current_steps": 13350, "total_steps": 25209, "loss": 0.3301, "lr": 3.2721700236492414e-05, "epoch": 1.5887183148875401, "percentage": 52.96, "elapsed_time": "21:00:44", "remaining_time": "18:39:56", "throughput": 59112.9, "total_tokens": 4471578752} {"current_steps": 13360, "total_steps": 25209, "loss": 0.3278, "lr": 3.271469539830788e-05, "epoch": 1.5899083660597406, "percentage": 53.0, "elapsed_time": "21:01:35", "remaining_time": "18:38:53", "throughput": 59118.9, "total_tokens": 4475005440} {"current_steps": 13370, "total_steps": 25209, "loss": 0.3388, "lr": 3.270769505684193e-05, "epoch": 1.5910984172319411, "percentage": 53.04, "elapsed_time": "21:02:20", "remaining_time": "18:37:47", "throughput": 59126.61, "total_tokens": 4478261888} {"current_steps": 13380, "total_steps": 25209, "loss": 0.3337, "lr": 3.2700699207285544e-05, "epoch": 1.5922884684041414, "percentage": 53.08, "elapsed_time": "21:03:07", "remaining_time": "18:36:42", "throughput": 59132.94, "total_tokens": 4481549568} {"current_steps": 13390, "total_steps": 25209, "loss": 0.3351, "lr": 3.269370784483691e-05, "epoch": 1.5934785195763417, "percentage": 53.12, "elapsed_time": "21:03:55", "remaining_time": "18:35:37", "throughput": 59140.04, "total_tokens": 4484891648} {"current_steps": 13400, "total_steps": 25209, "loss": 0.3359, "lr": 3.268672096470138e-05, "epoch": 1.5946685707485422, "percentage": 53.16, "elapsed_time": "21:04:41", "remaining_time": "18:34:32", "throughput": 59147.69, "total_tokens": 4488238464} {"current_steps": 13410, "total_steps": 25209, "loss": 0.3346, "lr": 3.2679738562091506e-05, "epoch": 1.5958586219207427, "percentage": 53.2, "elapsed_time": "21:05:36", "remaining_time": "18:33:34", "throughput": 59148.23, "total_tokens": 4491534848} {"current_steps": 13420, "total_steps": 25209, "loss": 0.3375, "lr": 3.2672760632226964e-05, "epoch": 1.597048673092943, "percentage": 53.23, "elapsed_time": "21:06:25", "remaining_time": "18:32:30", "throughput": 59154.44, "total_tokens": 4494892032} {"current_steps": 13430, "total_steps": 25209, "loss": 0.3353, "lr": 3.266578717033458e-05, "epoch": 1.5982387242651432, "percentage": 53.27, "elapsed_time": "21:07:13", "remaining_time": "18:31:26", "throughput": 59160.73, "total_tokens": 4498223360} {"current_steps": 13440, "total_steps": 25209, "loss": 0.3373, "lr": 3.265881817164833e-05, "epoch": 1.5994287754373437, "percentage": 53.31, "elapsed_time": "21:08:01", "remaining_time": "18:30:22", "throughput": 59167.54, "total_tokens": 4501540736} {"current_steps": 13450, "total_steps": 25209, "loss": 0.3307, "lr": 3.265185363140928e-05, "epoch": 1.6006188266095442, "percentage": 53.35, "elapsed_time": "21:08:51", "remaining_time": "18:29:20", "throughput": 59173.69, "total_tokens": 4504997504} {"current_steps": 13460, "total_steps": 25209, "loss": 0.3336, "lr": 3.26448935448656e-05, "epoch": 1.6018088777817447, "percentage": 53.39, "elapsed_time": "21:09:39", "remaining_time": "18:28:16", "throughput": 59179.91, "total_tokens": 4508323456} {"current_steps": 13470, "total_steps": 25209, "loss": 0.3302, "lr": 3.263793790727256e-05, "epoch": 1.602998928953945, "percentage": 53.43, "elapsed_time": "21:10:27", "remaining_time": "18:27:11", "throughput": 59186.75, "total_tokens": 4511658240} {"current_steps": 13480, "total_steps": 25209, "loss": 0.3337, "lr": 3.2630986713892495e-05, "epoch": 1.6041889801261453, "percentage": 53.47, "elapsed_time": "21:11:15", "remaining_time": "18:26:07", "throughput": 59193.48, "total_tokens": 4515020672} {"current_steps": 13490, "total_steps": 25209, "loss": 0.3335, "lr": 3.26240399599948e-05, "epoch": 1.6053790312983458, "percentage": 53.51, "elapsed_time": "21:12:06", "remaining_time": "18:25:05", "throughput": 59200.08, "total_tokens": 4518507392} {"current_steps": 13500, "total_steps": 25209, "loss": 0.3348, "lr": 3.2617097640855914e-05, "epoch": 1.6065690824705463, "percentage": 53.55, "elapsed_time": "21:12:52", "remaining_time": "18:24:00", "throughput": 59206.94, "total_tokens": 4521780736} {"current_steps": 13510, "total_steps": 25209, "loss": 0.3378, "lr": 3.2610159751759314e-05, "epoch": 1.6077591336427466, "percentage": 53.59, "elapsed_time": "21:13:44", "remaining_time": "18:22:59", "throughput": 59212.04, "total_tokens": 4525233536} {"current_steps": 13520, "total_steps": 25209, "loss": 0.3343, "lr": 3.26032262879955e-05, "epoch": 1.608949184814947, "percentage": 53.63, "elapsed_time": "21:14:33", "remaining_time": "18:21:56", "throughput": 59218.6, "total_tokens": 4528642816} {"current_steps": 13530, "total_steps": 25209, "loss": 0.3337, "lr": 3.259629724486198e-05, "epoch": 1.6101392359871474, "percentage": 53.67, "elapsed_time": "21:15:20", "remaining_time": "18:20:51", "throughput": 59225.85, "total_tokens": 4531977472} {"current_steps": 13540, "total_steps": 25209, "loss": 0.3315, "lr": 3.258937261766323e-05, "epoch": 1.6113292871593479, "percentage": 53.71, "elapsed_time": "21:16:09", "remaining_time": "18:19:49", "throughput": 59232.17, "total_tokens": 4535392256} {"current_steps": 13550, "total_steps": 25209, "loss": 0.3386, "lr": 3.258245240171074e-05, "epoch": 1.6125193383315484, "percentage": 53.75, "elapsed_time": "21:16:56", "remaining_time": "18:18:44", "throughput": 59239.49, "total_tokens": 4538723584} {"current_steps": 13560, "total_steps": 25209, "loss": 0.3346, "lr": 3.2575536592322935e-05, "epoch": 1.6137093895037486, "percentage": 53.79, "elapsed_time": "21:17:43", "remaining_time": "18:17:39", "throughput": 59246.27, "total_tokens": 4542050688} {"current_steps": 13570, "total_steps": 25209, "loss": 0.3332, "lr": 3.256862518482523e-05, "epoch": 1.614899440675949, "percentage": 53.83, "elapsed_time": "21:18:31", "remaining_time": "18:16:35", "throughput": 59252.55, "total_tokens": 4545376640} {"current_steps": 13580, "total_steps": 25209, "loss": 0.3338, "lr": 3.256171817454994e-05, "epoch": 1.6160894918481494, "percentage": 53.87, "elapsed_time": "21:19:16", "remaining_time": "18:15:29", "throughput": 59261.18, "total_tokens": 4548686720} {"current_steps": 13590, "total_steps": 25209, "loss": 0.3353, "lr": 3.255481555683633e-05, "epoch": 1.61727954302035, "percentage": 53.91, "elapsed_time": "21:20:02", "remaining_time": "18:14:23", "throughput": 59269.24, "total_tokens": 4552006912} {"current_steps": 13600, "total_steps": 25209, "loss": 0.3353, "lr": 3.254791732703057e-05, "epoch": 1.6184695941925504, "percentage": 53.95, "elapsed_time": "21:20:50", "remaining_time": "18:13:19", "throughput": 59275.46, "total_tokens": 4555345792} {"current_steps": 13610, "total_steps": 25209, "loss": 0.331, "lr": 3.254102348048575e-05, "epoch": 1.6196596453647507, "percentage": 53.99, "elapsed_time": "21:21:41", "remaining_time": "18:12:18", "throughput": 59279.88, "total_tokens": 4558735104} {"current_steps": 13620, "total_steps": 25209, "loss": 0.3345, "lr": 3.25341340125618e-05, "epoch": 1.620849696536951, "percentage": 54.03, "elapsed_time": "21:22:29", "remaining_time": "18:11:15", "throughput": 59286.82, "total_tokens": 4562114816} {"current_steps": 13630, "total_steps": 25209, "loss": 0.3353, "lr": 3.2527248918625575e-05, "epoch": 1.6220397477091515, "percentage": 54.07, "elapsed_time": "21:23:18", "remaining_time": "18:10:11", "throughput": 59293.7, "total_tokens": 4565507200} {"current_steps": 13640, "total_steps": 25209, "loss": 0.3319, "lr": 3.252036819405075e-05, "epoch": 1.623229798881352, "percentage": 54.11, "elapsed_time": "21:24:07", "remaining_time": "18:09:09", "throughput": 59298.49, "total_tokens": 4568819840} {"current_steps": 13650, "total_steps": 25209, "loss": 0.3328, "lr": 3.251349183421788e-05, "epoch": 1.6244198500535523, "percentage": 54.15, "elapsed_time": "21:24:55", "remaining_time": "18:08:05", "throughput": 59305.36, "total_tokens": 4572199296} {"current_steps": 13660, "total_steps": 25209, "loss": 0.338, "lr": 3.250661983451434e-05, "epoch": 1.6256099012257526, "percentage": 54.19, "elapsed_time": "21:25:43", "remaining_time": "18:07:01", "throughput": 59312.72, "total_tokens": 4575564928} {"current_steps": 13670, "total_steps": 25209, "loss": 0.3351, "lr": 3.2499752190334326e-05, "epoch": 1.626799952397953, "percentage": 54.23, "elapsed_time": "21:26:32", "remaining_time": "18:05:58", "throughput": 59318.48, "total_tokens": 4578930176} {"current_steps": 13680, "total_steps": 25209, "loss": 0.3291, "lr": 3.2492888897078834e-05, "epoch": 1.6279900035701536, "percentage": 54.27, "elapsed_time": "21:27:21", "remaining_time": "18:04:56", "throughput": 59325.19, "total_tokens": 4582348032} {"current_steps": 13690, "total_steps": 25209, "loss": 0.3318, "lr": 3.248602995015567e-05, "epoch": 1.629180054742354, "percentage": 54.31, "elapsed_time": "21:28:07", "remaining_time": "18:03:50", "throughput": 59332.61, "total_tokens": 4585660416} {"current_steps": 13700, "total_steps": 25209, "loss": 0.3353, "lr": 3.247917534497943e-05, "epoch": 1.6303701059145543, "percentage": 54.35, "elapsed_time": "21:28:51", "remaining_time": "18:02:44", "throughput": 59340.44, "total_tokens": 4588910848} {"current_steps": 13710, "total_steps": 25209, "loss": 0.331, "lr": 3.247232507697145e-05, "epoch": 1.6315601570867546, "percentage": 54.39, "elapsed_time": "21:29:35", "remaining_time": "18:01:36", "throughput": 59348.79, "total_tokens": 4592117504} {"current_steps": 13720, "total_steps": 25209, "loss": 0.3339, "lr": 3.246547914155985e-05, "epoch": 1.6327502082589551, "percentage": 54.43, "elapsed_time": "21:30:21", "remaining_time": "18:00:32", "throughput": 59355.94, "total_tokens": 4595450624} {"current_steps": 13730, "total_steps": 25209, "loss": 0.3349, "lr": 3.245863753417949e-05, "epoch": 1.6339402594311556, "percentage": 54.46, "elapsed_time": "21:31:08", "remaining_time": "17:59:27", "throughput": 59363.13, "total_tokens": 4598790016} {"current_steps": 13740, "total_steps": 25209, "loss": 0.3315, "lr": 3.2451800250271944e-05, "epoch": 1.635130310603356, "percentage": 54.5, "elapsed_time": "21:31:57", "remaining_time": "17:58:24", "throughput": 59368.95, "total_tokens": 4602112512} {"current_steps": 13750, "total_steps": 25209, "loss": 0.3292, "lr": 3.244496728528553e-05, "epoch": 1.6363203617755564, "percentage": 54.54, "elapsed_time": "21:32:46", "remaining_time": "17:57:22", "throughput": 59374.69, "total_tokens": 4605514624} {"current_steps": 13760, "total_steps": 25209, "loss": 0.3386, "lr": 3.243813863467525e-05, "epoch": 1.6375104129477567, "percentage": 54.58, "elapsed_time": "21:33:33", "remaining_time": "17:56:18", "throughput": 59381.94, "total_tokens": 4608842368} {"current_steps": 13770, "total_steps": 25209, "loss": 0.3362, "lr": 3.243131429390281e-05, "epoch": 1.6387004641199572, "percentage": 54.62, "elapsed_time": "21:34:21", "remaining_time": "17:55:14", "throughput": 59387.96, "total_tokens": 4612132352} {"current_steps": 13780, "total_steps": 25209, "loss": 0.3318, "lr": 3.2424494258436594e-05, "epoch": 1.6398905152921577, "percentage": 54.66, "elapsed_time": "21:35:10", "remaining_time": "17:54:11", "throughput": 59393.47, "total_tokens": 4615470208} {"current_steps": 13790, "total_steps": 25209, "loss": 0.334, "lr": 3.241767852375166e-05, "epoch": 1.641080566464358, "percentage": 54.7, "elapsed_time": "21:35:59", "remaining_time": "17:53:09", "throughput": 59398.1, "total_tokens": 4618772352} {"current_steps": 13800, "total_steps": 25209, "loss": 0.3274, "lr": 3.241086708532971e-05, "epoch": 1.6422706176365582, "percentage": 54.74, "elapsed_time": "21:36:51", "remaining_time": "17:52:10", "throughput": 59402.38, "total_tokens": 4622205184} {"current_steps": 13810, "total_steps": 25209, "loss": 0.3375, "lr": 3.24040599386591e-05, "epoch": 1.6434606688087587, "percentage": 54.78, "elapsed_time": "21:37:36", "remaining_time": "17:51:04", "throughput": 59409.65, "total_tokens": 4625450752} {"current_steps": 13820, "total_steps": 25209, "loss": 0.329, "lr": 3.23972570792348e-05, "epoch": 1.6446507199809592, "percentage": 54.82, "elapsed_time": "21:38:26", "remaining_time": "17:50:02", "throughput": 59416.01, "total_tokens": 4628904192} {"current_steps": 13830, "total_steps": 25209, "loss": 0.3336, "lr": 3.239045850255842e-05, "epoch": 1.6458407711531597, "percentage": 54.86, "elapsed_time": "21:39:13", "remaining_time": "17:48:58", "throughput": 59423.06, "total_tokens": 4632241664} {"current_steps": 13840, "total_steps": 25209, "loss": 0.3292, "lr": 3.238366420413817e-05, "epoch": 1.64703082232536, "percentage": 54.9, "elapsed_time": "21:40:02", "remaining_time": "17:47:55", "throughput": 59429.52, "total_tokens": 4635622528} {"current_steps": 13850, "total_steps": 25209, "loss": 0.3311, "lr": 3.237687417948882e-05, "epoch": 1.6482208734975603, "percentage": 54.94, "elapsed_time": "21:40:48", "remaining_time": "17:46:51", "throughput": 59436.28, "total_tokens": 4638915584} {"current_steps": 13860, "total_steps": 25209, "loss": 0.336, "lr": 3.2370088424131776e-05, "epoch": 1.6494109246697608, "percentage": 54.98, "elapsed_time": "21:41:36", "remaining_time": "17:45:47", "throughput": 59442.56, "total_tokens": 4642259456} {"current_steps": 13870, "total_steps": 25209, "loss": 0.3302, "lr": 3.236330693359497e-05, "epoch": 1.6506009758419613, "percentage": 55.02, "elapsed_time": "21:42:25", "remaining_time": "17:44:45", "throughput": 59449.06, "total_tokens": 4645672960} {"current_steps": 13880, "total_steps": 25209, "loss": 0.3337, "lr": 3.2356529703412894e-05, "epoch": 1.6517910270141616, "percentage": 55.06, "elapsed_time": "21:43:13", "remaining_time": "17:43:42", "throughput": 59454.94, "total_tokens": 4648992000} {"current_steps": 13890, "total_steps": 25209, "loss": 0.3346, "lr": 3.234975672912661e-05, "epoch": 1.6529810781863619, "percentage": 55.1, "elapsed_time": "21:44:02", "remaining_time": "17:42:40", "throughput": 59460.37, "total_tokens": 4652352384} {"current_steps": 13900, "total_steps": 25209, "loss": 0.3321, "lr": 3.234298800628368e-05, "epoch": 1.6541711293585624, "percentage": 55.14, "elapsed_time": "21:44:52", "remaining_time": "17:41:38", "throughput": 59465.87, "total_tokens": 4655736704} {"current_steps": 13910, "total_steps": 25209, "loss": 0.333, "lr": 3.2336223530438195e-05, "epoch": 1.6553611805307629, "percentage": 55.18, "elapsed_time": "21:45:38", "remaining_time": "17:40:33", "throughput": 59473.83, "total_tokens": 4659080704} {"current_steps": 13920, "total_steps": 25209, "loss": 0.3329, "lr": 3.232946329715076e-05, "epoch": 1.6565512317029634, "percentage": 55.22, "elapsed_time": "21:46:26", "remaining_time": "17:39:30", "throughput": 59479.78, "total_tokens": 4662409856} {"current_steps": 13930, "total_steps": 25209, "loss": 0.3343, "lr": 3.2322707301988456e-05, "epoch": 1.6577412828751636, "percentage": 55.26, "elapsed_time": "21:47:13", "remaining_time": "17:38:27", "throughput": 59486.83, "total_tokens": 4665766144} {"current_steps": 13940, "total_steps": 25209, "loss": 0.3312, "lr": 3.231595554052488e-05, "epoch": 1.658931334047364, "percentage": 55.3, "elapsed_time": "21:48:01", "remaining_time": "17:37:23", "throughput": 59493.42, "total_tokens": 4669133312} {"current_steps": 13950, "total_steps": 25209, "loss": 0.3338, "lr": 3.230920800834005e-05, "epoch": 1.6601213852195644, "percentage": 55.34, "elapsed_time": "21:48:50", "remaining_time": "17:36:21", "throughput": 59498.71, "total_tokens": 4672455936} {"current_steps": 13960, "total_steps": 25209, "loss": 0.3329, "lr": 3.2302464701020486e-05, "epoch": 1.661311436391765, "percentage": 55.38, "elapsed_time": "21:49:39", "remaining_time": "17:35:19", "throughput": 59504.85, "total_tokens": 4675880064} {"current_steps": 13970, "total_steps": 25209, "loss": 0.3342, "lr": 3.2295725614159126e-05, "epoch": 1.6625014875639652, "percentage": 55.42, "elapsed_time": "21:50:26", "remaining_time": "17:34:15", "throughput": 59511.28, "total_tokens": 4679174528} {"current_steps": 13980, "total_steps": 25209, "loss": 0.3348, "lr": 3.228899074335536e-05, "epoch": 1.6636915387361657, "percentage": 55.46, "elapsed_time": "21:51:13", "remaining_time": "17:33:11", "throughput": 59517.6, "total_tokens": 4682435072} {"current_steps": 13990, "total_steps": 25209, "loss": 0.333, "lr": 3.228226008421498e-05, "epoch": 1.664881589908366, "percentage": 55.5, "elapsed_time": "21:52:01", "remaining_time": "17:32:08", "throughput": 59524.18, "total_tokens": 4685812736} {"current_steps": 14000, "total_steps": 25209, "loss": 0.3373, "lr": 3.2275533632350193e-05, "epoch": 1.6660716410805665, "percentage": 55.54, "elapsed_time": "21:52:48", "remaining_time": "17:31:05", "throughput": 59530.66, "total_tokens": 4689156992} {"current_steps": 14010, "total_steps": 25209, "loss": 0.335, "lr": 3.226881138337963e-05, "epoch": 1.667261692252767, "percentage": 55.58, "elapsed_time": "21:53:33", "remaining_time": "17:30:00", "throughput": 59538.61, "total_tokens": 4692468992} {"current_steps": 14020, "total_steps": 25209, "loss": 0.3355, "lr": 3.2262093332928256e-05, "epoch": 1.6684517434249673, "percentage": 55.62, "elapsed_time": "21:54:20", "remaining_time": "17:28:56", "throughput": 59545.45, "total_tokens": 4695768192} {"current_steps": 14030, "total_steps": 25209, "loss": 0.333, "lr": 3.225537947662746e-05, "epoch": 1.6696417945971676, "percentage": 55.65, "elapsed_time": "21:55:10", "remaining_time": "17:27:55", "throughput": 59550.18, "total_tokens": 4699151104} {"current_steps": 14040, "total_steps": 25209, "loss": 0.3336, "lr": 3.224866981011494e-05, "epoch": 1.670831845769368, "percentage": 55.69, "elapsed_time": "21:55:58", "remaining_time": "17:26:52", "throughput": 59556.69, "total_tokens": 4702491136} {"current_steps": 14050, "total_steps": 25209, "loss": 0.3305, "lr": 3.22419643290348e-05, "epoch": 1.6720218969415686, "percentage": 55.73, "elapsed_time": "21:56:44", "remaining_time": "17:25:47", "throughput": 59563.88, "total_tokens": 4705798912} {"current_steps": 14060, "total_steps": 25209, "loss": 0.3406, "lr": 3.2235263029037446e-05, "epoch": 1.673211948113769, "percentage": 55.77, "elapsed_time": "21:57:35", "remaining_time": "17:24:47", "throughput": 59568.04, "total_tokens": 4709199744} {"current_steps": 14070, "total_steps": 25209, "loss": 0.3326, "lr": 3.222856590577962e-05, "epoch": 1.6744019992859693, "percentage": 55.81, "elapsed_time": "21:58:27", "remaining_time": "17:23:48", "throughput": 59573.63, "total_tokens": 4712707712} {"current_steps": 14080, "total_steps": 25209, "loss": 0.3364, "lr": 3.222187295492436e-05, "epoch": 1.6755920504581696, "percentage": 55.85, "elapsed_time": "21:59:17", "remaining_time": "17:22:46", "throughput": 59579.47, "total_tokens": 4716156032} {"current_steps": 14090, "total_steps": 25209, "loss": 0.3316, "lr": 3.221518417214104e-05, "epoch": 1.6767821016303701, "percentage": 55.89, "elapsed_time": "22:00:06", "remaining_time": "17:21:44", "throughput": 59584.44, "total_tokens": 4719461632} {"current_steps": 14100, "total_steps": 25209, "loss": 0.3278, "lr": 3.22084995531053e-05, "epoch": 1.6779721528025706, "percentage": 55.93, "elapsed_time": "22:00:57", "remaining_time": "17:20:44", "throughput": 59588.87, "total_tokens": 4722850304} {"current_steps": 14110, "total_steps": 25209, "loss": 0.3332, "lr": 3.220181909349907e-05, "epoch": 1.679162203974771, "percentage": 55.97, "elapsed_time": "22:01:44", "remaining_time": "17:19:41", "throughput": 59595.75, "total_tokens": 4726234496} {"current_steps": 14120, "total_steps": 25209, "loss": 0.3365, "lr": 3.219514278901053e-05, "epoch": 1.6803522551469712, "percentage": 56.01, "elapsed_time": "22:02:32", "remaining_time": "17:18:38", "throughput": 59602.78, "total_tokens": 4729612032} {"current_steps": 14130, "total_steps": 25209, "loss": 0.3351, "lr": 3.218847063533413e-05, "epoch": 1.6815423063191717, "percentage": 56.05, "elapsed_time": "22:03:19", "remaining_time": "17:17:35", "throughput": 59609.46, "total_tokens": 4732972800} {"current_steps": 14140, "total_steps": 25209, "loss": 0.3332, "lr": 3.218180262817055e-05, "epoch": 1.6827323574913722, "percentage": 56.09, "elapsed_time": "22:04:11", "remaining_time": "17:16:36", "throughput": 59613.97, "total_tokens": 4736448640} {"current_steps": 14150, "total_steps": 25209, "loss": 0.3345, "lr": 3.217513876322674e-05, "epoch": 1.6839224086635727, "percentage": 56.13, "elapsed_time": "22:05:01", "remaining_time": "17:15:34", "throughput": 59619.89, "total_tokens": 4739863936} {"current_steps": 14160, "total_steps": 25209, "loss": 0.3326, "lr": 3.216847903621581e-05, "epoch": 1.685112459835773, "percentage": 56.17, "elapsed_time": "22:05:48", "remaining_time": "17:14:31", "throughput": 59626.72, "total_tokens": 4743214080} {"current_steps": 14170, "total_steps": 25209, "loss": 0.3293, "lr": 3.216182344285713e-05, "epoch": 1.6863025110079732, "percentage": 56.21, "elapsed_time": "22:06:39", "remaining_time": "17:13:31", "throughput": 59631.29, "total_tokens": 4746616832} {"current_steps": 14180, "total_steps": 25209, "loss": 0.3326, "lr": 3.215517197887625e-05, "epoch": 1.6874925621801737, "percentage": 56.25, "elapsed_time": "22:07:26", "remaining_time": "17:12:27", "throughput": 59637.05, "total_tokens": 4749858560} {"current_steps": 14190, "total_steps": 25209, "loss": 0.3369, "lr": 3.214852464000488e-05, "epoch": 1.6886826133523742, "percentage": 56.29, "elapsed_time": "22:08:18", "remaining_time": "17:11:28", "throughput": 59641.08, "total_tokens": 4753285760} {"current_steps": 14200, "total_steps": 25209, "loss": 0.3328, "lr": 3.2141881421980945e-05, "epoch": 1.6898726645245745, "percentage": 56.33, "elapsed_time": "22:09:04", "remaining_time": "17:10:24", "throughput": 59647.91, "total_tokens": 4756606976} {"current_steps": 14210, "total_steps": 25209, "loss": 0.338, "lr": 3.213524232054851e-05, "epoch": 1.6910627156967748, "percentage": 56.37, "elapsed_time": "22:09:50", "remaining_time": "17:09:20", "throughput": 59654.94, "total_tokens": 4759914112} {"current_steps": 14220, "total_steps": 25209, "loss": 0.3305, "lr": 3.21286073314578e-05, "epoch": 1.6922527668689753, "percentage": 56.41, "elapsed_time": "22:10:41", "remaining_time": "17:08:20", "throughput": 59660.55, "total_tokens": 4763383296} {"current_steps": 14230, "total_steps": 25209, "loss": 0.335, "lr": 3.2121976450465155e-05, "epoch": 1.6934428180411758, "percentage": 56.45, "elapsed_time": "22:11:26", "remaining_time": "17:07:15", "throughput": 59668.06, "total_tokens": 4766678016} {"current_steps": 14240, "total_steps": 25209, "loss": 0.3317, "lr": 3.211534967333308e-05, "epoch": 1.6946328692133763, "percentage": 56.49, "elapsed_time": "22:12:16", "remaining_time": "17:06:14", "throughput": 59673.77, "total_tokens": 4770083328} {"current_steps": 14250, "total_steps": 25209, "loss": 0.334, "lr": 3.210872699583019e-05, "epoch": 1.6958229203855766, "percentage": 56.53, "elapsed_time": "22:13:03", "remaining_time": "17:05:11", "throughput": 59680.98, "total_tokens": 4773487232} {"current_steps": 14260, "total_steps": 25209, "loss": 0.332, "lr": 3.210210841373118e-05, "epoch": 1.6970129715577769, "percentage": 56.57, "elapsed_time": "22:13:50", "remaining_time": "17:04:08", "throughput": 59687.41, "total_tokens": 4776827136} {"current_steps": 14270, "total_steps": 25209, "loss": 0.3343, "lr": 3.2095493922816855e-05, "epoch": 1.6982030227299774, "percentage": 56.61, "elapsed_time": "22:14:38", "remaining_time": "17:03:06", "throughput": 59693.09, "total_tokens": 4780132096} {"current_steps": 14280, "total_steps": 25209, "loss": 0.3322, "lr": 3.2088883518874105e-05, "epoch": 1.6993930739021779, "percentage": 56.65, "elapsed_time": "22:15:26", "remaining_time": "17:02:03", "throughput": 59698.52, "total_tokens": 4783411072} {"current_steps": 14290, "total_steps": 25209, "loss": 0.3299, "lr": 3.208227719769589e-05, "epoch": 1.7005831250743781, "percentage": 56.69, "elapsed_time": "22:16:17", "remaining_time": "17:01:03", "throughput": 59702.88, "total_tokens": 4786817152} {"current_steps": 14300, "total_steps": 25209, "loss": 0.3369, "lr": 3.207567495508124e-05, "epoch": 1.7017731762465786, "percentage": 56.73, "elapsed_time": "22:17:04", "remaining_time": "17:00:00", "throughput": 59709.66, "total_tokens": 4790176256} {"current_steps": 14310, "total_steps": 25209, "loss": 0.3278, "lr": 3.2069076786835205e-05, "epoch": 1.702963227418779, "percentage": 56.77, "elapsed_time": "22:17:52", "remaining_time": "16:58:58", "throughput": 59715.68, "total_tokens": 4793540224} {"current_steps": 14320, "total_steps": 25209, "loss": 0.3303, "lr": 3.2062482688768904e-05, "epoch": 1.7041532785909794, "percentage": 56.81, "elapsed_time": "22:18:38", "remaining_time": "16:57:54", "throughput": 59722.32, "total_tokens": 4796790912} {"current_steps": 14330, "total_steps": 25209, "loss": 0.3309, "lr": 3.205589265669947e-05, "epoch": 1.70534332976318, "percentage": 56.84, "elapsed_time": "22:19:27", "remaining_time": "16:56:53", "throughput": 59728.96, "total_tokens": 4800265984} {"current_steps": 14340, "total_steps": 25209, "loss": 0.332, "lr": 3.204930668645005e-05, "epoch": 1.7065333809353802, "percentage": 56.88, "elapsed_time": "22:20:12", "remaining_time": "16:55:48", "throughput": 59736.27, "total_tokens": 4803535360} {"current_steps": 14350, "total_steps": 25209, "loss": 0.3286, "lr": 3.20427247738498e-05, "epoch": 1.7077234321075805, "percentage": 56.92, "elapsed_time": "22:21:06", "remaining_time": "16:54:50", "throughput": 59739.46, "total_tokens": 4807005312} {"current_steps": 14360, "total_steps": 25209, "loss": 0.3307, "lr": 3.2036146914733854e-05, "epoch": 1.708913483279781, "percentage": 56.96, "elapsed_time": "22:21:52", "remaining_time": "16:53:47", "throughput": 59746.31, "total_tokens": 4810301696} {"current_steps": 14370, "total_steps": 25209, "loss": 0.3367, "lr": 3.202957310494336e-05, "epoch": 1.7101035344519815, "percentage": 57.0, "elapsed_time": "22:22:38", "remaining_time": "16:52:43", "throughput": 59752.51, "total_tokens": 4813569152} {"current_steps": 14380, "total_steps": 25209, "loss": 0.3336, "lr": 3.202300334032542e-05, "epoch": 1.711293585624182, "percentage": 57.04, "elapsed_time": "22:23:25", "remaining_time": "16:51:41", "throughput": 59758.42, "total_tokens": 4816880256} {"current_steps": 14390, "total_steps": 25209, "loss": 0.3277, "lr": 3.201643761673308e-05, "epoch": 1.7124836367963823, "percentage": 57.08, "elapsed_time": "22:24:13", "remaining_time": "16:50:38", "throughput": 59764.96, "total_tokens": 4820253056} {"current_steps": 14400, "total_steps": 25209, "loss": 0.3339, "lr": 3.200987593002536e-05, "epoch": 1.7136736879685825, "percentage": 57.12, "elapsed_time": "22:25:01", "remaining_time": "16:49:36", "throughput": 59771.12, "total_tokens": 4823590144} {"current_steps": 14410, "total_steps": 25209, "loss": 0.3303, "lr": 3.200331827606721e-05, "epoch": 1.714863739140783, "percentage": 57.16, "elapsed_time": "22:25:48", "remaining_time": "16:48:33", "throughput": 59777.61, "total_tokens": 4826930560} {"current_steps": 14420, "total_steps": 25209, "loss": 0.3369, "lr": 3.199676465072951e-05, "epoch": 1.7160537903129836, "percentage": 57.2, "elapsed_time": "22:26:33", "remaining_time": "16:47:29", "throughput": 59784.44, "total_tokens": 4830204032} {"current_steps": 14430, "total_steps": 25209, "loss": 0.3314, "lr": 3.1990215049889046e-05, "epoch": 1.7172438414851838, "percentage": 57.24, "elapsed_time": "22:27:25", "remaining_time": "16:46:30", "throughput": 59788.8, "total_tokens": 4833676544} {"current_steps": 14440, "total_steps": 25209, "loss": 0.3281, "lr": 3.198366946942851e-05, "epoch": 1.718433892657384, "percentage": 57.28, "elapsed_time": "22:28:14", "remaining_time": "16:45:29", "throughput": 59794.72, "total_tokens": 4837061120} {"current_steps": 14450, "total_steps": 25209, "loss": 0.3314, "lr": 3.1977127905236514e-05, "epoch": 1.7196239438295846, "percentage": 57.32, "elapsed_time": "22:29:05", "remaining_time": "16:44:29", "throughput": 59799.4, "total_tokens": 4840521216} {"current_steps": 14460, "total_steps": 25209, "loss": 0.3353, "lr": 3.197059035320752e-05, "epoch": 1.7208139950017851, "percentage": 57.36, "elapsed_time": "22:29:52", "remaining_time": "16:43:26", "throughput": 59805.7, "total_tokens": 4843834880} {"current_steps": 14470, "total_steps": 25209, "loss": 0.334, "lr": 3.196405680924189e-05, "epoch": 1.7220040461739856, "percentage": 57.4, "elapsed_time": "22:30:43", "remaining_time": "16:42:26", "throughput": 59810.77, "total_tokens": 4847264128} {"current_steps": 14480, "total_steps": 25209, "loss": 0.3325, "lr": 3.195752726924582e-05, "epoch": 1.723194097346186, "percentage": 57.44, "elapsed_time": "22:31:33", "remaining_time": "16:41:26", "throughput": 59816.89, "total_tokens": 4850736640} {"current_steps": 14490, "total_steps": 25209, "loss": 0.3355, "lr": 3.195100172913139e-05, "epoch": 1.7243841485183862, "percentage": 57.48, "elapsed_time": "22:32:21", "remaining_time": "16:40:24", "throughput": 59822.52, "total_tokens": 4854099456} {"current_steps": 14500, "total_steps": 25209, "loss": 0.3351, "lr": 3.19444801848165e-05, "epoch": 1.7255741996905867, "percentage": 57.52, "elapsed_time": "22:33:08", "remaining_time": "16:39:22", "throughput": 59828.45, "total_tokens": 4857406976} {"current_steps": 14510, "total_steps": 25209, "loss": 0.331, "lr": 3.1937962632224885e-05, "epoch": 1.7267642508627872, "percentage": 57.56, "elapsed_time": "22:33:57", "remaining_time": "16:38:20", "throughput": 59834.09, "total_tokens": 4860768000} {"current_steps": 14520, "total_steps": 25209, "loss": 0.3358, "lr": 3.193144906728609e-05, "epoch": 1.7279543020349875, "percentage": 57.6, "elapsed_time": "22:34:42", "remaining_time": "16:37:16", "throughput": 59840.7, "total_tokens": 4863991296} {"current_steps": 14530, "total_steps": 25209, "loss": 0.3374, "lr": 3.1924939485935494e-05, "epoch": 1.729144353207188, "percentage": 57.64, "elapsed_time": "22:35:28", "remaining_time": "16:36:13", "throughput": 59847.14, "total_tokens": 4867277568} {"current_steps": 14540, "total_steps": 25209, "loss": 0.3345, "lr": 3.1918433884114253e-05, "epoch": 1.7303344043793882, "percentage": 57.68, "elapsed_time": "22:36:16", "remaining_time": "16:35:11", "throughput": 59853.04, "total_tokens": 4870637312} {"current_steps": 14550, "total_steps": 25209, "loss": 0.3344, "lr": 3.191193225776931e-05, "epoch": 1.7315244555515887, "percentage": 57.72, "elapsed_time": "22:37:03", "remaining_time": "16:34:09", "throughput": 59859.39, "total_tokens": 4873962624} {"current_steps": 14560, "total_steps": 25209, "loss": 0.3324, "lr": 3.190543460285339e-05, "epoch": 1.7327145067237892, "percentage": 57.76, "elapsed_time": "22:37:52", "remaining_time": "16:33:07", "throughput": 59865.93, "total_tokens": 4877426176} {"current_steps": 14570, "total_steps": 25209, "loss": 0.3307, "lr": 3.189894091532499e-05, "epoch": 1.7339045578959895, "percentage": 57.8, "elapsed_time": "22:38:40", "remaining_time": "16:32:06", "throughput": 59872.04, "total_tokens": 4880792576} {"current_steps": 14580, "total_steps": 25209, "loss": 0.3317, "lr": 3.1892451191148346e-05, "epoch": 1.7350946090681898, "percentage": 57.84, "elapsed_time": "22:39:28", "remaining_time": "16:31:04", "throughput": 59877.87, "total_tokens": 4884174336} {"current_steps": 14590, "total_steps": 25209, "loss": 0.3329, "lr": 3.1885965426293465e-05, "epoch": 1.7362846602403903, "percentage": 57.88, "elapsed_time": "22:40:17", "remaining_time": "16:30:03", "throughput": 59883.89, "total_tokens": 4887590784} {"current_steps": 14600, "total_steps": 25209, "loss": 0.3307, "lr": 3.187948361673606e-05, "epoch": 1.7374747114125908, "percentage": 57.92, "elapsed_time": "22:41:02", "remaining_time": "16:28:59", "throughput": 59892.07, "total_tokens": 4890917504} {"current_steps": 14610, "total_steps": 25209, "loss": 0.3339, "lr": 3.187300575845759e-05, "epoch": 1.7386647625847913, "percentage": 57.96, "elapsed_time": "22:41:51", "remaining_time": "16:27:58", "throughput": 59897.33, "total_tokens": 4894295296} {"current_steps": 14620, "total_steps": 25209, "loss": 0.3318, "lr": 3.186653184744521e-05, "epoch": 1.7398548137569916, "percentage": 58.0, "elapsed_time": "22:42:40", "remaining_time": "16:26:57", "throughput": 59902.95, "total_tokens": 4897675776} {"current_steps": 14630, "total_steps": 25209, "loss": 0.3322, "lr": 3.18600618796918e-05, "epoch": 1.7410448649291919, "percentage": 58.03, "elapsed_time": "22:43:27", "remaining_time": "16:25:55", "throughput": 59909.27, "total_tokens": 4901033984} {"current_steps": 14640, "total_steps": 25209, "loss": 0.3343, "lr": 3.185359585119591e-05, "epoch": 1.7422349161013924, "percentage": 58.07, "elapsed_time": "22:44:14", "remaining_time": "16:24:53", "throughput": 59915.09, "total_tokens": 4904349056} {"current_steps": 14650, "total_steps": 25209, "loss": 0.3342, "lr": 3.184713375796178e-05, "epoch": 1.7434249672735929, "percentage": 58.11, "elapsed_time": "22:45:00", "remaining_time": "16:23:49", "throughput": 59922.57, "total_tokens": 4907672448} {"current_steps": 14660, "total_steps": 25209, "loss": 0.3367, "lr": 3.1840675595999344e-05, "epoch": 1.7446150184457931, "percentage": 58.15, "elapsed_time": "22:45:47", "remaining_time": "16:22:47", "throughput": 59928.94, "total_tokens": 4911048960} {"current_steps": 14670, "total_steps": 25209, "loss": 0.3334, "lr": 3.1834221361324155e-05, "epoch": 1.7458050696179934, "percentage": 58.19, "elapsed_time": "22:46:38", "remaining_time": "16:21:47", "throughput": 59933.47, "total_tokens": 4914429824} {"current_steps": 14680, "total_steps": 25209, "loss": 0.3322, "lr": 3.182777104995744e-05, "epoch": 1.746995120790194, "percentage": 58.23, "elapsed_time": "22:47:21", "remaining_time": "16:20:43", "throughput": 59940.88, "total_tokens": 4917651200} {"current_steps": 14690, "total_steps": 25209, "loss": 0.3308, "lr": 3.182132465792609e-05, "epoch": 1.7481851719623944, "percentage": 58.27, "elapsed_time": "22:48:09", "remaining_time": "16:19:41", "throughput": 59947.1, "total_tokens": 4921008128} {"current_steps": 14700, "total_steps": 25209, "loss": 0.3289, "lr": 3.181488218126259e-05, "epoch": 1.749375223134595, "percentage": 58.31, "elapsed_time": "22:48:59", "remaining_time": "16:18:41", "throughput": 59951.26, "total_tokens": 4924364160} {"current_steps": 14710, "total_steps": 25209, "loss": 0.3376, "lr": 3.180844361600506e-05, "epoch": 1.7505652743067952, "percentage": 58.35, "elapsed_time": "22:49:45", "remaining_time": "16:17:38", "throughput": 59957.55, "total_tokens": 4927664768} {"current_steps": 14720, "total_steps": 25209, "loss": 0.3369, "lr": 3.180200895819722e-05, "epoch": 1.7517553254789955, "percentage": 58.39, "elapsed_time": "22:50:36", "remaining_time": "16:16:38", "throughput": 59961.48, "total_tokens": 4931011072} {"current_steps": 14730, "total_steps": 25209, "loss": 0.3336, "lr": 3.1795578203888424e-05, "epoch": 1.752945376651196, "percentage": 58.43, "elapsed_time": "22:51:26", "remaining_time": "16:15:38", "throughput": 59966.42, "total_tokens": 4934407296} {"current_steps": 14740, "total_steps": 25209, "loss": 0.3269, "lr": 3.178915134913357e-05, "epoch": 1.7541354278233965, "percentage": 58.47, "elapsed_time": "22:52:14", "remaining_time": "16:14:37", "throughput": 59972.38, "total_tokens": 4937780352} {"current_steps": 14750, "total_steps": 25209, "loss": 0.3299, "lr": 3.178272838999316e-05, "epoch": 1.7553254789955968, "percentage": 58.51, "elapsed_time": "22:53:00", "remaining_time": "16:13:34", "throughput": 59978.83, "total_tokens": 4941083904} {"current_steps": 14760, "total_steps": 25209, "loss": 0.3305, "lr": 3.1776309322533274e-05, "epoch": 1.7565155301677973, "percentage": 58.55, "elapsed_time": "22:53:49", "remaining_time": "16:12:34", "throughput": 59983.44, "total_tokens": 4944408832} {"current_steps": 14770, "total_steps": 25209, "loss": 0.3366, "lr": 3.1769894142825536e-05, "epoch": 1.7577055813399975, "percentage": 58.59, "elapsed_time": "22:54:34", "remaining_time": "16:11:30", "throughput": 59989.91, "total_tokens": 4947654784} {"current_steps": 14780, "total_steps": 25209, "loss": 0.3363, "lr": 3.176348284694712e-05, "epoch": 1.758895632512198, "percentage": 58.63, "elapsed_time": "22:55:25", "remaining_time": "16:10:31", "throughput": 59995.05, "total_tokens": 4951104896} {"current_steps": 14790, "total_steps": 25209, "loss": 0.3385, "lr": 3.175707543098075e-05, "epoch": 1.7600856836843985, "percentage": 58.67, "elapsed_time": "22:56:11", "remaining_time": "16:09:28", "throughput": 60001.11, "total_tokens": 4954382464} {"current_steps": 14800, "total_steps": 25209, "loss": 0.3303, "lr": 3.1750671891014653e-05, "epoch": 1.7612757348565988, "percentage": 58.71, "elapsed_time": "22:56:57", "remaining_time": "16:08:26", "throughput": 60007.54, "total_tokens": 4957699328} {"current_steps": 14810, "total_steps": 25209, "loss": 0.3324, "lr": 3.174427222314262e-05, "epoch": 1.762465786028799, "percentage": 58.75, "elapsed_time": "22:57:47", "remaining_time": "16:07:25", "throughput": 60013.0, "total_tokens": 4961134720} {"current_steps": 14820, "total_steps": 25209, "loss": 0.3327, "lr": 3.173787642346391e-05, "epoch": 1.7636558372009996, "percentage": 58.79, "elapsed_time": "22:58:34", "remaining_time": "16:06:23", "throughput": 60019.54, "total_tokens": 4964484864} {"current_steps": 14830, "total_steps": 25209, "loss": 0.3303, "lr": 3.173148448808331e-05, "epoch": 1.7648458883732001, "percentage": 58.83, "elapsed_time": "22:59:22", "remaining_time": "16:05:22", "throughput": 60025.17, "total_tokens": 4967823488} {"current_steps": 14840, "total_steps": 25209, "loss": 0.3313, "lr": 3.172509641311107e-05, "epoch": 1.7660359395454006, "percentage": 58.87, "elapsed_time": "23:00:08", "remaining_time": "16:04:20", "throughput": 60032.05, "total_tokens": 4971182720} {"current_steps": 14850, "total_steps": 25209, "loss": 0.3345, "lr": 3.171871219466293e-05, "epoch": 1.767225990717601, "percentage": 58.91, "elapsed_time": "23:00:58", "remaining_time": "16:03:19", "throughput": 60037.44, "total_tokens": 4974593920} {"current_steps": 14860, "total_steps": 25209, "loss": 0.3289, "lr": 3.171233182886011e-05, "epoch": 1.7684160418898012, "percentage": 58.95, "elapsed_time": "23:01:46", "remaining_time": "16:02:19", "throughput": 60042.82, "total_tokens": 4977958016} {"current_steps": 14870, "total_steps": 25209, "loss": 0.3349, "lr": 3.170595531182928e-05, "epoch": 1.7696060930620017, "percentage": 58.99, "elapsed_time": "23:02:34", "remaining_time": "16:01:17", "throughput": 60049.16, "total_tokens": 4981364480} {"current_steps": 14880, "total_steps": 25209, "loss": 0.3351, "lr": 3.169958263970256e-05, "epoch": 1.7707961442342022, "percentage": 59.03, "elapsed_time": "23:03:26", "remaining_time": "16:00:19", "throughput": 60052.56, "total_tokens": 4984756608} {"current_steps": 14890, "total_steps": 25209, "loss": 0.3339, "lr": 3.169321380861751e-05, "epoch": 1.7719861954064025, "percentage": 59.07, "elapsed_time": "23:04:15", "remaining_time": "15:59:18", "throughput": 60058.17, "total_tokens": 4988149248} {"current_steps": 14900, "total_steps": 25209, "loss": 0.3311, "lr": 3.168684881471711e-05, "epoch": 1.7731762465786027, "percentage": 59.11, "elapsed_time": "23:05:04", "remaining_time": "15:58:18", "throughput": 60063.45, "total_tokens": 4991572736} {"current_steps": 14910, "total_steps": 25209, "loss": 0.3334, "lr": 3.168048765414979e-05, "epoch": 1.7743662977508032, "percentage": 59.15, "elapsed_time": "23:05:52", "remaining_time": "15:57:16", "throughput": 60069.92, "total_tokens": 4994952320} {"current_steps": 14920, "total_steps": 25209, "loss": 0.3366, "lr": 3.167413032306936e-05, "epoch": 1.7755563489230037, "percentage": 59.19, "elapsed_time": "23:06:38", "remaining_time": "15:56:14", "throughput": 60076.48, "total_tokens": 4998288000} {"current_steps": 14930, "total_steps": 25209, "loss": 0.3323, "lr": 3.166777681763504e-05, "epoch": 1.7767464000952042, "percentage": 59.22, "elapsed_time": "23:07:27", "remaining_time": "15:55:14", "throughput": 60081.73, "total_tokens": 5001667968} {"current_steps": 14940, "total_steps": 25209, "loss": 0.3316, "lr": 3.166142713401144e-05, "epoch": 1.7779364512674045, "percentage": 59.26, "elapsed_time": "23:08:17", "remaining_time": "15:54:14", "throughput": 60087.46, "total_tokens": 5005113728} {"current_steps": 14950, "total_steps": 25209, "loss": 0.3321, "lr": 3.165508126836857e-05, "epoch": 1.7791265024396048, "percentage": 59.3, "elapsed_time": "23:09:04", "remaining_time": "15:53:13", "throughput": 60092.98, "total_tokens": 5008447232} {"current_steps": 14960, "total_steps": 25209, "loss": 0.3355, "lr": 3.164873921688177e-05, "epoch": 1.7803165536118053, "percentage": 59.34, "elapsed_time": "23:09:52", "remaining_time": "15:52:11", "throughput": 60098.71, "total_tokens": 5011803648} {"current_steps": 14970, "total_steps": 25209, "loss": 0.3359, "lr": 3.164240097573178e-05, "epoch": 1.7815066047840058, "percentage": 59.38, "elapsed_time": "23:10:39", "remaining_time": "15:51:09", "throughput": 60104.52, "total_tokens": 5015073920} {"current_steps": 14980, "total_steps": 25209, "loss": 0.3306, "lr": 3.163606654110467e-05, "epoch": 1.782696655956206, "percentage": 59.42, "elapsed_time": "23:11:28", "remaining_time": "15:50:09", "throughput": 60109.66, "total_tokens": 5018453120} {"current_steps": 14990, "total_steps": 25209, "loss": 0.3297, "lr": 3.162973590919187e-05, "epoch": 1.7838867071284064, "percentage": 59.46, "elapsed_time": "23:12:15", "remaining_time": "15:49:08", "throughput": 60115.97, "total_tokens": 5021840640} {"current_steps": 15000, "total_steps": 25209, "loss": 0.3271, "lr": 3.162340907619012e-05, "epoch": 1.7850767583006069, "percentage": 59.5, "elapsed_time": "23:13:02", "remaining_time": "15:48:06", "throughput": 60122.32, "total_tokens": 5025160704} {"current_steps": 15000, "total_steps": 25209, "eval_loss": 0.330203115940094, "epoch": 1.7850767583006069, "percentage": 59.5, "elapsed_time": "23:13:03", "remaining_time": "15:48:06", "throughput": 60121.65, "total_tokens": 5025160704} {"current_steps": 15010, "total_steps": 25209, "loss": 0.33, "lr": 3.1617086038301516e-05, "epoch": 1.7862668094728074, "percentage": 59.54, "elapsed_time": "23:14:30", "remaining_time": "15:47:32", "throughput": 60099.3, "total_tokens": 5028562304} {"current_steps": 15020, "total_steps": 25209, "loss": 0.3341, "lr": 3.161076679173344e-05, "epoch": 1.7874568606450079, "percentage": 59.58, "elapsed_time": "23:15:19", "remaining_time": "15:46:31", "throughput": 60104.2, "total_tokens": 5031874816} {"current_steps": 15030, "total_steps": 25209, "loss": 0.334, "lr": 3.1604451332698575e-05, "epoch": 1.7886469118172081, "percentage": 59.62, "elapsed_time": "23:16:08", "remaining_time": "15:45:31", "throughput": 60109.57, "total_tokens": 5035267200} {"current_steps": 15040, "total_steps": 25209, "loss": 0.3315, "lr": 3.1598139657414923e-05, "epoch": 1.7898369629894084, "percentage": 59.66, "elapsed_time": "23:16:55", "remaining_time": "15:44:30", "throughput": 60114.85, "total_tokens": 5038545664} {"current_steps": 15050, "total_steps": 25209, "loss": 0.3305, "lr": 3.159183176210574e-05, "epoch": 1.791027014161609, "percentage": 59.7, "elapsed_time": "23:17:41", "remaining_time": "15:43:28", "throughput": 60120.34, "total_tokens": 5041799296} {"current_steps": 15060, "total_steps": 25209, "loss": 0.3342, "lr": 3.1585527642999595e-05, "epoch": 1.7922170653338094, "percentage": 59.74, "elapsed_time": "23:18:32", "remaining_time": "15:42:28", "throughput": 60123.8, "total_tokens": 5045112960} {"current_steps": 15070, "total_steps": 25209, "loss": 0.3324, "lr": 3.1579227296330294e-05, "epoch": 1.79340711650601, "percentage": 59.78, "elapsed_time": "23:19:19", "remaining_time": "15:41:27", "throughput": 60129.64, "total_tokens": 5048460288} {"current_steps": 15080, "total_steps": 25209, "loss": 0.3343, "lr": 3.157293071833691e-05, "epoch": 1.7945971676782102, "percentage": 59.82, "elapsed_time": "23:20:06", "remaining_time": "15:40:25", "throughput": 60136.19, "total_tokens": 5051811712} {"current_steps": 15090, "total_steps": 25209, "loss": 0.3292, "lr": 3.156663790526375e-05, "epoch": 1.7957872188504105, "percentage": 59.86, "elapsed_time": "23:20:53", "remaining_time": "15:39:24", "throughput": 60141.37, "total_tokens": 5055109120} {"current_steps": 15100, "total_steps": 25209, "loss": 0.3336, "lr": 3.156034885336039e-05, "epoch": 1.796977270022611, "percentage": 59.9, "elapsed_time": "23:21:42", "remaining_time": "15:38:24", "throughput": 60146.26, "total_tokens": 5058470016} {"current_steps": 15110, "total_steps": 25209, "loss": 0.3388, "lr": 3.155406355888161e-05, "epoch": 1.7981673211948115, "percentage": 59.94, "elapsed_time": "23:22:31", "remaining_time": "15:37:24", "throughput": 60151.12, "total_tokens": 5061820416} {"current_steps": 15120, "total_steps": 25209, "loss": 0.3338, "lr": 3.1547782018087407e-05, "epoch": 1.7993573723670118, "percentage": 59.98, "elapsed_time": "23:23:23", "remaining_time": "15:36:25", "throughput": 60154.36, "total_tokens": 5065216000} {"current_steps": 15130, "total_steps": 25209, "loss": 0.333, "lr": 3.154150422724299e-05, "epoch": 1.800547423539212, "percentage": 60.02, "elapsed_time": "23:24:11", "remaining_time": "15:35:25", "throughput": 60159.54, "total_tokens": 5068560640} {"current_steps": 15140, "total_steps": 25209, "loss": 0.3329, "lr": 3.1535230182618783e-05, "epoch": 1.8017374747114125, "percentage": 60.06, "elapsed_time": "23:25:02", "remaining_time": "15:34:26", "throughput": 60163.34, "total_tokens": 5071911296} {"current_steps": 15150, "total_steps": 25209, "loss": 0.3281, "lr": 3.1528959880490387e-05, "epoch": 1.802927525883613, "percentage": 60.1, "elapsed_time": "23:25:54", "remaining_time": "15:33:28", "throughput": 60167.18, "total_tokens": 5075394048} {"current_steps": 15160, "total_steps": 25209, "loss": 0.3349, "lr": 3.152269331713859e-05, "epoch": 1.8041175770558135, "percentage": 60.14, "elapsed_time": "23:26:42", "remaining_time": "15:32:27", "throughput": 60173.44, "total_tokens": 5078803968} {"current_steps": 15170, "total_steps": 25209, "loss": 0.3323, "lr": 3.151643048884935e-05, "epoch": 1.8053076282280138, "percentage": 60.18, "elapsed_time": "23:27:29", "remaining_time": "15:31:25", "throughput": 60179.25, "total_tokens": 5082094080} {"current_steps": 15180, "total_steps": 25209, "loss": 0.3301, "lr": 3.151017139191379e-05, "epoch": 1.806497679400214, "percentage": 60.22, "elapsed_time": "23:28:17", "remaining_time": "15:30:25", "throughput": 60184.71, "total_tokens": 5085462912} {"current_steps": 15190, "total_steps": 25209, "loss": 0.329, "lr": 3.150391602262818e-05, "epoch": 1.8076877305724146, "percentage": 60.26, "elapsed_time": "23:29:04", "remaining_time": "15:29:23", "throughput": 60190.99, "total_tokens": 5088820992} {"current_steps": 15200, "total_steps": 25209, "loss": 0.331, "lr": 3.149766437729394e-05, "epoch": 1.808877781744615, "percentage": 60.3, "elapsed_time": "23:29:53", "remaining_time": "15:28:23", "throughput": 60195.64, "total_tokens": 5092164224} {"current_steps": 15210, "total_steps": 25209, "loss": 0.3318, "lr": 3.1491416452217635e-05, "epoch": 1.8100678329168154, "percentage": 60.34, "elapsed_time": "23:30:41", "remaining_time": "15:27:22", "throughput": 60200.99, "total_tokens": 5095493888} {"current_steps": 15220, "total_steps": 25209, "loss": 0.3311, "lr": 3.1485172243710954e-05, "epoch": 1.8112578840890157, "percentage": 60.38, "elapsed_time": "23:31:32", "remaining_time": "15:26:24", "throughput": 60204.35, "total_tokens": 5098862848} {"current_steps": 15230, "total_steps": 25209, "loss": 0.3346, "lr": 3.1478931748090676e-05, "epoch": 1.8124479352612162, "percentage": 60.41, "elapsed_time": "23:32:20", "remaining_time": "15:25:23", "throughput": 60211.37, "total_tokens": 5102318336} {"current_steps": 15240, "total_steps": 25209, "loss": 0.3325, "lr": 3.147269496167873e-05, "epoch": 1.8136379864334167, "percentage": 60.45, "elapsed_time": "23:33:08", "remaining_time": "15:24:23", "throughput": 60215.87, "total_tokens": 5105630208} {"current_steps": 15250, "total_steps": 25209, "loss": 0.3314, "lr": 3.1466461880802105e-05, "epoch": 1.8148280376056172, "percentage": 60.49, "elapsed_time": "23:33:55", "remaining_time": "15:23:21", "throughput": 60221.81, "total_tokens": 5108939136} {"current_steps": 15260, "total_steps": 25209, "loss": 0.3298, "lr": 3.146023250179291e-05, "epoch": 1.8160180887778175, "percentage": 60.53, "elapsed_time": "23:34:45", "remaining_time": "15:22:22", "throughput": 60225.95, "total_tokens": 5112281472} {"current_steps": 15270, "total_steps": 25209, "loss": 0.3312, "lr": 3.145400682098833e-05, "epoch": 1.8172081399500177, "percentage": 60.57, "elapsed_time": "23:35:31", "remaining_time": "15:21:20", "throughput": 60233.07, "total_tokens": 5115699584} {"current_steps": 15280, "total_steps": 25209, "loss": 0.3349, "lr": 3.14477848347306e-05, "epoch": 1.8183981911222182, "percentage": 60.61, "elapsed_time": "23:36:21", "remaining_time": "15:20:21", "throughput": 60237.62, "total_tokens": 5119112064} {"current_steps": 15290, "total_steps": 25209, "loss": 0.3308, "lr": 3.144156653936703e-05, "epoch": 1.8195882422944187, "percentage": 60.65, "elapsed_time": "23:37:08", "remaining_time": "15:19:20", "throughput": 60242.85, "total_tokens": 5122383104} {"current_steps": 15300, "total_steps": 25209, "loss": 0.3334, "lr": 3.1435351931250004e-05, "epoch": 1.820778293466619, "percentage": 60.69, "elapsed_time": "23:37:57", "remaining_time": "15:18:20", "throughput": 60247.8, "total_tokens": 5125716864} {"current_steps": 15310, "total_steps": 25209, "loss": 0.3325, "lr": 3.142914100673692e-05, "epoch": 1.8219683446388195, "percentage": 60.73, "elapsed_time": "23:38:43", "remaining_time": "15:17:18", "throughput": 60254.56, "total_tokens": 5129096192} {"current_steps": 15320, "total_steps": 25209, "loss": 0.3333, "lr": 3.1422933762190235e-05, "epoch": 1.8231583958110198, "percentage": 60.77, "elapsed_time": "23:39:32", "remaining_time": "15:16:18", "throughput": 60259.72, "total_tokens": 5132460032} {"current_steps": 15330, "total_steps": 25209, "loss": 0.3289, "lr": 3.141673019397741e-05, "epoch": 1.8243484469832203, "percentage": 60.81, "elapsed_time": "23:40:17", "remaining_time": "15:15:16", "throughput": 60266.16, "total_tokens": 5135761152} {"current_steps": 15340, "total_steps": 25209, "loss": 0.3337, "lr": 3.141053029847095e-05, "epoch": 1.8255384981554208, "percentage": 60.85, "elapsed_time": "23:41:05", "remaining_time": "15:14:15", "throughput": 60271.61, "total_tokens": 5139083008} {"current_steps": 15350, "total_steps": 25209, "loss": 0.3342, "lr": 3.140433407204835e-05, "epoch": 1.826728549327621, "percentage": 60.89, "elapsed_time": "23:41:52", "remaining_time": "15:13:14", "throughput": 60278.15, "total_tokens": 5142452352} {"current_steps": 15360, "total_steps": 25209, "loss": 0.3331, "lr": 3.1398141511092124e-05, "epoch": 1.8279186004998214, "percentage": 60.93, "elapsed_time": "23:42:39", "remaining_time": "15:12:13", "throughput": 60283.78, "total_tokens": 5145778048} {"current_steps": 15370, "total_steps": 25209, "loss": 0.3324, "lr": 3.1391952611989736e-05, "epoch": 1.8291086516720219, "percentage": 60.97, "elapsed_time": "23:43:22", "remaining_time": "15:11:09", "throughput": 60291.35, "total_tokens": 5149009024} {"current_steps": 15380, "total_steps": 25209, "loss": 0.3335, "lr": 3.138576737113369e-05, "epoch": 1.8302987028442224, "percentage": 61.01, "elapsed_time": "23:44:10", "remaining_time": "15:10:09", "throughput": 60296.62, "total_tokens": 5152384128} {"current_steps": 15390, "total_steps": 25209, "loss": 0.3313, "lr": 3.137958578492143e-05, "epoch": 1.8314887540164229, "percentage": 61.05, "elapsed_time": "23:44:58", "remaining_time": "15:09:08", "throughput": 60301.67, "total_tokens": 5155693824} {"current_steps": 15400, "total_steps": 25209, "loss": 0.3314, "lr": 3.137340784975535e-05, "epoch": 1.8326788051886231, "percentage": 61.09, "elapsed_time": "23:45:46", "remaining_time": "15:08:08", "throughput": 60306.88, "total_tokens": 5159044224} {"current_steps": 15410, "total_steps": 25209, "loss": 0.3276, "lr": 3.136723356204285e-05, "epoch": 1.8338688563608234, "percentage": 61.13, "elapsed_time": "23:46:33", "remaining_time": "15:07:07", "throughput": 60312.69, "total_tokens": 5162401664} {"current_steps": 15420, "total_steps": 25209, "loss": 0.3323, "lr": 3.136106291819622e-05, "epoch": 1.835058907533024, "percentage": 61.17, "elapsed_time": "23:47:20", "remaining_time": "15:06:06", "throughput": 60318.47, "total_tokens": 5165724672} {"current_steps": 15430, "total_steps": 25209, "loss": 0.3278, "lr": 3.1354895914632736e-05, "epoch": 1.8362489587052244, "percentage": 61.21, "elapsed_time": "23:48:11", "remaining_time": "15:05:08", "throughput": 60322.81, "total_tokens": 5169174528} {"current_steps": 15440, "total_steps": 25209, "loss": 0.3303, "lr": 3.1348732547774575e-05, "epoch": 1.8374390098774247, "percentage": 61.25, "elapsed_time": "23:49:01", "remaining_time": "15:04:09", "throughput": 60327.63, "total_tokens": 5172592128} {"current_steps": 15450, "total_steps": 25209, "loss": 0.3342, "lr": 3.134257281404883e-05, "epoch": 1.838629061049625, "percentage": 61.29, "elapsed_time": "23:49:51", "remaining_time": "15:03:10", "throughput": 60331.46, "total_tokens": 5175953024} {"current_steps": 15460, "total_steps": 25209, "loss": 0.3288, "lr": 3.133641670988755e-05, "epoch": 1.8398191122218255, "percentage": 61.33, "elapsed_time": "23:50:38", "remaining_time": "15:02:09", "throughput": 60336.88, "total_tokens": 5179255040} {"current_steps": 15470, "total_steps": 25209, "loss": 0.3308, "lr": 3.133026423172764e-05, "epoch": 1.841009163394026, "percentage": 61.37, "elapsed_time": "23:51:27", "remaining_time": "15:01:09", "throughput": 60341.96, "total_tokens": 5182605568} {"current_steps": 15480, "total_steps": 25209, "loss": 0.3301, "lr": 3.1324115376010897e-05, "epoch": 1.8421992145662265, "percentage": 61.41, "elapsed_time": "23:52:14", "remaining_time": "15:00:09", "throughput": 60347.11, "total_tokens": 5185923840} {"current_steps": 15490, "total_steps": 25209, "loss": 0.3331, "lr": 3.131797013918406e-05, "epoch": 1.8433892657384268, "percentage": 61.45, "elapsed_time": "23:53:05", "remaining_time": "14:59:10", "throughput": 60352.6, "total_tokens": 5189456384} {"current_steps": 15500, "total_steps": 25209, "loss": 0.3322, "lr": 3.13118285176987e-05, "epoch": 1.844579316910627, "percentage": 61.49, "elapsed_time": "23:53:52", "remaining_time": "14:58:09", "throughput": 60357.81, "total_tokens": 5192724608} {"current_steps": 15510, "total_steps": 25209, "loss": 0.3307, "lr": 3.130569050801126e-05, "epoch": 1.8457693680828275, "percentage": 61.53, "elapsed_time": "23:54:38", "remaining_time": "14:57:08", "throughput": 60363.9, "total_tokens": 5196045824} {"current_steps": 15520, "total_steps": 25209, "loss": 0.3328, "lr": 3.129955610658306e-05, "epoch": 1.846959419255028, "percentage": 61.57, "elapsed_time": "23:55:23", "remaining_time": "14:56:06", "throughput": 60370.48, "total_tokens": 5199329536} {"current_steps": 15530, "total_steps": 25209, "loss": 0.3344, "lr": 3.129342530988025e-05, "epoch": 1.8481494704272283, "percentage": 61.6, "elapsed_time": "23:56:11", "remaining_time": "14:55:06", "throughput": 60375.2, "total_tokens": 5202628224} {"current_steps": 15540, "total_steps": 25209, "loss": 0.3284, "lr": 3.128729811437385e-05, "epoch": 1.8493395215994288, "percentage": 61.64, "elapsed_time": "23:56:59", "remaining_time": "14:54:05", "throughput": 60379.86, "total_tokens": 5205934208} {"current_steps": 15550, "total_steps": 25209, "loss": 0.3343, "lr": 3.12811745165397e-05, "epoch": 1.850529572771629, "percentage": 61.68, "elapsed_time": "23:57:46", "remaining_time": "14:53:04", "throughput": 60386.09, "total_tokens": 5209282560} {"current_steps": 15560, "total_steps": 25209, "loss": 0.3328, "lr": 3.127505451285846e-05, "epoch": 1.8517196239438296, "percentage": 61.72, "elapsed_time": "23:58:35", "remaining_time": "14:52:05", "throughput": 60390.64, "total_tokens": 5212675840} {"current_steps": 15570, "total_steps": 25209, "loss": 0.3323, "lr": 3.126893809981563e-05, "epoch": 1.85290967511603, "percentage": 61.76, "elapsed_time": "23:59:24", "remaining_time": "14:51:06", "throughput": 60395.27, "total_tokens": 5216000768} {"current_steps": 15580, "total_steps": 25209, "loss": 0.3336, "lr": 3.126282527390149e-05, "epoch": 1.8540997262882304, "percentage": 61.8, "elapsed_time": "1 day, 0:00:10", "remaining_time": "14:50:05", "throughput": 60401.23, "total_tokens": 5219325056} {"current_steps": 15590, "total_steps": 25209, "loss": 0.3311, "lr": 3.1256716031611146e-05, "epoch": 1.8552897774604307, "percentage": 61.84, "elapsed_time": "1 day, 0:01:02", "remaining_time": "14:49:07", "throughput": 60404.41, "total_tokens": 5222745600} {"current_steps": 15600, "total_steps": 25209, "loss": 0.328, "lr": 3.1250610369444475e-05, "epoch": 1.8564798286326312, "percentage": 61.88, "elapsed_time": "1 day, 0:01:50", "remaining_time": "14:48:07", "throughput": 60409.54, "total_tokens": 5226084352} {"current_steps": 15610, "total_steps": 25209, "loss": 0.3377, "lr": 3.124450828390616e-05, "epoch": 1.8576698798048317, "percentage": 61.92, "elapsed_time": "1 day, 0:02:38", "remaining_time": "14:47:07", "throughput": 60414.18, "total_tokens": 5229387008} {"current_steps": 15620, "total_steps": 25209, "loss": 0.3319, "lr": 3.123840977150566e-05, "epoch": 1.8588599309770322, "percentage": 61.96, "elapsed_time": "1 day, 0:03:28", "remaining_time": "14:46:08", "throughput": 60418.85, "total_tokens": 5232759424} {"current_steps": 15630, "total_steps": 25209, "loss": 0.3284, "lr": 3.123231482875717e-05, "epoch": 1.8600499821492325, "percentage": 62.0, "elapsed_time": "1 day, 0:04:13", "remaining_time": "14:45:06", "throughput": 60425.2, "total_tokens": 5236056320} {"current_steps": 15640, "total_steps": 25209, "loss": 0.3311, "lr": 3.122622345217967e-05, "epoch": 1.8612400333214327, "percentage": 62.04, "elapsed_time": "1 day, 0:04:59", "remaining_time": "14:44:05", "throughput": 60431.6, "total_tokens": 5239382912} {"current_steps": 15650, "total_steps": 25209, "loss": 0.3324, "lr": 3.12201356382969e-05, "epoch": 1.8624300844936332, "percentage": 62.08, "elapsed_time": "1 day, 0:05:50", "remaining_time": "14:43:07", "throughput": 60435.51, "total_tokens": 5242822912} {"current_steps": 15660, "total_steps": 25209, "loss": 0.3336, "lr": 3.1214051383637304e-05, "epoch": 1.8636201356658337, "percentage": 62.12, "elapsed_time": "1 day, 0:06:37", "remaining_time": "14:42:06", "throughput": 60441.17, "total_tokens": 5246156672} {"current_steps": 15670, "total_steps": 25209, "loss": 0.3317, "lr": 3.1207970684734104e-05, "epoch": 1.864810186838034, "percentage": 62.16, "elapsed_time": "1 day, 0:07:30", "remaining_time": "14:41:09", "throughput": 60444.29, "total_tokens": 5249645568} {"current_steps": 15680, "total_steps": 25209, "loss": 0.332, "lr": 3.120189353812521e-05, "epoch": 1.8660002380102343, "percentage": 62.2, "elapsed_time": "1 day, 0:08:19", "remaining_time": "14:40:10", "throughput": 60449.23, "total_tokens": 5252996864} {"current_steps": 15690, "total_steps": 25209, "loss": 0.3321, "lr": 3.1195819940353294e-05, "epoch": 1.8671902891824348, "percentage": 62.24, "elapsed_time": "1 day, 0:09:06", "remaining_time": "14:39:09", "throughput": 60455.29, "total_tokens": 5256360064} {"current_steps": 15700, "total_steps": 25209, "loss": 0.3319, "lr": 3.1189749887965684e-05, "epoch": 1.8683803403546353, "percentage": 62.28, "elapsed_time": "1 day, 0:09:52", "remaining_time": "14:38:08", "throughput": 60461.07, "total_tokens": 5259666560} {"current_steps": 15710, "total_steps": 25209, "loss": 0.3293, "lr": 3.118368337751443e-05, "epoch": 1.8695703915268358, "percentage": 62.32, "elapsed_time": "1 day, 0:10:39", "remaining_time": "14:37:08", "throughput": 60467.06, "total_tokens": 5263026944} {"current_steps": 15720, "total_steps": 25209, "loss": 0.335, "lr": 3.1177620405556305e-05, "epoch": 1.870760442699036, "percentage": 62.36, "elapsed_time": "1 day, 0:11:25", "remaining_time": "14:36:06", "throughput": 60472.82, "total_tokens": 5266277504} {"current_steps": 15730, "total_steps": 25209, "loss": 0.33, "lr": 3.117156096865272e-05, "epoch": 1.8719504938712364, "percentage": 62.4, "elapsed_time": "1 day, 0:12:14", "remaining_time": "14:35:08", "throughput": 60477.61, "total_tokens": 5269712512} {"current_steps": 15740, "total_steps": 25209, "loss": 0.3286, "lr": 3.116550506336979e-05, "epoch": 1.8731405450434369, "percentage": 62.44, "elapsed_time": "1 day, 0:13:02", "remaining_time": "14:34:07", "throughput": 60483.29, "total_tokens": 5273079424} {"current_steps": 15750, "total_steps": 25209, "loss": 0.3334, "lr": 3.11594526862783e-05, "epoch": 1.8743305962156374, "percentage": 62.48, "elapsed_time": "1 day, 0:13:51", "remaining_time": "14:33:08", "throughput": 60487.07, "total_tokens": 5276385408} {"current_steps": 15760, "total_steps": 25209, "loss": 0.3326, "lr": 3.115340383395367e-05, "epoch": 1.8755206473878376, "percentage": 62.52, "elapsed_time": "1 day, 0:14:42", "remaining_time": "14:32:10", "throughput": 60491.91, "total_tokens": 5279870336} {"current_steps": 15770, "total_steps": 25209, "loss": 0.3321, "lr": 3.1147358502975995e-05, "epoch": 1.876710698560038, "percentage": 62.56, "elapsed_time": "1 day, 0:15:31", "remaining_time": "14:31:11", "throughput": 60496.25, "total_tokens": 5283217280} {"current_steps": 15780, "total_steps": 25209, "loss": 0.3323, "lr": 3.114131668993e-05, "epoch": 1.8779007497322384, "percentage": 62.6, "elapsed_time": "1 day, 0:16:17", "remaining_time": "14:30:10", "throughput": 60502.5, "total_tokens": 5286545920} {"current_steps": 15790, "total_steps": 25209, "loss": 0.3312, "lr": 3.113527839140507e-05, "epoch": 1.879090800904439, "percentage": 62.64, "elapsed_time": "1 day, 0:17:07", "remaining_time": "14:29:11", "throughput": 60506.53, "total_tokens": 5289915392} {"current_steps": 15800, "total_steps": 25209, "loss": 0.3286, "lr": 3.112924360399517e-05, "epoch": 1.8802808520766394, "percentage": 62.68, "elapsed_time": "1 day, 0:17:56", "remaining_time": "14:28:12", "throughput": 60511.16, "total_tokens": 5293284736} {"current_steps": 15810, "total_steps": 25209, "loss": 0.3356, "lr": 3.112321232429894e-05, "epoch": 1.8814709032488397, "percentage": 62.72, "elapsed_time": "1 day, 0:18:43", "remaining_time": "14:27:12", "throughput": 60516.6, "total_tokens": 5296649984} {"current_steps": 15820, "total_steps": 25209, "loss": 0.3322, "lr": 3.11171845489196e-05, "epoch": 1.88266095442104, "percentage": 62.76, "elapsed_time": "1 day, 0:19:30", "remaining_time": "14:26:12", "throughput": 60522.52, "total_tokens": 5300007680} {"current_steps": 15830, "total_steps": 25209, "loss": 0.3339, "lr": 3.1111160274464965e-05, "epoch": 1.8838510055932405, "percentage": 62.8, "elapsed_time": "1 day, 0:20:19", "remaining_time": "14:25:12", "throughput": 60527.89, "total_tokens": 5303410688} {"current_steps": 15840, "total_steps": 25209, "loss": 0.3321, "lr": 3.1105139497547466e-05, "epoch": 1.885041056765441, "percentage": 62.83, "elapsed_time": "1 day, 0:21:06", "remaining_time": "14:24:12", "throughput": 60532.83, "total_tokens": 5306722176} {"current_steps": 15850, "total_steps": 25209, "loss": 0.3287, "lr": 3.109912221478411e-05, "epoch": 1.8862311079376415, "percentage": 62.87, "elapsed_time": "1 day, 0:21:55", "remaining_time": "14:23:13", "throughput": 60537.53, "total_tokens": 5310059264} {"current_steps": 15860, "total_steps": 25209, "loss": 0.3311, "lr": 3.10931084227965e-05, "epoch": 1.8874211591098418, "percentage": 62.91, "elapsed_time": "1 day, 0:22:44", "remaining_time": "14:22:14", "throughput": 60541.58, "total_tokens": 5313401088} {"current_steps": 15870, "total_steps": 25209, "loss": 0.3321, "lr": 3.108709811821079e-05, "epoch": 1.888611210282042, "percentage": 62.95, "elapsed_time": "1 day, 0:23:30", "remaining_time": "14:21:13", "throughput": 60547.44, "total_tokens": 5316704000} {"current_steps": 15880, "total_steps": 25209, "loss": 0.3297, "lr": 3.1081091297657696e-05, "epoch": 1.8898012614542425, "percentage": 62.99, "elapsed_time": "1 day, 0:24:19", "remaining_time": "14:20:14", "throughput": 60552.28, "total_tokens": 5320099840} {"current_steps": 15890, "total_steps": 25209, "loss": 0.3319, "lr": 3.107508795777251e-05, "epoch": 1.890991312626443, "percentage": 63.03, "elapsed_time": "1 day, 0:25:04", "remaining_time": "14:19:13", "throughput": 60558.42, "total_tokens": 5323369600} {"current_steps": 15900, "total_steps": 25209, "loss": 0.3353, "lr": 3.1069088095195056e-05, "epoch": 1.8921813637986433, "percentage": 63.07, "elapsed_time": "1 day, 0:25:54", "remaining_time": "14:18:14", "throughput": 60563.15, "total_tokens": 5326780800} {"current_steps": 15910, "total_steps": 25209, "loss": 0.328, "lr": 3.1063091706569703e-05, "epoch": 1.8933714149708436, "percentage": 63.11, "elapsed_time": "1 day, 0:26:43", "remaining_time": "14:17:16", "throughput": 60567.26, "total_tokens": 5330149248} {"current_steps": 15920, "total_steps": 25209, "loss": 0.3295, "lr": 3.105709878854535e-05, "epoch": 1.894561466143044, "percentage": 63.15, "elapsed_time": "1 day, 0:27:32", "remaining_time": "14:16:16", "throughput": 60571.51, "total_tokens": 5333453952} {"current_steps": 15930, "total_steps": 25209, "loss": 0.3315, "lr": 3.105110933777541e-05, "epoch": 1.8957515173152446, "percentage": 63.19, "elapsed_time": "1 day, 0:28:23", "remaining_time": "14:15:18", "throughput": 60575.64, "total_tokens": 5336896768} {"current_steps": 15940, "total_steps": 25209, "loss": 0.3346, "lr": 3.104512335091783e-05, "epoch": 1.896941568487445, "percentage": 63.23, "elapsed_time": "1 day, 0:29:14", "remaining_time": "14:14:21", "throughput": 60579.64, "total_tokens": 5340374784} {"current_steps": 15950, "total_steps": 25209, "loss": 0.3327, "lr": 3.1039140824635074e-05, "epoch": 1.8981316196596454, "percentage": 63.27, "elapsed_time": "1 day, 0:30:02", "remaining_time": "14:13:21", "throughput": 60585.22, "total_tokens": 5343756288} {"current_steps": 15960, "total_steps": 25209, "loss": 0.3337, "lr": 3.103316175559406e-05, "epoch": 1.8993216708318457, "percentage": 63.31, "elapsed_time": "1 day, 0:30:50", "remaining_time": "14:12:22", "throughput": 60589.93, "total_tokens": 5347076864} {"current_steps": 15970, "total_steps": 25209, "loss": 0.332, "lr": 3.102718614046624e-05, "epoch": 1.9005117220040462, "percentage": 63.35, "elapsed_time": "1 day, 0:31:37", "remaining_time": "14:11:22", "throughput": 60594.64, "total_tokens": 5350366080} {"current_steps": 15980, "total_steps": 25209, "loss": 0.3334, "lr": 3.1021213975927546e-05, "epoch": 1.9017017731762467, "percentage": 63.39, "elapsed_time": "1 day, 0:32:30", "remaining_time": "14:10:25", "throughput": 60597.66, "total_tokens": 5353815296} {"current_steps": 15990, "total_steps": 25209, "loss": 0.3332, "lr": 3.1015245258658374e-05, "epoch": 1.902891824348447, "percentage": 63.43, "elapsed_time": "1 day, 0:33:19", "remaining_time": "14:09:26", "throughput": 60602.71, "total_tokens": 5357225088} {"current_steps": 16000, "total_steps": 25209, "loss": 0.3314, "lr": 3.1009279985343606e-05, "epoch": 1.9040818755206472, "percentage": 63.47, "elapsed_time": "1 day, 0:34:07", "remaining_time": "14:08:26", "throughput": 60607.04, "total_tokens": 5360523520} {"current_steps": 16010, "total_steps": 25209, "loss": 0.331, "lr": 3.100331815267255e-05, "epoch": 1.9052719266928477, "percentage": 63.51, "elapsed_time": "1 day, 0:34:53", "remaining_time": "14:07:26", "throughput": 60613.31, "total_tokens": 5363876992} {"current_steps": 16020, "total_steps": 25209, "loss": 0.3332, "lr": 3.099735975733902e-05, "epoch": 1.9064619778650482, "percentage": 63.55, "elapsed_time": "1 day, 0:35:40", "remaining_time": "14:06:26", "throughput": 60618.74, "total_tokens": 5367217152} {"current_steps": 16030, "total_steps": 25209, "loss": 0.3297, "lr": 3.099140479604123e-05, "epoch": 1.9076520290372487, "percentage": 63.59, "elapsed_time": "1 day, 0:36:27", "remaining_time": "14:05:26", "throughput": 60623.22, "total_tokens": 5370472192} {"current_steps": 16040, "total_steps": 25209, "loss": 0.3337, "lr": 3.098545326548186e-05, "epoch": 1.908842080209449, "percentage": 63.63, "elapsed_time": "1 day, 0:37:17", "remaining_time": "14:04:28", "throughput": 60626.77, "total_tokens": 5373810688} {"current_steps": 16050, "total_steps": 25209, "loss": 0.33, "lr": 3.0979505162368014e-05, "epoch": 1.9100321313816493, "percentage": 63.67, "elapsed_time": "1 day, 0:38:04", "remaining_time": "14:03:28", "throughput": 60632.4, "total_tokens": 5377173376} {"current_steps": 16060, "total_steps": 25209, "loss": 0.3301, "lr": 3.097356048341121e-05, "epoch": 1.9112221825538498, "percentage": 63.71, "elapsed_time": "1 day, 0:38:55", "remaining_time": "14:02:30", "throughput": 60636.67, "total_tokens": 5380607488} {"current_steps": 16070, "total_steps": 25209, "loss": 0.332, "lr": 3.0967619225327396e-05, "epoch": 1.9124122337260503, "percentage": 63.75, "elapsed_time": "1 day, 0:39:43", "remaining_time": "14:01:31", "throughput": 60641.61, "total_tokens": 5383989376} {"current_steps": 16080, "total_steps": 25209, "loss": 0.3287, "lr": 3.0961681384836924e-05, "epoch": 1.9136022848982506, "percentage": 63.79, "elapsed_time": "1 day, 0:40:30", "remaining_time": "14:00:31", "throughput": 60647.34, "total_tokens": 5387348864} {"current_steps": 16090, "total_steps": 25209, "loss": 0.3342, "lr": 3.095574695866453e-05, "epoch": 1.914792336070451, "percentage": 63.83, "elapsed_time": "1 day, 0:41:17", "remaining_time": "13:59:31", "throughput": 60652.79, "total_tokens": 5390687872} {"current_steps": 16100, "total_steps": 25209, "loss": 0.3332, "lr": 3.0949815943539355e-05, "epoch": 1.9159823872426514, "percentage": 63.87, "elapsed_time": "1 day, 0:42:07", "remaining_time": "13:58:33", "throughput": 60656.97, "total_tokens": 5394068352} {"current_steps": 16110, "total_steps": 25209, "loss": 0.3335, "lr": 3.094388833619495e-05, "epoch": 1.9171724384148519, "percentage": 63.91, "elapsed_time": "1 day, 0:42:55", "remaining_time": "13:57:33", "throughput": 60662.13, "total_tokens": 5397439104} {"current_steps": 16120, "total_steps": 25209, "loss": 0.33, "lr": 3.0937964133369196e-05, "epoch": 1.9183624895870524, "percentage": 63.95, "elapsed_time": "1 day, 0:43:44", "remaining_time": "13:56:34", "throughput": 60666.39, "total_tokens": 5400778496} {"current_steps": 16130, "total_steps": 25209, "loss": 0.3308, "lr": 3.093204333180437e-05, "epoch": 1.9195525407592526, "percentage": 63.99, "elapsed_time": "1 day, 0:44:34", "remaining_time": "13:55:36", "throughput": 60670.25, "total_tokens": 5404145024} {"current_steps": 16140, "total_steps": 25209, "loss": 0.3331, "lr": 3.0926125928247114e-05, "epoch": 1.920742591931453, "percentage": 64.02, "elapsed_time": "1 day, 0:45:22", "remaining_time": "13:54:37", "throughput": 60674.87, "total_tokens": 5407474048} {"current_steps": 16150, "total_steps": 25209, "loss": 0.332, "lr": 3.092021191944842e-05, "epoch": 1.9219326431036534, "percentage": 64.06, "elapsed_time": "1 day, 0:46:10", "remaining_time": "13:53:38", "throughput": 60679.48, "total_tokens": 5410789376} {"current_steps": 16160, "total_steps": 25209, "loss": 0.3318, "lr": 3.091430130216363e-05, "epoch": 1.923122694275854, "percentage": 64.1, "elapsed_time": "1 day, 0:46:58", "remaining_time": "13:52:38", "throughput": 60684.05, "total_tokens": 5414121216} {"current_steps": 16170, "total_steps": 25209, "loss": 0.3333, "lr": 3.090839407315242e-05, "epoch": 1.9243127454480544, "percentage": 64.14, "elapsed_time": "1 day, 0:47:46", "remaining_time": "13:51:39", "throughput": 60689.01, "total_tokens": 5417487104} {"current_steps": 16180, "total_steps": 25209, "loss": 0.3297, "lr": 3.0902490229178794e-05, "epoch": 1.9255027966202547, "percentage": 64.18, "elapsed_time": "1 day, 0:48:33", "remaining_time": "13:50:40", "throughput": 60694.38, "total_tokens": 5420839424} {"current_steps": 16190, "total_steps": 25209, "loss": 0.3312, "lr": 3.0896589767011104e-05, "epoch": 1.926692847792455, "percentage": 64.22, "elapsed_time": "1 day, 0:49:26", "remaining_time": "13:49:43", "throughput": 60697.53, "total_tokens": 5424322304} {"current_steps": 16200, "total_steps": 25209, "loss": 0.3322, "lr": 3.0890692683421985e-05, "epoch": 1.9278828989646555, "percentage": 64.26, "elapsed_time": "1 day, 0:50:14", "remaining_time": "13:48:44", "throughput": 60702.91, "total_tokens": 5427718784} {"current_steps": 16210, "total_steps": 25209, "loss": 0.3264, "lr": 3.088479897518843e-05, "epoch": 1.929072950136856, "percentage": 64.3, "elapsed_time": "1 day, 0:51:03", "remaining_time": "13:47:45", "throughput": 60707.49, "total_tokens": 5431104256} {"current_steps": 16220, "total_steps": 25209, "loss": 0.3308, "lr": 3.087890863909168e-05, "epoch": 1.9302630013090563, "percentage": 64.34, "elapsed_time": "1 day, 0:51:49", "remaining_time": "13:46:45", "throughput": 60712.34, "total_tokens": 5434325760} {"current_steps": 16230, "total_steps": 25209, "loss": 0.3348, "lr": 3.087302167191732e-05, "epoch": 1.9314530524812565, "percentage": 64.38, "elapsed_time": "1 day, 0:52:35", "remaining_time": "13:45:45", "throughput": 60717.98, "total_tokens": 5437622016} {"current_steps": 16240, "total_steps": 25209, "loss": 0.3337, "lr": 3.086713807045518e-05, "epoch": 1.932643103653457, "percentage": 64.42, "elapsed_time": "1 day, 0:53:25", "remaining_time": "13:44:46", "throughput": 60722.73, "total_tokens": 5441068032} {"current_steps": 16250, "total_steps": 25209, "loss": 0.3322, "lr": 3.086125783149941e-05, "epoch": 1.9338331548256575, "percentage": 64.46, "elapsed_time": "1 day, 0:54:12", "remaining_time": "13:43:47", "throughput": 60727.56, "total_tokens": 5444360320} {"current_steps": 16260, "total_steps": 25209, "loss": 0.3314, "lr": 3.0855380951848404e-05, "epoch": 1.935023205997858, "percentage": 64.5, "elapsed_time": "1 day, 0:55:00", "remaining_time": "13:42:48", "throughput": 60731.82, "total_tokens": 5447667328} {"current_steps": 16270, "total_steps": 25209, "loss": 0.3338, "lr": 3.084950742830484e-05, "epoch": 1.9362132571700583, "percentage": 64.54, "elapsed_time": "1 day, 0:55:45", "remaining_time": "13:41:47", "throughput": 60737.88, "total_tokens": 5450925568} {"current_steps": 16280, "total_steps": 25209, "loss": 0.3295, "lr": 3.0843637257675654e-05, "epoch": 1.9374033083422586, "percentage": 64.58, "elapsed_time": "1 day, 0:56:34", "remaining_time": "13:40:49", "throughput": 60742.39, "total_tokens": 5454356608} {"current_steps": 16290, "total_steps": 25209, "loss": 0.3319, "lr": 3.083777043677202e-05, "epoch": 1.938593359514459, "percentage": 64.62, "elapsed_time": "1 day, 0:57:22", "remaining_time": "13:39:50", "throughput": 60747.03, "total_tokens": 5457674368} {"current_steps": 16300, "total_steps": 25209, "loss": 0.3309, "lr": 3.083190696240936e-05, "epoch": 1.9397834106866596, "percentage": 64.66, "elapsed_time": "1 day, 0:58:10", "remaining_time": "13:38:50", "throughput": 60751.83, "total_tokens": 5460989952} {"current_steps": 16310, "total_steps": 25209, "loss": 0.3307, "lr": 3.082604683140735e-05, "epoch": 1.9409734618588599, "percentage": 64.7, "elapsed_time": "1 day, 0:58:57", "remaining_time": "13:37:51", "throughput": 60756.76, "total_tokens": 5464306816} {"current_steps": 16320, "total_steps": 25209, "loss": 0.3277, "lr": 3.082019004058987e-05, "epoch": 1.9421635130310604, "percentage": 64.74, "elapsed_time": "1 day, 0:59:47", "remaining_time": "13:36:53", "throughput": 60760.48, "total_tokens": 5467708544} {"current_steps": 16330, "total_steps": 25209, "loss": 0.3334, "lr": 3.081433658678505e-05, "epoch": 1.9433535642032607, "percentage": 64.78, "elapsed_time": "1 day, 1:00:32", "remaining_time": "13:35:52", "throughput": 60767.46, "total_tokens": 5471044864} {"current_steps": 16340, "total_steps": 25209, "loss": 0.3327, "lr": 3.080848646682521e-05, "epoch": 1.9445436153754612, "percentage": 64.82, "elapsed_time": "1 day, 1:01:18", "remaining_time": "13:34:52", "throughput": 60773.61, "total_tokens": 5474372864} {"current_steps": 16350, "total_steps": 25209, "loss": 0.3282, "lr": 3.080263967754689e-05, "epoch": 1.9457336665476617, "percentage": 64.86, "elapsed_time": "1 day, 1:02:05", "remaining_time": "13:33:53", "throughput": 60778.49, "total_tokens": 5477710592} {"current_steps": 16360, "total_steps": 25209, "loss": 0.3336, "lr": 3.079679621579083e-05, "epoch": 1.946923717719862, "percentage": 64.9, "elapsed_time": "1 day, 1:02:54", "remaining_time": "13:32:54", "throughput": 60783.61, "total_tokens": 5481109120} {"current_steps": 16370, "total_steps": 25209, "loss": 0.3284, "lr": 3.079095607840197e-05, "epoch": 1.9481137688920622, "percentage": 64.94, "elapsed_time": "1 day, 1:03:43", "remaining_time": "13:31:56", "throughput": 60787.26, "total_tokens": 5484466688} {"current_steps": 16380, "total_steps": 25209, "loss": 0.3292, "lr": 3.0785119262229416e-05, "epoch": 1.9493038200642627, "percentage": 64.98, "elapsed_time": "1 day, 1:04:33", "remaining_time": "13:30:58", "throughput": 60790.99, "total_tokens": 5487808256} {"current_steps": 16390, "total_steps": 25209, "loss": 0.3294, "lr": 3.0779285764126485e-05, "epoch": 1.9504938712364632, "percentage": 65.02, "elapsed_time": "1 day, 1:05:21", "remaining_time": "13:29:59", "throughput": 60796.1, "total_tokens": 5491186688} {"current_steps": 16400, "total_steps": 25209, "loss": 0.3294, "lr": 3.077345558095064e-05, "epoch": 1.9516839224086637, "percentage": 65.06, "elapsed_time": "1 day, 1:06:08", "remaining_time": "13:29:00", "throughput": 60801.26, "total_tokens": 5494528256} {"current_steps": 16410, "total_steps": 25209, "loss": 0.3259, "lr": 3.076762870956352e-05, "epoch": 1.952873973580864, "percentage": 65.1, "elapsed_time": "1 day, 1:06:56", "remaining_time": "13:28:01", "throughput": 60805.96, "total_tokens": 5497868416} {"current_steps": 16420, "total_steps": 25209, "loss": 0.3339, "lr": 3.076180514683092e-05, "epoch": 1.9540640247530643, "percentage": 65.14, "elapsed_time": "1 day, 1:07:45", "remaining_time": "13:27:02", "throughput": 60809.76, "total_tokens": 5501210368} {"current_steps": 16430, "total_steps": 25209, "loss": 0.3347, "lr": 3.075598488962278e-05, "epoch": 1.9552540759252648, "percentage": 65.18, "elapsed_time": "1 day, 1:08:33", "remaining_time": "13:26:03", "throughput": 60815.3, "total_tokens": 5504605440} {"current_steps": 16440, "total_steps": 25209, "loss": 0.3335, "lr": 3.0750167934813207e-05, "epoch": 1.9564441270974653, "percentage": 65.21, "elapsed_time": "1 day, 1:09:21", "remaining_time": "13:25:04", "throughput": 60820.27, "total_tokens": 5507952896} {"current_steps": 16450, "total_steps": 25209, "loss": 0.3285, "lr": 3.074435427928041e-05, "epoch": 1.9576341782696656, "percentage": 65.25, "elapsed_time": "1 day, 1:10:10", "remaining_time": "13:24:06", "throughput": 60825.26, "total_tokens": 5511380480} {"current_steps": 16460, "total_steps": 25209, "loss": 0.3328, "lr": 3.073854391990675e-05, "epoch": 1.9588242294418658, "percentage": 65.29, "elapsed_time": "1 day, 1:10:59", "remaining_time": "13:23:08", "throughput": 60829.03, "total_tokens": 5514754560} {"current_steps": 16470, "total_steps": 25209, "loss": 0.334, "lr": 3.073273685357871e-05, "epoch": 1.9600142806140664, "percentage": 65.33, "elapsed_time": "1 day, 1:11:49", "remaining_time": "13:22:10", "throughput": 60832.35, "total_tokens": 5518084352} {"current_steps": 16480, "total_steps": 25209, "loss": 0.3316, "lr": 3.072693307718689e-05, "epoch": 1.9612043317862669, "percentage": 65.37, "elapsed_time": "1 day, 1:12:41", "remaining_time": "13:21:13", "throughput": 60835.08, "total_tokens": 5521493376} {"current_steps": 16490, "total_steps": 25209, "loss": 0.3351, "lr": 3.0721132587626e-05, "epoch": 1.9623943829584674, "percentage": 65.41, "elapsed_time": "1 day, 1:13:29", "remaining_time": "13:20:15", "throughput": 60839.95, "total_tokens": 5524854272} {"current_steps": 16500, "total_steps": 25209, "loss": 0.3316, "lr": 3.071533538179482e-05, "epoch": 1.9635844341306676, "percentage": 65.45, "elapsed_time": "1 day, 1:14:16", "remaining_time": "13:19:15", "throughput": 60845.4, "total_tokens": 5528193024} {"current_steps": 16510, "total_steps": 25209, "loss": 0.3329, "lr": 3.070954145659627e-05, "epoch": 1.964774485302868, "percentage": 65.49, "elapsed_time": "1 day, 1:15:04", "remaining_time": "13:18:16", "throughput": 60850.39, "total_tokens": 5531583104} {"current_steps": 16520, "total_steps": 25209, "loss": 0.3292, "lr": 3.070375080893734e-05, "epoch": 1.9659645364750684, "percentage": 65.53, "elapsed_time": "1 day, 1:15:53", "remaining_time": "13:17:18", "throughput": 60854.17, "total_tokens": 5534916864} {"current_steps": 16530, "total_steps": 25209, "loss": 0.3347, "lr": 3.06979634357291e-05, "epoch": 1.967154587647269, "percentage": 65.57, "elapsed_time": "1 day, 1:16:40", "remaining_time": "13:16:19", "throughput": 60858.7, "total_tokens": 5538196992} {"current_steps": 16540, "total_steps": 25209, "loss": 0.3303, "lr": 3.0692179333886686e-05, "epoch": 1.9683446388194692, "percentage": 65.61, "elapsed_time": "1 day, 1:17:31", "remaining_time": "13:15:22", "throughput": 60861.95, "total_tokens": 5541596032} {"current_steps": 16550, "total_steps": 25209, "loss": 0.3333, "lr": 3.068639850032933e-05, "epoch": 1.9695346899916697, "percentage": 65.65, "elapsed_time": "1 day, 1:18:21", "remaining_time": "13:14:24", "throughput": 60866.32, "total_tokens": 5544996096} {"current_steps": 16560, "total_steps": 25209, "loss": 0.33, "lr": 3.068062093198028e-05, "epoch": 1.97072474116387, "percentage": 65.69, "elapsed_time": "1 day, 1:19:12", "remaining_time": "13:13:27", "throughput": 60869.43, "total_tokens": 5548392064} {"current_steps": 16570, "total_steps": 25209, "loss": 0.3302, "lr": 3.067484662576687e-05, "epoch": 1.9719147923360705, "percentage": 65.73, "elapsed_time": "1 day, 1:19:58", "remaining_time": "13:12:27", "throughput": 60875.13, "total_tokens": 5551692672} {"current_steps": 16580, "total_steps": 25209, "loss": 0.3302, "lr": 3.066907557862048e-05, "epoch": 1.973104843508271, "percentage": 65.77, "elapsed_time": "1 day, 1:20:47", "remaining_time": "13:11:29", "throughput": 60879.71, "total_tokens": 5555113600} {"current_steps": 16590, "total_steps": 25209, "loss": 0.3292, "lr": 3.066330778747651e-05, "epoch": 1.9742948946804713, "percentage": 65.81, "elapsed_time": "1 day, 1:21:37", "remaining_time": "13:10:31", "throughput": 60883.92, "total_tokens": 5558556160} {"current_steps": 16600, "total_steps": 25209, "loss": 0.3332, "lr": 3.065754324927441e-05, "epoch": 1.9754849458526715, "percentage": 65.85, "elapsed_time": "1 day, 1:22:26", "remaining_time": "13:09:33", "throughput": 60888.4, "total_tokens": 5561961344} {"current_steps": 16610, "total_steps": 25209, "loss": 0.3337, "lr": 3.065178196095765e-05, "epoch": 1.976674997024872, "percentage": 65.89, "elapsed_time": "1 day, 1:23:12", "remaining_time": "13:08:33", "throughput": 60893.59, "total_tokens": 5565225728} {"current_steps": 16620, "total_steps": 25209, "loss": 0.3337, "lr": 3.064602391947372e-05, "epoch": 1.9778650481970725, "percentage": 65.93, "elapsed_time": "1 day, 1:24:04", "remaining_time": "13:07:37", "throughput": 60897.56, "total_tokens": 5568718976} {"current_steps": 16630, "total_steps": 25209, "loss": 0.3351, "lr": 3.0640269121774126e-05, "epoch": 1.979055099369273, "percentage": 65.97, "elapsed_time": "1 day, 1:24:54", "remaining_time": "13:06:39", "throughput": 60901.2, "total_tokens": 5572100224} {"current_steps": 16640, "total_steps": 25209, "loss": 0.3319, "lr": 3.063451756481437e-05, "epoch": 1.9802451505414733, "percentage": 66.01, "elapsed_time": "1 day, 1:25:40", "remaining_time": "13:05:40", "throughput": 60906.25, "total_tokens": 5575391744} {"current_steps": 16650, "total_steps": 25209, "loss": 0.3296, "lr": 3.062876924555396e-05, "epoch": 1.9814352017136736, "percentage": 66.05, "elapsed_time": "1 day, 1:26:28", "remaining_time": "13:04:41", "throughput": 60910.53, "total_tokens": 5578722944} {"current_steps": 16660, "total_steps": 25209, "loss": 0.3331, "lr": 3.06230241609564e-05, "epoch": 1.982625252885874, "percentage": 66.09, "elapsed_time": "1 day, 1:27:14", "remaining_time": "13:03:41", "throughput": 60915.62, "total_tokens": 5581984512} {"current_steps": 16670, "total_steps": 25209, "loss": 0.3312, "lr": 3.061728230798916e-05, "epoch": 1.9838153040580746, "percentage": 66.13, "elapsed_time": "1 day, 1:28:02", "remaining_time": "13:02:43", "throughput": 60920.34, "total_tokens": 5585305856} {"current_steps": 16680, "total_steps": 25209, "loss": 0.3268, "lr": 3.061154368362373e-05, "epoch": 1.9850053552302749, "percentage": 66.17, "elapsed_time": "1 day, 1:28:51", "remaining_time": "13:01:45", "throughput": 60924.95, "total_tokens": 5588718720} {"current_steps": 16690, "total_steps": 25209, "loss": 0.3319, "lr": 3.060580828483552e-05, "epoch": 1.9861954064024752, "percentage": 66.21, "elapsed_time": "1 day, 1:29:34", "remaining_time": "13:00:44", "throughput": 60931.42, "total_tokens": 5591961344} {"current_steps": 16700, "total_steps": 25209, "loss": 0.329, "lr": 3.060007610860395e-05, "epoch": 1.9873854575746757, "percentage": 66.25, "elapsed_time": "1 day, 1:30:21", "remaining_time": "12:59:44", "throughput": 60937.34, "total_tokens": 5595329024} {"current_steps": 16710, "total_steps": 25209, "loss": 0.3308, "lr": 3.059434715191236e-05, "epoch": 1.9885755087468762, "percentage": 66.29, "elapsed_time": "1 day, 1:31:10", "remaining_time": "12:58:46", "throughput": 60941.84, "total_tokens": 5598731008} {"current_steps": 16720, "total_steps": 25209, "loss": 0.3306, "lr": 3.0588621411748074e-05, "epoch": 1.9897655599190767, "percentage": 66.33, "elapsed_time": "1 day, 1:31:56", "remaining_time": "12:57:47", "throughput": 60946.98, "total_tokens": 5602016768} {"current_steps": 16730, "total_steps": 25209, "loss": 0.3344, "lr": 3.0582898885102344e-05, "epoch": 1.990955611091277, "percentage": 66.37, "elapsed_time": "1 day, 1:32:43", "remaining_time": "12:56:48", "throughput": 60951.95, "total_tokens": 5605327872} {"current_steps": 16740, "total_steps": 25209, "loss": 0.3313, "lr": 3.0577179568970366e-05, "epoch": 1.9921456622634772, "percentage": 66.4, "elapsed_time": "1 day, 1:33:30", "remaining_time": "12:55:49", "throughput": 60956.48, "total_tokens": 5608657536} {"current_steps": 16750, "total_steps": 25209, "loss": 0.3299, "lr": 3.057146346035127e-05, "epoch": 1.9933357134356777, "percentage": 66.44, "elapsed_time": "1 day, 1:34:15", "remaining_time": "12:54:49", "throughput": 60961.53, "total_tokens": 5611859328} {"current_steps": 16760, "total_steps": 25209, "loss": 0.3308, "lr": 3.056575055624811e-05, "epoch": 1.9945257646078782, "percentage": 66.48, "elapsed_time": "1 day, 1:35:03", "remaining_time": "12:53:50", "throughput": 60965.99, "total_tokens": 5615168000} {"current_steps": 16770, "total_steps": 25209, "loss": 0.335, "lr": 3.0560040853667846e-05, "epoch": 1.9957158157800785, "percentage": 66.52, "elapsed_time": "1 day, 1:35:52", "remaining_time": "12:52:52", "throughput": 60970.16, "total_tokens": 5618542976} {"current_steps": 16780, "total_steps": 25209, "loss": 0.329, "lr": 3.0554334349621366e-05, "epoch": 1.9969058669522788, "percentage": 66.56, "elapsed_time": "1 day, 1:36:41", "remaining_time": "12:51:54", "throughput": 60973.77, "total_tokens": 5621847936} {"current_steps": 16790, "total_steps": 25209, "loss": 0.3292, "lr": 3.054863104112347e-05, "epoch": 1.9980959181244793, "percentage": 66.6, "elapsed_time": "1 day, 1:37:29", "remaining_time": "12:50:56", "throughput": 60978.23, "total_tokens": 5625196416} {"current_steps": 16800, "total_steps": 25209, "loss": 0.3295, "lr": 3.0542930925192835e-05, "epoch": 1.9992859692966798, "percentage": 66.64, "elapsed_time": "1 day, 1:38:17", "remaining_time": "12:49:58", "throughput": 60982.35, "total_tokens": 5628529024} {"current_steps": 16810, "total_steps": 25209, "loss": 0.3242, "lr": 3.053723399885205e-05, "epoch": 2.0004760204688803, "percentage": 66.68, "elapsed_time": "1 day, 1:39:07", "remaining_time": "12:49:00", "throughput": 60985.7, "total_tokens": 5631854848} {"current_steps": 16820, "total_steps": 25209, "loss": 0.3203, "lr": 3.0531540259127565e-05, "epoch": 2.0016660716410803, "percentage": 66.72, "elapsed_time": "1 day, 1:39:57", "remaining_time": "12:48:03", "throughput": 60989.01, "total_tokens": 5635229696} {"current_steps": 16830, "total_steps": 25209, "loss": 0.313, "lr": 3.052584970304976e-05, "epoch": 2.002856122813281, "percentage": 66.76, "elapsed_time": "1 day, 1:40:50", "remaining_time": "12:47:07", "throughput": 60991.7, "total_tokens": 5638683648} {"current_steps": 16840, "total_steps": 25209, "loss": 0.3181, "lr": 3.052016232765282e-05, "epoch": 2.0040461739854813, "percentage": 66.8, "elapsed_time": "1 day, 1:41:39", "remaining_time": "12:46:09", "throughput": 60996.5, "total_tokens": 5642132096} {"current_steps": 16850, "total_steps": 25209, "loss": 0.3179, "lr": 3.0514478129974845e-05, "epoch": 2.005236225157682, "percentage": 66.84, "elapsed_time": "1 day, 1:42:26", "remaining_time": "12:45:10", "throughput": 61001.95, "total_tokens": 5645496704} {"current_steps": 16860, "total_steps": 25209, "loss": 0.3185, "lr": 3.0508797107057785e-05, "epoch": 2.0064262763298824, "percentage": 66.88, "elapsed_time": "1 day, 1:43:13", "remaining_time": "12:44:11", "throughput": 61007.07, "total_tokens": 5648834688} {"current_steps": 16870, "total_steps": 25209, "loss": 0.3167, "lr": 3.0503119255947432e-05, "epoch": 2.0076163275020824, "percentage": 66.92, "elapsed_time": "1 day, 1:44:00", "remaining_time": "12:43:13", "throughput": 61011.12, "total_tokens": 5652122112} {"current_steps": 16880, "total_steps": 25209, "loss": 0.3224, "lr": 3.049744457369344e-05, "epoch": 2.008806378674283, "percentage": 66.96, "elapsed_time": "1 day, 1:44:50", "remaining_time": "12:42:15", "throughput": 61014.51, "total_tokens": 5655491584} {"current_steps": 16890, "total_steps": 25209, "loss": 0.3179, "lr": 3.049177305734929e-05, "epoch": 2.0099964298464834, "percentage": 67.0, "elapsed_time": "1 day, 1:45:37", "remaining_time": "12:41:16", "throughput": 61019.47, "total_tokens": 5658794496} {"current_steps": 16900, "total_steps": 25209, "loss": 0.3195, "lr": 3.04861047039723e-05, "epoch": 2.011186481018684, "percentage": 67.04, "elapsed_time": "1 day, 1:46:25", "remaining_time": "12:40:18", "throughput": 61024.02, "total_tokens": 5662135040} {"current_steps": 16910, "total_steps": 25209, "loss": 0.3167, "lr": 3.0480439510623638e-05, "epoch": 2.0123765321908844, "percentage": 67.08, "elapsed_time": "1 day, 1:47:11", "remaining_time": "12:39:19", "throughput": 61029.81, "total_tokens": 5665481984} {"current_steps": 16920, "total_steps": 25209, "loss": 0.3154, "lr": 3.0474777474368255e-05, "epoch": 2.0135665833630845, "percentage": 67.12, "elapsed_time": "1 day, 1:47:57", "remaining_time": "12:38:19", "throughput": 61035.06, "total_tokens": 5668756352} {"current_steps": 16930, "total_steps": 25209, "loss": 0.3151, "lr": 3.046911859227495e-05, "epoch": 2.014756634535285, "percentage": 67.16, "elapsed_time": "1 day, 1:48:47", "remaining_time": "12:37:22", "throughput": 61038.56, "total_tokens": 5672158592} {"current_steps": 16940, "total_steps": 25209, "loss": 0.3208, "lr": 3.0463462861416302e-05, "epoch": 2.0159466857074855, "percentage": 67.2, "elapsed_time": "1 day, 1:49:34", "remaining_time": "12:36:24", "throughput": 61042.81, "total_tokens": 5675445888} {"current_steps": 16950, "total_steps": 25209, "loss": 0.321, "lr": 3.045781027886873e-05, "epoch": 2.017136736879686, "percentage": 67.24, "elapsed_time": "1 day, 1:50:19", "remaining_time": "12:35:24", "throughput": 61048.13, "total_tokens": 5678669696} {"current_steps": 16960, "total_steps": 25209, "loss": 0.3174, "lr": 3.0452160841712408e-05, "epoch": 2.018326788051886, "percentage": 67.28, "elapsed_time": "1 day, 1:51:10", "remaining_time": "12:34:27", "throughput": 61052.22, "total_tokens": 5682147456} {"current_steps": 16970, "total_steps": 25209, "loss": 0.3177, "lr": 3.044651454703133e-05, "epoch": 2.0195168392240865, "percentage": 67.32, "elapsed_time": "1 day, 1:51:54", "remaining_time": "12:33:27", "throughput": 61058.01, "total_tokens": 5685401856} {"current_steps": 16980, "total_steps": 25209, "loss": 0.3199, "lr": 3.0440871391913257e-05, "epoch": 2.020706890396287, "percentage": 67.36, "elapsed_time": "1 day, 1:52:46", "remaining_time": "12:32:31", "throughput": 61060.45, "total_tokens": 5688771072} {"current_steps": 16990, "total_steps": 25209, "loss": 0.3178, "lr": 3.043523137344973e-05, "epoch": 2.0218969415684875, "percentage": 67.4, "elapsed_time": "1 day, 1:53:36", "remaining_time": "12:31:33", "throughput": 61064.27, "total_tokens": 5692195584} {"current_steps": 17000, "total_steps": 25209, "loss": 0.3168, "lr": 3.0429594488736074e-05, "epoch": 2.023086992740688, "percentage": 67.44, "elapsed_time": "1 day, 1:54:22", "remaining_time": "12:30:34", "throughput": 61069.23, "total_tokens": 5695482880} {"current_steps": 17010, "total_steps": 25209, "loss": 0.3199, "lr": 3.0423960734871348e-05, "epoch": 2.024277043912888, "percentage": 67.48, "elapsed_time": "1 day, 1:55:08", "remaining_time": "12:29:35", "throughput": 61073.88, "total_tokens": 5698730624} {"current_steps": 17020, "total_steps": 25209, "loss": 0.3142, "lr": 3.0418330108958404e-05, "epoch": 2.0254670950850886, "percentage": 67.52, "elapsed_time": "1 day, 1:55:53", "remaining_time": "12:28:36", "throughput": 61079.35, "total_tokens": 5701985408} {"current_steps": 17030, "total_steps": 25209, "loss": 0.3234, "lr": 3.0412702608103828e-05, "epoch": 2.026657146257289, "percentage": 67.56, "elapsed_time": "1 day, 1:56:44", "remaining_time": "12:27:39", "throughput": 61083.15, "total_tokens": 5705417472} {"current_steps": 17040, "total_steps": 25209, "loss": 0.3233, "lr": 3.0407078229417944e-05, "epoch": 2.0278471974294896, "percentage": 67.59, "elapsed_time": "1 day, 1:57:28", "remaining_time": "12:26:39", "throughput": 61088.55, "total_tokens": 5708652544} {"current_steps": 17050, "total_steps": 25209, "loss": 0.3203, "lr": 3.0401456970014836e-05, "epoch": 2.0290372486016897, "percentage": 67.63, "elapsed_time": "1 day, 1:58:15", "remaining_time": "12:25:40", "throughput": 61093.64, "total_tokens": 5711977600} {"current_steps": 17060, "total_steps": 25209, "loss": 0.3215, "lr": 3.039583882701231e-05, "epoch": 2.03022729977389, "percentage": 67.67, "elapsed_time": "1 day, 1:58:59", "remaining_time": "12:24:40", "throughput": 61099.41, "total_tokens": 5715234176} {"current_steps": 17070, "total_steps": 25209, "loss": 0.3211, "lr": 3.0390223797531887e-05, "epoch": 2.0314173509460907, "percentage": 67.71, "elapsed_time": "1 day, 1:59:47", "remaining_time": "12:23:42", "throughput": 61103.88, "total_tokens": 5718582656} {"current_steps": 17080, "total_steps": 25209, "loss": 0.3149, "lr": 3.0384611878698837e-05, "epoch": 2.032607402118291, "percentage": 67.75, "elapsed_time": "1 day, 2:00:35", "remaining_time": "12:22:44", "throughput": 61108.5, "total_tokens": 5721949312} {"current_steps": 17090, "total_steps": 25209, "loss": 0.3187, "lr": 3.0379003067642113e-05, "epoch": 2.0337974532904917, "percentage": 67.79, "elapsed_time": "1 day, 2:01:22", "remaining_time": "12:21:46", "throughput": 61113.32, "total_tokens": 5725278208} {"current_steps": 17100, "total_steps": 25209, "loss": 0.3196, "lr": 3.037339736149441e-05, "epoch": 2.0349875044626917, "percentage": 67.83, "elapsed_time": "1 day, 2:02:06", "remaining_time": "12:20:45", "throughput": 61119.25, "total_tokens": 5728464768} {"current_steps": 17110, "total_steps": 25209, "loss": 0.3212, "lr": 3.0367794757392092e-05, "epoch": 2.0361775556348922, "percentage": 67.87, "elapsed_time": "1 day, 2:02:53", "remaining_time": "12:19:47", "throughput": 61123.85, "total_tokens": 5731775616} {"current_steps": 17120, "total_steps": 25209, "loss": 0.3172, "lr": 3.0362195252475245e-05, "epoch": 2.0373676068070927, "percentage": 67.91, "elapsed_time": "1 day, 2:03:42", "remaining_time": "12:18:50", "throughput": 61127.92, "total_tokens": 5735201920} {"current_steps": 17130, "total_steps": 25209, "loss": 0.3191, "lr": 3.0356598843887634e-05, "epoch": 2.0385576579792932, "percentage": 67.95, "elapsed_time": "1 day, 2:04:29", "remaining_time": "12:17:51", "throughput": 61132.77, "total_tokens": 5738494464} {"current_steps": 17140, "total_steps": 25209, "loss": 0.3188, "lr": 3.03510055287767e-05, "epoch": 2.0397477091514937, "percentage": 67.99, "elapsed_time": "1 day, 2:05:17", "remaining_time": "12:16:53", "throughput": 61137.35, "total_tokens": 5741846016} {"current_steps": 17150, "total_steps": 25209, "loss": 0.3142, "lr": 3.0345415304293578e-05, "epoch": 2.040937760323694, "percentage": 68.03, "elapsed_time": "1 day, 2:06:06", "remaining_time": "12:15:56", "throughput": 61141.4, "total_tokens": 5745257856} {"current_steps": 17160, "total_steps": 25209, "loss": 0.3147, "lr": 3.0339828167593065e-05, "epoch": 2.0421278114958943, "percentage": 68.07, "elapsed_time": "1 day, 2:06:54", "remaining_time": "12:14:58", "throughput": 61146.79, "total_tokens": 5748686080} {"current_steps": 17170, "total_steps": 25209, "loss": 0.3245, "lr": 3.033424411583363e-05, "epoch": 2.043317862668095, "percentage": 68.11, "elapsed_time": "1 day, 2:07:40", "remaining_time": "12:13:58", "throughput": 61151.62, "total_tokens": 5751922432} {"current_steps": 17180, "total_steps": 25209, "loss": 0.3188, "lr": 3.0328663146177387e-05, "epoch": 2.0445079138402953, "percentage": 68.15, "elapsed_time": "1 day, 2:08:27", "remaining_time": "12:13:00", "throughput": 61156.07, "total_tokens": 5755274240} {"current_steps": 17190, "total_steps": 25209, "loss": 0.3186, "lr": 3.032308525579013e-05, "epoch": 2.0456979650124953, "percentage": 68.19, "elapsed_time": "1 day, 2:09:14", "remaining_time": "12:12:02", "throughput": 61160.75, "total_tokens": 5758586368} {"current_steps": 17200, "total_steps": 25209, "loss": 0.3179, "lr": 3.031751044184127e-05, "epoch": 2.046888016184696, "percentage": 68.23, "elapsed_time": "1 day, 2:10:02", "remaining_time": "12:11:04", "throughput": 61165.13, "total_tokens": 5761908608} {"current_steps": 17210, "total_steps": 25209, "loss": 0.3202, "lr": 3.0311938701503872e-05, "epoch": 2.0480780673568963, "percentage": 68.27, "elapsed_time": "1 day, 2:10:48", "remaining_time": "12:10:05", "throughput": 61170.37, "total_tokens": 5765216000} {"current_steps": 17220, "total_steps": 25209, "loss": 0.3195, "lr": 3.0306370031954646e-05, "epoch": 2.049268118529097, "percentage": 68.31, "elapsed_time": "1 day, 2:11:38", "remaining_time": "12:09:08", "throughput": 61174.36, "total_tokens": 5768666240} {"current_steps": 17230, "total_steps": 25209, "loss": 0.32, "lr": 3.030080443037393e-05, "epoch": 2.0504581697012974, "percentage": 68.35, "elapsed_time": "1 day, 2:12:30", "remaining_time": "12:08:12", "throughput": 61177.31, "total_tokens": 5772123008} {"current_steps": 17240, "total_steps": 25209, "loss": 0.3211, "lr": 3.0295241893945663e-05, "epoch": 2.0516482208734974, "percentage": 68.39, "elapsed_time": "1 day, 2:13:19", "remaining_time": "12:07:15", "throughput": 61180.87, "total_tokens": 5775464960} {"current_steps": 17250, "total_steps": 25209, "loss": 0.317, "lr": 3.028968241985743e-05, "epoch": 2.052838272045698, "percentage": 68.43, "elapsed_time": "1 day, 2:14:09", "remaining_time": "12:06:18", "throughput": 61184.81, "total_tokens": 5778864512} {"current_steps": 17260, "total_steps": 25209, "loss": 0.3171, "lr": 3.0284126005300405e-05, "epoch": 2.0540283232178984, "percentage": 68.47, "elapsed_time": "1 day, 2:14:57", "remaining_time": "12:05:20", "throughput": 61189.45, "total_tokens": 5782250368} {"current_steps": 17270, "total_steps": 25209, "loss": 0.3175, "lr": 3.0278572647469385e-05, "epoch": 2.055218374390099, "percentage": 68.51, "elapsed_time": "1 day, 2:15:44", "remaining_time": "12:04:21", "throughput": 61194.68, "total_tokens": 5785595904} {"current_steps": 17280, "total_steps": 25209, "loss": 0.3186, "lr": 3.027302234356275e-05, "epoch": 2.056408425562299, "percentage": 68.55, "elapsed_time": "1 day, 2:16:32", "remaining_time": "12:03:24", "throughput": 61199.35, "total_tokens": 5788994560} {"current_steps": 17290, "total_steps": 25209, "loss": 0.3205, "lr": 3.0267475090782494e-05, "epoch": 2.0575984767344995, "percentage": 68.59, "elapsed_time": "1 day, 2:17:20", "remaining_time": "12:02:26", "throughput": 61203.57, "total_tokens": 5792360960} {"current_steps": 17300, "total_steps": 25209, "loss": 0.3194, "lr": 3.026193088633418e-05, "epoch": 2.0587885279067, "percentage": 68.63, "elapsed_time": "1 day, 2:18:04", "remaining_time": "12:01:26", "throughput": 61210.24, "total_tokens": 5795677440} {"current_steps": 17310, "total_steps": 25209, "loss": 0.3253, "lr": 3.0256389727426952e-05, "epoch": 2.0599785790789005, "percentage": 68.67, "elapsed_time": "1 day, 2:18:53", "remaining_time": "12:00:29", "throughput": 61214.74, "total_tokens": 5799061504} {"current_steps": 17320, "total_steps": 25209, "loss": 0.3231, "lr": 3.0250851611273555e-05, "epoch": 2.061168630251101, "percentage": 68.71, "elapsed_time": "1 day, 2:19:39", "remaining_time": "11:59:30", "throughput": 61219.81, "total_tokens": 5802380416} {"current_steps": 17330, "total_steps": 25209, "loss": 0.3142, "lr": 3.0245316535090273e-05, "epoch": 2.062358681423301, "percentage": 68.75, "elapsed_time": "1 day, 2:20:26", "remaining_time": "11:58:32", "throughput": 61225.23, "total_tokens": 5805796224} {"current_steps": 17340, "total_steps": 25209, "loss": 0.3186, "lr": 3.023978449609697e-05, "epoch": 2.0635487325955015, "percentage": 68.78, "elapsed_time": "1 day, 2:21:16", "remaining_time": "11:57:35", "throughput": 61228.85, "total_tokens": 5809185792} {"current_steps": 17350, "total_steps": 25209, "loss": 0.3262, "lr": 3.023425549151707e-05, "epoch": 2.064738783767702, "percentage": 68.82, "elapsed_time": "1 day, 2:22:03", "remaining_time": "11:56:37", "throughput": 61233.37, "total_tokens": 5812459776} {"current_steps": 17360, "total_steps": 25209, "loss": 0.319, "lr": 3.022872951857754e-05, "epoch": 2.0659288349399025, "percentage": 68.86, "elapsed_time": "1 day, 2:22:51", "remaining_time": "11:55:39", "throughput": 61237.11, "total_tokens": 5815756800} {"current_steps": 17370, "total_steps": 25209, "loss": 0.316, "lr": 3.0223206574508904e-05, "epoch": 2.0671188861121026, "percentage": 68.9, "elapsed_time": "1 day, 2:23:39", "remaining_time": "11:54:41", "throughput": 61241.92, "total_tokens": 5819195520} {"current_steps": 17380, "total_steps": 25209, "loss": 0.3181, "lr": 3.0217686656545224e-05, "epoch": 2.068308937284303, "percentage": 68.94, "elapsed_time": "1 day, 2:24:30", "remaining_time": "11:53:45", "throughput": 61245.14, "total_tokens": 5822576640} {"current_steps": 17390, "total_steps": 25209, "loss": 0.3192, "lr": 3.0212169761924077e-05, "epoch": 2.0694989884565036, "percentage": 68.98, "elapsed_time": "1 day, 2:25:18", "remaining_time": "11:52:47", "throughput": 61248.7, "total_tokens": 5825897728} {"current_steps": 17400, "total_steps": 25209, "loss": 0.3142, "lr": 3.0206655887886604e-05, "epoch": 2.070689039628704, "percentage": 69.02, "elapsed_time": "1 day, 2:26:04", "remaining_time": "11:51:49", "throughput": 61254.5, "total_tokens": 5829230592} {"current_steps": 17410, "total_steps": 25209, "loss": 0.3233, "lr": 3.0201145031677448e-05, "epoch": 2.0718790908009046, "percentage": 69.06, "elapsed_time": "1 day, 2:26:54", "remaining_time": "11:50:52", "throughput": 61257.91, "total_tokens": 5832617600} {"current_steps": 17420, "total_steps": 25209, "loss": 0.3208, "lr": 3.019563719054477e-05, "epoch": 2.0730691419731047, "percentage": 69.1, "elapsed_time": "1 day, 2:27:45", "remaining_time": "11:49:55", "throughput": 61260.69, "total_tokens": 5836015744} {"current_steps": 17430, "total_steps": 25209, "loss": 0.3195, "lr": 3.019013236174025e-05, "epoch": 2.074259193145305, "percentage": 69.14, "elapsed_time": "1 day, 2:28:31", "remaining_time": "11:48:57", "throughput": 61265.84, "total_tokens": 5839357696} {"current_steps": 17440, "total_steps": 25209, "loss": 0.3188, "lr": 3.018463054251906e-05, "epoch": 2.0754492443175057, "percentage": 69.18, "elapsed_time": "1 day, 2:29:24", "remaining_time": "11:48:02", "throughput": 61269.07, "total_tokens": 5842915968} {"current_steps": 17450, "total_steps": 25209, "loss": 0.3172, "lr": 3.017913173013989e-05, "epoch": 2.076639295489706, "percentage": 69.22, "elapsed_time": "1 day, 2:30:16", "remaining_time": "11:47:06", "throughput": 61272.59, "total_tokens": 5846431232} {"current_steps": 17460, "total_steps": 25209, "loss": 0.314, "lr": 3.017363592186491e-05, "epoch": 2.0778293466619067, "percentage": 69.26, "elapsed_time": "1 day, 2:31:05", "remaining_time": "11:46:08", "throughput": 61276.23, "total_tokens": 5849744896} {"current_steps": 17470, "total_steps": 25209, "loss": 0.3195, "lr": 3.0168143114959797e-05, "epoch": 2.0790193978341067, "percentage": 69.3, "elapsed_time": "1 day, 2:31:51", "remaining_time": "11:45:10", "throughput": 61281.56, "total_tokens": 5853087872} {"current_steps": 17480, "total_steps": 25209, "loss": 0.3203, "lr": 3.016265330669369e-05, "epoch": 2.080209449006307, "percentage": 69.34, "elapsed_time": "1 day, 2:32:37", "remaining_time": "11:44:12", "throughput": 61285.83, "total_tokens": 5856347264} {"current_steps": 17490, "total_steps": 25209, "loss": 0.3207, "lr": 3.0157166494339223e-05, "epoch": 2.0813995001785077, "percentage": 69.38, "elapsed_time": "1 day, 2:33:26", "remaining_time": "11:43:14", "throughput": 61290.28, "total_tokens": 5859739776} {"current_steps": 17500, "total_steps": 25209, "loss": 0.3159, "lr": 3.0151682675172482e-05, "epoch": 2.0825895513507082, "percentage": 69.42, "elapsed_time": "1 day, 2:34:14", "remaining_time": "11:42:17", "throughput": 61294.89, "total_tokens": 5863145344} {"current_steps": 17510, "total_steps": 25209, "loss": 0.3192, "lr": 3.0146201846473034e-05, "epoch": 2.0837796025229083, "percentage": 69.46, "elapsed_time": "1 day, 2:35:02", "remaining_time": "11:41:19", "throughput": 61298.89, "total_tokens": 5866472064} {"current_steps": 17520, "total_steps": 25209, "loss": 0.3197, "lr": 3.01407240055239e-05, "epoch": 2.084969653695109, "percentage": 69.5, "elapsed_time": "1 day, 2:35:51", "remaining_time": "11:40:22", "throughput": 61302.68, "total_tokens": 5869813632} {"current_steps": 17530, "total_steps": 25209, "loss": 0.3186, "lr": 3.013524914961157e-05, "epoch": 2.0861597048673093, "percentage": 69.54, "elapsed_time": "1 day, 2:36:37", "remaining_time": "11:39:23", "throughput": 61307.77, "total_tokens": 5873124224} {"current_steps": 17540, "total_steps": 25209, "loss": 0.3234, "lr": 3.012977727602596e-05, "epoch": 2.08734975603951, "percentage": 69.58, "elapsed_time": "1 day, 2:37:26", "remaining_time": "11:38:26", "throughput": 61311.17, "total_tokens": 5876436096} {"current_steps": 17550, "total_steps": 25209, "loss": 0.3186, "lr": 3.0124308382060446e-05, "epoch": 2.0885398072117103, "percentage": 69.62, "elapsed_time": "1 day, 2:38:13", "remaining_time": "11:37:28", "throughput": 61315.82, "total_tokens": 5879765248} {"current_steps": 17560, "total_steps": 25209, "loss": 0.326, "lr": 3.011884246501183e-05, "epoch": 2.0897298583839103, "percentage": 69.66, "elapsed_time": "1 day, 2:38:59", "remaining_time": "11:36:30", "throughput": 61320.48, "total_tokens": 5883060480} {"current_steps": 17570, "total_steps": 25209, "loss": 0.318, "lr": 3.0113379522180363e-05, "epoch": 2.090919909556111, "percentage": 69.7, "elapsed_time": "1 day, 2:39:48", "remaining_time": "11:35:33", "throughput": 61323.64, "total_tokens": 5886345344} {"current_steps": 17580, "total_steps": 25209, "loss": 0.322, "lr": 3.0107919550869702e-05, "epoch": 2.0921099607283113, "percentage": 69.74, "elapsed_time": "1 day, 2:40:37", "remaining_time": "11:34:36", "throughput": 61327.94, "total_tokens": 5889755392} {"current_steps": 17590, "total_steps": 25209, "loss": 0.3195, "lr": 3.0102462548386933e-05, "epoch": 2.093300011900512, "percentage": 69.78, "elapsed_time": "1 day, 2:41:26", "remaining_time": "11:33:39", "throughput": 61332.2, "total_tokens": 5893193088} {"current_steps": 17600, "total_steps": 25209, "loss": 0.3155, "lr": 3.0097008512042572e-05, "epoch": 2.094490063072712, "percentage": 69.82, "elapsed_time": "1 day, 2:42:16", "remaining_time": "11:32:42", "throughput": 61336.53, "total_tokens": 5896672640} {"current_steps": 17610, "total_steps": 25209, "loss": 0.3143, "lr": 3.009155743915052e-05, "epoch": 2.0956801142449124, "percentage": 69.86, "elapsed_time": "1 day, 2:43:01", "remaining_time": "11:31:43", "throughput": 61342.18, "total_tokens": 5899971840} {"current_steps": 17620, "total_steps": 25209, "loss": 0.3208, "lr": 3.00861093270281e-05, "epoch": 2.096870165417113, "percentage": 69.9, "elapsed_time": "1 day, 2:43:50", "remaining_time": "11:30:46", "throughput": 61345.95, "total_tokens": 5903337728} {"current_steps": 17630, "total_steps": 25209, "loss": 0.3212, "lr": 3.008066417299602e-05, "epoch": 2.0980602165893134, "percentage": 69.94, "elapsed_time": "1 day, 2:44:38", "remaining_time": "11:29:49", "throughput": 61349.81, "total_tokens": 5906696704} {"current_steps": 17640, "total_steps": 25209, "loss": 0.3188, "lr": 3.00752219743784e-05, "epoch": 2.099250267761514, "percentage": 69.98, "elapsed_time": "1 day, 2:45:26", "remaining_time": "11:28:52", "throughput": 61354.0, "total_tokens": 5910030592} {"current_steps": 17650, "total_steps": 25209, "loss": 0.3164, "lr": 3.0069782728502737e-05, "epoch": 2.100440318933714, "percentage": 70.01, "elapsed_time": "1 day, 2:46:18", "remaining_time": "11:27:56", "throughput": 61356.6, "total_tokens": 5913456384} {"current_steps": 17660, "total_steps": 25209, "loss": 0.3205, "lr": 3.00643464326999e-05, "epoch": 2.1016303701059145, "percentage": 70.05, "elapsed_time": "1 day, 2:47:05", "remaining_time": "11:26:58", "throughput": 61361.55, "total_tokens": 5916844672} {"current_steps": 17670, "total_steps": 25209, "loss": 0.3131, "lr": 3.0058913084304146e-05, "epoch": 2.102820421278115, "percentage": 70.09, "elapsed_time": "1 day, 2:47:54", "remaining_time": "11:26:01", "throughput": 61366.64, "total_tokens": 5920316544} {"current_steps": 17680, "total_steps": 25209, "loss": 0.3206, "lr": 3.0053482680653112e-05, "epoch": 2.1040104724503155, "percentage": 70.13, "elapsed_time": "1 day, 2:48:39", "remaining_time": "11:25:02", "throughput": 61372.54, "total_tokens": 5923630592} {"current_steps": 17690, "total_steps": 25209, "loss": 0.3221, "lr": 3.0048055219087777e-05, "epoch": 2.105200523622516, "percentage": 70.17, "elapsed_time": "1 day, 2:49:27", "remaining_time": "11:24:05", "throughput": 61376.5, "total_tokens": 5927004544} {"current_steps": 17700, "total_steps": 25209, "loss": 0.3218, "lr": 3.0042630696952507e-05, "epoch": 2.106390574794716, "percentage": 70.21, "elapsed_time": "1 day, 2:50:16", "remaining_time": "11:23:08", "throughput": 61380.42, "total_tokens": 5930355072} {"current_steps": 17710, "total_steps": 25209, "loss": 0.3223, "lr": 3.0037209111594994e-05, "epoch": 2.1075806259669165, "percentage": 70.25, "elapsed_time": "1 day, 2:51:05", "remaining_time": "11:22:11", "throughput": 61384.92, "total_tokens": 5933802240} {"current_steps": 17720, "total_steps": 25209, "loss": 0.3191, "lr": 3.0031790460366305e-05, "epoch": 2.108770677139117, "percentage": 70.29, "elapsed_time": "1 day, 2:51:52", "remaining_time": "11:21:13", "throughput": 61389.34, "total_tokens": 5937120384} {"current_steps": 17730, "total_steps": 25209, "loss": 0.3213, "lr": 3.002637474062083e-05, "epoch": 2.1099607283113175, "percentage": 70.33, "elapsed_time": "1 day, 2:52:39", "remaining_time": "11:20:15", "throughput": 61393.47, "total_tokens": 5940425600} {"current_steps": 17740, "total_steps": 25209, "loss": 0.319, "lr": 3.0020961949716325e-05, "epoch": 2.1111507794835176, "percentage": 70.37, "elapsed_time": "1 day, 2:53:32", "remaining_time": "11:19:20", "throughput": 61396.06, "total_tokens": 5943887744} {"current_steps": 17750, "total_steps": 25209, "loss": 0.3192, "lr": 3.0015552085013847e-05, "epoch": 2.112340830655718, "percentage": 70.41, "elapsed_time": "1 day, 2:54:19", "remaining_time": "11:18:22", "throughput": 61401.13, "total_tokens": 5947294208} {"current_steps": 17760, "total_steps": 25209, "loss": 0.3216, "lr": 3.0010145143877805e-05, "epoch": 2.1135308818279186, "percentage": 70.45, "elapsed_time": "1 day, 2:55:06", "remaining_time": "11:17:25", "throughput": 61405.65, "total_tokens": 5950606080} {"current_steps": 17770, "total_steps": 25209, "loss": 0.3196, "lr": 3.0004741123675907e-05, "epoch": 2.114720933000119, "percentage": 70.49, "elapsed_time": "1 day, 2:55:55", "remaining_time": "11:16:28", "throughput": 61409.25, "total_tokens": 5953958016} {"current_steps": 17780, "total_steps": 25209, "loss": 0.3212, "lr": 2.9999340021779205e-05, "epoch": 2.1159109841723196, "percentage": 70.53, "elapsed_time": "1 day, 2:56:44", "remaining_time": "11:15:31", "throughput": 61412.6, "total_tokens": 5957303296} {"current_steps": 17790, "total_steps": 25209, "loss": 0.3169, "lr": 2.999394183556204e-05, "epoch": 2.1171010353445197, "percentage": 70.57, "elapsed_time": "1 day, 2:57:31", "remaining_time": "11:14:33", "throughput": 61417.48, "total_tokens": 5960633344} {"current_steps": 17800, "total_steps": 25209, "loss": 0.3233, "lr": 2.998854656240207e-05, "epoch": 2.11829108651672, "percentage": 70.61, "elapsed_time": "1 day, 2:58:20", "remaining_time": "11:13:36", "throughput": 61421.15, "total_tokens": 5964017792} {"current_steps": 17810, "total_steps": 25209, "loss": 0.3223, "lr": 2.9983154199680257e-05, "epoch": 2.1194811376889207, "percentage": 70.65, "elapsed_time": "1 day, 2:59:06", "remaining_time": "11:12:38", "throughput": 61426.06, "total_tokens": 5967309696} {"current_steps": 17820, "total_steps": 25209, "loss": 0.3169, "lr": 2.9977764744780845e-05, "epoch": 2.120671188861121, "percentage": 70.69, "elapsed_time": "1 day, 2:59:52", "remaining_time": "11:11:40", "throughput": 61430.44, "total_tokens": 5970581504} {"current_steps": 17830, "total_steps": 25209, "loss": 0.3182, "lr": 2.9972378195091384e-05, "epoch": 2.121861240033321, "percentage": 70.73, "elapsed_time": "1 day, 3:00:41", "remaining_time": "11:10:43", "throughput": 61434.58, "total_tokens": 5973999104} {"current_steps": 17840, "total_steps": 25209, "loss": 0.3169, "lr": 2.996699454800269e-05, "epoch": 2.1230512912055217, "percentage": 70.77, "elapsed_time": "1 day, 3:01:34", "remaining_time": "11:09:48", "throughput": 61436.68, "total_tokens": 5977436416} {"current_steps": 17850, "total_steps": 25209, "loss": 0.3157, "lr": 2.9961613800908883e-05, "epoch": 2.124241342377722, "percentage": 70.81, "elapsed_time": "1 day, 3:02:22", "remaining_time": "11:08:51", "throughput": 61440.64, "total_tokens": 5980789248} {"current_steps": 17860, "total_steps": 25209, "loss": 0.3172, "lr": 2.995623595120733e-05, "epoch": 2.1254313935499227, "percentage": 70.85, "elapsed_time": "1 day, 3:03:08", "remaining_time": "11:07:53", "throughput": 61446.12, "total_tokens": 5984147840} {"current_steps": 17870, "total_steps": 25209, "loss": 0.3231, "lr": 2.995086099629869e-05, "epoch": 2.126621444722123, "percentage": 70.89, "elapsed_time": "1 day, 3:03:55", "remaining_time": "11:06:55", "throughput": 61450.23, "total_tokens": 5987443584} {"current_steps": 17880, "total_steps": 25209, "loss": 0.3205, "lr": 2.9945488933586867e-05, "epoch": 2.1278114958943233, "percentage": 70.93, "elapsed_time": "1 day, 3:04:44", "remaining_time": "11:05:58", "throughput": 61453.76, "total_tokens": 5990759168} {"current_steps": 17890, "total_steps": 25209, "loss": 0.319, "lr": 2.9940119760479045e-05, "epoch": 2.129001547066524, "percentage": 70.97, "elapsed_time": "1 day, 3:05:31", "remaining_time": "11:05:01", "throughput": 61457.86, "total_tokens": 5994052736} {"current_steps": 17900, "total_steps": 25209, "loss": 0.3197, "lr": 2.9934753474385635e-05, "epoch": 2.1301915982387243, "percentage": 71.01, "elapsed_time": "1 day, 3:06:18", "remaining_time": "11:04:03", "throughput": 61463.07, "total_tokens": 5997447424} {"current_steps": 17910, "total_steps": 25209, "loss": 0.3162, "lr": 2.9929390072720314e-05, "epoch": 2.131381649410925, "percentage": 71.05, "elapsed_time": "1 day, 3:07:06", "remaining_time": "11:03:06", "throughput": 61467.1, "total_tokens": 6000846080} {"current_steps": 17920, "total_steps": 25209, "loss": 0.319, "lr": 2.99240295529e-05, "epoch": 2.1325717005831253, "percentage": 71.09, "elapsed_time": "1 day, 3:07:54", "remaining_time": "11:02:09", "throughput": 61471.14, "total_tokens": 6004171904} {"current_steps": 17930, "total_steps": 25209, "loss": 0.3179, "lr": 2.991867191234484e-05, "epoch": 2.1337617517553253, "percentage": 71.13, "elapsed_time": "1 day, 3:08:41", "remaining_time": "11:01:11", "throughput": 61475.79, "total_tokens": 6007485824} {"current_steps": 17940, "total_steps": 25209, "loss": 0.3184, "lr": 2.991331714847822e-05, "epoch": 2.134951802927526, "percentage": 71.17, "elapsed_time": "1 day, 3:09:30", "remaining_time": "11:00:14", "throughput": 61479.58, "total_tokens": 6010883328} {"current_steps": 17950, "total_steps": 25209, "loss": 0.3189, "lr": 2.990796525872675e-05, "epoch": 2.1361418540997263, "percentage": 71.2, "elapsed_time": "1 day, 3:10:16", "remaining_time": "10:59:17", "throughput": 61484.51, "total_tokens": 6014214016} {"current_steps": 17960, "total_steps": 25209, "loss": 0.3195, "lr": 2.990261624052027e-05, "epoch": 2.137331905271927, "percentage": 71.24, "elapsed_time": "1 day, 3:11:07", "remaining_time": "10:58:21", "throughput": 61487.31, "total_tokens": 6017629184} {"current_steps": 17970, "total_steps": 25209, "loss": 0.3224, "lr": 2.989727009129182e-05, "epoch": 2.138521956444127, "percentage": 71.28, "elapsed_time": "1 day, 3:11:57", "remaining_time": "10:57:24", "throughput": 61490.67, "total_tokens": 6021011456} {"current_steps": 17980, "total_steps": 25209, "loss": 0.3213, "lr": 2.989192680847766e-05, "epoch": 2.1397120076163274, "percentage": 71.32, "elapsed_time": "1 day, 3:12:44", "remaining_time": "10:56:27", "throughput": 61494.89, "total_tokens": 6024328960} {"current_steps": 17990, "total_steps": 25209, "loss": 0.3189, "lr": 2.9886586389517267e-05, "epoch": 2.140902058788528, "percentage": 71.36, "elapsed_time": "1 day, 3:13:33", "remaining_time": "10:55:30", "throughput": 61498.92, "total_tokens": 6027698432} {"current_steps": 18000, "total_steps": 25209, "loss": 0.3202, "lr": 2.98812488318533e-05, "epoch": 2.1420921099607284, "percentage": 71.4, "elapsed_time": "1 day, 3:14:21", "remaining_time": "10:54:33", "throughput": 61502.55, "total_tokens": 6031026688} {"current_steps": 18010, "total_steps": 25209, "loss": 0.32, "lr": 2.987591413293162e-05, "epoch": 2.143282161132929, "percentage": 71.44, "elapsed_time": "1 day, 3:15:07", "remaining_time": "10:53:35", "throughput": 61507.0, "total_tokens": 6034272768} {"current_steps": 18020, "total_steps": 25209, "loss": 0.3188, "lr": 2.98705822902013e-05, "epoch": 2.144472212305129, "percentage": 71.48, "elapsed_time": "1 day, 3:15:54", "remaining_time": "10:52:38", "throughput": 61511.25, "total_tokens": 6037620480} {"current_steps": 18030, "total_steps": 25209, "loss": 0.3189, "lr": 2.9865253301114553e-05, "epoch": 2.1456622634773295, "percentage": 71.52, "elapsed_time": "1 day, 3:16:45", "remaining_time": "10:51:42", "throughput": 61514.85, "total_tokens": 6041073536} {"current_steps": 18040, "total_steps": 25209, "loss": 0.3187, "lr": 2.985992716312683e-05, "epoch": 2.14685231464953, "percentage": 71.56, "elapsed_time": "1 day, 3:17:30", "remaining_time": "10:50:44", "throughput": 61519.69, "total_tokens": 6044329856} {"current_steps": 18050, "total_steps": 25209, "loss": 0.3197, "lr": 2.9854603873696703e-05, "epoch": 2.1480423658217305, "percentage": 71.6, "elapsed_time": "1 day, 3:18:18", "remaining_time": "10:49:47", "throughput": 61524.44, "total_tokens": 6047738368} {"current_steps": 18060, "total_steps": 25209, "loss": 0.3201, "lr": 2.9849283430285947e-05, "epoch": 2.1492324169939305, "percentage": 71.64, "elapsed_time": "1 day, 3:19:05", "remaining_time": "10:48:49", "throughput": 61528.59, "total_tokens": 6051087488} {"current_steps": 18070, "total_steps": 25209, "loss": 0.3216, "lr": 2.98439658303595e-05, "epoch": 2.150422468166131, "percentage": 71.68, "elapsed_time": "1 day, 3:19:54", "remaining_time": "10:47:53", "throughput": 61532.35, "total_tokens": 6054452736} {"current_steps": 18080, "total_steps": 25209, "loss": 0.3215, "lr": 2.9838651071385442e-05, "epoch": 2.1516125193383315, "percentage": 71.72, "elapsed_time": "1 day, 3:20:38", "remaining_time": "10:46:54", "throughput": 61537.12, "total_tokens": 6057640576} {"current_steps": 18090, "total_steps": 25209, "loss": 0.3185, "lr": 2.9833339150835037e-05, "epoch": 2.152802570510532, "percentage": 71.76, "elapsed_time": "1 day, 3:21:28", "remaining_time": "10:45:58", "throughput": 61540.04, "total_tokens": 6060980352} {"current_steps": 18100, "total_steps": 25209, "loss": 0.32, "lr": 2.982803006618267e-05, "epoch": 2.1539926216827325, "percentage": 71.8, "elapsed_time": "1 day, 3:22:15", "remaining_time": "10:45:01", "throughput": 61543.99, "total_tokens": 6064295040} {"current_steps": 18110, "total_steps": 25209, "loss": 0.3207, "lr": 2.982272381490588e-05, "epoch": 2.1551826728549326, "percentage": 71.84, "elapsed_time": "1 day, 3:23:06", "remaining_time": "10:44:05", "throughput": 61547.23, "total_tokens": 6067744896} {"current_steps": 18120, "total_steps": 25209, "loss": 0.3208, "lr": 2.9817420394485363e-05, "epoch": 2.156372724027133, "percentage": 71.88, "elapsed_time": "1 day, 3:23:59", "remaining_time": "10:43:10", "throughput": 61549.44, "total_tokens": 6071201792} {"current_steps": 18130, "total_steps": 25209, "loss": 0.3241, "lr": 2.9812119802404927e-05, "epoch": 2.1575627751993336, "percentage": 71.92, "elapsed_time": "1 day, 3:24:46", "remaining_time": "10:42:12", "throughput": 61553.82, "total_tokens": 6074518272} {"current_steps": 18140, "total_steps": 25209, "loss": 0.3201, "lr": 2.9806822036151523e-05, "epoch": 2.158752826371534, "percentage": 71.96, "elapsed_time": "1 day, 3:25:36", "remaining_time": "10:41:16", "throughput": 61556.64, "total_tokens": 6077878912} {"current_steps": 18150, "total_steps": 25209, "loss": 0.3184, "lr": 2.980152709321522e-05, "epoch": 2.1599428775437346, "percentage": 72.0, "elapsed_time": "1 day, 3:26:24", "remaining_time": "10:40:19", "throughput": 61560.39, "total_tokens": 6081221632} {"current_steps": 18160, "total_steps": 25209, "loss": 0.3155, "lr": 2.9796234971089214e-05, "epoch": 2.1611329287159347, "percentage": 72.04, "elapsed_time": "1 day, 3:27:10", "remaining_time": "10:39:22", "throughput": 61565.29, "total_tokens": 6084540288} {"current_steps": 18170, "total_steps": 25209, "loss": 0.3176, "lr": 2.979094566726981e-05, "epoch": 2.162322979888135, "percentage": 72.08, "elapsed_time": "1 day, 3:27:59", "remaining_time": "10:38:25", "throughput": 61568.34, "total_tokens": 6087861632} {"current_steps": 18180, "total_steps": 25209, "loss": 0.3197, "lr": 2.9785659179256427e-05, "epoch": 2.1635130310603357, "percentage": 72.12, "elapsed_time": "1 day, 3:28:45", "remaining_time": "10:37:27", "throughput": 61572.87, "total_tokens": 6091106304} {"current_steps": 18190, "total_steps": 25209, "loss": 0.3228, "lr": 2.978037550455159e-05, "epoch": 2.164703082232536, "percentage": 72.16, "elapsed_time": "1 day, 3:29:30", "remaining_time": "10:36:30", "throughput": 61578.36, "total_tokens": 6094470528} {"current_steps": 18200, "total_steps": 25209, "loss": 0.3173, "lr": 2.977509464066091e-05, "epoch": 2.165893133404736, "percentage": 72.2, "elapsed_time": "1 day, 3:30:18", "remaining_time": "10:35:33", "throughput": 61581.81, "total_tokens": 6097755520} {"current_steps": 18210, "total_steps": 25209, "loss": 0.3186, "lr": 2.9769816585093126e-05, "epoch": 2.1670831845769367, "percentage": 72.24, "elapsed_time": "1 day, 3:31:06", "remaining_time": "10:34:36", "throughput": 61585.57, "total_tokens": 6101090176} {"current_steps": 18220, "total_steps": 25209, "loss": 0.3189, "lr": 2.9764541335360024e-05, "epoch": 2.168273235749137, "percentage": 72.28, "elapsed_time": "1 day, 3:31:54", "remaining_time": "10:33:39", "throughput": 61589.93, "total_tokens": 6104442752} {"current_steps": 18230, "total_steps": 25209, "loss": 0.3216, "lr": 2.9759268888976505e-05, "epoch": 2.1694632869213377, "percentage": 72.32, "elapsed_time": "1 day, 3:32:43", "remaining_time": "10:32:42", "throughput": 61594.06, "total_tokens": 6107862272} {"current_steps": 18240, "total_steps": 25209, "loss": 0.3176, "lr": 2.9753999243460546e-05, "epoch": 2.170653338093538, "percentage": 72.36, "elapsed_time": "1 day, 3:33:31", "remaining_time": "10:31:45", "throughput": 61598.68, "total_tokens": 6111278592} {"current_steps": 18250, "total_steps": 25209, "loss": 0.3206, "lr": 2.974873239633319e-05, "epoch": 2.1718433892657383, "percentage": 72.39, "elapsed_time": "1 day, 3:34:22", "remaining_time": "10:30:50", "throughput": 61601.17, "total_tokens": 6114680832} {"current_steps": 18260, "total_steps": 25209, "loss": 0.3206, "lr": 2.9743468345118563e-05, "epoch": 2.173033440437939, "percentage": 72.43, "elapsed_time": "1 day, 3:35:09", "remaining_time": "10:29:52", "throughput": 61605.66, "total_tokens": 6118012800} {"current_steps": 18270, "total_steps": 25209, "loss": 0.3207, "lr": 2.9738207087343844e-05, "epoch": 2.1742234916101393, "percentage": 72.47, "elapsed_time": "1 day, 3:35:56", "remaining_time": "10:28:56", "throughput": 61609.71, "total_tokens": 6121353344} {"current_steps": 18280, "total_steps": 25209, "loss": 0.32, "lr": 2.9732948620539287e-05, "epoch": 2.17541354278234, "percentage": 72.51, "elapsed_time": "1 day, 3:36:44", "remaining_time": "10:27:58", "throughput": 61613.77, "total_tokens": 6124669056} {"current_steps": 18290, "total_steps": 25209, "loss": 0.317, "lr": 2.9727692942238188e-05, "epoch": 2.17660359395454, "percentage": 72.55, "elapsed_time": "1 day, 3:37:35", "remaining_time": "10:27:03", "throughput": 61616.63, "total_tokens": 6128105728} {"current_steps": 18300, "total_steps": 25209, "loss": 0.3198, "lr": 2.97224400499769e-05, "epoch": 2.1777936451267403, "percentage": 72.59, "elapsed_time": "1 day, 3:38:19", "remaining_time": "10:26:05", "throughput": 61621.54, "total_tokens": 6131295872} {"current_steps": 18310, "total_steps": 25209, "loss": 0.3182, "lr": 2.9717189941294826e-05, "epoch": 2.178983696298941, "percentage": 72.63, "elapsed_time": "1 day, 3:39:04", "remaining_time": "10:25:07", "throughput": 61626.22, "total_tokens": 6134554368} {"current_steps": 18320, "total_steps": 25209, "loss": 0.3161, "lr": 2.97119426137344e-05, "epoch": 2.1801737474711413, "percentage": 72.67, "elapsed_time": "1 day, 3:39:50", "remaining_time": "10:24:09", "throughput": 61631.53, "total_tokens": 6137900544} {"current_steps": 18330, "total_steps": 25209, "loss": 0.3225, "lr": 2.9706698064841103e-05, "epoch": 2.181363798643342, "percentage": 72.71, "elapsed_time": "1 day, 3:40:36", "remaining_time": "10:23:12", "throughput": 61636.39, "total_tokens": 6141221504} {"current_steps": 18340, "total_steps": 25209, "loss": 0.3196, "lr": 2.970145629216345e-05, "epoch": 2.182553849815542, "percentage": 72.75, "elapsed_time": "1 day, 3:41:25", "remaining_time": "10:22:15", "throughput": 61639.53, "total_tokens": 6144575744} {"current_steps": 18350, "total_steps": 25209, "loss": 0.3198, "lr": 2.969621729325296e-05, "epoch": 2.1837439009877424, "percentage": 72.79, "elapsed_time": "1 day, 3:42:13", "remaining_time": "10:21:19", "throughput": 61643.21, "total_tokens": 6147904896} {"current_steps": 18360, "total_steps": 25209, "loss": 0.3153, "lr": 2.969098106566421e-05, "epoch": 2.184933952159943, "percentage": 72.83, "elapsed_time": "1 day, 3:43:01", "remaining_time": "10:20:22", "throughput": 61647.63, "total_tokens": 6151308928} {"current_steps": 18370, "total_steps": 25209, "loss": 0.3197, "lr": 2.968574760695476e-05, "epoch": 2.1861240033321434, "percentage": 72.87, "elapsed_time": "1 day, 3:43:47", "remaining_time": "10:19:25", "throughput": 61651.79, "total_tokens": 6154562560} {"current_steps": 18380, "total_steps": 25209, "loss": 0.321, "lr": 2.9680516914685206e-05, "epoch": 2.187314054504344, "percentage": 72.91, "elapsed_time": "1 day, 3:44:35", "remaining_time": "10:18:28", "throughput": 61655.72, "total_tokens": 6157872896} {"current_steps": 18390, "total_steps": 25209, "loss": 0.3215, "lr": 2.9675288986419148e-05, "epoch": 2.188504105676544, "percentage": 72.95, "elapsed_time": "1 day, 3:45:22", "remaining_time": "10:17:31", "throughput": 61659.75, "total_tokens": 6161189888} {"current_steps": 18400, "total_steps": 25209, "loss": 0.3197, "lr": 2.967006381972317e-05, "epoch": 2.1896941568487445, "percentage": 72.99, "elapsed_time": "1 day, 3:46:09", "remaining_time": "10:16:34", "throughput": 61664.2, "total_tokens": 6164567680} {"current_steps": 18410, "total_steps": 25209, "loss": 0.3236, "lr": 2.9664841412166882e-05, "epoch": 2.190884208020945, "percentage": 73.03, "elapsed_time": "1 day, 3:46:59", "remaining_time": "10:15:38", "throughput": 61667.63, "total_tokens": 6167952000} {"current_steps": 18420, "total_steps": 25209, "loss": 0.3189, "lr": 2.965962176132287e-05, "epoch": 2.1920742591931455, "percentage": 73.07, "elapsed_time": "1 day, 3:47:48", "remaining_time": "10:14:42", "throughput": 61670.88, "total_tokens": 6171336704} {"current_steps": 18430, "total_steps": 25209, "loss": 0.3236, "lr": 2.9654404864766706e-05, "epoch": 2.1932643103653455, "percentage": 73.11, "elapsed_time": "1 day, 3:48:34", "remaining_time": "10:13:44", "throughput": 61675.36, "total_tokens": 6174625792} {"current_steps": 18440, "total_steps": 25209, "loss": 0.3208, "lr": 2.9649190720076962e-05, "epoch": 2.194454361537546, "percentage": 73.15, "elapsed_time": "1 day, 3:49:23", "remaining_time": "10:12:48", "throughput": 61679.05, "total_tokens": 6178015872} {"current_steps": 18450, "total_steps": 25209, "loss": 0.3168, "lr": 2.9643979324835176e-05, "epoch": 2.1956444127097465, "percentage": 73.19, "elapsed_time": "1 day, 3:50:13", "remaining_time": "10:11:52", "throughput": 61682.16, "total_tokens": 6181404544} {"current_steps": 18460, "total_steps": 25209, "loss": 0.3205, "lr": 2.9638770676625866e-05, "epoch": 2.196834463881947, "percentage": 73.23, "elapsed_time": "1 day, 3:51:00", "remaining_time": "10:10:55", "throughput": 61686.64, "total_tokens": 6184707072} {"current_steps": 18470, "total_steps": 25209, "loss": 0.3174, "lr": 2.9633564773036517e-05, "epoch": 2.1980245150541475, "percentage": 73.27, "elapsed_time": "1 day, 3:51:49", "remaining_time": "10:09:59", "throughput": 61689.9, "total_tokens": 6188068480} {"current_steps": 18480, "total_steps": 25209, "loss": 0.3225, "lr": 2.9628361611657578e-05, "epoch": 2.1992145662263476, "percentage": 73.31, "elapsed_time": "1 day, 3:52:33", "remaining_time": "10:09:01", "throughput": 61695.17, "total_tokens": 6191318144} {"current_steps": 18490, "total_steps": 25209, "loss": 0.3227, "lr": 2.9623161190082472e-05, "epoch": 2.200404617398548, "percentage": 73.35, "elapsed_time": "1 day, 3:53:20", "remaining_time": "10:08:04", "throughput": 61699.67, "total_tokens": 6194697728} {"current_steps": 18500, "total_steps": 25209, "loss": 0.3169, "lr": 2.9617963505907554e-05, "epoch": 2.2015946685707486, "percentage": 73.39, "elapsed_time": "1 day, 3:54:06", "remaining_time": "10:07:06", "throughput": 61704.36, "total_tokens": 6197973376} {"current_steps": 18510, "total_steps": 25209, "loss": 0.321, "lr": 2.9612768556732145e-05, "epoch": 2.202784719742949, "percentage": 73.43, "elapsed_time": "1 day, 3:54:52", "remaining_time": "10:06:09", "throughput": 61709.18, "total_tokens": 6201308288} {"current_steps": 18520, "total_steps": 25209, "loss": 0.3211, "lr": 2.960757634015852e-05, "epoch": 2.203974770915149, "percentage": 73.47, "elapsed_time": "1 day, 3:55:40", "remaining_time": "10:05:12", "throughput": 61713.28, "total_tokens": 6204676480} {"current_steps": 18530, "total_steps": 25209, "loss": 0.3173, "lr": 2.9602386853791885e-05, "epoch": 2.2051648220873497, "percentage": 73.51, "elapsed_time": "1 day, 3:56:28", "remaining_time": "10:04:16", "throughput": 61716.48, "total_tokens": 6207977984} {"current_steps": 18540, "total_steps": 25209, "loss": 0.3165, "lr": 2.959720009524038e-05, "epoch": 2.20635487325955, "percentage": 73.55, "elapsed_time": "1 day, 3:57:17", "remaining_time": "10:03:20", "throughput": 61720.17, "total_tokens": 6211355520} {"current_steps": 18550, "total_steps": 25209, "loss": 0.3236, "lr": 2.9592016062115085e-05, "epoch": 2.2075449244317507, "percentage": 73.58, "elapsed_time": "1 day, 3:58:02", "remaining_time": "10:02:22", "throughput": 61724.87, "total_tokens": 6214644096} {"current_steps": 18560, "total_steps": 25209, "loss": 0.3201, "lr": 2.9586834752030002e-05, "epoch": 2.208734975603951, "percentage": 73.62, "elapsed_time": "1 day, 3:58:52", "remaining_time": "10:01:26", "throughput": 61728.06, "total_tokens": 6217999616} {"current_steps": 18570, "total_steps": 25209, "loss": 0.3196, "lr": 2.958165616260206e-05, "epoch": 2.209925026776151, "percentage": 73.66, "elapsed_time": "1 day, 3:59:39", "remaining_time": "10:00:30", "throughput": 61732.55, "total_tokens": 6221399808} {"current_steps": 18580, "total_steps": 25209, "loss": 0.3198, "lr": 2.9576480291451114e-05, "epoch": 2.2111150779483517, "percentage": 73.7, "elapsed_time": "1 day, 4:00:27", "remaining_time": "9:59:33", "throughput": 61737.35, "total_tokens": 6224850816} {"current_steps": 18590, "total_steps": 25209, "loss": 0.3176, "lr": 2.957130713619991e-05, "epoch": 2.212305129120552, "percentage": 73.74, "elapsed_time": "1 day, 4:01:16", "remaining_time": "9:58:37", "throughput": 61741.04, "total_tokens": 6228201216} {"current_steps": 18600, "total_steps": 25209, "loss": 0.3194, "lr": 2.9566136694474138e-05, "epoch": 2.2134951802927527, "percentage": 73.78, "elapsed_time": "1 day, 4:02:02", "remaining_time": "9:57:40", "throughput": 61745.19, "total_tokens": 6231501952} {"current_steps": 18610, "total_steps": 25209, "loss": 0.3207, "lr": 2.9560968963902365e-05, "epoch": 2.214685231464953, "percentage": 73.82, "elapsed_time": "1 day, 4:02:49", "remaining_time": "9:56:43", "throughput": 61750.17, "total_tokens": 6234904192} {"current_steps": 18620, "total_steps": 25209, "loss": 0.3198, "lr": 2.9555803942116062e-05, "epoch": 2.2158752826371533, "percentage": 73.86, "elapsed_time": "1 day, 4:03:36", "remaining_time": "9:55:46", "throughput": 61754.74, "total_tokens": 6238276352} {"current_steps": 18630, "total_steps": 25209, "loss": 0.3175, "lr": 2.955064162674961e-05, "epoch": 2.2170653338093538, "percentage": 73.9, "elapsed_time": "1 day, 4:04:23", "remaining_time": "9:54:49", "throughput": 61758.7, "total_tokens": 6241564288} {"current_steps": 18640, "total_steps": 25209, "loss": 0.3211, "lr": 2.9545482015440266e-05, "epoch": 2.2182553849815543, "percentage": 73.94, "elapsed_time": "1 day, 4:05:12", "remaining_time": "9:53:53", "throughput": 61761.93, "total_tokens": 6244905088} {"current_steps": 18650, "total_steps": 25209, "loss": 0.3205, "lr": 2.954032510582819e-05, "epoch": 2.219445436153755, "percentage": 73.98, "elapsed_time": "1 day, 4:05:57", "remaining_time": "9:52:56", "throughput": 61766.43, "total_tokens": 6248164864} {"current_steps": 18660, "total_steps": 25209, "loss": 0.321, "lr": 2.95351708955564e-05, "epoch": 2.220635487325955, "percentage": 74.02, "elapsed_time": "1 day, 4:06:47", "remaining_time": "9:52:00", "throughput": 61769.21, "total_tokens": 6251516160} {"current_steps": 18670, "total_steps": 25209, "loss": 0.3223, "lr": 2.9530019382270823e-05, "epoch": 2.2218255384981553, "percentage": 74.06, "elapsed_time": "1 day, 4:07:34", "remaining_time": "9:51:03", "throughput": 61772.93, "total_tokens": 6254817408} {"current_steps": 18680, "total_steps": 25209, "loss": 0.3242, "lr": 2.9524870563620233e-05, "epoch": 2.223015589670356, "percentage": 74.1, "elapsed_time": "1 day, 4:08:25", "remaining_time": "9:50:07", "throughput": 61776.25, "total_tokens": 6258243328} {"current_steps": 18690, "total_steps": 25209, "loss": 0.3231, "lr": 2.9519724437256287e-05, "epoch": 2.2242056408425563, "percentage": 74.14, "elapsed_time": "1 day, 4:09:15", "remaining_time": "9:49:12", "throughput": 61778.97, "total_tokens": 6261621248} {"current_steps": 18700, "total_steps": 25209, "loss": 0.3227, "lr": 2.9514581000833496e-05, "epoch": 2.2253956920147564, "percentage": 74.18, "elapsed_time": "1 day, 4:10:02", "remaining_time": "9:48:15", "throughput": 61782.75, "total_tokens": 6264898432} {"current_steps": 18710, "total_steps": 25209, "loss": 0.3218, "lr": 2.950944025200924e-05, "epoch": 2.226585743186957, "percentage": 74.22, "elapsed_time": "1 day, 4:10:48", "remaining_time": "9:47:18", "throughput": 61786.79, "total_tokens": 6268200448} {"current_steps": 18720, "total_steps": 25209, "loss": 0.315, "lr": 2.950430218844375e-05, "epoch": 2.2277757943591574, "percentage": 74.26, "elapsed_time": "1 day, 4:11:36", "remaining_time": "9:46:22", "throughput": 61790.91, "total_tokens": 6271531136} {"current_steps": 18730, "total_steps": 25209, "loss": 0.319, "lr": 2.9499166807800106e-05, "epoch": 2.228965845531358, "percentage": 74.3, "elapsed_time": "1 day, 4:12:24", "remaining_time": "9:45:25", "throughput": 61795.52, "total_tokens": 6274968448} {"current_steps": 18740, "total_steps": 25209, "loss": 0.3178, "lr": 2.949403410774424e-05, "epoch": 2.2301558967035584, "percentage": 74.34, "elapsed_time": "1 day, 4:13:11", "remaining_time": "9:44:29", "throughput": 61799.29, "total_tokens": 6278302464} {"current_steps": 18750, "total_steps": 25209, "loss": 0.3205, "lr": 2.948890408594492e-05, "epoch": 2.2313459478757585, "percentage": 74.38, "elapsed_time": "1 day, 4:13:57", "remaining_time": "9:43:31", "throughput": 61803.76, "total_tokens": 6281556864} {"current_steps": 18760, "total_steps": 25209, "loss": 0.3176, "lr": 2.9483776740073748e-05, "epoch": 2.232535999047959, "percentage": 74.42, "elapsed_time": "1 day, 4:14:47", "remaining_time": "9:42:36", "throughput": 61807.27, "total_tokens": 6285005184} {"current_steps": 18770, "total_steps": 25209, "loss": 0.3201, "lr": 2.947865206780518e-05, "epoch": 2.2337260502201595, "percentage": 74.46, "elapsed_time": "1 day, 4:15:35", "remaining_time": "9:41:39", "throughput": 61811.33, "total_tokens": 6288376832} {"current_steps": 18780, "total_steps": 25209, "loss": 0.3204, "lr": 2.947353006681647e-05, "epoch": 2.23491610139236, "percentage": 74.5, "elapsed_time": "1 day, 4:16:19", "remaining_time": "9:40:42", "throughput": 61816.34, "total_tokens": 6291638144} {"current_steps": 18790, "total_steps": 25209, "loss": 0.3209, "lr": 2.9468410734787717e-05, "epoch": 2.2361061525645605, "percentage": 74.54, "elapsed_time": "1 day, 4:17:05", "remaining_time": "9:39:45", "throughput": 61820.92, "total_tokens": 6294965376} {"current_steps": 18800, "total_steps": 25209, "loss": 0.323, "lr": 2.9463294069401838e-05, "epoch": 2.2372962037367605, "percentage": 74.58, "elapsed_time": "1 day, 4:17:53", "remaining_time": "9:38:49", "throughput": 61825.09, "total_tokens": 6298344576} {"current_steps": 18810, "total_steps": 25209, "loss": 0.322, "lr": 2.9458180068344555e-05, "epoch": 2.238486254908961, "percentage": 74.62, "elapsed_time": "1 day, 4:18:42", "remaining_time": "9:37:53", "throughput": 61828.89, "total_tokens": 6301731968} {"current_steps": 18820, "total_steps": 25209, "loss": 0.3193, "lr": 2.9453068729304407e-05, "epoch": 2.2396763060811615, "percentage": 74.66, "elapsed_time": "1 day, 4:19:32", "remaining_time": "9:36:57", "throughput": 61832.14, "total_tokens": 6305155968} {"current_steps": 18830, "total_steps": 25209, "loss": 0.3197, "lr": 2.944796004997274e-05, "epoch": 2.240866357253362, "percentage": 74.7, "elapsed_time": "1 day, 4:20:20", "remaining_time": "9:36:01", "throughput": 61835.05, "total_tokens": 6308459904} {"current_steps": 18840, "total_steps": 25209, "loss": 0.3179, "lr": 2.94428540280437e-05, "epoch": 2.2420564084255625, "percentage": 74.74, "elapsed_time": "1 day, 4:21:05", "remaining_time": "9:35:03", "throughput": 61839.93, "total_tokens": 6311716992} {"current_steps": 18850, "total_steps": 25209, "loss": 0.3186, "lr": 2.9437750661214242e-05, "epoch": 2.2432464595977626, "percentage": 74.77, "elapsed_time": "1 day, 4:21:52", "remaining_time": "9:34:07", "throughput": 61844.39, "total_tokens": 6315078016} {"current_steps": 18860, "total_steps": 25209, "loss": 0.3203, "lr": 2.9432649947184094e-05, "epoch": 2.244436510769963, "percentage": 74.81, "elapsed_time": "1 day, 4:22:40", "remaining_time": "9:33:11", "throughput": 61848.01, "total_tokens": 6318437888} {"current_steps": 18870, "total_steps": 25209, "loss": 0.3199, "lr": 2.942755188365579e-05, "epoch": 2.2456265619421636, "percentage": 74.85, "elapsed_time": "1 day, 4:23:28", "remaining_time": "9:32:14", "throughput": 61852.0, "total_tokens": 6321813248} {"current_steps": 18880, "total_steps": 25209, "loss": 0.3166, "lr": 2.9422456468334635e-05, "epoch": 2.246816613114364, "percentage": 74.89, "elapsed_time": "1 day, 4:24:19", "remaining_time": "9:31:19", "throughput": 61854.76, "total_tokens": 6325209728} {"current_steps": 18890, "total_steps": 25209, "loss": 0.3198, "lr": 2.9417363698928734e-05, "epoch": 2.248006664286564, "percentage": 74.93, "elapsed_time": "1 day, 4:25:03", "remaining_time": "9:30:22", "throughput": 61859.75, "total_tokens": 6328492800} {"current_steps": 18900, "total_steps": 25209, "loss": 0.32, "lr": 2.9412273573148946e-05, "epoch": 2.2491967154587647, "percentage": 74.97, "elapsed_time": "1 day, 4:25:55", "remaining_time": "9:29:27", "throughput": 61862.08, "total_tokens": 6331906304} {"current_steps": 18910, "total_steps": 25209, "loss": 0.3232, "lr": 2.940718608870891e-05, "epoch": 2.250386766630965, "percentage": 75.01, "elapsed_time": "1 day, 4:26:41", "remaining_time": "9:28:30", "throughput": 61866.6, "total_tokens": 6335232256} {"current_steps": 18920, "total_steps": 25209, "loss": 0.3195, "lr": 2.940210124332504e-05, "epoch": 2.2515768178031657, "percentage": 75.05, "elapsed_time": "1 day, 4:27:27", "remaining_time": "9:27:33", "throughput": 61871.35, "total_tokens": 6338550400} {"current_steps": 18930, "total_steps": 25209, "loss": 0.3214, "lr": 2.9397019034716504e-05, "epoch": 2.2527668689753657, "percentage": 75.09, "elapsed_time": "1 day, 4:28:17", "remaining_time": "9:26:38", "throughput": 61873.74, "total_tokens": 6341914368} {"current_steps": 18940, "total_steps": 25209, "loss": 0.3186, "lr": 2.9391939460605233e-05, "epoch": 2.253956920147566, "percentage": 75.13, "elapsed_time": "1 day, 4:29:07", "remaining_time": "9:25:42", "throughput": 61876.87, "total_tokens": 6345290880} {"current_steps": 18950, "total_steps": 25209, "loss": 0.324, "lr": 2.9386862518715914e-05, "epoch": 2.2551469713197667, "percentage": 75.17, "elapsed_time": "1 day, 4:29:55", "remaining_time": "9:24:46", "throughput": 61879.93, "total_tokens": 6348593536} {"current_steps": 18960, "total_steps": 25209, "loss": 0.319, "lr": 2.9381788206775966e-05, "epoch": 2.256337022491967, "percentage": 75.21, "elapsed_time": "1 day, 4:30:41", "remaining_time": "9:23:49", "throughput": 61884.39, "total_tokens": 6351904640} {"current_steps": 18970, "total_steps": 25209, "loss": 0.3215, "lr": 2.937671652251559e-05, "epoch": 2.2575270736641677, "percentage": 75.25, "elapsed_time": "1 day, 4:31:33", "remaining_time": "9:22:54", "throughput": 61886.73, "total_tokens": 6355348608} {"current_steps": 18980, "total_steps": 25209, "loss": 0.3248, "lr": 2.9371647463667696e-05, "epoch": 2.2587171248363678, "percentage": 75.29, "elapsed_time": "1 day, 4:32:20", "remaining_time": "9:21:58", "throughput": 61890.82, "total_tokens": 6358693760} {"current_steps": 18990, "total_steps": 25209, "loss": 0.3217, "lr": 2.9366581027967943e-05, "epoch": 2.2599071760085683, "percentage": 75.33, "elapsed_time": "1 day, 4:33:09", "remaining_time": "9:21:02", "throughput": 61894.48, "total_tokens": 6362075264} {"current_steps": 19000, "total_steps": 25209, "loss": 0.3194, "lr": 2.9361517213154726e-05, "epoch": 2.2610972271807688, "percentage": 75.37, "elapsed_time": "1 day, 4:33:55", "remaining_time": "9:20:05", "throughput": 61899.58, "total_tokens": 6365452672} {"current_steps": 19010, "total_steps": 25209, "loss": 0.3241, "lr": 2.935645601696917e-05, "epoch": 2.2622872783529693, "percentage": 75.41, "elapsed_time": "1 day, 4:34:43", "remaining_time": "9:19:09", "throughput": 61903.24, "total_tokens": 6368825088} {"current_steps": 19020, "total_steps": 25209, "loss": 0.3165, "lr": 2.9351397437155114e-05, "epoch": 2.26347732952517, "percentage": 75.45, "elapsed_time": "1 day, 4:35:28", "remaining_time": "9:18:12", "throughput": 61907.76, "total_tokens": 6372079744} {"current_steps": 19030, "total_steps": 25209, "loss": 0.324, "lr": 2.934634147145913e-05, "epoch": 2.26466738069737, "percentage": 75.49, "elapsed_time": "1 day, 4:36:15", "remaining_time": "9:17:15", "throughput": 61911.8, "total_tokens": 6375374080} {"current_steps": 19040, "total_steps": 25209, "loss": 0.3206, "lr": 2.9341288117630495e-05, "epoch": 2.2658574318695703, "percentage": 75.53, "elapsed_time": "1 day, 4:37:05", "remaining_time": "9:16:20", "throughput": 61914.64, "total_tokens": 6378798976} {"current_steps": 19050, "total_steps": 25209, "loss": 0.3184, "lr": 2.933623737342121e-05, "epoch": 2.267047483041771, "percentage": 75.57, "elapsed_time": "1 day, 4:37:54", "remaining_time": "9:15:24", "throughput": 61918.17, "total_tokens": 6382156928} {"current_steps": 19060, "total_steps": 25209, "loss": 0.3195, "lr": 2.9331189236585977e-05, "epoch": 2.2682375342139713, "percentage": 75.61, "elapsed_time": "1 day, 4:38:44", "remaining_time": "9:14:29", "throughput": 61921.66, "total_tokens": 6385619200} {"current_steps": 19070, "total_steps": 25209, "loss": 0.3193, "lr": 2.9326143704882192e-05, "epoch": 2.269427585386172, "percentage": 75.65, "elapsed_time": "1 day, 4:39:33", "remaining_time": "9:13:33", "throughput": 61924.37, "total_tokens": 6388930432} {"current_steps": 19080, "total_steps": 25209, "loss": 0.3199, "lr": 2.932110077606997e-05, "epoch": 2.270617636558372, "percentage": 75.69, "elapsed_time": "1 day, 4:40:23", "remaining_time": "9:12:38", "throughput": 61927.39, "total_tokens": 6392365952} {"current_steps": 19090, "total_steps": 25209, "loss": 0.3186, "lr": 2.931606044791212e-05, "epoch": 2.2718076877305724, "percentage": 75.73, "elapsed_time": "1 day, 4:41:12", "remaining_time": "9:11:42", "throughput": 61930.76, "total_tokens": 6395735808} {"current_steps": 19100, "total_steps": 25209, "loss": 0.3195, "lr": 2.9311022718174114e-05, "epoch": 2.272997738902773, "percentage": 75.77, "elapsed_time": "1 day, 4:41:57", "remaining_time": "9:10:45", "throughput": 61935.03, "total_tokens": 6399001728} {"current_steps": 19110, "total_steps": 25209, "loss": 0.3234, "lr": 2.930598758462415e-05, "epoch": 2.2741877900749734, "percentage": 75.81, "elapsed_time": "1 day, 4:42:44", "remaining_time": "9:09:48", "throughput": 61939.29, "total_tokens": 6402308352} {"current_steps": 19120, "total_steps": 25209, "loss": 0.318, "lr": 2.9300955045033072e-05, "epoch": 2.2753778412471735, "percentage": 75.85, "elapsed_time": "1 day, 4:43:30", "remaining_time": "9:08:52", "throughput": 61943.82, "total_tokens": 6405638400} {"current_steps": 19130, "total_steps": 25209, "loss": 0.3244, "lr": 2.9295925097174435e-05, "epoch": 2.276567892419374, "percentage": 75.89, "elapsed_time": "1 day, 4:44:19", "remaining_time": "9:07:56", "throughput": 61947.44, "total_tokens": 6409062272} {"current_steps": 19140, "total_steps": 25209, "loss": 0.3234, "lr": 2.929089773882445e-05, "epoch": 2.2777579435915745, "percentage": 75.93, "elapsed_time": "1 day, 4:45:07", "remaining_time": "9:07:00", "throughput": 61950.68, "total_tokens": 6412386432} {"current_steps": 19150, "total_steps": 25209, "loss": 0.324, "lr": 2.9285872967762007e-05, "epoch": 2.278947994763775, "percentage": 75.96, "elapsed_time": "1 day, 4:45:54", "remaining_time": "9:06:04", "throughput": 61954.97, "total_tokens": 6415732992} {"current_steps": 19160, "total_steps": 25209, "loss": 0.3219, "lr": 2.9280850781768638e-05, "epoch": 2.280138045935975, "percentage": 76.0, "elapsed_time": "1 day, 4:46:44", "remaining_time": "9:05:09", "throughput": 61957.97, "total_tokens": 6419140992} {"current_steps": 19170, "total_steps": 25209, "loss": 0.3191, "lr": 2.9275831178628576e-05, "epoch": 2.2813280971081755, "percentage": 76.04, "elapsed_time": "1 day, 4:47:32", "remaining_time": "9:04:13", "throughput": 61962.51, "total_tokens": 6422592256} {"current_steps": 19180, "total_steps": 25209, "loss": 0.3229, "lr": 2.927081415612869e-05, "epoch": 2.282518148280376, "percentage": 76.08, "elapsed_time": "1 day, 4:48:21", "remaining_time": "9:03:17", "throughput": 61965.69, "total_tokens": 6425909888} {"current_steps": 19190, "total_steps": 25209, "loss": 0.325, "lr": 2.9265799712058505e-05, "epoch": 2.2837081994525765, "percentage": 76.12, "elapsed_time": "1 day, 4:49:05", "remaining_time": "9:02:20", "throughput": 61970.0, "total_tokens": 6429134592} {"current_steps": 19200, "total_steps": 25209, "loss": 0.319, "lr": 2.926078784421019e-05, "epoch": 2.284898250624777, "percentage": 76.16, "elapsed_time": "1 day, 4:49:53", "remaining_time": "9:01:24", "throughput": 61973.86, "total_tokens": 6432481664} {"current_steps": 19210, "total_steps": 25209, "loss": 0.3193, "lr": 2.9255778550378575e-05, "epoch": 2.286088301796977, "percentage": 76.2, "elapsed_time": "1 day, 4:50:40", "remaining_time": "9:00:27", "throughput": 61977.0, "total_tokens": 6435749376} {"current_steps": 19220, "total_steps": 25209, "loss": 0.3205, "lr": 2.9250771828361118e-05, "epoch": 2.2872783529691776, "percentage": 76.24, "elapsed_time": "1 day, 4:51:27", "remaining_time": "8:59:31", "throughput": 61982.2, "total_tokens": 6439177984} {"current_steps": 19230, "total_steps": 25209, "loss": 0.3191, "lr": 2.9245767675957923e-05, "epoch": 2.288468404141378, "percentage": 76.28, "elapsed_time": "1 day, 4:52:16", "remaining_time": "8:58:35", "throughput": 61985.36, "total_tokens": 6442523904} {"current_steps": 19240, "total_steps": 25209, "loss": 0.3157, "lr": 2.924076609097172e-05, "epoch": 2.2896584553135786, "percentage": 76.32, "elapsed_time": "1 day, 4:53:06", "remaining_time": "8:57:40", "throughput": 61988.1, "total_tokens": 6445939584} {"current_steps": 19250, "total_steps": 25209, "loss": 0.3192, "lr": 2.9235767071207876e-05, "epoch": 2.290848506485779, "percentage": 76.36, "elapsed_time": "1 day, 4:53:50", "remaining_time": "8:56:43", "throughput": 61992.79, "total_tokens": 6449149312} {"current_steps": 19260, "total_steps": 25209, "loss": 0.3208, "lr": 2.9230770614474383e-05, "epoch": 2.292038557657979, "percentage": 76.4, "elapsed_time": "1 day, 4:54:37", "remaining_time": "8:55:47", "throughput": 61996.6, "total_tokens": 6452474624} {"current_steps": 19270, "total_steps": 25209, "loss": 0.3152, "lr": 2.9225776718581842e-05, "epoch": 2.2932286088301796, "percentage": 76.44, "elapsed_time": "1 day, 4:55:24", "remaining_time": "8:54:51", "throughput": 62000.52, "total_tokens": 6455766912} {"current_steps": 19280, "total_steps": 25209, "loss": 0.3195, "lr": 2.9220785381343495e-05, "epoch": 2.29441866000238, "percentage": 76.48, "elapsed_time": "1 day, 4:56:14", "remaining_time": "8:53:55", "throughput": 62002.79, "total_tokens": 6459130752} {"current_steps": 19290, "total_steps": 25209, "loss": 0.3197, "lr": 2.9215796600575174e-05, "epoch": 2.2956087111745807, "percentage": 76.52, "elapsed_time": "1 day, 4:57:02", "remaining_time": "8:52:59", "throughput": 62006.33, "total_tokens": 6462436096} {"current_steps": 19300, "total_steps": 25209, "loss": 0.3208, "lr": 2.9210810374095332e-05, "epoch": 2.296798762346781, "percentage": 76.56, "elapsed_time": "1 day, 4:57:48", "remaining_time": "8:52:03", "throughput": 62011.12, "total_tokens": 6465809920} {"current_steps": 19310, "total_steps": 25209, "loss": 0.3185, "lr": 2.9205826699725026e-05, "epoch": 2.297988813518981, "percentage": 76.6, "elapsed_time": "1 day, 4:58:34", "remaining_time": "8:51:07", "throughput": 62015.31, "total_tokens": 6469113344} {"current_steps": 19320, "total_steps": 25209, "loss": 0.3135, "lr": 2.920084557528791e-05, "epoch": 2.2991788646911817, "percentage": 76.64, "elapsed_time": "1 day, 4:59:25", "remaining_time": "8:50:12", "throughput": 62017.74, "total_tokens": 6472511488} {"current_steps": 19330, "total_steps": 25209, "loss": 0.3143, "lr": 2.9195866998610245e-05, "epoch": 2.300368915863382, "percentage": 76.68, "elapsed_time": "1 day, 5:00:11", "remaining_time": "8:49:15", "throughput": 62022.25, "total_tokens": 6475839232} {"current_steps": 19340, "total_steps": 25209, "loss": 0.3222, "lr": 2.9190890967520878e-05, "epoch": 2.3015589670355827, "percentage": 76.72, "elapsed_time": "1 day, 5:00:57", "remaining_time": "8:48:19", "throughput": 62026.4, "total_tokens": 6479121024} {"current_steps": 19350, "total_steps": 25209, "loss": 0.3146, "lr": 2.9185917479851243e-05, "epoch": 2.3027490182077828, "percentage": 76.76, "elapsed_time": "1 day, 5:01:45", "remaining_time": "8:47:23", "throughput": 62030.37, "total_tokens": 6482510848} {"current_steps": 19360, "total_steps": 25209, "loss": 0.3166, "lr": 2.9180946533435366e-05, "epoch": 2.3039390693799833, "percentage": 76.8, "elapsed_time": "1 day, 5:02:33", "remaining_time": "8:46:27", "throughput": 62033.97, "total_tokens": 6485868032} {"current_steps": 19370, "total_steps": 25209, "loss": 0.3204, "lr": 2.9175978126109853e-05, "epoch": 2.3051291205521838, "percentage": 76.84, "elapsed_time": "1 day, 5:03:23", "remaining_time": "8:45:32", "throughput": 62037.42, "total_tokens": 6489303040} {"current_steps": 19380, "total_steps": 25209, "loss": 0.3234, "lr": 2.9171012255713885e-05, "epoch": 2.3063191717243843, "percentage": 76.88, "elapsed_time": "1 day, 5:04:08", "remaining_time": "8:44:35", "throughput": 62042.23, "total_tokens": 6492598400} {"current_steps": 19390, "total_steps": 25209, "loss": 0.3209, "lr": 2.9166048920089217e-05, "epoch": 2.3075092228965843, "percentage": 76.92, "elapsed_time": "1 day, 5:04:55", "remaining_time": "8:43:39", "throughput": 62046.71, "total_tokens": 6495982720} {"current_steps": 19400, "total_steps": 25209, "loss": 0.3199, "lr": 2.9161088117080175e-05, "epoch": 2.308699274068785, "percentage": 76.96, "elapsed_time": "1 day, 5:05:40", "remaining_time": "8:42:42", "throughput": 62051.53, "total_tokens": 6499325824} {"current_steps": 19410, "total_steps": 25209, "loss": 0.3179, "lr": 2.9156129844533658e-05, "epoch": 2.3098893252409853, "percentage": 77.0, "elapsed_time": "1 day, 5:06:28", "remaining_time": "8:41:46", "throughput": 62054.85, "total_tokens": 6502603904} {"current_steps": 19420, "total_steps": 25209, "loss": 0.3187, "lr": 2.9151174100299104e-05, "epoch": 2.311079376413186, "percentage": 77.04, "elapsed_time": "1 day, 5:07:14", "remaining_time": "8:40:50", "throughput": 62058.91, "total_tokens": 6505921536} {"current_steps": 19430, "total_steps": 25209, "loss": 0.3166, "lr": 2.9146220882228535e-05, "epoch": 2.3122694275853863, "percentage": 77.08, "elapsed_time": "1 day, 5:08:03", "remaining_time": "8:39:55", "throughput": 62063.01, "total_tokens": 6509390080} {"current_steps": 19440, "total_steps": 25209, "loss": 0.3194, "lr": 2.914127018817651e-05, "epoch": 2.3134594787575864, "percentage": 77.12, "elapsed_time": "1 day, 5:08:52", "remaining_time": "8:38:59", "throughput": 62066.21, "total_tokens": 6512740480} {"current_steps": 19450, "total_steps": 25209, "loss": 0.3182, "lr": 2.9136322016000152e-05, "epoch": 2.314649529929787, "percentage": 77.15, "elapsed_time": "1 day, 5:09:38", "remaining_time": "8:38:03", "throughput": 62070.33, "total_tokens": 6516029056} {"current_steps": 19460, "total_steps": 25209, "loss": 0.3193, "lr": 2.9131376363559116e-05, "epoch": 2.3158395811019874, "percentage": 77.19, "elapsed_time": "1 day, 5:10:27", "remaining_time": "8:37:07", "throughput": 62073.15, "total_tokens": 6519404672} {"current_steps": 19470, "total_steps": 25209, "loss": 0.3188, "lr": 2.9126433228715606e-05, "epoch": 2.317029632274188, "percentage": 77.23, "elapsed_time": "1 day, 5:11:15", "remaining_time": "8:36:12", "throughput": 62076.29, "total_tokens": 6522725504} {"current_steps": 19480, "total_steps": 25209, "loss": 0.3206, "lr": 2.9121492609334354e-05, "epoch": 2.3182196834463884, "percentage": 77.27, "elapsed_time": "1 day, 5:12:05", "remaining_time": "8:35:17", "throughput": 62078.73, "total_tokens": 6526060416} {"current_steps": 19490, "total_steps": 25209, "loss": 0.3172, "lr": 2.9116554503282656e-05, "epoch": 2.3194097346185885, "percentage": 77.31, "elapsed_time": "1 day, 5:12:56", "remaining_time": "8:34:22", "throughput": 62081.3, "total_tokens": 6529469696} {"current_steps": 19500, "total_steps": 25209, "loss": 0.322, "lr": 2.9111618908430303e-05, "epoch": 2.320599785790789, "percentage": 77.35, "elapsed_time": "1 day, 5:13:44", "remaining_time": "8:33:26", "throughput": 62085.03, "total_tokens": 6532849280} {"current_steps": 19510, "total_steps": 25209, "loss": 0.3198, "lr": 2.9106685822649643e-05, "epoch": 2.3217898369629895, "percentage": 77.39, "elapsed_time": "1 day, 5:14:32", "remaining_time": "8:32:30", "throughput": 62088.48, "total_tokens": 6536202496} {"current_steps": 19520, "total_steps": 25209, "loss": 0.3216, "lr": 2.910175524381552e-05, "epoch": 2.32297988813519, "percentage": 77.43, "elapsed_time": "1 day, 5:15:19", "remaining_time": "8:31:34", "throughput": 62092.31, "total_tokens": 6539539072} {"current_steps": 19530, "total_steps": 25209, "loss": 0.3172, "lr": 2.9096827169805318e-05, "epoch": 2.3241699393073905, "percentage": 77.47, "elapsed_time": "1 day, 5:16:07", "remaining_time": "8:30:39", "throughput": 62095.88, "total_tokens": 6542883584} {"current_steps": 19540, "total_steps": 25209, "loss": 0.3135, "lr": 2.9091901598498923e-05, "epoch": 2.3253599904795905, "percentage": 77.51, "elapsed_time": "1 day, 5:16:56", "remaining_time": "8:29:43", "throughput": 62099.18, "total_tokens": 6546304256} {"current_steps": 19550, "total_steps": 25209, "loss": 0.3151, "lr": 2.9086978527778736e-05, "epoch": 2.326550041651791, "percentage": 77.55, "elapsed_time": "1 day, 5:17:48", "remaining_time": "8:28:49", "throughput": 62101.65, "total_tokens": 6549744640} {"current_steps": 19560, "total_steps": 25209, "loss": 0.3201, "lr": 2.9082057955529668e-05, "epoch": 2.3277400928239915, "percentage": 77.59, "elapsed_time": "1 day, 5:18:36", "remaining_time": "8:27:53", "throughput": 62105.33, "total_tokens": 6553158400} {"current_steps": 19570, "total_steps": 25209, "loss": 0.3217, "lr": 2.907713987963914e-05, "epoch": 2.328930143996192, "percentage": 77.63, "elapsed_time": "1 day, 5:19:27", "remaining_time": "8:26:58", "throughput": 62107.99, "total_tokens": 6556611968} {"current_steps": 19580, "total_steps": 25209, "loss": 0.3214, "lr": 2.9072224297997058e-05, "epoch": 2.330120195168392, "percentage": 77.67, "elapsed_time": "1 day, 5:20:18", "remaining_time": "8:26:03", "throughput": 62111.09, "total_tokens": 6560081408} {"current_steps": 19590, "total_steps": 25209, "loss": 0.3232, "lr": 2.9067311208495834e-05, "epoch": 2.3313102463405926, "percentage": 77.71, "elapsed_time": "1 day, 5:21:04", "remaining_time": "8:25:07", "throughput": 62115.08, "total_tokens": 6563350144} {"current_steps": 19600, "total_steps": 25209, "loss": 0.32, "lr": 2.9062400609030372e-05, "epoch": 2.332500297512793, "percentage": 77.75, "elapsed_time": "1 day, 5:21:50", "remaining_time": "8:24:11", "throughput": 62118.95, "total_tokens": 6566617088} {"current_steps": 19610, "total_steps": 25209, "loss": 0.3217, "lr": 2.905749249749806e-05, "epoch": 2.3336903486849936, "percentage": 77.79, "elapsed_time": "1 day, 5:22:36", "remaining_time": "8:23:15", "throughput": 62123.24, "total_tokens": 6569921536} {"current_steps": 19620, "total_steps": 25209, "loss": 0.3192, "lr": 2.905258687179878e-05, "epoch": 2.3348803998571936, "percentage": 77.83, "elapsed_time": "1 day, 5:23:24", "remaining_time": "8:22:19", "throughput": 62126.49, "total_tokens": 6573231872} {"current_steps": 19630, "total_steps": 25209, "loss": 0.3165, "lr": 2.904768372983488e-05, "epoch": 2.336070451029394, "percentage": 77.87, "elapsed_time": "1 day, 5:24:15", "remaining_time": "8:21:24", "throughput": 62128.27, "total_tokens": 6576612736} {"current_steps": 19640, "total_steps": 25209, "loss": 0.3227, "lr": 2.90427830695112e-05, "epoch": 2.3372605022015946, "percentage": 77.91, "elapsed_time": "1 day, 5:25:02", "remaining_time": "8:20:28", "throughput": 62131.51, "total_tokens": 6579863296} {"current_steps": 19650, "total_steps": 25209, "loss": 0.3169, "lr": 2.9037884888735044e-05, "epoch": 2.338450553373795, "percentage": 77.95, "elapsed_time": "1 day, 5:25:53", "remaining_time": "8:19:34", "throughput": 62133.76, "total_tokens": 6583310848} {"current_steps": 19660, "total_steps": 25209, "loss": 0.3202, "lr": 2.9032989185416194e-05, "epoch": 2.3396406045459957, "percentage": 77.99, "elapsed_time": "1 day, 5:26:42", "remaining_time": "8:18:39", "throughput": 62136.43, "total_tokens": 6586644096} {"current_steps": 19670, "total_steps": 25209, "loss": 0.3186, "lr": 2.9028095957466888e-05, "epoch": 2.3408306557181957, "percentage": 78.03, "elapsed_time": "1 day, 5:27:30", "remaining_time": "8:17:43", "throughput": 62140.55, "total_tokens": 6590043136} {"current_steps": 19680, "total_steps": 25209, "loss": 0.3175, "lr": 2.9023205202801833e-05, "epoch": 2.342020706890396, "percentage": 78.07, "elapsed_time": "1 day, 5:28:21", "remaining_time": "8:16:48", "throughput": 62142.5, "total_tokens": 6593383680} {"current_steps": 19690, "total_steps": 25209, "loss": 0.3209, "lr": 2.90183169193382e-05, "epoch": 2.3432107580625967, "percentage": 78.11, "elapsed_time": "1 day, 5:29:09", "remaining_time": "8:15:53", "throughput": 62145.7, "total_tokens": 6596744448} {"current_steps": 19700, "total_steps": 25209, "loss": 0.3209, "lr": 2.90134311049956e-05, "epoch": 2.344400809234797, "percentage": 78.15, "elapsed_time": "1 day, 5:29:59", "remaining_time": "8:14:58", "throughput": 62148.66, "total_tokens": 6600146432} {"current_steps": 19710, "total_steps": 25209, "loss": 0.3259, "lr": 2.90085477576961e-05, "epoch": 2.3455908604069977, "percentage": 78.19, "elapsed_time": "1 day, 5:30:46", "remaining_time": "8:14:02", "throughput": 62151.83, "total_tokens": 6603398272} {"current_steps": 19720, "total_steps": 25209, "loss": 0.3201, "lr": 2.9003666875364226e-05, "epoch": 2.3467809115791978, "percentage": 78.23, "elapsed_time": "1 day, 5:31:33", "remaining_time": "8:13:06", "throughput": 62155.51, "total_tokens": 6606752256} {"current_steps": 19730, "total_steps": 25209, "loss": 0.3202, "lr": 2.899878845592694e-05, "epoch": 2.3479709627513983, "percentage": 78.27, "elapsed_time": "1 day, 5:32:23", "remaining_time": "8:12:11", "throughput": 62158.66, "total_tokens": 6610143616} {"current_steps": 19740, "total_steps": 25209, "loss": 0.3245, "lr": 2.8993912497313636e-05, "epoch": 2.3491610139235988, "percentage": 78.31, "elapsed_time": "1 day, 5:33:08", "remaining_time": "8:11:15", "throughput": 62163.26, "total_tokens": 6613485824} {"current_steps": 19750, "total_steps": 25209, "loss": 0.3215, "lr": 2.8989038997456153e-05, "epoch": 2.3503510650957993, "percentage": 78.35, "elapsed_time": "1 day, 5:33:57", "remaining_time": "8:10:20", "throughput": 62166.32, "total_tokens": 6616858368} {"current_steps": 19760, "total_steps": 25209, "loss": 0.3174, "lr": 2.898416795428876e-05, "epoch": 2.3515411162679993, "percentage": 78.38, "elapsed_time": "1 day, 5:34:46", "remaining_time": "8:09:24", "throughput": 62169.99, "total_tokens": 6620286464} {"current_steps": 19770, "total_steps": 25209, "loss": 0.3231, "lr": 2.897929936574816e-05, "epoch": 2.3527311674402, "percentage": 78.42, "elapsed_time": "1 day, 5:35:32", "remaining_time": "8:08:28", "throughput": 62173.9, "total_tokens": 6623566080} {"current_steps": 19780, "total_steps": 25209, "loss": 0.3197, "lr": 2.8974433229773478e-05, "epoch": 2.3539212186124003, "percentage": 78.46, "elapsed_time": "1 day, 5:36:20", "remaining_time": "8:07:32", "throughput": 62177.62, "total_tokens": 6626893184} {"current_steps": 19790, "total_steps": 25209, "loss": 0.3177, "lr": 2.896956954430625e-05, "epoch": 2.355111269784601, "percentage": 78.5, "elapsed_time": "1 day, 5:37:06", "remaining_time": "8:06:37", "throughput": 62181.72, "total_tokens": 6630242048} {"current_steps": 19800, "total_steps": 25209, "loss": 0.3206, "lr": 2.896470830729045e-05, "epoch": 2.356301320956801, "percentage": 78.54, "elapsed_time": "1 day, 5:37:55", "remaining_time": "8:05:41", "throughput": 62184.76, "total_tokens": 6633599232} {"current_steps": 19810, "total_steps": 25209, "loss": 0.3213, "lr": 2.895984951667245e-05, "epoch": 2.3574913721290014, "percentage": 78.58, "elapsed_time": "1 day, 5:38:42", "remaining_time": "8:04:46", "throughput": 62188.41, "total_tokens": 6636906112} {"current_steps": 19820, "total_steps": 25209, "loss": 0.3186, "lr": 2.8954993170401047e-05, "epoch": 2.358681423301202, "percentage": 78.62, "elapsed_time": "1 day, 5:39:33", "remaining_time": "8:03:51", "throughput": 62190.89, "total_tokens": 6640313472} {"current_steps": 19830, "total_steps": 25209, "loss": 0.3206, "lr": 2.8950139266427423e-05, "epoch": 2.3598714744734024, "percentage": 78.66, "elapsed_time": "1 day, 5:40:22", "remaining_time": "8:02:56", "throughput": 62194.17, "total_tokens": 6643710592} {"current_steps": 19840, "total_steps": 25209, "loss": 0.3143, "lr": 2.8945287802705186e-05, "epoch": 2.361061525645603, "percentage": 78.7, "elapsed_time": "1 day, 5:41:10", "remaining_time": "8:02:00", "throughput": 62198.19, "total_tokens": 6647137152} {"current_steps": 19850, "total_steps": 25209, "loss": 0.319, "lr": 2.8940438777190336e-05, "epoch": 2.362251576817803, "percentage": 78.74, "elapsed_time": "1 day, 5:41:56", "remaining_time": "8:01:04", "throughput": 62202.35, "total_tokens": 6650467584} {"current_steps": 19860, "total_steps": 25209, "loss": 0.3197, "lr": 2.8935592187841265e-05, "epoch": 2.3634416279900035, "percentage": 78.78, "elapsed_time": "1 day, 5:42:41", "remaining_time": "8:00:08", "throughput": 62206.93, "total_tokens": 6653771520} {"current_steps": 19870, "total_steps": 25209, "loss": 0.3231, "lr": 2.893074803261876e-05, "epoch": 2.364631679162204, "percentage": 78.82, "elapsed_time": "1 day, 5:43:30", "remaining_time": "7:59:13", "throughput": 62210.28, "total_tokens": 6657158400} {"current_steps": 19880, "total_steps": 25209, "loss": 0.3214, "lr": 2.8925906309485995e-05, "epoch": 2.3658217303344045, "percentage": 78.86, "elapsed_time": "1 day, 5:44:18", "remaining_time": "7:58:17", "throughput": 62214.1, "total_tokens": 6660521344} {"current_steps": 19890, "total_steps": 25209, "loss": 0.3145, "lr": 2.8921067016408532e-05, "epoch": 2.367011781506605, "percentage": 78.9, "elapsed_time": "1 day, 5:45:05", "remaining_time": "7:57:22", "throughput": 62218.05, "total_tokens": 6663881600} {"current_steps": 19900, "total_steps": 25209, "loss": 0.321, "lr": 2.8916230151354316e-05, "epoch": 2.368201832678805, "percentage": 78.94, "elapsed_time": "1 day, 5:45:50", "remaining_time": "7:56:26", "throughput": 62222.45, "total_tokens": 6667191296} {"current_steps": 19910, "total_steps": 25209, "loss": 0.3252, "lr": 2.8911395712293677e-05, "epoch": 2.3693918838510055, "percentage": 78.98, "elapsed_time": "1 day, 5:46:37", "remaining_time": "7:55:30", "throughput": 62225.46, "total_tokens": 6670429440} {"current_steps": 19920, "total_steps": 25209, "loss": 0.3194, "lr": 2.8906563697199294e-05, "epoch": 2.370581935023206, "percentage": 79.02, "elapsed_time": "1 day, 5:47:26", "remaining_time": "7:54:35", "throughput": 62228.87, "total_tokens": 6673854336} {"current_steps": 19930, "total_steps": 25209, "loss": 0.3211, "lr": 2.8901734104046245e-05, "epoch": 2.3717719861954065, "percentage": 79.06, "elapsed_time": "1 day, 5:48:14", "remaining_time": "7:53:39", "throughput": 62232.45, "total_tokens": 6677206912} {"current_steps": 19940, "total_steps": 25209, "loss": 0.3192, "lr": 2.8896906930811964e-05, "epoch": 2.372962037367607, "percentage": 79.1, "elapsed_time": "1 day, 5:49:04", "remaining_time": "7:52:45", "throughput": 62235.24, "total_tokens": 6680612608} {"current_steps": 19950, "total_steps": 25209, "loss": 0.3216, "lr": 2.8892082175476243e-05, "epoch": 2.374152088539807, "percentage": 79.14, "elapsed_time": "1 day, 5:49:50", "remaining_time": "7:51:49", "throughput": 62239.3, "total_tokens": 6683920000} {"current_steps": 19960, "total_steps": 25209, "loss": 0.3201, "lr": 2.8887259836021246e-05, "epoch": 2.3753421397120076, "percentage": 79.18, "elapsed_time": "1 day, 5:50:38", "remaining_time": "7:50:53", "throughput": 62243.33, "total_tokens": 6687299840} {"current_steps": 19970, "total_steps": 25209, "loss": 0.3194, "lr": 2.8882439910431493e-05, "epoch": 2.376532190884208, "percentage": 79.22, "elapsed_time": "1 day, 5:51:26", "remaining_time": "7:49:58", "throughput": 62246.52, "total_tokens": 6690688256} {"current_steps": 19980, "total_steps": 25209, "loss": 0.3237, "lr": 2.8877622396693843e-05, "epoch": 2.3777222420564086, "percentage": 79.26, "elapsed_time": "1 day, 5:52:17", "remaining_time": "7:49:03", "throughput": 62248.99, "total_tokens": 6694073728} {"current_steps": 19990, "total_steps": 25209, "loss": 0.3198, "lr": 2.8872807292797516e-05, "epoch": 2.3789122932286086, "percentage": 79.3, "elapsed_time": "1 day, 5:53:01", "remaining_time": "7:48:07", "throughput": 62253.37, "total_tokens": 6697325696} {"current_steps": 20000, "total_steps": 25209, "loss": 0.3185, "lr": 2.8867994596734084e-05, "epoch": 2.380102344400809, "percentage": 79.34, "elapsed_time": "1 day, 5:53:50", "remaining_time": "7:47:12", "throughput": 62256.56, "total_tokens": 6700715776} {"current_steps": 20000, "total_steps": 25209, "eval_loss": 0.33107635378837585, "epoch": 2.380102344400809, "percentage": 79.34, "elapsed_time": "1 day, 5:53:51", "remaining_time": "7:47:12", "throughput": 62256.02, "total_tokens": 6700715776} {"current_steps": 20010, "total_steps": 25209, "loss": 0.3204, "lr": 2.8863184306497437e-05, "epoch": 2.3812923955730096, "percentage": 79.38, "elapsed_time": "1 day, 5:54:55", "remaining_time": "7:46:21", "throughput": 62250.4, "total_tokens": 6704102912} {"current_steps": 20020, "total_steps": 25209, "loss": 0.3171, "lr": 2.8858376420083848e-05, "epoch": 2.38248244674521, "percentage": 79.42, "elapsed_time": "1 day, 5:55:44", "remaining_time": "7:45:26", "throughput": 62253.39, "total_tokens": 6707456768} {"current_steps": 20030, "total_steps": 25209, "loss": 0.3201, "lr": 2.8853570935491873e-05, "epoch": 2.38367249791741, "percentage": 79.46, "elapsed_time": "1 day, 5:56:30", "remaining_time": "7:44:30", "throughput": 62257.08, "total_tokens": 6710742144} {"current_steps": 20040, "total_steps": 25209, "loss": 0.3208, "lr": 2.8848767850722447e-05, "epoch": 2.3848625490896107, "percentage": 79.5, "elapsed_time": "1 day, 5:57:17", "remaining_time": "7:43:34", "throughput": 62260.79, "total_tokens": 6714018176} {"current_steps": 20050, "total_steps": 25209, "loss": 0.3191, "lr": 2.88439671637788e-05, "epoch": 2.386052600261811, "percentage": 79.54, "elapsed_time": "1 day, 5:58:07", "remaining_time": "7:42:40", "throughput": 62263.65, "total_tokens": 6717438592} {"current_steps": 20060, "total_steps": 25209, "loss": 0.3207, "lr": 2.8839168872666505e-05, "epoch": 2.3872426514340117, "percentage": 79.57, "elapsed_time": "1 day, 5:58:54", "remaining_time": "7:41:44", "throughput": 62267.18, "total_tokens": 6720747264} {"current_steps": 20070, "total_steps": 25209, "loss": 0.3213, "lr": 2.8834372975393448e-05, "epoch": 2.388432702606212, "percentage": 79.61, "elapsed_time": "1 day, 5:59:40", "remaining_time": "7:40:48", "throughput": 62270.58, "total_tokens": 6724006656} {"current_steps": 20080, "total_steps": 25209, "loss": 0.3239, "lr": 2.8829579469969843e-05, "epoch": 2.3896227537784123, "percentage": 79.65, "elapsed_time": "1 day, 6:00:26", "remaining_time": "7:39:53", "throughput": 62274.14, "total_tokens": 6727261312} {"current_steps": 20090, "total_steps": 25209, "loss": 0.3193, "lr": 2.88247883544082e-05, "epoch": 2.3908128049506128, "percentage": 79.69, "elapsed_time": "1 day, 6:01:11", "remaining_time": "7:38:56", "throughput": 62278.61, "total_tokens": 6730522240} {"current_steps": 20100, "total_steps": 25209, "loss": 0.3206, "lr": 2.8819999626723366e-05, "epoch": 2.3920028561228133, "percentage": 79.73, "elapsed_time": "1 day, 6:01:58", "remaining_time": "7:38:01", "throughput": 62282.76, "total_tokens": 6733940096} {"current_steps": 20110, "total_steps": 25209, "loss": 0.3201, "lr": 2.881521328493248e-05, "epoch": 2.3931929072950138, "percentage": 79.77, "elapsed_time": "1 day, 6:02:46", "remaining_time": "7:37:06", "throughput": 62286.0, "total_tokens": 6737232128} {"current_steps": 20120, "total_steps": 25209, "loss": 0.3218, "lr": 2.881042932705499e-05, "epoch": 2.3943829584672143, "percentage": 79.81, "elapsed_time": "1 day, 6:03:34", "remaining_time": "7:36:10", "throughput": 62289.63, "total_tokens": 6740623616} {"current_steps": 20130, "total_steps": 25209, "loss": 0.3225, "lr": 2.8805647751112635e-05, "epoch": 2.3955730096394143, "percentage": 79.85, "elapsed_time": "1 day, 6:04:19", "remaining_time": "7:35:14", "throughput": 62293.83, "total_tokens": 6743887232} {"current_steps": 20140, "total_steps": 25209, "loss": 0.3171, "lr": 2.8800868555129462e-05, "epoch": 2.396763060811615, "percentage": 79.89, "elapsed_time": "1 day, 6:05:05", "remaining_time": "7:34:19", "throughput": 62297.78, "total_tokens": 6747177600} {"current_steps": 20150, "total_steps": 25209, "loss": 0.3191, "lr": 2.8796091737131814e-05, "epoch": 2.3979531119838153, "percentage": 79.93, "elapsed_time": "1 day, 6:05:56", "remaining_time": "7:33:24", "throughput": 62299.7, "total_tokens": 6750584064} {"current_steps": 20160, "total_steps": 25209, "loss": 0.3233, "lr": 2.8791317295148322e-05, "epoch": 2.399143163156016, "percentage": 79.97, "elapsed_time": "1 day, 6:06:43", "remaining_time": "7:32:29", "throughput": 62303.75, "total_tokens": 6753947904} {"current_steps": 20170, "total_steps": 25209, "loss": 0.3207, "lr": 2.8786545227209893e-05, "epoch": 2.4003332143282163, "percentage": 80.01, "elapsed_time": "1 day, 6:07:29", "remaining_time": "7:31:33", "throughput": 62307.67, "total_tokens": 6757223040} {"current_steps": 20180, "total_steps": 25209, "loss": 0.3202, "lr": 2.8781775531349742e-05, "epoch": 2.4015232655004164, "percentage": 80.05, "elapsed_time": "1 day, 6:08:15", "remaining_time": "7:30:37", "throughput": 62311.4, "total_tokens": 6760493824} {"current_steps": 20190, "total_steps": 25209, "loss": 0.3232, "lr": 2.8777008205603334e-05, "epoch": 2.402713316672617, "percentage": 80.09, "elapsed_time": "1 day, 6:09:04", "remaining_time": "7:29:42", "throughput": 62314.22, "total_tokens": 6763860608} {"current_steps": 20200, "total_steps": 25209, "loss": 0.3224, "lr": 2.877224324800844e-05, "epoch": 2.4039033678448174, "percentage": 80.13, "elapsed_time": "1 day, 6:09:54", "remaining_time": "7:28:48", "throughput": 62316.38, "total_tokens": 6767224448} {"current_steps": 20210, "total_steps": 25209, "loss": 0.3212, "lr": 2.8767480656605078e-05, "epoch": 2.405093419017018, "percentage": 80.17, "elapsed_time": "1 day, 6:10:43", "remaining_time": "7:27:53", "throughput": 62318.83, "total_tokens": 6770543872} {"current_steps": 20220, "total_steps": 25209, "loss": 0.3191, "lr": 2.8762720429435556e-05, "epoch": 2.406283470189218, "percentage": 80.21, "elapsed_time": "1 day, 6:11:34", "remaining_time": "7:26:58", "throughput": 62320.77, "total_tokens": 6773901184} {"current_steps": 20230, "total_steps": 25209, "loss": 0.3193, "lr": 2.8757962564544448e-05, "epoch": 2.4074735213614185, "percentage": 80.25, "elapsed_time": "1 day, 6:12:18", "remaining_time": "7:26:02", "throughput": 62325.62, "total_tokens": 6777179648} {"current_steps": 20240, "total_steps": 25209, "loss": 0.3196, "lr": 2.8753207059978586e-05, "epoch": 2.408663572533619, "percentage": 80.29, "elapsed_time": "1 day, 6:13:05", "remaining_time": "7:25:07", "throughput": 62329.0, "total_tokens": 6780487424} {"current_steps": 20250, "total_steps": 25209, "loss": 0.3235, "lr": 2.874845391378706e-05, "epoch": 2.4098536237058195, "percentage": 80.33, "elapsed_time": "1 day, 6:13:55", "remaining_time": "7:24:12", "throughput": 62331.71, "total_tokens": 6783934208} {"current_steps": 20260, "total_steps": 25209, "loss": 0.3188, "lr": 2.874370312402121e-05, "epoch": 2.4110436748780195, "percentage": 80.37, "elapsed_time": "1 day, 6:14:43", "remaining_time": "7:23:17", "throughput": 62335.18, "total_tokens": 6787297408} {"current_steps": 20270, "total_steps": 25209, "loss": 0.3211, "lr": 2.8738954688734647e-05, "epoch": 2.41223372605022, "percentage": 80.41, "elapsed_time": "1 day, 6:15:34", "remaining_time": "7:22:23", "throughput": 62337.3, "total_tokens": 6790711936} {"current_steps": 20280, "total_steps": 25209, "loss": 0.3226, "lr": 2.8734208605983226e-05, "epoch": 2.4134237772224205, "percentage": 80.45, "elapsed_time": "1 day, 6:16:24", "remaining_time": "7:21:28", "throughput": 62340.23, "total_tokens": 6794133888} {"current_steps": 20290, "total_steps": 25209, "loss": 0.3186, "lr": 2.8729464873825035e-05, "epoch": 2.414613828394621, "percentage": 80.49, "elapsed_time": "1 day, 6:17:14", "remaining_time": "7:20:33", "throughput": 62342.74, "total_tokens": 6797513728} {"current_steps": 20300, "total_steps": 25209, "loss": 0.3199, "lr": 2.8724723490320427e-05, "epoch": 2.4158038795668215, "percentage": 80.53, "elapsed_time": "1 day, 6:18:04", "remaining_time": "7:19:39", "throughput": 62345.53, "total_tokens": 6800929536} {"current_steps": 20310, "total_steps": 25209, "loss": 0.3242, "lr": 2.8719984453531983e-05, "epoch": 2.4169939307390216, "percentage": 80.57, "elapsed_time": "1 day, 6:18:49", "remaining_time": "7:18:43", "throughput": 62349.39, "total_tokens": 6804173056} {"current_steps": 20320, "total_steps": 25209, "loss": 0.3249, "lr": 2.871524776152452e-05, "epoch": 2.418183981911222, "percentage": 80.61, "elapsed_time": "1 day, 6:19:38", "remaining_time": "7:17:48", "throughput": 62353.09, "total_tokens": 6807628288} {"current_steps": 20330, "total_steps": 25209, "loss": 0.3205, "lr": 2.8710513412365093e-05, "epoch": 2.4193740330834226, "percentage": 80.65, "elapsed_time": "1 day, 6:20:26", "remaining_time": "7:16:53", "throughput": 62355.97, "total_tokens": 6810926080} {"current_steps": 20340, "total_steps": 25209, "loss": 0.3193, "lr": 2.8705781404122977e-05, "epoch": 2.420564084255623, "percentage": 80.69, "elapsed_time": "1 day, 6:21:15", "remaining_time": "7:15:58", "throughput": 62358.97, "total_tokens": 6814275968} {"current_steps": 20350, "total_steps": 25209, "loss": 0.3208, "lr": 2.87010517348697e-05, "epoch": 2.4217541354278236, "percentage": 80.73, "elapsed_time": "1 day, 6:22:04", "remaining_time": "7:15:03", "throughput": 62361.7, "total_tokens": 6817649152} {"current_steps": 20360, "total_steps": 25209, "loss": 0.3187, "lr": 2.8696324402678976e-05, "epoch": 2.4229441866000236, "percentage": 80.76, "elapsed_time": "1 day, 6:22:55", "remaining_time": "7:14:09", "throughput": 62363.75, "total_tokens": 6821040384} {"current_steps": 20370, "total_steps": 25209, "loss": 0.3223, "lr": 2.8691599405626764e-05, "epoch": 2.424134237772224, "percentage": 80.8, "elapsed_time": "1 day, 6:23:40", "remaining_time": "7:13:13", "throughput": 62367.5, "total_tokens": 6824282240} {"current_steps": 20380, "total_steps": 25209, "loss": 0.317, "lr": 2.8686876741791234e-05, "epoch": 2.4253242889444246, "percentage": 80.84, "elapsed_time": "1 day, 6:24:28", "remaining_time": "7:12:18", "throughput": 62370.59, "total_tokens": 6827596672} {"current_steps": 20390, "total_steps": 25209, "loss": 0.3205, "lr": 2.8682156409252775e-05, "epoch": 2.426514340116625, "percentage": 80.88, "elapsed_time": "1 day, 6:25:15", "remaining_time": "7:11:23", "throughput": 62374.41, "total_tokens": 6830959616} {"current_steps": 20400, "total_steps": 25209, "loss": 0.3187, "lr": 2.8677438406093976e-05, "epoch": 2.4277043912888256, "percentage": 80.92, "elapsed_time": "1 day, 6:26:06", "remaining_time": "7:10:28", "throughput": 62376.7, "total_tokens": 6834424192} {"current_steps": 20410, "total_steps": 25209, "loss": 0.318, "lr": 2.867272273039964e-05, "epoch": 2.4288944424610257, "percentage": 80.96, "elapsed_time": "1 day, 6:26:54", "remaining_time": "7:09:33", "throughput": 62379.68, "total_tokens": 6837701888} {"current_steps": 20420, "total_steps": 25209, "loss": 0.3207, "lr": 2.8668009380256765e-05, "epoch": 2.430084493633226, "percentage": 81.0, "elapsed_time": "1 day, 6:27:41", "remaining_time": "7:08:38", "throughput": 62383.46, "total_tokens": 6841036032} {"current_steps": 20430, "total_steps": 25209, "loss": 0.3236, "lr": 2.8663298353754574e-05, "epoch": 2.4312745448054267, "percentage": 81.04, "elapsed_time": "1 day, 6:28:31", "remaining_time": "7:07:43", "throughput": 62384.92, "total_tokens": 6844373760} {"current_steps": 20440, "total_steps": 25209, "loss": 0.3199, "lr": 2.865858964898445e-05, "epoch": 2.432464595977627, "percentage": 81.08, "elapsed_time": "1 day, 6:29:19", "remaining_time": "7:06:48", "throughput": 62388.11, "total_tokens": 6847711232} {"current_steps": 20450, "total_steps": 25209, "loss": 0.3183, "lr": 2.8653883264040004e-05, "epoch": 2.4336546471498273, "percentage": 81.12, "elapsed_time": "1 day, 6:30:09", "remaining_time": "7:05:54", "throughput": 62391.04, "total_tokens": 6851103488} {"current_steps": 20460, "total_steps": 25209, "loss": 0.3171, "lr": 2.8649179197017017e-05, "epoch": 2.4348446983220278, "percentage": 81.16, "elapsed_time": "1 day, 6:30:58", "remaining_time": "7:04:59", "throughput": 62393.6, "total_tokens": 6854475392} {"current_steps": 20470, "total_steps": 25209, "loss": 0.3194, "lr": 2.864447744601347e-05, "epoch": 2.4360347494942283, "percentage": 81.2, "elapsed_time": "1 day, 6:31:45", "remaining_time": "7:04:04", "throughput": 62397.55, "total_tokens": 6857824256} {"current_steps": 20480, "total_steps": 25209, "loss": 0.3231, "lr": 2.8639778009129507e-05, "epoch": 2.4372248006664288, "percentage": 81.24, "elapsed_time": "1 day, 6:32:32", "remaining_time": "7:03:08", "throughput": 62401.55, "total_tokens": 6861194368} {"current_steps": 20490, "total_steps": 25209, "loss": 0.3207, "lr": 2.8635080884467492e-05, "epoch": 2.438414851838629, "percentage": 81.28, "elapsed_time": "1 day, 6:33:17", "remaining_time": "7:02:13", "throughput": 62406.35, "total_tokens": 6864543872} {"current_steps": 20500, "total_steps": 25209, "loss": 0.3204, "lr": 2.8630386070131927e-05, "epoch": 2.4396049030108293, "percentage": 81.32, "elapsed_time": "1 day, 6:34:06", "remaining_time": "7:01:18", "throughput": 62409.62, "total_tokens": 6867952128} {"current_steps": 20510, "total_steps": 25209, "loss": 0.3216, "lr": 2.8625693564229507e-05, "epoch": 2.44079495418303, "percentage": 81.36, "elapsed_time": "1 day, 6:34:53", "remaining_time": "7:00:23", "throughput": 62412.95, "total_tokens": 6871255936} {"current_steps": 20520, "total_steps": 25209, "loss": 0.3197, "lr": 2.8621003364869102e-05, "epoch": 2.4419850053552303, "percentage": 81.4, "elapsed_time": "1 day, 6:35:40", "remaining_time": "6:59:28", "throughput": 62416.8, "total_tokens": 6874628736} {"current_steps": 20530, "total_steps": 25209, "loss": 0.3169, "lr": 2.8616315470161738e-05, "epoch": 2.443175056527431, "percentage": 81.44, "elapsed_time": "1 day, 6:36:29", "remaining_time": "6:58:33", "throughput": 62419.68, "total_tokens": 6877970816} {"current_steps": 20540, "total_steps": 25209, "loss": 0.3149, "lr": 2.8611629878220624e-05, "epoch": 2.444365107699631, "percentage": 81.48, "elapsed_time": "1 day, 6:37:15", "remaining_time": "6:57:37", "throughput": 62423.52, "total_tokens": 6881279616} {"current_steps": 20550, "total_steps": 25209, "loss": 0.3182, "lr": 2.8606946587161116e-05, "epoch": 2.4455551588718314, "percentage": 81.52, "elapsed_time": "1 day, 6:38:04", "remaining_time": "6:56:43", "throughput": 62426.87, "total_tokens": 6884688128} {"current_steps": 20560, "total_steps": 25209, "loss": 0.3197, "lr": 2.860226559510072e-05, "epoch": 2.446745210044032, "percentage": 81.56, "elapsed_time": "1 day, 6:38:51", "remaining_time": "6:55:47", "throughput": 62430.4, "total_tokens": 6888023424} {"current_steps": 20570, "total_steps": 25209, "loss": 0.3229, "lr": 2.859758690015913e-05, "epoch": 2.4479352612162324, "percentage": 81.6, "elapsed_time": "1 day, 6:39:37", "remaining_time": "6:54:52", "throughput": 62434.13, "total_tokens": 6891352192} {"current_steps": 20580, "total_steps": 25209, "loss": 0.3204, "lr": 2.8592910500458154e-05, "epoch": 2.449125312388433, "percentage": 81.64, "elapsed_time": "1 day, 6:40:24", "remaining_time": "6:53:57", "throughput": 62437.81, "total_tokens": 6894685696} {"current_steps": 20590, "total_steps": 25209, "loss": 0.3212, "lr": 2.858823639412178e-05, "epoch": 2.450315363560633, "percentage": 81.68, "elapsed_time": "1 day, 6:41:13", "remaining_time": "6:53:02", "throughput": 62440.7, "total_tokens": 6898065152} {"current_steps": 20600, "total_steps": 25209, "loss": 0.3217, "lr": 2.858356457927613e-05, "epoch": 2.4515054147328335, "percentage": 81.72, "elapsed_time": "1 day, 6:42:01", "remaining_time": "6:52:07", "throughput": 62443.96, "total_tokens": 6901429760} {"current_steps": 20610, "total_steps": 25209, "loss": 0.3271, "lr": 2.857889505404946e-05, "epoch": 2.452695465905034, "percentage": 81.76, "elapsed_time": "1 day, 6:42:48", "remaining_time": "6:51:12", "throughput": 62447.16, "total_tokens": 6904714240} {"current_steps": 20620, "total_steps": 25209, "loss": 0.3219, "lr": 2.8574227816572184e-05, "epoch": 2.4538855170772345, "percentage": 81.8, "elapsed_time": "1 day, 6:43:34", "remaining_time": "6:50:17", "throughput": 62450.82, "total_tokens": 6907987584} {"current_steps": 20630, "total_steps": 25209, "loss": 0.3152, "lr": 2.856956286497684e-05, "epoch": 2.455075568249435, "percentage": 81.84, "elapsed_time": "1 day, 6:44:23", "remaining_time": "6:49:22", "throughput": 62454.2, "total_tokens": 6911386368} {"current_steps": 20640, "total_steps": 25209, "loss": 0.3188, "lr": 2.85649001973981e-05, "epoch": 2.456265619421635, "percentage": 81.88, "elapsed_time": "1 day, 6:45:14", "remaining_time": "6:48:28", "throughput": 62456.42, "total_tokens": 6914804608} {"current_steps": 20650, "total_steps": 25209, "loss": 0.3217, "lr": 2.8560239811972754e-05, "epoch": 2.4574556705938355, "percentage": 81.92, "elapsed_time": "1 day, 6:46:03", "remaining_time": "6:47:33", "throughput": 62459.81, "total_tokens": 6918245248} {"current_steps": 20660, "total_steps": 25209, "loss": 0.3138, "lr": 2.855558170683976e-05, "epoch": 2.458645721766036, "percentage": 81.95, "elapsed_time": "1 day, 6:46:53", "remaining_time": "6:46:39", "throughput": 62462.34, "total_tokens": 6921655552} {"current_steps": 20670, "total_steps": 25209, "loss": 0.321, "lr": 2.855092588014017e-05, "epoch": 2.4598357729382365, "percentage": 81.99, "elapsed_time": "1 day, 6:47:41", "remaining_time": "6:45:44", "throughput": 62465.25, "total_tokens": 6924984832} {"current_steps": 20680, "total_steps": 25209, "loss": 0.3205, "lr": 2.854627233001715e-05, "epoch": 2.4610258241104366, "percentage": 82.03, "elapsed_time": "1 day, 6:48:28", "remaining_time": "6:44:49", "throughput": 62468.96, "total_tokens": 6928315648} {"current_steps": 20690, "total_steps": 25209, "loss": 0.3215, "lr": 2.8541621054615992e-05, "epoch": 2.462215875282637, "percentage": 82.07, "elapsed_time": "1 day, 6:49:17", "remaining_time": "6:43:54", "throughput": 62471.35, "total_tokens": 6931637376} {"current_steps": 20700, "total_steps": 25209, "loss": 0.3203, "lr": 2.8536972052084122e-05, "epoch": 2.4634059264548376, "percentage": 82.11, "elapsed_time": "1 day, 6:50:06", "remaining_time": "6:43:00", "throughput": 62474.14, "total_tokens": 6935027328} {"current_steps": 20710, "total_steps": 25209, "loss": 0.3182, "lr": 2.853232532057104e-05, "epoch": 2.464595977627038, "percentage": 82.15, "elapsed_time": "1 day, 6:50:55", "remaining_time": "6:42:05", "throughput": 62476.55, "total_tokens": 6938355328} {"current_steps": 20720, "total_steps": 25209, "loss": 0.3196, "lr": 2.8527680858228395e-05, "epoch": 2.465786028799238, "percentage": 82.19, "elapsed_time": "1 day, 6:51:40", "remaining_time": "6:41:10", "throughput": 62480.93, "total_tokens": 6941671296} {"current_steps": 20730, "total_steps": 25209, "loss": 0.3191, "lr": 2.8523038663209906e-05, "epoch": 2.4669760799714386, "percentage": 82.23, "elapsed_time": "1 day, 6:52:27", "remaining_time": "6:40:15", "throughput": 62485.06, "total_tokens": 6945088512} {"current_steps": 20740, "total_steps": 25209, "loss": 0.3193, "lr": 2.8518398733671427e-05, "epoch": 2.468166131143639, "percentage": 82.27, "elapsed_time": "1 day, 6:53:14", "remaining_time": "6:39:20", "throughput": 62488.9, "total_tokens": 6948453376} {"current_steps": 20750, "total_steps": 25209, "loss": 0.3208, "lr": 2.8513761067770877e-05, "epoch": 2.4693561823158396, "percentage": 82.31, "elapsed_time": "1 day, 6:54:01", "remaining_time": "6:38:24", "throughput": 62492.49, "total_tokens": 6951772800} {"current_steps": 20760, "total_steps": 25209, "loss": 0.3197, "lr": 2.85091256636683e-05, "epoch": 2.47054623348804, "percentage": 82.35, "elapsed_time": "1 day, 6:54:49", "remaining_time": "6:37:30", "throughput": 62496.07, "total_tokens": 6955152128} {"current_steps": 20770, "total_steps": 25209, "loss": 0.3253, "lr": 2.850449251952582e-05, "epoch": 2.47173628466024, "percentage": 82.39, "elapsed_time": "1 day, 6:55:36", "remaining_time": "6:36:34", "throughput": 62499.21, "total_tokens": 6958426624} {"current_steps": 20780, "total_steps": 25209, "loss": 0.3209, "lr": 2.849986163350766e-05, "epoch": 2.4729263358324407, "percentage": 82.43, "elapsed_time": "1 day, 6:56:24", "remaining_time": "6:35:40", "throughput": 62502.14, "total_tokens": 6961791104} {"current_steps": 20790, "total_steps": 25209, "loss": 0.3231, "lr": 2.8495233003780103e-05, "epoch": 2.474116387004641, "percentage": 82.47, "elapsed_time": "1 day, 6:57:13", "remaining_time": "6:34:45", "throughput": 62505.09, "total_tokens": 6965171840} {"current_steps": 20800, "total_steps": 25209, "loss": 0.3224, "lr": 2.8490606628511557e-05, "epoch": 2.4753064381768417, "percentage": 82.51, "elapsed_time": "1 day, 6:58:03", "remaining_time": "6:33:51", "throughput": 62507.05, "total_tokens": 6968483712} {"current_steps": 20810, "total_steps": 25209, "loss": 0.319, "lr": 2.8485982505872476e-05, "epoch": 2.476496489349042, "percentage": 82.55, "elapsed_time": "1 day, 6:58:51", "remaining_time": "6:32:56", "throughput": 62510.22, "total_tokens": 6971855616} {"current_steps": 20820, "total_steps": 25209, "loss": 0.3199, "lr": 2.8481360634035415e-05, "epoch": 2.4776865405212423, "percentage": 82.59, "elapsed_time": "1 day, 6:59:40", "remaining_time": "6:32:01", "throughput": 62513.25, "total_tokens": 6975257472} {"current_steps": 20830, "total_steps": 25209, "loss": 0.3198, "lr": 2.847674101117499e-05, "epoch": 2.4788765916934428, "percentage": 82.63, "elapsed_time": "1 day, 7:00:25", "remaining_time": "6:31:06", "throughput": 62517.53, "total_tokens": 6978576512} {"current_steps": 20840, "total_steps": 25209, "loss": 0.3196, "lr": 2.8472123635467896e-05, "epoch": 2.4800666428656433, "percentage": 82.67, "elapsed_time": "1 day, 7:01:16", "remaining_time": "6:30:12", "throughput": 62520.4, "total_tokens": 6982035200} {"current_steps": 20850, "total_steps": 25209, "loss": 0.3208, "lr": 2.846750850509289e-05, "epoch": 2.4812566940378438, "percentage": 82.71, "elapsed_time": "1 day, 7:02:04", "remaining_time": "6:29:17", "throughput": 62523.46, "total_tokens": 6985381632} {"current_steps": 20860, "total_steps": 25209, "loss": 0.3217, "lr": 2.8462895618230813e-05, "epoch": 2.4824467452100443, "percentage": 82.75, "elapsed_time": "1 day, 7:02:52", "remaining_time": "6:28:22", "throughput": 62526.44, "total_tokens": 6988750464} {"current_steps": 20870, "total_steps": 25209, "loss": 0.3213, "lr": 2.845828497306453e-05, "epoch": 2.4836367963822443, "percentage": 82.79, "elapsed_time": "1 day, 7:03:44", "remaining_time": "6:27:28", "throughput": 62528.3, "total_tokens": 6992174208} {"current_steps": 20880, "total_steps": 25209, "loss": 0.3208, "lr": 2.8453676567779018e-05, "epoch": 2.484826847554445, "percentage": 82.83, "elapsed_time": "1 day, 7:04:30", "remaining_time": "6:26:33", "throughput": 62530.96, "total_tokens": 6995381632} {"current_steps": 20890, "total_steps": 25209, "loss": 0.3219, "lr": 2.8449070400561267e-05, "epoch": 2.4860168987266453, "percentage": 82.87, "elapsed_time": "1 day, 7:05:17", "remaining_time": "6:25:38", "throughput": 62534.83, "total_tokens": 6998727168} {"current_steps": 20900, "total_steps": 25209, "loss": 0.3195, "lr": 2.8444466469600343e-05, "epoch": 2.487206949898846, "percentage": 82.91, "elapsed_time": "1 day, 7:06:06", "remaining_time": "6:24:44", "throughput": 62537.38, "total_tokens": 7002080000} {"current_steps": 20910, "total_steps": 25209, "loss": 0.3184, "lr": 2.8439864773087354e-05, "epoch": 2.488397001071046, "percentage": 82.95, "elapsed_time": "1 day, 7:06:53", "remaining_time": "6:23:49", "throughput": 62539.88, "total_tokens": 7005327360} {"current_steps": 20920, "total_steps": 25209, "loss": 0.3223, "lr": 2.8435265309215465e-05, "epoch": 2.4895870522432464, "percentage": 82.99, "elapsed_time": "1 day, 7:07:44", "remaining_time": "6:22:55", "throughput": 62541.89, "total_tokens": 7008712320} {"current_steps": 20930, "total_steps": 25209, "loss": 0.3196, "lr": 2.843066807617987e-05, "epoch": 2.490777103415447, "percentage": 83.03, "elapsed_time": "1 day, 7:08:31", "remaining_time": "6:22:00", "throughput": 62544.84, "total_tokens": 7011991296} {"current_steps": 20940, "total_steps": 25209, "loss": 0.323, "lr": 2.8426073072177827e-05, "epoch": 2.4919671545876474, "percentage": 83.07, "elapsed_time": "1 day, 7:09:17", "remaining_time": "6:21:05", "throughput": 62548.1, "total_tokens": 7015236736} {"current_steps": 20950, "total_steps": 25209, "loss": 0.3192, "lr": 2.8421480295408616e-05, "epoch": 2.4931572057598475, "percentage": 83.11, "elapsed_time": "1 day, 7:10:05", "remaining_time": "6:20:10", "throughput": 62551.66, "total_tokens": 7018610304} {"current_steps": 20960, "total_steps": 25209, "loss": 0.3152, "lr": 2.841688974407355e-05, "epoch": 2.494347256932048, "percentage": 83.14, "elapsed_time": "1 day, 7:10:55", "remaining_time": "6:19:16", "throughput": 62553.51, "total_tokens": 7021957376} {"current_steps": 20970, "total_steps": 25209, "loss": 0.3179, "lr": 2.8412301416375984e-05, "epoch": 2.4955373081042485, "percentage": 83.18, "elapsed_time": "1 day, 7:11:45", "remaining_time": "6:18:22", "throughput": 62555.6, "total_tokens": 7025324672} {"current_steps": 20980, "total_steps": 25209, "loss": 0.316, "lr": 2.840771531052131e-05, "epoch": 2.496727359276449, "percentage": 83.22, "elapsed_time": "1 day, 7:12:33", "remaining_time": "6:17:27", "throughput": 62558.27, "total_tokens": 7028641792} {"current_steps": 20990, "total_steps": 25209, "loss": 0.3197, "lr": 2.840313142471694e-05, "epoch": 2.4979174104486495, "percentage": 83.26, "elapsed_time": "1 day, 7:13:23", "remaining_time": "6:16:33", "throughput": 62560.59, "total_tokens": 7032015360} {"current_steps": 21000, "total_steps": 25209, "loss": 0.319, "lr": 2.83985497571723e-05, "epoch": 2.4991074616208495, "percentage": 83.3, "elapsed_time": "1 day, 7:14:12", "remaining_time": "6:15:38", "throughput": 62563.19, "total_tokens": 7035396736} {"current_steps": 21010, "total_steps": 25209, "loss": 0.3194, "lr": 2.8393970306098843e-05, "epoch": 2.50029751279305, "percentage": 83.34, "elapsed_time": "1 day, 7:15:01", "remaining_time": "6:14:44", "throughput": 62565.61, "total_tokens": 7038736640} {"current_steps": 21020, "total_steps": 25209, "loss": 0.3225, "lr": 2.8389393069710053e-05, "epoch": 2.5014875639652505, "percentage": 83.38, "elapsed_time": "1 day, 7:15:50", "remaining_time": "6:13:49", "throughput": 62568.03, "total_tokens": 7042045312} {"current_steps": 21030, "total_steps": 25209, "loss": 0.3154, "lr": 2.8384818046221418e-05, "epoch": 2.502677615137451, "percentage": 83.42, "elapsed_time": "1 day, 7:16:37", "remaining_time": "6:12:54", "throughput": 62571.5, "total_tokens": 7045377152} {"current_steps": 21040, "total_steps": 25209, "loss": 0.3198, "lr": 2.8380245233850434e-05, "epoch": 2.5038676663096515, "percentage": 83.46, "elapsed_time": "1 day, 7:17:23", "remaining_time": "6:11:59", "throughput": 62575.12, "total_tokens": 7048700800} {"current_steps": 21050, "total_steps": 25209, "loss": 0.3224, "lr": 2.837567463081662e-05, "epoch": 2.5050577174818516, "percentage": 83.5, "elapsed_time": "1 day, 7:18:09", "remaining_time": "6:11:04", "throughput": 62578.57, "total_tokens": 7051966720} {"current_steps": 21060, "total_steps": 25209, "loss": 0.3203, "lr": 2.8371106235341477e-05, "epoch": 2.506247768654052, "percentage": 83.54, "elapsed_time": "1 day, 7:18:57", "remaining_time": "6:10:10", "throughput": 62581.53, "total_tokens": 7055285760} {"current_steps": 21070, "total_steps": 25209, "loss": 0.319, "lr": 2.836654004564855e-05, "epoch": 2.5074378198262526, "percentage": 83.58, "elapsed_time": "1 day, 7:19:46", "remaining_time": "6:09:15", "throughput": 62584.57, "total_tokens": 7058690048} {"current_steps": 21080, "total_steps": 25209, "loss": 0.3172, "lr": 2.8361976059963348e-05, "epoch": 2.508627870998453, "percentage": 83.62, "elapsed_time": "1 day, 7:20:31", "remaining_time": "6:08:20", "throughput": 62588.6, "total_tokens": 7061937792} {"current_steps": 21090, "total_steps": 25209, "loss": 0.3201, "lr": 2.835741427651339e-05, "epoch": 2.5098179221706536, "percentage": 83.66, "elapsed_time": "1 day, 7:21:19", "remaining_time": "6:07:26", "throughput": 62591.18, "total_tokens": 7065280768} {"current_steps": 21100, "total_steps": 25209, "loss": 0.3211, "lr": 2.8352854693528197e-05, "epoch": 2.5110079733428536, "percentage": 83.7, "elapsed_time": "1 day, 7:22:03", "remaining_time": "6:06:30", "throughput": 62595.3, "total_tokens": 7068494720} {"current_steps": 21110, "total_steps": 25209, "loss": 0.3225, "lr": 2.8348297309239274e-05, "epoch": 2.512198024515054, "percentage": 83.74, "elapsed_time": "1 day, 7:22:50", "remaining_time": "6:05:35", "throughput": 62598.54, "total_tokens": 7071816064} {"current_steps": 21120, "total_steps": 25209, "loss": 0.3261, "lr": 2.834374212188012e-05, "epoch": 2.5133880756872546, "percentage": 83.78, "elapsed_time": "1 day, 7:23:40", "remaining_time": "6:04:41", "throughput": 62600.84, "total_tokens": 7075169280} {"current_steps": 21130, "total_steps": 25209, "loss": 0.32, "lr": 2.833918912968621e-05, "epoch": 2.5145781268594547, "percentage": 83.82, "elapsed_time": "1 day, 7:24:29", "remaining_time": "6:03:47", "throughput": 62603.16, "total_tokens": 7078530176} {"current_steps": 21140, "total_steps": 25209, "loss": 0.3195, "lr": 2.833463833089502e-05, "epoch": 2.515768178031655, "percentage": 83.86, "elapsed_time": "1 day, 7:25:18", "remaining_time": "6:02:52", "throughput": 62605.65, "total_tokens": 7081885568} {"current_steps": 21150, "total_steps": 25209, "loss": 0.3222, "lr": 2.8330089723745985e-05, "epoch": 2.5169582292038557, "percentage": 83.9, "elapsed_time": "1 day, 7:26:06", "remaining_time": "6:01:58", "throughput": 62608.3, "total_tokens": 7085152256} {"current_steps": 21160, "total_steps": 25209, "loss": 0.3193, "lr": 2.8325543306480538e-05, "epoch": 2.518148280376056, "percentage": 83.94, "elapsed_time": "1 day, 7:26:54", "remaining_time": "6:01:03", "throughput": 62611.45, "total_tokens": 7088502784} {"current_steps": 21170, "total_steps": 25209, "loss": 0.3192, "lr": 2.832099907734208e-05, "epoch": 2.5193383315482567, "percentage": 83.98, "elapsed_time": "1 day, 7:27:40", "remaining_time": "6:00:08", "throughput": 62615.07, "total_tokens": 7091822080} {"current_steps": 21180, "total_steps": 25209, "loss": 0.3231, "lr": 2.831645703457598e-05, "epoch": 2.5205283827204568, "percentage": 84.02, "elapsed_time": "1 day, 7:28:26", "remaining_time": "5:59:13", "throughput": 62618.85, "total_tokens": 7095115392} {"current_steps": 21190, "total_steps": 25209, "loss": 0.3186, "lr": 2.8311917176429582e-05, "epoch": 2.5217184338926573, "percentage": 84.06, "elapsed_time": "1 day, 7:29:10", "remaining_time": "5:58:18", "throughput": 62623.7, "total_tokens": 7098442624} {"current_steps": 21200, "total_steps": 25209, "loss": 0.3191, "lr": 2.830737950115218e-05, "epoch": 2.5229084850648578, "percentage": 84.1, "elapsed_time": "1 day, 7:30:02", "remaining_time": "5:57:24", "throughput": 62625.3, "total_tokens": 7101876864} {"current_steps": 21210, "total_steps": 25209, "loss": 0.3191, "lr": 2.8302844006995062e-05, "epoch": 2.5240985362370583, "percentage": 84.14, "elapsed_time": "1 day, 7:30:49", "remaining_time": "5:56:30", "throughput": 62628.71, "total_tokens": 7105171072} {"current_steps": 21220, "total_steps": 25209, "loss": 0.3217, "lr": 2.829831069221145e-05, "epoch": 2.5252885874092588, "percentage": 84.18, "elapsed_time": "1 day, 7:31:37", "remaining_time": "5:55:35", "throughput": 62631.18, "total_tokens": 7108498816} {"current_steps": 21230, "total_steps": 25209, "loss": 0.3212, "lr": 2.8293779555056532e-05, "epoch": 2.526478638581459, "percentage": 84.22, "elapsed_time": "1 day, 7:32:27", "remaining_time": "5:54:41", "throughput": 62633.52, "total_tokens": 7111857792} {"current_steps": 21240, "total_steps": 25209, "loss": 0.3177, "lr": 2.8289250593787454e-05, "epoch": 2.5276686897536593, "percentage": 84.26, "elapsed_time": "1 day, 7:33:15", "remaining_time": "5:53:47", "throughput": 62636.57, "total_tokens": 7115254272} {"current_steps": 21250, "total_steps": 25209, "loss": 0.3195, "lr": 2.8284723806663316e-05, "epoch": 2.52885874092586, "percentage": 84.3, "elapsed_time": "1 day, 7:34:04", "remaining_time": "5:52:52", "throughput": 62639.76, "total_tokens": 7118644224} {"current_steps": 21260, "total_steps": 25209, "loss": 0.3188, "lr": 2.828019919194515e-05, "epoch": 2.5300487920980603, "percentage": 84.33, "elapsed_time": "1 day, 7:34:52", "remaining_time": "5:51:58", "throughput": 62642.12, "total_tokens": 7121949184} {"current_steps": 21270, "total_steps": 25209, "loss": 0.319, "lr": 2.827567674789597e-05, "epoch": 2.531238843270261, "percentage": 84.37, "elapsed_time": "1 day, 7:35:41", "remaining_time": "5:51:03", "throughput": 62644.66, "total_tokens": 7125316096} {"current_steps": 21280, "total_steps": 25209, "loss": 0.3229, "lr": 2.8271156472780697e-05, "epoch": 2.532428894442461, "percentage": 84.41, "elapsed_time": "1 day, 7:36:31", "remaining_time": "5:50:09", "throughput": 62647.18, "total_tokens": 7128710656} {"current_steps": 21290, "total_steps": 25209, "loss": 0.3215, "lr": 2.826663836486621e-05, "epoch": 2.5336189456146614, "percentage": 84.45, "elapsed_time": "1 day, 7:37:20", "remaining_time": "5:49:15", "throughput": 62649.74, "total_tokens": 7132081536} {"current_steps": 21300, "total_steps": 25209, "loss": 0.323, "lr": 2.8262122422421326e-05, "epoch": 2.534808996786862, "percentage": 84.49, "elapsed_time": "1 day, 7:38:11", "remaining_time": "5:48:21", "throughput": 62651.39, "total_tokens": 7135491328} {"current_steps": 21310, "total_steps": 25209, "loss": 0.3219, "lr": 2.8257608643716797e-05, "epoch": 2.5359990479590624, "percentage": 84.53, "elapsed_time": "1 day, 7:39:00", "remaining_time": "5:47:27", "throughput": 62654.31, "total_tokens": 7138873088} {"current_steps": 21320, "total_steps": 25209, "loss": 0.3187, "lr": 2.8253097027025312e-05, "epoch": 2.537189099131263, "percentage": 84.57, "elapsed_time": "1 day, 7:39:49", "remaining_time": "5:46:32", "throughput": 62657.56, "total_tokens": 7142322688} {"current_steps": 21330, "total_steps": 25209, "loss": 0.3171, "lr": 2.8248587570621472e-05, "epoch": 2.538379150303463, "percentage": 84.61, "elapsed_time": "1 day, 7:40:35", "remaining_time": "5:45:38", "throughput": 62661.78, "total_tokens": 7145645568} {"current_steps": 21340, "total_steps": 25209, "loss": 0.318, "lr": 2.824408027278182e-05, "epoch": 2.5395692014756635, "percentage": 84.65, "elapsed_time": "1 day, 7:41:23", "remaining_time": "5:44:43", "throughput": 62664.7, "total_tokens": 7149016960} {"current_steps": 21350, "total_steps": 25209, "loss": 0.3227, "lr": 2.823957513178483e-05, "epoch": 2.540759252647864, "percentage": 84.69, "elapsed_time": "1 day, 7:42:13", "remaining_time": "5:43:49", "throughput": 62666.96, "total_tokens": 7152372608} {"current_steps": 21360, "total_steps": 25209, "loss": 0.3236, "lr": 2.8235072145910878e-05, "epoch": 2.541949303820064, "percentage": 84.73, "elapsed_time": "1 day, 7:43:02", "remaining_time": "5:42:55", "throughput": 62669.28, "total_tokens": 7155710208} {"current_steps": 21370, "total_steps": 25209, "loss": 0.3207, "lr": 2.8230571313442273e-05, "epoch": 2.5431393549922645, "percentage": 84.77, "elapsed_time": "1 day, 7:43:52", "remaining_time": "5:42:01", "throughput": 62671.6, "total_tokens": 7159109888} {"current_steps": 21380, "total_steps": 25209, "loss": 0.322, "lr": 2.822607263266324e-05, "epoch": 2.544329406164465, "percentage": 84.81, "elapsed_time": "1 day, 7:44:41", "remaining_time": "5:41:07", "throughput": 62674.23, "total_tokens": 7162520192} {"current_steps": 21390, "total_steps": 25209, "loss": 0.316, "lr": 2.822157610185991e-05, "epoch": 2.5455194573366655, "percentage": 84.85, "elapsed_time": "1 day, 7:45:27", "remaining_time": "5:40:12", "throughput": 62677.6, "total_tokens": 7165794432} {"current_steps": 21400, "total_steps": 25209, "loss": 0.3238, "lr": 2.821708171932032e-05, "epoch": 2.546709508508866, "percentage": 84.89, "elapsed_time": "1 day, 7:46:15", "remaining_time": "5:39:17", "throughput": 62680.43, "total_tokens": 7169100416} {"current_steps": 21410, "total_steps": 25209, "loss": 0.3197, "lr": 2.821258948333444e-05, "epoch": 2.547899559681066, "percentage": 84.93, "elapsed_time": "1 day, 7:47:04", "remaining_time": "5:38:23", "throughput": 62682.86, "total_tokens": 7172469376} {"current_steps": 21420, "total_steps": 25209, "loss": 0.3191, "lr": 2.8208099392194116e-05, "epoch": 2.5490896108532666, "percentage": 84.97, "elapsed_time": "1 day, 7:47:53", "remaining_time": "5:37:29", "throughput": 62685.69, "total_tokens": 7175872000} {"current_steps": 21430, "total_steps": 25209, "loss": 0.3192, "lr": 2.8203611444193113e-05, "epoch": 2.550279662025467, "percentage": 85.01, "elapsed_time": "1 day, 7:48:40", "remaining_time": "5:36:34", "throughput": 62689.29, "total_tokens": 7179225984} {"current_steps": 21440, "total_steps": 25209, "loss": 0.3206, "lr": 2.8199125637627084e-05, "epoch": 2.5514697131976676, "percentage": 85.05, "elapsed_time": "1 day, 7:49:30", "remaining_time": "5:35:40", "throughput": 62691.63, "total_tokens": 7182618624} {"current_steps": 21450, "total_steps": 25209, "loss": 0.32, "lr": 2.8194641970793593e-05, "epoch": 2.552659764369868, "percentage": 85.09, "elapsed_time": "1 day, 7:50:22", "remaining_time": "5:34:47", "throughput": 62693.76, "total_tokens": 7186127232} {"current_steps": 21460, "total_steps": 25209, "loss": 0.3221, "lr": 2.8190160441992092e-05, "epoch": 2.553849815542068, "percentage": 85.13, "elapsed_time": "1 day, 7:51:10", "remaining_time": "5:33:52", "throughput": 62696.68, "total_tokens": 7189483776} {"current_steps": 21470, "total_steps": 25209, "loss": 0.3188, "lr": 2.818568104952392e-05, "epoch": 2.5550398667142686, "percentage": 85.17, "elapsed_time": "1 day, 7:52:02", "remaining_time": "5:32:58", "throughput": 62698.98, "total_tokens": 7192957824} {"current_steps": 21480, "total_steps": 25209, "loss": 0.3191, "lr": 2.8181203791692306e-05, "epoch": 2.556229917886469, "percentage": 85.21, "elapsed_time": "1 day, 7:52:50", "remaining_time": "5:32:04", "throughput": 62701.91, "total_tokens": 7196332928} {"current_steps": 21490, "total_steps": 25209, "loss": 0.3204, "lr": 2.8176728666802375e-05, "epoch": 2.5574199690586696, "percentage": 85.25, "elapsed_time": "1 day, 7:53:37", "remaining_time": "5:31:10", "throughput": 62705.41, "total_tokens": 7199690112} {"current_steps": 21500, "total_steps": 25209, "loss": 0.3198, "lr": 2.8172255673161124e-05, "epoch": 2.55861002023087, "percentage": 85.29, "elapsed_time": "1 day, 7:54:23", "remaining_time": "5:30:15", "throughput": 62708.85, "total_tokens": 7202957824} {"current_steps": 21510, "total_steps": 25209, "loss": 0.3184, "lr": 2.8167784809077436e-05, "epoch": 2.55980007140307, "percentage": 85.33, "elapsed_time": "1 day, 7:55:10", "remaining_time": "5:29:20", "throughput": 62712.45, "total_tokens": 7206287744} {"current_steps": 21520, "total_steps": 25209, "loss": 0.3221, "lr": 2.816331607286207e-05, "epoch": 2.5609901225752707, "percentage": 85.37, "elapsed_time": "1 day, 7:56:01", "remaining_time": "5:28:26", "throughput": 62713.99, "total_tokens": 7209688704} {"current_steps": 21530, "total_steps": 25209, "loss": 0.32, "lr": 2.815884946282766e-05, "epoch": 2.562180173747471, "percentage": 85.41, "elapsed_time": "1 day, 7:56:49", "remaining_time": "5:27:32", "throughput": 62717.01, "total_tokens": 7213050880} {"current_steps": 21540, "total_steps": 25209, "loss": 0.32, "lr": 2.815438497728871e-05, "epoch": 2.5633702249196717, "percentage": 85.45, "elapsed_time": "1 day, 7:57:35", "remaining_time": "5:26:37", "throughput": 62720.86, "total_tokens": 7216405504} {"current_steps": 21550, "total_steps": 25209, "loss": 0.3176, "lr": 2.8149922614561607e-05, "epoch": 2.564560276091872, "percentage": 85.49, "elapsed_time": "1 day, 7:58:22", "remaining_time": "5:25:43", "throughput": 62724.42, "total_tokens": 7219730176} {"current_steps": 21560, "total_steps": 25209, "loss": 0.3172, "lr": 2.8145462372964588e-05, "epoch": 2.5657503272640723, "percentage": 85.53, "elapsed_time": "1 day, 7:59:08", "remaining_time": "5:24:48", "throughput": 62727.91, "total_tokens": 7223030912} {"current_steps": 21570, "total_steps": 25209, "loss": 0.317, "lr": 2.814100425081777e-05, "epoch": 2.5669403784362728, "percentage": 85.56, "elapsed_time": "1 day, 7:59:55", "remaining_time": "5:23:54", "throughput": 62731.34, "total_tokens": 7226394496} {"current_steps": 21580, "total_steps": 25209, "loss": 0.3235, "lr": 2.8136548246443117e-05, "epoch": 2.5681304296084733, "percentage": 85.6, "elapsed_time": "1 day, 8:00:40", "remaining_time": "5:22:59", "throughput": 62735.79, "total_tokens": 7229680640} {"current_steps": 21590, "total_steps": 25209, "loss": 0.3195, "lr": 2.8132094358164468e-05, "epoch": 2.5693204807806733, "percentage": 85.64, "elapsed_time": "1 day, 8:01:25", "remaining_time": "5:22:04", "throughput": 62740.2, "total_tokens": 7233004160} {"current_steps": 21600, "total_steps": 25209, "loss": 0.3191, "lr": 2.8127642584307508e-05, "epoch": 2.570510531952874, "percentage": 85.68, "elapsed_time": "1 day, 8:02:11", "remaining_time": "5:21:09", "throughput": 62743.89, "total_tokens": 7236316416} {"current_steps": 21610, "total_steps": 25209, "loss": 0.319, "lr": 2.8123192923199776e-05, "epoch": 2.5717005831250743, "percentage": 85.72, "elapsed_time": "1 day, 8:03:02", "remaining_time": "5:20:16", "throughput": 62746.2, "total_tokens": 7239800576} {"current_steps": 21620, "total_steps": 25209, "loss": 0.3186, "lr": 2.8118745373170667e-05, "epoch": 2.572890634297275, "percentage": 85.76, "elapsed_time": "1 day, 8:03:47", "remaining_time": "5:19:21", "throughput": 62749.82, "total_tokens": 7243034880} {"current_steps": 21630, "total_steps": 25209, "loss": 0.3231, "lr": 2.8114299932551423e-05, "epoch": 2.5740806854694753, "percentage": 85.8, "elapsed_time": "1 day, 8:04:34", "remaining_time": "5:18:26", "throughput": 62752.81, "total_tokens": 7246333184} {"current_steps": 21640, "total_steps": 25209, "loss": 0.3152, "lr": 2.8109856599675145e-05, "epoch": 2.5752707366416754, "percentage": 85.84, "elapsed_time": "1 day, 8:05:21", "remaining_time": "5:17:32", "throughput": 62756.15, "total_tokens": 7249703296} {"current_steps": 21650, "total_steps": 25209, "loss": 0.3188, "lr": 2.8105415372876742e-05, "epoch": 2.576460787813876, "percentage": 85.88, "elapsed_time": "1 day, 8:06:09", "remaining_time": "5:16:38", "throughput": 62759.19, "total_tokens": 7253049472} {"current_steps": 21660, "total_steps": 25209, "loss": 0.3194, "lr": 2.8100976250493e-05, "epoch": 2.5776508389860764, "percentage": 85.92, "elapsed_time": "1 day, 8:06:59", "remaining_time": "5:15:44", "throughput": 62760.88, "total_tokens": 7256379008} {"current_steps": 21670, "total_steps": 25209, "loss": 0.3203, "lr": 2.8096539230862527e-05, "epoch": 2.578840890158277, "percentage": 85.96, "elapsed_time": "1 day, 8:07:50", "remaining_time": "5:14:50", "throughput": 62762.75, "total_tokens": 7259804672} {"current_steps": 21680, "total_steps": 25209, "loss": 0.3175, "lr": 2.809210431232578e-05, "epoch": 2.5800309413304774, "percentage": 86.0, "elapsed_time": "1 day, 8:08:37", "remaining_time": "5:13:56", "throughput": 62766.23, "total_tokens": 7263163776} {"current_steps": 21690, "total_steps": 25209, "loss": 0.3208, "lr": 2.8087671493225025e-05, "epoch": 2.5812209925026774, "percentage": 86.04, "elapsed_time": "1 day, 8:09:23", "remaining_time": "5:13:01", "throughput": 62770.13, "total_tokens": 7266485504} {"current_steps": 21700, "total_steps": 25209, "loss": 0.3211, "lr": 2.808324077190438e-05, "epoch": 2.582411043674878, "percentage": 86.08, "elapsed_time": "1 day, 8:10:13", "remaining_time": "5:12:07", "throughput": 62772.86, "total_tokens": 7269949696} {"current_steps": 21710, "total_steps": 25209, "loss": 0.3231, "lr": 2.807881214670978e-05, "epoch": 2.5836010948470784, "percentage": 86.12, "elapsed_time": "1 day, 8:10:59", "remaining_time": "5:11:13", "throughput": 62775.49, "total_tokens": 7273160192} {"current_steps": 21720, "total_steps": 25209, "loss": 0.3214, "lr": 2.8074385615988996e-05, "epoch": 2.584791146019279, "percentage": 86.16, "elapsed_time": "1 day, 8:11:48", "remaining_time": "5:10:19", "throughput": 62778.13, "total_tokens": 7276527488} {"current_steps": 21730, "total_steps": 25209, "loss": 0.3216, "lr": 2.8069961178091602e-05, "epoch": 2.5859811971914795, "percentage": 86.2, "elapsed_time": "1 day, 8:12:37", "remaining_time": "5:09:24", "throughput": 62780.66, "total_tokens": 7279900672} {"current_steps": 21740, "total_steps": 25209, "loss": 0.32, "lr": 2.806553883136901e-05, "epoch": 2.5871712483636795, "percentage": 86.24, "elapsed_time": "1 day, 8:13:25", "remaining_time": "5:08:30", "throughput": 62783.25, "total_tokens": 7283225472} {"current_steps": 21750, "total_steps": 25209, "loss": 0.324, "lr": 2.806111857417445e-05, "epoch": 2.58836129953588, "percentage": 86.28, "elapsed_time": "1 day, 8:14:13", "remaining_time": "5:07:36", "throughput": 62786.97, "total_tokens": 7286620672} {"current_steps": 21760, "total_steps": 25209, "loss": 0.3223, "lr": 2.8056700404862957e-05, "epoch": 2.5895513507080805, "percentage": 86.32, "elapsed_time": "1 day, 8:15:00", "remaining_time": "5:06:42", "throughput": 62789.96, "total_tokens": 7289939712} {"current_steps": 21770, "total_steps": 25209, "loss": 0.3223, "lr": 2.8052284321791383e-05, "epoch": 2.590741401880281, "percentage": 86.36, "elapsed_time": "1 day, 8:15:50", "remaining_time": "5:05:48", "throughput": 62792.07, "total_tokens": 7293340416} {"current_steps": 21780, "total_steps": 25209, "loss": 0.3173, "lr": 2.8047870323318382e-05, "epoch": 2.5919314530524815, "percentage": 86.4, "elapsed_time": "1 day, 8:16:36", "remaining_time": "5:04:53", "throughput": 62795.85, "total_tokens": 7296678144} {"current_steps": 21790, "total_steps": 25209, "loss": 0.3194, "lr": 2.8043458407804428e-05, "epoch": 2.5931215042246816, "percentage": 86.44, "elapsed_time": "1 day, 8:17:25", "remaining_time": "5:03:59", "throughput": 62798.14, "total_tokens": 7300031744} {"current_steps": 21800, "total_steps": 25209, "loss": 0.3207, "lr": 2.8039048573611805e-05, "epoch": 2.594311555396882, "percentage": 86.48, "elapsed_time": "1 day, 8:18:08", "remaining_time": "5:03:04", "throughput": 62802.63, "total_tokens": 7303230848} {"current_steps": 21810, "total_steps": 25209, "loss": 0.3234, "lr": 2.8034640819104574e-05, "epoch": 2.5955016065690826, "percentage": 86.52, "elapsed_time": "1 day, 8:18:55", "remaining_time": "5:02:10", "throughput": 62805.4, "total_tokens": 7306516224} {"current_steps": 21820, "total_steps": 25209, "loss": 0.316, "lr": 2.803023514264861e-05, "epoch": 2.5966916577412826, "percentage": 86.56, "elapsed_time": "1 day, 8:19:44", "remaining_time": "5:01:16", "throughput": 62808.17, "total_tokens": 7309886720} {"current_steps": 21830, "total_steps": 25209, "loss": 0.3195, "lr": 2.8025831542611596e-05, "epoch": 2.597881708913483, "percentage": 86.6, "elapsed_time": "1 day, 8:20:31", "remaining_time": "5:00:22", "throughput": 62811.4, "total_tokens": 7313214720} {"current_steps": 21840, "total_steps": 25209, "loss": 0.3199, "lr": 2.8021430017362994e-05, "epoch": 2.5990717600856836, "percentage": 86.64, "elapsed_time": "1 day, 8:21:18", "remaining_time": "4:59:27", "throughput": 62814.5, "total_tokens": 7316538752} {"current_steps": 21850, "total_steps": 25209, "loss": 0.3214, "lr": 2.801703056527406e-05, "epoch": 2.600261811257884, "percentage": 86.68, "elapsed_time": "1 day, 8:22:06", "remaining_time": "4:58:33", "throughput": 62817.01, "total_tokens": 7319864832} {"current_steps": 21860, "total_steps": 25209, "loss": 0.3162, "lr": 2.801263318471784e-05, "epoch": 2.6014518624300846, "percentage": 86.72, "elapsed_time": "1 day, 8:22:54", "remaining_time": "4:57:39", "throughput": 62819.89, "total_tokens": 7323207808} {"current_steps": 21870, "total_steps": 25209, "loss": 0.318, "lr": 2.800823787406917e-05, "epoch": 2.6026419136022847, "percentage": 86.75, "elapsed_time": "1 day, 8:23:43", "remaining_time": "4:56:45", "throughput": 62822.71, "total_tokens": 7326608256} {"current_steps": 21880, "total_steps": 25209, "loss": 0.3177, "lr": 2.8003844631704678e-05, "epoch": 2.603831964774485, "percentage": 86.79, "elapsed_time": "1 day, 8:24:30", "remaining_time": "4:55:51", "throughput": 62825.87, "total_tokens": 7329928064} {"current_steps": 21890, "total_steps": 25209, "loss": 0.3207, "lr": 2.7999453456002755e-05, "epoch": 2.6050220159466857, "percentage": 86.83, "elapsed_time": "1 day, 8:25:19", "remaining_time": "4:54:57", "throughput": 62828.01, "total_tokens": 7333267584} {"current_steps": 21900, "total_steps": 25209, "loss": 0.3204, "lr": 2.799506434534359e-05, "epoch": 2.606212067118886, "percentage": 86.87, "elapsed_time": "1 day, 8:26:06", "remaining_time": "4:54:02", "throughput": 62831.24, "total_tokens": 7336570368} {"current_steps": 21910, "total_steps": 25209, "loss": 0.3166, "lr": 2.7990677298109136e-05, "epoch": 2.6074021182910867, "percentage": 86.91, "elapsed_time": "1 day, 8:26:52", "remaining_time": "4:53:08", "throughput": 62835.01, "total_tokens": 7339922048} {"current_steps": 21920, "total_steps": 25209, "loss": 0.3216, "lr": 2.7986292312683125e-05, "epoch": 2.6085921694632868, "percentage": 86.95, "elapsed_time": "1 day, 8:27:40", "remaining_time": "4:52:14", "throughput": 62837.54, "total_tokens": 7343220992} {"current_steps": 21930, "total_steps": 25209, "loss": 0.3225, "lr": 2.798190938745106e-05, "epoch": 2.6097822206354873, "percentage": 86.99, "elapsed_time": "1 day, 8:28:27", "remaining_time": "4:51:20", "throughput": 62840.5, "total_tokens": 7346522496} {"current_steps": 21940, "total_steps": 25209, "loss": 0.3176, "lr": 2.7977528520800218e-05, "epoch": 2.6109722718076878, "percentage": 87.03, "elapsed_time": "1 day, 8:29:15", "remaining_time": "4:50:26", "throughput": 62843.31, "total_tokens": 7349894528} {"current_steps": 21950, "total_steps": 25209, "loss": 0.3185, "lr": 2.7973149711119635e-05, "epoch": 2.6121623229798883, "percentage": 87.07, "elapsed_time": "1 day, 8:30:04", "remaining_time": "4:49:32", "throughput": 62845.77, "total_tokens": 7353252096} {"current_steps": 21960, "total_steps": 25209, "loss": 0.3214, "lr": 2.7968772956800115e-05, "epoch": 2.6133523741520888, "percentage": 87.11, "elapsed_time": "1 day, 8:30:55", "remaining_time": "4:48:38", "throughput": 62846.21, "total_tokens": 7356493312} {"current_steps": 21970, "total_steps": 25209, "loss": 0.3205, "lr": 2.796439825623423e-05, "epoch": 2.614542425324289, "percentage": 87.15, "elapsed_time": "1 day, 8:34:06", "remaining_time": "4:48:05", "throughput": 62772.99, "total_tokens": 7359892864} {"current_steps": 21980, "total_steps": 25209, "loss": 0.3198, "lr": 2.79600256078163e-05, "epoch": 2.6157324764964893, "percentage": 87.19, "elapsed_time": "1 day, 8:36:23", "remaining_time": "4:47:24", "throughput": 62728.16, "total_tokens": 7363234176} {"current_steps": 21990, "total_steps": 25209, "loss": 0.3201, "lr": 2.7955655009942416e-05, "epoch": 2.61692252766869, "percentage": 87.23, "elapsed_time": "1 day, 8:38:42", "remaining_time": "4:46:43", "throughput": 62682.07, "total_tokens": 7366551296} {"current_steps": 22000, "total_steps": 25209, "loss": 0.3152, "lr": 2.79512864610104e-05, "epoch": 2.61811257884089, "percentage": 87.27, "elapsed_time": "1 day, 8:40:17", "remaining_time": "4:45:56", "throughput": 62660.53, "total_tokens": 7369958016} {"current_steps": 22010, "total_steps": 25209, "loss": 0.321, "lr": 2.794691995941986e-05, "epoch": 2.619302630013091, "percentage": 87.31, "elapsed_time": "1 day, 8:41:21", "remaining_time": "4:45:04", "throughput": 62654.03, "total_tokens": 7373249920} {"current_steps": 22020, "total_steps": 25209, "loss": 0.3217, "lr": 2.7942555503572115e-05, "epoch": 2.620492681185291, "percentage": 87.35, "elapsed_time": "1 day, 8:42:17", "remaining_time": "4:44:11", "throughput": 62652.08, "total_tokens": 7376519936} {"current_steps": 22030, "total_steps": 25209, "loss": 0.3235, "lr": 2.7938193091870268e-05, "epoch": 2.6216827323574914, "percentage": 87.39, "elapsed_time": "1 day, 8:43:12", "remaining_time": "4:43:17", "throughput": 62651.21, "total_tokens": 7379846400} {"current_steps": 22040, "total_steps": 25209, "loss": 0.3205, "lr": 2.793383272271914e-05, "epoch": 2.622872783529692, "percentage": 87.43, "elapsed_time": "1 day, 8:44:08", "remaining_time": "4:42:24", "throughput": 62650.06, "total_tokens": 7383215360} {"current_steps": 22050, "total_steps": 25209, "loss": 0.3235, "lr": 2.7929474394525307e-05, "epoch": 2.624062834701892, "percentage": 87.47, "elapsed_time": "1 day, 8:45:00", "remaining_time": "4:41:31", "throughput": 62649.55, "total_tokens": 7386429696} {"current_steps": 22060, "total_steps": 25209, "loss": 0.3206, "lr": 2.7925118105697078e-05, "epoch": 2.6252528858740924, "percentage": 87.51, "elapsed_time": "1 day, 8:45:55", "remaining_time": "4:40:37", "throughput": 62649.08, "total_tokens": 7389830528} {"current_steps": 22070, "total_steps": 25209, "loss": 0.3211, "lr": 2.792076385464451e-05, "epoch": 2.626442937046293, "percentage": 87.55, "elapsed_time": "1 day, 8:46:47", "remaining_time": "4:39:44", "throughput": 62649.09, "total_tokens": 7393090560} {"current_steps": 22080, "total_steps": 25209, "loss": 0.3181, "lr": 2.7916411639779383e-05, "epoch": 2.6276329882184934, "percentage": 87.59, "elapsed_time": "1 day, 8:47:40", "remaining_time": "4:38:50", "throughput": 62649.57, "total_tokens": 7396435712} {"current_steps": 22090, "total_steps": 25209, "loss": 0.3205, "lr": 2.7912061459515215e-05, "epoch": 2.628823039390694, "percentage": 87.63, "elapsed_time": "1 day, 8:48:35", "remaining_time": "4:37:57", "throughput": 62648.88, "total_tokens": 7399773056} {"current_steps": 22100, "total_steps": 25209, "loss": 0.3205, "lr": 2.7907713312267247e-05, "epoch": 2.630013090562894, "percentage": 87.67, "elapsed_time": "1 day, 8:49:29", "remaining_time": "4:37:03", "throughput": 62648.16, "total_tokens": 7403071744} {"current_steps": 22110, "total_steps": 25209, "loss": 0.3192, "lr": 2.7903367196452457e-05, "epoch": 2.6312031417350945, "percentage": 87.71, "elapsed_time": "1 day, 8:50:33", "remaining_time": "4:36:11", "throughput": 62642.72, "total_tokens": 7406469376} {"current_steps": 22120, "total_steps": 25209, "loss": 0.3203, "lr": 2.7899023110489554e-05, "epoch": 2.632393192907295, "percentage": 87.75, "elapsed_time": "1 day, 8:51:48", "remaining_time": "4:35:21", "throughput": 62631.94, "total_tokens": 7409881088} {"current_steps": 22130, "total_steps": 25209, "loss": 0.3207, "lr": 2.789468105279895e-05, "epoch": 2.6335832440794955, "percentage": 87.79, "elapsed_time": "1 day, 8:54:26", "remaining_time": "4:34:42", "throughput": 62577.46, "total_tokens": 7413354112} {"current_steps": 22140, "total_steps": 25209, "loss": 0.3184, "lr": 2.7890341021802786e-05, "epoch": 2.634773295251696, "percentage": 87.83, "elapsed_time": "1 day, 8:56:13", "remaining_time": "4:33:56", "throughput": 62549.01, "total_tokens": 7416638336} {"current_steps": 22150, "total_steps": 25209, "loss": 0.3218, "lr": 2.7886003015924933e-05, "epoch": 2.635963346423896, "percentage": 87.87, "elapsed_time": "1 day, 8:57:51", "remaining_time": "4:33:08", "throughput": 62525.76, "total_tokens": 7420000768} {"current_steps": 22160, "total_steps": 25209, "loss": 0.3202, "lr": 2.788166703359096e-05, "epoch": 2.6371533975960966, "percentage": 87.91, "elapsed_time": "1 day, 8:58:46", "remaining_time": "4:32:15", "throughput": 62525.1, "total_tokens": 7423382528} {"current_steps": 22170, "total_steps": 25209, "loss": 0.3179, "lr": 2.787733307322816e-05, "epoch": 2.638343448768297, "percentage": 87.94, "elapsed_time": "1 day, 8:59:40", "remaining_time": "4:31:22", "throughput": 62524.99, "total_tokens": 7426780032} {"current_steps": 22180, "total_steps": 25209, "loss": 0.3167, "lr": 2.7873001133265518e-05, "epoch": 2.6395334999404976, "percentage": 87.98, "elapsed_time": "1 day, 9:00:33", "remaining_time": "4:30:28", "throughput": 62525.92, "total_tokens": 7430198400} {"current_steps": 22190, "total_steps": 25209, "loss": 0.319, "lr": 2.7868671212133768e-05, "epoch": 2.640723551112698, "percentage": 88.02, "elapsed_time": "1 day, 9:01:31", "remaining_time": "4:29:35", "throughput": 62523.65, "total_tokens": 7433548672} {"current_steps": 22200, "total_steps": 25209, "loss": 0.3185, "lr": 2.7864343308265313e-05, "epoch": 2.641913602284898, "percentage": 88.06, "elapsed_time": "1 day, 9:02:42", "remaining_time": "4:28:44", "throughput": 62514.81, "total_tokens": 7436945280} {"current_steps": 22210, "total_steps": 25209, "loss": 0.3203, "lr": 2.7860017420094258e-05, "epoch": 2.6431036534570986, "percentage": 88.1, "elapsed_time": "1 day, 9:03:59", "remaining_time": "4:27:53", "throughput": 62502.73, "total_tokens": 7440277504} {"current_steps": 22220, "total_steps": 25209, "loss": 0.3171, "lr": 2.7855693546056445e-05, "epoch": 2.644293704629299, "percentage": 88.14, "elapsed_time": "1 day, 9:05:14", "remaining_time": "4:27:03", "throughput": 62491.02, "total_tokens": 7443598976} {"current_steps": 22230, "total_steps": 25209, "loss": 0.3167, "lr": 2.785137168458937e-05, "epoch": 2.645483755801499, "percentage": 88.18, "elapsed_time": "1 day, 9:06:13", "remaining_time": "4:26:10", "throughput": 62488.64, "total_tokens": 7446974208} {"current_steps": 22240, "total_steps": 25209, "loss": 0.3223, "lr": 2.7847051834132265e-05, "epoch": 2.6466738069737, "percentage": 88.22, "elapsed_time": "1 day, 9:07:06", "remaining_time": "4:25:16", "throughput": 62488.77, "total_tokens": 7450297088} {"current_steps": 22250, "total_steps": 25209, "loss": 0.3205, "lr": 2.784273399312603e-05, "epoch": 2.6478638581459, "percentage": 88.26, "elapsed_time": "1 day, 9:07:53", "remaining_time": "4:24:22", "throughput": 62490.65, "total_tokens": 7453496320} {"current_steps": 22260, "total_steps": 25209, "loss": 0.3206, "lr": 2.783841816001326e-05, "epoch": 2.6490539093181007, "percentage": 88.3, "elapsed_time": "1 day, 9:08:43", "remaining_time": "4:23:28", "throughput": 62491.84, "total_tokens": 7456773248} {"current_steps": 22270, "total_steps": 25209, "loss": 0.318, "lr": 2.7834104333238255e-05, "epoch": 2.650243960490301, "percentage": 88.34, "elapsed_time": "1 day, 9:09:37", "remaining_time": "4:22:34", "throughput": 62492.1, "total_tokens": 7460157568} {"current_steps": 22280, "total_steps": 25209, "loss": 0.3224, "lr": 2.7829792511246987e-05, "epoch": 2.6514340116625013, "percentage": 88.38, "elapsed_time": "1 day, 9:10:30", "remaining_time": "4:21:40", "throughput": 62491.48, "total_tokens": 7463417600} {"current_steps": 22290, "total_steps": 25209, "loss": 0.3164, "lr": 2.7825482692487114e-05, "epoch": 2.6526240628347018, "percentage": 88.42, "elapsed_time": "1 day, 9:11:24", "remaining_time": "4:20:47", "throughput": 62492.38, "total_tokens": 7466844544} {"current_steps": 22300, "total_steps": 25209, "loss": 0.318, "lr": 2.7821174875407985e-05, "epoch": 2.6538141140069023, "percentage": 88.46, "elapsed_time": "1 day, 9:12:19", "remaining_time": "4:19:53", "throughput": 62492.31, "total_tokens": 7470307712} {"current_steps": 22310, "total_steps": 25209, "loss": 0.3178, "lr": 2.781686905846062e-05, "epoch": 2.6550041651791028, "percentage": 88.5, "elapsed_time": "1 day, 9:13:15", "remaining_time": "4:19:00", "throughput": 62492.2, "total_tokens": 7473778048} {"current_steps": 22320, "total_steps": 25209, "loss": 0.3186, "lr": 2.7812565240097716e-05, "epoch": 2.6561942163513033, "percentage": 88.54, "elapsed_time": "1 day, 9:14:09", "remaining_time": "4:18:06", "throughput": 62492.28, "total_tokens": 7477197312} {"current_steps": 22330, "total_steps": 25209, "loss": 0.3217, "lr": 2.7808263418773656e-05, "epoch": 2.6573842675235033, "percentage": 88.58, "elapsed_time": "1 day, 9:15:01", "remaining_time": "4:17:13", "throughput": 62493.26, "total_tokens": 7480523904} {"current_steps": 22340, "total_steps": 25209, "loss": 0.3174, "lr": 2.7803963592944482e-05, "epoch": 2.658574318695704, "percentage": 88.62, "elapsed_time": "1 day, 9:16:01", "remaining_time": "4:16:20", "throughput": 62489.54, "total_tokens": 7483853696} {"current_steps": 22350, "total_steps": 25209, "loss": 0.3191, "lr": 2.779966576106792e-05, "epoch": 2.6597643698679043, "percentage": 88.66, "elapsed_time": "1 day, 9:17:14", "remaining_time": "4:15:29", "throughput": 62479.81, "total_tokens": 7487208576} {"current_steps": 22360, "total_steps": 25209, "loss": 0.3186, "lr": 2.779536992160336e-05, "epoch": 2.660954421040105, "percentage": 88.7, "elapsed_time": "1 day, 9:18:48", "remaining_time": "4:14:40", "throughput": 62459.69, "total_tokens": 7490711168} {"current_steps": 22370, "total_steps": 25209, "loss": 0.3177, "lr": 2.7791076073011845e-05, "epoch": 2.6621444722123053, "percentage": 88.74, "elapsed_time": "1 day, 9:20:55", "remaining_time": "4:13:56", "throughput": 62421.35, "total_tokens": 7494044032} {"current_steps": 22380, "total_steps": 25209, "loss": 0.3221, "lr": 2.7786784213756102e-05, "epoch": 2.6633345233845054, "percentage": 88.78, "elapsed_time": "1 day, 9:22:23", "remaining_time": "4:13:07", "throughput": 62404.14, "total_tokens": 7497440000} {"current_steps": 22390, "total_steps": 25209, "loss": 0.3187, "lr": 2.7782494342300502e-05, "epoch": 2.664524574556706, "percentage": 88.82, "elapsed_time": "1 day, 9:23:18", "remaining_time": "4:12:13", "throughput": 62403.5, "total_tokens": 7500800128} {"current_steps": 22400, "total_steps": 25209, "loss": 0.3186, "lr": 2.777820645711109e-05, "epoch": 2.6657146257289064, "percentage": 88.86, "elapsed_time": "1 day, 9:24:11", "remaining_time": "4:11:19", "throughput": 62404.08, "total_tokens": 7504168320} {"current_steps": 22410, "total_steps": 25209, "loss": 0.3223, "lr": 2.777392055665556e-05, "epoch": 2.666904676901107, "percentage": 88.9, "elapsed_time": "1 day, 9:25:03", "remaining_time": "4:10:25", "throughput": 62404.64, "total_tokens": 7507480832} {"current_steps": 22420, "total_steps": 25209, "loss": 0.3234, "lr": 2.7769636639403252e-05, "epoch": 2.6680947280733074, "percentage": 88.94, "elapsed_time": "1 day, 9:25:54", "remaining_time": "4:09:31", "throughput": 62405.88, "total_tokens": 7510799360} {"current_steps": 22430, "total_steps": 25209, "loss": 0.3178, "lr": 2.776535470382518e-05, "epoch": 2.6692847792455074, "percentage": 88.98, "elapsed_time": "1 day, 9:26:47", "remaining_time": "4:08:38", "throughput": 62405.58, "total_tokens": 7514090752} {"current_steps": 22440, "total_steps": 25209, "loss": 0.3238, "lr": 2.776107474839399e-05, "epoch": 2.670474830417708, "percentage": 89.02, "elapsed_time": "1 day, 9:27:51", "remaining_time": "4:07:45", "throughput": 62400.24, "total_tokens": 7517438592} {"current_steps": 22450, "total_steps": 25209, "loss": 0.3203, "lr": 2.7756796771583976e-05, "epoch": 2.6716648815899084, "percentage": 89.06, "elapsed_time": "1 day, 9:28:59", "remaining_time": "4:06:53", "throughput": 62393.84, "total_tokens": 7520892672} {"current_steps": 22460, "total_steps": 25209, "loss": 0.3163, "lr": 2.775252077187109e-05, "epoch": 2.6728549327621085, "percentage": 89.1, "elapsed_time": "1 day, 9:30:11", "remaining_time": "4:06:02", "throughput": 62383.79, "total_tokens": 7524233088} {"current_steps": 22470, "total_steps": 25209, "loss": 0.3213, "lr": 2.7748246747732902e-05, "epoch": 2.6740449839343094, "percentage": 89.13, "elapsed_time": "1 day, 9:31:29", "remaining_time": "4:05:11", "throughput": 62370.95, "total_tokens": 7527524096} {"current_steps": 22480, "total_steps": 25209, "loss": 0.3204, "lr": 2.774397469764866e-05, "epoch": 2.6752350351065095, "percentage": 89.17, "elapsed_time": "1 day, 9:32:20", "remaining_time": "4:04:17", "throughput": 62372.17, "total_tokens": 7530863360} {"current_steps": 22490, "total_steps": 25209, "loss": 0.3221, "lr": 2.7739704620099226e-05, "epoch": 2.67642508627871, "percentage": 89.21, "elapsed_time": "1 day, 9:33:13", "remaining_time": "4:03:23", "throughput": 62372.41, "total_tokens": 7534186752} {"current_steps": 22500, "total_steps": 25209, "loss": 0.3218, "lr": 2.7735436513567098e-05, "epoch": 2.6776151374509105, "percentage": 89.25, "elapsed_time": "1 day, 9:34:03", "remaining_time": "4:02:29", "throughput": 62374.02, "total_tokens": 7537497728} {"current_steps": 22510, "total_steps": 25209, "loss": 0.3246, "lr": 2.7731170376536402e-05, "epoch": 2.6788051886231106, "percentage": 89.29, "elapsed_time": "1 day, 9:34:54", "remaining_time": "4:01:35", "throughput": 62375.18, "total_tokens": 7540806144} {"current_steps": 22520, "total_steps": 25209, "loss": 0.3188, "lr": 2.7726906207492925e-05, "epoch": 2.679995239795311, "percentage": 89.33, "elapsed_time": "1 day, 9:35:46", "remaining_time": "4:00:41", "throughput": 62375.8, "total_tokens": 7544164608} {"current_steps": 22530, "total_steps": 25209, "loss": 0.3187, "lr": 2.7722644004924048e-05, "epoch": 2.6811852909675116, "percentage": 89.37, "elapsed_time": "1 day, 9:36:34", "remaining_time": "3:59:47", "throughput": 62378.42, "total_tokens": 7547418752} {"current_steps": 22540, "total_steps": 25209, "loss": 0.3189, "lr": 2.77183837673188e-05, "epoch": 2.682375342139712, "percentage": 89.41, "elapsed_time": "1 day, 9:37:25", "remaining_time": "3:58:53", "throughput": 62379.93, "total_tokens": 7550782720} {"current_steps": 22550, "total_steps": 25209, "loss": 0.3234, "lr": 2.7714125493167835e-05, "epoch": 2.6835653933119126, "percentage": 89.45, "elapsed_time": "1 day, 9:38:17", "remaining_time": "3:57:59", "throughput": 62381.12, "total_tokens": 7554167168} {"current_steps": 22560, "total_steps": 25209, "loss": 0.3234, "lr": 2.770986918096342e-05, "epoch": 2.6847554444841126, "percentage": 89.49, "elapsed_time": "1 day, 9:39:12", "remaining_time": "3:57:05", "throughput": 62381.12, "total_tokens": 7557616768} {"current_steps": 22570, "total_steps": 25209, "loss": 0.3203, "lr": 2.7705614829199454e-05, "epoch": 2.685945495656313, "percentage": 89.53, "elapsed_time": "1 day, 9:40:04", "remaining_time": "3:56:11", "throughput": 62381.58, "total_tokens": 7560949120} {"current_steps": 22580, "total_steps": 25209, "loss": 0.3239, "lr": 2.7701362436371437e-05, "epoch": 2.6871355468285136, "percentage": 89.57, "elapsed_time": "1 day, 9:40:56", "remaining_time": "3:55:17", "throughput": 62382.28, "total_tokens": 7564275072} {"current_steps": 22590, "total_steps": 25209, "loss": 0.3221, "lr": 2.7697112000976492e-05, "epoch": 2.688325598000714, "percentage": 89.61, "elapsed_time": "1 day, 9:41:52", "remaining_time": "3:54:24", "throughput": 62380.66, "total_tokens": 7567578240} {"current_steps": 22600, "total_steps": 25209, "loss": 0.3191, "lr": 2.769286352151338e-05, "epoch": 2.6895156491729146, "percentage": 89.65, "elapsed_time": "1 day, 9:42:47", "remaining_time": "3:53:30", "throughput": 62380.66, "total_tokens": 7570969344} {"current_steps": 22610, "total_steps": 25209, "loss": 0.3202, "lr": 2.768861699648243e-05, "epoch": 2.6907057003451147, "percentage": 89.69, "elapsed_time": "1 day, 9:44:09", "remaining_time": "3:52:40", "throughput": 62366.58, "total_tokens": 7574392192} {"current_steps": 22620, "total_steps": 25209, "loss": 0.3185, "lr": 2.7684372424385613e-05, "epoch": 2.691895751517315, "percentage": 89.73, "elapsed_time": "1 day, 9:45:26", "remaining_time": "3:51:49", "throughput": 62353.57, "total_tokens": 7577622016} {"current_steps": 22630, "total_steps": 25209, "loss": 0.3177, "lr": 2.7680129803726496e-05, "epoch": 2.6930858026895157, "percentage": 89.77, "elapsed_time": "1 day, 9:46:42", "remaining_time": "3:50:58", "throughput": 62342.55, "total_tokens": 7580987520} {"current_steps": 22640, "total_steps": 25209, "loss": 0.3165, "lr": 2.767588913301025e-05, "epoch": 2.694275853861716, "percentage": 89.81, "elapsed_time": "1 day, 9:47:38", "remaining_time": "3:50:04", "throughput": 62340.57, "total_tokens": 7584271488} {"current_steps": 22650, "total_steps": 25209, "loss": 0.3197, "lr": 2.767165041074365e-05, "epoch": 2.6954659050339167, "percentage": 89.85, "elapsed_time": "1 day, 9:48:25", "remaining_time": "3:49:10", "throughput": 62343.22, "total_tokens": 7587521280} {"current_steps": 22660, "total_steps": 25209, "loss": 0.3187, "lr": 2.766741363543507e-05, "epoch": 2.6966559562061168, "percentage": 89.89, "elapsed_time": "1 day, 9:49:18", "remaining_time": "3:48:16", "throughput": 62343.57, "total_tokens": 7590855552} {"current_steps": 22670, "total_steps": 25209, "loss": 0.3177, "lr": 2.7663178805594482e-05, "epoch": 2.6978460073783173, "percentage": 89.93, "elapsed_time": "1 day, 9:50:06", "remaining_time": "3:47:22", "throughput": 62346.09, "total_tokens": 7594172928} {"current_steps": 22680, "total_steps": 25209, "loss": 0.3211, "lr": 2.7658945919733463e-05, "epoch": 2.6990360585505178, "percentage": 89.97, "elapsed_time": "1 day, 9:51:07", "remaining_time": "3:46:29", "throughput": 62342.58, "total_tokens": 7597539072} {"current_steps": 22690, "total_steps": 25209, "loss": 0.3191, "lr": 2.7654714976365164e-05, "epoch": 2.700226109722718, "percentage": 90.01, "elapsed_time": "1 day, 9:51:59", "remaining_time": "3:45:35", "throughput": 62343.39, "total_tokens": 7600873728} {"current_steps": 22700, "total_steps": 25209, "loss": 0.323, "lr": 2.765048597400436e-05, "epoch": 2.7014161608949183, "percentage": 90.05, "elapsed_time": "1 day, 9:52:57", "remaining_time": "3:44:42", "throughput": 62341.31, "total_tokens": 7604261760} {"current_steps": 22710, "total_steps": 25209, "loss": 0.3217, "lr": 2.7646258911167373e-05, "epoch": 2.702606212067119, "percentage": 90.09, "elapsed_time": "1 day, 9:54:06", "remaining_time": "3:43:50", "throughput": 62333.34, "total_tokens": 7607593984} {"current_steps": 22720, "total_steps": 25209, "loss": 0.3194, "lr": 2.7642033786372145e-05, "epoch": 2.7037962632393193, "percentage": 90.13, "elapsed_time": "1 day, 9:55:10", "remaining_time": "3:42:57", "throughput": 62327.93, "total_tokens": 7610918400} {"current_steps": 22730, "total_steps": 25209, "loss": 0.3171, "lr": 2.7637810598138193e-05, "epoch": 2.70498631441152, "percentage": 90.17, "elapsed_time": "1 day, 9:56:26", "remaining_time": "3:42:06", "throughput": 62316.45, "total_tokens": 7614230784} {"current_steps": 22740, "total_steps": 25209, "loss": 0.3207, "lr": 2.7633589344986615e-05, "epoch": 2.70617636558372, "percentage": 90.21, "elapsed_time": "1 day, 9:57:31", "remaining_time": "3:41:13", "throughput": 62312.03, "total_tokens": 7617708928} {"current_steps": 22750, "total_steps": 25209, "loss": 0.3227, "lr": 2.7629370025440087e-05, "epoch": 2.7073664167559204, "percentage": 90.25, "elapsed_time": "1 day, 9:58:20", "remaining_time": "3:40:19", "throughput": 62313.87, "total_tokens": 7621022848} {"current_steps": 22760, "total_steps": 25209, "loss": 0.3184, "lr": 2.762515263802287e-05, "epoch": 2.708556467928121, "percentage": 90.29, "elapsed_time": "1 day, 9:59:11", "remaining_time": "3:39:25", "throughput": 62315.5, "total_tokens": 7624378240} {"current_steps": 22770, "total_steps": 25209, "loss": 0.3176, "lr": 2.762093718126081e-05, "epoch": 2.7097465191003214, "percentage": 90.32, "elapsed_time": "1 day, 10:00:05", "remaining_time": "3:38:31", "throughput": 62314.83, "total_tokens": 7627691264} {"current_steps": 22780, "total_steps": 25209, "loss": 0.3212, "lr": 2.7616723653681298e-05, "epoch": 2.710936570272522, "percentage": 90.36, "elapsed_time": "1 day, 10:01:02", "remaining_time": "3:37:38", "throughput": 62312.95, "total_tokens": 7631028352} {"current_steps": 22790, "total_steps": 25209, "loss": 0.3217, "lr": 2.761251205381332e-05, "epoch": 2.712126621444722, "percentage": 90.4, "elapsed_time": "1 day, 10:01:59", "remaining_time": "3:36:44", "throughput": 62311.96, "total_tokens": 7634419584} {"current_steps": 22800, "total_steps": 25209, "loss": 0.3206, "lr": 2.760830238018744e-05, "epoch": 2.7133166726169224, "percentage": 90.44, "elapsed_time": "1 day, 10:02:54", "remaining_time": "3:35:51", "throughput": 62311.64, "total_tokens": 7637842816} {"current_steps": 22810, "total_steps": 25209, "loss": 0.3162, "lr": 2.760409463133576e-05, "epoch": 2.714506723789123, "percentage": 90.48, "elapsed_time": "1 day, 10:03:44", "remaining_time": "3:34:56", "throughput": 62312.99, "total_tokens": 7641099264} {"current_steps": 22820, "total_steps": 25209, "loss": 0.3202, "lr": 2.7599888805791967e-05, "epoch": 2.7156967749613234, "percentage": 90.52, "elapsed_time": "1 day, 10:04:34", "remaining_time": "3:34:02", "throughput": 62315.12, "total_tokens": 7644488320} {"current_steps": 22830, "total_steps": 25209, "loss": 0.3192, "lr": 2.759568490209132e-05, "epoch": 2.716886826133524, "percentage": 90.56, "elapsed_time": "1 day, 10:05:27", "remaining_time": "3:33:08", "throughput": 62316.11, "total_tokens": 7647869312} {"current_steps": 22840, "total_steps": 25209, "loss": 0.3209, "lr": 2.7591482918770613e-05, "epoch": 2.718076877305724, "percentage": 90.6, "elapsed_time": "1 day, 10:06:21", "remaining_time": "3:32:15", "throughput": 62316.16, "total_tokens": 7651271552} {"current_steps": 22850, "total_steps": 25209, "loss": 0.3188, "lr": 2.7587282854368222e-05, "epoch": 2.7192669284779245, "percentage": 90.64, "elapsed_time": "1 day, 10:07:09", "remaining_time": "3:31:20", "throughput": 62318.53, "total_tokens": 7654581760} {"current_steps": 22860, "total_steps": 25209, "loss": 0.3229, "lr": 2.7583084707424072e-05, "epoch": 2.720456979650125, "percentage": 90.68, "elapsed_time": "1 day, 10:08:13", "remaining_time": "3:30:28", "throughput": 62313.62, "total_tokens": 7657926912} {"current_steps": 22870, "total_steps": 25209, "loss": 0.3218, "lr": 2.7578888476479643e-05, "epoch": 2.7216470308223255, "percentage": 90.72, "elapsed_time": "1 day, 10:09:18", "remaining_time": "3:29:35", "throughput": 62307.1, "total_tokens": 7661187072} {"current_steps": 22880, "total_steps": 25209, "loss": 0.3199, "lr": 2.7574694160077964e-05, "epoch": 2.722837081994526, "percentage": 90.76, "elapsed_time": "1 day, 10:10:46", "remaining_time": "3:28:45", "throughput": 62289.87, "total_tokens": 7664524672} {"current_steps": 22890, "total_steps": 25209, "loss": 0.3213, "lr": 2.757050175676362e-05, "epoch": 2.724027133166726, "percentage": 90.8, "elapsed_time": "1 day, 10:12:03", "remaining_time": "3:27:53", "throughput": 62277.99, "total_tokens": 7667914240} {"current_steps": 22900, "total_steps": 25209, "loss": 0.3191, "lr": 2.756631126508274e-05, "epoch": 2.7252171843389266, "percentage": 90.84, "elapsed_time": "1 day, 10:12:58", "remaining_time": "3:27:00", "throughput": 62277.68, "total_tokens": 7671252736} {"current_steps": 22910, "total_steps": 25209, "loss": 0.3195, "lr": 2.7562122683583004e-05, "epoch": 2.726407235511127, "percentage": 90.88, "elapsed_time": "1 day, 10:13:48", "remaining_time": "3:26:05", "throughput": 62278.97, "total_tokens": 7674538624} {"current_steps": 22920, "total_steps": 25209, "loss": 0.317, "lr": 2.7557936010813634e-05, "epoch": 2.727597286683327, "percentage": 90.92, "elapsed_time": "1 day, 10:14:38", "remaining_time": "3:25:11", "throughput": 62280.96, "total_tokens": 7677893888} {"current_steps": 22930, "total_steps": 25209, "loss": 0.3198, "lr": 2.75537512453254e-05, "epoch": 2.7287873378555276, "percentage": 90.96, "elapsed_time": "1 day, 10:15:28", "remaining_time": "3:24:17", "throughput": 62282.85, "total_tokens": 7681245952} {"current_steps": 22940, "total_steps": 25209, "loss": 0.3195, "lr": 2.7549568385670595e-05, "epoch": 2.729977389027728, "percentage": 91.0, "elapsed_time": "1 day, 10:16:19", "remaining_time": "3:23:23", "throughput": 62284.61, "total_tokens": 7684649088} {"current_steps": 22950, "total_steps": 25209, "loss": 0.321, "lr": 2.754538743040307e-05, "epoch": 2.7311674401999286, "percentage": 91.04, "elapsed_time": "1 day, 10:17:11", "remaining_time": "3:22:29", "throughput": 62286.06, "total_tokens": 7688048128} {"current_steps": 22960, "total_steps": 25209, "loss": 0.32, "lr": 2.75412083780782e-05, "epoch": 2.732357491372129, "percentage": 91.08, "elapsed_time": "1 day, 10:18:02", "remaining_time": "3:21:35", "throughput": 62287.21, "total_tokens": 7691376256} {"current_steps": 22970, "total_steps": 25209, "loss": 0.324, "lr": 2.7537031227252898e-05, "epoch": 2.733547542544329, "percentage": 91.12, "elapsed_time": "1 day, 10:19:05", "remaining_time": "3:20:42", "throughput": 62281.76, "total_tokens": 7694658432} {"current_steps": 22980, "total_steps": 25209, "loss": 0.3194, "lr": 2.75328559764856e-05, "epoch": 2.7347375937165297, "percentage": 91.16, "elapsed_time": "1 day, 10:20:06", "remaining_time": "3:19:49", "throughput": 62278.85, "total_tokens": 7698050688} {"current_steps": 22990, "total_steps": 25209, "loss": 0.3184, "lr": 2.752868262433629e-05, "epoch": 2.73592764488873, "percentage": 91.2, "elapsed_time": "1 day, 10:21:08", "remaining_time": "3:18:56", "throughput": 62274.98, "total_tokens": 7701463424} {"current_steps": 23000, "total_steps": 25209, "loss": 0.3193, "lr": 2.752451116936646e-05, "epoch": 2.7371176960609307, "percentage": 91.24, "elapsed_time": "1 day, 10:22:21", "remaining_time": "3:18:04", "throughput": 62265.65, "total_tokens": 7704825216} {"current_steps": 23010, "total_steps": 25209, "loss": 0.3224, "lr": 2.752034161013915e-05, "epoch": 2.738307747233131, "percentage": 91.28, "elapsed_time": "1 day, 10:23:18", "remaining_time": "3:17:11", "throughput": 62263.68, "total_tokens": 7708132352} {"current_steps": 23020, "total_steps": 25209, "loss": 0.3176, "lr": 2.7516173945218888e-05, "epoch": 2.7394977984053313, "percentage": 91.32, "elapsed_time": "1 day, 10:24:08", "remaining_time": "3:16:16", "throughput": 62265.7, "total_tokens": 7711494144} {"current_steps": 23030, "total_steps": 25209, "loss": 0.3227, "lr": 2.751200817317176e-05, "epoch": 2.7406878495775318, "percentage": 91.36, "elapsed_time": "1 day, 10:24:59", "remaining_time": "3:15:22", "throughput": 62267.4, "total_tokens": 7714902144} {"current_steps": 23040, "total_steps": 25209, "loss": 0.3197, "lr": 2.7507844292565354e-05, "epoch": 2.7418779007497323, "percentage": 91.4, "elapsed_time": "1 day, 10:25:51", "remaining_time": "3:14:28", "throughput": 62268.48, "total_tokens": 7718246400} {"current_steps": 23050, "total_steps": 25209, "loss": 0.3189, "lr": 2.7503682301968763e-05, "epoch": 2.7430679519219328, "percentage": 91.44, "elapsed_time": "1 day, 10:26:44", "remaining_time": "3:13:34", "throughput": 62269.43, "total_tokens": 7721680896} {"current_steps": 23060, "total_steps": 25209, "loss": 0.3212, "lr": 2.7499522199952627e-05, "epoch": 2.7442580030941333, "percentage": 91.48, "elapsed_time": "1 day, 10:27:36", "remaining_time": "3:12:41", "throughput": 62270.72, "total_tokens": 7725093376} {"current_steps": 23070, "total_steps": 25209, "loss": 0.3183, "lr": 2.7495363985089072e-05, "epoch": 2.7454480542663333, "percentage": 91.51, "elapsed_time": "1 day, 10:28:29", "remaining_time": "3:11:47", "throughput": 62272.11, "total_tokens": 7728539008} {"current_steps": 23080, "total_steps": 25209, "loss": 0.3167, "lr": 2.7491207655951745e-05, "epoch": 2.746638105438534, "percentage": 91.55, "elapsed_time": "1 day, 10:29:21", "remaining_time": "3:10:53", "throughput": 62273.3, "total_tokens": 7731919232} {"current_steps": 23090, "total_steps": 25209, "loss": 0.3191, "lr": 2.7487053211115797e-05, "epoch": 2.7478281566107343, "percentage": 91.59, "elapsed_time": "1 day, 10:30:12", "remaining_time": "3:09:59", "throughput": 62274.98, "total_tokens": 7735313920} {"current_steps": 23100, "total_steps": 25209, "loss": 0.3148, "lr": 2.748290064915789e-05, "epoch": 2.749018207782935, "percentage": 91.63, "elapsed_time": "1 day, 10:30:59", "remaining_time": "3:09:04", "throughput": 62276.93, "total_tokens": 7738521472} {"current_steps": 23110, "total_steps": 25209, "loss": 0.3218, "lr": 2.747874996865619e-05, "epoch": 2.7502082589551353, "percentage": 91.67, "elapsed_time": "1 day, 10:31:50", "remaining_time": "3:08:10", "throughput": 62278.16, "total_tokens": 7741846784} {"current_steps": 23120, "total_steps": 25209, "loss": 0.318, "lr": 2.747460116819037e-05, "epoch": 2.7513983101273354, "percentage": 91.71, "elapsed_time": "1 day, 10:32:42", "remaining_time": "3:07:16", "throughput": 62279.1, "total_tokens": 7745169152} {"current_steps": 23130, "total_steps": 25209, "loss": 0.3195, "lr": 2.7470454246341597e-05, "epoch": 2.752588361299536, "percentage": 91.75, "elapsed_time": "1 day, 10:33:42", "remaining_time": "3:06:23", "throughput": 62276.72, "total_tokens": 7748608256} {"current_steps": 23140, "total_steps": 25209, "loss": 0.3201, "lr": 2.746630920169254e-05, "epoch": 2.7537784124717364, "percentage": 91.79, "elapsed_time": "1 day, 10:34:41", "remaining_time": "3:05:30", "throughput": 62274.06, "total_tokens": 7751997568} {"current_steps": 23150, "total_steps": 25209, "loss": 0.3168, "lr": 2.7462166032827358e-05, "epoch": 2.7549684636439364, "percentage": 91.83, "elapsed_time": "1 day, 10:35:56", "remaining_time": "3:04:38", "throughput": 62263.54, "total_tokens": 7755344768} {"current_steps": 23160, "total_steps": 25209, "loss": 0.3141, "lr": 2.745802473833171e-05, "epoch": 2.756158514816137, "percentage": 91.87, "elapsed_time": "1 day, 10:37:18", "remaining_time": "3:03:46", "throughput": 62250.33, "total_tokens": 7758770176} {"current_steps": 23170, "total_steps": 25209, "loss": 0.3207, "lr": 2.7453885316792755e-05, "epoch": 2.7573485659883374, "percentage": 91.91, "elapsed_time": "1 day, 10:38:19", "remaining_time": "3:02:53", "throughput": 62246.87, "total_tokens": 7762150272} {"current_steps": 23180, "total_steps": 25209, "loss": 0.3183, "lr": 2.7449747766799135e-05, "epoch": 2.758538617160538, "percentage": 91.95, "elapsed_time": "1 day, 10:39:12", "remaining_time": "3:01:59", "throughput": 62246.75, "total_tokens": 7765459968} {"current_steps": 23190, "total_steps": 25209, "loss": 0.3223, "lr": 2.744561208694097e-05, "epoch": 2.7597286683327384, "percentage": 91.99, "elapsed_time": "1 day, 10:40:11", "remaining_time": "3:01:06", "throughput": 62245.4, "total_tokens": 7768944512} {"current_steps": 23200, "total_steps": 25209, "loss": 0.3168, "lr": 2.7441478275809884e-05, "epoch": 2.7609187195049385, "percentage": 92.03, "elapsed_time": "1 day, 10:41:14", "remaining_time": "3:00:13", "throughput": 62240.72, "total_tokens": 7772254592} {"current_steps": 23210, "total_steps": 25209, "loss": 0.3175, "lr": 2.743734633199898e-05, "epoch": 2.762108770677139, "percentage": 92.07, "elapsed_time": "1 day, 10:42:16", "remaining_time": "2:59:20", "throughput": 62236.8, "total_tokens": 7775627136} {"current_steps": 23220, "total_steps": 25209, "loss": 0.3183, "lr": 2.743321625410284e-05, "epoch": 2.7632988218493395, "percentage": 92.11, "elapsed_time": "1 day, 10:43:18", "remaining_time": "2:58:27", "throughput": 62232.05, "total_tokens": 7778923264} {"current_steps": 23230, "total_steps": 25209, "loss": 0.3216, "lr": 2.7429088040717526e-05, "epoch": 2.76448887302154, "percentage": 92.15, "elapsed_time": "1 day, 10:44:11", "remaining_time": "2:57:33", "throughput": 62232.62, "total_tokens": 7782253312} {"current_steps": 23240, "total_steps": 25209, "loss": 0.3155, "lr": 2.7424961690440586e-05, "epoch": 2.7656789241937405, "percentage": 92.19, "elapsed_time": "1 day, 10:45:27", "remaining_time": "2:56:41", "throughput": 62222.71, "total_tokens": 7785751168} {"current_steps": 23250, "total_steps": 25209, "loss": 0.321, "lr": 2.742083720187103e-05, "epoch": 2.7668689753659406, "percentage": 92.23, "elapsed_time": "1 day, 10:46:41", "remaining_time": "2:55:49", "throughput": 62212.23, "total_tokens": 7789092480} {"current_steps": 23260, "total_steps": 25209, "loss": 0.3191, "lr": 2.7416714573609363e-05, "epoch": 2.768059026538141, "percentage": 92.27, "elapsed_time": "1 day, 10:48:04", "remaining_time": "2:54:57", "throughput": 62197.93, "total_tokens": 7792428800} {"current_steps": 23270, "total_steps": 25209, "loss": 0.3217, "lr": 2.7412593804257543e-05, "epoch": 2.7692490777103416, "percentage": 92.31, "elapsed_time": "1 day, 10:49:07", "remaining_time": "2:54:04", "throughput": 62193.21, "total_tokens": 7795762048} {"current_steps": 23280, "total_steps": 25209, "loss": 0.315, "lr": 2.740847489241901e-05, "epoch": 2.770439128882542, "percentage": 92.35, "elapsed_time": "1 day, 10:50:04", "remaining_time": "2:53:11", "throughput": 62192.48, "total_tokens": 7799214976} {"current_steps": 23290, "total_steps": 25209, "loss": 0.3223, "lr": 2.7404357836698668e-05, "epoch": 2.7716291800547426, "percentage": 92.39, "elapsed_time": "1 day, 10:50:58", "remaining_time": "2:52:17", "throughput": 62192.43, "total_tokens": 7802565376} {"current_steps": 23300, "total_steps": 25209, "loss": 0.3225, "lr": 2.740024263570289e-05, "epoch": 2.7728192312269426, "percentage": 92.43, "elapsed_time": "1 day, 10:51:52", "remaining_time": "2:51:23", "throughput": 62192.71, "total_tokens": 7805974272} {"current_steps": 23310, "total_steps": 25209, "loss": 0.323, "lr": 2.7396129288039503e-05, "epoch": 2.774009282399143, "percentage": 92.47, "elapsed_time": "1 day, 10:52:41", "remaining_time": "2:50:29", "throughput": 62194.66, "total_tokens": 7809264256} {"current_steps": 23320, "total_steps": 25209, "loss": 0.3195, "lr": 2.739201779231782e-05, "epoch": 2.7751993335713436, "percentage": 92.51, "elapsed_time": "1 day, 10:53:32", "remaining_time": "2:49:35", "throughput": 62196.89, "total_tokens": 7812689280} {"current_steps": 23330, "total_steps": 25209, "loss": 0.3192, "lr": 2.7387908147148587e-05, "epoch": 2.776389384743544, "percentage": 92.55, "elapsed_time": "1 day, 10:54:25", "remaining_time": "2:48:41", "throughput": 62197.67, "total_tokens": 7816101760} {"current_steps": 23340, "total_steps": 25209, "loss": 0.3166, "lr": 2.7383800351144027e-05, "epoch": 2.7775794359157446, "percentage": 92.59, "elapsed_time": "1 day, 10:55:14", "remaining_time": "2:47:46", "throughput": 62200.19, "total_tokens": 7819453952} {"current_steps": 23350, "total_steps": 25209, "loss": 0.3139, "lr": 2.737969440291782e-05, "epoch": 2.7787694870879447, "percentage": 92.63, "elapsed_time": "1 day, 10:56:04", "remaining_time": "2:46:52", "throughput": 62202.24, "total_tokens": 7822834432} {"current_steps": 23360, "total_steps": 25209, "loss": 0.3183, "lr": 2.7375590301085087e-05, "epoch": 2.779959538260145, "percentage": 92.67, "elapsed_time": "1 day, 10:56:57", "remaining_time": "2:45:58", "throughput": 62202.87, "total_tokens": 7826239104} {"current_steps": 23370, "total_steps": 25209, "loss": 0.3192, "lr": 2.7371488044262406e-05, "epoch": 2.7811495894323457, "percentage": 92.7, "elapsed_time": "1 day, 10:57:46", "remaining_time": "2:45:04", "throughput": 62205.23, "total_tokens": 7829525632} {"current_steps": 23380, "total_steps": 25209, "loss": 0.3217, "lr": 2.7367387631067816e-05, "epoch": 2.7823396406045457, "percentage": 92.74, "elapsed_time": "1 day, 10:58:34", "remaining_time": "2:44:10", "throughput": 62206.68, "total_tokens": 7832748928} {"current_steps": 23390, "total_steps": 25209, "loss": 0.3213, "lr": 2.73632890601208e-05, "epoch": 2.7835296917767463, "percentage": 92.78, "elapsed_time": "1 day, 10:59:30", "remaining_time": "2:43:16", "throughput": 62205.21, "total_tokens": 7836020736} {"current_steps": 23400, "total_steps": 25209, "loss": 0.3195, "lr": 2.7359192330042277e-05, "epoch": 2.7847197429489468, "percentage": 92.82, "elapsed_time": "1 day, 11:00:33", "remaining_time": "2:42:23", "throughput": 62200.95, "total_tokens": 7839383296} {"current_steps": 23410, "total_steps": 25209, "loss": 0.3187, "lr": 2.7355097439454625e-05, "epoch": 2.7859097941211473, "percentage": 92.86, "elapsed_time": "1 day, 11:01:47", "remaining_time": "2:41:31", "throughput": 62191.18, "total_tokens": 7842770304} {"current_steps": 23420, "total_steps": 25209, "loss": 0.3206, "lr": 2.735100438698166e-05, "epoch": 2.7870998452933478, "percentage": 92.9, "elapsed_time": "1 day, 11:03:04", "remaining_time": "2:40:38", "throughput": 62180.25, "total_tokens": 7846153344} {"current_steps": 23430, "total_steps": 25209, "loss": 0.3183, "lr": 2.7346913171248635e-05, "epoch": 2.788289896465548, "percentage": 92.94, "elapsed_time": "1 day, 11:04:11", "remaining_time": "2:39:46", "throughput": 62173.82, "total_tokens": 7849513856} {"current_steps": 23440, "total_steps": 25209, "loss": 0.32, "lr": 2.734282379088225e-05, "epoch": 2.7894799476377483, "percentage": 92.98, "elapsed_time": "1 day, 11:05:03", "remaining_time": "2:38:52", "throughput": 62173.89, "total_tokens": 7852757120} {"current_steps": 23450, "total_steps": 25209, "loss": 0.3199, "lr": 2.733873624451063e-05, "epoch": 2.790669998809949, "percentage": 93.02, "elapsed_time": "1 day, 11:05:52", "remaining_time": "2:37:57", "throughput": 62175.98, "total_tokens": 7856061568} {"current_steps": 23460, "total_steps": 25209, "loss": 0.3171, "lr": 2.733465053076335e-05, "epoch": 2.7918600499821493, "percentage": 93.06, "elapsed_time": "1 day, 11:06:44", "remaining_time": "2:37:03", "throughput": 62176.57, "total_tokens": 7859381632} {"current_steps": 23470, "total_steps": 25209, "loss": 0.3181, "lr": 2.733056664827141e-05, "epoch": 2.79305010115435, "percentage": 93.1, "elapsed_time": "1 day, 11:07:37", "remaining_time": "2:36:09", "throughput": 62177.58, "total_tokens": 7862794112} {"current_steps": 23480, "total_steps": 25209, "loss": 0.3198, "lr": 2.732648459566724e-05, "epoch": 2.79424015232655, "percentage": 93.14, "elapsed_time": "1 day, 11:08:27", "remaining_time": "2:35:15", "throughput": 62179.39, "total_tokens": 7866152704} {"current_steps": 23490, "total_steps": 25209, "loss": 0.3155, "lr": 2.73224043715847e-05, "epoch": 2.7954302034987504, "percentage": 93.18, "elapsed_time": "1 day, 11:09:16", "remaining_time": "2:34:21", "throughput": 62182.09, "total_tokens": 7869522688} {"current_steps": 23500, "total_steps": 25209, "loss": 0.3202, "lr": 2.731832597465908e-05, "epoch": 2.796620254670951, "percentage": 93.22, "elapsed_time": "1 day, 11:10:07", "remaining_time": "2:33:27", "throughput": 62183.56, "total_tokens": 7872920832} {"current_steps": 23510, "total_steps": 25209, "loss": 0.3236, "lr": 2.7314249403527097e-05, "epoch": 2.7978103058431514, "percentage": 93.26, "elapsed_time": "1 day, 11:11:12", "remaining_time": "2:32:34", "throughput": 62178.8, "total_tokens": 7876338944} {"current_steps": 23520, "total_steps": 25209, "loss": 0.3141, "lr": 2.731017465682689e-05, "epoch": 2.799000357015352, "percentage": 93.3, "elapsed_time": "1 day, 11:12:15", "remaining_time": "2:31:41", "throughput": 62174.82, "total_tokens": 7879777664} {"current_steps": 23530, "total_steps": 25209, "loss": 0.319, "lr": 2.730610173319802e-05, "epoch": 2.800190408187552, "percentage": 93.34, "elapsed_time": "1 day, 11:13:20", "remaining_time": "2:30:47", "throughput": 62169.41, "total_tokens": 7883113344} {"current_steps": 23540, "total_steps": 25209, "loss": 0.3182, "lr": 2.7302030631281454e-05, "epoch": 2.8013804593597524, "percentage": 93.38, "elapsed_time": "1 day, 11:14:24", "remaining_time": "2:29:54", "throughput": 62164.18, "total_tokens": 7886407168} {"current_steps": 23550, "total_steps": 25209, "loss": 0.3214, "lr": 2.7297961349719608e-05, "epoch": 2.802570510531953, "percentage": 93.42, "elapsed_time": "1 day, 11:15:34", "remaining_time": "2:29:02", "throughput": 62156.46, "total_tokens": 7889791872} {"current_steps": 23560, "total_steps": 25209, "loss": 0.3176, "lr": 2.729389388715628e-05, "epoch": 2.8037605617041534, "percentage": 93.46, "elapsed_time": "1 day, 11:16:28", "remaining_time": "2:28:08", "throughput": 62156.79, "total_tokens": 7893179904} {"current_steps": 23570, "total_steps": 25209, "loss": 0.3206, "lr": 2.728982824223671e-05, "epoch": 2.804950612876354, "percentage": 93.5, "elapsed_time": "1 day, 11:17:16", "remaining_time": "2:27:13", "throughput": 62159.03, "total_tokens": 7896490880} {"current_steps": 23580, "total_steps": 25209, "loss": 0.3165, "lr": 2.7285764413607527e-05, "epoch": 2.806140664048554, "percentage": 93.54, "elapsed_time": "1 day, 11:18:03", "remaining_time": "2:26:19", "throughput": 62162.02, "total_tokens": 7899749760} {"current_steps": 23590, "total_steps": 25209, "loss": 0.322, "lr": 2.7281702399916786e-05, "epoch": 2.8073307152207545, "percentage": 93.58, "elapsed_time": "1 day, 11:18:51", "remaining_time": "2:25:25", "throughput": 62164.2, "total_tokens": 7902999168} {"current_steps": 23600, "total_steps": 25209, "loss": 0.3218, "lr": 2.7277642199813954e-05, "epoch": 2.808520766392955, "percentage": 93.62, "elapsed_time": "1 day, 11:19:39", "remaining_time": "2:24:30", "throughput": 62166.21, "total_tokens": 7906275200} {"current_steps": 23610, "total_steps": 25209, "loss": 0.3191, "lr": 2.7273583811949882e-05, "epoch": 2.809710817565155, "percentage": 93.66, "elapsed_time": "1 day, 11:20:27", "remaining_time": "2:23:36", "throughput": 62168.38, "total_tokens": 7909548928} {"current_steps": 23620, "total_steps": 25209, "loss": 0.3187, "lr": 2.7269527234976844e-05, "epoch": 2.8109008687373556, "percentage": 93.7, "elapsed_time": "1 day, 11:21:17", "remaining_time": "2:22:42", "throughput": 62170.06, "total_tokens": 7912861824} {"current_steps": 23630, "total_steps": 25209, "loss": 0.3182, "lr": 2.726547246754852e-05, "epoch": 2.812090919909556, "percentage": 93.74, "elapsed_time": "1 day, 11:22:16", "remaining_time": "2:21:48", "throughput": 62167.72, "total_tokens": 7916227968} {"current_steps": 23640, "total_steps": 25209, "loss": 0.3192, "lr": 2.726141950831998e-05, "epoch": 2.8132809710817566, "percentage": 93.78, "elapsed_time": "1 day, 11:23:09", "remaining_time": "2:20:54", "throughput": 62168.33, "total_tokens": 7919583872} {"current_steps": 23650, "total_steps": 25209, "loss": 0.3149, "lr": 2.7257368355947686e-05, "epoch": 2.814471022253957, "percentage": 93.82, "elapsed_time": "1 day, 11:24:10", "remaining_time": "2:20:01", "throughput": 62164.69, "total_tokens": 7922932864} {"current_steps": 23660, "total_steps": 25209, "loss": 0.3224, "lr": 2.7253319009089528e-05, "epoch": 2.815661073426157, "percentage": 93.86, "elapsed_time": "1 day, 11:25:10", "remaining_time": "2:19:08", "throughput": 62161.81, "total_tokens": 7926281216} {"current_steps": 23670, "total_steps": 25209, "loss": 0.3195, "lr": 2.7249271466404758e-05, "epoch": 2.8168511245983576, "percentage": 93.9, "elapsed_time": "1 day, 11:26:11", "remaining_time": "2:18:14", "throughput": 62158.3, "total_tokens": 7929646592} {"current_steps": 23680, "total_steps": 25209, "loss": 0.3192, "lr": 2.724522572655403e-05, "epoch": 2.818041175770558, "percentage": 93.93, "elapsed_time": "1 day, 11:27:23", "remaining_time": "2:17:21", "throughput": 62149.94, "total_tokens": 7933038592} {"current_steps": 23690, "total_steps": 25209, "loss": 0.321, "lr": 2.7241181788199405e-05, "epoch": 2.8192312269427586, "percentage": 93.97, "elapsed_time": "1 day, 11:28:34", "remaining_time": "2:16:29", "throughput": 62141.36, "total_tokens": 7936380032} {"current_steps": 23700, "total_steps": 25209, "loss": 0.3233, "lr": 2.7237139650004316e-05, "epoch": 2.820421278114959, "percentage": 94.01, "elapsed_time": "1 day, 11:29:39", "remaining_time": "2:15:35", "throughput": 62136.05, "total_tokens": 7939742464} {"current_steps": 23710, "total_steps": 25209, "loss": 0.3189, "lr": 2.7233099310633598e-05, "epoch": 2.821611329287159, "percentage": 94.05, "elapsed_time": "1 day, 11:30:29", "remaining_time": "2:14:41", "throughput": 62138.34, "total_tokens": 7943113984} {"current_steps": 23720, "total_steps": 25209, "loss": 0.3177, "lr": 2.722906076875345e-05, "epoch": 2.8228013804593597, "percentage": 94.09, "elapsed_time": "1 day, 11:31:20", "remaining_time": "2:13:47", "throughput": 62140.22, "total_tokens": 7946517504} {"current_steps": 23730, "total_steps": 25209, "loss": 0.3202, "lr": 2.7225024023031487e-05, "epoch": 2.82399143163156, "percentage": 94.13, "elapsed_time": "1 day, 11:32:11", "remaining_time": "2:12:53", "throughput": 62141.9, "total_tokens": 7949914112} {"current_steps": 23740, "total_steps": 25209, "loss": 0.3211, "lr": 2.7220989072136676e-05, "epoch": 2.8251814828037607, "percentage": 94.17, "elapsed_time": "1 day, 11:33:02", "remaining_time": "2:11:59", "throughput": 62143.5, "total_tokens": 7953302016} {"current_steps": 23750, "total_steps": 25209, "loss": 0.3148, "lr": 2.7216955914739385e-05, "epoch": 2.826371533975961, "percentage": 94.21, "elapsed_time": "1 day, 11:33:52", "remaining_time": "2:11:05", "throughput": 62145.34, "total_tokens": 7956612224} {"current_steps": 23760, "total_steps": 25209, "loss": 0.3214, "lr": 2.7212924549511348e-05, "epoch": 2.8275615851481612, "percentage": 94.25, "elapsed_time": "1 day, 11:34:41", "remaining_time": "2:10:11", "throughput": 62147.51, "total_tokens": 7959968896} {"current_steps": 23770, "total_steps": 25209, "loss": 0.3176, "lr": 2.7208894975125688e-05, "epoch": 2.8287516363203618, "percentage": 94.29, "elapsed_time": "1 day, 11:35:31", "remaining_time": "2:09:16", "throughput": 62149.89, "total_tokens": 7963329536} {"current_steps": 23780, "total_steps": 25209, "loss": 0.3139, "lr": 2.720486719025689e-05, "epoch": 2.8299416874925623, "percentage": 94.33, "elapsed_time": "1 day, 11:36:24", "remaining_time": "2:08:22", "throughput": 62151.37, "total_tokens": 7966828928} {"current_steps": 23790, "total_steps": 25209, "loss": 0.3201, "lr": 2.7200841193580816e-05, "epoch": 2.8311317386647623, "percentage": 94.37, "elapsed_time": "1 day, 11:37:19", "remaining_time": "2:07:29", "throughput": 62150.4, "total_tokens": 7970141056} {"current_steps": 23800, "total_steps": 25209, "loss": 0.3143, "lr": 2.7196816983774708e-05, "epoch": 2.8323217898369633, "percentage": 94.41, "elapsed_time": "1 day, 11:38:22", "remaining_time": "2:06:35", "throughput": 62147.06, "total_tokens": 7973600640} {"current_steps": 23810, "total_steps": 25209, "loss": 0.3236, "lr": 2.7192794559517166e-05, "epoch": 2.8335118410091633, "percentage": 94.45, "elapsed_time": "1 day, 11:39:22", "remaining_time": "2:05:42", "throughput": 62144.5, "total_tokens": 7977001600} {"current_steps": 23820, "total_steps": 25209, "loss": 0.3214, "lr": 2.7188773919488165e-05, "epoch": 2.834701892181364, "percentage": 94.49, "elapsed_time": "1 day, 11:40:31", "remaining_time": "2:04:49", "throughput": 62137.57, "total_tokens": 7980413696} {"current_steps": 23830, "total_steps": 25209, "loss": 0.3173, "lr": 2.7184755062369043e-05, "epoch": 2.8358919433535643, "percentage": 94.53, "elapsed_time": "1 day, 11:41:32", "remaining_time": "2:03:55", "throughput": 62133.64, "total_tokens": 7983707776} {"current_steps": 23840, "total_steps": 25209, "loss": 0.32, "lr": 2.7180737986842498e-05, "epoch": 2.8370819945257644, "percentage": 94.57, "elapsed_time": "1 day, 11:42:22", "remaining_time": "2:03:01", "throughput": 62134.5, "total_tokens": 7986921600} {"current_steps": 23850, "total_steps": 25209, "loss": 0.319, "lr": 2.71767226915926e-05, "epoch": 2.838272045697965, "percentage": 94.61, "elapsed_time": "1 day, 11:43:14", "remaining_time": "2:02:07", "throughput": 62135.64, "total_tokens": 7990308352} {"current_steps": 23860, "total_steps": 25209, "loss": 0.3188, "lr": 2.7172709175304767e-05, "epoch": 2.8394620968701654, "percentage": 94.65, "elapsed_time": "1 day, 11:44:05", "remaining_time": "2:01:13", "throughput": 62137.21, "total_tokens": 7993644672} {"current_steps": 23870, "total_steps": 25209, "loss": 0.318, "lr": 2.716869743666579e-05, "epoch": 2.840652148042366, "percentage": 94.69, "elapsed_time": "1 day, 11:44:54", "remaining_time": "2:00:19", "throughput": 62139.26, "total_tokens": 7996996736} {"current_steps": 23880, "total_steps": 25209, "loss": 0.3194, "lr": 2.7164687474363803e-05, "epoch": 2.8418421992145664, "percentage": 94.73, "elapsed_time": "1 day, 11:45:44", "remaining_time": "1:59:25", "throughput": 62140.62, "total_tokens": 8000292992} {"current_steps": 23890, "total_steps": 25209, "loss": 0.3209, "lr": 2.7160679287088307e-05, "epoch": 2.8430322503867664, "percentage": 94.77, "elapsed_time": "1 day, 11:46:35", "remaining_time": "1:58:30", "throughput": 62143.18, "total_tokens": 8003732608} {"current_steps": 23900, "total_steps": 25209, "loss": 0.3236, "lr": 2.7156672873530147e-05, "epoch": 2.844222301558967, "percentage": 94.81, "elapsed_time": "1 day, 11:47:24", "remaining_time": "1:57:36", "throughput": 62144.81, "total_tokens": 8007028736} {"current_steps": 23910, "total_steps": 25209, "loss": 0.3196, "lr": 2.715266823238152e-05, "epoch": 2.8454123527311674, "percentage": 94.85, "elapsed_time": "1 day, 11:48:11", "remaining_time": "1:56:42", "throughput": 62147.91, "total_tokens": 8010348416} {"current_steps": 23920, "total_steps": 25209, "loss": 0.3196, "lr": 2.714866536233598e-05, "epoch": 2.846602403903368, "percentage": 94.89, "elapsed_time": "1 day, 11:49:00", "remaining_time": "1:55:48", "throughput": 62150.2, "total_tokens": 8013689472} {"current_steps": 23930, "total_steps": 25209, "loss": 0.3199, "lr": 2.7144664262088422e-05, "epoch": 2.8477924550755684, "percentage": 94.93, "elapsed_time": "1 day, 11:49:50", "remaining_time": "1:54:54", "throughput": 62152.01, "total_tokens": 8017043328} {"current_steps": 23940, "total_steps": 25209, "loss": 0.3209, "lr": 2.7140664930335084e-05, "epoch": 2.8489825062477685, "percentage": 94.97, "elapsed_time": "1 day, 11:50:52", "remaining_time": "1:54:00", "throughput": 62148.91, "total_tokens": 8020476288} {"current_steps": 23950, "total_steps": 25209, "loss": 0.3192, "lr": 2.713666736577356e-05, "epoch": 2.850172557419969, "percentage": 95.01, "elapsed_time": "1 day, 11:51:45", "remaining_time": "1:53:06", "throughput": 62149.52, "total_tokens": 8023835648} {"current_steps": 23960, "total_steps": 25209, "loss": 0.3197, "lr": 2.713267156710278e-05, "epoch": 2.8513626085921695, "percentage": 95.05, "elapsed_time": "1 day, 11:52:52", "remaining_time": "1:52:13", "throughput": 62143.74, "total_tokens": 8027238144} {"current_steps": 23970, "total_steps": 25209, "loss": 0.3202, "lr": 2.712867753302301e-05, "epoch": 2.85255265976437, "percentage": 95.09, "elapsed_time": "1 day, 11:54:05", "remaining_time": "1:51:20", "throughput": 62134.22, "total_tokens": 8030563968} {"current_steps": 23980, "total_steps": 25209, "loss": 0.3183, "lr": 2.7124685262235865e-05, "epoch": 2.8537427109365705, "percentage": 95.12, "elapsed_time": "1 day, 11:55:16", "remaining_time": "1:50:27", "throughput": 62126.0, "total_tokens": 8033920896} {"current_steps": 23990, "total_steps": 25209, "loss": 0.32, "lr": 2.7120694753444287e-05, "epoch": 2.8549327621087706, "percentage": 95.16, "elapsed_time": "1 day, 11:56:12", "remaining_time": "1:49:33", "throughput": 62124.69, "total_tokens": 8037196032} {"current_steps": 24000, "total_steps": 25209, "loss": 0.3214, "lr": 2.7116706005352547e-05, "epoch": 2.856122813280971, "percentage": 95.2, "elapsed_time": "1 day, 11:57:01", "remaining_time": "1:48:39", "throughput": 62126.09, "total_tokens": 8040468352} {"current_steps": 24010, "total_steps": 25209, "loss": 0.3203, "lr": 2.7112719016666282e-05, "epoch": 2.8573128644531716, "percentage": 95.24, "elapsed_time": "1 day, 11:57:51", "remaining_time": "1:47:45", "throughput": 62127.91, "total_tokens": 8043810176} {"current_steps": 24020, "total_steps": 25209, "loss": 0.3226, "lr": 2.7108733786092427e-05, "epoch": 2.8585029156253716, "percentage": 95.28, "elapsed_time": "1 day, 11:58:48", "remaining_time": "1:46:51", "throughput": 62127.36, "total_tokens": 8047278848} {"current_steps": 24030, "total_steps": 25209, "loss": 0.3154, "lr": 2.7104750312339254e-05, "epoch": 2.8596929667975726, "percentage": 95.32, "elapsed_time": "1 day, 11:59:41", "remaining_time": "1:45:57", "throughput": 62128.18, "total_tokens": 8050688384} {"current_steps": 24040, "total_steps": 25209, "loss": 0.3212, "lr": 2.7100768594116382e-05, "epoch": 2.8608830179697726, "percentage": 95.36, "elapsed_time": "1 day, 12:00:29", "remaining_time": "1:45:03", "throughput": 62130.6, "total_tokens": 8053972096} {"current_steps": 24050, "total_steps": 25209, "loss": 0.318, "lr": 2.709678863013473e-05, "epoch": 2.862073069141973, "percentage": 95.4, "elapsed_time": "1 day, 12:01:17", "remaining_time": "1:44:09", "throughput": 62133.56, "total_tokens": 8057353856} {"current_steps": 24060, "total_steps": 25209, "loss": 0.3214, "lr": 2.7092810419106562e-05, "epoch": 2.8632631203141736, "percentage": 95.44, "elapsed_time": "1 day, 12:02:05", "remaining_time": "1:43:15", "throughput": 62136.24, "total_tokens": 8060635520} {"current_steps": 24070, "total_steps": 25209, "loss": 0.3204, "lr": 2.7088833959745457e-05, "epoch": 2.8644531714863737, "percentage": 95.48, "elapsed_time": "1 day, 12:02:55", "remaining_time": "1:42:21", "throughput": 62137.51, "total_tokens": 8063914496} {"current_steps": 24080, "total_steps": 25209, "loss": 0.3198, "lr": 2.708485925076631e-05, "epoch": 2.865643222658574, "percentage": 95.52, "elapsed_time": "1 day, 12:04:00", "remaining_time": "1:41:27", "throughput": 62132.1, "total_tokens": 8067265920} {"current_steps": 24090, "total_steps": 25209, "loss": 0.3235, "lr": 2.708088629088535e-05, "epoch": 2.8668332738307747, "percentage": 95.56, "elapsed_time": "1 day, 12:05:09", "remaining_time": "1:40:34", "throughput": 62124.79, "total_tokens": 8070581248} {"current_steps": 24100, "total_steps": 25209, "loss": 0.3197, "lr": 2.7076915078820115e-05, "epoch": 2.868023325002975, "percentage": 95.6, "elapsed_time": "1 day, 12:06:16", "remaining_time": "1:39:41", "throughput": 62118.32, "total_tokens": 8073925120} {"current_steps": 24110, "total_steps": 25209, "loss": 0.3214, "lr": 2.707294561328945e-05, "epoch": 2.8692133761751757, "percentage": 95.64, "elapsed_time": "1 day, 12:07:22", "remaining_time": "1:38:47", "throughput": 62112.84, "total_tokens": 8077279616} {"current_steps": 24120, "total_steps": 25209, "loss": 0.3199, "lr": 2.706897789301353e-05, "epoch": 2.8704034273473757, "percentage": 95.68, "elapsed_time": "1 day, 12:08:18", "remaining_time": "1:37:53", "throughput": 62111.54, "total_tokens": 8080620928} {"current_steps": 24130, "total_steps": 25209, "loss": 0.3214, "lr": 2.706501191671384e-05, "epoch": 2.8715934785195762, "percentage": 95.72, "elapsed_time": "1 day, 12:09:18", "remaining_time": "1:37:00", "throughput": 62108.17, "total_tokens": 8083933568} {"current_steps": 24140, "total_steps": 25209, "loss": 0.3193, "lr": 2.7061047683113165e-05, "epoch": 2.8727835296917767, "percentage": 95.76, "elapsed_time": "1 day, 12:10:15", "remaining_time": "1:36:06", "throughput": 62106.81, "total_tokens": 8087280384} {"current_steps": 24150, "total_steps": 25209, "loss": 0.3186, "lr": 2.705708519093561e-05, "epoch": 2.8739735808639773, "percentage": 95.8, "elapsed_time": "1 day, 12:11:05", "remaining_time": "1:35:12", "throughput": 62108.62, "total_tokens": 8090584320} {"current_steps": 24160, "total_steps": 25209, "loss": 0.3199, "lr": 2.705312443890658e-05, "epoch": 2.8751636320361778, "percentage": 95.84, "elapsed_time": "1 day, 12:12:02", "remaining_time": "1:34:18", "throughput": 62108.39, "total_tokens": 8094146816} {"current_steps": 24170, "total_steps": 25209, "loss": 0.3227, "lr": 2.70491654257528e-05, "epoch": 2.876353683208378, "percentage": 95.88, "elapsed_time": "1 day, 12:12:53", "remaining_time": "1:33:24", "throughput": 62110.34, "total_tokens": 8097513344} {"current_steps": 24180, "total_steps": 25209, "loss": 0.3161, "lr": 2.7045208150202274e-05, "epoch": 2.8775437343805783, "percentage": 95.92, "elapsed_time": "1 day, 12:13:41", "remaining_time": "1:32:30", "throughput": 62113.19, "total_tokens": 8100865920} {"current_steps": 24190, "total_steps": 25209, "loss": 0.3206, "lr": 2.704125261098433e-05, "epoch": 2.878733785552779, "percentage": 95.96, "elapsed_time": "1 day, 12:14:25", "remaining_time": "1:31:35", "throughput": 62116.34, "total_tokens": 8104058240} {"current_steps": 24200, "total_steps": 25209, "loss": 0.3239, "lr": 2.7037298806829586e-05, "epoch": 2.8799238367249793, "percentage": 96.0, "elapsed_time": "1 day, 12:15:16", "remaining_time": "1:30:41", "throughput": 62118.24, "total_tokens": 8107427968} {"current_steps": 24210, "total_steps": 25209, "loss": 0.3189, "lr": 2.7033346736469967e-05, "epoch": 2.88111388789718, "percentage": 96.04, "elapsed_time": "1 day, 12:16:04", "remaining_time": "1:29:47", "throughput": 62121.16, "total_tokens": 8110790784} {"current_steps": 24220, "total_steps": 25209, "loss": 0.3181, "lr": 2.702939639863869e-05, "epoch": 2.88230393906938, "percentage": 96.08, "elapsed_time": "1 day, 12:16:57", "remaining_time": "1:28:53", "throughput": 62120.87, "total_tokens": 8114084864} {"current_steps": 24230, "total_steps": 25209, "loss": 0.3174, "lr": 2.7025447792070262e-05, "epoch": 2.8834939902415804, "percentage": 96.12, "elapsed_time": "1 day, 12:17:47", "remaining_time": "1:27:59", "throughput": 62122.67, "total_tokens": 8117409920} {"current_steps": 24240, "total_steps": 25209, "loss": 0.3185, "lr": 2.7021500915500493e-05, "epoch": 2.884684041413781, "percentage": 96.16, "elapsed_time": "1 day, 12:18:42", "remaining_time": "1:27:05", "throughput": 62121.45, "total_tokens": 8120666752} {"current_steps": 24250, "total_steps": 25209, "loss": 0.3228, "lr": 2.701755576766648e-05, "epoch": 2.885874092585981, "percentage": 96.2, "elapsed_time": "1 day, 12:19:45", "remaining_time": "1:26:12", "throughput": 62116.62, "total_tokens": 8123979136} {"current_steps": 24260, "total_steps": 25209, "loss": 0.3186, "lr": 2.701361234730661e-05, "epoch": 2.887064143758182, "percentage": 96.24, "elapsed_time": "1 day, 12:20:48", "remaining_time": "1:25:18", "throughput": 62111.95, "total_tokens": 8127278592} {"current_steps": 24270, "total_steps": 25209, "loss": 0.3185, "lr": 2.700967065316056e-05, "epoch": 2.888254194930382, "percentage": 96.28, "elapsed_time": "1 day, 12:21:50", "remaining_time": "1:24:24", "throughput": 62108.82, "total_tokens": 8130668672} {"current_steps": 24280, "total_steps": 25209, "loss": 0.3131, "lr": 2.70057306839693e-05, "epoch": 2.8894442461025824, "percentage": 96.31, "elapsed_time": "1 day, 12:22:39", "remaining_time": "1:23:30", "throughput": 62111.03, "total_tokens": 8134024064} {"current_steps": 24290, "total_steps": 25209, "loss": 0.3197, "lr": 2.7001792438475076e-05, "epoch": 2.890634297274783, "percentage": 96.35, "elapsed_time": "1 day, 12:23:28", "remaining_time": "1:22:36", "throughput": 62113.3, "total_tokens": 8137350144} {"current_steps": 24300, "total_steps": 25209, "loss": 0.3182, "lr": 2.6997855915421416e-05, "epoch": 2.891824348446983, "percentage": 96.39, "elapsed_time": "1 day, 12:24:18", "remaining_time": "1:21:42", "throughput": 62115.38, "total_tokens": 8140759168} {"current_steps": 24310, "total_steps": 25209, "loss": 0.3194, "lr": 2.6993921113553145e-05, "epoch": 2.8930143996191835, "percentage": 96.43, "elapsed_time": "1 day, 12:25:08", "remaining_time": "1:20:48", "throughput": 62118.03, "total_tokens": 8144186624} {"current_steps": 24320, "total_steps": 25209, "loss": 0.3169, "lr": 2.6989988031616343e-05, "epoch": 2.894204450791384, "percentage": 96.47, "elapsed_time": "1 day, 12:26:01", "remaining_time": "1:19:54", "throughput": 62118.95, "total_tokens": 8147643904} {"current_steps": 24330, "total_steps": 25209, "loss": 0.3234, "lr": 2.6986056668358396e-05, "epoch": 2.8953945019635845, "percentage": 96.51, "elapsed_time": "1 day, 12:26:51", "remaining_time": "1:19:00", "throughput": 62120.95, "total_tokens": 8150955904} {"current_steps": 24340, "total_steps": 25209, "loss": 0.3161, "lr": 2.6982127022527947e-05, "epoch": 2.896584553135785, "percentage": 96.55, "elapsed_time": "1 day, 12:27:40", "remaining_time": "1:18:06", "throughput": 62123.3, "total_tokens": 8154322304} {"current_steps": 24350, "total_steps": 25209, "loss": 0.3194, "lr": 2.697819909287493e-05, "epoch": 2.897774604307985, "percentage": 96.59, "elapsed_time": "1 day, 12:28:32", "remaining_time": "1:17:12", "throughput": 62124.49, "total_tokens": 8157740928} {"current_steps": 24360, "total_steps": 25209, "loss": 0.3242, "lr": 2.697427287815053e-05, "epoch": 2.8989646554801856, "percentage": 96.63, "elapsed_time": "1 day, 12:29:20", "remaining_time": "1:16:18", "throughput": 62127.28, "total_tokens": 8161089152} {"current_steps": 24370, "total_steps": 25209, "loss": 0.3181, "lr": 2.6970348377107236e-05, "epoch": 2.900154706652386, "percentage": 96.67, "elapsed_time": "1 day, 12:30:07", "remaining_time": "1:15:24", "throughput": 62129.81, "total_tokens": 8164326272} {"current_steps": 24380, "total_steps": 25209, "loss": 0.3177, "lr": 2.696642558849877e-05, "epoch": 2.9013447578245866, "percentage": 96.71, "elapsed_time": "1 day, 12:31:00", "remaining_time": "1:14:30", "throughput": 62130.79, "total_tokens": 8167740288} {"current_steps": 24390, "total_steps": 25209, "loss": 0.3187, "lr": 2.696250451108016e-05, "epoch": 2.902534808996787, "percentage": 96.75, "elapsed_time": "1 day, 12:31:52", "remaining_time": "1:13:36", "throughput": 62130.92, "total_tokens": 8171003776} {"current_steps": 24400, "total_steps": 25209, "loss": 0.3145, "lr": 2.6958585143607662e-05, "epoch": 2.903724860168987, "percentage": 96.79, "elapsed_time": "1 day, 12:32:50", "remaining_time": "1:12:42", "throughput": 62129.25, "total_tokens": 8174406912} {"current_steps": 24410, "total_steps": 25209, "loss": 0.3162, "lr": 2.695466748483883e-05, "epoch": 2.9049149113411876, "percentage": 96.83, "elapsed_time": "1 day, 12:33:49", "remaining_time": "1:11:48", "throughput": 62127.09, "total_tokens": 8177742080} {"current_steps": 24420, "total_steps": 25209, "loss": 0.3207, "lr": 2.695075153353247e-05, "epoch": 2.906104962513388, "percentage": 96.87, "elapsed_time": "1 day, 12:34:43", "remaining_time": "1:10:54", "throughput": 62127.12, "total_tokens": 8181097856} {"current_steps": 24430, "total_steps": 25209, "loss": 0.3214, "lr": 2.6946837288448646e-05, "epoch": 2.9072950136855886, "percentage": 96.91, "elapsed_time": "1 day, 12:35:41", "remaining_time": "1:10:00", "throughput": 62125.72, "total_tokens": 8184526336} {"current_steps": 24440, "total_steps": 25209, "loss": 0.3197, "lr": 2.6942924748348684e-05, "epoch": 2.908485064857789, "percentage": 96.95, "elapsed_time": "1 day, 12:36:28", "remaining_time": "1:09:06", "throughput": 62128.71, "total_tokens": 8187831424} {"current_steps": 24450, "total_steps": 25209, "loss": 0.3195, "lr": 2.693901391199517e-05, "epoch": 2.909675116029989, "percentage": 96.99, "elapsed_time": "1 day, 12:37:18", "remaining_time": "1:08:12", "throughput": 62130.81, "total_tokens": 8191253120} {"current_steps": 24460, "total_steps": 25209, "loss": 0.3194, "lr": 2.6935104778151943e-05, "epoch": 2.9108651672021897, "percentage": 97.03, "elapsed_time": "1 day, 12:38:10", "remaining_time": "1:07:18", "throughput": 62132.37, "total_tokens": 8194673792} {"current_steps": 24470, "total_steps": 25209, "loss": 0.3176, "lr": 2.6931197345584102e-05, "epoch": 2.91205521837439, "percentage": 97.07, "elapsed_time": "1 day, 12:39:01", "remaining_time": "1:06:24", "throughput": 62133.93, "total_tokens": 8198047872} {"current_steps": 24480, "total_steps": 25209, "loss": 0.321, "lr": 2.6927291613058003e-05, "epoch": 2.9132452695465902, "percentage": 97.11, "elapsed_time": "1 day, 12:39:49", "remaining_time": "1:05:30", "throughput": 62136.47, "total_tokens": 8201332352} {"current_steps": 24490, "total_steps": 25209, "loss": 0.3174, "lr": 2.6923387579341254e-05, "epoch": 2.9144353207187907, "percentage": 97.15, "elapsed_time": "1 day, 12:40:39", "remaining_time": "1:04:36", "throughput": 62138.48, "total_tokens": 8204719744} {"current_steps": 24500, "total_steps": 25209, "loss": 0.3209, "lr": 2.6919485243202693e-05, "epoch": 2.9156253718909912, "percentage": 97.19, "elapsed_time": "1 day, 12:41:29", "remaining_time": "1:03:42", "throughput": 62140.59, "total_tokens": 8208098432} {"current_steps": 24510, "total_steps": 25209, "loss": 0.3195, "lr": 2.6915584603412434e-05, "epoch": 2.9168154230631917, "percentage": 97.23, "elapsed_time": "1 day, 12:42:21", "remaining_time": "1:02:48", "throughput": 62141.75, "total_tokens": 8211507968} {"current_steps": 24520, "total_steps": 25209, "loss": 0.3189, "lr": 2.6911685658741827e-05, "epoch": 2.9180054742353922, "percentage": 97.27, "elapsed_time": "1 day, 12:43:10", "remaining_time": "1:01:54", "throughput": 62143.99, "total_tokens": 8214855552} {"current_steps": 24530, "total_steps": 25209, "loss": 0.3199, "lr": 2.690778840796346e-05, "epoch": 2.9191955254075923, "percentage": 97.31, "elapsed_time": "1 day, 12:44:10", "remaining_time": "1:01:00", "throughput": 62142.17, "total_tokens": 8218323584} {"current_steps": 24540, "total_steps": 25209, "loss": 0.3166, "lr": 2.6903892849851175e-05, "epoch": 2.920385576579793, "percentage": 97.35, "elapsed_time": "1 day, 12:45:10", "remaining_time": "1:00:07", "throughput": 62139.06, "total_tokens": 8221666560} {"current_steps": 24550, "total_steps": 25209, "loss": 0.3217, "lr": 2.6899998983180057e-05, "epoch": 2.9215756277519933, "percentage": 97.39, "elapsed_time": "1 day, 12:46:18", "remaining_time": "0:59:13", "throughput": 62133.25, "total_tokens": 8225122048} {"current_steps": 24560, "total_steps": 25209, "loss": 0.3203, "lr": 2.689610680672642e-05, "epoch": 2.922765678924194, "percentage": 97.43, "elapsed_time": "1 day, 12:47:24", "remaining_time": "0:58:19", "throughput": 62127.92, "total_tokens": 8228525312} {"current_steps": 24570, "total_steps": 25209, "loss": 0.3234, "lr": 2.6892216319267843e-05, "epoch": 2.9239557300963943, "percentage": 97.47, "elapsed_time": "1 day, 12:48:24", "remaining_time": "0:57:26", "throughput": 62125.31, "total_tokens": 8231876480} {"current_steps": 24580, "total_steps": 25209, "loss": 0.3226, "lr": 2.6888327519583107e-05, "epoch": 2.9251457812685944, "percentage": 97.5, "elapsed_time": "1 day, 12:49:12", "remaining_time": "0:56:32", "throughput": 62127.56, "total_tokens": 8235174400} {"current_steps": 24590, "total_steps": 25209, "loss": 0.3224, "lr": 2.688444040645225e-05, "epoch": 2.926335832440795, "percentage": 97.54, "elapsed_time": "1 day, 12:50:02", "remaining_time": "0:55:37", "throughput": 62128.89, "total_tokens": 8238472704} {"current_steps": 24600, "total_steps": 25209, "loss": 0.323, "lr": 2.688055497865654e-05, "epoch": 2.9275258836129954, "percentage": 97.58, "elapsed_time": "1 day, 12:50:52", "remaining_time": "0:54:43", "throughput": 62131.72, "total_tokens": 8241953920} {"current_steps": 24610, "total_steps": 25209, "loss": 0.3229, "lr": 2.6876671234978483e-05, "epoch": 2.928715934785196, "percentage": 97.62, "elapsed_time": "1 day, 12:51:40", "remaining_time": "0:53:49", "throughput": 62134.79, "total_tokens": 8245298688} {"current_steps": 24620, "total_steps": 25209, "loss": 0.3178, "lr": 2.6872789174201807e-05, "epoch": 2.9299059859573964, "percentage": 97.66, "elapsed_time": "1 day, 12:52:28", "remaining_time": "0:52:55", "throughput": 62137.04, "total_tokens": 8248618752} {"current_steps": 24630, "total_steps": 25209, "loss": 0.3198, "lr": 2.686890879511147e-05, "epoch": 2.9310960371295964, "percentage": 97.7, "elapsed_time": "1 day, 12:53:19", "remaining_time": "0:52:01", "throughput": 62139.14, "total_tokens": 8252059264} {"current_steps": 24640, "total_steps": 25209, "loss": 0.3196, "lr": 2.6865030096493665e-05, "epoch": 2.932286088301797, "percentage": 97.74, "elapsed_time": "1 day, 12:54:11", "remaining_time": "0:51:07", "throughput": 62140.81, "total_tokens": 8255482368} {"current_steps": 24650, "total_steps": 25209, "loss": 0.3179, "lr": 2.6861153077135815e-05, "epoch": 2.9334761394739974, "percentage": 97.78, "elapsed_time": "1 day, 12:55:01", "remaining_time": "0:50:13", "throughput": 62142.93, "total_tokens": 8258891136} {"current_steps": 24660, "total_steps": 25209, "loss": 0.3126, "lr": 2.6857277735826545e-05, "epoch": 2.934666190646198, "percentage": 97.82, "elapsed_time": "1 day, 12:55:50", "remaining_time": "0:49:19", "throughput": 62145.84, "total_tokens": 8262296960} {"current_steps": 24670, "total_steps": 25209, "loss": 0.3183, "lr": 2.685340407135573e-05, "epoch": 2.9358562418183984, "percentage": 97.86, "elapsed_time": "1 day, 12:56:39", "remaining_time": "0:48:25", "throughput": 62147.91, "total_tokens": 8265654400} {"current_steps": 24680, "total_steps": 25209, "loss": 0.3149, "lr": 2.6849532082514445e-05, "epoch": 2.9370462929905985, "percentage": 97.9, "elapsed_time": "1 day, 12:57:32", "remaining_time": "0:47:31", "throughput": 62149.33, "total_tokens": 8269093248} {"current_steps": 24690, "total_steps": 25209, "loss": 0.3192, "lr": 2.6845661768095005e-05, "epoch": 2.938236344162799, "percentage": 97.94, "elapsed_time": "1 day, 12:58:35", "remaining_time": "0:46:38", "throughput": 62144.78, "total_tokens": 8272402176} {"current_steps": 24700, "total_steps": 25209, "loss": 0.3213, "lr": 2.6841793126890925e-05, "epoch": 2.9394263953349995, "percentage": 97.98, "elapsed_time": "1 day, 12:59:32", "remaining_time": "0:45:44", "throughput": 62143.29, "total_tokens": 8275750016} {"current_steps": 24710, "total_steps": 25209, "loss": 0.3154, "lr": 2.6837926157696946e-05, "epoch": 2.9406164465071996, "percentage": 98.02, "elapsed_time": "1 day, 13:00:42", "remaining_time": "0:44:50", "throughput": 62136.28, "total_tokens": 8279180160} {"current_steps": 24720, "total_steps": 25209, "loss": 0.3187, "lr": 2.6834060859309018e-05, "epoch": 2.9418064976794, "percentage": 98.06, "elapsed_time": "1 day, 13:01:50", "remaining_time": "0:43:57", "throughput": 62129.43, "total_tokens": 8282525952} {"current_steps": 24730, "total_steps": 25209, "loss": 0.3166, "lr": 2.6830197230524317e-05, "epoch": 2.9429965488516006, "percentage": 98.1, "elapsed_time": "1 day, 13:02:46", "remaining_time": "0:43:03", "throughput": 62128.75, "total_tokens": 8285870592} {"current_steps": 24740, "total_steps": 25209, "loss": 0.318, "lr": 2.6826335270141216e-05, "epoch": 2.944186600023801, "percentage": 98.14, "elapsed_time": "1 day, 13:03:47", "remaining_time": "0:42:09", "throughput": 62125.09, "total_tokens": 8289197696} {"current_steps": 24750, "total_steps": 25209, "loss": 0.3172, "lr": 2.6822474976959312e-05, "epoch": 2.9453766511960016, "percentage": 98.18, "elapsed_time": "1 day, 13:04:51", "remaining_time": "0:41:15", "throughput": 62120.73, "total_tokens": 8292579712} {"current_steps": 24760, "total_steps": 25209, "loss": 0.3167, "lr": 2.6818616349779397e-05, "epoch": 2.9465667023682016, "percentage": 98.22, "elapsed_time": "1 day, 13:05:50", "remaining_time": "0:40:21", "throughput": 62118.84, "total_tokens": 8295986176} {"current_steps": 24770, "total_steps": 25209, "loss": 0.3174, "lr": 2.6814759387403482e-05, "epoch": 2.947756753540402, "percentage": 98.26, "elapsed_time": "1 day, 13:06:40", "remaining_time": "0:39:27", "throughput": 62120.45, "total_tokens": 8299296256} {"current_steps": 24780, "total_steps": 25209, "loss": 0.3179, "lr": 2.681090408863477e-05, "epoch": 2.9489468047126026, "percentage": 98.3, "elapsed_time": "1 day, 13:07:28", "remaining_time": "0:38:33", "throughput": 62122.52, "total_tokens": 8302586624} {"current_steps": 24790, "total_steps": 25209, "loss": 0.3194, "lr": 2.6807050452277694e-05, "epoch": 2.950136855884803, "percentage": 98.34, "elapsed_time": "1 day, 13:08:19", "remaining_time": "0:37:39", "throughput": 62124.22, "total_tokens": 8305996288} {"current_steps": 24800, "total_steps": 25209, "loss": 0.3167, "lr": 2.6803198477137853e-05, "epoch": 2.9513269070570036, "percentage": 98.38, "elapsed_time": "1 day, 13:09:14", "remaining_time": "0:36:45", "throughput": 62124.25, "total_tokens": 8309370880} {"current_steps": 24810, "total_steps": 25209, "loss": 0.3219, "lr": 2.6799348162022082e-05, "epoch": 2.9525169582292037, "percentage": 98.42, "elapsed_time": "1 day, 13:10:09", "remaining_time": "0:35:51", "throughput": 62123.75, "total_tokens": 8312740992} {"current_steps": 24820, "total_steps": 25209, "loss": 0.3178, "lr": 2.6795499505738397e-05, "epoch": 2.953707009401404, "percentage": 98.46, "elapsed_time": "1 day, 13:11:11", "remaining_time": "0:34:58", "throughput": 62121.25, "total_tokens": 8316248320} {"current_steps": 24830, "total_steps": 25209, "loss": 0.3237, "lr": 2.679165250709601e-05, "epoch": 2.9548970605736047, "percentage": 98.5, "elapsed_time": "1 day, 13:12:06", "remaining_time": "0:34:04", "throughput": 62120.69, "total_tokens": 8319595648} {"current_steps": 24840, "total_steps": 25209, "loss": 0.3159, "lr": 2.678780716490533e-05, "epoch": 2.956087111745805, "percentage": 98.54, "elapsed_time": "1 day, 13:13:09", "remaining_time": "0:33:10", "throughput": 62117.19, "total_tokens": 8323061120} {"current_steps": 24850, "total_steps": 25209, "loss": 0.3182, "lr": 2.678396347797798e-05, "epoch": 2.9572771629180057, "percentage": 98.58, "elapsed_time": "1 day, 13:14:02", "remaining_time": "0:32:16", "throughput": 62117.08, "total_tokens": 8326331776} {"current_steps": 24860, "total_steps": 25209, "loss": 0.3195, "lr": 2.6780121445126756e-05, "epoch": 2.9584672140902057, "percentage": 98.62, "elapsed_time": "1 day, 13:14:52", "remaining_time": "0:31:22", "throughput": 62119.66, "total_tokens": 8329769216} {"current_steps": 24870, "total_steps": 25209, "loss": 0.3196, "lr": 2.6776281065165644e-05, "epoch": 2.9596572652624062, "percentage": 98.66, "elapsed_time": "1 day, 13:15:35", "remaining_time": "0:30:28", "throughput": 62123.77, "total_tokens": 8333033728} {"current_steps": 24880, "total_steps": 25209, "loss": 0.3165, "lr": 2.677244233690983e-05, "epoch": 2.9608473164346067, "percentage": 98.69, "elapsed_time": "1 day, 13:16:26", "remaining_time": "0:29:34", "throughput": 62125.39, "total_tokens": 8336414720} {"current_steps": 24890, "total_steps": 25209, "loss": 0.3187, "lr": 2.6768605259175694e-05, "epoch": 2.9620373676068072, "percentage": 98.73, "elapsed_time": "1 day, 13:17:17", "remaining_time": "0:28:40", "throughput": 62126.85, "total_tokens": 8339739776} {"current_steps": 24900, "total_steps": 25209, "loss": 0.3205, "lr": 2.6764769830780784e-05, "epoch": 2.9632274187790077, "percentage": 98.77, "elapsed_time": "1 day, 13:18:05", "remaining_time": "0:27:46", "throughput": 62129.21, "total_tokens": 8343048960} {"current_steps": 24910, "total_steps": 25209, "loss": 0.3251, "lr": 2.6760936050543857e-05, "epoch": 2.964417469951208, "percentage": 98.81, "elapsed_time": "1 day, 13:18:52", "remaining_time": "0:26:52", "throughput": 62131.58, "total_tokens": 8346318464} {"current_steps": 24920, "total_steps": 25209, "loss": 0.3153, "lr": 2.675710391728483e-05, "epoch": 2.9656075211234083, "percentage": 98.85, "elapsed_time": "1 day, 13:19:43", "remaining_time": "0:25:58", "throughput": 62133.41, "total_tokens": 8349704704} {"current_steps": 24930, "total_steps": 25209, "loss": 0.3209, "lr": 2.6753273429824822e-05, "epoch": 2.966797572295609, "percentage": 98.89, "elapsed_time": "1 day, 13:20:32", "remaining_time": "0:25:04", "throughput": 62135.83, "total_tokens": 8353075968} {"current_steps": 24940, "total_steps": 25209, "loss": 0.3177, "lr": 2.6749444586986127e-05, "epoch": 2.967987623467809, "percentage": 98.93, "elapsed_time": "1 day, 13:21:21", "remaining_time": "0:24:10", "throughput": 62138.02, "total_tokens": 8356427776} {"current_steps": 24950, "total_steps": 25209, "loss": 0.3212, "lr": 2.6745617387592214e-05, "epoch": 2.9691776746400094, "percentage": 98.97, "elapsed_time": "1 day, 13:22:10", "remaining_time": "0:23:16", "throughput": 62140.55, "total_tokens": 8359775488} {"current_steps": 24960, "total_steps": 25209, "loss": 0.317, "lr": 2.6741791830467728e-05, "epoch": 2.97036772581221, "percentage": 99.01, "elapsed_time": "1 day, 13:22:57", "remaining_time": "0:22:22", "throughput": 62143.78, "total_tokens": 8363154048} {"current_steps": 24970, "total_steps": 25209, "loss": 0.3185, "lr": 2.67379679144385e-05, "epoch": 2.9715577769844104, "percentage": 99.05, "elapsed_time": "1 day, 13:23:44", "remaining_time": "0:21:28", "throughput": 62146.19, "total_tokens": 8366420992} {"current_steps": 24980, "total_steps": 25209, "loss": 0.3195, "lr": 2.6734145638331536e-05, "epoch": 2.972747828156611, "percentage": 99.09, "elapsed_time": "1 day, 13:24:34", "remaining_time": "0:20:34", "throughput": 62147.91, "total_tokens": 8369712640} {"current_steps": 24990, "total_steps": 25209, "loss": 0.3154, "lr": 2.673032500097501e-05, "epoch": 2.973937879328811, "percentage": 99.13, "elapsed_time": "1 day, 13:25:25", "remaining_time": "0:19:40", "throughput": 62149.15, "total_tokens": 8373090432} {"current_steps": 25000, "total_steps": 25209, "loss": 0.3187, "lr": 2.672650600119826e-05, "epoch": 2.9751279305010114, "percentage": 99.17, "elapsed_time": "1 day, 13:26:19", "remaining_time": "0:18:46", "throughput": 62150.31, "total_tokens": 8376560768} {"current_steps": 25000, "total_steps": 25209, "eval_loss": 0.3315782845020294, "epoch": 2.9751279305010114, "percentage": 99.17, "elapsed_time": "1 day, 13:26:20", "remaining_time": "0:18:46", "throughput": 62149.84, "total_tokens": 8376560768} {"current_steps": 25010, "total_steps": 25209, "loss": 0.3198, "lr": 2.672268863783181e-05, "epoch": 2.976317981673212, "percentage": 99.21, "elapsed_time": "1 day, 13:27:39", "remaining_time": "0:17:53", "throughput": 62138.0, "total_tokens": 8379881984} {"current_steps": 25020, "total_steps": 25209, "loss": 0.3194, "lr": 2.6718872909707347e-05, "epoch": 2.9775080328454124, "percentage": 99.25, "elapsed_time": "1 day, 13:28:37", "remaining_time": "0:16:59", "throughput": 62135.71, "total_tokens": 8383186432} {"current_steps": 25030, "total_steps": 25209, "loss": 0.3204, "lr": 2.671505881565772e-05, "epoch": 2.978698084017613, "percentage": 99.29, "elapsed_time": "1 day, 13:29:44", "remaining_time": "0:16:05", "throughput": 62129.8, "total_tokens": 8386573824} {"current_steps": 25040, "total_steps": 25209, "loss": 0.3176, "lr": 2.671124635451696e-05, "epoch": 2.979888135189813, "percentage": 99.33, "elapsed_time": "1 day, 13:30:43", "remaining_time": "0:15:11", "throughput": 62127.6, "total_tokens": 8389935488} {"current_steps": 25050, "total_steps": 25209, "loss": 0.3181, "lr": 2.6707435525120237e-05, "epoch": 2.9810781863620135, "percentage": 99.37, "elapsed_time": "1 day, 13:31:38", "remaining_time": "0:14:17", "throughput": 62126.51, "total_tokens": 8393193344} {"current_steps": 25060, "total_steps": 25209, "loss": 0.3197, "lr": 2.6703626326303906e-05, "epoch": 2.982268237534214, "percentage": 99.41, "elapsed_time": "1 day, 13:32:30", "remaining_time": "0:13:23", "throughput": 62127.67, "total_tokens": 8396566016} {"current_steps": 25070, "total_steps": 25209, "loss": 0.3204, "lr": 2.669981875690547e-05, "epoch": 2.9834582887064145, "percentage": 99.45, "elapsed_time": "1 day, 13:33:19", "remaining_time": "0:12:29", "throughput": 62129.39, "total_tokens": 8399857792} {"current_steps": 25080, "total_steps": 25209, "loss": 0.3224, "lr": 2.6696012815763604e-05, "epoch": 2.984648339878615, "percentage": 99.49, "elapsed_time": "1 day, 13:34:07", "remaining_time": "0:11:35", "throughput": 62131.93, "total_tokens": 8403214976} {"current_steps": 25090, "total_steps": 25209, "loss": 0.317, "lr": 2.669220850171813e-05, "epoch": 2.985838391050815, "percentage": 99.53, "elapsed_time": "1 day, 13:34:58", "remaining_time": "0:10:41", "throughput": 62133.12, "total_tokens": 8406548224} {"current_steps": 25100, "total_steps": 25209, "loss": 0.3164, "lr": 2.668840581361003e-05, "epoch": 2.9870284422230156, "percentage": 99.57, "elapsed_time": "1 day, 13:35:51", "remaining_time": "0:09:47", "throughput": 62134.34, "total_tokens": 8410002688} {"current_steps": 25110, "total_steps": 25209, "loss": 0.3209, "lr": 2.668460475028145e-05, "epoch": 2.988218493395216, "percentage": 99.61, "elapsed_time": "1 day, 13:36:48", "remaining_time": "0:08:53", "throughput": 62133.01, "total_tokens": 8413337600} {"current_steps": 25120, "total_steps": 25209, "loss": 0.3129, "lr": 2.6680805310575686e-05, "epoch": 2.9894085445674166, "percentage": 99.65, "elapsed_time": "1 day, 13:37:48", "remaining_time": "0:07:59", "throughput": 62130.26, "total_tokens": 8416692864} {"current_steps": 25130, "total_steps": 25209, "loss": 0.3146, "lr": 2.6677007493337164e-05, "epoch": 2.990598595739617, "percentage": 99.69, "elapsed_time": "1 day, 13:38:58", "remaining_time": "0:07:06", "throughput": 62123.94, "total_tokens": 8420156160} {"current_steps": 25140, "total_steps": 25209, "loss": 0.3195, "lr": 2.6673211297411503e-05, "epoch": 2.991788646911817, "percentage": 99.73, "elapsed_time": "1 day, 13:39:52", "remaining_time": "0:06:12", "throughput": 62123.82, "total_tokens": 8423504384} {"current_steps": 25150, "total_steps": 25209, "loss": 0.3197, "lr": 2.6669416721645447e-05, "epoch": 2.9929786980840176, "percentage": 99.77, "elapsed_time": "1 day, 13:40:39", "remaining_time": "0:05:18", "throughput": 62126.48, "total_tokens": 8426831104} {"current_steps": 25160, "total_steps": 25209, "loss": 0.3224, "lr": 2.6665623764886876e-05, "epoch": 2.994168749256218, "percentage": 99.81, "elapsed_time": "1 day, 13:41:28", "remaining_time": "0:04:24", "throughput": 62128.65, "total_tokens": 8430171904} {"current_steps": 25170, "total_steps": 25209, "loss": 0.326, "lr": 2.6661832425984847e-05, "epoch": 2.995358800428418, "percentage": 99.85, "elapsed_time": "1 day, 13:42:20", "remaining_time": "0:03:30", "throughput": 62130.59, "total_tokens": 8433641856} {"current_steps": 25180, "total_steps": 25209, "loss": 0.3171, "lr": 2.665804270378953e-05, "epoch": 2.9965488516006187, "percentage": 99.88, "elapsed_time": "1 day, 13:43:07", "remaining_time": "0:02:36", "throughput": 62133.27, "total_tokens": 8436931712} {"current_steps": 25190, "total_steps": 25209, "loss": 0.3173, "lr": 2.665425459715228e-05, "epoch": 2.997738902772819, "percentage": 99.92, "elapsed_time": "1 day, 13:43:59", "remaining_time": "0:01:42", "throughput": 62134.47, "total_tokens": 8440306048} {"current_steps": 25200, "total_steps": 25209, "loss": 0.3229, "lr": 2.6650468104925547e-05, "epoch": 2.9989289539450197, "percentage": 99.96, "elapsed_time": "1 day, 13:44:51", "remaining_time": "0:00:48", "throughput": 62135.79, "total_tokens": 8443745920} {"current_steps": 25209, "total_steps": 25209, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1 day, 13:46:19", "remaining_time": "0:00:00", "throughput": 62117.85, "total_tokens": 8446782720}