{"current_steps": 10, "total_steps": 15426, "loss": 1.3741, "lr": 4.9977515176118345e-05, "epoch": 0.0019449576971700866, "percentage": 0.06, "elapsed_time": "0:01:20", "remaining_time": "1 day, 10:30:33", "throughput": 48873.06, "total_tokens": 3938560} {"current_steps": 20, "total_steps": 15426, "loss": 0.7823, "lr": 4.9952567580506e-05, "epoch": 0.0038899153943401732, "percentage": 0.13, "elapsed_time": "0:02:39", "remaining_time": "1 day, 10:08:26", "throughput": 49486.65, "total_tokens": 7895936} {"current_steps": 30, "total_steps": 15426, "loss": 0.6514, "lr": 4.992765730738634e-05, "epoch": 0.005834873091510259, "percentage": 0.19, "elapsed_time": "0:03:39", "remaining_time": "1 day, 7:13:41", "throughput": 53552.51, "total_tokens": 11731200} {"current_steps": 40, "total_steps": 15426, "loss": 0.5947, "lr": 4.9902784263792476e-05, "epoch": 0.0077798307886803465, "percentage": 0.26, "elapsed_time": "0:04:39", "remaining_time": "1 day, 5:50:33", "throughput": 55763.27, "total_tokens": 15574784} {"current_steps": 50, "total_steps": 15426, "loss": 0.5684, "lr": 4.987794835708133e-05, "epoch": 0.009724788485850433, "percentage": 0.32, "elapsed_time": "0:05:41", "remaining_time": "1 day, 5:09:24", "throughput": 56984.94, "total_tokens": 19450368} {"current_steps": 60, "total_steps": 15426, "loss": 0.5423, "lr": 4.985314949493234e-05, "epoch": 0.011669746183020519, "percentage": 0.39, "elapsed_time": "0:06:43", "remaining_time": "1 day, 4:41:38", "throughput": 57853.29, "total_tokens": 23335168} {"current_steps": 70, "total_steps": 15426, "loss": 0.5255, "lr": 4.982838758534584e-05, "epoch": 0.013614703880190605, "percentage": 0.45, "elapsed_time": "0:08:23", "remaining_time": "1 day, 6:40:38", "throughput": 54279.44, "total_tokens": 27326080} {"current_steps": 80, "total_steps": 15426, "loss": 0.514, "lr": 4.980366253664179e-05, "epoch": 0.015559661577360693, "percentage": 0.52, "elapsed_time": "0:09:34", "remaining_time": "1 day, 6:35:52", "throughput": 54373.59, "total_tokens": 31223168} {"current_steps": 90, "total_steps": 15426, "loss": 0.4939, "lr": 4.977897425745825e-05, "epoch": 0.01750461927453078, "percentage": 0.58, "elapsed_time": "0:11:36", "remaining_time": "1 day, 8:57:21", "throughput": 50528.01, "total_tokens": 35180288} {"current_steps": 100, "total_steps": 15426, "loss": 0.4927, "lr": 4.975432265674997e-05, "epoch": 0.019449576971700865, "percentage": 0.65, "elapsed_time": "0:13:58", "remaining_time": "1 day, 11:42:49", "throughput": 46681.19, "total_tokens": 39160832} {"current_steps": 110, "total_steps": 15426, "loss": 0.4823, "lr": 4.972970764378705e-05, "epoch": 0.02139453466887095, "percentage": 0.71, "elapsed_time": "0:16:34", "remaining_time": "1 day, 14:27:57", "throughput": 43446.37, "total_tokens": 43209600} {"current_steps": 120, "total_steps": 15426, "loss": 0.4765, "lr": 4.970512912815344e-05, "epoch": 0.023339492366041038, "percentage": 0.78, "elapsed_time": "0:19:17", "remaining_time": "1 day, 17:01:23", "throughput": 40739.25, "total_tokens": 47169792} {"current_steps": 130, "total_steps": 15426, "loss": 0.4692, "lr": 4.968058701974564e-05, "epoch": 0.025284450063211124, "percentage": 0.84, "elapsed_time": "0:21:42", "remaining_time": "1 day, 18:33:18", "throughput": 39210.32, "total_tokens": 51053056} {"current_steps": 140, "total_steps": 15426, "loss": 0.4649, "lr": 4.96560812287712e-05, "epoch": 0.02722940776038121, "percentage": 0.91, "elapsed_time": "0:24:29", "remaining_time": "1 day, 20:34:29", "throughput": 37413.16, "total_tokens": 54985984} {"current_steps": 150, "total_steps": 15426, "loss": 0.4614, "lr": 4.963161166574748e-05, "epoch": 0.0291743654575513, "percentage": 0.97, "elapsed_time": "0:27:07", "remaining_time": "1 day, 22:02:44", "throughput": 36191.54, "total_tokens": 58908672} {"current_steps": 160, "total_steps": 15426, "loss": 0.4539, "lr": 4.960717824150013e-05, "epoch": 0.031119323154721386, "percentage": 1.04, "elapsed_time": "0:29:20", "remaining_time": "1 day, 22:38:50", "throughput": 35628.13, "total_tokens": 62707072} {"current_steps": 170, "total_steps": 15426, "loss": 0.4493, "lr": 4.9582780867161893e-05, "epoch": 0.03306428085189147, "percentage": 1.1, "elapsed_time": "0:31:45", "remaining_time": "1 day, 23:30:39", "throughput": 34972.09, "total_tokens": 66653952} {"current_steps": 180, "total_steps": 15426, "loss": 0.4449, "lr": 4.955841945417105e-05, "epoch": 0.03500923854906156, "percentage": 1.17, "elapsed_time": "0:33:15", "remaining_time": "1 day, 22:56:54", "throughput": 35357.68, "total_tokens": 70554240} {"current_steps": 190, "total_steps": 15426, "loss": 0.445, "lr": 4.953409391427024e-05, "epoch": 0.03695419624623165, "percentage": 1.23, "elapsed_time": "0:34:19", "remaining_time": "1 day, 21:52:55", "throughput": 36168.9, "total_tokens": 74501248} {"current_steps": 200, "total_steps": 15426, "loss": 0.4401, "lr": 4.950980415950502e-05, "epoch": 0.03889915394340173, "percentage": 1.3, "elapsed_time": "0:35:18", "remaining_time": "1 day, 20:48:01", "throughput": 37020.38, "total_tokens": 78427904} {"current_steps": 210, "total_steps": 15426, "loss": 0.4368, "lr": 4.9485550102222575e-05, "epoch": 0.04084411164057182, "percentage": 1.36, "elapsed_time": "0:36:20", "remaining_time": "1 day, 19:52:44", "throughput": 37759.6, "total_tokens": 82320000} {"current_steps": 220, "total_steps": 15426, "loss": 0.4343, "lr": 4.946133165507037e-05, "epoch": 0.0427890693377419, "percentage": 1.43, "elapsed_time": "0:37:23", "remaining_time": "1 day, 19:04:12", "throughput": 38412.29, "total_tokens": 86170368} {"current_steps": 230, "total_steps": 15426, "loss": 0.43, "lr": 4.943714873099483e-05, "epoch": 0.04473402703491199, "percentage": 1.49, "elapsed_time": "0:38:23", "remaining_time": "1 day, 18:16:40", "throughput": 39062.73, "total_tokens": 89986432} {"current_steps": 240, "total_steps": 15426, "loss": 0.426, "lr": 4.9413001243240024e-05, "epoch": 0.046678984732082075, "percentage": 1.56, "elapsed_time": "0:39:23", "remaining_time": "1 day, 17:32:59", "throughput": 39730.96, "total_tokens": 93922176} {"current_steps": 250, "total_steps": 15426, "loss": 0.4247, "lr": 4.938888910534637e-05, "epoch": 0.048623942429252165, "percentage": 1.62, "elapsed_time": "0:40:24", "remaining_time": "1 day, 16:52:51", "throughput": 40356.93, "total_tokens": 97841920} {"current_steps": 260, "total_steps": 15426, "loss": 0.4245, "lr": 4.936481223114932e-05, "epoch": 0.05056890012642225, "percentage": 1.69, "elapsed_time": "0:41:25", "remaining_time": "1 day, 16:16:44", "throughput": 40955.04, "total_tokens": 101809920} {"current_steps": 270, "total_steps": 15426, "loss": 0.4229, "lr": 4.934077053477808e-05, "epoch": 0.05251385782359234, "percentage": 1.75, "elapsed_time": "0:42:24", "remaining_time": "1 day, 15:40:44", "throughput": 41559.68, "total_tokens": 105758336} {"current_steps": 280, "total_steps": 15426, "loss": 0.4165, "lr": 4.931676393065431e-05, "epoch": 0.05445881552076242, "percentage": 1.82, "elapsed_time": "0:43:28", "remaining_time": "1 day, 15:11:48", "throughput": 42038.46, "total_tokens": 109662848} {"current_steps": 290, "total_steps": 15426, "loss": 0.4153, "lr": 4.929279233349088e-05, "epoch": 0.05640377321793251, "percentage": 1.88, "elapsed_time": "0:45:02", "remaining_time": "1 day, 15:10:58", "throughput": 42016.85, "total_tokens": 113556224} {"current_steps": 300, "total_steps": 15426, "loss": 0.4092, "lr": 4.926885565829051e-05, "epoch": 0.0583487309151026, "percentage": 1.94, "elapsed_time": "0:47:09", "remaining_time": "1 day, 15:37:54", "throughput": 41526.46, "total_tokens": 117508224} {"current_steps": 310, "total_steps": 15426, "loss": 0.4136, "lr": 4.924495382034461e-05, "epoch": 0.06029368861227268, "percentage": 2.01, "elapsed_time": "0:49:00", "remaining_time": "1 day, 15:50:03", "throughput": 41295.28, "total_tokens": 121446656} {"current_steps": 320, "total_steps": 15426, "loss": 0.4137, "lr": 4.9221086735231975e-05, "epoch": 0.06223864630944277, "percentage": 2.07, "elapsed_time": "0:51:12", "remaining_time": "1 day, 16:17:17", "throughput": 40801.44, "total_tokens": 125359104} {"current_steps": 330, "total_steps": 15426, "loss": 0.4092, "lr": 4.919725431881751e-05, "epoch": 0.06418360400661285, "percentage": 2.14, "elapsed_time": "0:53:07", "remaining_time": "1 day, 16:30:34", "throughput": 40539.28, "total_tokens": 129237632} {"current_steps": 340, "total_steps": 15426, "loss": 0.4078, "lr": 4.917345648725101e-05, "epoch": 0.06612856170378294, "percentage": 2.2, "elapsed_time": "0:54:46", "remaining_time": "1 day, 16:30:20", "throughput": 40558.6, "total_tokens": 133292672} {"current_steps": 350, "total_steps": 15426, "loss": 0.4057, "lr": 4.914969315696596e-05, "epoch": 0.06807351940095303, "percentage": 2.27, "elapsed_time": "0:56:02", "remaining_time": "1 day, 16:14:12", "throughput": 40808.4, "total_tokens": 137232512} {"current_steps": 360, "total_steps": 15426, "loss": 0.4024, "lr": 4.912596424467818e-05, "epoch": 0.07001847709812312, "percentage": 2.33, "elapsed_time": "0:57:01", "remaining_time": "1 day, 15:46:44", "throughput": 41265.06, "total_tokens": 141202944} {"current_steps": 370, "total_steps": 15426, "loss": 0.4, "lr": 4.910226966738475e-05, "epoch": 0.0719634347952932, "percentage": 2.4, "elapsed_time": "0:57:59", "remaining_time": "1 day, 15:19:55", "throughput": 41702.86, "total_tokens": 145113728} {"current_steps": 380, "total_steps": 15426, "loss": 0.403, "lr": 4.9078609342362666e-05, "epoch": 0.0739083924924633, "percentage": 2.46, "elapsed_time": "0:58:59", "remaining_time": "1 day, 14:55:40", "throughput": 42127.55, "total_tokens": 149104640} {"current_steps": 390, "total_steps": 15426, "loss": 0.4001, "lr": 4.905498318716775e-05, "epoch": 0.07585335018963338, "percentage": 2.53, "elapsed_time": "1:00:06", "remaining_time": "1 day, 14:37:24", "throughput": 42415.82, "total_tokens": 152972288} {"current_steps": 400, "total_steps": 15426, "loss": 0.3996, "lr": 4.9031391119633295e-05, "epoch": 0.07779830788680346, "percentage": 2.59, "elapsed_time": "1:01:04", "remaining_time": "1 day, 14:14:11", "throughput": 42815.05, "total_tokens": 156890112} {"current_steps": 410, "total_steps": 15426, "loss": 0.3941, "lr": 4.9007833057869e-05, "epoch": 0.07974326558397354, "percentage": 2.66, "elapsed_time": "1:02:02", "remaining_time": "1 day, 13:52:16", "throughput": 43220.62, "total_tokens": 160891520} {"current_steps": 420, "total_steps": 15426, "loss": 0.3945, "lr": 4.898430892025967e-05, "epoch": 0.08168822328114364, "percentage": 2.72, "elapsed_time": "1:03:16", "remaining_time": "1 day, 13:40:40", "throughput": 43411.44, "total_tokens": 164808192} {"current_steps": 430, "total_steps": 15426, "loss": 0.3893, "lr": 4.896081862546415e-05, "epoch": 0.08363318097831372, "percentage": 2.79, "elapsed_time": "1:04:24", "remaining_time": "1 day, 13:26:04", "throughput": 43652.71, "total_tokens": 168686464} {"current_steps": 440, "total_steps": 15426, "loss": 0.3911, "lr": 4.8937362092414e-05, "epoch": 0.0855781386754838, "percentage": 2.85, "elapsed_time": "1:05:31", "remaining_time": "1 day, 13:11:52", "throughput": 43915.64, "total_tokens": 172665856} {"current_steps": 450, "total_steps": 15426, "loss": 0.3923, "lr": 4.891393924031244e-05, "epoch": 0.08752309637265389, "percentage": 2.92, "elapsed_time": "1:06:35", "remaining_time": "1 day, 12:55:58", "throughput": 44195.11, "total_tokens": 176565376} {"current_steps": 460, "total_steps": 15426, "loss": 0.393, "lr": 4.8890549988633095e-05, "epoch": 0.08946805406982399, "percentage": 2.98, "elapsed_time": "1:07:35", "remaining_time": "1 day, 12:39:08", "throughput": 44522.17, "total_tokens": 180564224} {"current_steps": 470, "total_steps": 15426, "loss": 0.3873, "lr": 4.8867194257118907e-05, "epoch": 0.09141301176699407, "percentage": 3.05, "elapsed_time": "1:08:34", "remaining_time": "1 day, 12:21:56", "throughput": 44848.88, "total_tokens": 184513792} {"current_steps": 480, "total_steps": 15426, "loss": 0.3874, "lr": 4.884387196578093e-05, "epoch": 0.09335796946416415, "percentage": 3.11, "elapsed_time": "1:09:40", "remaining_time": "1 day, 12:09:31", "throughput": 45084.05, "total_tokens": 188475520} {"current_steps": 490, "total_steps": 15426, "loss": 0.3831, "lr": 4.882058303489718e-05, "epoch": 0.09530292716133425, "percentage": 3.18, "elapsed_time": "1:10:59", "remaining_time": "1 day, 12:04:08", "throughput": 45153.09, "total_tokens": 192347520} {"current_steps": 500, "total_steps": 15426, "loss": 0.387, "lr": 4.8797327385011496e-05, "epoch": 0.09724788485850433, "percentage": 3.24, "elapsed_time": "1:13:04", "remaining_time": "1 day, 12:21:11", "throughput": 44786.59, "total_tokens": 196344448} {"current_steps": 510, "total_steps": 15426, "loss": 0.3794, "lr": 4.8774104936932425e-05, "epoch": 0.09919284255567441, "percentage": 3.31, "elapsed_time": "1:14:32", "remaining_time": "1 day, 12:19:55", "throughput": 44771.79, "total_tokens": 200223872} {"current_steps": 520, "total_steps": 15426, "loss": 0.3845, "lr": 4.8750915611732076e-05, "epoch": 0.1011378002528445, "percentage": 3.37, "elapsed_time": "1:15:57", "remaining_time": "1 day, 12:17:35", "throughput": 44788.36, "total_tokens": 204143232} {"current_steps": 530, "total_steps": 15426, "loss": 0.3832, "lr": 4.8727759330744986e-05, "epoch": 0.10308275795001459, "percentage": 3.44, "elapsed_time": "1:17:21", "remaining_time": "1 day, 12:14:09", "throughput": 44845.52, "total_tokens": 208146560} {"current_steps": 540, "total_steps": 15426, "loss": 0.3801, "lr": 4.870463601556696e-05, "epoch": 0.10502771564718467, "percentage": 3.5, "elapsed_time": "1:18:58", "remaining_time": "1 day, 12:16:55", "throughput": 44758.1, "total_tokens": 212070912} {"current_steps": 550, "total_steps": 15426, "loss": 0.3825, "lr": 4.8681545588054075e-05, "epoch": 0.10697267334435476, "percentage": 3.57, "elapsed_time": "1:20:31", "remaining_time": "1 day, 12:17:45", "throughput": 44716.76, "total_tokens": 216027520} {"current_steps": 560, "total_steps": 15426, "loss": 0.3789, "lr": 4.8658487970321404e-05, "epoch": 0.10891763104152484, "percentage": 3.63, "elapsed_time": "1:21:36", "remaining_time": "1 day, 12:06:22", "throughput": 44926.78, "total_tokens": 219980160} {"current_steps": 570, "total_steps": 15426, "loss": 0.3781, "lr": 4.863546308474209e-05, "epoch": 0.11086258873869494, "percentage": 3.7, "elapsed_time": "1:22:35", "remaining_time": "1 day, 11:52:47", "throughput": 45173.93, "total_tokens": 223879040} {"current_steps": 580, "total_steps": 15426, "loss": 0.3764, "lr": 4.86124708539461e-05, "epoch": 0.11280754643586502, "percentage": 3.76, "elapsed_time": "1:23:33", "remaining_time": "1 day, 11:38:42", "throughput": 45435.95, "total_tokens": 227783296} {"current_steps": 590, "total_steps": 15426, "loss": 0.3738, "lr": 4.8589511200819216e-05, "epoch": 0.1147525041330351, "percentage": 3.82, "elapsed_time": "1:24:33", "remaining_time": "1 day, 11:26:09", "throughput": 45692.3, "total_tokens": 231806336} {"current_steps": 600, "total_steps": 15426, "loss": 0.3744, "lr": 4.8566584048501926e-05, "epoch": 0.1166974618302052, "percentage": 3.89, "elapsed_time": "1:25:26", "remaining_time": "1 day, 11:11:06", "throughput": 45962.5, "total_tokens": 235609472} {"current_steps": 610, "total_steps": 15426, "loss": 0.3759, "lr": 4.854368932038835e-05, "epoch": 0.11864241952737528, "percentage": 3.95, "elapsed_time": "1:26:24", "remaining_time": "1 day, 10:58:45", "throughput": 46206.53, "total_tokens": 239560704} {"current_steps": 620, "total_steps": 15426, "loss": 0.37, "lr": 4.8520826940125144e-05, "epoch": 0.12058737722454536, "percentage": 4.02, "elapsed_time": "1:27:23", "remaining_time": "1 day, 10:47:09", "throughput": 46446.33, "total_tokens": 243564032} {"current_steps": 630, "total_steps": 15426, "loss": 0.3771, "lr": 4.849799683161046e-05, "epoch": 0.12253233492171545, "percentage": 4.08, "elapsed_time": "1:28:19", "remaining_time": "1 day, 10:34:12", "throughput": 46680.79, "total_tokens": 247365888} {"current_steps": 640, "total_steps": 15426, "loss": 0.3717, "lr": 4.8475198918992835e-05, "epoch": 0.12447729261888554, "percentage": 4.15, "elapsed_time": "1:29:18", "remaining_time": "1 day, 10:23:08", "throughput": 46898.24, "total_tokens": 251285248} {"current_steps": 650, "total_steps": 15426, "loss": 0.3757, "lr": 4.845243312667023e-05, "epoch": 0.1264222503160556, "percentage": 4.21, "elapsed_time": "1:30:20", "remaining_time": "1 day, 10:13:29", "throughput": 47082.98, "total_tokens": 255190656} {"current_steps": 660, "total_steps": 15426, "loss": 0.37, "lr": 4.842969937928884e-05, "epoch": 0.1283672080132257, "percentage": 4.28, "elapsed_time": "1:31:36", "remaining_time": "1 day, 10:09:29", "throughput": 47144.84, "total_tokens": 259127680} {"current_steps": 670, "total_steps": 15426, "loss": 0.3702, "lr": 4.840699760174217e-05, "epoch": 0.1303121657103958, "percentage": 4.34, "elapsed_time": "1:32:30", "remaining_time": "1 day, 9:57:27", "throughput": 47359.87, "total_tokens": 262879744} {"current_steps": 680, "total_steps": 15426, "loss": 0.3693, "lr": 4.8384327719169906e-05, "epoch": 0.13225712340756587, "percentage": 4.41, "elapsed_time": "1:33:29", "remaining_time": "1 day, 9:47:13", "throughput": 47564.94, "total_tokens": 266792192} {"current_steps": 690, "total_steps": 15426, "loss": 0.3712, "lr": 4.836168965695694e-05, "epoch": 0.13420208110473597, "percentage": 4.47, "elapsed_time": "1:34:27", "remaining_time": "1 day, 9:37:20", "throughput": 47761.85, "total_tokens": 270696192} {"current_steps": 700, "total_steps": 15426, "loss": 0.3668, "lr": 4.8339083340732304e-05, "epoch": 0.13614703880190607, "percentage": 4.54, "elapsed_time": "1:35:25", "remaining_time": "1 day, 9:27:30", "throughput": 47971.03, "total_tokens": 274664448} {"current_steps": 710, "total_steps": 15426, "loss": 0.37, "lr": 4.8316508696368154e-05, "epoch": 0.13809199649907614, "percentage": 4.6, "elapsed_time": "1:36:24", "remaining_time": "1 day, 9:18:17", "throughput": 48151.26, "total_tokens": 278539008} {"current_steps": 720, "total_steps": 15426, "loss": 0.3678, "lr": 4.8293965649978714e-05, "epoch": 0.14003695419624623, "percentage": 4.67, "elapsed_time": "1:37:23", "remaining_time": "1 day, 9:09:19", "throughput": 48334.91, "total_tokens": 282458752} {"current_steps": 730, "total_steps": 15426, "loss": 0.369, "lr": 4.8271454127919364e-05, "epoch": 0.14198191189341633, "percentage": 4.73, "elapsed_time": "1:38:21", "remaining_time": "1 day, 9:00:15", "throughput": 48527.47, "total_tokens": 286406400} {"current_steps": 740, "total_steps": 15426, "loss": 0.3656, "lr": 4.824897405678549e-05, "epoch": 0.1439268695905864, "percentage": 4.8, "elapsed_time": "1:39:18", "remaining_time": "1 day, 8:51:00", "throughput": 48723.01, "total_tokens": 290335744} {"current_steps": 750, "total_steps": 15426, "loss": 0.3638, "lr": 4.8226525363411576e-05, "epoch": 0.1458718272877565, "percentage": 4.86, "elapsed_time": "1:40:14", "remaining_time": "1 day, 8:41:25", "throughput": 48923.45, "total_tokens": 294233472} {"current_steps": 760, "total_steps": 15426, "loss": 0.3647, "lr": 4.820410797487017e-05, "epoch": 0.1478167849849266, "percentage": 4.93, "elapsed_time": "1:41:11", "remaining_time": "1 day, 8:32:48", "throughput": 49094.79, "total_tokens": 298091648} {"current_steps": 770, "total_steps": 15426, "loss": 0.3632, "lr": 4.818172181847091e-05, "epoch": 0.14976174268209666, "percentage": 4.99, "elapsed_time": "1:42:07", "remaining_time": "1 day, 8:23:48", "throughput": 49284.55, "total_tokens": 301989632} {"current_steps": 780, "total_steps": 15426, "loss": 0.3646, "lr": 4.81593668217595e-05, "epoch": 0.15170670037926676, "percentage": 5.06, "elapsed_time": "1:43:07", "remaining_time": "1 day, 8:16:19", "throughput": 49436.05, "total_tokens": 305877760} {"current_steps": 790, "total_steps": 15426, "loss": 0.361, "lr": 4.813704291251675e-05, "epoch": 0.15365165807643683, "percentage": 5.12, "elapsed_time": "1:44:04", "remaining_time": "1 day, 8:08:14", "throughput": 49610.4, "total_tokens": 309805696} {"current_steps": 800, "total_steps": 15426, "loss": 0.3595, "lr": 4.811475001875759e-05, "epoch": 0.15559661577360692, "percentage": 5.19, "elapsed_time": "1:45:04", "remaining_time": "1 day, 8:01:03", "throughput": 49781.42, "total_tokens": 313850624} {"current_steps": 810, "total_steps": 15426, "loss": 0.3667, "lr": 4.8092488068730105e-05, "epoch": 0.15754157347077702, "percentage": 5.25, "elapsed_time": "1:46:06", "remaining_time": "1 day, 7:54:40", "throughput": 49908.29, "total_tokens": 317741696} {"current_steps": 820, "total_steps": 15426, "loss": 0.3637, "lr": 4.807025699091452e-05, "epoch": 0.1594865311679471, "percentage": 5.32, "elapsed_time": "1:47:00", "remaining_time": "1 day, 7:46:06", "throughput": 50080.24, "total_tokens": 321550208} {"current_steps": 830, "total_steps": 15426, "loss": 0.3635, "lr": 4.8048056714022325e-05, "epoch": 0.16143148886511718, "percentage": 5.38, "elapsed_time": "1:47:57", "remaining_time": "1 day, 7:38:23", "throughput": 50245.44, "total_tokens": 325444608} {"current_steps": 840, "total_steps": 15426, "loss": 0.3602, "lr": 4.802588716699519e-05, "epoch": 0.16337644656228728, "percentage": 5.45, "elapsed_time": "1:48:56", "remaining_time": "1 day, 7:31:36", "throughput": 50400.44, "total_tokens": 329427328} {"current_steps": 850, "total_steps": 15426, "loss": 0.358, "lr": 4.8003748279004156e-05, "epoch": 0.16532140425945735, "percentage": 5.51, "elapsed_time": "1:49:51", "remaining_time": "1 day, 7:24:01", "throughput": 50555.77, "total_tokens": 333263232} {"current_steps": 860, "total_steps": 15426, "loss": 0.3626, "lr": 4.798163997944854e-05, "epoch": 0.16726636195662745, "percentage": 5.58, "elapsed_time": "1:50:47", "remaining_time": "1 day, 7:16:31", "throughput": 50709.54, "total_tokens": 337095424} {"current_steps": 870, "total_steps": 15426, "loss": 0.3607, "lr": 4.79595621979551e-05, "epoch": 0.16921131965379754, "percentage": 5.64, "elapsed_time": "1:51:46", "remaining_time": "1 day, 7:10:05", "throughput": 50843.64, "total_tokens": 340979840} {"current_steps": 880, "total_steps": 15426, "loss": 0.3587, "lr": 4.793751486437702e-05, "epoch": 0.1711562773509676, "percentage": 5.7, "elapsed_time": "1:52:51", "remaining_time": "1 day, 7:05:33", "throughput": 50938.32, "total_tokens": 344940160} {"current_steps": 890, "total_steps": 15426, "loss": 0.3589, "lr": 4.7915497908793064e-05, "epoch": 0.1731012350481377, "percentage": 5.77, "elapsed_time": "1:53:51", "remaining_time": "1 day, 6:59:39", "throughput": 51067.55, "total_tokens": 348877824} {"current_steps": 900, "total_steps": 15426, "loss": 0.3559, "lr": 4.7893511261506516e-05, "epoch": 0.17504619274530778, "percentage": 5.83, "elapsed_time": "1:54:53", "remaining_time": "1 day, 6:54:20", "throughput": 51178.94, "total_tokens": 352801408} {"current_steps": 910, "total_steps": 15426, "loss": 0.3609, "lr": 4.787155485304435e-05, "epoch": 0.17699115044247787, "percentage": 5.9, "elapsed_time": "1:55:47", "remaining_time": "1 day, 6:46:59", "throughput": 51341.89, "total_tokens": 356681472} {"current_steps": 920, "total_steps": 15426, "loss": 0.356, "lr": 4.784962861415629e-05, "epoch": 0.17893610813964797, "percentage": 5.96, "elapsed_time": "1:56:45", "remaining_time": "1 day, 6:40:56", "throughput": 51474.72, "total_tokens": 360599680} {"current_steps": 930, "total_steps": 15426, "loss": 0.3564, "lr": 4.7827732475813884e-05, "epoch": 0.18088106583681804, "percentage": 6.03, "elapsed_time": "1:57:44", "remaining_time": "1 day, 6:35:13", "throughput": 51602.81, "total_tokens": 364542080} {"current_steps": 940, "total_steps": 15426, "loss": 0.3596, "lr": 4.7805866369209576e-05, "epoch": 0.18282602353398814, "percentage": 6.09, "elapsed_time": "1:58:49", "remaining_time": "1 day, 6:31:04", "throughput": 51695.12, "total_tokens": 368541568} {"current_steps": 950, "total_steps": 15426, "loss": 0.3552, "lr": 4.778403022575583e-05, "epoch": 0.18477098123115823, "percentage": 6.16, "elapsed_time": "1:59:48", "remaining_time": "1 day, 6:25:35", "throughput": 51809.85, "total_tokens": 372429312} {"current_steps": 960, "total_steps": 15426, "loss": 0.3549, "lr": 4.7762223977084195e-05, "epoch": 0.1867159389283283, "percentage": 6.22, "elapsed_time": "2:00:46", "remaining_time": "1 day, 6:19:54", "throughput": 51938.07, "total_tokens": 376364032} {"current_steps": 970, "total_steps": 15426, "loss": 0.3587, "lr": 4.774044755504444e-05, "epoch": 0.1886608966254984, "percentage": 6.29, "elapsed_time": "2:01:43", "remaining_time": "1 day, 6:13:59", "throughput": 52067.56, "total_tokens": 380257152} {"current_steps": 980, "total_steps": 15426, "loss": 0.3536, "lr": 4.7718700891703616e-05, "epoch": 0.1906058543226685, "percentage": 6.35, "elapsed_time": "2:02:40", "remaining_time": "1 day, 6:08:14", "throughput": 52196.88, "total_tokens": 384176384} {"current_steps": 990, "total_steps": 15426, "loss": 0.3538, "lr": 4.7696983919345215e-05, "epoch": 0.19255081201983856, "percentage": 6.42, "elapsed_time": "2:03:36", "remaining_time": "1 day, 6:02:27", "throughput": 52322.74, "total_tokens": 388057728} {"current_steps": 1000, "total_steps": 15426, "loss": 0.3528, "lr": 4.7675296570468216e-05, "epoch": 0.19449576971700866, "percentage": 6.48, "elapsed_time": "2:04:35", "remaining_time": "1 day, 5:57:21", "throughput": 52444.4, "total_tokens": 392048896} {"current_steps": 1010, "total_steps": 15426, "loss": 0.3531, "lr": 4.76536387777863e-05, "epoch": 0.19644072741417873, "percentage": 6.55, "elapsed_time": "2:05:32", "remaining_time": "1 day, 5:51:54", "throughput": 52564.8, "total_tokens": 395949696} {"current_steps": 1020, "total_steps": 15426, "loss": 0.3504, "lr": 4.7632010474226915e-05, "epoch": 0.19838568511134883, "percentage": 6.61, "elapsed_time": "2:06:29", "remaining_time": "1 day, 5:46:37", "throughput": 52675.3, "total_tokens": 399803392} {"current_steps": 1030, "total_steps": 15426, "loss": 0.351, "lr": 4.761041159293035e-05, "epoch": 0.20033064280851892, "percentage": 6.68, "elapsed_time": "2:07:27", "remaining_time": "1 day, 5:41:21", "throughput": 52781.07, "total_tokens": 403625088} {"current_steps": 1040, "total_steps": 15426, "loss": 0.3527, "lr": 4.7588842067249e-05, "epoch": 0.202275600505689, "percentage": 6.74, "elapsed_time": "2:08:24", "remaining_time": "1 day, 5:36:18", "throughput": 52895.27, "total_tokens": 407548672} {"current_steps": 1050, "total_steps": 15426, "loss": 0.3482, "lr": 4.756730183074637e-05, "epoch": 0.2042205582028591, "percentage": 6.81, "elapsed_time": "2:09:24", "remaining_time": "1 day, 5:31:47", "throughput": 52999.81, "total_tokens": 411518848} {"current_steps": 1060, "total_steps": 15426, "loss": 0.3499, "lr": 4.7545790817196314e-05, "epoch": 0.20616551590002918, "percentage": 6.87, "elapsed_time": "2:10:19", "remaining_time": "1 day, 5:26:22", "throughput": 53121.96, "total_tokens": 415412480} {"current_steps": 1070, "total_steps": 15426, "loss": 0.3491, "lr": 4.752430896058212e-05, "epoch": 0.20811047359719925, "percentage": 6.94, "elapsed_time": "2:11:19", "remaining_time": "1 day, 5:21:59", "throughput": 53223.84, "total_tokens": 419382016} {"current_steps": 1080, "total_steps": 15426, "loss": 0.3489, "lr": 4.750285619509567e-05, "epoch": 0.21005543129436935, "percentage": 7.0, "elapsed_time": "2:12:14", "remaining_time": "1 day, 5:16:42", "throughput": 53343.78, "total_tokens": 423279232} {"current_steps": 1090, "total_steps": 15426, "loss": 0.3512, "lr": 4.7481432455136644e-05, "epoch": 0.21200038899153945, "percentage": 7.07, "elapsed_time": "2:13:16", "remaining_time": "1 day, 5:12:51", "throughput": 53422.16, "total_tokens": 427188736} {"current_steps": 1100, "total_steps": 15426, "loss": 0.3426, "lr": 4.7460037675311584e-05, "epoch": 0.21394534668870951, "percentage": 7.13, "elapsed_time": "2:14:13", "remaining_time": "1 day, 5:08:10", "throughput": 53527.51, "total_tokens": 431104640} {"current_steps": 1110, "total_steps": 15426, "loss": 0.3498, "lr": 4.7438671790433126e-05, "epoch": 0.2158903043858796, "percentage": 7.2, "elapsed_time": "2:15:07", "remaining_time": "1 day, 5:02:44", "throughput": 53638.95, "total_tokens": 434878464} {"current_steps": 1120, "total_steps": 15426, "loss": 0.3511, "lr": 4.741733473551915e-05, "epoch": 0.21783526208304968, "percentage": 7.26, "elapsed_time": "2:16:05", "remaining_time": "1 day, 4:58:21", "throughput": 53756.04, "total_tokens": 438952064} {"current_steps": 1130, "total_steps": 15426, "loss": 0.3485, "lr": 4.7396026445791966e-05, "epoch": 0.21978021978021978, "percentage": 7.33, "elapsed_time": "2:17:02", "remaining_time": "1 day, 4:53:48", "throughput": 53856.15, "total_tokens": 442846208} {"current_steps": 1140, "total_steps": 15426, "loss": 0.3484, "lr": 4.737474685667742e-05, "epoch": 0.22172517747738987, "percentage": 7.39, "elapsed_time": "2:17:58", "remaining_time": "1 day, 4:49:01", "throughput": 53961.35, "total_tokens": 446715264} {"current_steps": 1150, "total_steps": 15426, "loss": 0.345, "lr": 4.7353495903804165e-05, "epoch": 0.22367013517455994, "percentage": 7.45, "elapsed_time": "2:18:54", "remaining_time": "1 day, 4:44:21", "throughput": 54064.01, "total_tokens": 450588672} {"current_steps": 1160, "total_steps": 15426, "loss": 0.3479, "lr": 4.733227352300277e-05, "epoch": 0.22561509287173004, "percentage": 7.52, "elapsed_time": "2:19:51", "remaining_time": "1 day, 4:40:06", "throughput": 54154.25, "total_tokens": 454458496} {"current_steps": 1170, "total_steps": 15426, "loss": 0.348, "lr": 4.731107965030496e-05, "epoch": 0.22756005056890014, "percentage": 7.58, "elapsed_time": "2:20:47", "remaining_time": "1 day, 4:35:28", "throughput": 54249.38, "total_tokens": 458267520} {"current_steps": 1180, "total_steps": 15426, "loss": 0.3481, "lr": 4.728991422194278e-05, "epoch": 0.2295050082660702, "percentage": 7.65, "elapsed_time": "2:21:44", "remaining_time": "1 day, 4:31:16", "throughput": 54343.5, "total_tokens": 462176640} {"current_steps": 1190, "total_steps": 15426, "loss": 0.345, "lr": 4.726877717434773e-05, "epoch": 0.2314499659632403, "percentage": 7.71, "elapsed_time": "2:22:37", "remaining_time": "1 day, 4:26:11", "throughput": 54458.33, "total_tokens": 466016000} {"current_steps": 1200, "total_steps": 15426, "loss": 0.3464, "lr": 4.724766844415013e-05, "epoch": 0.2333949236604104, "percentage": 7.78, "elapsed_time": "2:23:33", "remaining_time": "1 day, 4:21:57", "throughput": 54552.42, "total_tokens": 469910016} {"current_steps": 1210, "total_steps": 15426, "loss": 0.3458, "lr": 4.722658796817813e-05, "epoch": 0.23533988135758047, "percentage": 7.84, "elapsed_time": "2:24:27", "remaining_time": "1 day, 4:17:08", "throughput": 54653.76, "total_tokens": 473694720} {"current_steps": 1220, "total_steps": 15426, "loss": 0.3461, "lr": 4.7205535683457044e-05, "epoch": 0.23728483905475056, "percentage": 7.91, "elapsed_time": "2:25:24", "remaining_time": "1 day, 4:13:05", "throughput": 54743.83, "total_tokens": 477589888} {"current_steps": 1230, "total_steps": 15426, "loss": 0.3465, "lr": 4.7184511527208484e-05, "epoch": 0.23922979675192066, "percentage": 7.97, "elapsed_time": "2:26:38", "remaining_time": "1 day, 4:12:26", "throughput": 54723.1, "total_tokens": 481474816} {"current_steps": 1240, "total_steps": 15426, "loss": 0.3469, "lr": 4.7163515436849644e-05, "epoch": 0.24117475444909073, "percentage": 8.04, "elapsed_time": "2:27:45", "remaining_time": "1 day, 4:10:18", "throughput": 54765.27, "total_tokens": 485495680} {"current_steps": 1250, "total_steps": 15426, "loss": 0.3458, "lr": 4.714254734999245e-05, "epoch": 0.24311971214626082, "percentage": 8.1, "elapsed_time": "2:28:42", "remaining_time": "1 day, 4:06:26", "throughput": 54842.56, "total_tokens": 489322752} {"current_steps": 1260, "total_steps": 15426, "loss": 0.348, "lr": 4.712160720444284e-05, "epoch": 0.2450646698434309, "percentage": 8.17, "elapsed_time": "2:29:39", "remaining_time": "1 day, 4:02:38", "throughput": 54917.53, "total_tokens": 493147776} {"current_steps": 1270, "total_steps": 15426, "loss": 0.3438, "lr": 4.710069493819992e-05, "epoch": 0.247009627540601, "percentage": 8.23, "elapsed_time": "2:30:36", "remaining_time": "1 day, 3:58:47", "throughput": 55003.83, "total_tokens": 497053312} {"current_steps": 1280, "total_steps": 15426, "loss": 0.3422, "lr": 4.70798104894553e-05, "epoch": 0.2489545852377711, "percentage": 8.3, "elapsed_time": "2:31:34", "remaining_time": "1 day, 3:55:11", "throughput": 55094.21, "total_tokens": 501067136} {"current_steps": 1290, "total_steps": 15426, "loss": 0.3452, "lr": 4.705895379659219e-05, "epoch": 0.25089954293494116, "percentage": 8.36, "elapsed_time": "2:32:32", "remaining_time": "1 day, 3:51:35", "throughput": 55167.13, "total_tokens": 504924416} {"current_steps": 1300, "total_steps": 15426, "loss": 0.3417, "lr": 4.7038124798184766e-05, "epoch": 0.2528445006321112, "percentage": 8.43, "elapsed_time": "2:33:27", "remaining_time": "1 day, 3:47:33", "throughput": 55260.13, "total_tokens": 508824064} {"current_steps": 1310, "total_steps": 15426, "loss": 0.3439, "lr": 4.7017323432997304e-05, "epoch": 0.25478945832928135, "percentage": 8.49, "elapsed_time": "2:34:26", "remaining_time": "1 day, 3:44:15", "throughput": 55340.66, "total_tokens": 512834688} {"current_steps": 1320, "total_steps": 15426, "loss": 0.3425, "lr": 4.6996549639983506e-05, "epoch": 0.2567344160264514, "percentage": 8.56, "elapsed_time": "2:35:25", "remaining_time": "1 day, 3:40:52", "throughput": 55417.76, "total_tokens": 516782720} {"current_steps": 1330, "total_steps": 15426, "loss": 0.3427, "lr": 4.697580335828569e-05, "epoch": 0.2586793737236215, "percentage": 8.62, "elapsed_time": "2:36:24", "remaining_time": "1 day, 3:37:46", "throughput": 55486.44, "total_tokens": 520736384} {"current_steps": 1340, "total_steps": 15426, "loss": 0.3435, "lr": 4.6955084527234076e-05, "epoch": 0.2606243314207916, "percentage": 8.69, "elapsed_time": "2:37:27", "remaining_time": "1 day, 3:35:14", "throughput": 55548.03, "total_tokens": 524803712} {"current_steps": 1350, "total_steps": 15426, "loss": 0.3454, "lr": 4.6934393086346034e-05, "epoch": 0.2625692891179617, "percentage": 8.75, "elapsed_time": "2:38:22", "remaining_time": "1 day, 3:31:23", "throughput": 55627.45, "total_tokens": 528619904} {"current_steps": 1360, "total_steps": 15426, "loss": 0.3403, "lr": 4.6913728975325324e-05, "epoch": 0.26451424681513175, "percentage": 8.82, "elapsed_time": "2:39:17", "remaining_time": "1 day, 3:27:26", "throughput": 55718.7, "total_tokens": 532515968} {"current_steps": 1370, "total_steps": 15426, "loss": 0.3382, "lr": 4.6893092134061393e-05, "epoch": 0.2664592045123019, "percentage": 8.88, "elapsed_time": "2:40:13", "remaining_time": "1 day, 3:23:57", "throughput": 55799.49, "total_tokens": 536451968} {"current_steps": 1380, "total_steps": 15426, "loss": 0.3396, "lr": 4.687248250262859e-05, "epoch": 0.26840416220947194, "percentage": 8.95, "elapsed_time": "2:41:10", "remaining_time": "1 day, 3:20:24", "throughput": 55876.38, "total_tokens": 540329728} {"current_steps": 1390, "total_steps": 15426, "loss": 0.3394, "lr": 4.685190002128548e-05, "epoch": 0.270349119906642, "percentage": 9.01, "elapsed_time": "2:42:05", "remaining_time": "1 day, 3:16:50", "throughput": 55963.4, "total_tokens": 544294144} {"current_steps": 1400, "total_steps": 15426, "loss": 0.34, "lr": 4.6831344630474114e-05, "epoch": 0.27229407760381213, "percentage": 9.08, "elapsed_time": "2:43:04", "remaining_time": "1 day, 3:13:43", "throughput": 56033.82, "total_tokens": 548242432} {"current_steps": 1410, "total_steps": 15426, "loss": 0.3417, "lr": 4.6810816270819276e-05, "epoch": 0.2742390353009822, "percentage": 9.14, "elapsed_time": "2:44:03", "remaining_time": "1 day, 3:10:47", "throughput": 56104.32, "total_tokens": 552257152} {"current_steps": 1420, "total_steps": 15426, "loss": 0.3373, "lr": 4.679031488312777e-05, "epoch": 0.2761839929981523, "percentage": 9.21, "elapsed_time": "2:45:01", "remaining_time": "1 day, 3:07:46", "throughput": 56173.56, "total_tokens": 556228480} {"current_steps": 1430, "total_steps": 15426, "loss": 0.3361, "lr": 4.6769840408387717e-05, "epoch": 0.2781289506953224, "percentage": 9.27, "elapsed_time": "2:45:58", "remaining_time": "1 day, 3:04:27", "throughput": 56250.86, "total_tokens": 560173824} {"current_steps": 1440, "total_steps": 15426, "loss": 0.3406, "lr": 4.674939278776787e-05, "epoch": 0.28007390839249247, "percentage": 9.33, "elapsed_time": "2:46:51", "remaining_time": "1 day, 3:00:41", "throughput": 56333.18, "total_tokens": 564006656} {"current_steps": 1450, "total_steps": 15426, "loss": 0.3387, "lr": 4.672897196261683e-05, "epoch": 0.28201886608966253, "percentage": 9.4, "elapsed_time": "2:47:50", "remaining_time": "1 day, 2:57:44", "throughput": 56394.86, "total_tokens": 567920128} {"current_steps": 1460, "total_steps": 15426, "loss": 0.3364, "lr": 4.670857787446238e-05, "epoch": 0.28396382378683266, "percentage": 9.46, "elapsed_time": "2:48:51", "remaining_time": "1 day, 2:55:10", "throughput": 56446.42, "total_tokens": 571860352} {"current_steps": 1470, "total_steps": 15426, "loss": 0.3404, "lr": 4.668821046501082e-05, "epoch": 0.2859087814840027, "percentage": 9.53, "elapsed_time": "2:49:48", "remaining_time": "1 day, 2:52:07", "throughput": 56520.05, "total_tokens": 575848832} {"current_steps": 1480, "total_steps": 15426, "loss": 0.3371, "lr": 4.6667869676146194e-05, "epoch": 0.2878537391811728, "percentage": 9.59, "elapsed_time": "2:50:44", "remaining_time": "1 day, 2:48:55", "throughput": 56585.8, "total_tokens": 579705088} {"current_steps": 1490, "total_steps": 15426, "loss": 0.3374, "lr": 4.6647555449929645e-05, "epoch": 0.2897986968783429, "percentage": 9.66, "elapsed_time": "2:51:40", "remaining_time": "1 day, 2:45:43", "throughput": 56659.05, "total_tokens": 583635968} {"current_steps": 1500, "total_steps": 15426, "loss": 0.3379, "lr": 4.662726772859869e-05, "epoch": 0.291743654575513, "percentage": 9.72, "elapsed_time": "2:52:37", "remaining_time": "1 day, 2:42:36", "throughput": 56729.08, "total_tokens": 587553792} {"current_steps": 1510, "total_steps": 15426, "loss": 0.3396, "lr": 4.660700645456655e-05, "epoch": 0.29368861227268306, "percentage": 9.79, "elapsed_time": "2:53:33", "remaining_time": "1 day, 2:39:26", "throughput": 56800.78, "total_tokens": 591472768} {"current_steps": 1520, "total_steps": 15426, "loss": 0.3387, "lr": 4.658677157042149e-05, "epoch": 0.2956335699698532, "percentage": 9.85, "elapsed_time": "2:54:26", "remaining_time": "1 day, 2:35:56", "throughput": 56871.93, "total_tokens": 595260288} {"current_steps": 1530, "total_steps": 15426, "loss": 0.3382, "lr": 4.656656301892605e-05, "epoch": 0.29757852766702325, "percentage": 9.92, "elapsed_time": "2:55:21", "remaining_time": "1 day, 2:32:36", "throughput": 56947.44, "total_tokens": 599150592} {"current_steps": 1540, "total_steps": 15426, "loss": 0.3383, "lr": 4.6546380743016465e-05, "epoch": 0.2995234853641933, "percentage": 9.98, "elapsed_time": "2:56:20", "remaining_time": "1 day, 2:30:05", "throughput": 56998.64, "total_tokens": 603088768} {"current_steps": 1550, "total_steps": 15426, "loss": 0.3359, "lr": 4.652622468580193e-05, "epoch": 0.3014684430613634, "percentage": 10.05, "elapsed_time": "2:57:16", "remaining_time": "1 day, 2:26:58", "throughput": 57061.12, "total_tokens": 606914048} {"current_steps": 1560, "total_steps": 15426, "loss": 0.3391, "lr": 4.650609479056392e-05, "epoch": 0.3034134007585335, "percentage": 10.11, "elapsed_time": "2:58:11", "remaining_time": "1 day, 2:23:52", "throughput": 57131.4, "total_tokens": 610830336} {"current_steps": 1570, "total_steps": 15426, "loss": 0.3383, "lr": 4.648599100075556e-05, "epoch": 0.3053583584557036, "percentage": 10.18, "elapsed_time": "2:59:08", "remaining_time": "1 day, 2:21:04", "throughput": 57203.78, "total_tokens": 614881920} {"current_steps": 1580, "total_steps": 15426, "loss": 0.3376, "lr": 4.6465913260000945e-05, "epoch": 0.30730331615287365, "percentage": 10.24, "elapsed_time": "3:00:04", "remaining_time": "1 day, 2:18:02", "throughput": 57270.57, "total_tokens": 618777088} {"current_steps": 1590, "total_steps": 15426, "loss": 0.3334, "lr": 4.644586151209444e-05, "epoch": 0.3092482738500438, "percentage": 10.31, "elapsed_time": "3:01:02", "remaining_time": "1 day, 2:15:25", "throughput": 57336.85, "total_tokens": 622831488} {"current_steps": 1600, "total_steps": 15426, "loss": 0.3361, "lr": 4.6425835701000084e-05, "epoch": 0.31119323154721384, "percentage": 10.37, "elapsed_time": "3:02:02", "remaining_time": "1 day, 2:13:01", "throughput": 57380.9, "total_tokens": 626723840} {"current_steps": 1610, "total_steps": 15426, "loss": 0.3385, "lr": 4.640583577085084e-05, "epoch": 0.3131381892443839, "percentage": 10.44, "elapsed_time": "3:03:10", "remaining_time": "1 day, 2:11:57", "throughput": 57379.37, "total_tokens": 630653952} {"current_steps": 1620, "total_steps": 15426, "loss": 0.3345, "lr": 4.638586166594806e-05, "epoch": 0.31508314694155404, "percentage": 10.5, "elapsed_time": "3:04:38", "remaining_time": "1 day, 2:13:31", "throughput": 57278.59, "total_tokens": 634550016} {"current_steps": 1630, "total_steps": 15426, "loss": 0.3347, "lr": 4.6365913330760726e-05, "epoch": 0.3170281046387241, "percentage": 10.57, "elapsed_time": "3:06:03", "remaining_time": "1 day, 2:14:47", "throughput": 57194.08, "total_tokens": 638500736} {"current_steps": 1640, "total_steps": 15426, "loss": 0.3305, "lr": 4.6345990709924855e-05, "epoch": 0.3189730623358942, "percentage": 10.63, "elapsed_time": "3:07:14", "remaining_time": "1 day, 2:13:59", "throughput": 57185.39, "total_tokens": 642459008} {"current_steps": 1650, "total_steps": 15426, "loss": 0.3354, "lr": 4.632609374824284e-05, "epoch": 0.3209180200330643, "percentage": 10.7, "elapsed_time": "3:08:30", "remaining_time": "1 day, 2:13:50", "throughput": 57148.11, "total_tokens": 646359680} {"current_steps": 1660, "total_steps": 15426, "loss": 0.3342, "lr": 4.630622239068285e-05, "epoch": 0.32286297773023437, "percentage": 10.76, "elapsed_time": "3:09:43", "remaining_time": "1 day, 2:13:17", "throughput": 57134.3, "total_tokens": 650363776} {"current_steps": 1670, "total_steps": 15426, "loss": 0.3298, "lr": 4.628637658237808e-05, "epoch": 0.32480793542740444, "percentage": 10.83, "elapsed_time": "3:10:55", "remaining_time": "1 day, 2:12:39", "throughput": 57106.94, "total_tokens": 654180352} {"current_steps": 1680, "total_steps": 15426, "loss": 0.3301, "lr": 4.626655626862625e-05, "epoch": 0.32675289312457456, "percentage": 10.89, "elapsed_time": "3:12:17", "remaining_time": "1 day, 2:13:17", "throughput": 57033.87, "total_tokens": 658003840} {"current_steps": 1690, "total_steps": 15426, "loss": 0.3321, "lr": 4.624676139488888e-05, "epoch": 0.32869785082174463, "percentage": 10.96, "elapsed_time": "3:13:24", "remaining_time": "1 day, 2:12:00", "throughput": 57041.17, "total_tokens": 661942912} {"current_steps": 1700, "total_steps": 15426, "loss": 0.335, "lr": 4.6226991906790686e-05, "epoch": 0.3306428085189147, "percentage": 11.02, "elapsed_time": "3:14:44", "remaining_time": "1 day, 2:12:23", "throughput": 56977.71, "total_tokens": 665768704} {"current_steps": 1710, "total_steps": 15426, "loss": 0.3329, "lr": 4.620724775011897e-05, "epoch": 0.3325877662160848, "percentage": 11.09, "elapsed_time": "3:15:58", "remaining_time": "1 day, 2:11:58", "throughput": 56954.58, "total_tokens": 669721216} {"current_steps": 1720, "total_steps": 15426, "loss": 0.3311, "lr": 4.618752887082297e-05, "epoch": 0.3345327239132549, "percentage": 11.15, "elapsed_time": "3:17:09", "remaining_time": "1 day, 2:11:00", "throughput": 56954.55, "total_tokens": 673716864} {"current_steps": 1730, "total_steps": 15426, "loss": 0.3348, "lr": 4.616783521501325e-05, "epoch": 0.33647768161042496, "percentage": 11.21, "elapsed_time": "3:18:13", "remaining_time": "1 day, 2:09:17", "throughput": 56972.48, "total_tokens": 677598208} {"current_steps": 1740, "total_steps": 15426, "loss": 0.3319, "lr": 4.614816672896108e-05, "epoch": 0.3384226393075951, "percentage": 11.28, "elapsed_time": "3:19:15", "remaining_time": "1 day, 2:07:14", "throughput": 57009.93, "total_tokens": 681570688} {"current_steps": 1750, "total_steps": 15426, "loss": 0.3323, "lr": 4.612852335909782e-05, "epoch": 0.34036759700476515, "percentage": 11.34, "elapsed_time": "3:20:09", "remaining_time": "1 day, 2:04:13", "throughput": 57070.78, "total_tokens": 685398912} {"current_steps": 1760, "total_steps": 15426, "loss": 0.3315, "lr": 4.6108905052014323e-05, "epoch": 0.3423125547019352, "percentage": 11.41, "elapsed_time": "3:21:02", "remaining_time": "1 day, 2:00:59", "throughput": 57139.5, "total_tokens": 689223296} {"current_steps": 1770, "total_steps": 15426, "loss": 0.331, "lr": 4.608931175446027e-05, "epoch": 0.3442575123991053, "percentage": 11.47, "elapsed_time": "3:21:57", "remaining_time": "1 day, 1:58:09", "throughput": 57204.74, "total_tokens": 693176576} {"current_steps": 1780, "total_steps": 15426, "loss": 0.3288, "lr": 4.606974341334367e-05, "epoch": 0.3462024700962754, "percentage": 11.54, "elapsed_time": "3:22:54", "remaining_time": "1 day, 1:55:36", "throughput": 57261.28, "total_tokens": 697152128} {"current_steps": 1790, "total_steps": 15426, "loss": 0.3329, "lr": 4.605019997573011e-05, "epoch": 0.3481474277934455, "percentage": 11.6, "elapsed_time": "3:23:54", "remaining_time": "1 day, 1:53:17", "throughput": 57305.17, "total_tokens": 701074688} {"current_steps": 1800, "total_steps": 15426, "loss": 0.3295, "lr": 4.603068138884229e-05, "epoch": 0.35009238549061555, "percentage": 11.67, "elapsed_time": "3:24:55", "remaining_time": "1 day, 1:51:18", "throughput": 57336.11, "total_tokens": 704988544} {"current_steps": 1810, "total_steps": 15426, "loss": 0.3284, "lr": 4.6011187600059345e-05, "epoch": 0.3520373431877857, "percentage": 11.73, "elapsed_time": "3:25:57", "remaining_time": "1 day, 1:49:22", "throughput": 57369.05, "total_tokens": 708949376} {"current_steps": 1820, "total_steps": 15426, "loss": 0.3295, "lr": 4.599171855691629e-05, "epoch": 0.35398230088495575, "percentage": 11.8, "elapsed_time": "3:26:54", "remaining_time": "1 day, 1:46:47", "throughput": 57425.19, "total_tokens": 712894208} {"current_steps": 1830, "total_steps": 15426, "loss": 0.3328, "lr": 4.597227420710335e-05, "epoch": 0.3559272585821258, "percentage": 11.86, "elapsed_time": "3:27:46", "remaining_time": "1 day, 1:43:43", "throughput": 57483.39, "total_tokens": 716642048} {"current_steps": 1840, "total_steps": 15426, "loss": 0.3308, "lr": 4.595285449846551e-05, "epoch": 0.35787221627929594, "percentage": 11.93, "elapsed_time": "3:28:39", "remaining_time": "1 day, 1:40:37", "throughput": 57550.42, "total_tokens": 720481280} {"current_steps": 1850, "total_steps": 15426, "loss": 0.3283, "lr": 4.593345937900178e-05, "epoch": 0.359817173976466, "percentage": 11.99, "elapsed_time": "3:29:38", "remaining_time": "1 day, 1:38:27", "throughput": 57591.35, "total_tokens": 724427136} {"current_steps": 1860, "total_steps": 15426, "loss": 0.3312, "lr": 4.591408879686472e-05, "epoch": 0.3617621316736361, "percentage": 12.06, "elapsed_time": "3:30:34", "remaining_time": "1 day, 1:35:50", "throughput": 57643.7, "total_tokens": 728300928} {"current_steps": 1870, "total_steps": 15426, "loss": 0.3314, "lr": 4.5894742700359775e-05, "epoch": 0.3637070893708062, "percentage": 12.12, "elapsed_time": "3:31:52", "remaining_time": "1 day, 1:35:57", "throughput": 57597.84, "total_tokens": 732226176} {"current_steps": 1880, "total_steps": 15426, "loss": 0.3283, "lr": 4.587542103794477e-05, "epoch": 0.36565204706797627, "percentage": 12.19, "elapsed_time": "3:33:05", "remaining_time": "1 day, 1:35:26", "throughput": 57573.84, "total_tokens": 736130816} {"current_steps": 1890, "total_steps": 15426, "loss": 0.3291, "lr": 4.5856123758229247e-05, "epoch": 0.36759700476514634, "percentage": 12.25, "elapsed_time": "3:34:28", "remaining_time": "1 day, 1:36:04", "throughput": 57505.65, "total_tokens": 740022656} {"current_steps": 1900, "total_steps": 15426, "loss": 0.3269, "lr": 4.5836850809973993e-05, "epoch": 0.36954196246231646, "percentage": 12.32, "elapsed_time": "3:36:06", "remaining_time": "1 day, 1:38:28", "throughput": 57370.6, "total_tokens": 743903488} {"current_steps": 1910, "total_steps": 15426, "loss": 0.329, "lr": 4.5817602142090385e-05, "epoch": 0.37148692015948653, "percentage": 12.38, "elapsed_time": "3:37:19", "remaining_time": "1 day, 1:37:54", "throughput": 57354.54, "total_tokens": 747888256} {"current_steps": 1920, "total_steps": 15426, "loss": 0.3315, "lr": 4.579837770363989e-05, "epoch": 0.3734318778566566, "percentage": 12.45, "elapsed_time": "3:38:34", "remaining_time": "1 day, 1:37:31", "throughput": 57323.55, "total_tokens": 751761408} {"current_steps": 1930, "total_steps": 15426, "loss": 0.3268, "lr": 4.57791774438334e-05, "epoch": 0.3753768355538267, "percentage": 12.51, "elapsed_time": "3:39:44", "remaining_time": "1 day, 1:36:33", "throughput": 57321.78, "total_tokens": 755740800} {"current_steps": 1940, "total_steps": 15426, "loss": 0.3282, "lr": 4.576000131203078e-05, "epoch": 0.3773217932509968, "percentage": 12.58, "elapsed_time": "3:41:09", "remaining_time": "1 day, 1:37:25", "throughput": 57253.6, "total_tokens": 759743744} {"current_steps": 1950, "total_steps": 15426, "loss": 0.3269, "lr": 4.574084925774023e-05, "epoch": 0.37926675094816686, "percentage": 12.64, "elapsed_time": "3:42:25", "remaining_time": "1 day, 1:37:08", "throughput": 57225.03, "total_tokens": 763706112} {"current_steps": 1960, "total_steps": 15426, "loss": 0.3237, "lr": 4.5721721230617795e-05, "epoch": 0.381211708645337, "percentage": 12.71, "elapsed_time": "3:43:49", "remaining_time": "1 day, 1:37:46", "throughput": 57165.76, "total_tokens": 767710080} {"current_steps": 1970, "total_steps": 15426, "loss": 0.3274, "lr": 4.57026171804667e-05, "epoch": 0.38315666634250706, "percentage": 12.77, "elapsed_time": "3:45:21", "remaining_time": "1 day, 1:39:15", "throughput": 57061.42, "total_tokens": 771532416} {"current_steps": 1980, "total_steps": 15426, "loss": 0.3239, "lr": 4.568353705723692e-05, "epoch": 0.3851016240396771, "percentage": 12.84, "elapsed_time": "3:46:51", "remaining_time": "1 day, 1:40:37", "throughput": 56968.78, "total_tokens": 775454976} {"current_steps": 1990, "total_steps": 15426, "loss": 0.3263, "lr": 4.566448081102455e-05, "epoch": 0.38704658173684725, "percentage": 12.9, "elapsed_time": "3:48:11", "remaining_time": "1 day, 1:40:41", "throughput": 56918.04, "total_tokens": 779295616} {"current_steps": 2000, "total_steps": 15426, "loss": 0.3242, "lr": 4.564544839207128e-05, "epoch": 0.3889915394340173, "percentage": 12.97, "elapsed_time": "3:49:19", "remaining_time": "1 day, 1:39:25", "throughput": 56916.72, "total_tokens": 783131520} {"current_steps": 2010, "total_steps": 15426, "loss": 0.3256, "lr": 4.562643975076387e-05, "epoch": 0.3909364971311874, "percentage": 13.03, "elapsed_time": "3:50:49", "remaining_time": "1 day, 1:40:37", "throughput": 56828.12, "total_tokens": 787017472} {"current_steps": 2020, "total_steps": 15426, "loss": 0.3277, "lr": 4.560745483763357e-05, "epoch": 0.39288145482835746, "percentage": 13.09, "elapsed_time": "3:51:55", "remaining_time": "1 day, 1:39:13", "throughput": 56838.7, "total_tokens": 790953600} {"current_steps": 2030, "total_steps": 15426, "loss": 0.3278, "lr": 4.5588493603355595e-05, "epoch": 0.3948264125255276, "percentage": 13.16, "elapsed_time": "3:53:04", "remaining_time": "1 day, 1:38:05", "throughput": 56833.52, "total_tokens": 794805632} {"current_steps": 2040, "total_steps": 15426, "loss": 0.3271, "lr": 4.556955599874859e-05, "epoch": 0.39677137022269765, "percentage": 13.22, "elapsed_time": "3:54:04", "remaining_time": "1 day, 1:35:55", "throughput": 56870.62, "total_tokens": 798711680} {"current_steps": 2050, "total_steps": 15426, "loss": 0.3256, "lr": 4.555064197477409e-05, "epoch": 0.3987163279198677, "percentage": 13.29, "elapsed_time": "3:54:57", "remaining_time": "1 day, 1:33:04", "throughput": 56933.37, "total_tokens": 802616576} {"current_steps": 2060, "total_steps": 15426, "loss": 0.3242, "lr": 4.5531751482536e-05, "epoch": 0.40066128561703784, "percentage": 13.35, "elapsed_time": "3:55:57", "remaining_time": "1 day, 1:30:56", "throughput": 56974.01, "total_tokens": 806592512} {"current_steps": 2070, "total_steps": 15426, "loss": 0.3256, "lr": 4.5512884473280024e-05, "epoch": 0.4026062433142079, "percentage": 13.42, "elapsed_time": "3:56:50", "remaining_time": "1 day, 1:28:10", "throughput": 57033.09, "total_tokens": 810487680} {"current_steps": 2080, "total_steps": 15426, "loss": 0.3269, "lr": 4.549404089839322e-05, "epoch": 0.404551201011378, "percentage": 13.48, "elapsed_time": "3:57:43", "remaining_time": "1 day, 1:25:22", "throughput": 57090.11, "total_tokens": 814326912} {"current_steps": 2090, "total_steps": 15426, "loss": 0.3284, "lr": 4.547522070940335e-05, "epoch": 0.4064961587085481, "percentage": 13.55, "elapsed_time": "3:58:39", "remaining_time": "1 day, 1:22:48", "throughput": 57147.14, "total_tokens": 818296960} {"current_steps": 2100, "total_steps": 15426, "loss": 0.3293, "lr": 4.545642385797848e-05, "epoch": 0.4084411164057182, "percentage": 13.61, "elapsed_time": "3:59:35", "remaining_time": "1 day, 1:20:21", "throughput": 57197.19, "total_tokens": 822222080} {"current_steps": 2110, "total_steps": 15426, "loss": 0.3226, "lr": 4.543765029592637e-05, "epoch": 0.41038607410288824, "percentage": 13.68, "elapsed_time": "4:00:30", "remaining_time": "1 day, 1:17:48", "throughput": 57249.31, "total_tokens": 826130176} {"current_steps": 2120, "total_steps": 15426, "loss": 0.3264, "lr": 4.541889997519403e-05, "epoch": 0.41233103180005837, "percentage": 13.74, "elapsed_time": "4:01:25", "remaining_time": "1 day, 1:15:14", "throughput": 57302.53, "total_tokens": 830034176} {"current_steps": 2130, "total_steps": 15426, "loss": 0.3241, "lr": 4.5400172847867095e-05, "epoch": 0.41427598949722844, "percentage": 13.81, "elapsed_time": "4:02:19", "remaining_time": "1 day, 1:12:39", "throughput": 57349.84, "total_tokens": 833842304} {"current_steps": 2140, "total_steps": 15426, "loss": 0.3214, "lr": 4.5381468866169466e-05, "epoch": 0.4162209471943985, "percentage": 13.87, "elapsed_time": "4:03:16", "remaining_time": "1 day, 1:10:19", "throughput": 57397.17, "total_tokens": 837779456} {"current_steps": 2150, "total_steps": 15426, "loss": 0.3204, "lr": 4.5362787982462616e-05, "epoch": 0.41816590489156863, "percentage": 13.94, "elapsed_time": "4:04:09", "remaining_time": "1 day, 1:07:41", "throughput": 57449.58, "total_tokens": 841635328} {"current_steps": 2160, "total_steps": 15426, "loss": 0.3224, "lr": 4.5344130149245275e-05, "epoch": 0.4201108625887387, "percentage": 14.0, "elapsed_time": "4:05:02", "remaining_time": "1 day, 1:04:59", "throughput": 57505.57, "total_tokens": 845487744} {"current_steps": 2170, "total_steps": 15426, "loss": 0.3236, "lr": 4.5325495319152715e-05, "epoch": 0.42205582028590877, "percentage": 14.07, "elapsed_time": "4:05:57", "remaining_time": "1 day, 1:02:30", "throughput": 57557.12, "total_tokens": 849407488} {"current_steps": 2180, "total_steps": 15426, "loss": 0.3229, "lr": 4.530688344495644e-05, "epoch": 0.4240007779830789, "percentage": 14.13, "elapsed_time": "4:06:53", "remaining_time": "1 day, 1:00:10", "throughput": 57597.55, "total_tokens": 853232256} {"current_steps": 2190, "total_steps": 15426, "loss": 0.3231, "lr": 4.528829447956357e-05, "epoch": 0.42594573568024896, "percentage": 14.2, "elapsed_time": "4:07:51", "remaining_time": "1 day, 0:58:00", "throughput": 57632.6, "total_tokens": 857081600} {"current_steps": 2200, "total_steps": 15426, "loss": 0.3264, "lr": 4.526972837601633e-05, "epoch": 0.42789069337741903, "percentage": 14.26, "elapsed_time": "4:08:47", "remaining_time": "1 day, 0:55:41", "throughput": 57676.22, "total_tokens": 860965376} {"current_steps": 2210, "total_steps": 15426, "loss": 0.3235, "lr": 4.525118508749165e-05, "epoch": 0.42983565107458915, "percentage": 14.33, "elapsed_time": "4:09:40", "remaining_time": "1 day, 0:53:04", "throughput": 57729.67, "total_tokens": 864820992} {"current_steps": 2220, "total_steps": 15426, "loss": 0.323, "lr": 4.5232664567300546e-05, "epoch": 0.4317806087717592, "percentage": 14.39, "elapsed_time": "4:10:34", "remaining_time": "1 day, 0:50:35", "throughput": 57777.2, "total_tokens": 868658176} {"current_steps": 2230, "total_steps": 15426, "loss": 0.323, "lr": 4.521416676888773e-05, "epoch": 0.4337255664689293, "percentage": 14.46, "elapsed_time": "4:11:31", "remaining_time": "1 day, 0:48:23", "throughput": 57821.64, "total_tokens": 872609920} {"current_steps": 2240, "total_steps": 15426, "loss": 0.3247, "lr": 4.519569164583107e-05, "epoch": 0.43567052416609936, "percentage": 14.52, "elapsed_time": "4:12:26", "remaining_time": "1 day, 0:46:03", "throughput": 57872.2, "total_tokens": 876585600} {"current_steps": 2250, "total_steps": 15426, "loss": 0.3265, "lr": 4.517723915184109e-05, "epoch": 0.4376154818632695, "percentage": 14.59, "elapsed_time": "4:13:27", "remaining_time": "1 day, 0:44:16", "throughput": 57908.39, "total_tokens": 880658944} {"current_steps": 2260, "total_steps": 15426, "loss": 0.3206, "lr": 4.5158809240760506e-05, "epoch": 0.43956043956043955, "percentage": 14.65, "elapsed_time": "4:14:22", "remaining_time": "1 day, 0:41:56", "throughput": 57957.06, "total_tokens": 884592768} {"current_steps": 2270, "total_steps": 15426, "loss": 0.3252, "lr": 4.514040186656375e-05, "epoch": 0.4415053972576096, "percentage": 14.72, "elapsed_time": "4:15:16", "remaining_time": "1 day, 0:39:26", "throughput": 58008.35, "total_tokens": 888471040} {"current_steps": 2280, "total_steps": 15426, "loss": 0.3155, "lr": 4.512201698335644e-05, "epoch": 0.44345035495477975, "percentage": 14.78, "elapsed_time": "4:16:10", "remaining_time": "1 day, 0:37:03", "throughput": 58058.46, "total_tokens": 892395264} {"current_steps": 2290, "total_steps": 15426, "loss": 0.3239, "lr": 4.510365454537496e-05, "epoch": 0.4453953126519498, "percentage": 14.85, "elapsed_time": "4:17:06", "remaining_time": "1 day, 0:34:48", "throughput": 58098.02, "total_tokens": 896235264} {"current_steps": 2300, "total_steps": 15426, "loss": 0.3217, "lr": 4.5085314506985945e-05, "epoch": 0.4473402703491199, "percentage": 14.91, "elapsed_time": "4:18:01", "remaining_time": "1 day, 0:32:33", "throughput": 58141.75, "total_tokens": 900135424} {"current_steps": 2310, "total_steps": 15426, "loss": 0.3238, "lr": 4.50669968226858e-05, "epoch": 0.44928522804629, "percentage": 14.97, "elapsed_time": "4:18:57", "remaining_time": "1 day, 0:30:18", "throughput": 58184.55, "total_tokens": 904017664} {"current_steps": 2320, "total_steps": 15426, "loss": 0.3209, "lr": 4.504870144710027e-05, "epoch": 0.4512301857434601, "percentage": 15.04, "elapsed_time": "4:19:52", "remaining_time": "1 day, 0:28:01", "throughput": 58226.98, "total_tokens": 907879296} {"current_steps": 2330, "total_steps": 15426, "loss": 0.3185, "lr": 4.5030428334983884e-05, "epoch": 0.45317514344063015, "percentage": 15.1, "elapsed_time": "4:20:49", "remaining_time": "1 day, 0:26:01", "throughput": 58258.32, "total_tokens": 911737856} {"current_steps": 2340, "total_steps": 15426, "loss": 0.3224, "lr": 4.501217744121959e-05, "epoch": 0.45512010113780027, "percentage": 15.17, "elapsed_time": "4:21:44", "remaining_time": "1 day, 0:23:45", "throughput": 58300.7, "total_tokens": 915590784} {"current_steps": 2350, "total_steps": 15426, "loss": 0.3243, "lr": 4.499394872081821e-05, "epoch": 0.45706505883497034, "percentage": 15.23, "elapsed_time": "4:22:39", "remaining_time": "1 day, 0:21:31", "throughput": 58342.95, "total_tokens": 919475712} {"current_steps": 2360, "total_steps": 15426, "loss": 0.3207, "lr": 4.4975742128918e-05, "epoch": 0.4590100165321404, "percentage": 15.3, "elapsed_time": "4:23:32", "remaining_time": "1 day, 0:19:06", "throughput": 58389.21, "total_tokens": 923294848} {"current_steps": 2370, "total_steps": 15426, "loss": 0.3213, "lr": 4.495755762078418e-05, "epoch": 0.46095497422931053, "percentage": 15.36, "elapsed_time": "4:24:27", "remaining_time": "1 day, 0:16:52", "throughput": 58434.37, "total_tokens": 927219456} {"current_steps": 2380, "total_steps": 15426, "loss": 0.3223, "lr": 4.49393951518085e-05, "epoch": 0.4628999319264806, "percentage": 15.43, "elapsed_time": "4:25:21", "remaining_time": "1 day, 0:14:36", "throughput": 58483.02, "total_tokens": 931164288} {"current_steps": 2390, "total_steps": 15426, "loss": 0.3212, "lr": 4.4921254677508716e-05, "epoch": 0.46484488962365067, "percentage": 15.49, "elapsed_time": "4:26:17", "remaining_time": "1 day, 0:12:27", "throughput": 58526.11, "total_tokens": 935104768} {"current_steps": 2400, "total_steps": 15426, "loss": 0.3213, "lr": 4.490313615352821e-05, "epoch": 0.4667898473208208, "percentage": 15.56, "elapsed_time": "4:27:12", "remaining_time": "1 day, 0:10:17", "throughput": 58569.73, "total_tokens": 939030144} {"current_steps": 2410, "total_steps": 15426, "loss": 0.3196, "lr": 4.48850395356355e-05, "epoch": 0.46873480501799086, "percentage": 15.62, "elapsed_time": "4:28:08", "remaining_time": "1 day, 0:08:12", "throughput": 58610.16, "total_tokens": 942967040} {"current_steps": 2420, "total_steps": 15426, "loss": 0.3198, "lr": 4.486696477972375e-05, "epoch": 0.47067976271516093, "percentage": 15.69, "elapsed_time": "4:29:04", "remaining_time": "1 day, 0:06:08", "throughput": 58648.72, "total_tokens": 946874880} {"current_steps": 2430, "total_steps": 15426, "loss": 0.3158, "lr": 4.484891184181041e-05, "epoch": 0.47262472041233106, "percentage": 15.75, "elapsed_time": "4:30:01", "remaining_time": "1 day, 0:04:06", "throughput": 58685.08, "total_tokens": 950772736} {"current_steps": 2440, "total_steps": 15426, "loss": 0.3198, "lr": 4.483088067803662e-05, "epoch": 0.4745696781095011, "percentage": 15.82, "elapsed_time": "4:30:56", "remaining_time": "1 day, 0:01:59", "throughput": 58727.45, "total_tokens": 954702208} {"current_steps": 2450, "total_steps": 15426, "loss": 0.3201, "lr": 4.481287124466697e-05, "epoch": 0.4765146358066712, "percentage": 15.88, "elapsed_time": "4:31:53", "remaining_time": "1 day, 0:00:01", "throughput": 58768.41, "total_tokens": 958714368} {"current_steps": 2460, "total_steps": 15426, "loss": 0.3225, "lr": 4.479488349808885e-05, "epoch": 0.4784595935038413, "percentage": 15.95, "elapsed_time": "4:32:46", "remaining_time": "23:57:45", "throughput": 58809.18, "total_tokens": 962523648} {"current_steps": 2470, "total_steps": 15426, "loss": 0.3208, "lr": 4.4776917394812114e-05, "epoch": 0.4804045512010114, "percentage": 16.01, "elapsed_time": "4:33:42", "remaining_time": "23:55:42", "throughput": 58850.38, "total_tokens": 966478080} {"current_steps": 2480, "total_steps": 15426, "loss": 0.3155, "lr": 4.475897289146862e-05, "epoch": 0.48234950889818146, "percentage": 16.08, "elapsed_time": "4:34:38", "remaining_time": "23:53:42", "throughput": 58887.92, "total_tokens": 970404992} {"current_steps": 2490, "total_steps": 15426, "loss": 0.3194, "lr": 4.4741049944811806e-05, "epoch": 0.4842944665953515, "percentage": 16.14, "elapsed_time": "4:35:37", "remaining_time": "23:51:55", "throughput": 58922.27, "total_tokens": 974429568} {"current_steps": 2500, "total_steps": 15426, "loss": 0.3133, "lr": 4.472314851171621e-05, "epoch": 0.48623942429252165, "percentage": 16.21, "elapsed_time": "4:36:29", "remaining_time": "23:49:34", "throughput": 58970.45, "total_tokens": 978296576} {"current_steps": 2510, "total_steps": 15426, "loss": 0.3163, "lr": 4.4705268549177084e-05, "epoch": 0.4881843819896917, "percentage": 16.27, "elapsed_time": "4:37:27", "remaining_time": "23:47:43", "throughput": 59004.84, "total_tokens": 982266368} {"current_steps": 2520, "total_steps": 15426, "loss": 0.3193, "lr": 4.468741001430989e-05, "epoch": 0.4901293396868618, "percentage": 16.34, "elapsed_time": "4:38:23", "remaining_time": "23:45:47", "throughput": 59038.23, "total_tokens": 986164864} {"current_steps": 2530, "total_steps": 15426, "loss": 0.3187, "lr": 4.466957286434997e-05, "epoch": 0.4920742973840319, "percentage": 16.4, "elapsed_time": "4:39:17", "remaining_time": "23:43:37", "throughput": 59078.69, "total_tokens": 990018688} {"current_steps": 2540, "total_steps": 15426, "loss": 0.3146, "lr": 4.4651757056652e-05, "epoch": 0.494019255081202, "percentage": 16.47, "elapsed_time": "4:40:14", "remaining_time": "23:41:42", "throughput": 59118.96, "total_tokens": 994042496} {"current_steps": 2550, "total_steps": 15426, "loss": 0.3155, "lr": 4.463396254868968e-05, "epoch": 0.49596421277837205, "percentage": 16.53, "elapsed_time": "4:41:06", "remaining_time": "23:39:26", "throughput": 59165.2, "total_tokens": 997919360} {"current_steps": 2560, "total_steps": 15426, "loss": 0.3171, "lr": 4.461618929805519e-05, "epoch": 0.4979091704755422, "percentage": 16.6, "elapsed_time": "4:42:01", "remaining_time": "23:37:21", "throughput": 59205.47, "total_tokens": 1001822720} {"current_steps": 2570, "total_steps": 15426, "loss": 0.3174, "lr": 4.459843726245888e-05, "epoch": 0.49985412817271224, "percentage": 16.66, "elapsed_time": "4:42:59", "remaining_time": "23:35:37", "throughput": 59241.66, "total_tokens": 1005902464} {"current_steps": 2580, "total_steps": 15426, "loss": 0.3174, "lr": 4.458070639972875e-05, "epoch": 0.5017990858698823, "percentage": 16.73, "elapsed_time": "4:43:55", "remaining_time": "23:33:41", "throughput": 59276.81, "total_tokens": 1009819776} {"current_steps": 2590, "total_steps": 15426, "loss": 0.312, "lr": 4.456299666781007e-05, "epoch": 0.5037440435670524, "percentage": 16.79, "elapsed_time": "4:44:59", "remaining_time": "23:32:23", "throughput": 59290.02, "total_tokens": 1013808768} {"current_steps": 2600, "total_steps": 15426, "loss": 0.314, "lr": 4.4545308024764984e-05, "epoch": 0.5056890012642224, "percentage": 16.85, "elapsed_time": "4:45:59", "remaining_time": "23:30:48", "throughput": 59306.24, "total_tokens": 1017654272} {"current_steps": 2610, "total_steps": 15426, "loss": 0.3209, "lr": 4.452764042877207e-05, "epoch": 0.5076339589613926, "percentage": 16.92, "elapsed_time": "4:46:58", "remaining_time": "23:29:08", "throughput": 59329.42, "total_tokens": 1021565824} {"current_steps": 2620, "total_steps": 15426, "loss": 0.3157, "lr": 4.45099938381259e-05, "epoch": 0.5095789166585627, "percentage": 16.98, "elapsed_time": "4:48:06", "remaining_time": "23:28:11", "throughput": 59319.29, "total_tokens": 1025413504} {"current_steps": 2630, "total_steps": 15426, "loss": 0.3133, "lr": 4.449236821123667e-05, "epoch": 0.5115238743557328, "percentage": 17.05, "elapsed_time": "4:49:04", "remaining_time": "23:26:25", "throughput": 59348.62, "total_tokens": 1029348352} {"current_steps": 2640, "total_steps": 15426, "loss": 0.3162, "lr": 4.447476350662976e-05, "epoch": 0.5134688320529028, "percentage": 17.11, "elapsed_time": "4:50:01", "remaining_time": "23:24:38", "throughput": 59377.78, "total_tokens": 1033263360} {"current_steps": 2650, "total_steps": 15426, "loss": 0.314, "lr": 4.4457179682945346e-05, "epoch": 0.5154137897500729, "percentage": 17.18, "elapsed_time": "4:51:00", "remaining_time": "23:22:57", "throughput": 59409.48, "total_tokens": 1037292160} {"current_steps": 2660, "total_steps": 15426, "loss": 0.3175, "lr": 4.443961669893798e-05, "epoch": 0.517358747447243, "percentage": 17.24, "elapsed_time": "4:51:54", "remaining_time": "23:20:56", "throughput": 59449.47, "total_tokens": 1041229952} {"current_steps": 2670, "total_steps": 15426, "loss": 0.3168, "lr": 4.4422074513476155e-05, "epoch": 0.5193037051444132, "percentage": 17.31, "elapsed_time": "4:52:49", "remaining_time": "23:18:59", "throughput": 59486.17, "total_tokens": 1045152384} {"current_steps": 2680, "total_steps": 15426, "loss": 0.3152, "lr": 4.4404553085541955e-05, "epoch": 0.5212486628415832, "percentage": 17.37, "elapsed_time": "4:53:47", "remaining_time": "23:17:14", "throughput": 59520.04, "total_tokens": 1049169024} {"current_steps": 2690, "total_steps": 15426, "loss": 0.3163, "lr": 4.438705237423063e-05, "epoch": 0.5231936205387533, "percentage": 17.44, "elapsed_time": "4:54:42", "remaining_time": "23:15:16", "throughput": 59553.98, "total_tokens": 1053034624} {"current_steps": 2700, "total_steps": 15426, "loss": 0.3143, "lr": 4.436957233875017e-05, "epoch": 0.5251385782359234, "percentage": 17.5, "elapsed_time": "4:55:36", "remaining_time": "23:13:19", "throughput": 59590.41, "total_tokens": 1056937984} {"current_steps": 2710, "total_steps": 15426, "loss": 0.3136, "lr": 4.4352112938420956e-05, "epoch": 0.5270835359330934, "percentage": 17.57, "elapsed_time": "4:56:31", "remaining_time": "23:11:23", "throughput": 59625.73, "total_tokens": 1060850176} {"current_steps": 2720, "total_steps": 15426, "loss": 0.3141, "lr": 4.433467413267529e-05, "epoch": 0.5290284936302635, "percentage": 17.63, "elapsed_time": "4:57:25", "remaining_time": "23:09:24", "throughput": 59664.2, "total_tokens": 1064763776} {"current_steps": 2730, "total_steps": 15426, "loss": 0.3123, "lr": 4.431725588105708e-05, "epoch": 0.5309734513274337, "percentage": 17.7, "elapsed_time": "4:58:21", "remaining_time": "23:07:33", "throughput": 59700.26, "total_tokens": 1068749568} {"current_steps": 2740, "total_steps": 15426, "loss": 0.3169, "lr": 4.4299858143221377e-05, "epoch": 0.5329184090246037, "percentage": 17.76, "elapsed_time": "4:59:13", "remaining_time": "23:05:25", "throughput": 59738.46, "total_tokens": 1072535424} {"current_steps": 2750, "total_steps": 15426, "loss": 0.3137, "lr": 4.4282480878934065e-05, "epoch": 0.5348633667217738, "percentage": 17.83, "elapsed_time": "5:00:08", "remaining_time": "23:03:28", "throughput": 59771.88, "total_tokens": 1076396416} {"current_steps": 2760, "total_steps": 15426, "loss": 0.3146, "lr": 4.4265124048071346e-05, "epoch": 0.5368083244189439, "percentage": 17.89, "elapsed_time": "5:01:03", "remaining_time": "23:01:37", "throughput": 59805.53, "total_tokens": 1080323968} {"current_steps": 2770, "total_steps": 15426, "loss": 0.3124, "lr": 4.4247787610619477e-05, "epoch": 0.538753282116114, "percentage": 17.96, "elapsed_time": "5:01:59", "remaining_time": "22:59:49", "throughput": 59840.01, "total_tokens": 1084300416} {"current_steps": 2780, "total_steps": 15426, "loss": 0.3136, "lr": 4.42304715266743e-05, "epoch": 0.540698239813284, "percentage": 18.02, "elapsed_time": "5:02:55", "remaining_time": "22:57:59", "throughput": 59873.79, "total_tokens": 1088248576} {"current_steps": 2790, "total_steps": 15426, "loss": 0.3168, "lr": 4.421317575644092e-05, "epoch": 0.5426431975104542, "percentage": 18.09, "elapsed_time": "5:03:45", "remaining_time": "22:55:43", "throughput": 59915.75, "total_tokens": 1091989376} {"current_steps": 2800, "total_steps": 15426, "loss": 0.3147, "lr": 4.419590026023325e-05, "epoch": 0.5445881552076243, "percentage": 18.15, "elapsed_time": "5:04:38", "remaining_time": "22:53:41", "throughput": 59954.26, "total_tokens": 1095848960} {"current_steps": 2810, "total_steps": 15426, "loss": 0.3129, "lr": 4.417864499847368e-05, "epoch": 0.5465331129047943, "percentage": 18.22, "elapsed_time": "5:05:33", "remaining_time": "22:51:52", "throughput": 59986.72, "total_tokens": 1099779840} {"current_steps": 2820, "total_steps": 15426, "loss": 0.3127, "lr": 4.4161409931692676e-05, "epoch": 0.5484780706019644, "percentage": 18.28, "elapsed_time": "5:06:30", "remaining_time": "22:50:09", "throughput": 60022.61, "total_tokens": 1103845248} {"current_steps": 2830, "total_steps": 15426, "loss": 0.3142, "lr": 4.414419502052841e-05, "epoch": 0.5504230282991345, "percentage": 18.35, "elapsed_time": "5:07:24", "remaining_time": "22:48:14", "throughput": 60060.72, "total_tokens": 1107792896} {"current_steps": 2840, "total_steps": 15426, "loss": 0.3164, "lr": 4.412700022572637e-05, "epoch": 0.5523679859963045, "percentage": 18.41, "elapsed_time": "5:08:18", "remaining_time": "22:46:21", "throughput": 60098.46, "total_tokens": 1111751680} {"current_steps": 2850, "total_steps": 15426, "loss": 0.3152, "lr": 4.410982550813902e-05, "epoch": 0.5543129436934746, "percentage": 18.48, "elapsed_time": "5:09:14", "remaining_time": "22:44:35", "throughput": 60130.93, "total_tokens": 1115713536} {"current_steps": 2860, "total_steps": 15426, "loss": 0.3159, "lr": 4.409267082872535e-05, "epoch": 0.5562579013906448, "percentage": 18.54, "elapsed_time": "5:10:14", "remaining_time": "22:43:07", "throughput": 60148.59, "total_tokens": 1119642752} {"current_steps": 2870, "total_steps": 15426, "loss": 0.3128, "lr": 4.407553614855059e-05, "epoch": 0.5582028590878149, "percentage": 18.6, "elapsed_time": "5:11:13", "remaining_time": "22:41:33", "throughput": 60171.71, "total_tokens": 1123594624} {"current_steps": 2880, "total_steps": 15426, "loss": 0.3139, "lr": 4.405842142878579e-05, "epoch": 0.5601478167849849, "percentage": 18.67, "elapsed_time": "5:12:16", "remaining_time": "22:40:20", "throughput": 60178.49, "total_tokens": 1127523328} {"current_steps": 2890, "total_steps": 15426, "loss": 0.3152, "lr": 4.404132663070745e-05, "epoch": 0.562092774482155, "percentage": 18.73, "elapsed_time": "5:13:16", "remaining_time": "22:38:53", "throughput": 60196.08, "total_tokens": 1131468800} {"current_steps": 2900, "total_steps": 15426, "loss": 0.3145, "lr": 4.402425171569716e-05, "epoch": 0.5640377321793251, "percentage": 18.8, "elapsed_time": "5:14:11", "remaining_time": "22:37:04", "throughput": 60221.43, "total_tokens": 1135249408} {"current_steps": 2910, "total_steps": 15426, "loss": 0.3116, "lr": 4.400719664524127e-05, "epoch": 0.5659826898764951, "percentage": 18.86, "elapsed_time": "5:15:10", "remaining_time": "22:35:34", "throughput": 60240.57, "total_tokens": 1139183616} {"current_steps": 2920, "total_steps": 15426, "loss": 0.3121, "lr": 4.399016138093044e-05, "epoch": 0.5679276475736653, "percentage": 18.93, "elapsed_time": "5:16:05", "remaining_time": "22:33:48", "throughput": 60273.24, "total_tokens": 1143137792} {"current_steps": 2930, "total_steps": 15426, "loss": 0.3139, "lr": 4.397314588445937e-05, "epoch": 0.5698726052708354, "percentage": 18.99, "elapsed_time": "5:17:00", "remaining_time": "22:32:00", "throughput": 60307.08, "total_tokens": 1147090688} {"current_steps": 2940, "total_steps": 15426, "loss": 0.3105, "lr": 4.395615011762637e-05, "epoch": 0.5718175629680055, "percentage": 19.06, "elapsed_time": "5:17:57", "remaining_time": "22:30:21", "throughput": 60335.72, "total_tokens": 1151061888} {"current_steps": 2950, "total_steps": 15426, "loss": 0.312, "lr": 4.3939174042333057e-05, "epoch": 0.5737625206651755, "percentage": 19.12, "elapsed_time": "5:18:53", "remaining_time": "22:28:38", "throughput": 60365.03, "total_tokens": 1154991872} {"current_steps": 2960, "total_steps": 15426, "loss": 0.3132, "lr": 4.3922217620583904e-05, "epoch": 0.5757074783623456, "percentage": 19.19, "elapsed_time": "5:19:48", "remaining_time": "22:26:50", "throughput": 60395.28, "total_tokens": 1158873856} {"current_steps": 2970, "total_steps": 15426, "loss": 0.3106, "lr": 4.3905280814486025e-05, "epoch": 0.5776524360595157, "percentage": 19.25, "elapsed_time": "5:20:45", "remaining_time": "22:25:14", "throughput": 60422.42, "total_tokens": 1162859008} {"current_steps": 2980, "total_steps": 15426, "loss": 0.31, "lr": 4.388836358624867e-05, "epoch": 0.5795973937566858, "percentage": 19.32, "elapsed_time": "5:21:36", "remaining_time": "22:23:11", "throughput": 60464.08, "total_tokens": 1166742016} {"current_steps": 2990, "total_steps": 15426, "loss": 0.3131, "lr": 4.3871465898182976e-05, "epoch": 0.5815423514538559, "percentage": 19.38, "elapsed_time": "5:22:29", "remaining_time": "22:21:17", "throughput": 60497.72, "total_tokens": 1170590464} {"current_steps": 3000, "total_steps": 15426, "loss": 0.3114, "lr": 4.385458771270156e-05, "epoch": 0.583487309151026, "percentage": 19.45, "elapsed_time": "5:23:24", "remaining_time": "22:19:34", "throughput": 60525.79, "total_tokens": 1174486016} {"current_steps": 3010, "total_steps": 15426, "loss": 0.3118, "lr": 4.3837728992318205e-05, "epoch": 0.585432266848196, "percentage": 19.51, "elapsed_time": "5:24:20", "remaining_time": "22:17:54", "throughput": 60558.38, "total_tokens": 1178517760} {"current_steps": 3020, "total_steps": 15426, "loss": 0.3116, "lr": 4.382088969964746e-05, "epoch": 0.5873772245453661, "percentage": 19.58, "elapsed_time": "5:25:12", "remaining_time": "22:15:56", "throughput": 60595.74, "total_tokens": 1182376960} {"current_steps": 3030, "total_steps": 15426, "loss": 0.3101, "lr": 4.380406979740436e-05, "epoch": 0.5893221822425362, "percentage": 19.64, "elapsed_time": "5:26:05", "remaining_time": "22:14:03", "throughput": 60629.24, "total_tokens": 1186234240} {"current_steps": 3040, "total_steps": 15426, "loss": 0.313, "lr": 4.3787269248403994e-05, "epoch": 0.5912671399397064, "percentage": 19.71, "elapsed_time": "5:26:59", "remaining_time": "22:12:15", "throughput": 60661.79, "total_tokens": 1190145024} {"current_steps": 3050, "total_steps": 15426, "loss": 0.3137, "lr": 4.377048801556126e-05, "epoch": 0.5932120976368764, "percentage": 19.77, "elapsed_time": "5:27:54", "remaining_time": "22:10:35", "throughput": 60690.17, "total_tokens": 1194077568} {"current_steps": 3060, "total_steps": 15426, "loss": 0.3129, "lr": 4.3753726061890446e-05, "epoch": 0.5951570553340465, "percentage": 19.84, "elapsed_time": "5:28:49", "remaining_time": "22:08:49", "throughput": 60717.11, "total_tokens": 1197906304} {"current_steps": 3070, "total_steps": 15426, "loss": 0.311, "lr": 4.373698335050488e-05, "epoch": 0.5971020130312166, "percentage": 19.9, "elapsed_time": "5:29:40", "remaining_time": "22:06:53", "throughput": 60754.15, "total_tokens": 1201774464} {"current_steps": 3080, "total_steps": 15426, "loss": 0.3136, "lr": 4.372025984461667e-05, "epoch": 0.5990469707283866, "percentage": 19.97, "elapsed_time": "5:30:34", "remaining_time": "22:05:05", "throughput": 60787.21, "total_tokens": 1205689216} {"current_steps": 3090, "total_steps": 15426, "loss": 0.3099, "lr": 4.370355550753629e-05, "epoch": 0.6009919284255567, "percentage": 20.03, "elapsed_time": "5:31:30", "remaining_time": "22:03:27", "throughput": 60817.31, "total_tokens": 1209691008} {"current_steps": 3100, "total_steps": 15426, "loss": 0.3123, "lr": 4.368687030267226e-05, "epoch": 0.6029368861227268, "percentage": 20.1, "elapsed_time": "5:32:25", "remaining_time": "22:01:45", "throughput": 60844.27, "total_tokens": 1213560320} {"current_steps": 3110, "total_steps": 15426, "loss": 0.3128, "lr": 4.367020419353081e-05, "epoch": 0.604881843819897, "percentage": 20.16, "elapsed_time": "5:33:20", "remaining_time": "22:00:02", "throughput": 60870.88, "total_tokens": 1217421824} {"current_steps": 3120, "total_steps": 15426, "loss": 0.3113, "lr": 4.365355714371558e-05, "epoch": 0.606826801517067, "percentage": 20.23, "elapsed_time": "5:34:14", "remaining_time": "21:58:17", "throughput": 60899.23, "total_tokens": 1221276800} {"current_steps": 3130, "total_steps": 15426, "loss": 0.3098, "lr": 4.3636929116927235e-05, "epoch": 0.6087717592142371, "percentage": 20.29, "elapsed_time": "5:35:10", "remaining_time": "21:56:40", "throughput": 60925.14, "total_tokens": 1225205760} {"current_steps": 3140, "total_steps": 15426, "loss": 0.3127, "lr": 4.362032007696314e-05, "epoch": 0.6107167169114072, "percentage": 20.36, "elapsed_time": "5:36:00", "remaining_time": "21:54:42", "throughput": 60958.41, "total_tokens": 1228943616} {"current_steps": 3150, "total_steps": 15426, "loss": 0.3122, "lr": 4.360372998771707e-05, "epoch": 0.6126616746085772, "percentage": 20.42, "elapsed_time": "5:36:54", "remaining_time": "21:52:59", "throughput": 60985.14, "total_tokens": 1232794112} {"current_steps": 3160, "total_steps": 15426, "loss": 0.3105, "lr": 4.358715881317884e-05, "epoch": 0.6146066323057473, "percentage": 20.48, "elapsed_time": "5:37:47", "remaining_time": "21:51:11", "throughput": 61017.33, "total_tokens": 1236665088} {"current_steps": 3170, "total_steps": 15426, "loss": 0.3104, "lr": 4.357060651743399e-05, "epoch": 0.6165515900029175, "percentage": 20.55, "elapsed_time": "5:38:39", "remaining_time": "21:49:21", "throughput": 61047.66, "total_tokens": 1240484352} {"current_steps": 3180, "total_steps": 15426, "loss": 0.3095, "lr": 4.3554073064663454e-05, "epoch": 0.6184965477000876, "percentage": 20.61, "elapsed_time": "5:39:33", "remaining_time": "21:47:35", "throughput": 61079.46, "total_tokens": 1244379008} {"current_steps": 3190, "total_steps": 15426, "loss": 0.3064, "lr": 4.353755841914325e-05, "epoch": 0.6204415053972576, "percentage": 20.68, "elapsed_time": "5:41:14", "remaining_time": "21:48:55", "throughput": 60965.5, "total_tokens": 1248243456} {"current_steps": 3200, "total_steps": 15426, "loss": 0.311, "lr": 4.3521062545244116e-05, "epoch": 0.6223864630944277, "percentage": 20.74, "elapsed_time": "5:43:02", "remaining_time": "21:50:37", "throughput": 60842.15, "total_tokens": 1252273408} {"current_steps": 3210, "total_steps": 15426, "loss": 0.31, "lr": 4.350458540743126e-05, "epoch": 0.6243314207915978, "percentage": 20.81, "elapsed_time": "5:45:39", "remaining_time": "21:55:27", "throughput": 60567.04, "total_tokens": 1256144000} {"current_steps": 3220, "total_steps": 15426, "loss": 0.3107, "lr": 4.3488126970263955e-05, "epoch": 0.6262763784887678, "percentage": 20.87, "elapsed_time": "5:46:38", "remaining_time": "21:54:02", "throughput": 60577.97, "total_tokens": 1259956224} {"current_steps": 3230, "total_steps": 15426, "loss": 0.306, "lr": 4.347168719839527e-05, "epoch": 0.628221336185938, "percentage": 20.94, "elapsed_time": "5:47:35", "remaining_time": "21:52:27", "throughput": 60601.87, "total_tokens": 1263886208} {"current_steps": 3240, "total_steps": 15426, "loss": 0.3118, "lr": 4.345526605657173e-05, "epoch": 0.6301662938831081, "percentage": 21.0, "elapsed_time": "5:48:29", "remaining_time": "21:50:44", "throughput": 60628.06, "total_tokens": 1267723264} {"current_steps": 3250, "total_steps": 15426, "loss": 0.3084, "lr": 4.343886350963304e-05, "epoch": 0.6321112515802781, "percentage": 21.07, "elapsed_time": "5:49:33", "remaining_time": "21:49:34", "throughput": 60632.2, "total_tokens": 1271643264} {"current_steps": 3260, "total_steps": 15426, "loss": 0.3099, "lr": 4.3422479522511697e-05, "epoch": 0.6340562092774482, "percentage": 21.13, "elapsed_time": "5:50:46", "remaining_time": "21:49:02", "throughput": 60605.43, "total_tokens": 1275521280} {"current_steps": 3270, "total_steps": 15426, "loss": 0.3088, "lr": 4.340611406023272e-05, "epoch": 0.6360011669746183, "percentage": 21.2, "elapsed_time": "5:52:23", "remaining_time": "21:49:59", "throughput": 60514.14, "total_tokens": 1279475456} {"current_steps": 3280, "total_steps": 15426, "loss": 0.3109, "lr": 4.338976708791336e-05, "epoch": 0.6379461246717884, "percentage": 21.26, "elapsed_time": "5:53:35", "remaining_time": "21:49:23", "throughput": 60481.13, "total_tokens": 1283161856} {"current_steps": 3290, "total_steps": 15426, "loss": 0.3091, "lr": 4.337343857076272e-05, "epoch": 0.6398910823689585, "percentage": 21.33, "elapsed_time": "5:57:13", "remaining_time": "21:57:41", "throughput": 60054.32, "total_tokens": 1287146368} {"current_steps": 3300, "total_steps": 15426, "loss": 0.3039, "lr": 4.33571284740815e-05, "epoch": 0.6418360400661286, "percentage": 21.39, "elapsed_time": "5:59:19", "remaining_time": "22:00:22", "throughput": 59883.99, "total_tokens": 1291095424} {"current_steps": 3310, "total_steps": 15426, "loss": 0.3084, "lr": 4.3340836763261675e-05, "epoch": 0.6437809977632987, "percentage": 21.46, "elapsed_time": "6:01:31", "remaining_time": "22:03:18", "throughput": 59697.92, "total_tokens": 1294914560} {"current_steps": 3320, "total_steps": 15426, "loss": 0.3082, "lr": 4.332456340378618e-05, "epoch": 0.6457259554604687, "percentage": 21.52, "elapsed_time": "6:03:11", "remaining_time": "22:04:20", "throughput": 59602.58, "total_tokens": 1298836736} {"current_steps": 3330, "total_steps": 15426, "loss": 0.3106, "lr": 4.3308308361228586e-05, "epoch": 0.6476709131576388, "percentage": 21.59, "elapsed_time": "6:04:39", "remaining_time": "22:04:34", "throughput": 59545.19, "total_tokens": 1302799104} {"current_steps": 3340, "total_steps": 15426, "loss": 0.3108, "lr": 4.329207160125282e-05, "epoch": 0.6496158708548089, "percentage": 21.65, "elapsed_time": "6:07:07", "remaining_time": "22:08:29", "throughput": 59323.29, "total_tokens": 1306769152} {"current_steps": 3350, "total_steps": 15426, "loss": 0.3118, "lr": 4.327585308961287e-05, "epoch": 0.6515608285519789, "percentage": 21.72, "elapsed_time": "6:09:17", "remaining_time": "22:11:12", "throughput": 59154.36, "total_tokens": 1310714112} {"current_steps": 3360, "total_steps": 15426, "loss": 0.3055, "lr": 4.325965279215243e-05, "epoch": 0.6535057862491491, "percentage": 21.78, "elapsed_time": "6:10:33", "remaining_time": "22:10:42", "throughput": 59130.11, "total_tokens": 1314682496} {"current_steps": 3370, "total_steps": 15426, "loss": 0.3091, "lr": 4.3243470674804686e-05, "epoch": 0.6554507439463192, "percentage": 21.85, "elapsed_time": "6:12:23", "remaining_time": "22:12:11", "throughput": 59020.73, "total_tokens": 1318707456} {"current_steps": 3380, "total_steps": 15426, "loss": 0.3054, "lr": 4.3227306703591904e-05, "epoch": 0.6573957016434893, "percentage": 21.91, "elapsed_time": "6:13:24", "remaining_time": "22:10:46", "throughput": 59034.35, "total_tokens": 1322619520} {"current_steps": 3390, "total_steps": 15426, "loss": 0.3108, "lr": 4.32111608446252e-05, "epoch": 0.6593406593406593, "percentage": 21.98, "elapsed_time": "6:14:21", "remaining_time": "22:09:09", "throughput": 59059.86, "total_tokens": 1326598656} {"current_steps": 3400, "total_steps": 15426, "loss": 0.3114, "lr": 4.319503306410426e-05, "epoch": 0.6612856170378294, "percentage": 22.04, "elapsed_time": "6:15:21", "remaining_time": "22:07:38", "throughput": 59079.85, "total_tokens": 1330543488} {"current_steps": 3410, "total_steps": 15426, "loss": 0.3066, "lr": 4.317892332831699e-05, "epoch": 0.6632305747349995, "percentage": 22.11, "elapsed_time": "6:16:20", "remaining_time": "22:06:07", "throughput": 59095.63, "total_tokens": 1334391936} {"current_steps": 3420, "total_steps": 15426, "loss": 0.3081, "lr": 4.316283160363922e-05, "epoch": 0.6651755324321696, "percentage": 22.17, "elapsed_time": "6:17:29", "remaining_time": "22:05:10", "throughput": 59087.52, "total_tokens": 1338274816} {"current_steps": 3430, "total_steps": 15426, "loss": 0.3086, "lr": 4.314675785653447e-05, "epoch": 0.6671204901293397, "percentage": 22.24, "elapsed_time": "6:18:23", "remaining_time": "22:03:24", "throughput": 59113.38, "total_tokens": 1342108800} {"current_steps": 3440, "total_steps": 15426, "loss": 0.3076, "lr": 4.3130702053553606e-05, "epoch": 0.6690654478265098, "percentage": 22.3, "elapsed_time": "6:19:18", "remaining_time": "22:01:37", "throughput": 59143.7, "total_tokens": 1346023424} {"current_steps": 3450, "total_steps": 15426, "loss": 0.308, "lr": 4.3114664161334546e-05, "epoch": 0.6710104055236799, "percentage": 22.36, "elapsed_time": "6:20:13", "remaining_time": "21:59:52", "throughput": 59173.8, "total_tokens": 1349967104} {"current_steps": 3460, "total_steps": 15426, "loss": 0.3068, "lr": 4.3098644146601984e-05, "epoch": 0.6729553632208499, "percentage": 22.43, "elapsed_time": "6:21:11", "remaining_time": "21:58:16", "throughput": 59196.6, "total_tokens": 1353890432} {"current_steps": 3470, "total_steps": 15426, "loss": 0.3069, "lr": 4.30826419761671e-05, "epoch": 0.67490032091802, "percentage": 22.49, "elapsed_time": "6:22:07", "remaining_time": "21:56:38", "throughput": 59222.45, "total_tokens": 1357837696} {"current_steps": 3480, "total_steps": 15426, "loss": 0.3081, "lr": 4.30666576169273e-05, "epoch": 0.6768452786151902, "percentage": 22.56, "elapsed_time": "6:23:05", "remaining_time": "21:55:03", "throughput": 59250.47, "total_tokens": 1361904128} {"current_steps": 3490, "total_steps": 15426, "loss": 0.3091, "lr": 4.305069103586585e-05, "epoch": 0.6787902363123602, "percentage": 22.62, "elapsed_time": "6:23:57", "remaining_time": "21:53:08", "throughput": 59282.81, "total_tokens": 1365708288} {"current_steps": 3500, "total_steps": 15426, "loss": 0.305, "lr": 4.303474220005164e-05, "epoch": 0.6807351940095303, "percentage": 22.69, "elapsed_time": "6:25:01", "remaining_time": "21:51:57", "throughput": 59285.94, "total_tokens": 1369604480} {"current_steps": 3510, "total_steps": 15426, "loss": 0.3018, "lr": 4.3018811076638944e-05, "epoch": 0.6826801517067004, "percentage": 22.75, "elapsed_time": "6:25:56", "remaining_time": "21:50:12", "throughput": 59315.91, "total_tokens": 1373531648} {"current_steps": 3520, "total_steps": 15426, "loss": 0.3078, "lr": 4.300289763286704e-05, "epoch": 0.6846251094038704, "percentage": 22.82, "elapsed_time": "6:26:51", "remaining_time": "21:48:29", "throughput": 59344.28, "total_tokens": 1377459712} {"current_steps": 3530, "total_steps": 15426, "loss": 0.3039, "lr": 4.298700183606e-05, "epoch": 0.6865700671010405, "percentage": 22.88, "elapsed_time": "6:27:47", "remaining_time": "21:46:50", "throughput": 59370.51, "total_tokens": 1381393920} {"current_steps": 3540, "total_steps": 15426, "loss": 0.3057, "lr": 4.297112365362637e-05, "epoch": 0.6885150247982106, "percentage": 22.95, "elapsed_time": "6:28:41", "remaining_time": "21:45:03", "throughput": 59400.61, "total_tokens": 1385294592} {"current_steps": 3550, "total_steps": 15426, "loss": 0.3076, "lr": 4.295526305305891e-05, "epoch": 0.6904599824953808, "percentage": 23.01, "elapsed_time": "6:29:32", "remaining_time": "21:43:09", "throughput": 59433.2, "total_tokens": 1389107328} {"current_steps": 3560, "total_steps": 15426, "loss": 0.3077, "lr": 4.293942000193429e-05, "epoch": 0.6924049401925508, "percentage": 23.08, "elapsed_time": "6:30:27", "remaining_time": "21:41:26", "throughput": 59460.72, "total_tokens": 1392994560} {"current_steps": 3570, "total_steps": 15426, "loss": 0.3087, "lr": 4.2923594467912866e-05, "epoch": 0.6943498978897209, "percentage": 23.14, "elapsed_time": "6:31:20", "remaining_time": "21:39:39", "throughput": 59490.94, "total_tokens": 1396886272} {"current_steps": 3580, "total_steps": 15426, "loss": 0.31, "lr": 4.290778641873832e-05, "epoch": 0.696294855586891, "percentage": 23.21, "elapsed_time": "6:32:16", "remaining_time": "21:38:01", "throughput": 59515.02, "total_tokens": 1400779264} {"current_steps": 3590, "total_steps": 15426, "loss": 0.3091, "lr": 4.2891995822237455e-05, "epoch": 0.698239813284061, "percentage": 23.27, "elapsed_time": "6:33:11", "remaining_time": "21:36:20", "throughput": 59542.89, "total_tokens": 1404712192} {"current_steps": 3600, "total_steps": 15426, "loss": 0.3111, "lr": 4.28762226463199e-05, "epoch": 0.7001847709812311, "percentage": 23.34, "elapsed_time": "6:34:05", "remaining_time": "21:34:34", "throughput": 59571.53, "total_tokens": 1408586624} {"current_steps": 3610, "total_steps": 15426, "loss": 0.3102, "lr": 4.286046685897781e-05, "epoch": 0.7021297286784013, "percentage": 23.4, "elapsed_time": "6:35:01", "remaining_time": "21:32:56", "throughput": 59597.84, "total_tokens": 1412532096} {"current_steps": 3620, "total_steps": 15426, "loss": 0.3076, "lr": 4.284472842828562e-05, "epoch": 0.7040746863755714, "percentage": 23.47, "elapsed_time": "6:35:54", "remaining_time": "21:31:09", "throughput": 59629.71, "total_tokens": 1416449280} {"current_steps": 3630, "total_steps": 15426, "loss": 0.3064, "lr": 4.282900732239977e-05, "epoch": 0.7060196440727414, "percentage": 23.53, "elapsed_time": "6:36:47", "remaining_time": "21:29:23", "throughput": 59658.52, "total_tokens": 1420295552} {"current_steps": 3640, "total_steps": 15426, "loss": 0.3071, "lr": 4.281330350955845e-05, "epoch": 0.7079646017699115, "percentage": 23.6, "elapsed_time": "6:37:38", "remaining_time": "21:27:33", "throughput": 59688.63, "total_tokens": 1424110976} {"current_steps": 3650, "total_steps": 15426, "loss": 0.3074, "lr": 4.279761695808125e-05, "epoch": 0.7099095594670816, "percentage": 23.66, "elapsed_time": "6:38:32", "remaining_time": "21:25:47", "throughput": 59720.5, "total_tokens": 1428047104} {"current_steps": 3660, "total_steps": 15426, "loss": 0.3083, "lr": 4.278194763636904e-05, "epoch": 0.7118545171642516, "percentage": 23.73, "elapsed_time": "6:39:26", "remaining_time": "21:24:06", "throughput": 59744.83, "total_tokens": 1431881472} {"current_steps": 3670, "total_steps": 15426, "loss": 0.3049, "lr": 4.276629551290354e-05, "epoch": 0.7137994748614218, "percentage": 23.79, "elapsed_time": "6:40:23", "remaining_time": "21:22:32", "throughput": 59770.0, "total_tokens": 1435863040} {"current_steps": 3680, "total_steps": 15426, "loss": 0.3052, "lr": 4.2750660556247175e-05, "epoch": 0.7157444325585919, "percentage": 23.86, "elapsed_time": "6:41:15", "remaining_time": "21:20:44", "throughput": 59800.9, "total_tokens": 1439724672} {"current_steps": 3690, "total_steps": 15426, "loss": 0.3069, "lr": 4.273504273504274e-05, "epoch": 0.717689390255762, "percentage": 23.92, "elapsed_time": "6:42:09", "remaining_time": "21:19:04", "throughput": 59829.7, "total_tokens": 1443681024} {"current_steps": 3700, "total_steps": 15426, "loss": 0.3067, "lr": 4.271944201801317e-05, "epoch": 0.719634347952932, "percentage": 23.99, "elapsed_time": "6:43:04", "remaining_time": "21:17:26", "throughput": 59853.34, "total_tokens": 1447541248} {"current_steps": 3710, "total_steps": 15426, "loss": 0.3037, "lr": 4.270385837396127e-05, "epoch": 0.7215793056501021, "percentage": 24.05, "elapsed_time": "6:43:58", "remaining_time": "21:15:43", "throughput": 59882.9, "total_tokens": 1451465728} {"current_steps": 3720, "total_steps": 15426, "loss": 0.3024, "lr": 4.268829177176945e-05, "epoch": 0.7235242633472722, "percentage": 24.12, "elapsed_time": "6:44:51", "remaining_time": "21:13:59", "throughput": 59913.57, "total_tokens": 1455379968} {"current_steps": 3730, "total_steps": 15426, "loss": 0.3051, "lr": 4.2672742180399455e-05, "epoch": 0.7254692210444423, "percentage": 24.18, "elapsed_time": "6:45:45", "remaining_time": "21:12:18", "throughput": 59940.91, "total_tokens": 1459273088} {"current_steps": 3740, "total_steps": 15426, "loss": 0.3033, "lr": 4.265720956889213e-05, "epoch": 0.7274141787416124, "percentage": 24.24, "elapsed_time": "6:46:39", "remaining_time": "21:10:39", "throughput": 59970.95, "total_tokens": 1463281024} {"current_steps": 3750, "total_steps": 15426, "loss": 0.3062, "lr": 4.2641693906367113e-05, "epoch": 0.7293591364387825, "percentage": 24.31, "elapsed_time": "6:47:31", "remaining_time": "21:08:51", "throughput": 59999.66, "total_tokens": 1467067648} {"current_steps": 3760, "total_steps": 15426, "loss": 0.3007, "lr": 4.2626195162022646e-05, "epoch": 0.7313040941359525, "percentage": 24.37, "elapsed_time": "6:48:27", "remaining_time": "21:07:19", "throughput": 60025.72, "total_tokens": 1471094400} {"current_steps": 3770, "total_steps": 15426, "loss": 0.3073, "lr": 4.2610713305135255e-05, "epoch": 0.7332490518331226, "percentage": 24.44, "elapsed_time": "6:49:24", "remaining_time": "21:05:47", "throughput": 60047.62, "total_tokens": 1475026816} {"current_steps": 3780, "total_steps": 15426, "loss": 0.3044, "lr": 4.2595248305059546e-05, "epoch": 0.7351940095302927, "percentage": 24.5, "elapsed_time": "6:50:20", "remaining_time": "21:04:14", "throughput": 60070.84, "total_tokens": 1478968960} {"current_steps": 3790, "total_steps": 15426, "loss": 0.3047, "lr": 4.2579800131227916e-05, "epoch": 0.7371389672274627, "percentage": 24.57, "elapsed_time": "6:51:14", "remaining_time": "21:02:36", "throughput": 60094.9, "total_tokens": 1482836480} {"current_steps": 3800, "total_steps": 15426, "loss": 0.304, "lr": 4.256436875315028e-05, "epoch": 0.7390839249246329, "percentage": 24.63, "elapsed_time": "6:52:09", "remaining_time": "21:01:00", "throughput": 60118.49, "total_tokens": 1486717312} {"current_steps": 3810, "total_steps": 15426, "loss": 0.3019, "lr": 4.2548954140413895e-05, "epoch": 0.741028882621803, "percentage": 24.7, "elapsed_time": "6:53:05", "remaining_time": "20:59:27", "throughput": 60146.53, "total_tokens": 1490774656} {"current_steps": 3820, "total_steps": 15426, "loss": 0.3069, "lr": 4.253355626268302e-05, "epoch": 0.7429738403189731, "percentage": 24.76, "elapsed_time": "6:54:00", "remaining_time": "20:57:51", "throughput": 60172.05, "total_tokens": 1494710144} {"current_steps": 3830, "total_steps": 15426, "loss": 0.3043, "lr": 4.2518175089698716e-05, "epoch": 0.7449187980161431, "percentage": 24.83, "elapsed_time": "6:54:52", "remaining_time": "20:56:06", "throughput": 60202.24, "total_tokens": 1498590464} {"current_steps": 3840, "total_steps": 15426, "loss": 0.3038, "lr": 4.25028105912786e-05, "epoch": 0.7468637557133132, "percentage": 24.89, "elapsed_time": "6:55:49", "remaining_time": "20:54:37", "throughput": 60223.22, "total_tokens": 1502544256} {"current_steps": 3850, "total_steps": 15426, "loss": 0.2994, "lr": 4.2487462737316565e-05, "epoch": 0.7488087134104833, "percentage": 24.96, "elapsed_time": "6:56:45", "remaining_time": "20:53:06", "throughput": 60245.25, "total_tokens": 1506486784} {"current_steps": 3860, "total_steps": 15426, "loss": 0.3011, "lr": 4.2472131497782555e-05, "epoch": 0.7507536711076535, "percentage": 25.02, "elapsed_time": "6:57:40", "remaining_time": "20:51:30", "throughput": 60269.07, "total_tokens": 1510370048} {"current_steps": 3870, "total_steps": 15426, "loss": 0.3061, "lr": 4.245681684272231e-05, "epoch": 0.7526986288048235, "percentage": 25.09, "elapsed_time": "6:58:33", "remaining_time": "20:49:50", "throughput": 60295.45, "total_tokens": 1514240768} {"current_steps": 3880, "total_steps": 15426, "loss": 0.3078, "lr": 4.244151874225712e-05, "epoch": 0.7546435865019936, "percentage": 25.15, "elapsed_time": "6:59:26", "remaining_time": "20:48:09", "throughput": 60324.41, "total_tokens": 1518145536} {"current_steps": 3890, "total_steps": 15426, "loss": 0.3031, "lr": 4.2426237166583596e-05, "epoch": 0.7565885441991637, "percentage": 25.22, "elapsed_time": "7:00:20", "remaining_time": "20:46:31", "throughput": 60353.78, "total_tokens": 1522131712} {"current_steps": 3900, "total_steps": 15426, "loss": 0.3002, "lr": 4.241097208597339e-05, "epoch": 0.7585335018963337, "percentage": 25.28, "elapsed_time": "7:01:15", "remaining_time": "20:44:58", "throughput": 60374.71, "total_tokens": 1525998336} {"current_steps": 3910, "total_steps": 15426, "loss": 0.3039, "lr": 4.2395723470773005e-05, "epoch": 0.7604784595935038, "percentage": 25.35, "elapsed_time": "7:02:08", "remaining_time": "20:43:20", "throughput": 60398.04, "total_tokens": 1529814656} {"current_steps": 3920, "total_steps": 15426, "loss": 0.3069, "lr": 4.238049129140347e-05, "epoch": 0.762423417290674, "percentage": 25.41, "elapsed_time": "7:03:01", "remaining_time": "20:41:40", "throughput": 60422.55, "total_tokens": 1533634176} {"current_steps": 3930, "total_steps": 15426, "loss": 0.3032, "lr": 4.236527551836022e-05, "epoch": 0.764368374987844, "percentage": 25.48, "elapsed_time": "7:03:55", "remaining_time": "20:40:04", "throughput": 60448.76, "total_tokens": 1537553408} {"current_steps": 3940, "total_steps": 15426, "loss": 0.3055, "lr": 4.235007612221274e-05, "epoch": 0.7663133326850141, "percentage": 25.54, "elapsed_time": "7:04:50", "remaining_time": "20:38:29", "throughput": 60474.95, "total_tokens": 1541513728} {"current_steps": 3950, "total_steps": 15426, "loss": 0.301, "lr": 4.2334893073604386e-05, "epoch": 0.7682582903821842, "percentage": 25.61, "elapsed_time": "7:05:43", "remaining_time": "20:36:51", "throughput": 60499.57, "total_tokens": 1545368192} {"current_steps": 3960, "total_steps": 15426, "loss": 0.3044, "lr": 4.231972634325214e-05, "epoch": 0.7702032480793543, "percentage": 25.67, "elapsed_time": "7:06:37", "remaining_time": "20:35:15", "throughput": 60523.05, "total_tokens": 1549226880} {"current_steps": 3970, "total_steps": 15426, "loss": 0.2999, "lr": 4.230457590194635e-05, "epoch": 0.7721482057765243, "percentage": 25.74, "elapsed_time": "7:07:30", "remaining_time": "20:33:38", "throughput": 60547.8, "total_tokens": 1553096192} {"current_steps": 3980, "total_steps": 15426, "loss": 0.3067, "lr": 4.228944172055053e-05, "epoch": 0.7740931634736945, "percentage": 25.8, "elapsed_time": "7:08:25", "remaining_time": "20:32:05", "throughput": 60571.22, "total_tokens": 1557008128} {"current_steps": 3990, "total_steps": 15426, "loss": 0.3041, "lr": 4.22743237700011e-05, "epoch": 0.7760381211708646, "percentage": 25.87, "elapsed_time": "7:09:21", "remaining_time": "20:30:38", "throughput": 60593.95, "total_tokens": 1561020800} {"current_steps": 4000, "total_steps": 15426, "loss": 0.3015, "lr": 4.225922202130716e-05, "epoch": 0.7779830788680346, "percentage": 25.93, "elapsed_time": "7:10:16", "remaining_time": "20:29:05", "throughput": 60616.95, "total_tokens": 1564933120} {"current_steps": 4010, "total_steps": 15426, "loss": 0.3037, "lr": 4.224413644555024e-05, "epoch": 0.7799280365652047, "percentage": 26.0, "elapsed_time": "7:11:09", "remaining_time": "20:27:27", "throughput": 60641.97, "total_tokens": 1568787968} {"current_steps": 4020, "total_steps": 15426, "loss": 0.3049, "lr": 4.222906701388411e-05, "epoch": 0.7818729942623748, "percentage": 26.06, "elapsed_time": "7:12:03", "remaining_time": "20:25:53", "throughput": 60667.26, "total_tokens": 1572726912} {"current_steps": 4030, "total_steps": 15426, "loss": 0.3028, "lr": 4.2214013697534466e-05, "epoch": 0.7838179519595448, "percentage": 26.12, "elapsed_time": "7:12:56", "remaining_time": "20:24:16", "throughput": 60691.33, "total_tokens": 1576560000} {"current_steps": 4040, "total_steps": 15426, "loss": 0.298, "lr": 4.219897646779882e-05, "epoch": 0.7857629096567149, "percentage": 26.19, "elapsed_time": "7:13:53", "remaining_time": "20:22:49", "throughput": 60713.3, "total_tokens": 1580554880} {"current_steps": 4050, "total_steps": 15426, "loss": 0.3012, "lr": 4.2183955296046145e-05, "epoch": 0.7877078673538851, "percentage": 26.25, "elapsed_time": "7:14:46", "remaining_time": "20:21:14", "throughput": 60739.11, "total_tokens": 1584472064} {"current_steps": 4060, "total_steps": 15426, "loss": 0.3013, "lr": 4.2168950153716746e-05, "epoch": 0.7896528250510552, "percentage": 26.32, "elapsed_time": "7:15:40", "remaining_time": "20:19:39", "throughput": 60765.67, "total_tokens": 1588422656} {"current_steps": 4070, "total_steps": 15426, "loss": 0.3006, "lr": 4.215396101232197e-05, "epoch": 0.7915977827482252, "percentage": 26.38, "elapsed_time": "7:16:34", "remaining_time": "20:18:08", "throughput": 60790.77, "total_tokens": 1592411648} {"current_steps": 4080, "total_steps": 15426, "loss": 0.3, "lr": 4.213898784344398e-05, "epoch": 0.7935427404453953, "percentage": 26.45, "elapsed_time": "7:17:29", "remaining_time": "20:16:35", "throughput": 60816.22, "total_tokens": 1596368512} {"current_steps": 4090, "total_steps": 15426, "loss": 0.2999, "lr": 4.21240306187356e-05, "epoch": 0.7954876981425654, "percentage": 26.51, "elapsed_time": "7:18:23", "remaining_time": "20:15:04", "throughput": 60837.71, "total_tokens": 1600262144} {"current_steps": 4100, "total_steps": 15426, "loss": 0.3025, "lr": 4.2109089309919967e-05, "epoch": 0.7974326558397354, "percentage": 26.58, "elapsed_time": "7:19:15", "remaining_time": "20:13:25", "throughput": 60862.59, "total_tokens": 1604075392} {"current_steps": 4110, "total_steps": 15426, "loss": 0.3011, "lr": 4.2094163888790445e-05, "epoch": 0.7993776135369056, "percentage": 26.64, "elapsed_time": "7:20:07", "remaining_time": "20:11:48", "throughput": 60888.36, "total_tokens": 1607928704} {"current_steps": 4120, "total_steps": 15426, "loss": 0.3012, "lr": 4.2079254327210294e-05, "epoch": 0.8013225712340757, "percentage": 26.71, "elapsed_time": "7:21:03", "remaining_time": "20:10:19", "throughput": 60911.69, "total_tokens": 1611907456} {"current_steps": 4130, "total_steps": 15426, "loss": 0.2992, "lr": 4.206436059711249e-05, "epoch": 0.8032675289312458, "percentage": 26.77, "elapsed_time": "7:21:55", "remaining_time": "20:08:42", "throughput": 60938.07, "total_tokens": 1615785984} {"current_steps": 4140, "total_steps": 15426, "loss": 0.3034, "lr": 4.20494826704995e-05, "epoch": 0.8052124866284158, "percentage": 26.84, "elapsed_time": "7:22:48", "remaining_time": "20:07:08", "throughput": 60959.91, "total_tokens": 1619624448} {"current_steps": 4150, "total_steps": 15426, "loss": 0.3017, "lr": 4.203462051944307e-05, "epoch": 0.8071574443255859, "percentage": 26.9, "elapsed_time": "7:23:40", "remaining_time": "20:05:29", "throughput": 60984.71, "total_tokens": 1623424256} {"current_steps": 4160, "total_steps": 15426, "loss": 0.3046, "lr": 4.201977411608398e-05, "epoch": 0.809102402022756, "percentage": 26.97, "elapsed_time": "7:24:33", "remaining_time": "20:03:55", "throughput": 61006.79, "total_tokens": 1627245056} {"current_steps": 4170, "total_steps": 15426, "loss": 0.3016, "lr": 4.200494343263185e-05, "epoch": 0.8110473597199261, "percentage": 27.03, "elapsed_time": "7:25:25", "remaining_time": "20:02:18", "throughput": 61032.15, "total_tokens": 1631088896} {"current_steps": 4180, "total_steps": 15426, "loss": 0.3021, "lr": 4.1990128441364914e-05, "epoch": 0.8129923174170962, "percentage": 27.1, "elapsed_time": "7:26:19", "remaining_time": "20:00:49", "throughput": 61053.77, "total_tokens": 1635008000} {"current_steps": 4190, "total_steps": 15426, "loss": 0.3016, "lr": 4.197532911462977e-05, "epoch": 0.8149372751142663, "percentage": 27.16, "elapsed_time": "7:27:10", "remaining_time": "19:59:09", "throughput": 61081.57, "total_tokens": 1638856832} {"current_steps": 4200, "total_steps": 15426, "loss": 0.3, "lr": 4.196054542484125e-05, "epoch": 0.8168822328114363, "percentage": 27.23, "elapsed_time": "7:28:06", "remaining_time": "19:57:44", "throughput": 61105.45, "total_tokens": 1642925696} {"current_steps": 4210, "total_steps": 15426, "loss": 0.296, "lr": 4.1945777344482084e-05, "epoch": 0.8188271905086064, "percentage": 27.29, "elapsed_time": "7:29:03", "remaining_time": "19:56:20", "throughput": 61124.39, "total_tokens": 1646890240} {"current_steps": 4220, "total_steps": 15426, "loss": 0.2973, "lr": 4.19310248461028e-05, "epoch": 0.8207721482057765, "percentage": 27.36, "elapsed_time": "7:29:57", "remaining_time": "19:54:49", "throughput": 61147.7, "total_tokens": 1650817024} {"current_steps": 4230, "total_steps": 15426, "loss": 0.3004, "lr": 4.1916287902321405e-05, "epoch": 0.8227171059029467, "percentage": 27.42, "elapsed_time": "7:30:49", "remaining_time": "19:53:14", "throughput": 61171.59, "total_tokens": 1654654976} {"current_steps": 4240, "total_steps": 15426, "loss": 0.2994, "lr": 4.190156648582328e-05, "epoch": 0.8246620636001167, "percentage": 27.49, "elapsed_time": "7:31:45", "remaining_time": "19:51:48", "throughput": 61191.26, "total_tokens": 1658590208} {"current_steps": 4250, "total_steps": 15426, "loss": 0.3007, "lr": 4.188686056936087e-05, "epoch": 0.8266070212972868, "percentage": 27.55, "elapsed_time": "7:32:42", "remaining_time": "19:50:26", "throughput": 61210.67, "total_tokens": 1662615936} {"current_steps": 4260, "total_steps": 15426, "loss": 0.2977, "lr": 4.187217012575352e-05, "epoch": 0.8285519789944569, "percentage": 27.62, "elapsed_time": "7:33:34", "remaining_time": "19:48:52", "throughput": 61235.29, "total_tokens": 1666492800} {"current_steps": 4270, "total_steps": 15426, "loss": 0.302, "lr": 4.185749512788727e-05, "epoch": 0.8304969366916269, "percentage": 27.68, "elapsed_time": "7:34:27", "remaining_time": "19:47:20", "throughput": 61259.13, "total_tokens": 1670380416} {"current_steps": 4280, "total_steps": 15426, "loss": 0.3021, "lr": 4.184283554871462e-05, "epoch": 0.832441894388797, "percentage": 27.75, "elapsed_time": "7:35:26", "remaining_time": "19:46:04", "throughput": 61268.3, "total_tokens": 1674269184} {"current_steps": 4290, "total_steps": 15426, "loss": 0.3016, "lr": 4.1828191361254344e-05, "epoch": 0.8343868520859671, "percentage": 27.81, "elapsed_time": "7:36:23", "remaining_time": "19:44:41", "throughput": 61285.5, "total_tokens": 1678201216} {"current_steps": 4300, "total_steps": 15426, "loss": 0.3017, "lr": 4.181356253859127e-05, "epoch": 0.8363318097831373, "percentage": 27.88, "elapsed_time": "7:37:17", "remaining_time": "19:43:11", "throughput": 61306.27, "total_tokens": 1682063104} {"current_steps": 4310, "total_steps": 15426, "loss": 0.2979, "lr": 4.179894905387606e-05, "epoch": 0.8382767674803073, "percentage": 27.94, "elapsed_time": "7:38:15", "remaining_time": "19:41:54", "throughput": 61316.51, "total_tokens": 1685938048} {"current_steps": 4320, "total_steps": 15426, "loss": 0.2999, "lr": 4.178435088032502e-05, "epoch": 0.8402217251774774, "percentage": 28.0, "elapsed_time": "7:39:10", "remaining_time": "19:40:27", "throughput": 61336.45, "total_tokens": 1689847680} {"current_steps": 4330, "total_steps": 15426, "loss": 0.2996, "lr": 4.176976799121989e-05, "epoch": 0.8421666828746475, "percentage": 28.07, "elapsed_time": "7:40:02", "remaining_time": "19:38:53", "throughput": 61360.14, "total_tokens": 1693688064} {"current_steps": 4340, "total_steps": 15426, "loss": 0.2977, "lr": 4.1755200359907657e-05, "epoch": 0.8441116405718175, "percentage": 28.13, "elapsed_time": "7:40:56", "remaining_time": "19:37:24", "throughput": 61381.33, "total_tokens": 1697579776} {"current_steps": 4350, "total_steps": 15426, "loss": 0.2961, "lr": 4.174064795980028e-05, "epoch": 0.8460565982689876, "percentage": 28.2, "elapsed_time": "7:41:51", "remaining_time": "19:35:59", "throughput": 61400.42, "total_tokens": 1701510400} {"current_steps": 4360, "total_steps": 15426, "loss": 0.2966, "lr": 4.17261107643746e-05, "epoch": 0.8480015559661578, "percentage": 28.26, "elapsed_time": "7:42:44", "remaining_time": "19:34:29", "throughput": 61423.15, "total_tokens": 1705403648} {"current_steps": 4370, "total_steps": 15426, "loss": 0.2995, "lr": 4.171158874717204e-05, "epoch": 0.8499465136633279, "percentage": 28.33, "elapsed_time": "7:43:41", "remaining_time": "19:33:07", "throughput": 61439.27, "total_tokens": 1709316352} {"current_steps": 4380, "total_steps": 15426, "loss": 0.2961, "lr": 4.169708188179844e-05, "epoch": 0.8518914713604979, "percentage": 28.39, "elapsed_time": "7:44:37", "remaining_time": "19:31:44", "throughput": 61456.18, "total_tokens": 1713235456} {"current_steps": 4390, "total_steps": 15426, "loss": 0.2987, "lr": 4.1682590141923846e-05, "epoch": 0.853836429057668, "percentage": 28.46, "elapsed_time": "7:45:28", "remaining_time": "19:30:09", "throughput": 61479.9, "total_tokens": 1717055104} {"current_steps": 4400, "total_steps": 15426, "loss": 0.2976, "lr": 4.1668113501282335e-05, "epoch": 0.8557813867548381, "percentage": 28.52, "elapsed_time": "7:46:23", "remaining_time": "19:28:45", "throughput": 61500.26, "total_tokens": 1721019520} {"current_steps": 4410, "total_steps": 15426, "loss": 0.2947, "lr": 4.165365193367178e-05, "epoch": 0.8577263444520081, "percentage": 28.59, "elapsed_time": "7:47:18", "remaining_time": "19:27:18", "throughput": 61521.11, "total_tokens": 1724944000} {"current_steps": 4420, "total_steps": 15426, "loss": 0.2987, "lr": 4.163920541295369e-05, "epoch": 0.8596713021491783, "percentage": 28.65, "elapsed_time": "7:48:11", "remaining_time": "19:25:50", "throughput": 61542.97, "total_tokens": 1728856832} {"current_steps": 4430, "total_steps": 15426, "loss": 0.2961, "lr": 4.1624773913052946e-05, "epoch": 0.8616162598463484, "percentage": 28.72, "elapsed_time": "7:49:07", "remaining_time": "19:24:27", "throughput": 61561.53, "total_tokens": 1732817152} {"current_steps": 4440, "total_steps": 15426, "loss": 0.2988, "lr": 4.161035740795769e-05, "epoch": 0.8635612175435184, "percentage": 28.78, "elapsed_time": "7:50:02", "remaining_time": "19:23:02", "throughput": 61580.74, "total_tokens": 1736733056} {"current_steps": 4450, "total_steps": 15426, "loss": 0.2974, "lr": 4.1595955871719055e-05, "epoch": 0.8655061752406885, "percentage": 28.85, "elapsed_time": "7:51:00", "remaining_time": "19:21:45", "throughput": 61593.57, "total_tokens": 1740680576} {"current_steps": 4460, "total_steps": 15426, "loss": 0.2974, "lr": 4.158156927845101e-05, "epoch": 0.8674511329378586, "percentage": 28.91, "elapsed_time": "7:51:55", "remaining_time": "19:20:19", "throughput": 61615.16, "total_tokens": 1744635776} {"current_steps": 4470, "total_steps": 15426, "loss": 0.2991, "lr": 4.156719760233016e-05, "epoch": 0.8693960906350287, "percentage": 28.98, "elapsed_time": "7:52:45", "remaining_time": "19:18:44", "throughput": 61637.8, "total_tokens": 1748405888} {"current_steps": 4480, "total_steps": 15426, "loss": 0.3007, "lr": 4.155284081759552e-05, "epoch": 0.8713410483321987, "percentage": 29.04, "elapsed_time": "7:53:40", "remaining_time": "19:17:20", "throughput": 61655.79, "total_tokens": 1752297472} {"current_steps": 4490, "total_steps": 15426, "loss": 0.2974, "lr": 4.1538498898548356e-05, "epoch": 0.8732860060293689, "percentage": 29.11, "elapsed_time": "7:54:38", "remaining_time": "19:16:03", "throughput": 61668.24, "total_tokens": 1756219776} {"current_steps": 4500, "total_steps": 15426, "loss": 0.3008, "lr": 4.1524171819552e-05, "epoch": 0.875230963726539, "percentage": 29.17, "elapsed_time": "7:55:31", "remaining_time": "19:14:34", "throughput": 61688.0, "total_tokens": 1760061696} {"current_steps": 4510, "total_steps": 15426, "loss": 0.2957, "lr": 4.15098595550316e-05, "epoch": 0.877175921423709, "percentage": 29.24, "elapsed_time": "7:56:28", "remaining_time": "19:13:14", "throughput": 61705.09, "total_tokens": 1764026240} {"current_steps": 4520, "total_steps": 15426, "loss": 0.2979, "lr": 4.1495562079474e-05, "epoch": 0.8791208791208791, "percentage": 29.3, "elapsed_time": "7:57:24", "remaining_time": "19:11:53", "throughput": 61722.01, "total_tokens": 1767983616} {"current_steps": 4530, "total_steps": 15426, "loss": 0.2969, "lr": 4.148127936742749e-05, "epoch": 0.8810658368180492, "percentage": 29.37, "elapsed_time": "7:58:17", "remaining_time": "19:10:25", "throughput": 61741.78, "total_tokens": 1771829120} {"current_steps": 4540, "total_steps": 15426, "loss": 0.2979, "lr": 4.146701139350166e-05, "epoch": 0.8830107945152192, "percentage": 29.43, "elapsed_time": "7:59:13", "remaining_time": "19:09:05", "throughput": 61759.14, "total_tokens": 1775793408} {"current_steps": 4550, "total_steps": 15426, "loss": 0.296, "lr": 4.1452758132367196e-05, "epoch": 0.8849557522123894, "percentage": 29.5, "elapsed_time": "8:00:12", "remaining_time": "19:07:50", "throughput": 61770.94, "total_tokens": 1779754880} {"current_steps": 4560, "total_steps": 15426, "loss": 0.2982, "lr": 4.1438519558755656e-05, "epoch": 0.8869007099095595, "percentage": 29.56, "elapsed_time": "8:01:05", "remaining_time": "19:06:24", "throughput": 61791.8, "total_tokens": 1783670784} {"current_steps": 4570, "total_steps": 15426, "loss": 0.2951, "lr": 4.1424295647459336e-05, "epoch": 0.8888456676067296, "percentage": 29.63, "elapsed_time": "8:02:04", "remaining_time": "19:05:10", "throughput": 61805.31, "total_tokens": 1787706240} {"current_steps": 4580, "total_steps": 15426, "loss": 0.2974, "lr": 4.141008637333106e-05, "epoch": 0.8907906253038996, "percentage": 29.69, "elapsed_time": "8:02:57", "remaining_time": "19:03:41", "throughput": 61826.14, "total_tokens": 1791543680} {"current_steps": 4590, "total_steps": 15426, "loss": 0.2991, "lr": 4.1395891711283974e-05, "epoch": 0.8927355830010697, "percentage": 29.75, "elapsed_time": "8:05:29", "remaining_time": "19:06:09", "throughput": 61631.32, "total_tokens": 1795307520} {"current_steps": 4600, "total_steps": 15426, "loss": 0.2952, "lr": 4.1381711636291395e-05, "epoch": 0.8946805406982398, "percentage": 29.82, "elapsed_time": "8:08:57", "remaining_time": "19:10:45", "throughput": 61327.14, "total_tokens": 1799205248} {"current_steps": 4610, "total_steps": 15426, "loss": 0.2974, "lr": 4.1367546123386604e-05, "epoch": 0.89662549839541, "percentage": 29.88, "elapsed_time": "8:11:28", "remaining_time": "19:13:04", "throughput": 61146.45, "total_tokens": 1803088768} {"current_steps": 4620, "total_steps": 15426, "loss": 0.3017, "lr": 4.1353395147662673e-05, "epoch": 0.89857045609258, "percentage": 29.95, "elapsed_time": "8:13:00", "remaining_time": "19:13:07", "throughput": 61085.27, "total_tokens": 1806918528} {"current_steps": 4630, "total_steps": 15426, "loss": 0.2927, "lr": 4.133925868427225e-05, "epoch": 0.9005154137897501, "percentage": 30.01, "elapsed_time": "8:13:58", "remaining_time": "19:11:48", "throughput": 61096.2, "total_tokens": 1810784768} {"current_steps": 4640, "total_steps": 15426, "loss": 0.3025, "lr": 4.132513670842744e-05, "epoch": 0.9024603714869202, "percentage": 30.08, "elapsed_time": "8:14:58", "remaining_time": "19:10:36", "throughput": 61103.14, "total_tokens": 1814668288} {"current_steps": 4650, "total_steps": 15426, "loss": 0.2957, "lr": 4.1311029195399534e-05, "epoch": 0.9044053291840902, "percentage": 30.14, "elapsed_time": "8:15:59", "remaining_time": "19:09:24", "throughput": 61110.78, "total_tokens": 1818618496} {"current_steps": 4660, "total_steps": 15426, "loss": 0.2951, "lr": 4.129693612051892e-05, "epoch": 0.9063502868812603, "percentage": 30.21, "elapsed_time": "8:17:06", "remaining_time": "19:08:27", "throughput": 61104.12, "total_tokens": 1822511744} {"current_steps": 4670, "total_steps": 15426, "loss": 0.2996, "lr": 4.1282857459174826e-05, "epoch": 0.9082952445784305, "percentage": 30.27, "elapsed_time": "8:18:04", "remaining_time": "19:07:11", "throughput": 61111.78, "total_tokens": 1826317440} {"current_steps": 4680, "total_steps": 15426, "loss": 0.2984, "lr": 4.1268793186815184e-05, "epoch": 0.9102402022756005, "percentage": 30.34, "elapsed_time": "8:19:08", "remaining_time": "19:06:05", "throughput": 61114.86, "total_tokens": 1830285696} {"current_steps": 4690, "total_steps": 15426, "loss": 0.3013, "lr": 4.1254743278946456e-05, "epoch": 0.9121851599727706, "percentage": 30.4, "elapsed_time": "8:20:08", "remaining_time": "19:04:52", "throughput": 61122.2, "total_tokens": 1834174208} {"current_steps": 4700, "total_steps": 15426, "loss": 0.2953, "lr": 4.1240707711133394e-05, "epoch": 0.9141301176699407, "percentage": 30.47, "elapsed_time": "8:21:08", "remaining_time": "19:03:40", "throughput": 61131.18, "total_tokens": 1838144640} {"current_steps": 4710, "total_steps": 15426, "loss": 0.2974, "lr": 4.122668645899893e-05, "epoch": 0.9160750753671107, "percentage": 30.53, "elapsed_time": "8:22:10", "remaining_time": "19:02:31", "throughput": 61137.93, "total_tokens": 1842104960} {"current_steps": 4720, "total_steps": 15426, "loss": 0.2977, "lr": 4.1212679498223975e-05, "epoch": 0.9180200330642808, "percentage": 30.6, "elapsed_time": "8:23:09", "remaining_time": "19:01:17", "throughput": 61142.55, "total_tokens": 1845890432} {"current_steps": 4730, "total_steps": 15426, "loss": 0.296, "lr": 4.1198686804547215e-05, "epoch": 0.9199649907614509, "percentage": 30.66, "elapsed_time": "8:24:18", "remaining_time": "19:00:24", "throughput": 61132.86, "total_tokens": 1849806592} {"current_steps": 4740, "total_steps": 15426, "loss": 0.2968, "lr": 4.118470835376499e-05, "epoch": 0.9219099484586211, "percentage": 30.73, "elapsed_time": "8:25:28", "remaining_time": "18:59:33", "throughput": 61122.84, "total_tokens": 1853755008} {"current_steps": 4750, "total_steps": 15426, "loss": 0.2985, "lr": 4.117074412173107e-05, "epoch": 0.9238549061557911, "percentage": 30.79, "elapsed_time": "8:26:29", "remaining_time": "18:58:23", "throughput": 61129.04, "total_tokens": 1857702912} {"current_steps": 4760, "total_steps": 15426, "loss": 0.297, "lr": 4.115679408435648e-05, "epoch": 0.9257998638529612, "percentage": 30.86, "elapsed_time": "8:27:25", "remaining_time": "18:57:00", "throughput": 61141.36, "total_tokens": 1861469696} {"current_steps": 4770, "total_steps": 15426, "loss": 0.298, "lr": 4.114285821760937e-05, "epoch": 0.9277448215501313, "percentage": 30.92, "elapsed_time": "8:28:43", "remaining_time": "18:56:29", "throughput": 61112.12, "total_tokens": 1865377792} {"current_steps": 4780, "total_steps": 15426, "loss": 0.2972, "lr": 4.11289364975148e-05, "epoch": 0.9296897792473013, "percentage": 30.99, "elapsed_time": "8:30:00", "remaining_time": "18:55:53", "throughput": 61084.48, "total_tokens": 1869228416} {"current_steps": 4790, "total_steps": 15426, "loss": 0.296, "lr": 4.111502890015456e-05, "epoch": 0.9316347369444714, "percentage": 31.05, "elapsed_time": "8:31:29", "remaining_time": "18:55:44", "throughput": 61035.56, "total_tokens": 1873135360} {"current_steps": 4800, "total_steps": 15426, "loss": 0.2968, "lr": 4.1101135401667056e-05, "epoch": 0.9335796946416416, "percentage": 31.12, "elapsed_time": "8:34:21", "remaining_time": "18:58:40", "throughput": 60821.61, "total_tokens": 1877060608} {"current_steps": 4810, "total_steps": 15426, "loss": 0.296, "lr": 4.108725597824708e-05, "epoch": 0.9355246523388117, "percentage": 31.18, "elapsed_time": "8:37:10", "remaining_time": "19:01:26", "throughput": 60614.91, "total_tokens": 1880920448} {"current_steps": 4820, "total_steps": 15426, "loss": 0.299, "lr": 4.107339060614564e-05, "epoch": 0.9374696100359817, "percentage": 31.25, "elapsed_time": "8:39:26", "remaining_time": "19:02:59", "throughput": 60476.67, "total_tokens": 1884842624} {"current_steps": 4830, "total_steps": 15426, "loss": 0.2979, "lr": 4.1059539261669825e-05, "epoch": 0.9394145677331518, "percentage": 31.31, "elapsed_time": "8:41:23", "remaining_time": "19:03:50", "throughput": 60380.34, "total_tokens": 1888929024} {"current_steps": 4840, "total_steps": 15426, "loss": 0.2978, "lr": 4.104570192118262e-05, "epoch": 0.9413595254303219, "percentage": 31.38, "elapsed_time": "8:42:59", "remaining_time": "19:03:52", "throughput": 60320.6, "total_tokens": 1892815104} {"current_steps": 4850, "total_steps": 15426, "loss": 0.2968, "lr": 4.1031878561102714e-05, "epoch": 0.9433044831274919, "percentage": 31.44, "elapsed_time": "8:44:34", "remaining_time": "19:03:53", "throughput": 60260.46, "total_tokens": 1896649728} {"current_steps": 4860, "total_steps": 15426, "loss": 0.2979, "lr": 4.1018069157904385e-05, "epoch": 0.9452494408246621, "percentage": 31.51, "elapsed_time": "8:46:08", "remaining_time": "19:03:52", "throughput": 60203.15, "total_tokens": 1900522496} {"current_steps": 4870, "total_steps": 15426, "loss": 0.2934, "lr": 4.100427368811727e-05, "epoch": 0.9471943985218322, "percentage": 31.57, "elapsed_time": "8:48:14", "remaining_time": "19:04:58", "throughput": 60089.59, "total_tokens": 1904484608} {"current_steps": 4880, "total_steps": 15426, "loss": 0.2938, "lr": 4.099049212832622e-05, "epoch": 0.9491393562190023, "percentage": 31.63, "elapsed_time": "8:49:49", "remaining_time": "19:04:58", "throughput": 60035.51, "total_tokens": 1908484608} {"current_steps": 4890, "total_steps": 15426, "loss": 0.2957, "lr": 4.0976724455171155e-05, "epoch": 0.9510843139161723, "percentage": 31.7, "elapsed_time": "8:51:07", "remaining_time": "19:04:22", "throughput": 60011.58, "total_tokens": 1912440320} {"current_steps": 4900, "total_steps": 15426, "loss": 0.2965, "lr": 4.096297064534688e-05, "epoch": 0.9530292716133424, "percentage": 31.76, "elapsed_time": "8:52:18", "remaining_time": "19:03:28", "throughput": 60002.92, "total_tokens": 1916383872} {"current_steps": 4910, "total_steps": 15426, "loss": 0.296, "lr": 4.0949230675602904e-05, "epoch": 0.9549742293105125, "percentage": 31.83, "elapsed_time": "8:53:19", "remaining_time": "19:02:14", "throughput": 60009.68, "total_tokens": 1920263808} {"current_steps": 4920, "total_steps": 15426, "loss": 0.2913, "lr": 4.09355045227433e-05, "epoch": 0.9569191870076826, "percentage": 31.89, "elapsed_time": "8:54:20", "remaining_time": "19:01:01", "throughput": 60019.98, "total_tokens": 1924299264} {"current_steps": 4930, "total_steps": 15426, "loss": 0.2979, "lr": 4.092179216362654e-05, "epoch": 0.9588641447048527, "percentage": 31.96, "elapsed_time": "8:55:19", "remaining_time": "18:59:43", "throughput": 60029.94, "total_tokens": 1928147200} {"current_steps": 4940, "total_steps": 15426, "loss": 0.2976, "lr": 4.090809357516532e-05, "epoch": 0.9608091024020228, "percentage": 32.02, "elapsed_time": "8:56:18", "remaining_time": "18:58:24", "throughput": 60042.31, "total_tokens": 1932063360} {"current_steps": 4950, "total_steps": 15426, "loss": 0.295, "lr": 4.089440873432638e-05, "epoch": 0.9627540600991928, "percentage": 32.09, "elapsed_time": "8:57:19", "remaining_time": "18:57:11", "throughput": 60049.53, "total_tokens": 1935992832} {"current_steps": 4960, "total_steps": 15426, "loss": 0.2975, "lr": 4.088073761813037e-05, "epoch": 0.9646990177963629, "percentage": 32.15, "elapsed_time": "8:58:27", "remaining_time": "18:56:10", "throughput": 60046.08, "total_tokens": 1939909504} {"current_steps": 4970, "total_steps": 15426, "loss": 0.2936, "lr": 4.086708020365172e-05, "epoch": 0.966643975493533, "percentage": 32.22, "elapsed_time": "9:00:44", "remaining_time": "18:57:37", "throughput": 59914.5, "total_tokens": 1943892224} {"current_steps": 4980, "total_steps": 15426, "loss": 0.2974, "lr": 4.0853436468018354e-05, "epoch": 0.968588933190703, "percentage": 32.28, "elapsed_time": "9:02:47", "remaining_time": "18:58:33", "throughput": 59807.23, "total_tokens": 1947792000} {"current_steps": 4990, "total_steps": 15426, "loss": 0.2972, "lr": 4.0839806388411686e-05, "epoch": 0.9705338908878732, "percentage": 32.35, "elapsed_time": "9:04:02", "remaining_time": "18:57:47", "throughput": 59789.02, "total_tokens": 1951650560} {"current_steps": 5000, "total_steps": 15426, "loss": 0.2941, "lr": 4.0826189942066346e-05, "epoch": 0.9724788485850433, "percentage": 32.41, "elapsed_time": "9:04:57", "remaining_time": "18:56:20", "throughput": 59804.19, "total_tokens": 1955450112} {"current_steps": 5000, "total_steps": 15426, "eval_loss": 0.2654576003551483, "epoch": 0.9724788485850433, "percentage": 32.41, "elapsed_time": "9:04:58", "remaining_time": "18:56:23", "throughput": 59801.98, "total_tokens": 1955450112} {"current_steps": 5010, "total_steps": 15426, "loss": 0.2984, "lr": 4.081258710627008e-05, "epoch": 0.9744238062822134, "percentage": 32.48, "elapsed_time": "9:06:13", "remaining_time": "18:55:36", "throughput": 59787.32, "total_tokens": 1959410560} {"current_steps": 5020, "total_steps": 15426, "loss": 0.2961, "lr": 4.0798997858363557e-05, "epoch": 0.9763687639793834, "percentage": 32.54, "elapsed_time": "9:07:11", "remaining_time": "18:54:17", "throughput": 59800.27, "total_tokens": 1963344640} {"current_steps": 5030, "total_steps": 15426, "loss": 0.2932, "lr": 4.078542217574024e-05, "epoch": 0.9783137216765535, "percentage": 32.61, "elapsed_time": "9:08:07", "remaining_time": "18:52:52", "throughput": 59815.05, "total_tokens": 1967192064} {"current_steps": 5040, "total_steps": 15426, "loss": 0.2933, "lr": 4.0771860035846196e-05, "epoch": 0.9802586793737236, "percentage": 32.67, "elapsed_time": "9:09:07", "remaining_time": "18:51:35", "throughput": 59823.83, "total_tokens": 1971036544} {"current_steps": 5050, "total_steps": 15426, "loss": 0.2921, "lr": 4.0758311416179965e-05, "epoch": 0.9822036370708938, "percentage": 32.74, "elapsed_time": "9:10:02", "remaining_time": "18:50:08", "throughput": 59839.5, "total_tokens": 1974853248} {"current_steps": 5060, "total_steps": 15426, "loss": 0.2967, "lr": 4.0744776294292386e-05, "epoch": 0.9841485947680638, "percentage": 32.8, "elapsed_time": "9:10:58", "remaining_time": "18:48:45", "throughput": 59852.51, "total_tokens": 1978663040} {"current_steps": 5070, "total_steps": 15426, "loss": 0.2963, "lr": 4.073125464778646e-05, "epoch": 0.9860935524652339, "percentage": 32.87, "elapsed_time": "9:11:58", "remaining_time": "18:47:28", "throughput": 59863.71, "total_tokens": 1982613504} {"current_steps": 5080, "total_steps": 15426, "loss": 0.2965, "lr": 4.071774645431717e-05, "epoch": 0.988038510162404, "percentage": 32.93, "elapsed_time": "9:12:58", "remaining_time": "18:46:11", "throughput": 59874.32, "total_tokens": 1986522624} {"current_steps": 5090, "total_steps": 15426, "loss": 0.2958, "lr": 4.070425169159135e-05, "epoch": 0.989983467859574, "percentage": 33.0, "elapsed_time": "9:13:55", "remaining_time": "18:44:49", "throughput": 59889.81, "total_tokens": 1990452736} {"current_steps": 5100, "total_steps": 15426, "loss": 0.2977, "lr": 4.069077033736751e-05, "epoch": 0.9919284255567441, "percentage": 33.06, "elapsed_time": "9:14:52", "remaining_time": "18:43:27", "throughput": 59904.06, "total_tokens": 1994362880} {"current_steps": 5110, "total_steps": 15426, "loss": 0.2946, "lr": 4.06773023694557e-05, "epoch": 0.9938733832539143, "percentage": 33.13, "elapsed_time": "9:15:51", "remaining_time": "18:42:08", "throughput": 59915.64, "total_tokens": 1998250112} {"current_steps": 5120, "total_steps": 15426, "loss": 0.3001, "lr": 4.066384776571732e-05, "epoch": 0.9958183409510843, "percentage": 33.19, "elapsed_time": "9:17:46", "remaining_time": "18:42:44", "throughput": 59826.04, "total_tokens": 2002159488} {"current_steps": 5130, "total_steps": 15426, "loss": 0.2943, "lr": 4.065040650406504e-05, "epoch": 0.9977632986482544, "percentage": 33.26, "elapsed_time": "9:19:14", "remaining_time": "18:42:23", "throughput": 59784.89, "total_tokens": 2006027904} {"current_steps": 5140, "total_steps": 15426, "loss": 0.2937, "lr": 4.0636978562462576e-05, "epoch": 0.9997082563454245, "percentage": 33.32, "elapsed_time": "9:20:24", "remaining_time": "18:41:28", "throughput": 59771.77, "total_tokens": 2009803904} {"current_steps": 5150, "total_steps": 15426, "loss": 0.283, "lr": 4.062356391892456e-05, "epoch": 1.001555966157736, "percentage": 33.39, "elapsed_time": "9:21:23", "remaining_time": "18:40:09", "throughput": 59775.67, "total_tokens": 2013434368} {"current_steps": 5160, "total_steps": 15426, "loss": 0.2777, "lr": 4.0610162551516395e-05, "epoch": 1.0035009238549062, "percentage": 33.45, "elapsed_time": "9:22:19", "remaining_time": "18:38:46", "throughput": 59789.49, "total_tokens": 2017290752} {"current_steps": 5170, "total_steps": 15426, "loss": 0.2798, "lr": 4.059677443835412e-05, "epoch": 1.0054458815520761, "percentage": 33.51, "elapsed_time": "9:23:18", "remaining_time": "18:37:27", "throughput": 59802.45, "total_tokens": 2021209600} {"current_steps": 5180, "total_steps": 15426, "loss": 0.2793, "lr": 4.058339955760423e-05, "epoch": 1.0073908392492463, "percentage": 33.58, "elapsed_time": "9:24:25", "remaining_time": "18:36:25", "throughput": 59801.78, "total_tokens": 2025198592} {"current_steps": 5190, "total_steps": 15426, "loss": 0.2804, "lr": 4.0570037887483535e-05, "epoch": 1.0093357969464165, "percentage": 33.64, "elapsed_time": "9:25:37", "remaining_time": "18:35:34", "throughput": 59787.81, "total_tokens": 2029076864} {"current_steps": 5200, "total_steps": 15426, "loss": 0.2805, "lr": 4.0556689406259025e-05, "epoch": 1.0112807546435865, "percentage": 33.71, "elapsed_time": "9:27:21", "remaining_time": "18:35:44", "throughput": 59722.13, "total_tokens": 2033045376} {"current_steps": 5210, "total_steps": 15426, "loss": 0.2789, "lr": 4.054335409224771e-05, "epoch": 1.0132257123407566, "percentage": 33.77, "elapsed_time": "9:29:12", "remaining_time": "18:36:07", "throughput": 59641.07, "total_tokens": 2036886144} {"current_steps": 5220, "total_steps": 15426, "loss": 0.2759, "lr": 4.053003192381646e-05, "epoch": 1.0151706700379266, "percentage": 33.84, "elapsed_time": "9:30:51", "remaining_time": "18:36:07", "throughput": 59583.02, "total_tokens": 2040794880} {"current_steps": 5230, "total_steps": 15426, "loss": 0.2795, "lr": 4.051672287938189e-05, "epoch": 1.0171156277350968, "percentage": 33.9, "elapsed_time": "9:31:58", "remaining_time": "18:35:04", "throughput": 59582.87, "total_tokens": 2044797824} {"current_steps": 5240, "total_steps": 15426, "loss": 0.2748, "lr": 4.050342693741019e-05, "epoch": 1.0190605854322667, "percentage": 33.97, "elapsed_time": "9:33:06", "remaining_time": "18:34:03", "throughput": 59579.55, "total_tokens": 2048728832} {"current_steps": 5250, "total_steps": 15426, "loss": 0.279, "lr": 4.049014407641699e-05, "epoch": 1.021005543129437, "percentage": 34.03, "elapsed_time": "9:34:09", "remaining_time": "18:32:52", "throughput": 59582.07, "total_tokens": 2052567552} {"current_steps": 5260, "total_steps": 15426, "loss": 0.2824, "lr": 4.047687427496717e-05, "epoch": 1.022950500826607, "percentage": 34.1, "elapsed_time": "9:35:15", "remaining_time": "18:31:47", "throughput": 59582.11, "total_tokens": 2056485120} {"current_steps": 5270, "total_steps": 15426, "loss": 0.281, "lr": 4.046361751167479e-05, "epoch": 1.024895458523777, "percentage": 34.16, "elapsed_time": "9:36:12", "remaining_time": "18:30:26", "throughput": 59594.9, "total_tokens": 2060351104} {"current_steps": 5280, "total_steps": 15426, "loss": 0.2791, "lr": 4.045037376520292e-05, "epoch": 1.0268404162209472, "percentage": 34.23, "elapsed_time": "9:37:13", "remaining_time": "18:29:11", "throughput": 59602.24, "total_tokens": 2064237696} {"current_steps": 5290, "total_steps": 15426, "loss": 0.2794, "lr": 4.043714301426344e-05, "epoch": 1.0287853739181172, "percentage": 34.29, "elapsed_time": "9:38:22", "remaining_time": "18:28:12", "throughput": 59601.77, "total_tokens": 2068338816} {"current_steps": 5300, "total_steps": 15426, "loss": 0.2773, "lr": 4.042392523761696e-05, "epoch": 1.0307303316152874, "percentage": 34.36, "elapsed_time": "9:39:20", "remaining_time": "18:26:51", "throughput": 59614.73, "total_tokens": 2072217344} {"current_steps": 5310, "total_steps": 15426, "loss": 0.2771, "lr": 4.041072041407267e-05, "epoch": 1.0326752893124576, "percentage": 34.42, "elapsed_time": "9:40:20", "remaining_time": "18:25:36", "throughput": 59621.04, "total_tokens": 2076036992} {"current_steps": 5320, "total_steps": 15426, "loss": 0.2803, "lr": 4.039752852248815e-05, "epoch": 1.0346202470096275, "percentage": 34.49, "elapsed_time": "9:41:19", "remaining_time": "18:24:17", "throughput": 59632.66, "total_tokens": 2079956352} {"current_steps": 5330, "total_steps": 15426, "loss": 0.28, "lr": 4.0384349541769286e-05, "epoch": 1.0365652047067977, "percentage": 34.55, "elapsed_time": "9:42:24", "remaining_time": "18:23:11", "throughput": 59632.07, "total_tokens": 2083830656} {"current_steps": 5340, "total_steps": 15426, "loss": 0.2794, "lr": 4.037118345087011e-05, "epoch": 1.0385101624039677, "percentage": 34.62, "elapsed_time": "9:43:33", "remaining_time": "18:22:12", "throughput": 59627.87, "total_tokens": 2087780992} {"current_steps": 5350, "total_steps": 15426, "loss": 0.2768, "lr": 4.0358030228792636e-05, "epoch": 1.0404551201011378, "percentage": 34.68, "elapsed_time": "9:44:35", "remaining_time": "18:21:00", "throughput": 59632.57, "total_tokens": 2091659904} {"current_steps": 5360, "total_steps": 15426, "loss": 0.2799, "lr": 4.034488985458673e-05, "epoch": 1.0424000777983078, "percentage": 34.75, "elapsed_time": "9:45:44", "remaining_time": "18:20:01", "throughput": 59626.47, "total_tokens": 2095563904} {"current_steps": 5370, "total_steps": 15426, "loss": 0.2795, "lr": 4.033176230735001e-05, "epoch": 1.044345035495478, "percentage": 34.81, "elapsed_time": "9:46:42", "remaining_time": "18:18:41", "throughput": 59636.1, "total_tokens": 2099352192} {"current_steps": 5380, "total_steps": 15426, "loss": 0.2792, "lr": 4.0318647566227626e-05, "epoch": 1.0462899931926481, "percentage": 34.88, "elapsed_time": "9:47:42", "remaining_time": "18:17:26", "throughput": 59642.93, "total_tokens": 2103184896} {"current_steps": 5390, "total_steps": 15426, "loss": 0.2782, "lr": 4.0305545610412205e-05, "epoch": 1.048234950889818, "percentage": 34.94, "elapsed_time": "9:48:42", "remaining_time": "18:16:09", "throughput": 59652.3, "total_tokens": 2107068672} {"current_steps": 5400, "total_steps": 15426, "loss": 0.2796, "lr": 4.029245641914365e-05, "epoch": 1.0501799085869883, "percentage": 35.01, "elapsed_time": "9:49:44", "remaining_time": "18:14:57", "throughput": 59659.6, "total_tokens": 2111020672} {"current_steps": 5410, "total_steps": 15426, "loss": 0.2806, "lr": 4.027937997170904e-05, "epoch": 1.0521248662841582, "percentage": 35.07, "elapsed_time": "9:50:42", "remaining_time": "18:13:36", "throughput": 59671.68, "total_tokens": 2114884352} {"current_steps": 5420, "total_steps": 15426, "loss": 0.2778, "lr": 4.026631624744247e-05, "epoch": 1.0540698239813284, "percentage": 35.14, "elapsed_time": "9:51:45", "remaining_time": "18:12:28", "throughput": 59673.76, "total_tokens": 2118776448} {"current_steps": 5430, "total_steps": 15426, "loss": 0.2787, "lr": 4.025326522572493e-05, "epoch": 1.0560147816784986, "percentage": 35.2, "elapsed_time": "9:52:56", "remaining_time": "18:11:33", "throughput": 59664.8, "total_tokens": 2122693760} {"current_steps": 5440, "total_steps": 15426, "loss": 0.2783, "lr": 4.024022688598415e-05, "epoch": 1.0579597393756686, "percentage": 35.27, "elapsed_time": "9:54:15", "remaining_time": "18:10:52", "throughput": 59640.73, "total_tokens": 2126544896} {"current_steps": 5450, "total_steps": 15426, "loss": 0.2803, "lr": 4.0227201207694494e-05, "epoch": 1.0599046970728387, "percentage": 35.33, "elapsed_time": "9:56:04", "remaining_time": "18:11:04", "throughput": 59571.29, "total_tokens": 2130515328} {"current_steps": 5460, "total_steps": 15426, "loss": 0.2797, "lr": 4.021418817037677e-05, "epoch": 1.0618496547700087, "percentage": 35.39, "elapsed_time": "9:57:58", "remaining_time": "18:11:27", "throughput": 59494.28, "total_tokens": 2134536192} {"current_steps": 5470, "total_steps": 15426, "loss": 0.2774, "lr": 4.0201187753598174e-05, "epoch": 1.0637946124671789, "percentage": 35.46, "elapsed_time": "9:59:00", "remaining_time": "18:10:16", "throughput": 59502.23, "total_tokens": 2138554240} {"current_steps": 5480, "total_steps": 15426, "loss": 0.2769, "lr": 4.018819993697208e-05, "epoch": 1.0657395701643488, "percentage": 35.52, "elapsed_time": "9:59:58", "remaining_time": "18:08:56", "throughput": 59514.69, "total_tokens": 2142449536} {"current_steps": 5490, "total_steps": 15426, "loss": 0.2772, "lr": 4.017522470015793e-05, "epoch": 1.067684527861519, "percentage": 35.59, "elapsed_time": "10:00:57", "remaining_time": "18:07:38", "throughput": 59525.44, "total_tokens": 2146354688} {"current_steps": 5500, "total_steps": 15426, "loss": 0.279, "lr": 4.0162262022861144e-05, "epoch": 1.0696294855586892, "percentage": 35.65, "elapsed_time": "10:01:56", "remaining_time": "18:06:20", "throughput": 59536.33, "total_tokens": 2150260224} {"current_steps": 5510, "total_steps": 15426, "loss": 0.2803, "lr": 4.0149311884832906e-05, "epoch": 1.0715744432558592, "percentage": 35.72, "elapsed_time": "10:02:54", "remaining_time": "18:05:00", "throughput": 59548.04, "total_tokens": 2154109184} {"current_steps": 5520, "total_steps": 15426, "loss": 0.2791, "lr": 4.0136374265870116e-05, "epoch": 1.0735194009530293, "percentage": 35.78, "elapsed_time": "10:03:53", "remaining_time": "18:03:42", "throughput": 59557.94, "total_tokens": 2157963392} {"current_steps": 5530, "total_steps": 15426, "loss": 0.2816, "lr": 4.0123449145815174e-05, "epoch": 1.0754643586501993, "percentage": 35.85, "elapsed_time": "10:04:53", "remaining_time": "18:02:28", "throughput": 59565.73, "total_tokens": 2161866496} {"current_steps": 5540, "total_steps": 15426, "loss": 0.2774, "lr": 4.011053650455592e-05, "epoch": 1.0774093163473695, "percentage": 35.91, "elapsed_time": "10:05:56", "remaining_time": "18:01:17", "throughput": 59572.11, "total_tokens": 2165844864} {"current_steps": 5550, "total_steps": 15426, "loss": 0.2763, "lr": 4.0097636322025466e-05, "epoch": 1.0793542740445394, "percentage": 35.98, "elapsed_time": "10:06:54", "remaining_time": "17:59:58", "throughput": 59585.3, "total_tokens": 2169767680} {"current_steps": 5560, "total_steps": 15426, "loss": 0.2773, "lr": 4.008474857820206e-05, "epoch": 1.0812992317417096, "percentage": 36.04, "elapsed_time": "10:07:55", "remaining_time": "17:58:43", "throughput": 59595.53, "total_tokens": 2173759872} {"current_steps": 5570, "total_steps": 15426, "loss": 0.277, "lr": 4.007187325310899e-05, "epoch": 1.0832441894388798, "percentage": 36.11, "elapsed_time": "10:08:52", "remaining_time": "17:57:23", "throughput": 59608.1, "total_tokens": 2177643520} {"current_steps": 5580, "total_steps": 15426, "loss": 0.2773, "lr": 4.00590103268144e-05, "epoch": 1.0851891471360497, "percentage": 36.17, "elapsed_time": "10:09:48", "remaining_time": "17:56:01", "throughput": 59621.83, "total_tokens": 2181484544} {"current_steps": 5590, "total_steps": 15426, "loss": 0.276, "lr": 4.004615977943124e-05, "epoch": 1.08713410483322, "percentage": 36.24, "elapsed_time": "10:10:50", "remaining_time": "17:54:49", "throughput": 59628.14, "total_tokens": 2185417600} {"current_steps": 5600, "total_steps": 15426, "loss": 0.2776, "lr": 4.0033321591117025e-05, "epoch": 1.0890790625303899, "percentage": 36.3, "elapsed_time": "10:11:49", "remaining_time": "17:53:32", "throughput": 59640.19, "total_tokens": 2189383296} {"current_steps": 5610, "total_steps": 15426, "loss": 0.2792, "lr": 4.002049574207381e-05, "epoch": 1.09102402022756, "percentage": 36.37, "elapsed_time": "10:12:48", "remaining_time": "17:52:14", "throughput": 59651.42, "total_tokens": 2193276672} {"current_steps": 5620, "total_steps": 15426, "loss": 0.2757, "lr": 4.000768221254803e-05, "epoch": 1.09296897792473, "percentage": 36.43, "elapsed_time": "10:13:46", "remaining_time": "17:50:56", "throughput": 59662.88, "total_tokens": 2197166208} {"current_steps": 5630, "total_steps": 15426, "loss": 0.2819, "lr": 3.999488098283034e-05, "epoch": 1.0949139356219002, "percentage": 36.5, "elapsed_time": "10:14:42", "remaining_time": "17:49:33", "throughput": 59676.27, "total_tokens": 2200987392} {"current_steps": 5640, "total_steps": 15426, "loss": 0.2803, "lr": 3.9982092033255506e-05, "epoch": 1.0968588933190704, "percentage": 36.56, "elapsed_time": "10:15:37", "remaining_time": "17:48:10", "throughput": 59690.76, "total_tokens": 2204827776} {"current_steps": 5650, "total_steps": 15426, "loss": 0.2813, "lr": 3.996931534420232e-05, "epoch": 1.0988038510162403, "percentage": 36.63, "elapsed_time": "10:16:34", "remaining_time": "17:46:50", "throughput": 59702.19, "total_tokens": 2208676224} {"current_steps": 5660, "total_steps": 15426, "loss": 0.2768, "lr": 3.995655089609339e-05, "epoch": 1.1007488087134105, "percentage": 36.69, "elapsed_time": "10:17:35", "remaining_time": "17:45:36", "throughput": 59709.13, "total_tokens": 2212533632} {"current_steps": 5670, "total_steps": 15426, "loss": 0.2799, "lr": 3.994379866939511e-05, "epoch": 1.1026937664105805, "percentage": 36.76, "elapsed_time": "10:18:45", "remaining_time": "17:44:40", "throughput": 59701.4, "total_tokens": 2216466176} {"current_steps": 5680, "total_steps": 15426, "loss": 0.2829, "lr": 3.993105864461745e-05, "epoch": 1.1046387241077507, "percentage": 36.82, "elapsed_time": "10:20:53", "remaining_time": "17:45:21", "throughput": 59601.58, "total_tokens": 2220377472} {"current_steps": 5690, "total_steps": 15426, "loss": 0.2767, "lr": 3.9918330802313866e-05, "epoch": 1.1065836818049208, "percentage": 36.89, "elapsed_time": "10:23:28", "remaining_time": "17:46:49", "throughput": 59459.31, "total_tokens": 2224304640} {"current_steps": 5700, "total_steps": 15426, "loss": 0.2777, "lr": 3.9905615123081206e-05, "epoch": 1.1085286395020908, "percentage": 36.95, "elapsed_time": "10:25:44", "remaining_time": "17:47:43", "throughput": 59347.09, "total_tokens": 2228167552} {"current_steps": 5710, "total_steps": 15426, "loss": 0.2795, "lr": 3.989291158755953e-05, "epoch": 1.110473597199261, "percentage": 37.02, "elapsed_time": "10:28:03", "remaining_time": "17:48:40", "throughput": 59231.9, "total_tokens": 2232036096} {"current_steps": 5720, "total_steps": 15426, "loss": 0.2777, "lr": 3.988022017643201e-05, "epoch": 1.112418554896431, "percentage": 37.08, "elapsed_time": "10:29:45", "remaining_time": "17:48:35", "throughput": 59175.94, "total_tokens": 2235974400} {"current_steps": 5730, "total_steps": 15426, "loss": 0.2773, "lr": 3.9867540870424826e-05, "epoch": 1.1143635125936011, "percentage": 37.15, "elapsed_time": "10:31:29", "remaining_time": "17:48:34", "throughput": 59118.09, "total_tokens": 2239968000} {"current_steps": 5740, "total_steps": 15426, "loss": 0.278, "lr": 3.985487365030702e-05, "epoch": 1.1163084702907713, "percentage": 37.21, "elapsed_time": "10:33:04", "remaining_time": "17:48:16", "throughput": 59073.97, "total_tokens": 2243870720} {"current_steps": 5750, "total_steps": 15426, "loss": 0.2761, "lr": 3.984221849689036e-05, "epoch": 1.1182534279879413, "percentage": 37.27, "elapsed_time": "10:34:35", "remaining_time": "17:47:52", "throughput": 59035.87, "total_tokens": 2247793536} {"current_steps": 5760, "total_steps": 15426, "loss": 0.2784, "lr": 3.982957539102927e-05, "epoch": 1.1201983856851114, "percentage": 37.34, "elapsed_time": "10:35:59", "remaining_time": "17:47:16", "throughput": 59005.8, "total_tokens": 2251644928} {"current_steps": 5770, "total_steps": 15426, "loss": 0.2751, "lr": 3.981694431362065e-05, "epoch": 1.1221433433822814, "percentage": 37.4, "elapsed_time": "10:37:27", "remaining_time": "17:46:47", "throughput": 58973.4, "total_tokens": 2255603584} {"current_steps": 5780, "total_steps": 15426, "loss": 0.2769, "lr": 3.9804325245603786e-05, "epoch": 1.1240883010794516, "percentage": 37.47, "elapsed_time": "10:38:51", "remaining_time": "17:46:10", "throughput": 58945.06, "total_tokens": 2259466880} {"current_steps": 5790, "total_steps": 15426, "loss": 0.2795, "lr": 3.9791718167960226e-05, "epoch": 1.1260332587766215, "percentage": 37.53, "elapsed_time": "10:40:09", "remaining_time": "17:45:22", "throughput": 58928.31, "total_tokens": 2263389056} {"current_steps": 5800, "total_steps": 15426, "loss": 0.2801, "lr": 3.9779123061713665e-05, "epoch": 1.1279782164737917, "percentage": 37.6, "elapsed_time": "10:41:10", "remaining_time": "17:44:08", "throughput": 58936.36, "total_tokens": 2267319936} {"current_steps": 5810, "total_steps": 15426, "loss": 0.2818, "lr": 3.976653990792979e-05, "epoch": 1.1299231741709619, "percentage": 37.66, "elapsed_time": "10:42:09", "remaining_time": "17:42:49", "throughput": 58949.95, "total_tokens": 2271320576} {"current_steps": 5820, "total_steps": 15426, "loss": 0.2767, "lr": 3.9753968687716206e-05, "epoch": 1.1318681318681318, "percentage": 37.73, "elapsed_time": "10:43:05", "remaining_time": "17:41:26", "throughput": 58965.07, "total_tokens": 2275221760} {"current_steps": 5830, "total_steps": 15426, "loss": 0.2772, "lr": 3.974140938222232e-05, "epoch": 1.133813089565302, "percentage": 37.79, "elapsed_time": "10:44:05", "remaining_time": "17:40:09", "throughput": 58976.54, "total_tokens": 2279184256} {"current_steps": 5840, "total_steps": 15426, "loss": 0.2776, "lr": 3.972886197263915e-05, "epoch": 1.135758047262472, "percentage": 37.86, "elapsed_time": "10:45:03", "remaining_time": "17:38:49", "throughput": 58991.04, "total_tokens": 2283165440} {"current_steps": 5850, "total_steps": 15426, "loss": 0.2784, "lr": 3.97163264401993e-05, "epoch": 1.1377030049596422, "percentage": 37.92, "elapsed_time": "10:46:03", "remaining_time": "17:37:33", "throughput": 59002.49, "total_tokens": 2287150208} {"current_steps": 5860, "total_steps": 15426, "loss": 0.2789, "lr": 3.970380276617677e-05, "epoch": 1.1396479626568121, "percentage": 37.99, "elapsed_time": "10:47:00", "remaining_time": "17:36:12", "throughput": 59015.71, "total_tokens": 2291045120} {"current_steps": 5870, "total_steps": 15426, "loss": 0.2783, "lr": 3.96912909318869e-05, "epoch": 1.1415929203539823, "percentage": 38.05, "elapsed_time": "10:48:03", "remaining_time": "17:34:59", "throughput": 59019.63, "total_tokens": 2294886400} {"current_steps": 5880, "total_steps": 15426, "loss": 0.2768, "lr": 3.96787909186862e-05, "epoch": 1.1435378780511525, "percentage": 38.12, "elapsed_time": "10:48:57", "remaining_time": "17:33:34", "throughput": 59035.27, "total_tokens": 2298712704} {"current_steps": 5890, "total_steps": 15426, "loss": 0.2789, "lr": 3.9666302707972244e-05, "epoch": 1.1454828357483224, "percentage": 38.18, "elapsed_time": "10:50:23", "remaining_time": "17:32:59", "throughput": 59007.12, "total_tokens": 2302645248} {"current_steps": 5900, "total_steps": 15426, "loss": 0.2755, "lr": 3.965382628118358e-05, "epoch": 1.1474277934454926, "percentage": 38.25, "elapsed_time": "10:52:10", "remaining_time": "17:32:58", "throughput": 58946.38, "total_tokens": 2306586368} {"current_steps": 5910, "total_steps": 15426, "loss": 0.2781, "lr": 3.964136161979959e-05, "epoch": 1.1493727511426626, "percentage": 38.31, "elapsed_time": "10:54:21", "remaining_time": "17:33:37", "throughput": 58848.09, "total_tokens": 2310474496} {"current_steps": 5920, "total_steps": 15426, "loss": 0.2776, "lr": 3.9628908705340406e-05, "epoch": 1.1513177088398328, "percentage": 38.38, "elapsed_time": "10:55:22", "remaining_time": "17:32:22", "throughput": 58855.44, "total_tokens": 2314372096} {"current_steps": 5930, "total_steps": 15426, "loss": 0.2772, "lr": 3.961646751936673e-05, "epoch": 1.1532626665370027, "percentage": 38.44, "elapsed_time": "10:56:27", "remaining_time": "17:31:13", "throughput": 58859.44, "total_tokens": 2318342784} {"current_steps": 5940, "total_steps": 15426, "loss": 0.2799, "lr": 3.960403804347979e-05, "epoch": 1.155207624234173, "percentage": 38.51, "elapsed_time": "10:57:24", "remaining_time": "17:29:51", "throughput": 58874.57, "total_tokens": 2322277376} {"current_steps": 5950, "total_steps": 15426, "loss": 0.2789, "lr": 3.959162025932119e-05, "epoch": 1.157152581931343, "percentage": 38.57, "elapsed_time": "10:58:20", "remaining_time": "17:28:28", "throughput": 58887.83, "total_tokens": 2326109056} {"current_steps": 5960, "total_steps": 15426, "loss": 0.2736, "lr": 3.95792141485728e-05, "epoch": 1.159097539628513, "percentage": 38.64, "elapsed_time": "10:59:35", "remaining_time": "17:27:35", "throughput": 58877.09, "total_tokens": 2330069248} {"current_steps": 5970, "total_steps": 15426, "loss": 0.2747, "lr": 3.956681969295664e-05, "epoch": 1.1610424973256832, "percentage": 38.7, "elapsed_time": "11:00:34", "remaining_time": "17:26:17", "throughput": 58889.86, "total_tokens": 2334072448} {"current_steps": 5980, "total_steps": 15426, "loss": 0.2817, "lr": 3.955443687423479e-05, "epoch": 1.1629874550228532, "percentage": 38.77, "elapsed_time": "11:01:30", "remaining_time": "17:24:55", "throughput": 58904.96, "total_tokens": 2337969152} {"current_steps": 5990, "total_steps": 15426, "loss": 0.2776, "lr": 3.954206567420924e-05, "epoch": 1.1649324127200233, "percentage": 38.83, "elapsed_time": "11:02:27", "remaining_time": "17:23:33", "throughput": 58917.54, "total_tokens": 2341798272} {"current_steps": 6000, "total_steps": 15426, "loss": 0.2801, "lr": 3.952970607472179e-05, "epoch": 1.1668773704171933, "percentage": 38.9, "elapsed_time": "11:03:20", "remaining_time": "17:22:07", "throughput": 58934.12, "total_tokens": 2345630592} {"current_steps": 6010, "total_steps": 15426, "loss": 0.2795, "lr": 3.951735805765399e-05, "epoch": 1.1688223281143635, "percentage": 38.96, "elapsed_time": "11:04:17", "remaining_time": "17:20:45", "throughput": 58950.49, "total_tokens": 2349612544} {"current_steps": 6020, "total_steps": 15426, "loss": 0.2794, "lr": 3.950502160492692e-05, "epoch": 1.1707672858115337, "percentage": 39.03, "elapsed_time": "11:05:14", "remaining_time": "17:19:24", "throughput": 58963.76, "total_tokens": 2353504768} {"current_steps": 6030, "total_steps": 15426, "loss": 0.2773, "lr": 3.9492696698501205e-05, "epoch": 1.1727122435087036, "percentage": 39.09, "elapsed_time": "11:06:11", "remaining_time": "17:18:03", "throughput": 58976.71, "total_tokens": 2357363072} {"current_steps": 6040, "total_steps": 15426, "loss": 0.2765, "lr": 3.9480383320376784e-05, "epoch": 1.1746572012058738, "percentage": 39.15, "elapsed_time": "11:07:07", "remaining_time": "17:16:42", "throughput": 58990.71, "total_tokens": 2361272448} {"current_steps": 6050, "total_steps": 15426, "loss": 0.2793, "lr": 3.94680814525929e-05, "epoch": 1.176602158903044, "percentage": 39.22, "elapsed_time": "11:08:03", "remaining_time": "17:15:19", "throughput": 59004.52, "total_tokens": 2365096960} {"current_steps": 6060, "total_steps": 15426, "loss": 0.2782, "lr": 3.945579107722792e-05, "epoch": 1.178547116600214, "percentage": 39.28, "elapsed_time": "11:09:01", "remaining_time": "17:14:00", "throughput": 59017.56, "total_tokens": 2369052160} {"current_steps": 6070, "total_steps": 15426, "loss": 0.2813, "lr": 3.9443512176399276e-05, "epoch": 1.1804920742973841, "percentage": 39.35, "elapsed_time": "11:09:56", "remaining_time": "17:12:36", "throughput": 59031.54, "total_tokens": 2372858880} {"current_steps": 6080, "total_steps": 15426, "loss": 0.2789, "lr": 3.9431244732263307e-05, "epoch": 1.182437031994554, "percentage": 39.41, "elapsed_time": "11:10:52", "remaining_time": "17:11:15", "throughput": 59045.64, "total_tokens": 2376753664} {"current_steps": 6090, "total_steps": 15426, "loss": 0.275, "lr": 3.941898872701519e-05, "epoch": 1.1843819896917243, "percentage": 39.48, "elapsed_time": "11:11:50", "remaining_time": "17:09:55", "throughput": 59060.75, "total_tokens": 2380760704} {"current_steps": 6100, "total_steps": 15426, "loss": 0.2806, "lr": 3.940674414288882e-05, "epoch": 1.1863269473888942, "percentage": 39.54, "elapsed_time": "11:12:47", "remaining_time": "17:08:35", "throughput": 59075.13, "total_tokens": 2384712576} {"current_steps": 6110, "total_steps": 15426, "loss": 0.2768, "lr": 3.939451096215668e-05, "epoch": 1.1882719050860644, "percentage": 39.61, "elapsed_time": "11:13:46", "remaining_time": "17:07:18", "throughput": 59088.0, "total_tokens": 2388702720} {"current_steps": 6120, "total_steps": 15426, "loss": 0.2725, "lr": 3.938228916712978e-05, "epoch": 1.1902168627832346, "percentage": 39.67, "elapsed_time": "11:14:44", "remaining_time": "17:06:00", "throughput": 59101.12, "total_tokens": 2392692736} {"current_steps": 6130, "total_steps": 15426, "loss": 0.2816, "lr": 3.937007874015748e-05, "epoch": 1.1921618204804045, "percentage": 39.74, "elapsed_time": "11:15:46", "remaining_time": "17:04:48", "throughput": 59105.03, "total_tokens": 2396530944} {"current_steps": 6140, "total_steps": 15426, "loss": 0.2794, "lr": 3.935787966362748e-05, "epoch": 1.1941067781775747, "percentage": 39.8, "elapsed_time": "11:16:45", "remaining_time": "17:03:30", "throughput": 59115.25, "total_tokens": 2400388352} {"current_steps": 6150, "total_steps": 15426, "loss": 0.2786, "lr": 3.9345691919965595e-05, "epoch": 1.1960517358747447, "percentage": 39.87, "elapsed_time": "11:18:07", "remaining_time": "17:02:48", "throughput": 59088.94, "total_tokens": 2404193920} {"current_steps": 6160, "total_steps": 15426, "loss": 0.2792, "lr": 3.9333515491635764e-05, "epoch": 1.1979966935719149, "percentage": 39.93, "elapsed_time": "11:19:32", "remaining_time": "17:02:11", "throughput": 59059.98, "total_tokens": 2408048896} {"current_steps": 6170, "total_steps": 15426, "loss": 0.2753, "lr": 3.932135036113987e-05, "epoch": 1.1999416512690848, "percentage": 40.0, "elapsed_time": "11:20:39", "remaining_time": "17:01:05", "throughput": 59062.0, "total_tokens": 2412059520} {"current_steps": 6180, "total_steps": 15426, "loss": 0.2776, "lr": 3.930919651101764e-05, "epoch": 1.201886608966255, "percentage": 40.06, "elapsed_time": "11:21:33", "remaining_time": "16:59:42", "throughput": 59078.49, "total_tokens": 2415952640} {"current_steps": 6190, "total_steps": 15426, "loss": 0.2755, "lr": 3.9297053923846576e-05, "epoch": 1.2038315666634252, "percentage": 40.13, "elapsed_time": "11:22:30", "remaining_time": "16:58:22", "throughput": 59090.55, "total_tokens": 2419812224} {"current_steps": 6200, "total_steps": 15426, "loss": 0.2769, "lr": 3.928492258224183e-05, "epoch": 1.2057765243605951, "percentage": 40.19, "elapsed_time": "11:23:30", "remaining_time": "16:57:06", "throughput": 59101.69, "total_tokens": 2423792384} {"current_steps": 6210, "total_steps": 15426, "loss": 0.2809, "lr": 3.927280246885609e-05, "epoch": 1.2077214820577653, "percentage": 40.26, "elapsed_time": "11:24:27", "remaining_time": "16:55:46", "throughput": 59114.48, "total_tokens": 2427664768} {"current_steps": 6220, "total_steps": 15426, "loss": 0.2778, "lr": 3.9260693566379486e-05, "epoch": 1.2096664397549353, "percentage": 40.32, "elapsed_time": "11:25:24", "remaining_time": "16:54:27", "throughput": 59127.19, "total_tokens": 2431594752} {"current_steps": 6230, "total_steps": 15426, "loss": 0.2771, "lr": 3.924859585753948e-05, "epoch": 1.2116113974521054, "percentage": 40.39, "elapsed_time": "11:26:22", "remaining_time": "16:53:09", "throughput": 59140.95, "total_tokens": 2435589248} {"current_steps": 6240, "total_steps": 15426, "loss": 0.2793, "lr": 3.923650932510079e-05, "epoch": 1.2135563551492754, "percentage": 40.45, "elapsed_time": "11:27:16", "remaining_time": "16:51:44", "throughput": 59157.35, "total_tokens": 2439446272} {"current_steps": 6250, "total_steps": 15426, "loss": 0.2791, "lr": 3.9224433951865215e-05, "epoch": 1.2155013128464456, "percentage": 40.52, "elapsed_time": "11:28:10", "remaining_time": "16:50:20", "throughput": 59173.4, "total_tokens": 2443271424} {"current_steps": 6260, "total_steps": 15426, "loss": 0.2765, "lr": 3.921236972067165e-05, "epoch": 1.2174462705436158, "percentage": 40.58, "elapsed_time": "11:29:06", "remaining_time": "16:48:59", "throughput": 59187.78, "total_tokens": 2447192320} {"current_steps": 6270, "total_steps": 15426, "loss": 0.2772, "lr": 3.920031661439585e-05, "epoch": 1.2193912282407857, "percentage": 40.65, "elapsed_time": "11:30:02", "remaining_time": "16:47:39", "throughput": 59202.31, "total_tokens": 2451135360} {"current_steps": 6280, "total_steps": 15426, "loss": 0.2767, "lr": 3.918827461595045e-05, "epoch": 1.221336185937956, "percentage": 40.71, "elapsed_time": "11:30:59", "remaining_time": "16:46:20", "throughput": 59213.25, "total_tokens": 2454966656} {"current_steps": 6290, "total_steps": 15426, "loss": 0.2763, "lr": 3.9176243708284746e-05, "epoch": 1.2232811436351259, "percentage": 40.78, "elapsed_time": "11:31:56", "remaining_time": "16:45:01", "throughput": 59228.2, "total_tokens": 2458970624} {"current_steps": 6300, "total_steps": 15426, "loss": 0.2742, "lr": 3.9164223874384715e-05, "epoch": 1.225226101332296, "percentage": 40.84, "elapsed_time": "11:32:51", "remaining_time": "16:43:39", "throughput": 59243.0, "total_tokens": 2462830336} {"current_steps": 6310, "total_steps": 15426, "loss": 0.2762, "lr": 3.91522150972728e-05, "epoch": 1.227171059029466, "percentage": 40.9, "elapsed_time": "11:33:51", "remaining_time": "16:42:24", "throughput": 59256.17, "total_tokens": 2466913024} {"current_steps": 6320, "total_steps": 15426, "loss": 0.2758, "lr": 3.9140217360007896e-05, "epoch": 1.2291160167266362, "percentage": 40.97, "elapsed_time": "11:34:53", "remaining_time": "16:41:12", "throughput": 59263.1, "total_tokens": 2470876160} {"current_steps": 6330, "total_steps": 15426, "loss": 0.2747, "lr": 3.912823064568521e-05, "epoch": 1.2310609744238064, "percentage": 41.03, "elapsed_time": "11:35:55", "remaining_time": "16:40:00", "throughput": 59270.32, "total_tokens": 2474845696} {"current_steps": 6340, "total_steps": 15426, "loss": 0.28, "lr": 3.9116254937436155e-05, "epoch": 1.2330059321209763, "percentage": 41.1, "elapsed_time": "11:37:02", "remaining_time": "16:38:56", "throughput": 59269.72, "total_tokens": 2478791680} {"current_steps": 6350, "total_steps": 15426, "loss": 0.2773, "lr": 3.910429021842825e-05, "epoch": 1.2349508898181465, "percentage": 41.16, "elapsed_time": "11:37:59", "remaining_time": "16:37:37", "throughput": 59282.95, "total_tokens": 2482729344} {"current_steps": 6360, "total_steps": 15426, "loss": 0.2757, "lr": 3.9092336471865084e-05, "epoch": 1.2368958475153164, "percentage": 41.23, "elapsed_time": "11:38:56", "remaining_time": "16:36:19", "throughput": 59294.87, "total_tokens": 2486607744} {"current_steps": 6370, "total_steps": 15426, "loss": 0.2792, "lr": 3.908039368098611e-05, "epoch": 1.2388408052124866, "percentage": 41.29, "elapsed_time": "11:39:54", "remaining_time": "16:35:01", "throughput": 59307.28, "total_tokens": 2490555008} {"current_steps": 6380, "total_steps": 15426, "loss": 0.2761, "lr": 3.9068461829066633e-05, "epoch": 1.2407857629096568, "percentage": 41.36, "elapsed_time": "11:40:51", "remaining_time": "16:33:43", "throughput": 59318.71, "total_tokens": 2494434560} {"current_steps": 6390, "total_steps": 15426, "loss": 0.2751, "lr": 3.9056540899417656e-05, "epoch": 1.2427307206068268, "percentage": 41.42, "elapsed_time": "11:41:50", "remaining_time": "16:32:28", "throughput": 59325.95, "total_tokens": 2498262400} {"current_steps": 6400, "total_steps": 15426, "loss": 0.2795, "lr": 3.904463087538585e-05, "epoch": 1.244675678303997, "percentage": 41.49, "elapsed_time": "11:42:50", "remaining_time": "16:31:14", "throughput": 59334.16, "total_tokens": 2502174592} {"current_steps": 6410, "total_steps": 15426, "loss": 0.2758, "lr": 3.903273174035336e-05, "epoch": 1.246620636001167, "percentage": 41.55, "elapsed_time": "11:44:07", "remaining_time": "16:30:22", "throughput": 59323.8, "total_tokens": 2506259712} {"current_steps": 6420, "total_steps": 15426, "loss": 0.2761, "lr": 3.902084347773779e-05, "epoch": 1.248565593698337, "percentage": 41.62, "elapsed_time": "11:45:28", "remaining_time": "16:29:38", "throughput": 59303.15, "total_tokens": 2510212352} {"current_steps": 6430, "total_steps": 15426, "loss": 0.2758, "lr": 3.900896607099207e-05, "epoch": 1.2505105513955073, "percentage": 41.68, "elapsed_time": "11:46:43", "remaining_time": "16:28:45", "throughput": 59291.19, "total_tokens": 2514171648} {"current_steps": 6440, "total_steps": 15426, "loss": 0.2779, "lr": 3.899709950360437e-05, "epoch": 1.2524555090926772, "percentage": 41.75, "elapsed_time": "11:47:38", "remaining_time": "16:27:24", "throughput": 59305.34, "total_tokens": 2518040064} {"current_steps": 6450, "total_steps": 15426, "loss": 0.2734, "lr": 3.8985243759097997e-05, "epoch": 1.2544004667898474, "percentage": 41.81, "elapsed_time": "11:48:32", "remaining_time": "16:26:01", "throughput": 59322.81, "total_tokens": 2521936896} {"current_steps": 6460, "total_steps": 15426, "loss": 0.2722, "lr": 3.897339882103129e-05, "epoch": 1.2563454244870174, "percentage": 41.88, "elapsed_time": "11:49:28", "remaining_time": "16:24:41", "throughput": 59338.65, "total_tokens": 2525937408} {"current_steps": 6470, "total_steps": 15426, "loss": 0.2784, "lr": 3.8961564672997544e-05, "epoch": 1.2582903821841875, "percentage": 41.94, "elapsed_time": "11:50:25", "remaining_time": "16:23:23", "throughput": 59350.66, "total_tokens": 2529849216} {"current_steps": 6480, "total_steps": 15426, "loss": 0.2799, "lr": 3.8949741298624924e-05, "epoch": 1.2602353398813575, "percentage": 42.01, "elapsed_time": "11:51:22", "remaining_time": "16:22:05", "throughput": 59363.11, "total_tokens": 2533771904} {"current_steps": 6490, "total_steps": 15426, "loss": 0.2767, "lr": 3.8937928681576305e-05, "epoch": 1.2621802975785277, "percentage": 42.07, "elapsed_time": "11:52:18", "remaining_time": "16:20:45", "throughput": 59377.49, "total_tokens": 2537688960} {"current_steps": 6500, "total_steps": 15426, "loss": 0.2726, "lr": 3.8926126805549276e-05, "epoch": 1.2641252552756979, "percentage": 42.14, "elapsed_time": "11:53:12", "remaining_time": "16:19:23", "throughput": 59393.03, "total_tokens": 2541548288} {"current_steps": 6510, "total_steps": 15426, "loss": 0.275, "lr": 3.891433565427596e-05, "epoch": 1.2660702129728678, "percentage": 42.2, "elapsed_time": "11:54:06", "remaining_time": "16:18:02", "throughput": 59406.87, "total_tokens": 2545394304} {"current_steps": 6520, "total_steps": 15426, "loss": 0.2771, "lr": 3.8902555211522964e-05, "epoch": 1.268015170670038, "percentage": 42.27, "elapsed_time": "11:55:04", "remaining_time": "16:16:45", "throughput": 59418.34, "total_tokens": 2549305600} {"current_steps": 6530, "total_steps": 15426, "loss": 0.2791, "lr": 3.889078546109127e-05, "epoch": 1.269960128367208, "percentage": 42.33, "elapsed_time": "11:56:02", "remaining_time": "16:15:28", "throughput": 59427.81, "total_tokens": 2553140224} {"current_steps": 6540, "total_steps": 15426, "loss": 0.2757, "lr": 3.887902638681616e-05, "epoch": 1.2719050860643781, "percentage": 42.4, "elapsed_time": "11:56:57", "remaining_time": "16:14:09", "throughput": 59442.18, "total_tokens": 2557074944} {"current_steps": 6550, "total_steps": 15426, "loss": 0.2766, "lr": 3.886727797256707e-05, "epoch": 1.273850043761548, "percentage": 42.46, "elapsed_time": "11:57:51", "remaining_time": "16:12:46", "throughput": 59459.01, "total_tokens": 2560994176} {"current_steps": 6560, "total_steps": 15426, "loss": 0.2788, "lr": 3.88555402022476e-05, "epoch": 1.2757950014587183, "percentage": 42.53, "elapsed_time": "11:58:46", "remaining_time": "16:11:27", "throughput": 59472.84, "total_tokens": 2564880512} {"current_steps": 6570, "total_steps": 15426, "loss": 0.2786, "lr": 3.884381305979528e-05, "epoch": 1.2777399591558884, "percentage": 42.59, "elapsed_time": "11:59:42", "remaining_time": "16:10:08", "throughput": 59486.33, "total_tokens": 2568792832} {"current_steps": 6580, "total_steps": 15426, "loss": 0.2776, "lr": 3.883209652918163e-05, "epoch": 1.2796849168530584, "percentage": 42.66, "elapsed_time": "12:00:38", "remaining_time": "16:08:48", "throughput": 59500.97, "total_tokens": 2572729728} {"current_steps": 6590, "total_steps": 15426, "loss": 0.2764, "lr": 3.8820390594411935e-05, "epoch": 1.2816298745502286, "percentage": 42.72, "elapsed_time": "12:01:30", "remaining_time": "16:07:24", "throughput": 59516.58, "total_tokens": 2576502656} {"current_steps": 6600, "total_steps": 15426, "loss": 0.2769, "lr": 3.880869523952524e-05, "epoch": 1.2835748322473985, "percentage": 42.78, "elapsed_time": "12:02:24", "remaining_time": "16:06:03", "throughput": 59532.98, "total_tokens": 2580430592} {"current_steps": 6610, "total_steps": 15426, "loss": 0.2746, "lr": 3.879701044859422e-05, "epoch": 1.2855197899445687, "percentage": 42.85, "elapsed_time": "12:03:19", "remaining_time": "16:04:43", "throughput": 59549.72, "total_tokens": 2584424704} {"current_steps": 6620, "total_steps": 15426, "loss": 0.2741, "lr": 3.87853362057251e-05, "epoch": 1.2874647476417387, "percentage": 42.91, "elapsed_time": "12:04:11", "remaining_time": "16:03:19", "throughput": 59566.36, "total_tokens": 2588258816} {"current_steps": 6630, "total_steps": 15426, "loss": 0.2708, "lr": 3.8773672495057576e-05, "epoch": 1.2894097053389089, "percentage": 42.98, "elapsed_time": "12:05:05", "remaining_time": "16:01:58", "throughput": 59582.42, "total_tokens": 2592173440} {"current_steps": 6640, "total_steps": 15426, "loss": 0.2762, "lr": 3.8762019300764674e-05, "epoch": 1.291354663036079, "percentage": 43.04, "elapsed_time": "12:06:03", "remaining_time": "16:00:42", "throughput": 59594.02, "total_tokens": 2596115456} {"current_steps": 6650, "total_steps": 15426, "loss": 0.2735, "lr": 3.875037660705273e-05, "epoch": 1.293299620733249, "percentage": 43.11, "elapsed_time": "12:06:58", "remaining_time": "15:59:22", "throughput": 59608.02, "total_tokens": 2599986688} {"current_steps": 6660, "total_steps": 15426, "loss": 0.2773, "lr": 3.873874439816127e-05, "epoch": 1.2952445784304192, "percentage": 43.17, "elapsed_time": "12:07:55", "remaining_time": "15:58:06", "throughput": 59621.09, "total_tokens": 2603965696} {"current_steps": 6670, "total_steps": 15426, "loss": 0.2779, "lr": 3.872712265836289e-05, "epoch": 1.2971895361275894, "percentage": 43.24, "elapsed_time": "12:08:54", "remaining_time": "15:56:52", "throughput": 59629.56, "total_tokens": 2607895168} {"current_steps": 6680, "total_steps": 15426, "loss": 0.2751, "lr": 3.8715511371963225e-05, "epoch": 1.2991344938247593, "percentage": 43.3, "elapsed_time": "12:09:53", "remaining_time": "15:55:37", "throughput": 59642.25, "total_tokens": 2611922304} {"current_steps": 6690, "total_steps": 15426, "loss": 0.2776, "lr": 3.87039105233008e-05, "epoch": 1.3010794515219293, "percentage": 43.37, "elapsed_time": "12:11:08", "remaining_time": "15:54:44", "throughput": 59630.44, "total_tokens": 2615880064} {"current_steps": 6700, "total_steps": 15426, "loss": 0.2764, "lr": 3.8692320096746975e-05, "epoch": 1.3030244092190995, "percentage": 43.43, "elapsed_time": "12:12:24", "remaining_time": "15:53:52", "throughput": 59617.51, "total_tokens": 2619857024} {"current_steps": 6710, "total_steps": 15426, "loss": 0.2763, "lr": 3.868074007670589e-05, "epoch": 1.3049693669162696, "percentage": 43.5, "elapsed_time": "12:13:35", "remaining_time": "15:52:53", "throughput": 59606.58, "total_tokens": 2623595136} {"current_steps": 6720, "total_steps": 15426, "loss": 0.2782, "lr": 3.866917044761428e-05, "epoch": 1.3069143246134396, "percentage": 43.56, "elapsed_time": "12:14:29", "remaining_time": "15:51:33", "throughput": 59620.09, "total_tokens": 2627410944} {"current_steps": 6730, "total_steps": 15426, "loss": 0.2751, "lr": 3.8657611193941486e-05, "epoch": 1.3088592823106098, "percentage": 43.63, "elapsed_time": "12:15:26", "remaining_time": "15:50:17", "throughput": 59629.84, "total_tokens": 2631270528} {"current_steps": 6740, "total_steps": 15426, "loss": 0.2757, "lr": 3.8646062300189315e-05, "epoch": 1.31080424000778, "percentage": 43.69, "elapsed_time": "12:16:25", "remaining_time": "15:49:02", "throughput": 59638.5, "total_tokens": 2635153280} {"current_steps": 6750, "total_steps": 15426, "loss": 0.2737, "lr": 3.8634523750891984e-05, "epoch": 1.31274919770495, "percentage": 43.76, "elapsed_time": "12:17:22", "remaining_time": "15:47:46", "throughput": 59650.67, "total_tokens": 2639114624} {"current_steps": 6760, "total_steps": 15426, "loss": 0.2805, "lr": 3.862299553061597e-05, "epoch": 1.3146941554021199, "percentage": 43.82, "elapsed_time": "12:18:21", "remaining_time": "15:46:32", "throughput": 59658.59, "total_tokens": 2642982272} {"current_steps": 6770, "total_steps": 15426, "loss": 0.2766, "lr": 3.861147762396e-05, "epoch": 1.31663911309929, "percentage": 43.89, "elapsed_time": "12:19:17", "remaining_time": "15:45:14", "throughput": 59672.58, "total_tokens": 2646904960} {"current_steps": 6780, "total_steps": 15426, "loss": 0.2724, "lr": 3.859997001555494e-05, "epoch": 1.3185840707964602, "percentage": 43.95, "elapsed_time": "12:20:17", "remaining_time": "15:44:02", "throughput": 59681.58, "total_tokens": 2650926848} {"current_steps": 6790, "total_steps": 15426, "loss": 0.2744, "lr": 3.8588472690063676e-05, "epoch": 1.3205290284936302, "percentage": 44.02, "elapsed_time": "12:21:14", "remaining_time": "15:42:45", "throughput": 59694.77, "total_tokens": 2654898048} {"current_steps": 6800, "total_steps": 15426, "loss": 0.2756, "lr": 3.857698563218106e-05, "epoch": 1.3224739861908004, "percentage": 44.08, "elapsed_time": "12:22:11", "remaining_time": "15:41:30", "throughput": 59706.31, "total_tokens": 2658835072} {"current_steps": 6810, "total_steps": 15426, "loss": 0.2746, "lr": 3.8565508826633836e-05, "epoch": 1.3244189438879705, "percentage": 44.15, "elapsed_time": "12:23:08", "remaining_time": "15:40:13", "throughput": 59719.94, "total_tokens": 2662827776} {"current_steps": 6820, "total_steps": 15426, "loss": 0.269, "lr": 3.855404225818049e-05, "epoch": 1.3263639015851405, "percentage": 44.21, "elapsed_time": "12:24:05", "remaining_time": "15:38:57", "throughput": 59731.31, "total_tokens": 2666729088} {"current_steps": 6830, "total_steps": 15426, "loss": 0.2773, "lr": 3.8542585911611286e-05, "epoch": 1.3283088592823107, "percentage": 44.28, "elapsed_time": "12:25:00", "remaining_time": "15:37:38", "throughput": 59745.08, "total_tokens": 2670652672} {"current_steps": 6840, "total_steps": 15426, "loss": 0.2761, "lr": 3.853113977174803e-05, "epoch": 1.3302538169794806, "percentage": 44.34, "elapsed_time": "12:25:55", "remaining_time": "15:36:20", "throughput": 59760.75, "total_tokens": 2674642048} {"current_steps": 6850, "total_steps": 15426, "loss": 0.2744, "lr": 3.851970382344411e-05, "epoch": 1.3321987746766508, "percentage": 44.41, "elapsed_time": "12:26:53", "remaining_time": "15:35:05", "throughput": 59773.47, "total_tokens": 2678673280} {"current_steps": 6860, "total_steps": 15426, "loss": 0.2755, "lr": 3.850827805158433e-05, "epoch": 1.3341437323738208, "percentage": 44.47, "elapsed_time": "12:27:47", "remaining_time": "15:33:44", "throughput": 59789.24, "total_tokens": 2682564224} {"current_steps": 6870, "total_steps": 15426, "loss": 0.2766, "lr": 3.8496862441084896e-05, "epoch": 1.336088690070991, "percentage": 44.54, "elapsed_time": "12:28:43", "remaining_time": "15:32:28", "throughput": 59801.32, "total_tokens": 2686500864} {"current_steps": 6880, "total_steps": 15426, "loss": 0.2746, "lr": 3.848545697689328e-05, "epoch": 1.3380336477681611, "percentage": 44.6, "elapsed_time": "12:29:36", "remaining_time": "15:31:07", "throughput": 59816.66, "total_tokens": 2690336256} {"current_steps": 6890, "total_steps": 15426, "loss": 0.2788, "lr": 3.8474061643988136e-05, "epoch": 1.339978605465331, "percentage": 44.66, "elapsed_time": "12:30:33", "remaining_time": "15:29:51", "throughput": 59828.45, "total_tokens": 2694288640} {"current_steps": 6900, "total_steps": 15426, "loss": 0.2767, "lr": 3.846267642737925e-05, "epoch": 1.3419235631625013, "percentage": 44.73, "elapsed_time": "12:31:28", "remaining_time": "15:28:34", "throughput": 59842.43, "total_tokens": 2698230784} {"current_steps": 6910, "total_steps": 15426, "loss": 0.2771, "lr": 3.8451301312107455e-05, "epoch": 1.3438685208596712, "percentage": 44.79, "elapsed_time": "12:32:22", "remaining_time": "15:27:14", "throughput": 59857.34, "total_tokens": 2702101504} {"current_steps": 6920, "total_steps": 15426, "loss": 0.271, "lr": 3.843993628324451e-05, "epoch": 1.3458134785568414, "percentage": 44.86, "elapsed_time": "12:33:20", "remaining_time": "15:25:59", "throughput": 59868.13, "total_tokens": 2706062848} {"current_steps": 6930, "total_steps": 15426, "loss": 0.2729, "lr": 3.8428581325893034e-05, "epoch": 1.3477584362540114, "percentage": 44.92, "elapsed_time": "12:34:15", "remaining_time": "15:24:41", "throughput": 59882.82, "total_tokens": 2710021632} {"current_steps": 6940, "total_steps": 15426, "loss": 0.2748, "lr": 3.8417236425186484e-05, "epoch": 1.3497033939511816, "percentage": 44.99, "elapsed_time": "12:35:20", "remaining_time": "15:23:35", "throughput": 59886.22, "total_tokens": 2714051456} {"current_steps": 6950, "total_steps": 15426, "loss": 0.2749, "lr": 3.840590156628895e-05, "epoch": 1.3516483516483517, "percentage": 45.05, "elapsed_time": "12:36:20", "remaining_time": "15:22:24", "throughput": 59892.97, "total_tokens": 2717963520} {"current_steps": 6960, "total_steps": 15426, "loss": 0.2733, "lr": 3.8394576734395205e-05, "epoch": 1.3535933093455217, "percentage": 45.12, "elapsed_time": "12:37:25", "remaining_time": "15:21:18", "throughput": 59892.97, "total_tokens": 2721863552} {"current_steps": 6970, "total_steps": 15426, "loss": 0.2731, "lr": 3.838326191473054e-05, "epoch": 1.3555382670426919, "percentage": 45.18, "elapsed_time": "12:38:36", "remaining_time": "15:20:20", "throughput": 59888.05, "total_tokens": 2725889920} {"current_steps": 6980, "total_steps": 15426, "loss": 0.2732, "lr": 3.837195709255069e-05, "epoch": 1.3574832247398618, "percentage": 45.25, "elapsed_time": "12:39:39", "remaining_time": "15:19:12", "throughput": 59889.28, "total_tokens": 2729730304} {"current_steps": 6990, "total_steps": 15426, "loss": 0.2787, "lr": 3.8360662253141796e-05, "epoch": 1.359428182437032, "percentage": 45.31, "elapsed_time": "12:40:51", "remaining_time": "15:18:15", "throughput": 59879.24, "total_tokens": 2733606016} {"current_steps": 7000, "total_steps": 15426, "loss": 0.2737, "lr": 3.834937738182029e-05, "epoch": 1.361373140134202, "percentage": 45.38, "elapsed_time": "12:41:49", "remaining_time": "15:17:01", "throughput": 59889.61, "total_tokens": 2737541120} {"current_steps": 7010, "total_steps": 15426, "loss": 0.274, "lr": 3.833810246393281e-05, "epoch": 1.3633180978313721, "percentage": 45.44, "elapsed_time": "12:42:44", "remaining_time": "15:15:43", "throughput": 59903.33, "total_tokens": 2741441664} {"current_steps": 7020, "total_steps": 15426, "loss": 0.2738, "lr": 3.832683748485616e-05, "epoch": 1.3652630555285423, "percentage": 45.51, "elapsed_time": "12:43:44", "remaining_time": "15:14:31", "throughput": 59915.0, "total_tokens": 2745545344} {"current_steps": 7030, "total_steps": 15426, "loss": 0.2768, "lr": 3.8315582429997184e-05, "epoch": 1.3672080132257123, "percentage": 45.57, "elapsed_time": "12:44:38", "remaining_time": "15:13:12", "throughput": 59927.52, "total_tokens": 2749374464} {"current_steps": 7040, "total_steps": 15426, "loss": 0.2739, "lr": 3.830433728479272e-05, "epoch": 1.3691529709228825, "percentage": 45.64, "elapsed_time": "12:45:38", "remaining_time": "15:12:01", "throughput": 59937.11, "total_tokens": 2753423104} {"current_steps": 7050, "total_steps": 15426, "loss": 0.2754, "lr": 3.829310203470948e-05, "epoch": 1.3710979286200526, "percentage": 45.7, "elapsed_time": "12:46:34", "remaining_time": "15:10:45", "throughput": 59950.81, "total_tokens": 2757406592} {"current_steps": 7060, "total_steps": 15426, "loss": 0.2721, "lr": 3.828187666524403e-05, "epoch": 1.3730428863172226, "percentage": 45.77, "elapsed_time": "12:47:29", "remaining_time": "15:09:28", "throughput": 59961.41, "total_tokens": 2761222400} {"current_steps": 7070, "total_steps": 15426, "loss": 0.2739, "lr": 3.827066116192266e-05, "epoch": 1.3749878440143926, "percentage": 45.83, "elapsed_time": "12:48:24", "remaining_time": "15:08:11", "throughput": 59975.67, "total_tokens": 2765166592} {"current_steps": 7080, "total_steps": 15426, "loss": 0.2768, "lr": 3.825945551030135e-05, "epoch": 1.3769328017115627, "percentage": 45.9, "elapsed_time": "12:49:19", "remaining_time": "15:06:53", "throughput": 59987.57, "total_tokens": 2768975616} {"current_steps": 7090, "total_steps": 15426, "loss": 0.2747, "lr": 3.824825969596561e-05, "epoch": 1.378877759408733, "percentage": 45.96, "elapsed_time": "12:50:14", "remaining_time": "15:05:36", "throughput": 59999.99, "total_tokens": 2772878848} {"current_steps": 7100, "total_steps": 15426, "loss": 0.2711, "lr": 3.823707370453054e-05, "epoch": 1.3808227171059029, "percentage": 46.03, "elapsed_time": "12:51:07", "remaining_time": "15:04:16", "throughput": 60015.63, "total_tokens": 2776772224} {"current_steps": 7110, "total_steps": 15426, "loss": 0.2734, "lr": 3.8225897521640614e-05, "epoch": 1.382767674803073, "percentage": 46.09, "elapsed_time": "12:51:59", "remaining_time": "15:02:55", "throughput": 60030.52, "total_tokens": 2780562304} {"current_steps": 7120, "total_steps": 15426, "loss": 0.2739, "lr": 3.8214731132969675e-05, "epoch": 1.3847126325002432, "percentage": 46.16, "elapsed_time": "12:52:54", "remaining_time": "15:01:39", "throughput": 60043.17, "total_tokens": 2784477312} {"current_steps": 7130, "total_steps": 15426, "loss": 0.2744, "lr": 3.820357452422084e-05, "epoch": 1.3866575901974132, "percentage": 46.22, "elapsed_time": "12:53:50", "remaining_time": "15:00:23", "throughput": 60054.73, "total_tokens": 2788350208} {"current_steps": 7140, "total_steps": 15426, "loss": 0.2763, "lr": 3.8192427681126445e-05, "epoch": 1.3886025478945834, "percentage": 46.29, "elapsed_time": "12:54:43", "remaining_time": "14:59:04", "throughput": 60069.25, "total_tokens": 2792247168} {"current_steps": 7150, "total_steps": 15426, "loss": 0.2752, "lr": 3.818129058944793e-05, "epoch": 1.3905475055917533, "percentage": 46.35, "elapsed_time": "12:55:40", "remaining_time": "14:57:49", "throughput": 60081.55, "total_tokens": 2796221824} {"current_steps": 7160, "total_steps": 15426, "loss": 0.2704, "lr": 3.817016323497578e-05, "epoch": 1.3924924632889235, "percentage": 46.42, "elapsed_time": "12:56:35", "remaining_time": "14:56:33", "throughput": 60093.14, "total_tokens": 2800084480} {"current_steps": 7170, "total_steps": 15426, "loss": 0.276, "lr": 3.8159045603529455e-05, "epoch": 1.3944374209860935, "percentage": 46.48, "elapsed_time": "12:57:30", "remaining_time": "14:55:16", "throughput": 60105.88, "total_tokens": 2803968512} {"current_steps": 7180, "total_steps": 15426, "loss": 0.2732, "lr": 3.8147937680957334e-05, "epoch": 1.3963823786832636, "percentage": 46.54, "elapsed_time": "12:58:25", "remaining_time": "14:53:59", "throughput": 60117.76, "total_tokens": 2807838080} {"current_steps": 7190, "total_steps": 15426, "loss": 0.2746, "lr": 3.813683945313658e-05, "epoch": 1.3983273363804338, "percentage": 46.61, "elapsed_time": "12:59:20", "remaining_time": "14:52:43", "throughput": 60129.7, "total_tokens": 2811709056} {"current_steps": 7200, "total_steps": 15426, "loss": 0.2756, "lr": 3.812575090597313e-05, "epoch": 1.4002722940776038, "percentage": 46.67, "elapsed_time": "13:00:15", "remaining_time": "14:51:26", "throughput": 60142.81, "total_tokens": 2815610240} {"current_steps": 7210, "total_steps": 15426, "loss": 0.2749, "lr": 3.811467202540156e-05, "epoch": 1.402217251774774, "percentage": 46.74, "elapsed_time": "13:01:15", "remaining_time": "14:50:15", "throughput": 60150.11, "total_tokens": 2819544448} {"current_steps": 7220, "total_steps": 15426, "loss": 0.2769, "lr": 3.810360279738507e-05, "epoch": 1.404162209471944, "percentage": 46.8, "elapsed_time": "13:02:14", "remaining_time": "14:49:03", "throughput": 60156.83, "total_tokens": 2823416832} {"current_steps": 7230, "total_steps": 15426, "loss": 0.2779, "lr": 3.809254320791535e-05, "epoch": 1.406107167169114, "percentage": 46.87, "elapsed_time": "13:03:20", "remaining_time": "14:48:00", "throughput": 60154.17, "total_tokens": 2827300224} {"current_steps": 7240, "total_steps": 15426, "loss": 0.2722, "lr": 3.808149324301256e-05, "epoch": 1.408052124866284, "percentage": 46.93, "elapsed_time": "13:04:30", "remaining_time": "14:47:01", "throughput": 60148.07, "total_tokens": 2831226496} {"current_steps": 7250, "total_steps": 15426, "loss": 0.2745, "lr": 3.807045288872522e-05, "epoch": 1.4099970825634542, "percentage": 47.0, "elapsed_time": "13:05:44", "remaining_time": "14:46:05", "throughput": 60135.12, "total_tokens": 2835026688} {"current_steps": 7260, "total_steps": 15426, "loss": 0.2704, "lr": 3.805942213113015e-05, "epoch": 1.4119420402606244, "percentage": 47.06, "elapsed_time": "13:06:44", "remaining_time": "14:44:55", "throughput": 60143.64, "total_tokens": 2839050368} {"current_steps": 7270, "total_steps": 15426, "loss": 0.2761, "lr": 3.8048400956332385e-05, "epoch": 1.4138869979577944, "percentage": 47.13, "elapsed_time": "13:07:40", "remaining_time": "14:43:39", "throughput": 60155.51, "total_tokens": 2842951552} {"current_steps": 7280, "total_steps": 15426, "loss": 0.2686, "lr": 3.803738935046512e-05, "epoch": 1.4158319556549646, "percentage": 47.19, "elapsed_time": "13:08:37", "remaining_time": "14:42:26", "throughput": 60166.77, "total_tokens": 2846947072} {"current_steps": 7290, "total_steps": 15426, "loss": 0.2762, "lr": 3.802638729968962e-05, "epoch": 1.4177769133521345, "percentage": 47.26, "elapsed_time": "13:09:30", "remaining_time": "14:41:07", "throughput": 60180.22, "total_tokens": 2850755328} {"current_steps": 7300, "total_steps": 15426, "loss": 0.2791, "lr": 3.8015394790195145e-05, "epoch": 1.4197218710493047, "percentage": 47.32, "elapsed_time": "13:10:23", "remaining_time": "14:39:49", "throughput": 60194.08, "total_tokens": 2854617088} {"current_steps": 7310, "total_steps": 15426, "loss": 0.2732, "lr": 3.800441180819891e-05, "epoch": 1.4216668287464747, "percentage": 47.39, "elapsed_time": "13:11:19", "remaining_time": "14:38:34", "throughput": 60207.44, "total_tokens": 2858611328} {"current_steps": 7320, "total_steps": 15426, "loss": 0.2773, "lr": 3.7993438339945965e-05, "epoch": 1.4236117864436448, "percentage": 47.45, "elapsed_time": "13:12:11", "remaining_time": "14:37:14", "throughput": 60222.34, "total_tokens": 2862432768} {"current_steps": 7330, "total_steps": 15426, "loss": 0.2741, "lr": 3.798247437170914e-05, "epoch": 1.425556744140815, "percentage": 47.52, "elapsed_time": "13:13:04", "remaining_time": "14:35:56", "throughput": 60236.05, "total_tokens": 2866279552} {"current_steps": 7340, "total_steps": 15426, "loss": 0.2748, "lr": 3.797151988978901e-05, "epoch": 1.427501701837985, "percentage": 47.58, "elapsed_time": "13:13:57", "remaining_time": "14:34:39", "throughput": 60249.16, "total_tokens": 2870128768} {"current_steps": 7350, "total_steps": 15426, "loss": 0.2727, "lr": 3.796057488051377e-05, "epoch": 1.4294466595351552, "percentage": 47.65, "elapsed_time": "13:14:52", "remaining_time": "14:33:23", "throughput": 60262.09, "total_tokens": 2874034304} {"current_steps": 7360, "total_steps": 15426, "loss": 0.2747, "lr": 3.794963933023918e-05, "epoch": 1.4313916172323253, "percentage": 47.71, "elapsed_time": "13:15:44", "remaining_time": "14:32:04", "throughput": 60273.93, "total_tokens": 2877778432} {"current_steps": 7370, "total_steps": 15426, "loss": 0.2746, "lr": 3.79387132253485e-05, "epoch": 1.4333365749294953, "percentage": 47.78, "elapsed_time": "13:16:40", "remaining_time": "14:30:49", "throughput": 60285.43, "total_tokens": 2881683968} {"current_steps": 7380, "total_steps": 15426, "loss": 0.2746, "lr": 3.792779655225243e-05, "epoch": 1.4352815326266652, "percentage": 47.84, "elapsed_time": "13:17:38", "remaining_time": "14:29:37", "throughput": 60295.23, "total_tokens": 2885637632} {"current_steps": 7390, "total_steps": 15426, "loss": 0.2721, "lr": 3.791688929738902e-05, "epoch": 1.4372264903238354, "percentage": 47.91, "elapsed_time": "13:18:30", "remaining_time": "14:28:18", "throughput": 60310.26, "total_tokens": 2889499520} {"current_steps": 7400, "total_steps": 15426, "loss": 0.2734, "lr": 3.79059914472236e-05, "epoch": 1.4391714480210056, "percentage": 47.97, "elapsed_time": "13:19:25", "remaining_time": "14:27:02", "throughput": 60322.18, "total_tokens": 2893362432} {"current_steps": 7410, "total_steps": 15426, "loss": 0.2715, "lr": 3.7895102988248716e-05, "epoch": 1.4411164057181756, "percentage": 48.04, "elapsed_time": "13:20:18", "remaining_time": "14:25:45", "throughput": 60337.58, "total_tokens": 2897324160} {"current_steps": 7420, "total_steps": 15426, "loss": 0.273, "lr": 3.7884223906984064e-05, "epoch": 1.4430613634153457, "percentage": 48.1, "elapsed_time": "13:21:12", "remaining_time": "14:24:29", "throughput": 60350.24, "total_tokens": 2901200640} {"current_steps": 7430, "total_steps": 15426, "loss": 0.2784, "lr": 3.787335418997641e-05, "epoch": 1.445006321112516, "percentage": 48.17, "elapsed_time": "13:22:05", "remaining_time": "14:23:11", "throughput": 60363.55, "total_tokens": 2905029888} {"current_steps": 7440, "total_steps": 15426, "loss": 0.2762, "lr": 3.786249382379952e-05, "epoch": 1.4469512788096859, "percentage": 48.23, "elapsed_time": "13:22:58", "remaining_time": "14:21:54", "throughput": 60377.39, "total_tokens": 2908883328} {"current_steps": 7450, "total_steps": 15426, "loss": 0.2759, "lr": 3.785164279505411e-05, "epoch": 1.4488962365068558, "percentage": 48.3, "elapsed_time": "13:23:50", "remaining_time": "14:20:35", "throughput": 60393.76, "total_tokens": 2912821632} {"current_steps": 7460, "total_steps": 15426, "loss": 0.2745, "lr": 3.7840801090367744e-05, "epoch": 1.450841194204026, "percentage": 48.36, "elapsed_time": "13:24:47", "remaining_time": "14:19:22", "throughput": 60402.33, "total_tokens": 2916682240} {"current_steps": 7470, "total_steps": 15426, "loss": 0.2761, "lr": 3.782996869639479e-05, "epoch": 1.4527861519011962, "percentage": 48.42, "elapsed_time": "13:25:45", "remaining_time": "14:18:11", "throughput": 60412.53, "total_tokens": 2920692992} {"current_steps": 7480, "total_steps": 15426, "loss": 0.272, "lr": 3.7819145599816354e-05, "epoch": 1.4547311095983662, "percentage": 48.49, "elapsed_time": "13:26:44", "remaining_time": "14:16:59", "throughput": 60421.65, "total_tokens": 2924650368} {"current_steps": 7490, "total_steps": 15426, "loss": 0.2755, "lr": 3.780833178734018e-05, "epoch": 1.4566760672955363, "percentage": 48.55, "elapsed_time": "13:27:40", "remaining_time": "14:15:45", "throughput": 60431.05, "total_tokens": 2928499840} {"current_steps": 7500, "total_steps": 15426, "loss": 0.278, "lr": 3.77975272457006e-05, "epoch": 1.4586210249927065, "percentage": 48.62, "elapsed_time": "13:28:36", "remaining_time": "14:14:32", "throughput": 60440.25, "total_tokens": 2932370560} {"current_steps": 7510, "total_steps": 15426, "loss": 0.2743, "lr": 3.778673196165851e-05, "epoch": 1.4605659826898765, "percentage": 48.68, "elapsed_time": "13:29:38", "remaining_time": "14:13:25", "throughput": 60444.18, "total_tokens": 2936306304} {"current_steps": 7520, "total_steps": 15426, "loss": 0.2758, "lr": 3.7775945922001186e-05, "epoch": 1.4625109403870467, "percentage": 48.75, "elapsed_time": "13:30:42", "remaining_time": "14:12:19", "throughput": 60447.38, "total_tokens": 2940308864} {"current_steps": 7530, "total_steps": 15426, "loss": 0.2725, "lr": 3.776516911354236e-05, "epoch": 1.4644558980842166, "percentage": 48.81, "elapsed_time": "13:31:52", "remaining_time": "14:11:19", "throughput": 60442.7, "total_tokens": 2944303232} {"current_steps": 7540, "total_steps": 15426, "loss": 0.2756, "lr": 3.775440152312205e-05, "epoch": 1.4664008557813868, "percentage": 48.88, "elapsed_time": "13:32:55", "remaining_time": "14:10:13", "throughput": 60442.5, "total_tokens": 2948096256} {"current_steps": 7550, "total_steps": 15426, "loss": 0.2749, "lr": 3.774364313760652e-05, "epoch": 1.4683458134785567, "percentage": 48.94, "elapsed_time": "13:33:56", "remaining_time": "14:09:05", "throughput": 60446.19, "total_tokens": 2951974784} {"current_steps": 7560, "total_steps": 15426, "loss": 0.2725, "lr": 3.7732893943888224e-05, "epoch": 1.470290771175727, "percentage": 49.01, "elapsed_time": "13:34:54", "remaining_time": "14:07:53", "throughput": 60454.31, "total_tokens": 2955899520} {"current_steps": 7570, "total_steps": 15426, "loss": 0.2739, "lr": 3.772215392888574e-05, "epoch": 1.472235728872897, "percentage": 49.07, "elapsed_time": "13:35:50", "remaining_time": "14:06:39", "throughput": 60467.04, "total_tokens": 2959874816} {"current_steps": 7580, "total_steps": 15426, "loss": 0.2763, "lr": 3.771142307954368e-05, "epoch": 1.474180686570067, "percentage": 49.14, "elapsed_time": "13:36:43", "remaining_time": "14:05:23", "throughput": 60480.86, "total_tokens": 2963778304} {"current_steps": 7590, "total_steps": 15426, "loss": 0.271, "lr": 3.770070138283264e-05, "epoch": 1.4761256442672372, "percentage": 49.2, "elapsed_time": "13:37:41", "remaining_time": "14:04:11", "throughput": 60489.43, "total_tokens": 2967707776} {"current_steps": 7600, "total_steps": 15426, "loss": 0.2722, "lr": 3.768998882574915e-05, "epoch": 1.4780706019644072, "percentage": 49.27, "elapsed_time": "13:38:36", "remaining_time": "14:02:57", "throughput": 60500.78, "total_tokens": 2971599232} {"current_steps": 7610, "total_steps": 15426, "loss": 0.2746, "lr": 3.767928539531557e-05, "epoch": 1.4800155596615774, "percentage": 49.33, "elapsed_time": "13:39:33", "remaining_time": "14:01:44", "throughput": 60512.13, "total_tokens": 2975602176} {"current_steps": 7620, "total_steps": 15426, "loss": 0.2733, "lr": 3.7668591078580055e-05, "epoch": 1.4819605173587473, "percentage": 49.4, "elapsed_time": "13:40:30", "remaining_time": "14:00:31", "throughput": 60522.98, "total_tokens": 2979563776} {"current_steps": 7630, "total_steps": 15426, "loss": 0.2759, "lr": 3.765790586261647e-05, "epoch": 1.4839054750559175, "percentage": 49.46, "elapsed_time": "13:41:21", "remaining_time": "13:59:13", "throughput": 60538.48, "total_tokens": 2983406848} {"current_steps": 7640, "total_steps": 15426, "loss": 0.2747, "lr": 3.7647229734524326e-05, "epoch": 1.4858504327530877, "percentage": 49.53, "elapsed_time": "13:42:14", "remaining_time": "13:57:57", "throughput": 60551.6, "total_tokens": 2987301504} {"current_steps": 7650, "total_steps": 15426, "loss": 0.2703, "lr": 3.7636562681428744e-05, "epoch": 1.4877953904502577, "percentage": 49.59, "elapsed_time": "13:43:11", "remaining_time": "13:56:44", "throughput": 60563.47, "total_tokens": 2991319040} {"current_steps": 7660, "total_steps": 15426, "loss": 0.2737, "lr": 3.7625904690480346e-05, "epoch": 1.4897403481474278, "percentage": 49.66, "elapsed_time": "13:44:05", "remaining_time": "13:55:29", "throughput": 60575.28, "total_tokens": 2995174784} {"current_steps": 7670, "total_steps": 15426, "loss": 0.2711, "lr": 3.7615255748855224e-05, "epoch": 1.4916853058445978, "percentage": 49.72, "elapsed_time": "13:44:56", "remaining_time": "13:54:11", "throughput": 60589.38, "total_tokens": 2998981632} {"current_steps": 7680, "total_steps": 15426, "loss": 0.2748, "lr": 3.7604615843754845e-05, "epoch": 1.493630263541768, "percentage": 49.79, "elapsed_time": "13:45:50", "remaining_time": "13:52:55", "throughput": 60602.05, "total_tokens": 3002838016} {"current_steps": 7690, "total_steps": 15426, "loss": 0.2767, "lr": 3.759398496240601e-05, "epoch": 1.495575221238938, "percentage": 49.85, "elapsed_time": "13:46:44", "remaining_time": "13:51:40", "throughput": 60613.78, "total_tokens": 3006694400} {"current_steps": 7700, "total_steps": 15426, "loss": 0.2711, "lr": 3.7583363092060815e-05, "epoch": 1.4975201789361081, "percentage": 49.92, "elapsed_time": "13:47:40", "remaining_time": "13:50:28", "throughput": 60625.0, "total_tokens": 3010671872} {"current_steps": 7710, "total_steps": 15426, "loss": 0.2732, "lr": 3.757275021999649e-05, "epoch": 1.4994651366332783, "percentage": 49.98, "elapsed_time": "13:48:36", "remaining_time": "13:49:15", "throughput": 60637.25, "total_tokens": 3014662400} {"current_steps": 7720, "total_steps": 15426, "loss": 0.2754, "lr": 3.7562146333515445e-05, "epoch": 1.5014100943304483, "percentage": 50.05, "elapsed_time": "13:49:32", "remaining_time": "13:48:02", "throughput": 60648.92, "total_tokens": 3018667392} {"current_steps": 7730, "total_steps": 15426, "loss": 0.2728, "lr": 3.7551551419945167e-05, "epoch": 1.5033550520276184, "percentage": 50.11, "elapsed_time": "13:50:29", "remaining_time": "13:46:49", "throughput": 60661.38, "total_tokens": 3022697216} {"current_steps": 7740, "total_steps": 15426, "loss": 0.2694, "lr": 3.7540965466638104e-05, "epoch": 1.5053000097247886, "percentage": 50.18, "elapsed_time": "13:51:24", "remaining_time": "13:45:36", "throughput": 60672.71, "total_tokens": 3026636544} {"current_steps": 7750, "total_steps": 15426, "loss": 0.2768, "lr": 3.753038846097172e-05, "epoch": 1.5072449674219586, "percentage": 50.24, "elapsed_time": "13:52:16", "remaining_time": "13:44:19", "throughput": 60687.0, "total_tokens": 3030468480} {"current_steps": 7760, "total_steps": 15426, "loss": 0.2728, "lr": 3.751982039034827e-05, "epoch": 1.5091899251191285, "percentage": 50.3, "elapsed_time": "13:53:10", "remaining_time": "13:43:05", "throughput": 60698.11, "total_tokens": 3034334848} {"current_steps": 7770, "total_steps": 15426, "loss": 0.2743, "lr": 3.75092612421949e-05, "epoch": 1.5111348828162987, "percentage": 50.37, "elapsed_time": "13:54:03", "remaining_time": "13:41:49", "throughput": 60711.16, "total_tokens": 3038227584} {"current_steps": 7780, "total_steps": 15426, "loss": 0.2762, "lr": 3.7498711003963475e-05, "epoch": 1.5130798405134689, "percentage": 50.43, "elapsed_time": "13:54:59", "remaining_time": "13:40:36", "throughput": 60721.72, "total_tokens": 3042104192} {"current_steps": 7790, "total_steps": 15426, "loss": 0.2749, "lr": 3.748816966313058e-05, "epoch": 1.5150247982106388, "percentage": 50.5, "elapsed_time": "13:55:53", "remaining_time": "13:39:22", "throughput": 60732.37, "total_tokens": 3045960704} {"current_steps": 7800, "total_steps": 15426, "loss": 0.2757, "lr": 3.7477637207197374e-05, "epoch": 1.516969755907809, "percentage": 50.56, "elapsed_time": "13:56:56", "remaining_time": "13:38:16", "throughput": 60733.16, "total_tokens": 3049795840} {"current_steps": 7810, "total_steps": 15426, "loss": 0.2754, "lr": 3.7467113623689666e-05, "epoch": 1.5189147136049792, "percentage": 50.63, "elapsed_time": "13:58:00", "remaining_time": "13:37:11", "throughput": 60731.47, "total_tokens": 3053601920} {"current_steps": 7820, "total_steps": 15426, "loss": 0.2748, "lr": 3.745659890015768e-05, "epoch": 1.5208596713021492, "percentage": 50.69, "elapsed_time": "13:59:05", "remaining_time": "13:36:07", "throughput": 60732.09, "total_tokens": 3057573120} {"current_steps": 7830, "total_steps": 15426, "loss": 0.2775, "lr": 3.744609302417615e-05, "epoch": 1.5228046289993191, "percentage": 50.76, "elapsed_time": "14:00:01", "remaining_time": "13:34:55", "throughput": 60740.43, "total_tokens": 3061407616} {"current_steps": 7840, "total_steps": 15426, "loss": 0.2723, "lr": 3.7435595983344175e-05, "epoch": 1.5247495866964893, "percentage": 50.82, "elapsed_time": "14:00:56", "remaining_time": "13:33:41", "throughput": 60751.47, "total_tokens": 3065299712} {"current_steps": 7850, "total_steps": 15426, "loss": 0.2728, "lr": 3.7425107765285155e-05, "epoch": 1.5266945443936595, "percentage": 50.89, "elapsed_time": "14:01:47", "remaining_time": "13:32:24", "throughput": 60765.92, "total_tokens": 3069151232} {"current_steps": 7860, "total_steps": 15426, "loss": 0.2734, "lr": 3.741462835764676e-05, "epoch": 1.5286395020908294, "percentage": 50.95, "elapsed_time": "14:02:43", "remaining_time": "13:31:11", "throughput": 60777.94, "total_tokens": 3073131904} {"current_steps": 7870, "total_steps": 15426, "loss": 0.2741, "lr": 3.740415774810088e-05, "epoch": 1.5305844597879996, "percentage": 51.02, "elapsed_time": "14:03:37", "remaining_time": "13:29:57", "throughput": 60790.5, "total_tokens": 3077065344} {"current_steps": 7880, "total_steps": 15426, "loss": 0.2756, "lr": 3.739369592434351e-05, "epoch": 1.5325294174851698, "percentage": 51.08, "elapsed_time": "14:04:32", "remaining_time": "13:28:44", "throughput": 60802.03, "total_tokens": 3080987520} {"current_steps": 7890, "total_steps": 15426, "loss": 0.2744, "lr": 3.738324287409473e-05, "epoch": 1.5344743751823398, "percentage": 51.15, "elapsed_time": "14:05:27", "remaining_time": "13:27:31", "throughput": 60813.46, "total_tokens": 3084889344} {"current_steps": 7900, "total_steps": 15426, "loss": 0.2751, "lr": 3.7372798585098644e-05, "epoch": 1.5364193328795097, "percentage": 51.21, "elapsed_time": "14:06:20", "remaining_time": "13:26:16", "throughput": 60826.84, "total_tokens": 3088792704} {"current_steps": 7910, "total_steps": 15426, "loss": 0.2702, "lr": 3.736236304512331e-05, "epoch": 1.5383642905766801, "percentage": 51.28, "elapsed_time": "14:07:14", "remaining_time": "13:25:02", "throughput": 60838.47, "total_tokens": 3092696448} {"current_steps": 7920, "total_steps": 15426, "loss": 0.2729, "lr": 3.735193624196067e-05, "epoch": 1.54030924827385, "percentage": 51.34, "elapsed_time": "14:08:10", "remaining_time": "13:23:50", "throughput": 60849.43, "total_tokens": 3096682624} {"current_steps": 7930, "total_steps": 15426, "loss": 0.2742, "lr": 3.7341518163426514e-05, "epoch": 1.54225420597102, "percentage": 51.41, "elapsed_time": "14:09:07", "remaining_time": "13:22:39", "throughput": 60857.25, "total_tokens": 3100554112} {"current_steps": 7940, "total_steps": 15426, "loss": 0.2749, "lr": 3.73311087973604e-05, "epoch": 1.5441991636681902, "percentage": 51.47, "elapsed_time": "14:10:08", "remaining_time": "13:21:31", "throughput": 60861.4, "total_tokens": 3104430720} {"current_steps": 7950, "total_steps": 15426, "loss": 0.2723, "lr": 3.732070813162561e-05, "epoch": 1.5461441213653604, "percentage": 51.54, "elapsed_time": "14:11:04", "remaining_time": "13:20:20", "throughput": 60871.49, "total_tokens": 3108393856} {"current_steps": 7960, "total_steps": 15426, "loss": 0.2731, "lr": 3.731031615410908e-05, "epoch": 1.5480890790625303, "percentage": 51.6, "elapsed_time": "14:12:02", "remaining_time": "13:19:09", "throughput": 60880.31, "total_tokens": 3112328960} {"current_steps": 7970, "total_steps": 15426, "loss": 0.2741, "lr": 3.729993285272132e-05, "epoch": 1.5500340367597005, "percentage": 51.67, "elapsed_time": "14:12:56", "remaining_time": "13:17:55", "throughput": 60893.72, "total_tokens": 3116302208} {"current_steps": 7980, "total_steps": 15426, "loss": 0.2723, "lr": 3.7289558215396414e-05, "epoch": 1.5519789944568707, "percentage": 51.73, "elapsed_time": "14:13:51", "remaining_time": "13:16:43", "throughput": 60904.67, "total_tokens": 3120235264} {"current_steps": 7990, "total_steps": 15426, "loss": 0.2723, "lr": 3.727919223009191e-05, "epoch": 1.5539239521540407, "percentage": 51.8, "elapsed_time": "14:14:46", "remaining_time": "13:15:30", "throughput": 60915.53, "total_tokens": 3124159360} {"current_steps": 8000, "total_steps": 15426, "loss": 0.2741, "lr": 3.726883488478877e-05, "epoch": 1.5558689098512106, "percentage": 51.86, "elapsed_time": "14:15:41", "remaining_time": "13:14:17", "throughput": 60926.98, "total_tokens": 3128083456} {"current_steps": 8010, "total_steps": 15426, "loss": 0.2711, "lr": 3.7258486167491323e-05, "epoch": 1.5578138675483808, "percentage": 51.93, "elapsed_time": "14:16:36", "remaining_time": "13:13:05", "throughput": 60938.1, "total_tokens": 3132029312} {"current_steps": 8020, "total_steps": 15426, "loss": 0.2743, "lr": 3.724814606622721e-05, "epoch": 1.559758825245551, "percentage": 51.99, "elapsed_time": "14:17:31", "remaining_time": "13:11:52", "throughput": 60950.37, "total_tokens": 3136016256} {"current_steps": 8030, "total_steps": 15426, "loss": 0.2737, "lr": 3.7237814569047294e-05, "epoch": 1.561703782942721, "percentage": 52.05, "elapsed_time": "14:18:27", "remaining_time": "13:10:40", "throughput": 60962.37, "total_tokens": 3139989760} {"current_steps": 8040, "total_steps": 15426, "loss": 0.2716, "lr": 3.7227491664025656e-05, "epoch": 1.5636487406398911, "percentage": 52.12, "elapsed_time": "14:19:19", "remaining_time": "13:09:25", "throughput": 60977.36, "total_tokens": 3143953920} {"current_steps": 8050, "total_steps": 15426, "loss": 0.272, "lr": 3.721717733925948e-05, "epoch": 1.5655936983370613, "percentage": 52.18, "elapsed_time": "14:20:13", "remaining_time": "13:08:12", "throughput": 60989.34, "total_tokens": 3147871488} {"current_steps": 8060, "total_steps": 15426, "loss": 0.2741, "lr": 3.720687158286904e-05, "epoch": 1.5675386560342313, "percentage": 52.25, "elapsed_time": "14:21:10", "remaining_time": "13:07:01", "throughput": 60997.59, "total_tokens": 3151753216} {"current_steps": 8070, "total_steps": 15426, "loss": 0.2722, "lr": 3.719657438299762e-05, "epoch": 1.5694836137314012, "percentage": 52.31, "elapsed_time": "14:22:07", "remaining_time": "13:05:51", "throughput": 61006.85, "total_tokens": 3155741056} {"current_steps": 8080, "total_steps": 15426, "loss": 0.2747, "lr": 3.7186285727811446e-05, "epoch": 1.5714285714285714, "percentage": 52.38, "elapsed_time": "14:23:10", "remaining_time": "13:04:45", "throughput": 61009.05, "total_tokens": 3159666176} {"current_steps": 8090, "total_steps": 15426, "loss": 0.27, "lr": 3.717600560549967e-05, "epoch": 1.5733735291257416, "percentage": 52.44, "elapsed_time": "14:24:13", "remaining_time": "13:03:40", "throughput": 61012.05, "total_tokens": 3163671936} {"current_steps": 8100, "total_steps": 15426, "loss": 0.2742, "lr": 3.716573400427426e-05, "epoch": 1.5753184868229115, "percentage": 52.51, "elapsed_time": "14:25:17", "remaining_time": "13:02:36", "throughput": 61013.94, "total_tokens": 3167665024} {"current_steps": 8110, "total_steps": 15426, "loss": 0.2713, "lr": 3.7155470912370004e-05, "epoch": 1.5772634445200817, "percentage": 52.57, "elapsed_time": "14:26:17", "remaining_time": "13:01:28", "throughput": 61020.74, "total_tokens": 3171689984} {"current_steps": 8120, "total_steps": 15426, "loss": 0.2735, "lr": 3.714521631804439e-05, "epoch": 1.579208402217252, "percentage": 52.64, "elapsed_time": "14:27:14", "remaining_time": "13:00:18", "throughput": 61026.84, "total_tokens": 3175507584} {"current_steps": 8130, "total_steps": 15426, "loss": 0.275, "lr": 3.713497020957759e-05, "epoch": 1.5811533599144219, "percentage": 52.7, "elapsed_time": "14:28:09", "remaining_time": "12:59:05", "throughput": 61038.26, "total_tokens": 3179421824} {"current_steps": 8140, "total_steps": 15426, "loss": 0.2739, "lr": 3.712473257527238e-05, "epoch": 1.5830983176115918, "percentage": 52.77, "elapsed_time": "14:29:03", "remaining_time": "12:57:53", "throughput": 61049.7, "total_tokens": 3183353728} {"current_steps": 8150, "total_steps": 15426, "loss": 0.2705, "lr": 3.711450340345412e-05, "epoch": 1.585043275308762, "percentage": 52.83, "elapsed_time": "14:29:56", "remaining_time": "12:56:39", "throughput": 61062.64, "total_tokens": 3187282048} {"current_steps": 8160, "total_steps": 15426, "loss": 0.2729, "lr": 3.710428268247067e-05, "epoch": 1.5869882330059322, "percentage": 52.9, "elapsed_time": "14:30:51", "remaining_time": "12:55:27", "throughput": 61073.02, "total_tokens": 3191184896} {"current_steps": 8170, "total_steps": 15426, "loss": 0.273, "lr": 3.709407040069233e-05, "epoch": 1.5889331907031021, "percentage": 52.96, "elapsed_time": "14:31:49", "remaining_time": "12:54:17", "throughput": 61081.45, "total_tokens": 3195111296} {"current_steps": 8180, "total_steps": 15426, "loss": 0.2715, "lr": 3.708386654651179e-05, "epoch": 1.5908781484002723, "percentage": 53.03, "elapsed_time": "14:32:43", "remaining_time": "12:53:04", "throughput": 61093.13, "total_tokens": 3199037696} {"current_steps": 8190, "total_steps": 15426, "loss": 0.271, "lr": 3.707367110834409e-05, "epoch": 1.5928231060974425, "percentage": 53.09, "elapsed_time": "14:33:40", "remaining_time": "12:51:53", "throughput": 61103.31, "total_tokens": 3203036800} {"current_steps": 8200, "total_steps": 15426, "loss": 0.2742, "lr": 3.7063484074626555e-05, "epoch": 1.5947680637946124, "percentage": 53.16, "elapsed_time": "14:34:31", "remaining_time": "12:50:38", "throughput": 61116.88, "total_tokens": 3206883200} {"current_steps": 8210, "total_steps": 15426, "loss": 0.2724, "lr": 3.7053305433818725e-05, "epoch": 1.5967130214917824, "percentage": 53.22, "elapsed_time": "14:35:25", "remaining_time": "12:49:26", "throughput": 61127.63, "total_tokens": 3210750848} {"current_steps": 8220, "total_steps": 15426, "loss": 0.2728, "lr": 3.704313517440232e-05, "epoch": 1.5986579791889528, "percentage": 53.29, "elapsed_time": "14:36:21", "remaining_time": "12:48:15", "throughput": 61137.71, "total_tokens": 3214707328} {"current_steps": 8230, "total_steps": 15426, "loss": 0.2691, "lr": 3.703297328488118e-05, "epoch": 1.6006029368861228, "percentage": 53.35, "elapsed_time": "14:37:14", "remaining_time": "12:47:01", "throughput": 61150.23, "total_tokens": 3218637952} {"current_steps": 8240, "total_steps": 15426, "loss": 0.2724, "lr": 3.70228197537812e-05, "epoch": 1.6025478945832927, "percentage": 53.42, "elapsed_time": "14:38:07", "remaining_time": "12:45:48", "throughput": 61162.85, "total_tokens": 3222546176} {"current_steps": 8250, "total_steps": 15426, "loss": 0.2737, "lr": 3.7012674569650305e-05, "epoch": 1.604492852280463, "percentage": 53.48, "elapsed_time": "14:39:03", "remaining_time": "12:44:37", "throughput": 61173.67, "total_tokens": 3226496896} {"current_steps": 8260, "total_steps": 15426, "loss": 0.2733, "lr": 3.700253772105835e-05, "epoch": 1.606437809977633, "percentage": 53.55, "elapsed_time": "14:39:57", "remaining_time": "12:43:25", "throughput": 61183.29, "total_tokens": 3230345728} {"current_steps": 8270, "total_steps": 15426, "loss": 0.2718, "lr": 3.699240919659711e-05, "epoch": 1.608382767674803, "percentage": 53.61, "elapsed_time": "14:40:51", "remaining_time": "12:42:12", "throughput": 61194.65, "total_tokens": 3234227200} {"current_steps": 8280, "total_steps": 15426, "loss": 0.2762, "lr": 3.698228898488019e-05, "epoch": 1.610327725371973, "percentage": 53.68, "elapsed_time": "14:41:46", "remaining_time": "12:41:00", "throughput": 61206.03, "total_tokens": 3238224384} {"current_steps": 8290, "total_steps": 15426, "loss": 0.2695, "lr": 3.6972177074543e-05, "epoch": 1.6122726830691434, "percentage": 53.74, "elapsed_time": "14:42:43", "remaining_time": "12:39:51", "throughput": 61216.96, "total_tokens": 3242281088} {"current_steps": 8300, "total_steps": 15426, "loss": 0.2735, "lr": 3.69620734542427e-05, "epoch": 1.6142176407663134, "percentage": 53.81, "elapsed_time": "14:43:37", "remaining_time": "12:38:38", "throughput": 61227.45, "total_tokens": 3246115584} {"current_steps": 8310, "total_steps": 15426, "loss": 0.2709, "lr": 3.695197811265811e-05, "epoch": 1.6161625984634833, "percentage": 53.87, "elapsed_time": "14:44:30", "remaining_time": "12:37:25", "throughput": 61239.72, "total_tokens": 3250045696} {"current_steps": 8320, "total_steps": 15426, "loss": 0.2711, "lr": 3.6941891038489694e-05, "epoch": 1.6181075561606535, "percentage": 53.93, "elapsed_time": "14:45:24", "remaining_time": "12:36:13", "throughput": 61251.42, "total_tokens": 3253963392} {"current_steps": 8330, "total_steps": 15426, "loss": 0.2745, "lr": 3.693181222045952e-05, "epoch": 1.6200525138578237, "percentage": 54.0, "elapsed_time": "14:46:19", "remaining_time": "12:35:01", "throughput": 61260.9, "total_tokens": 3257813632} {"current_steps": 8340, "total_steps": 15426, "loss": 0.2742, "lr": 3.692174164731113e-05, "epoch": 1.6219974715549936, "percentage": 54.06, "elapsed_time": "14:47:16", "remaining_time": "12:33:51", "throughput": 61267.9, "total_tokens": 3261696640} {"current_steps": 8350, "total_steps": 15426, "loss": 0.2707, "lr": 3.6911679307809595e-05, "epoch": 1.6239424292521638, "percentage": 54.13, "elapsed_time": "14:48:13", "remaining_time": "12:32:42", "throughput": 61277.65, "total_tokens": 3265709184} {"current_steps": 8360, "total_steps": 15426, "loss": 0.2747, "lr": 3.690162519074137e-05, "epoch": 1.625887386949334, "percentage": 54.19, "elapsed_time": "14:49:07", "remaining_time": "12:31:30", "throughput": 61287.25, "total_tokens": 3269532032} {"current_steps": 8370, "total_steps": 15426, "loss": 0.2752, "lr": 3.689157928491431e-05, "epoch": 1.627832344646504, "percentage": 54.26, "elapsed_time": "14:50:01", "remaining_time": "12:30:17", "throughput": 61297.92, "total_tokens": 3273378432} {"current_steps": 8380, "total_steps": 15426, "loss": 0.2739, "lr": 3.6881541579157566e-05, "epoch": 1.629777302343674, "percentage": 54.32, "elapsed_time": "14:50:55", "remaining_time": "12:29:06", "throughput": 61307.26, "total_tokens": 3277231488} {"current_steps": 8390, "total_steps": 15426, "loss": 0.2745, "lr": 3.687151206232154e-05, "epoch": 1.631722260040844, "percentage": 54.39, "elapsed_time": "14:51:49", "remaining_time": "12:27:54", "throughput": 61318.72, "total_tokens": 3281162496} {"current_steps": 8400, "total_steps": 15426, "loss": 0.2746, "lr": 3.686149072327788e-05, "epoch": 1.6336672177380143, "percentage": 54.45, "elapsed_time": "14:52:43", "remaining_time": "12:26:42", "throughput": 61328.9, "total_tokens": 3285011328} {"current_steps": 8410, "total_steps": 15426, "loss": 0.2764, "lr": 3.685147755091937e-05, "epoch": 1.6356121754351842, "percentage": 54.52, "elapsed_time": "14:53:42", "remaining_time": "12:25:34", "throughput": 61336.66, "total_tokens": 3289011456} {"current_steps": 8420, "total_steps": 15426, "loss": 0.2755, "lr": 3.684147253415992e-05, "epoch": 1.6375571331323544, "percentage": 54.58, "elapsed_time": "14:54:38", "remaining_time": "12:24:23", "throughput": 61345.66, "total_tokens": 3292924288} {"current_steps": 8430, "total_steps": 15426, "loss": 0.271, "lr": 3.683147566193448e-05, "epoch": 1.6395020908295246, "percentage": 54.65, "elapsed_time": "14:55:32", "remaining_time": "12:23:11", "throughput": 61357.77, "total_tokens": 3296881408} {"current_steps": 8440, "total_steps": 15426, "loss": 0.2735, "lr": 3.6821486923199025e-05, "epoch": 1.6414470485266945, "percentage": 54.71, "elapsed_time": "14:56:25", "remaining_time": "12:21:59", "throughput": 61369.21, "total_tokens": 3300746880} {"current_steps": 8450, "total_steps": 15426, "loss": 0.2715, "lr": 3.681150630693046e-05, "epoch": 1.6433920062238645, "percentage": 54.78, "elapsed_time": "14:57:18", "remaining_time": "12:20:46", "throughput": 61380.08, "total_tokens": 3304604928} {"current_steps": 8460, "total_steps": 15426, "loss": 0.274, "lr": 3.6801533802126615e-05, "epoch": 1.6453369639210347, "percentage": 54.84, "elapsed_time": "14:58:09", "remaining_time": "12:19:32", "throughput": 61392.78, "total_tokens": 3308423552} {"current_steps": 8470, "total_steps": 15426, "loss": 0.2736, "lr": 3.679156939780617e-05, "epoch": 1.6472819216182049, "percentage": 54.91, "elapsed_time": "14:59:02", "remaining_time": "12:18:20", "throughput": 61404.43, "total_tokens": 3312306304} {"current_steps": 8480, "total_steps": 15426, "loss": 0.2756, "lr": 3.6781613083008594e-05, "epoch": 1.6492268793153748, "percentage": 54.97, "elapsed_time": "14:59:54", "remaining_time": "12:17:07", "throughput": 61416.39, "total_tokens": 3316154240} {"current_steps": 8490, "total_steps": 15426, "loss": 0.2679, "lr": 3.677166484679412e-05, "epoch": 1.651171837012545, "percentage": 55.04, "elapsed_time": "15:00:49", "remaining_time": "12:15:56", "throughput": 61426.86, "total_tokens": 3320112000} {"current_steps": 8500, "total_steps": 15426, "loss": 0.2713, "lr": 3.676172467824368e-05, "epoch": 1.6531167947097152, "percentage": 55.1, "elapsed_time": "15:01:43", "remaining_time": "12:14:44", "throughput": 61438.21, "total_tokens": 3324014720} {"current_steps": 8510, "total_steps": 15426, "loss": 0.2713, "lr": 3.675179256645885e-05, "epoch": 1.6550617524068851, "percentage": 55.17, "elapsed_time": "15:02:37", "remaining_time": "12:13:33", "throughput": 61448.79, "total_tokens": 3327916544} {"current_steps": 8520, "total_steps": 15426, "loss": 0.2714, "lr": 3.674186850056181e-05, "epoch": 1.657006710104055, "percentage": 55.23, "elapsed_time": "15:03:31", "remaining_time": "12:12:21", "throughput": 61457.64, "total_tokens": 3331688576} {"current_steps": 8530, "total_steps": 15426, "loss": 0.2707, "lr": 3.67319524696953e-05, "epoch": 1.6589516678012253, "percentage": 55.3, "elapsed_time": "15:04:24", "remaining_time": "12:11:09", "throughput": 61467.62, "total_tokens": 3335526016} {"current_steps": 8540, "total_steps": 15426, "loss": 0.2726, "lr": 3.6722044463022536e-05, "epoch": 1.6608966254983955, "percentage": 55.36, "elapsed_time": "15:05:22", "remaining_time": "12:10:01", "throughput": 61476.62, "total_tokens": 3339555840} {"current_steps": 8550, "total_steps": 15426, "loss": 0.2722, "lr": 3.6712144469727214e-05, "epoch": 1.6628415831955654, "percentage": 55.43, "elapsed_time": "15:06:15", "remaining_time": "12:08:49", "throughput": 61487.97, "total_tokens": 3343450752} {"current_steps": 8560, "total_steps": 15426, "loss": 0.2756, "lr": 3.67022524790134e-05, "epoch": 1.6647865408927356, "percentage": 55.49, "elapsed_time": "15:07:10", "remaining_time": "12:07:38", "throughput": 61498.99, "total_tokens": 3347412096} {"current_steps": 8570, "total_steps": 15426, "loss": 0.2728, "lr": 3.6692368480105546e-05, "epoch": 1.6667314985899058, "percentage": 55.56, "elapsed_time": "15:08:03", "remaining_time": "12:06:26", "throughput": 61511.02, "total_tokens": 3351333632} {"current_steps": 8580, "total_steps": 15426, "loss": 0.2723, "lr": 3.6682492462248374e-05, "epoch": 1.6686764562870757, "percentage": 55.62, "elapsed_time": "15:08:56", "remaining_time": "12:05:14", "throughput": 61521.94, "total_tokens": 3355206656} {"current_steps": 8590, "total_steps": 15426, "loss": 0.2724, "lr": 3.667262441470689e-05, "epoch": 1.6706214139842457, "percentage": 55.69, "elapsed_time": "15:09:50", "remaining_time": "12:04:03", "throughput": 61532.21, "total_tokens": 3359056896} {"current_steps": 8600, "total_steps": 15426, "loss": 0.2707, "lr": 3.6662764326766255e-05, "epoch": 1.672566371681416, "percentage": 55.75, "elapsed_time": "15:10:45", "remaining_time": "12:02:52", "throughput": 61543.42, "total_tokens": 3363048576} {"current_steps": 8610, "total_steps": 15426, "loss": 0.2726, "lr": 3.665291218773185e-05, "epoch": 1.674511329378586, "percentage": 55.81, "elapsed_time": "15:11:39", "remaining_time": "12:01:41", "throughput": 61553.56, "total_tokens": 3366927872} {"current_steps": 8620, "total_steps": 15426, "loss": 0.2705, "lr": 3.664306798692912e-05, "epoch": 1.676456287075756, "percentage": 55.88, "elapsed_time": "15:12:31", "remaining_time": "12:00:29", "throughput": 61565.04, "total_tokens": 3370768384} {"current_steps": 8630, "total_steps": 15426, "loss": 0.2704, "lr": 3.6633231713703576e-05, "epoch": 1.6784012447729262, "percentage": 55.94, "elapsed_time": "15:13:24", "remaining_time": "11:59:17", "throughput": 61576.46, "total_tokens": 3374637952} {"current_steps": 8640, "total_steps": 15426, "loss": 0.2742, "lr": 3.6623403357420745e-05, "epoch": 1.6803462024700964, "percentage": 56.01, "elapsed_time": "15:14:25", "remaining_time": "11:58:12", "throughput": 61579.53, "total_tokens": 3378619776} {"current_steps": 8650, "total_steps": 15426, "loss": 0.2749, "lr": 3.661358290746611e-05, "epoch": 1.6822911601672663, "percentage": 56.07, "elapsed_time": "15:15:20", "remaining_time": "11:57:02", "throughput": 61589.39, "total_tokens": 3382515456} {"current_steps": 8660, "total_steps": 15426, "loss": 0.2734, "lr": 3.6603770353245056e-05, "epoch": 1.6842361178644365, "percentage": 56.14, "elapsed_time": "15:16:19", "remaining_time": "11:55:55", "throughput": 61595.62, "total_tokens": 3386523520} {"current_steps": 8670, "total_steps": 15426, "loss": 0.2714, "lr": 3.659396568418286e-05, "epoch": 1.6861810755616067, "percentage": 56.2, "elapsed_time": "15:17:14", "remaining_time": "11:54:45", "throughput": 61605.09, "total_tokens": 3390412544} {"current_steps": 8680, "total_steps": 15426, "loss": 0.2724, "lr": 3.658416888972459e-05, "epoch": 1.6881260332587766, "percentage": 56.27, "elapsed_time": "15:18:10", "remaining_time": "11:53:36", "throughput": 61614.81, "total_tokens": 3394415360} {"current_steps": 8690, "total_steps": 15426, "loss": 0.2716, "lr": 3.6574379959335106e-05, "epoch": 1.6900709909559466, "percentage": 56.33, "elapsed_time": "15:19:04", "remaining_time": "11:52:25", "throughput": 61626.27, "total_tokens": 3398376320} {"current_steps": 8700, "total_steps": 15426, "loss": 0.27, "lr": 3.6564598882498976e-05, "epoch": 1.6920159486531168, "percentage": 56.4, "elapsed_time": "15:20:02", "remaining_time": "11:51:16", "throughput": 61634.35, "total_tokens": 3402347904} {"current_steps": 8710, "total_steps": 15426, "loss": 0.273, "lr": 3.655482564872043e-05, "epoch": 1.693960906350287, "percentage": 56.46, "elapsed_time": "15:20:59", "remaining_time": "11:50:08", "throughput": 61642.77, "total_tokens": 3406337280} {"current_steps": 8720, "total_steps": 15426, "loss": 0.2699, "lr": 3.654506024752336e-05, "epoch": 1.695905864047457, "percentage": 56.53, "elapsed_time": "15:21:53", "remaining_time": "11:48:57", "throughput": 61653.26, "total_tokens": 3410227072} {"current_steps": 8730, "total_steps": 15426, "loss": 0.2737, "lr": 3.653530266845121e-05, "epoch": 1.697850821744627, "percentage": 56.59, "elapsed_time": "15:22:47", "remaining_time": "11:47:47", "throughput": 61663.29, "total_tokens": 3414117504} {"current_steps": 8740, "total_steps": 15426, "loss": 0.2668, "lr": 3.652555290106696e-05, "epoch": 1.6997957794417973, "percentage": 56.66, "elapsed_time": "15:23:42", "remaining_time": "11:46:37", "throughput": 61673.4, "total_tokens": 3418072832} {"current_steps": 8750, "total_steps": 15426, "loss": 0.2718, "lr": 3.6515810934953084e-05, "epoch": 1.7017407371389672, "percentage": 56.72, "elapsed_time": "15:24:36", "remaining_time": "11:45:26", "throughput": 61683.52, "total_tokens": 3421970688} {"current_steps": 8760, "total_steps": 15426, "loss": 0.2711, "lr": 3.650607675971151e-05, "epoch": 1.7036856948361372, "percentage": 56.79, "elapsed_time": "15:25:30", "remaining_time": "11:44:16", "throughput": 61694.33, "total_tokens": 3425937024} {"current_steps": 8770, "total_steps": 15426, "loss": 0.2734, "lr": 3.649635036496351e-05, "epoch": 1.7056306525333074, "percentage": 56.85, "elapsed_time": "15:26:26", "remaining_time": "11:43:07", "throughput": 61703.6, "total_tokens": 3429866752} {"current_steps": 8780, "total_steps": 15426, "loss": 0.2706, "lr": 3.6486631740349746e-05, "epoch": 1.7075756102304775, "percentage": 56.92, "elapsed_time": "15:27:22", "remaining_time": "11:41:58", "throughput": 61711.36, "total_tokens": 3433763584} {"current_steps": 8790, "total_steps": 15426, "loss": 0.2723, "lr": 3.647692087553018e-05, "epoch": 1.7095205679276475, "percentage": 56.98, "elapsed_time": "15:28:15", "remaining_time": "11:40:47", "throughput": 61722.3, "total_tokens": 3437645952} {"current_steps": 8800, "total_steps": 15426, "loss": 0.2722, "lr": 3.6467217760184005e-05, "epoch": 1.7114655256248177, "percentage": 57.05, "elapsed_time": "15:29:12", "remaining_time": "11:39:39", "throughput": 61730.13, "total_tokens": 3441638528} {"current_steps": 8810, "total_steps": 15426, "loss": 0.2733, "lr": 3.6457522384009625e-05, "epoch": 1.7134104833219879, "percentage": 57.11, "elapsed_time": "15:30:06", "remaining_time": "11:38:28", "throughput": 61741.26, "total_tokens": 3445538944} {"current_steps": 8820, "total_steps": 15426, "loss": 0.2727, "lr": 3.644783473672462e-05, "epoch": 1.7153554410191578, "percentage": 57.18, "elapsed_time": "15:31:01", "remaining_time": "11:37:18", "throughput": 61750.32, "total_tokens": 3449440128} {"current_steps": 8830, "total_steps": 15426, "loss": 0.2717, "lr": 3.643815480806568e-05, "epoch": 1.7173003987163278, "percentage": 57.24, "elapsed_time": "15:31:57", "remaining_time": "11:36:10", "throughput": 61758.52, "total_tokens": 3453379200} {"current_steps": 8840, "total_steps": 15426, "loss": 0.2704, "lr": 3.6428482587788555e-05, "epoch": 1.719245356413498, "percentage": 57.31, "elapsed_time": "15:32:51", "remaining_time": "11:35:00", "throughput": 61768.72, "total_tokens": 3457312128} {"current_steps": 8850, "total_steps": 15426, "loss": 0.2729, "lr": 3.641881806566803e-05, "epoch": 1.7211903141106681, "percentage": 57.37, "elapsed_time": "15:33:46", "remaining_time": "11:33:50", "throughput": 61779.24, "total_tokens": 3461257728} {"current_steps": 8860, "total_steps": 15426, "loss": 0.2685, "lr": 3.640916123149788e-05, "epoch": 1.723135271807838, "percentage": 57.44, "elapsed_time": "15:34:41", "remaining_time": "11:32:40", "throughput": 61787.94, "total_tokens": 3465148672} {"current_steps": 8870, "total_steps": 15426, "loss": 0.271, "lr": 3.639951207509079e-05, "epoch": 1.7250802295050083, "percentage": 57.5, "elapsed_time": "15:35:34", "remaining_time": "11:31:30", "throughput": 61796.97, "total_tokens": 3468969472} {"current_steps": 8880, "total_steps": 15426, "loss": 0.2705, "lr": 3.6389870586278333e-05, "epoch": 1.7270251872021785, "percentage": 57.57, "elapsed_time": "15:36:30", "remaining_time": "11:30:21", "throughput": 61804.35, "total_tokens": 3472821248} {"current_steps": 8890, "total_steps": 15426, "loss": 0.2714, "lr": 3.6380236754910965e-05, "epoch": 1.7289701448993484, "percentage": 57.63, "elapsed_time": "15:37:25", "remaining_time": "11:29:11", "throughput": 61813.69, "total_tokens": 3476713344} {"current_steps": 8900, "total_steps": 15426, "loss": 0.2731, "lr": 3.6370610570857897e-05, "epoch": 1.7309151025965184, "percentage": 57.69, "elapsed_time": "15:38:18", "remaining_time": "11:28:01", "throughput": 61823.88, "total_tokens": 3480617344} {"current_steps": 8910, "total_steps": 15426, "loss": 0.2765, "lr": 3.6360992024007114e-05, "epoch": 1.7328600602936888, "percentage": 57.76, "elapsed_time": "15:39:13", "remaining_time": "11:26:52", "throughput": 61833.09, "total_tokens": 3484520448} {"current_steps": 8920, "total_steps": 15426, "loss": 0.2724, "lr": 3.6351381104265304e-05, "epoch": 1.7348050179908587, "percentage": 57.82, "elapsed_time": "15:40:04", "remaining_time": "11:25:40", "throughput": 61845.36, "total_tokens": 3488380800} {"current_steps": 8930, "total_steps": 15426, "loss": 0.2743, "lr": 3.634177780155783e-05, "epoch": 1.7367499756880287, "percentage": 57.89, "elapsed_time": "15:40:58", "remaining_time": "11:24:30", "throughput": 61855.54, "total_tokens": 3492292864} {"current_steps": 8940, "total_steps": 15426, "loss": 0.2682, "lr": 3.633218210582867e-05, "epoch": 1.7386949333851989, "percentage": 57.95, "elapsed_time": "15:41:56", "remaining_time": "11:23:23", "throughput": 61862.88, "total_tokens": 3496293504} {"current_steps": 8950, "total_steps": 15426, "loss": 0.2711, "lr": 3.6322594007040376e-05, "epoch": 1.740639891082369, "percentage": 58.02, "elapsed_time": "15:42:49", "remaining_time": "11:22:12", "throughput": 61873.21, "total_tokens": 3500149632} {"current_steps": 8960, "total_steps": 15426, "loss": 0.2688, "lr": 3.631301349517403e-05, "epoch": 1.742584848779539, "percentage": 58.08, "elapsed_time": "15:43:49", "remaining_time": "11:21:06", "throughput": 61877.34, "total_tokens": 3504097664} {"current_steps": 8970, "total_steps": 15426, "loss": 0.2706, "lr": 3.6303440560229216e-05, "epoch": 1.744529806476709, "percentage": 58.15, "elapsed_time": "15:44:47", "remaining_time": "11:19:59", "throughput": 61884.28, "total_tokens": 3508052864} {"current_steps": 8980, "total_steps": 15426, "loss": 0.2701, "lr": 3.629387519222395e-05, "epoch": 1.7464747641738794, "percentage": 58.21, "elapsed_time": "15:45:50", "remaining_time": "11:18:56", "throughput": 61884.63, "total_tokens": 3512012544} {"current_steps": 8990, "total_steps": 15426, "loss": 0.2759, "lr": 3.628431738119464e-05, "epoch": 1.7484197218710493, "percentage": 58.28, "elapsed_time": "15:46:44", "remaining_time": "11:17:46", "throughput": 61894.92, "total_tokens": 3515888896} {"current_steps": 9000, "total_steps": 15426, "loss": 0.2716, "lr": 3.62747671171961e-05, "epoch": 1.7503646795682193, "percentage": 58.34, "elapsed_time": "15:47:41", "remaining_time": "11:16:38", "throughput": 61900.81, "total_tokens": 3519752576} {"current_steps": 9010, "total_steps": 15426, "loss": 0.2701, "lr": 3.626522439030138e-05, "epoch": 1.7523096372653895, "percentage": 58.41, "elapsed_time": "15:48:36", "remaining_time": "11:15:30", "throughput": 61910.44, "total_tokens": 3523724928} {"current_steps": 9020, "total_steps": 15426, "loss": 0.2696, "lr": 3.6255689190601863e-05, "epoch": 1.7542545949625596, "percentage": 58.47, "elapsed_time": "15:49:29", "remaining_time": "11:14:19", "throughput": 61920.81, "total_tokens": 3527594240} {"current_steps": 9030, "total_steps": 15426, "loss": 0.271, "lr": 3.624616150820714e-05, "epoch": 1.7561995526597296, "percentage": 58.54, "elapsed_time": "15:50:23", "remaining_time": "11:13:09", "throughput": 61930.45, "total_tokens": 3531477632} {"current_steps": 9040, "total_steps": 15426, "loss": 0.272, "lr": 3.623664133324499e-05, "epoch": 1.7581445103568998, "percentage": 58.6, "elapsed_time": "15:51:18", "remaining_time": "11:12:00", "throughput": 61939.15, "total_tokens": 3535364096} {"current_steps": 9050, "total_steps": 15426, "loss": 0.2699, "lr": 3.622712865586131e-05, "epoch": 1.76008946805407, "percentage": 58.67, "elapsed_time": "15:52:12", "remaining_time": "11:10:51", "throughput": 61949.03, "total_tokens": 3539292544} {"current_steps": 9060, "total_steps": 15426, "loss": 0.2724, "lr": 3.621762346622014e-05, "epoch": 1.76203442575124, "percentage": 58.73, "elapsed_time": "15:53:06", "remaining_time": "11:09:41", "throughput": 61958.15, "total_tokens": 3543162880} {"current_steps": 9070, "total_steps": 15426, "loss": 0.2728, "lr": 3.620812575450352e-05, "epoch": 1.7639793834484099, "percentage": 58.8, "elapsed_time": "15:54:01", "remaining_time": "11:08:33", "throughput": 61967.45, "total_tokens": 3547093376} {"current_steps": 9080, "total_steps": 15426, "loss": 0.2687, "lr": 3.6198635510911556e-05, "epoch": 1.76592434114558, "percentage": 58.86, "elapsed_time": "15:54:55", "remaining_time": "11:07:23", "throughput": 61976.43, "total_tokens": 3550971776} {"current_steps": 9090, "total_steps": 15426, "loss": 0.2719, "lr": 3.618915272566228e-05, "epoch": 1.7678692988427502, "percentage": 58.93, "elapsed_time": "15:55:48", "remaining_time": "11:06:13", "throughput": 61987.8, "total_tokens": 3554910720} {"current_steps": 9100, "total_steps": 15426, "loss": 0.273, "lr": 3.6179677388991694e-05, "epoch": 1.7698142565399202, "percentage": 58.99, "elapsed_time": "15:56:42", "remaining_time": "11:05:04", "throughput": 61997.65, "total_tokens": 3558841088} {"current_steps": 9110, "total_steps": 15426, "loss": 0.2735, "lr": 3.617020949115366e-05, "epoch": 1.7717592142370904, "percentage": 59.06, "elapsed_time": "15:57:35", "remaining_time": "11:03:54", "throughput": 62007.32, "total_tokens": 3562668544} {"current_steps": 9120, "total_steps": 15426, "loss": 0.2744, "lr": 3.6160749022419886e-05, "epoch": 1.7737041719342606, "percentage": 59.12, "elapsed_time": "15:58:28", "remaining_time": "11:02:44", "throughput": 62018.01, "total_tokens": 3566557312} {"current_steps": 9130, "total_steps": 15426, "loss": 0.2681, "lr": 3.6151295973079887e-05, "epoch": 1.7756491296314305, "percentage": 59.19, "elapsed_time": "15:59:25", "remaining_time": "11:01:37", "throughput": 62026.38, "total_tokens": 3570595328} {"current_steps": 9140, "total_steps": 15426, "loss": 0.272, "lr": 3.6141850333440934e-05, "epoch": 1.7775940873286005, "percentage": 59.25, "elapsed_time": "16:00:20", "remaining_time": "11:00:28", "throughput": 62036.06, "total_tokens": 3574573952} {"current_steps": 9150, "total_steps": 15426, "loss": 0.2745, "lr": 3.613241209382803e-05, "epoch": 1.7795390450257706, "percentage": 59.32, "elapsed_time": "16:01:15", "remaining_time": "10:59:19", "throughput": 62045.81, "total_tokens": 3578520448} {"current_steps": 9160, "total_steps": 15426, "loss": 0.2716, "lr": 3.6122981244583834e-05, "epoch": 1.7814840027229408, "percentage": 59.38, "elapsed_time": "16:02:09", "remaining_time": "10:58:10", "throughput": 62056.12, "total_tokens": 3582445824} {"current_steps": 9170, "total_steps": 15426, "loss": 0.2702, "lr": 3.6113557776068644e-05, "epoch": 1.7834289604201108, "percentage": 59.45, "elapsed_time": "16:03:03", "remaining_time": "10:57:01", "throughput": 62067.45, "total_tokens": 3586467584} {"current_steps": 9180, "total_steps": 15426, "loss": 0.273, "lr": 3.6104141678660386e-05, "epoch": 1.785373918117281, "percentage": 59.51, "elapsed_time": "16:03:56", "remaining_time": "10:55:51", "throughput": 62076.6, "total_tokens": 3590308224} {"current_steps": 9190, "total_steps": 15426, "loss": 0.273, "lr": 3.6094732942754487e-05, "epoch": 1.7873188758144511, "percentage": 59.57, "elapsed_time": "16:04:52", "remaining_time": "10:54:43", "throughput": 62083.56, "total_tokens": 3594182016} {"current_steps": 9200, "total_steps": 15426, "loss": 0.2722, "lr": 3.60853315587639e-05, "epoch": 1.789263833511621, "percentage": 59.64, "elapsed_time": "16:05:45", "remaining_time": "10:53:33", "throughput": 62093.76, "total_tokens": 3598038144} {"current_steps": 9210, "total_steps": 15426, "loss": 0.273, "lr": 3.607593751711909e-05, "epoch": 1.791208791208791, "percentage": 59.7, "elapsed_time": "16:06:38", "remaining_time": "10:52:24", "throughput": 62104.18, "total_tokens": 3601960576} {"current_steps": 9220, "total_steps": 15426, "loss": 0.27, "lr": 3.60665508082679e-05, "epoch": 1.7931537489059612, "percentage": 59.77, "elapsed_time": "16:07:32", "remaining_time": "10:51:15", "throughput": 62113.71, "total_tokens": 3605879040} {"current_steps": 9230, "total_steps": 15426, "loss": 0.2694, "lr": 3.6057171422675585e-05, "epoch": 1.7950987066031314, "percentage": 59.83, "elapsed_time": "16:08:31", "remaining_time": "10:50:09", "throughput": 62120.47, "total_tokens": 3609883904} {"current_steps": 9240, "total_steps": 15426, "loss": 0.2725, "lr": 3.604779935082474e-05, "epoch": 1.7970436643003014, "percentage": 59.9, "elapsed_time": "16:09:29", "remaining_time": "10:49:03", "throughput": 62125.44, "total_tokens": 3613791488} {"current_steps": 9250, "total_steps": 15426, "loss": 0.2687, "lr": 3.603843458321526e-05, "epoch": 1.7989886219974716, "percentage": 59.96, "elapsed_time": "16:10:20", "remaining_time": "10:47:52", "throughput": 62137.13, "total_tokens": 3617679616} {"current_steps": 9260, "total_steps": 15426, "loss": 0.2707, "lr": 3.6029077110364355e-05, "epoch": 1.8009335796946417, "percentage": 60.03, "elapsed_time": "16:11:17", "remaining_time": "10:46:45", "throughput": 62145.46, "total_tokens": 3621680512} {"current_steps": 9270, "total_steps": 15426, "loss": 0.2713, "lr": 3.60197269228064e-05, "epoch": 1.8028785373918117, "percentage": 60.09, "elapsed_time": "16:12:14", "remaining_time": "10:45:38", "throughput": 62152.18, "total_tokens": 3625629952} {"current_steps": 9280, "total_steps": 15426, "loss": 0.2711, "lr": 3.601038401109299e-05, "epoch": 1.8048234950889817, "percentage": 60.16, "elapsed_time": "16:13:07", "remaining_time": "10:44:28", "throughput": 62161.62, "total_tokens": 3629434368} {"current_steps": 9290, "total_steps": 15426, "loss": 0.2726, "lr": 3.6001048365792846e-05, "epoch": 1.806768452786152, "percentage": 60.22, "elapsed_time": "16:14:03", "remaining_time": "10:43:21", "throughput": 62169.61, "total_tokens": 3633382272} {"current_steps": 9300, "total_steps": 15426, "loss": 0.2731, "lr": 3.599171997749182e-05, "epoch": 1.808713410483322, "percentage": 60.29, "elapsed_time": "16:14:55", "remaining_time": "10:42:11", "throughput": 62179.34, "total_tokens": 3637194368} {"current_steps": 9310, "total_steps": 15426, "loss": 0.2708, "lr": 3.598239883679281e-05, "epoch": 1.810658368180492, "percentage": 60.35, "elapsed_time": "16:15:50", "remaining_time": "10:41:03", "throughput": 62187.76, "total_tokens": 3641107328} {"current_steps": 9320, "total_steps": 15426, "loss": 0.2682, "lr": 3.597308493431576e-05, "epoch": 1.8126033258776622, "percentage": 60.42, "elapsed_time": "16:16:43", "remaining_time": "10:39:54", "throughput": 62196.93, "total_tokens": 3644966656} {"current_steps": 9330, "total_steps": 15426, "loss": 0.272, "lr": 3.596377826069758e-05, "epoch": 1.8145482835748323, "percentage": 60.48, "elapsed_time": "16:17:38", "remaining_time": "10:38:45", "throughput": 62206.05, "total_tokens": 3648903680} {"current_steps": 9340, "total_steps": 15426, "loss": 0.2734, "lr": 3.5954478806592155e-05, "epoch": 1.8164932412720023, "percentage": 60.55, "elapsed_time": "16:18:31", "remaining_time": "10:37:36", "throughput": 62216.03, "total_tokens": 3652802304} {"current_steps": 9350, "total_steps": 15426, "loss": 0.2712, "lr": 3.594518656267024e-05, "epoch": 1.8184381989691725, "percentage": 60.61, "elapsed_time": "16:19:23", "remaining_time": "10:36:26", "throughput": 62226.09, "total_tokens": 3656594560} {"current_steps": 9360, "total_steps": 15426, "loss": 0.2673, "lr": 3.5935901519619496e-05, "epoch": 1.8203831566663426, "percentage": 60.68, "elapsed_time": "16:20:22", "remaining_time": "10:35:21", "throughput": 62229.73, "total_tokens": 3660519552} {"current_steps": 9370, "total_steps": 15426, "loss": 0.2693, "lr": 3.5926623668144385e-05, "epoch": 1.8223281143635126, "percentage": 60.74, "elapsed_time": "16:21:17", "remaining_time": "10:34:13", "throughput": 62238.93, "total_tokens": 3664462976} {"current_steps": 9380, "total_steps": 15426, "loss": 0.2677, "lr": 3.5917352998966194e-05, "epoch": 1.8242730720606826, "percentage": 60.81, "elapsed_time": "16:22:12", "remaining_time": "10:33:05", "throughput": 62247.96, "total_tokens": 3668427008} {"current_steps": 9390, "total_steps": 15426, "loss": 0.2717, "lr": 3.5908089502822914e-05, "epoch": 1.8262180297578527, "percentage": 60.87, "elapsed_time": "16:23:08", "remaining_time": "10:31:58", "throughput": 62254.96, "total_tokens": 3672319360} {"current_steps": 9400, "total_steps": 15426, "loss": 0.2736, "lr": 3.589883317046929e-05, "epoch": 1.828162987455023, "percentage": 60.94, "elapsed_time": "16:24:00", "remaining_time": "10:30:48", "throughput": 62265.37, "total_tokens": 3676197888} {"current_steps": 9410, "total_steps": 15426, "loss": 0.2733, "lr": 3.5889583992676715e-05, "epoch": 1.8301079451521929, "percentage": 61.0, "elapsed_time": "16:24:54", "remaining_time": "10:29:40", "throughput": 62274.14, "total_tokens": 3680085120} {"current_steps": 9420, "total_steps": 15426, "loss": 0.2684, "lr": 3.5880341960233244e-05, "epoch": 1.832052902849363, "percentage": 61.07, "elapsed_time": "16:25:48", "remaining_time": "10:28:31", "throughput": 62283.22, "total_tokens": 3683929472} {"current_steps": 9430, "total_steps": 15426, "loss": 0.2692, "lr": 3.58711070639435e-05, "epoch": 1.8339978605465332, "percentage": 61.13, "elapsed_time": "16:26:43", "remaining_time": "10:27:23", "throughput": 62292.27, "total_tokens": 3687895040} {"current_steps": 9440, "total_steps": 15426, "loss": 0.2697, "lr": 3.586187929462869e-05, "epoch": 1.8359428182437032, "percentage": 61.2, "elapsed_time": "16:27:39", "remaining_time": "10:26:16", "throughput": 62300.3, "total_tokens": 3691861888} {"current_steps": 9450, "total_steps": 15426, "loss": 0.2718, "lr": 3.585265864312651e-05, "epoch": 1.8378877759408732, "percentage": 61.26, "elapsed_time": "16:28:32", "remaining_time": "10:25:07", "throughput": 62310.21, "total_tokens": 3695761152} {"current_steps": 9460, "total_steps": 15426, "loss": 0.2698, "lr": 3.584344510029118e-05, "epoch": 1.8398327336380433, "percentage": 61.33, "elapsed_time": "16:29:25", "remaining_time": "10:23:59", "throughput": 62320.95, "total_tokens": 3699707904} {"current_steps": 9470, "total_steps": 15426, "loss": 0.2738, "lr": 3.583423865699333e-05, "epoch": 1.8417776913352135, "percentage": 61.39, "elapsed_time": "16:30:19", "remaining_time": "10:22:50", "throughput": 62330.12, "total_tokens": 3703622144} {"current_steps": 9480, "total_steps": 15426, "loss": 0.2736, "lr": 3.5825039304119994e-05, "epoch": 1.8437226490323835, "percentage": 61.45, "elapsed_time": "16:31:12", "remaining_time": "10:21:42", "throughput": 62339.69, "total_tokens": 3707510528} {"current_steps": 9490, "total_steps": 15426, "loss": 0.2727, "lr": 3.581584703257461e-05, "epoch": 1.8456676067295537, "percentage": 61.52, "elapsed_time": "16:32:06", "remaining_time": "10:20:33", "throughput": 62348.7, "total_tokens": 3711397376} {"current_steps": 9500, "total_steps": 15426, "loss": 0.2717, "lr": 3.580666183327689e-05, "epoch": 1.8476125644267238, "percentage": 61.58, "elapsed_time": "16:33:01", "remaining_time": "10:19:26", "throughput": 62357.83, "total_tokens": 3715373952} {"current_steps": 9510, "total_steps": 15426, "loss": 0.2693, "lr": 3.5797483697162906e-05, "epoch": 1.8495575221238938, "percentage": 61.65, "elapsed_time": "16:33:54", "remaining_time": "10:18:17", "throughput": 62368.84, "total_tokens": 3719351296} {"current_steps": 9520, "total_steps": 15426, "loss": 0.2726, "lr": 3.5788312615184936e-05, "epoch": 1.8515024798210638, "percentage": 61.71, "elapsed_time": "16:34:48", "remaining_time": "10:17:09", "throughput": 62379.3, "total_tokens": 3723321088} {"current_steps": 9530, "total_steps": 15426, "loss": 0.272, "lr": 3.5779148578311476e-05, "epoch": 1.853447437518234, "percentage": 61.78, "elapsed_time": "16:35:42", "remaining_time": "10:16:01", "throughput": 62387.94, "total_tokens": 3727221504} {"current_steps": 9540, "total_steps": 15426, "loss": 0.2708, "lr": 3.5769991577527236e-05, "epoch": 1.8553923952154041, "percentage": 61.84, "elapsed_time": "16:36:37", "remaining_time": "10:14:54", "throughput": 62395.02, "total_tokens": 3731079808} {"current_steps": 9550, "total_steps": 15426, "loss": 0.2745, "lr": 3.5760841603833034e-05, "epoch": 1.857337352912574, "percentage": 61.91, "elapsed_time": "16:37:29", "remaining_time": "10:13:44", "throughput": 62404.78, "total_tokens": 3734923520} {"current_steps": 9560, "total_steps": 15426, "loss": 0.2718, "lr": 3.5751698648245814e-05, "epoch": 1.8592823106097442, "percentage": 61.97, "elapsed_time": "16:38:23", "remaining_time": "10:12:36", "throughput": 62412.54, "total_tokens": 3738724352} {"current_steps": 9570, "total_steps": 15426, "loss": 0.2712, "lr": 3.574256270179857e-05, "epoch": 1.8612272683069144, "percentage": 62.04, "elapsed_time": "16:39:17", "remaining_time": "10:11:28", "throughput": 62422.44, "total_tokens": 3742668928} {"current_steps": 9580, "total_steps": 15426, "loss": 0.2705, "lr": 3.573343375554037e-05, "epoch": 1.8631722260040844, "percentage": 62.1, "elapsed_time": "16:40:08", "remaining_time": "10:10:18", "throughput": 62433.69, "total_tokens": 3746554368} {"current_steps": 9590, "total_steps": 15426, "loss": 0.2699, "lr": 3.572431180053621e-05, "epoch": 1.8651171837012543, "percentage": 62.17, "elapsed_time": "16:41:01", "remaining_time": "10:09:10", "throughput": 62444.25, "total_tokens": 3750510848} {"current_steps": 9600, "total_steps": 15426, "loss": 0.2685, "lr": 3.571519682786711e-05, "epoch": 1.8670621413984247, "percentage": 62.23, "elapsed_time": "16:41:55", "remaining_time": "10:08:02", "throughput": 62452.68, "total_tokens": 3754381312} {"current_steps": 9610, "total_steps": 15426, "loss": 0.2689, "lr": 3.570608882862996e-05, "epoch": 1.8690070990955947, "percentage": 62.3, "elapsed_time": "16:42:49", "remaining_time": "10:06:55", "throughput": 62460.84, "total_tokens": 3758263680} {"current_steps": 9620, "total_steps": 15426, "loss": 0.2702, "lr": 3.569698779393757e-05, "epoch": 1.8709520567927647, "percentage": 62.36, "elapsed_time": "16:43:41", "remaining_time": "10:05:46", "throughput": 62469.87, "total_tokens": 3762057984} {"current_steps": 9630, "total_steps": 15426, "loss": 0.2705, "lr": 3.568789371491859e-05, "epoch": 1.8728970144899348, "percentage": 62.43, "elapsed_time": "16:44:36", "remaining_time": "10:04:38", "throughput": 62479.22, "total_tokens": 3766022144} {"current_steps": 9640, "total_steps": 15426, "loss": 0.2682, "lr": 3.567880658271748e-05, "epoch": 1.874841972187105, "percentage": 62.49, "elapsed_time": "16:45:31", "remaining_time": "10:03:31", "throughput": 62487.44, "total_tokens": 3769979776} {"current_steps": 9650, "total_steps": 15426, "loss": 0.2697, "lr": 3.566972638849445e-05, "epoch": 1.876786929884275, "percentage": 62.56, "elapsed_time": "16:46:25", "remaining_time": "10:02:23", "throughput": 62496.23, "total_tokens": 3773838336} {"current_steps": 9660, "total_steps": 15426, "loss": 0.2715, "lr": 3.566065312342551e-05, "epoch": 1.878731887581445, "percentage": 62.62, "elapsed_time": "16:47:16", "remaining_time": "10:01:14", "throughput": 62506.78, "total_tokens": 3777693824} {"current_steps": 9670, "total_steps": 15426, "loss": 0.2708, "lr": 3.565158677870231e-05, "epoch": 1.8806768452786153, "percentage": 62.69, "elapsed_time": "16:48:08", "remaining_time": "10:00:05", "throughput": 62517.04, "total_tokens": 3781586816} {"current_steps": 9680, "total_steps": 15426, "loss": 0.2702, "lr": 3.564252734553221e-05, "epoch": 1.8826218029757853, "percentage": 62.75, "elapsed_time": "16:49:03", "remaining_time": "9:58:58", "throughput": 62526.78, "total_tokens": 3785564544} {"current_steps": 9690, "total_steps": 15426, "loss": 0.2713, "lr": 3.563347481513818e-05, "epoch": 1.8845667606729553, "percentage": 62.82, "elapsed_time": "16:49:57", "remaining_time": "9:57:50", "throughput": 62535.0, "total_tokens": 3789455872} {"current_steps": 9700, "total_steps": 15426, "loss": 0.2734, "lr": 3.56244291787588e-05, "epoch": 1.8865117183701254, "percentage": 62.88, "elapsed_time": "16:50:54", "remaining_time": "9:56:44", "throughput": 62542.55, "total_tokens": 3793471104} {"current_steps": 9710, "total_steps": 15426, "loss": 0.2709, "lr": 3.5615390427648216e-05, "epoch": 1.8884566760672956, "percentage": 62.95, "elapsed_time": "16:51:48", "remaining_time": "9:55:37", "throughput": 62552.18, "total_tokens": 3797436416} {"current_steps": 9720, "total_steps": 15426, "loss": 0.273, "lr": 3.5606358553076075e-05, "epoch": 1.8904016337644656, "percentage": 63.01, "elapsed_time": "16:52:40", "remaining_time": "9:54:28", "throughput": 62560.43, "total_tokens": 3801227520} {"current_steps": 9730, "total_steps": 15426, "loss": 0.2718, "lr": 3.5597333546327526e-05, "epoch": 1.8923465914616358, "percentage": 63.08, "elapsed_time": "16:53:36", "remaining_time": "9:53:22", "throughput": 62567.64, "total_tokens": 3805145088} {"current_steps": 9740, "total_steps": 15426, "loss": 0.2682, "lr": 3.5588315398703186e-05, "epoch": 1.894291549158806, "percentage": 63.14, "elapsed_time": "16:54:31", "remaining_time": "9:52:15", "throughput": 62574.54, "total_tokens": 3809018752} {"current_steps": 9750, "total_steps": 15426, "loss": 0.2726, "lr": 3.557930410151907e-05, "epoch": 1.896236506855976, "percentage": 63.2, "elapsed_time": "16:55:27", "remaining_time": "9:51:08", "throughput": 62582.9, "total_tokens": 3812993024} {"current_steps": 9760, "total_steps": 15426, "loss": 0.2701, "lr": 3.5570299646106606e-05, "epoch": 1.8981814645531458, "percentage": 63.27, "elapsed_time": "16:56:21", "remaining_time": "9:50:01", "throughput": 62592.33, "total_tokens": 3816971264} {"current_steps": 9770, "total_steps": 15426, "loss": 0.2679, "lr": 3.556130202381253e-05, "epoch": 1.900126422250316, "percentage": 63.33, "elapsed_time": "16:57:14", "remaining_time": "9:48:53", "throughput": 62602.2, "total_tokens": 3820912640} {"current_steps": 9780, "total_steps": 15426, "loss": 0.2697, "lr": 3.555231122599892e-05, "epoch": 1.9020713799474862, "percentage": 63.4, "elapsed_time": "16:58:08", "remaining_time": "9:47:46", "throughput": 62610.01, "total_tokens": 3824776832} {"current_steps": 9790, "total_steps": 15426, "loss": 0.2706, "lr": 3.554332724404313e-05, "epoch": 1.9040163376446562, "percentage": 63.46, "elapsed_time": "16:59:04", "remaining_time": "9:46:40", "throughput": 62616.88, "total_tokens": 3828676480} {"current_steps": 9800, "total_steps": 15426, "loss": 0.2711, "lr": 3.553435006933777e-05, "epoch": 1.9059612953418263, "percentage": 63.53, "elapsed_time": "16:59:57", "remaining_time": "9:45:32", "throughput": 62625.81, "total_tokens": 3832541184} {"current_steps": 9810, "total_steps": 15426, "loss": 0.2718, "lr": 3.5525379693290626e-05, "epoch": 1.9079062530389965, "percentage": 63.59, "elapsed_time": "17:00:55", "remaining_time": "9:44:27", "throughput": 62632.46, "total_tokens": 3836576896} {"current_steps": 9820, "total_steps": 15426, "loss": 0.2696, "lr": 3.551641610732469e-05, "epoch": 1.9098512107361665, "percentage": 63.66, "elapsed_time": "17:01:49", "remaining_time": "9:43:19", "throughput": 62640.16, "total_tokens": 3840420480} {"current_steps": 9830, "total_steps": 15426, "loss": 0.2723, "lr": 3.55074593028781e-05, "epoch": 1.9117961684333364, "percentage": 63.72, "elapsed_time": "17:02:43", "remaining_time": "9:42:12", "throughput": 62648.62, "total_tokens": 3844346496} {"current_steps": 9840, "total_steps": 15426, "loss": 0.2721, "lr": 3.5498509271404065e-05, "epoch": 1.9137411261305066, "percentage": 63.79, "elapsed_time": "17:03:36", "remaining_time": "9:41:05", "throughput": 62658.6, "total_tokens": 3848274688} {"current_steps": 9850, "total_steps": 15426, "loss": 0.2697, "lr": 3.5489566004370893e-05, "epoch": 1.9156860838276768, "percentage": 63.85, "elapsed_time": "17:04:30", "remaining_time": "9:39:57", "throughput": 62667.69, "total_tokens": 3852218240} {"current_steps": 9860, "total_steps": 15426, "loss": 0.267, "lr": 3.548062949326194e-05, "epoch": 1.9176310415248468, "percentage": 63.92, "elapsed_time": "17:05:23", "remaining_time": "9:38:50", "throughput": 62675.9, "total_tokens": 3856062208} {"current_steps": 9870, "total_steps": 15426, "loss": 0.2705, "lr": 3.547169972957554e-05, "epoch": 1.919575999222017, "percentage": 63.98, "elapsed_time": "17:06:17", "remaining_time": "9:37:42", "throughput": 62684.86, "total_tokens": 3859949696} {"current_steps": 9880, "total_steps": 15426, "loss": 0.2738, "lr": 3.5462776704825e-05, "epoch": 1.9215209569191871, "percentage": 64.05, "elapsed_time": "17:07:10", "remaining_time": "9:36:35", "throughput": 62693.3, "total_tokens": 3863822464} {"current_steps": 9890, "total_steps": 15426, "loss": 0.2719, "lr": 3.5453860410538594e-05, "epoch": 1.923465914616357, "percentage": 64.11, "elapsed_time": "17:08:05", "remaining_time": "9:35:29", "throughput": 62701.72, "total_tokens": 3867799296} {"current_steps": 9900, "total_steps": 15426, "loss": 0.27, "lr": 3.5444950838259455e-05, "epoch": 1.925410872313527, "percentage": 64.18, "elapsed_time": "17:09:02", "remaining_time": "9:34:23", "throughput": 62708.47, "total_tokens": 3871746304} {"current_steps": 9910, "total_steps": 15426, "loss": 0.2698, "lr": 3.543604797954563e-05, "epoch": 1.9273558300106972, "percentage": 64.24, "elapsed_time": "17:09:56", "remaining_time": "9:33:16", "throughput": 62717.37, "total_tokens": 3875707264} {"current_steps": 9920, "total_steps": 15426, "loss": 0.273, "lr": 3.542715182596996e-05, "epoch": 1.9293007877078674, "percentage": 64.31, "elapsed_time": "17:10:47", "remaining_time": "9:32:07", "throughput": 62726.65, "total_tokens": 3879498752} {"current_steps": 9930, "total_steps": 15426, "loss": 0.2706, "lr": 3.5418262369120115e-05, "epoch": 1.9312457454050374, "percentage": 64.37, "elapsed_time": "17:11:41", "remaining_time": "9:31:00", "throughput": 62735.66, "total_tokens": 3883414528} {"current_steps": 9940, "total_steps": 15426, "loss": 0.2728, "lr": 3.5409379600598526e-05, "epoch": 1.9331907031022075, "percentage": 64.44, "elapsed_time": "17:12:35", "remaining_time": "9:29:53", "throughput": 62744.64, "total_tokens": 3887358464} {"current_steps": 9950, "total_steps": 15426, "loss": 0.2685, "lr": 3.540050351202235e-05, "epoch": 1.9351356607993777, "percentage": 64.5, "elapsed_time": "17:13:30", "remaining_time": "9:28:47", "throughput": 62752.42, "total_tokens": 3891328640} {"current_steps": 9960, "total_steps": 15426, "loss": 0.2727, "lr": 3.539163409502347e-05, "epoch": 1.9370806184965477, "percentage": 64.57, "elapsed_time": "17:14:25", "remaining_time": "9:27:41", "throughput": 62759.55, "total_tokens": 3895175680} {"current_steps": 9970, "total_steps": 15426, "loss": 0.2715, "lr": 3.5382771341248416e-05, "epoch": 1.9390255761937176, "percentage": 64.63, "elapsed_time": "17:15:19", "remaining_time": "9:26:34", "throughput": 62768.72, "total_tokens": 3899148928} {"current_steps": 9980, "total_steps": 15426, "loss": 0.272, "lr": 3.537391524235835e-05, "epoch": 1.940970533890888, "percentage": 64.7, "elapsed_time": "17:16:13", "remaining_time": "9:25:27", "throughput": 62778.07, "total_tokens": 3903152640} {"current_steps": 9990, "total_steps": 15426, "loss": 0.2701, "lr": 3.5365065790029055e-05, "epoch": 1.942915491588058, "percentage": 64.76, "elapsed_time": "17:17:07", "remaining_time": "9:24:20", "throughput": 62786.83, "total_tokens": 3907051520} {"current_steps": 10000, "total_steps": 15426, "loss": 0.2693, "lr": 3.535622297595087e-05, "epoch": 1.944860449285228, "percentage": 64.83, "elapsed_time": "17:18:01", "remaining_time": "9:23:14", "throughput": 62795.7, "total_tokens": 3911020672} {"current_steps": 10000, "total_steps": 15426, "eval_loss": 0.26242271065711975, "epoch": 1.944860449285228, "percentage": 64.83, "elapsed_time": "17:18:02", "remaining_time": "9:23:14", "throughput": 62794.52, "total_tokens": 3911020672} {"current_steps": 10010, "total_steps": 15426, "loss": 0.2706, "lr": 3.534738679182869e-05, "epoch": 1.9468054069823981, "percentage": 64.89, "elapsed_time": "17:19:09", "remaining_time": "9:22:14", "throughput": 62790.75, "total_tokens": 3914947584} {"current_steps": 10020, "total_steps": 15426, "loss": 0.272, "lr": 3.533855722938188e-05, "epoch": 1.9487503646795683, "percentage": 64.96, "elapsed_time": "17:20:03", "remaining_time": "9:21:08", "throughput": 62797.82, "total_tokens": 3918832128} {"current_steps": 10030, "total_steps": 15426, "loss": 0.2732, "lr": 3.5329734280344325e-05, "epoch": 1.9506953223767383, "percentage": 65.02, "elapsed_time": "17:20:58", "remaining_time": "9:20:01", "throughput": 62805.37, "total_tokens": 3922725504} {"current_steps": 10040, "total_steps": 15426, "loss": 0.273, "lr": 3.5320917936464294e-05, "epoch": 1.9526402800739084, "percentage": 65.08, "elapsed_time": "17:21:54", "remaining_time": "9:18:56", "throughput": 62811.31, "total_tokens": 3926629504} {"current_steps": 10050, "total_steps": 15426, "loss": 0.2711, "lr": 3.5312108189504505e-05, "epoch": 1.9545852377710786, "percentage": 65.15, "elapsed_time": "17:22:50", "remaining_time": "9:17:50", "throughput": 62818.17, "total_tokens": 3930585472} {"current_steps": 10060, "total_steps": 15426, "loss": 0.2699, "lr": 3.530330503124204e-05, "epoch": 1.9565301954682486, "percentage": 65.21, "elapsed_time": "17:23:43", "remaining_time": "9:16:43", "throughput": 62826.38, "total_tokens": 3934433536} {"current_steps": 10070, "total_steps": 15426, "loss": 0.2727, "lr": 3.5294508453468325e-05, "epoch": 1.9584751531654185, "percentage": 65.28, "elapsed_time": "17:24:33", "remaining_time": "9:15:34", "throughput": 62837.21, "total_tokens": 3938233600} {"current_steps": 10080, "total_steps": 15426, "loss": 0.2677, "lr": 3.528571844798908e-05, "epoch": 1.9604201108625887, "percentage": 65.34, "elapsed_time": "17:25:29", "remaining_time": "9:14:29", "throughput": 62844.51, "total_tokens": 3942226816} {"current_steps": 10090, "total_steps": 15426, "loss": 0.2701, "lr": 3.527693500662431e-05, "epoch": 1.962365068559759, "percentage": 65.41, "elapsed_time": "17:26:21", "remaining_time": "9:13:21", "throughput": 62853.94, "total_tokens": 3946054144} {"current_steps": 10100, "total_steps": 15426, "loss": 0.2716, "lr": 3.5268158121208294e-05, "epoch": 1.9643100262569289, "percentage": 65.47, "elapsed_time": "17:27:11", "remaining_time": "9:12:12", "throughput": 62864.0, "total_tokens": 3949861248} {"current_steps": 10110, "total_steps": 15426, "loss": 0.2671, "lr": 3.525938778358949e-05, "epoch": 1.966254983954099, "percentage": 65.54, "elapsed_time": "17:28:05", "remaining_time": "9:11:06", "throughput": 62872.73, "total_tokens": 3953810176} {"current_steps": 10120, "total_steps": 15426, "loss": 0.2691, "lr": 3.5250623985630537e-05, "epoch": 1.9681999416512692, "percentage": 65.6, "elapsed_time": "17:28:59", "remaining_time": "9:09:59", "throughput": 62880.82, "total_tokens": 3957713408} {"current_steps": 10130, "total_steps": 15426, "loss": 0.2735, "lr": 3.524186671920826e-05, "epoch": 1.9701448993484392, "percentage": 65.67, "elapsed_time": "17:29:52", "remaining_time": "9:08:52", "throughput": 62890.57, "total_tokens": 3961607168} {"current_steps": 10140, "total_steps": 15426, "loss": 0.271, "lr": 3.523311597621358e-05, "epoch": 1.9720898570456091, "percentage": 65.73, "elapsed_time": "17:30:44", "remaining_time": "9:07:45", "throughput": 62899.77, "total_tokens": 3965512704} {"current_steps": 10150, "total_steps": 15426, "loss": 0.2666, "lr": 3.5224371748551505e-05, "epoch": 1.9740348147427793, "percentage": 65.8, "elapsed_time": "17:31:38", "remaining_time": "9:06:38", "throughput": 62909.52, "total_tokens": 3969481856} {"current_steps": 10160, "total_steps": 15426, "loss": 0.2689, "lr": 3.521563402814109e-05, "epoch": 1.9759797724399495, "percentage": 65.86, "elapsed_time": "17:32:31", "remaining_time": "9:05:31", "throughput": 62918.33, "total_tokens": 3973394432} {"current_steps": 10170, "total_steps": 15426, "loss": 0.2706, "lr": 3.5206902806915436e-05, "epoch": 1.9779247301371194, "percentage": 65.93, "elapsed_time": "17:33:25", "remaining_time": "9:04:25", "throughput": 62926.98, "total_tokens": 3977320192} {"current_steps": 10180, "total_steps": 15426, "loss": 0.2675, "lr": 3.5198178076821644e-05, "epoch": 1.9798696878342896, "percentage": 65.99, "elapsed_time": "17:34:18", "remaining_time": "9:03:18", "throughput": 62935.8, "total_tokens": 3981229312} {"current_steps": 10190, "total_steps": 15426, "loss": 0.2715, "lr": 3.5189459829820743e-05, "epoch": 1.9818146455314598, "percentage": 66.06, "elapsed_time": "17:35:15", "remaining_time": "9:02:13", "throughput": 62941.57, "total_tokens": 3985159808} {"current_steps": 10200, "total_steps": 15426, "loss": 0.274, "lr": 3.5180748057887714e-05, "epoch": 1.9837596032286298, "percentage": 66.12, "elapsed_time": "17:36:05", "remaining_time": "9:01:05", "throughput": 62951.33, "total_tokens": 3988951936} {"current_steps": 10210, "total_steps": 15426, "loss": 0.2707, "lr": 3.517204275301144e-05, "epoch": 1.9857045609257997, "percentage": 66.19, "elapsed_time": "17:36:58", "remaining_time": "8:59:58", "throughput": 62959.08, "total_tokens": 3992756992} {"current_steps": 10220, "total_steps": 15426, "loss": 0.2695, "lr": 3.5163343907194676e-05, "epoch": 1.98764951862297, "percentage": 66.25, "elapsed_time": "17:37:52", "remaining_time": "8:58:52", "throughput": 62967.07, "total_tokens": 3996682240} {"current_steps": 10230, "total_steps": 15426, "loss": 0.273, "lr": 3.5154651512453995e-05, "epoch": 1.98959447632014, "percentage": 66.32, "elapsed_time": "17:38:45", "remaining_time": "8:57:45", "throughput": 62974.9, "total_tokens": 4000496768} {"current_steps": 10240, "total_steps": 15426, "loss": 0.2705, "lr": 3.514596556081981e-05, "epoch": 1.99153943401731, "percentage": 66.38, "elapsed_time": "17:39:37", "remaining_time": "8:56:38", "throughput": 62983.82, "total_tokens": 4004326656} {"current_steps": 10250, "total_steps": 15426, "loss": 0.2713, "lr": 3.513728604433628e-05, "epoch": 1.9934843917144802, "percentage": 66.45, "elapsed_time": "17:40:30", "remaining_time": "8:55:31", "throughput": 62992.01, "total_tokens": 4008194432} {"current_steps": 10260, "total_steps": 15426, "loss": 0.268, "lr": 3.5128612955061334e-05, "epoch": 1.9954293494116504, "percentage": 66.51, "elapsed_time": "17:41:21", "remaining_time": "8:54:24", "throughput": 63000.45, "total_tokens": 4011962624} {"current_steps": 10270, "total_steps": 15426, "loss": 0.2728, "lr": 3.5119946285066595e-05, "epoch": 1.9973743071088204, "percentage": 66.58, "elapsed_time": "17:42:16", "remaining_time": "8:53:18", "throughput": 63007.11, "total_tokens": 4015843456} {"current_steps": 10280, "total_steps": 15426, "loss": 0.269, "lr": 3.511128602643739e-05, "epoch": 1.9993192648059903, "percentage": 66.64, "elapsed_time": "17:43:07", "remaining_time": "8:52:11", "throughput": 63017.0, "total_tokens": 4019709568} {"current_steps": 10290, "total_steps": 15426, "loss": 0.2634, "lr": 3.510263217127269e-05, "epoch": 2.001166974618302, "percentage": 66.71, "elapsed_time": "17:44:00", "remaining_time": "8:51:04", "throughput": 63022.25, "total_tokens": 4023355904} {"current_steps": 10300, "total_steps": 15426, "loss": 0.2565, "lr": 3.50939847116851e-05, "epoch": 2.003111932315472, "percentage": 66.77, "elapsed_time": "17:44:53", "remaining_time": "8:49:58", "throughput": 63030.5, "total_tokens": 4027266432} {"current_steps": 10310, "total_steps": 15426, "loss": 0.2556, "lr": 3.508534363980081e-05, "epoch": 2.0050568900126424, "percentage": 66.84, "elapsed_time": "17:45:49", "remaining_time": "8:48:52", "throughput": 63037.83, "total_tokens": 4031206912} {"current_steps": 10320, "total_steps": 15426, "loss": 0.2569, "lr": 3.507670894775958e-05, "epoch": 2.0070018477098124, "percentage": 66.9, "elapsed_time": "17:46:39", "remaining_time": "8:47:44", "throughput": 63047.77, "total_tokens": 4035012096} {"current_steps": 10330, "total_steps": 15426, "loss": 0.257, "lr": 3.506808062771471e-05, "epoch": 2.0089468054069823, "percentage": 66.96, "elapsed_time": "17:47:30", "remaining_time": "8:46:37", "throughput": 63055.97, "total_tokens": 4038786816} {"current_steps": 10340, "total_steps": 15426, "loss": 0.254, "lr": 3.505945867183298e-05, "epoch": 2.0108917631041523, "percentage": 67.03, "elapsed_time": "17:48:24", "remaining_time": "8:45:31", "throughput": 63063.88, "total_tokens": 4042664832} {"current_steps": 10350, "total_steps": 15426, "loss": 0.2569, "lr": 3.505084307229468e-05, "epoch": 2.0128367208013227, "percentage": 67.09, "elapsed_time": "17:49:22", "remaining_time": "8:44:27", "throughput": 63070.41, "total_tokens": 4046745472} {"current_steps": 10360, "total_steps": 15426, "loss": 0.2587, "lr": 3.5042233821293525e-05, "epoch": 2.0147816784984927, "percentage": 67.16, "elapsed_time": "17:50:16", "remaining_time": "8:43:21", "throughput": 63078.77, "total_tokens": 4050673920} {"current_steps": 10370, "total_steps": 15426, "loss": 0.2552, "lr": 3.503363091103664e-05, "epoch": 2.0167266361956626, "percentage": 67.22, "elapsed_time": "17:51:11", "remaining_time": "8:42:16", "throughput": 63086.27, "total_tokens": 4054666624} {"current_steps": 10380, "total_steps": 15426, "loss": 0.26, "lr": 3.5025034333744545e-05, "epoch": 2.018671593892833, "percentage": 67.29, "elapsed_time": "17:52:06", "remaining_time": "8:41:10", "throughput": 63093.97, "total_tokens": 4058610944} {"current_steps": 10390, "total_steps": 15426, "loss": 0.2592, "lr": 3.501644408165112e-05, "epoch": 2.020616551590003, "percentage": 67.35, "elapsed_time": "17:52:59", "remaining_time": "8:40:04", "throughput": 63103.31, "total_tokens": 4062572672} {"current_steps": 10400, "total_steps": 15426, "loss": 0.2559, "lr": 3.500786014700357e-05, "epoch": 2.022561509287173, "percentage": 67.42, "elapsed_time": "17:53:54", "remaining_time": "8:38:58", "throughput": 63110.77, "total_tokens": 4066480512} {"current_steps": 10410, "total_steps": 15426, "loss": 0.2572, "lr": 3.499928252206237e-05, "epoch": 2.024506466984343, "percentage": 67.48, "elapsed_time": "17:54:50", "remaining_time": "8:37:54", "throughput": 63118.07, "total_tokens": 4070489600} {"current_steps": 10420, "total_steps": 15426, "loss": 0.2569, "lr": 3.499071119910131e-05, "epoch": 2.0264514246815133, "percentage": 67.55, "elapsed_time": "17:55:45", "remaining_time": "8:36:49", "throughput": 63125.25, "total_tokens": 4074468480} {"current_steps": 10430, "total_steps": 15426, "loss": 0.2582, "lr": 3.498214617040739e-05, "epoch": 2.0283963823786832, "percentage": 67.61, "elapsed_time": "17:56:39", "remaining_time": "8:35:43", "throughput": 63133.43, "total_tokens": 4078374528} {"current_steps": 10440, "total_steps": 15426, "loss": 0.2519, "lr": 3.49735874282808e-05, "epoch": 2.030341340075853, "percentage": 67.68, "elapsed_time": "17:57:33", "remaining_time": "8:34:37", "throughput": 63142.57, "total_tokens": 4082384256} {"current_steps": 10450, "total_steps": 15426, "loss": 0.2596, "lr": 3.4965034965034965e-05, "epoch": 2.0322862977730236, "percentage": 67.74, "elapsed_time": "17:58:26", "remaining_time": "8:33:31", "throughput": 63151.4, "total_tokens": 4086304000} {"current_steps": 10460, "total_steps": 15426, "loss": 0.255, "lr": 3.495648877299642e-05, "epoch": 2.0342312554701936, "percentage": 67.81, "elapsed_time": "17:59:18", "remaining_time": "8:32:24", "throughput": 63160.49, "total_tokens": 4090164608} {"current_steps": 10470, "total_steps": 15426, "loss": 0.2601, "lr": 3.494794884450483e-05, "epoch": 2.0361762131673635, "percentage": 67.87, "elapsed_time": "18:00:13", "remaining_time": "8:31:19", "throughput": 63166.24, "total_tokens": 4094000896} {"current_steps": 10480, "total_steps": 15426, "loss": 0.2553, "lr": 3.4939415171912954e-05, "epoch": 2.0381211708645335, "percentage": 67.94, "elapsed_time": "18:01:07", "remaining_time": "8:30:14", "throughput": 63174.61, "total_tokens": 4097999360} {"current_steps": 10490, "total_steps": 15426, "loss": 0.2611, "lr": 3.4930887747586616e-05, "epoch": 2.040066128561704, "percentage": 68.0, "elapsed_time": "18:02:03", "remaining_time": "8:29:09", "throughput": 63180.06, "total_tokens": 4101853440} {"current_steps": 10500, "total_steps": 15426, "loss": 0.2584, "lr": 3.492236656390469e-05, "epoch": 2.042011086258874, "percentage": 68.07, "elapsed_time": "18:02:54", "remaining_time": "8:28:02", "throughput": 63190.49, "total_tokens": 4105775744} {"current_steps": 10510, "total_steps": 15426, "loss": 0.26, "lr": 3.4913851613259034e-05, "epoch": 2.043956043956044, "percentage": 68.13, "elapsed_time": "18:03:47", "remaining_time": "8:26:56", "throughput": 63198.2, "total_tokens": 4109621120} {"current_steps": 10520, "total_steps": 15426, "loss": 0.2578, "lr": 3.490534288805452e-05, "epoch": 2.045901001653214, "percentage": 68.2, "elapsed_time": "18:04:41", "remaining_time": "8:25:50", "throughput": 63207.27, "total_tokens": 4113602816} {"current_steps": 10530, "total_steps": 15426, "loss": 0.256, "lr": 3.489684038070891e-05, "epoch": 2.047845959350384, "percentage": 68.26, "elapsed_time": "18:05:34", "remaining_time": "8:24:44", "throughput": 63214.2, "total_tokens": 4117427456} {"current_steps": 10540, "total_steps": 15426, "loss": 0.2616, "lr": 3.488834408365296e-05, "epoch": 2.049790917047554, "percentage": 68.33, "elapsed_time": "18:06:26", "remaining_time": "8:23:38", "throughput": 63222.67, "total_tokens": 4121256320} {"current_steps": 10550, "total_steps": 15426, "loss": 0.2568, "lr": 3.487985398933027e-05, "epoch": 2.0517358747447245, "percentage": 68.39, "elapsed_time": "18:07:21", "remaining_time": "8:22:33", "throughput": 63230.46, "total_tokens": 4125239552} {"current_steps": 10560, "total_steps": 15426, "loss": 0.2556, "lr": 3.4871370090197324e-05, "epoch": 2.0536808324418945, "percentage": 68.46, "elapsed_time": "18:08:16", "remaining_time": "8:21:28", "throughput": 63238.24, "total_tokens": 4129218688} {"current_steps": 10570, "total_steps": 15426, "loss": 0.2551, "lr": 3.486289237872343e-05, "epoch": 2.0556257901390644, "percentage": 68.52, "elapsed_time": "18:09:11", "remaining_time": "8:20:23", "throughput": 63245.93, "total_tokens": 4133211392} {"current_steps": 10580, "total_steps": 15426, "loss": 0.2611, "lr": 3.485442084739075e-05, "epoch": 2.0575707478362344, "percentage": 68.59, "elapsed_time": "18:10:03", "remaining_time": "8:19:17", "throughput": 63254.73, "total_tokens": 4137086336} {"current_steps": 10590, "total_steps": 15426, "loss": 0.2565, "lr": 3.484595548869416e-05, "epoch": 2.059515705533405, "percentage": 68.65, "elapsed_time": "18:10:57", "remaining_time": "8:18:11", "throughput": 63263.15, "total_tokens": 4141036416} {"current_steps": 10600, "total_steps": 15426, "loss": 0.26, "lr": 3.4837496295141335e-05, "epoch": 2.0614606632305748, "percentage": 68.72, "elapsed_time": "18:11:51", "remaining_time": "8:17:06", "throughput": 63270.36, "total_tokens": 4144924416} {"current_steps": 10610, "total_steps": 15426, "loss": 0.261, "lr": 3.482904325925266e-05, "epoch": 2.0634056209277447, "percentage": 68.78, "elapsed_time": "18:12:45", "remaining_time": "8:16:00", "throughput": 63277.9, "total_tokens": 4148837632} {"current_steps": 10620, "total_steps": 15426, "loss": 0.2596, "lr": 3.482059637356124e-05, "epoch": 2.065350578624915, "percentage": 68.84, "elapsed_time": "18:13:39", "remaining_time": "8:14:55", "throughput": 63285.69, "total_tokens": 4152787328} {"current_steps": 10630, "total_steps": 15426, "loss": 0.2566, "lr": 3.481215563061281e-05, "epoch": 2.067295536322085, "percentage": 68.91, "elapsed_time": "18:14:31", "remaining_time": "8:13:49", "throughput": 63296.25, "total_tokens": 4156739456} {"current_steps": 10640, "total_steps": 15426, "loss": 0.2557, "lr": 3.4803721022965785e-05, "epoch": 2.069240494019255, "percentage": 68.97, "elapsed_time": "18:15:25", "remaining_time": "8:12:44", "throughput": 63303.11, "total_tokens": 4160616192} {"current_steps": 10650, "total_steps": 15426, "loss": 0.2545, "lr": 3.479529254319117e-05, "epoch": 2.071185451716425, "percentage": 69.04, "elapsed_time": "18:16:20", "remaining_time": "8:11:39", "throughput": 63309.88, "total_tokens": 4164554368} {"current_steps": 10660, "total_steps": 15426, "loss": 0.2574, "lr": 3.478687018387257e-05, "epoch": 2.0731304094135954, "percentage": 69.1, "elapsed_time": "18:17:12", "remaining_time": "8:10:33", "throughput": 63318.49, "total_tokens": 4168396288} {"current_steps": 10670, "total_steps": 15426, "loss": 0.2554, "lr": 3.477845393760616e-05, "epoch": 2.0750753671107653, "percentage": 69.17, "elapsed_time": "18:18:07", "remaining_time": "8:09:28", "throughput": 63324.95, "total_tokens": 4172308736} {"current_steps": 10680, "total_steps": 15426, "loss": 0.2589, "lr": 3.4770043797000614e-05, "epoch": 2.0770203248079353, "percentage": 69.23, "elapsed_time": "18:19:01", "remaining_time": "8:08:23", "throughput": 63332.19, "total_tokens": 4176251008} {"current_steps": 10690, "total_steps": 15426, "loss": 0.2585, "lr": 3.4761639754677146e-05, "epoch": 2.0789652825051057, "percentage": 69.3, "elapsed_time": "18:19:54", "remaining_time": "8:07:17", "throughput": 63341.24, "total_tokens": 4180187008} {"current_steps": 10700, "total_steps": 15426, "loss": 0.2583, "lr": 3.4753241803269435e-05, "epoch": 2.0809102402022757, "percentage": 69.36, "elapsed_time": "18:20:47", "remaining_time": "8:06:12", "throughput": 63349.07, "total_tokens": 4184063488} {"current_steps": 10710, "total_steps": 15426, "loss": 0.2586, "lr": 3.474484993542361e-05, "epoch": 2.0828551978994456, "percentage": 69.43, "elapsed_time": "18:21:43", "remaining_time": "8:05:07", "throughput": 63355.04, "total_tokens": 4187966336} {"current_steps": 10720, "total_steps": 15426, "loss": 0.2592, "lr": 3.473646414379822e-05, "epoch": 2.0848001555966156, "percentage": 69.49, "elapsed_time": "18:22:36", "remaining_time": "8:04:02", "throughput": 63361.9, "total_tokens": 4191784448} {"current_steps": 10730, "total_steps": 15426, "loss": 0.2612, "lr": 3.472808442106422e-05, "epoch": 2.086745113293786, "percentage": 69.56, "elapsed_time": "18:23:30", "remaining_time": "8:02:56", "throughput": 63368.91, "total_tokens": 4195667328} {"current_steps": 10740, "total_steps": 15426, "loss": 0.257, "lr": 3.4719710759904936e-05, "epoch": 2.088690070990956, "percentage": 69.62, "elapsed_time": "18:24:24", "remaining_time": "8:01:51", "throughput": 63376.53, "total_tokens": 4199591680} {"current_steps": 10750, "total_steps": 15426, "loss": 0.2564, "lr": 3.471134315301603e-05, "epoch": 2.090635028688126, "percentage": 69.69, "elapsed_time": "18:25:19", "remaining_time": "8:00:47", "throughput": 63382.92, "total_tokens": 4203514112} {"current_steps": 10760, "total_steps": 15426, "loss": 0.2579, "lr": 3.470298159310549e-05, "epoch": 2.0925799863852963, "percentage": 69.75, "elapsed_time": "18:26:12", "remaining_time": "7:59:42", "throughput": 63389.92, "total_tokens": 4207377536} {"current_steps": 10770, "total_steps": 15426, "loss": 0.2578, "lr": 3.4694626072893585e-05, "epoch": 2.0945249440824663, "percentage": 69.82, "elapsed_time": "18:27:07", "remaining_time": "7:58:37", "throughput": 63397.14, "total_tokens": 4211319808} {"current_steps": 10780, "total_steps": 15426, "loss": 0.2582, "lr": 3.468627658511285e-05, "epoch": 2.096469901779636, "percentage": 69.88, "elapsed_time": "18:28:03", "remaining_time": "7:57:33", "throughput": 63403.18, "total_tokens": 4215260416} {"current_steps": 10790, "total_steps": 15426, "loss": 0.2596, "lr": 3.467793312250806e-05, "epoch": 2.098414859476806, "percentage": 69.95, "elapsed_time": "18:28:59", "remaining_time": "7:56:29", "throughput": 63409.21, "total_tokens": 4219244544} {"current_steps": 10800, "total_steps": 15426, "loss": 0.257, "lr": 3.466959567783619e-05, "epoch": 2.1003598171739766, "percentage": 70.01, "elapsed_time": "18:29:54", "remaining_time": "7:55:24", "throughput": 63415.94, "total_tokens": 4223160576} {"current_steps": 10810, "total_steps": 15426, "loss": 0.2572, "lr": 3.466126424386642e-05, "epoch": 2.1023047748711465, "percentage": 70.08, "elapsed_time": "18:30:50", "remaining_time": "7:54:20", "throughput": 63422.69, "total_tokens": 4227144448} {"current_steps": 10820, "total_steps": 15426, "loss": 0.2576, "lr": 3.4652938813380056e-05, "epoch": 2.1042497325683165, "percentage": 70.14, "elapsed_time": "18:31:45", "remaining_time": "7:53:16", "throughput": 63430.17, "total_tokens": 4231143680} {"current_steps": 10830, "total_steps": 15426, "loss": 0.2584, "lr": 3.464461937917057e-05, "epoch": 2.106194690265487, "percentage": 70.21, "elapsed_time": "18:32:37", "remaining_time": "7:52:10", "throughput": 63438.34, "total_tokens": 4234977280} {"current_steps": 10840, "total_steps": 15426, "loss": 0.258, "lr": 3.4636305934043525e-05, "epoch": 2.108139647962657, "percentage": 70.27, "elapsed_time": "18:33:30", "remaining_time": "7:51:05", "throughput": 63446.32, "total_tokens": 4238880768} {"current_steps": 10850, "total_steps": 15426, "loss": 0.2547, "lr": 3.4627998470816544e-05, "epoch": 2.110084605659827, "percentage": 70.34, "elapsed_time": "18:34:28", "remaining_time": "7:50:01", "throughput": 63451.65, "total_tokens": 4242920064} {"current_steps": 10860, "total_steps": 15426, "loss": 0.2572, "lr": 3.4619696982319334e-05, "epoch": 2.112029563356997, "percentage": 70.4, "elapsed_time": "18:35:25", "remaining_time": "7:48:58", "throughput": 63457.54, "total_tokens": 4246931712} {"current_steps": 10870, "total_steps": 15426, "loss": 0.255, "lr": 3.461140146139361e-05, "epoch": 2.113974521054167, "percentage": 70.47, "elapsed_time": "18:36:19", "remaining_time": "7:47:53", "throughput": 63464.82, "total_tokens": 4250815104} {"current_steps": 10880, "total_steps": 15426, "loss": 0.2566, "lr": 3.460311190089309e-05, "epoch": 2.115919478751337, "percentage": 70.53, "elapsed_time": "18:37:14", "remaining_time": "7:46:49", "throughput": 63470.93, "total_tokens": 4254743808} {"current_steps": 10890, "total_steps": 15426, "loss": 0.2554, "lr": 3.459482829368348e-05, "epoch": 2.117864436448507, "percentage": 70.6, "elapsed_time": "18:38:07", "remaining_time": "7:45:43", "throughput": 63479.46, "total_tokens": 4258674304} {"current_steps": 10900, "total_steps": 15426, "loss": 0.2583, "lr": 3.4586550632642425e-05, "epoch": 2.1198093941456775, "percentage": 70.66, "elapsed_time": "18:38:58", "remaining_time": "7:44:38", "throughput": 63488.02, "total_tokens": 4262520448} {"current_steps": 10910, "total_steps": 15426, "loss": 0.2587, "lr": 3.457827891065949e-05, "epoch": 2.1217543518428474, "percentage": 70.72, "elapsed_time": "18:39:51", "remaining_time": "7:43:32", "throughput": 63495.19, "total_tokens": 4266326912} {"current_steps": 10920, "total_steps": 15426, "loss": 0.2584, "lr": 3.457001312063614e-05, "epoch": 2.1236993095400174, "percentage": 70.79, "elapsed_time": "18:40:45", "remaining_time": "7:42:28", "throughput": 63503.04, "total_tokens": 4270293376} {"current_steps": 10930, "total_steps": 15426, "loss": 0.2573, "lr": 3.45617532554857e-05, "epoch": 2.1256442672371874, "percentage": 70.85, "elapsed_time": "18:41:38", "remaining_time": "7:41:23", "throughput": 63510.27, "total_tokens": 4274166400} {"current_steps": 10940, "total_steps": 15426, "loss": 0.2586, "lr": 3.455349930813339e-05, "epoch": 2.1275892249343578, "percentage": 70.92, "elapsed_time": "18:42:33", "remaining_time": "7:40:18", "throughput": 63516.33, "total_tokens": 4278019712} {"current_steps": 10950, "total_steps": 15426, "loss": 0.2591, "lr": 3.45452512715162e-05, "epoch": 2.1295341826315277, "percentage": 70.98, "elapsed_time": "18:43:24", "remaining_time": "7:39:12", "throughput": 63525.02, "total_tokens": 4281841664} {"current_steps": 10960, "total_steps": 15426, "loss": 0.2583, "lr": 3.4537009138582935e-05, "epoch": 2.1314791403286977, "percentage": 71.05, "elapsed_time": "18:44:16", "remaining_time": "7:38:07", "throughput": 63533.68, "total_tokens": 4285733760} {"current_steps": 10970, "total_steps": 15426, "loss": 0.2572, "lr": 3.4528772902294174e-05, "epoch": 2.133424098025868, "percentage": 71.11, "elapsed_time": "18:45:13", "remaining_time": "7:37:03", "throughput": 63538.84, "total_tokens": 4289714176} {"current_steps": 10980, "total_steps": 15426, "loss": 0.2583, "lr": 3.452054255562222e-05, "epoch": 2.135369055723038, "percentage": 71.18, "elapsed_time": "18:46:09", "remaining_time": "7:36:00", "throughput": 63544.78, "total_tokens": 4293717120} {"current_steps": 10990, "total_steps": 15426, "loss": 0.2574, "lr": 3.451231809155115e-05, "epoch": 2.137314013420208, "percentage": 71.24, "elapsed_time": "18:47:06", "remaining_time": "7:34:56", "throughput": 63550.84, "total_tokens": 4297718784} {"current_steps": 11000, "total_steps": 15426, "loss": 0.2566, "lr": 3.450409950307666e-05, "epoch": 2.1392589711173784, "percentage": 71.31, "elapsed_time": "18:48:03", "remaining_time": "7:33:53", "throughput": 63555.5, "total_tokens": 4301648384} {"current_steps": 11010, "total_steps": 15426, "loss": 0.2588, "lr": 3.449588678320619e-05, "epoch": 2.1412039288145484, "percentage": 71.37, "elapsed_time": "18:48:57", "remaining_time": "7:32:49", "throughput": 63563.23, "total_tokens": 4305642880} {"current_steps": 11020, "total_steps": 15426, "loss": 0.2559, "lr": 3.4487679924958767e-05, "epoch": 2.1431488865117183, "percentage": 71.44, "elapsed_time": "18:49:51", "remaining_time": "7:31:44", "throughput": 63571.35, "total_tokens": 4309619328} {"current_steps": 11030, "total_steps": 15426, "loss": 0.2542, "lr": 3.4479478921365076e-05, "epoch": 2.1450938442088883, "percentage": 71.5, "elapsed_time": "18:50:44", "remaining_time": "7:30:39", "throughput": 63579.89, "total_tokens": 4313570048} {"current_steps": 11040, "total_steps": 15426, "loss": 0.2595, "lr": 3.447128376546738e-05, "epoch": 2.1470388019060587, "percentage": 71.57, "elapsed_time": "18:51:37", "remaining_time": "7:29:34", "throughput": 63588.08, "total_tokens": 4317485440} {"current_steps": 11050, "total_steps": 15426, "loss": 0.258, "lr": 3.4463094450319505e-05, "epoch": 2.1489837596032286, "percentage": 71.63, "elapsed_time": "18:52:31", "remaining_time": "7:28:30", "throughput": 63595.35, "total_tokens": 4321412224} {"current_steps": 11060, "total_steps": 15426, "loss": 0.2583, "lr": 3.4454910968986855e-05, "epoch": 2.1509287173003986, "percentage": 71.7, "elapsed_time": "18:53:25", "remaining_time": "7:27:25", "throughput": 63602.25, "total_tokens": 4325328512} {"current_steps": 11070, "total_steps": 15426, "loss": 0.255, "lr": 3.4446733314546336e-05, "epoch": 2.152873674997569, "percentage": 71.76, "elapsed_time": "18:54:19", "remaining_time": "7:26:21", "throughput": 63610.14, "total_tokens": 4329304064} {"current_steps": 11080, "total_steps": 15426, "loss": 0.2571, "lr": 3.443856148008633e-05, "epoch": 2.154818632694739, "percentage": 71.83, "elapsed_time": "18:55:17", "remaining_time": "7:25:18", "throughput": 63616.03, "total_tokens": 4333336320} {"current_steps": 11090, "total_steps": 15426, "loss": 0.2578, "lr": 3.443039545870672e-05, "epoch": 2.156763590391909, "percentage": 71.89, "elapsed_time": "18:56:10", "remaining_time": "7:24:13", "throughput": 63623.05, "total_tokens": 4337215872} {"current_steps": 11100, "total_steps": 15426, "loss": 0.261, "lr": 3.442223524351883e-05, "epoch": 2.158708548089079, "percentage": 71.96, "elapsed_time": "18:57:03", "remaining_time": "7:23:08", "throughput": 63631.5, "total_tokens": 4341182080} {"current_steps": 11110, "total_steps": 15426, "loss": 0.2576, "lr": 3.44140808276454e-05, "epoch": 2.1606535057862493, "percentage": 72.02, "elapsed_time": "18:57:55", "remaining_time": "7:22:03", "throughput": 63639.4, "total_tokens": 4344996224} {"current_steps": 11120, "total_steps": 15426, "loss": 0.2565, "lr": 3.4405932204220575e-05, "epoch": 2.162598463483419, "percentage": 72.09, "elapsed_time": "18:58:49", "remaining_time": "7:20:59", "throughput": 63645.78, "total_tokens": 4348854272} {"current_steps": 11130, "total_steps": 15426, "loss": 0.2571, "lr": 3.4397789366389876e-05, "epoch": 2.164543421180589, "percentage": 72.15, "elapsed_time": "18:59:44", "remaining_time": "7:19:55", "throughput": 63651.81, "total_tokens": 4352799360} {"current_steps": 11140, "total_steps": 15426, "loss": 0.2579, "lr": 3.438965230731016e-05, "epoch": 2.1664883788777596, "percentage": 72.22, "elapsed_time": "19:00:40", "remaining_time": "7:18:51", "throughput": 63657.75, "total_tokens": 4356758784} {"current_steps": 11150, "total_steps": 15426, "loss": 0.2566, "lr": 3.438152102014964e-05, "epoch": 2.1684333365749295, "percentage": 72.28, "elapsed_time": "19:01:35", "remaining_time": "7:17:47", "throughput": 63664.66, "total_tokens": 4360728576} {"current_steps": 11160, "total_steps": 15426, "loss": 0.2582, "lr": 3.437339549808778e-05, "epoch": 2.1703782942720995, "percentage": 72.35, "elapsed_time": "19:02:31", "remaining_time": "7:16:44", "throughput": 63671.91, "total_tokens": 4364807296} {"current_steps": 11170, "total_steps": 15426, "loss": 0.2592, "lr": 3.43652757343154e-05, "epoch": 2.17232325196927, "percentage": 72.41, "elapsed_time": "19:03:26", "remaining_time": "7:15:40", "throughput": 63678.6, "total_tokens": 4368737920} {"current_steps": 11180, "total_steps": 15426, "loss": 0.2613, "lr": 3.435716172203449e-05, "epoch": 2.17426820966644, "percentage": 72.48, "elapsed_time": "19:04:21", "remaining_time": "7:14:36", "throughput": 63684.61, "total_tokens": 4372677248} {"current_steps": 11190, "total_steps": 15426, "loss": 0.2587, "lr": 3.434905345445833e-05, "epoch": 2.17621316736361, "percentage": 72.54, "elapsed_time": "19:05:15", "remaining_time": "7:13:32", "throughput": 63691.24, "total_tokens": 4376558080} {"current_steps": 11200, "total_steps": 15426, "loss": 0.2563, "lr": 3.4340950924811374e-05, "epoch": 2.1781581250607798, "percentage": 72.6, "elapsed_time": "19:06:09", "remaining_time": "7:12:28", "throughput": 63697.16, "total_tokens": 4380447232} {"current_steps": 11210, "total_steps": 15426, "loss": 0.26, "lr": 3.433285412632927e-05, "epoch": 2.18010308275795, "percentage": 72.67, "elapsed_time": "19:07:01", "remaining_time": "7:11:23", "throughput": 63705.46, "total_tokens": 4384297600} {"current_steps": 11220, "total_steps": 15426, "loss": 0.2639, "lr": 3.4324763052258835e-05, "epoch": 2.18204804045512, "percentage": 72.73, "elapsed_time": "19:07:55", "remaining_time": "7:10:19", "throughput": 63711.81, "total_tokens": 4388186240} {"current_steps": 11230, "total_steps": 15426, "loss": 0.2608, "lr": 3.4316677695858003e-05, "epoch": 2.18399299815229, "percentage": 72.8, "elapsed_time": "19:08:48", "remaining_time": "7:09:14", "throughput": 63719.33, "total_tokens": 4392080384} {"current_steps": 11240, "total_steps": 15426, "loss": 0.2594, "lr": 3.430859805039583e-05, "epoch": 2.18593795584946, "percentage": 72.86, "elapsed_time": "19:09:42", "remaining_time": "7:08:10", "throughput": 63726.61, "total_tokens": 4396044928} {"current_steps": 11250, "total_steps": 15426, "loss": 0.2589, "lr": 3.430052410915246e-05, "epoch": 2.1878829135466304, "percentage": 72.93, "elapsed_time": "19:10:36", "remaining_time": "7:07:06", "throughput": 63733.99, "total_tokens": 4399949184} {"current_steps": 11260, "total_steps": 15426, "loss": 0.2596, "lr": 3.4292455865419086e-05, "epoch": 2.1898278712438004, "percentage": 72.99, "elapsed_time": "19:11:31", "remaining_time": "7:06:02", "throughput": 63739.78, "total_tokens": 4403893632} {"current_steps": 11270, "total_steps": 15426, "loss": 0.2597, "lr": 3.4284393312497973e-05, "epoch": 2.1917728289409704, "percentage": 73.06, "elapsed_time": "19:12:25", "remaining_time": "7:04:58", "throughput": 63746.61, "total_tokens": 4407764992} {"current_steps": 11280, "total_steps": 15426, "loss": 0.2573, "lr": 3.427633644370238e-05, "epoch": 2.1937177866381408, "percentage": 73.12, "elapsed_time": "19:13:22", "remaining_time": "7:03:55", "throughput": 63750.87, "total_tokens": 4411725440} {"current_steps": 11290, "total_steps": 15426, "loss": 0.2591, "lr": 3.4268285252356564e-05, "epoch": 2.1956627443353107, "percentage": 73.19, "elapsed_time": "19:14:17", "remaining_time": "7:02:51", "throughput": 63757.16, "total_tokens": 4415649920} {"current_steps": 11300, "total_steps": 15426, "loss": 0.2563, "lr": 3.426023973179575e-05, "epoch": 2.1976077020324807, "percentage": 73.25, "elapsed_time": "19:15:10", "remaining_time": "7:01:47", "throughput": 63765.35, "total_tokens": 4419617280} {"current_steps": 11310, "total_steps": 15426, "loss": 0.2575, "lr": 3.425219987536614e-05, "epoch": 2.199552659729651, "percentage": 73.32, "elapsed_time": "19:16:06", "remaining_time": "7:00:44", "throughput": 63771.84, "total_tokens": 4423650944} {"current_steps": 11320, "total_steps": 15426, "loss": 0.2575, "lr": 3.4244165676424815e-05, "epoch": 2.201497617426821, "percentage": 73.38, "elapsed_time": "19:17:02", "remaining_time": "6:59:40", "throughput": 63778.51, "total_tokens": 4427632128} {"current_steps": 11330, "total_steps": 15426, "loss": 0.2594, "lr": 3.423613712833979e-05, "epoch": 2.203442575123991, "percentage": 73.45, "elapsed_time": "19:17:56", "remaining_time": "6:58:37", "throughput": 63784.89, "total_tokens": 4431553792} {"current_steps": 11340, "total_steps": 15426, "loss": 0.259, "lr": 3.422811422448995e-05, "epoch": 2.205387532821161, "percentage": 73.51, "elapsed_time": "19:18:48", "remaining_time": "6:57:32", "throughput": 63792.9, "total_tokens": 4435449984} {"current_steps": 11350, "total_steps": 15426, "loss": 0.258, "lr": 3.422009695826503e-05, "epoch": 2.2073324905183314, "percentage": 73.58, "elapsed_time": "19:19:42", "remaining_time": "6:56:28", "throughput": 63801.04, "total_tokens": 4439442048} {"current_steps": 11360, "total_steps": 15426, "loss": 0.2569, "lr": 3.4212085323065626e-05, "epoch": 2.2092774482155013, "percentage": 73.64, "elapsed_time": "19:20:40", "remaining_time": "6:55:25", "throughput": 63806.02, "total_tokens": 4443477888} {"current_steps": 11370, "total_steps": 15426, "loss": 0.2587, "lr": 3.4204079312303103e-05, "epoch": 2.2112224059126713, "percentage": 73.71, "elapsed_time": "19:21:32", "remaining_time": "6:54:21", "throughput": 63813.04, "total_tokens": 4447297024} {"current_steps": 11380, "total_steps": 15426, "loss": 0.2579, "lr": 3.419607891939964e-05, "epoch": 2.2131673636098417, "percentage": 73.77, "elapsed_time": "19:22:27", "remaining_time": "6:53:17", "throughput": 63818.96, "total_tokens": 4451234560} {"current_steps": 11390, "total_steps": 15426, "loss": 0.2566, "lr": 3.4188084137788166e-05, "epoch": 2.2151123213070116, "percentage": 73.84, "elapsed_time": "19:23:22", "remaining_time": "6:52:14", "throughput": 63825.42, "total_tokens": 4455151616} {"current_steps": 11400, "total_steps": 15426, "loss": 0.2615, "lr": 3.418009496091238e-05, "epoch": 2.2170572790041816, "percentage": 73.9, "elapsed_time": "19:24:14", "remaining_time": "6:51:09", "throughput": 63832.41, "total_tokens": 4458984832} {"current_steps": 11410, "total_steps": 15426, "loss": 0.2577, "lr": 3.417211138222666e-05, "epoch": 2.2190022367013515, "percentage": 73.97, "elapsed_time": "19:25:09", "remaining_time": "6:50:06", "throughput": 63838.65, "total_tokens": 4462896768} {"current_steps": 11420, "total_steps": 15426, "loss": 0.2572, "lr": 3.416413339519612e-05, "epoch": 2.220947194398522, "percentage": 74.03, "elapsed_time": "19:26:01", "remaining_time": "6:49:01", "throughput": 63845.77, "total_tokens": 4466714624} {"current_steps": 11430, "total_steps": 15426, "loss": 0.2568, "lr": 3.4156160993296524e-05, "epoch": 2.222892152095692, "percentage": 74.1, "elapsed_time": "19:26:56", "remaining_time": "6:47:58", "throughput": 63852.43, "total_tokens": 4470698112} {"current_steps": 11440, "total_steps": 15426, "loss": 0.2584, "lr": 3.4148194170014295e-05, "epoch": 2.224837109792862, "percentage": 74.16, "elapsed_time": "19:27:50", "remaining_time": "6:46:54", "throughput": 63858.49, "total_tokens": 4474604544} {"current_steps": 11450, "total_steps": 15426, "loss": 0.2567, "lr": 3.4140232918846484e-05, "epoch": 2.2267820674900323, "percentage": 74.23, "elapsed_time": "19:28:45", "remaining_time": "6:45:50", "throughput": 63865.17, "total_tokens": 4478562560} {"current_steps": 11460, "total_steps": 15426, "loss": 0.2603, "lr": 3.4132277233300753e-05, "epoch": 2.2287270251872022, "percentage": 74.29, "elapsed_time": "19:29:40", "remaining_time": "6:44:47", "throughput": 63872.19, "total_tokens": 4482602624} {"current_steps": 11470, "total_steps": 15426, "loss": 0.2551, "lr": 3.4124327106895356e-05, "epoch": 2.230671982884372, "percentage": 74.35, "elapsed_time": "19:30:35", "remaining_time": "6:43:44", "throughput": 63879.31, "total_tokens": 4486565504} {"current_steps": 11480, "total_steps": 15426, "loss": 0.258, "lr": 3.4116382533159097e-05, "epoch": 2.2326169405815426, "percentage": 74.42, "elapsed_time": "19:31:31", "remaining_time": "6:42:41", "throughput": 63884.77, "total_tokens": 4490580480} {"current_steps": 11490, "total_steps": 15426, "loss": 0.2592, "lr": 3.4108443505631335e-05, "epoch": 2.2345618982787125, "percentage": 74.48, "elapsed_time": "19:32:24", "remaining_time": "6:41:37", "throughput": 63891.97, "total_tokens": 4494463232} {"current_steps": 11500, "total_steps": 15426, "loss": 0.258, "lr": 3.410051001786192e-05, "epoch": 2.2365068559758825, "percentage": 74.55, "elapsed_time": "19:33:19", "remaining_time": "6:40:33", "throughput": 63898.49, "total_tokens": 4498430720} {"current_steps": 11510, "total_steps": 15426, "loss": 0.2612, "lr": 3.409258206341124e-05, "epoch": 2.2384518136730525, "percentage": 74.61, "elapsed_time": "19:34:14", "remaining_time": "6:39:30", "throughput": 63904.43, "total_tokens": 4502344576} {"current_steps": 11520, "total_steps": 15426, "loss": 0.257, "lr": 3.4084659635850134e-05, "epoch": 2.240396771370223, "percentage": 74.68, "elapsed_time": "19:35:06", "remaining_time": "6:38:26", "throughput": 63911.54, "total_tokens": 4506210304} {"current_steps": 11530, "total_steps": 15426, "loss": 0.2587, "lr": 3.40767427287599e-05, "epoch": 2.242341729067393, "percentage": 74.74, "elapsed_time": "19:36:01", "remaining_time": "6:37:22", "throughput": 63917.29, "total_tokens": 4510082560} {"current_steps": 11540, "total_steps": 15426, "loss": 0.26, "lr": 3.406883133573224e-05, "epoch": 2.2442866867645628, "percentage": 74.81, "elapsed_time": "19:36:56", "remaining_time": "6:36:19", "throughput": 63923.34, "total_tokens": 4514034944} {"current_steps": 11550, "total_steps": 15426, "loss": 0.258, "lr": 3.406092545036932e-05, "epoch": 2.2462316444617327, "percentage": 74.87, "elapsed_time": "19:37:49", "remaining_time": "6:35:15", "throughput": 63929.5, "total_tokens": 4517840896} {"current_steps": 11560, "total_steps": 15426, "loss": 0.2612, "lr": 3.405302506628365e-05, "epoch": 2.248176602158903, "percentage": 74.94, "elapsed_time": "19:38:41", "remaining_time": "6:34:11", "throughput": 63936.9, "total_tokens": 4521683840} {"current_steps": 11570, "total_steps": 15426, "loss": 0.2582, "lr": 3.404513017709813e-05, "epoch": 2.250121559856073, "percentage": 75.0, "elapsed_time": "19:39:33", "remaining_time": "6:33:07", "throughput": 63943.67, "total_tokens": 4525534848} {"current_steps": 11580, "total_steps": 15426, "loss": 0.2562, "lr": 3.403724077644598e-05, "epoch": 2.252066517553243, "percentage": 75.07, "elapsed_time": "19:40:29", "remaining_time": "6:32:04", "throughput": 63949.78, "total_tokens": 4529544832} {"current_steps": 11590, "total_steps": 15426, "loss": 0.2567, "lr": 3.402935685797077e-05, "epoch": 2.2540114752504135, "percentage": 75.13, "elapsed_time": "19:41:27", "remaining_time": "6:31:01", "throughput": 63954.46, "total_tokens": 4533550720} {"current_steps": 11600, "total_steps": 15426, "loss": 0.2584, "lr": 3.4021478415326355e-05, "epoch": 2.2559564329475834, "percentage": 75.2, "elapsed_time": "19:42:19", "remaining_time": "6:29:57", "throughput": 63961.42, "total_tokens": 4537408384} {"current_steps": 11610, "total_steps": 15426, "loss": 0.2585, "lr": 3.401360544217687e-05, "epoch": 2.2579013906447534, "percentage": 75.26, "elapsed_time": "19:43:11", "remaining_time": "6:28:53", "throughput": 63968.84, "total_tokens": 4541237888} {"current_steps": 11620, "total_steps": 15426, "loss": 0.2607, "lr": 3.400573793219672e-05, "epoch": 2.2598463483419238, "percentage": 75.33, "elapsed_time": "19:44:07", "remaining_time": "6:27:50", "throughput": 63973.22, "total_tokens": 4545135232} {"current_steps": 11630, "total_steps": 15426, "loss": 0.2581, "lr": 3.3997875879070546e-05, "epoch": 2.2617913060390937, "percentage": 75.39, "elapsed_time": "19:45:01", "remaining_time": "6:26:47", "throughput": 63979.64, "total_tokens": 4549057280} {"current_steps": 11640, "total_steps": 15426, "loss": 0.2601, "lr": 3.399001927649318e-05, "epoch": 2.2637362637362637, "percentage": 75.46, "elapsed_time": "19:45:57", "remaining_time": "6:25:44", "throughput": 63984.82, "total_tokens": 4553016832} {"current_steps": 11650, "total_steps": 15426, "loss": 0.2564, "lr": 3.398216811816968e-05, "epoch": 2.2656812214334336, "percentage": 75.52, "elapsed_time": "19:46:48", "remaining_time": "6:24:40", "throughput": 63993.3, "total_tokens": 4556864384} {"current_steps": 11660, "total_steps": 15426, "loss": 0.2579, "lr": 3.397432239781527e-05, "epoch": 2.267626179130604, "percentage": 75.59, "elapsed_time": "19:47:43", "remaining_time": "6:23:37", "throughput": 63999.01, "total_tokens": 4560798848} {"current_steps": 11670, "total_steps": 15426, "loss": 0.2619, "lr": 3.396648210915531e-05, "epoch": 2.269571136827774, "percentage": 75.65, "elapsed_time": "19:48:37", "remaining_time": "6:22:33", "throughput": 64004.74, "total_tokens": 4564676224} {"current_steps": 11680, "total_steps": 15426, "loss": 0.2597, "lr": 3.3958647245925315e-05, "epoch": 2.271516094524944, "percentage": 75.72, "elapsed_time": "19:49:33", "remaining_time": "6:21:30", "throughput": 64010.26, "total_tokens": 4568644096} {"current_steps": 11690, "total_steps": 15426, "loss": 0.2587, "lr": 3.3950817801870885e-05, "epoch": 2.273461052222114, "percentage": 75.78, "elapsed_time": "19:50:26", "remaining_time": "6:20:27", "throughput": 64017.23, "total_tokens": 4572520832} {"current_steps": 11700, "total_steps": 15426, "loss": 0.2593, "lr": 3.3942993770747735e-05, "epoch": 2.2754060099192843, "percentage": 75.85, "elapsed_time": "19:51:18", "remaining_time": "6:19:23", "throughput": 64024.72, "total_tokens": 4576409216} {"current_steps": 11710, "total_steps": 15426, "loss": 0.2604, "lr": 3.3935175146321626e-05, "epoch": 2.2773509676164543, "percentage": 75.91, "elapsed_time": "19:52:10", "remaining_time": "6:18:19", "throughput": 64032.52, "total_tokens": 4580264576} {"current_steps": 11720, "total_steps": 15426, "loss": 0.2573, "lr": 3.392736192236839e-05, "epoch": 2.2792959253136242, "percentage": 75.98, "elapsed_time": "19:53:04", "remaining_time": "6:17:15", "throughput": 64037.71, "total_tokens": 4584104832} {"current_steps": 11730, "total_steps": 15426, "loss": 0.2555, "lr": 3.391955409267387e-05, "epoch": 2.2812408830107946, "percentage": 76.04, "elapsed_time": "19:54:00", "remaining_time": "6:16:13", "throughput": 64044.39, "total_tokens": 4588166656} {"current_steps": 11740, "total_steps": 15426, "loss": 0.2601, "lr": 3.3911751651033896e-05, "epoch": 2.2831858407079646, "percentage": 76.11, "elapsed_time": "19:54:54", "remaining_time": "6:15:09", "throughput": 64050.87, "total_tokens": 4592088704} {"current_steps": 11750, "total_steps": 15426, "loss": 0.2594, "lr": 3.3903954591254334e-05, "epoch": 2.2851307984051346, "percentage": 76.17, "elapsed_time": "19:55:49", "remaining_time": "6:14:06", "throughput": 64057.2, "total_tokens": 4596073600} {"current_steps": 11760, "total_steps": 15426, "loss": 0.2562, "lr": 3.389616290715097e-05, "epoch": 2.287075756102305, "percentage": 76.23, "elapsed_time": "19:56:43", "remaining_time": "6:13:03", "throughput": 64063.92, "total_tokens": 4599991552} {"current_steps": 11770, "total_steps": 15426, "loss": 0.2572, "lr": 3.388837659254955e-05, "epoch": 2.289020713799475, "percentage": 76.3, "elapsed_time": "19:57:34", "remaining_time": "6:11:59", "throughput": 64072.15, "total_tokens": 4603873280} {"current_steps": 11780, "total_steps": 15426, "loss": 0.2569, "lr": 3.3880595641285746e-05, "epoch": 2.290965671496645, "percentage": 76.36, "elapsed_time": "19:58:27", "remaining_time": "6:10:55", "throughput": 64079.58, "total_tokens": 4607779328} {"current_steps": 11790, "total_steps": 15426, "loss": 0.2584, "lr": 3.387282004720513e-05, "epoch": 2.2929106291938153, "percentage": 76.43, "elapsed_time": "19:59:22", "remaining_time": "6:09:52", "throughput": 64084.58, "total_tokens": 4611671808} {"current_steps": 11800, "total_steps": 15426, "loss": 0.259, "lr": 3.386504980416316e-05, "epoch": 2.2948555868909852, "percentage": 76.49, "elapsed_time": "20:00:16", "remaining_time": "6:08:49", "throughput": 64090.7, "total_tokens": 4615559424} {"current_steps": 11810, "total_steps": 15426, "loss": 0.2567, "lr": 3.385728490602515e-05, "epoch": 2.296800544588155, "percentage": 76.56, "elapsed_time": "20:01:11", "remaining_time": "6:07:46", "throughput": 64096.87, "total_tokens": 4619529472} {"current_steps": 11820, "total_steps": 15426, "loss": 0.2588, "lr": 3.384952534666625e-05, "epoch": 2.298745502285325, "percentage": 76.62, "elapsed_time": "20:02:06", "remaining_time": "6:06:43", "throughput": 64102.35, "total_tokens": 4623448576} {"current_steps": 11830, "total_steps": 15426, "loss": 0.2595, "lr": 3.3841771119971455e-05, "epoch": 2.3006904599824956, "percentage": 76.69, "elapsed_time": "20:02:58", "remaining_time": "6:05:40", "throughput": 64109.3, "total_tokens": 4627341952} {"current_steps": 11840, "total_steps": 15426, "loss": 0.2584, "lr": 3.383402221983554e-05, "epoch": 2.3026354176796655, "percentage": 76.75, "elapsed_time": "20:03:51", "remaining_time": "6:04:36", "throughput": 64116.83, "total_tokens": 4631254016} {"current_steps": 11850, "total_steps": 15426, "loss": 0.2567, "lr": 3.3826278640163064e-05, "epoch": 2.3045803753768355, "percentage": 76.82, "elapsed_time": "20:04:40", "remaining_time": "6:03:32", "throughput": 64125.67, "total_tokens": 4635048448} {"current_steps": 11860, "total_steps": 15426, "loss": 0.2584, "lr": 3.3818540374868354e-05, "epoch": 2.3065253330740054, "percentage": 76.88, "elapsed_time": "20:05:37", "remaining_time": "6:02:30", "throughput": 64129.92, "total_tokens": 4638989568} {"current_steps": 11870, "total_steps": 15426, "loss": 0.257, "lr": 3.381080741787547e-05, "epoch": 2.308470290771176, "percentage": 76.95, "elapsed_time": "20:06:31", "remaining_time": "6:01:26", "throughput": 64136.46, "total_tokens": 4642928512} {"current_steps": 11880, "total_steps": 15426, "loss": 0.2573, "lr": 3.38030797631182e-05, "epoch": 2.310415248468346, "percentage": 77.01, "elapsed_time": "20:07:26", "remaining_time": "6:00:24", "throughput": 64141.34, "total_tokens": 4646818816} {"current_steps": 11890, "total_steps": 15426, "loss": 0.2568, "lr": 3.379535740454003e-05, "epoch": 2.3123602061655157, "percentage": 77.08, "elapsed_time": "20:08:21", "remaining_time": "5:59:21", "throughput": 64147.77, "total_tokens": 4650831488} {"current_steps": 11900, "total_steps": 15426, "loss": 0.2564, "lr": 3.3787640336094126e-05, "epoch": 2.314305163862686, "percentage": 77.14, "elapsed_time": "20:09:16", "remaining_time": "5:58:18", "throughput": 64153.91, "total_tokens": 4654752512} {"current_steps": 11910, "total_steps": 15426, "loss": 0.2586, "lr": 3.3779928551743325e-05, "epoch": 2.316250121559856, "percentage": 77.21, "elapsed_time": "20:10:08", "remaining_time": "5:57:15", "throughput": 64160.82, "total_tokens": 4658643328} {"current_steps": 11920, "total_steps": 15426, "loss": 0.2585, "lr": 3.3772222045460084e-05, "epoch": 2.318195079257026, "percentage": 77.27, "elapsed_time": "20:11:04", "remaining_time": "5:56:12", "throughput": 64165.98, "total_tokens": 4662556928} {"current_steps": 11930, "total_steps": 15426, "loss": 0.2612, "lr": 3.37645208112265e-05, "epoch": 2.3201400369541965, "percentage": 77.34, "elapsed_time": "20:11:53", "remaining_time": "5:55:08", "throughput": 64174.45, "total_tokens": 4666350080} {"current_steps": 11940, "total_steps": 15426, "loss": 0.2604, "lr": 3.3756824843034255e-05, "epoch": 2.3220849946513664, "percentage": 77.4, "elapsed_time": "20:12:47", "remaining_time": "5:54:05", "throughput": 64179.41, "total_tokens": 4670187008} {"current_steps": 11950, "total_steps": 15426, "loss": 0.2575, "lr": 3.374913413488464e-05, "epoch": 2.3240299523485364, "percentage": 77.47, "elapsed_time": "20:13:41", "remaining_time": "5:53:02", "throughput": 64185.57, "total_tokens": 4674103168} {"current_steps": 11960, "total_steps": 15426, "loss": 0.2535, "lr": 3.374144868078848e-05, "epoch": 2.3259749100457063, "percentage": 77.53, "elapsed_time": "20:14:37", "remaining_time": "5:51:59", "throughput": 64191.48, "total_tokens": 4678109312} {"current_steps": 11970, "total_steps": 15426, "loss": 0.2578, "lr": 3.373376847476615e-05, "epoch": 2.3279198677428767, "percentage": 77.6, "elapsed_time": "20:15:30", "remaining_time": "5:50:56", "throughput": 64198.11, "total_tokens": 4682026368} {"current_steps": 11980, "total_steps": 15426, "loss": 0.2601, "lr": 3.3726093510847566e-05, "epoch": 2.3298648254400467, "percentage": 77.66, "elapsed_time": "20:16:28", "remaining_time": "5:49:54", "throughput": 64203.57, "total_tokens": 4686098048} {"current_steps": 11990, "total_steps": 15426, "loss": 0.2554, "lr": 3.371842378307212e-05, "epoch": 2.3318097831372167, "percentage": 77.73, "elapsed_time": "20:17:22", "remaining_time": "5:48:52", "throughput": 64209.48, "total_tokens": 4690050432} {"current_steps": 12000, "total_steps": 15426, "loss": 0.2579, "lr": 3.371075928548872e-05, "epoch": 2.3337547408343866, "percentage": 77.79, "elapsed_time": "20:18:21", "remaining_time": "5:47:50", "throughput": 64213.73, "total_tokens": 4694120320} {"current_steps": 12010, "total_steps": 15426, "loss": 0.2603, "lr": 3.37031000121557e-05, "epoch": 2.335699698531557, "percentage": 77.86, "elapsed_time": "20:19:13", "remaining_time": "5:46:46", "throughput": 64220.98, "total_tokens": 4697982080} {"current_steps": 12020, "total_steps": 15426, "loss": 0.2587, "lr": 3.369544595714088e-05, "epoch": 2.337644656228727, "percentage": 77.92, "elapsed_time": "20:20:05", "remaining_time": "5:45:43", "throughput": 64227.88, "total_tokens": 4701845632} {"current_steps": 12030, "total_steps": 15426, "loss": 0.2582, "lr": 3.368779711452148e-05, "epoch": 2.339589613925897, "percentage": 77.99, "elapsed_time": "20:20:59", "remaining_time": "5:44:40", "throughput": 64234.49, "total_tokens": 4705763200} {"current_steps": 12040, "total_steps": 15426, "loss": 0.2634, "lr": 3.368015347838413e-05, "epoch": 2.3415345716230673, "percentage": 78.05, "elapsed_time": "20:21:53", "remaining_time": "5:43:37", "throughput": 64240.71, "total_tokens": 4709715712} {"current_steps": 12050, "total_steps": 15426, "loss": 0.2564, "lr": 3.3672515042824855e-05, "epoch": 2.3434795293202373, "percentage": 78.11, "elapsed_time": "20:22:46", "remaining_time": "5:42:34", "throughput": 64246.97, "total_tokens": 4713577728} {"current_steps": 12060, "total_steps": 15426, "loss": 0.2614, "lr": 3.366488180194904e-05, "epoch": 2.3454244870174072, "percentage": 78.18, "elapsed_time": "20:23:38", "remaining_time": "5:41:31", "throughput": 64252.28, "total_tokens": 4717312640} {"current_steps": 12070, "total_steps": 15426, "loss": 0.2567, "lr": 3.365725374987143e-05, "epoch": 2.3473694447145776, "percentage": 78.24, "elapsed_time": "20:24:33", "remaining_time": "5:40:29", "throughput": 64257.7, "total_tokens": 4721258496} {"current_steps": 12080, "total_steps": 15426, "loss": 0.2569, "lr": 3.36496308807161e-05, "epoch": 2.3493144024117476, "percentage": 78.31, "elapsed_time": "20:25:25", "remaining_time": "5:39:25", "throughput": 64265.06, "total_tokens": 4725133184} {"current_steps": 12090, "total_steps": 15426, "loss": 0.2609, "lr": 3.3642013188616426e-05, "epoch": 2.3512593601089176, "percentage": 78.37, "elapsed_time": "20:26:18", "remaining_time": "5:38:22", "throughput": 64272.26, "total_tokens": 4729048704} {"current_steps": 12100, "total_steps": 15426, "loss": 0.2574, "lr": 3.3634400667715074e-05, "epoch": 2.353204317806088, "percentage": 78.44, "elapsed_time": "20:27:14", "remaining_time": "5:37:20", "throughput": 64275.93, "total_tokens": 4732943104} {"current_steps": 12110, "total_steps": 15426, "loss": 0.2614, "lr": 3.3626793312164013e-05, "epoch": 2.355149275503258, "percentage": 78.5, "elapsed_time": "20:28:10", "remaining_time": "5:36:18", "throughput": 64279.89, "total_tokens": 4736843008} {"current_steps": 12120, "total_steps": 15426, "loss": 0.2603, "lr": 3.361919111612443e-05, "epoch": 2.357094233200428, "percentage": 78.57, "elapsed_time": "20:29:02", "remaining_time": "5:35:14", "throughput": 64286.48, "total_tokens": 4740665984} {"current_steps": 12130, "total_steps": 15426, "loss": 0.2587, "lr": 3.361159407376678e-05, "epoch": 2.359039190897598, "percentage": 78.63, "elapsed_time": "20:29:55", "remaining_time": "5:34:11", "throughput": 64293.33, "total_tokens": 4744535552} {"current_steps": 12140, "total_steps": 15426, "loss": 0.2588, "lr": 3.3604002179270685e-05, "epoch": 2.3609841485947682, "percentage": 78.7, "elapsed_time": "20:30:49", "remaining_time": "5:33:09", "throughput": 64298.86, "total_tokens": 4748423808} {"current_steps": 12150, "total_steps": 15426, "loss": 0.2591, "lr": 3.359641542682504e-05, "epoch": 2.362929106291938, "percentage": 78.76, "elapsed_time": "20:31:43", "remaining_time": "5:32:06", "throughput": 64304.05, "total_tokens": 4752316928} {"current_steps": 12160, "total_steps": 15426, "loss": 0.2596, "lr": 3.3588833810627854e-05, "epoch": 2.364874063989108, "percentage": 78.83, "elapsed_time": "20:32:34", "remaining_time": "5:31:03", "throughput": 64312.08, "total_tokens": 4756167680} {"current_steps": 12170, "total_steps": 15426, "loss": 0.2548, "lr": 3.358125732488632e-05, "epoch": 2.366819021686278, "percentage": 78.89, "elapsed_time": "20:33:31", "remaining_time": "5:30:01", "throughput": 64316.66, "total_tokens": 4760167168} {"current_steps": 12180, "total_steps": 15426, "loss": 0.2592, "lr": 3.357368596381679e-05, "epoch": 2.3687639793834485, "percentage": 78.96, "elapsed_time": "20:34:25", "remaining_time": "5:28:58", "throughput": 64323.36, "total_tokens": 4764110208} {"current_steps": 12190, "total_steps": 15426, "loss": 0.2612, "lr": 3.356611972164471e-05, "epoch": 2.3707089370806185, "percentage": 79.02, "elapsed_time": "20:35:15", "remaining_time": "5:27:55", "throughput": 64330.84, "total_tokens": 4767926144} {"current_steps": 12200, "total_steps": 15426, "loss": 0.2586, "lr": 3.355855859260466e-05, "epoch": 2.3726538947777884, "percentage": 79.09, "elapsed_time": "20:36:10", "remaining_time": "5:26:52", "throughput": 64337.11, "total_tokens": 4771890688} {"current_steps": 12210, "total_steps": 15426, "loss": 0.2591, "lr": 3.3551002570940285e-05, "epoch": 2.374598852474959, "percentage": 79.15, "elapsed_time": "20:37:01", "remaining_time": "5:25:49", "throughput": 64344.63, "total_tokens": 4775724032} {"current_steps": 12220, "total_steps": 15426, "loss": 0.2572, "lr": 3.354345165090431e-05, "epoch": 2.376543810172129, "percentage": 79.22, "elapsed_time": "20:37:53", "remaining_time": "5:24:46", "throughput": 64351.0, "total_tokens": 4779580416} {"current_steps": 12230, "total_steps": 15426, "loss": 0.2593, "lr": 3.3535905826758515e-05, "epoch": 2.3784887678692987, "percentage": 79.28, "elapsed_time": "20:38:46", "remaining_time": "5:23:43", "throughput": 64357.0, "total_tokens": 4783435776} {"current_steps": 12240, "total_steps": 15426, "loss": 0.2584, "lr": 3.352836509277369e-05, "epoch": 2.380433725566469, "percentage": 79.35, "elapsed_time": "20:39:38", "remaining_time": "5:22:40", "throughput": 64363.55, "total_tokens": 4787293952} {"current_steps": 12250, "total_steps": 15426, "loss": 0.2598, "lr": 3.352082944322966e-05, "epoch": 2.382378683263639, "percentage": 79.41, "elapsed_time": "20:40:31", "remaining_time": "5:21:37", "throughput": 64371.28, "total_tokens": 4791245696} {"current_steps": 12260, "total_steps": 15426, "loss": 0.2568, "lr": 3.351329887241524e-05, "epoch": 2.384323640960809, "percentage": 79.48, "elapsed_time": "20:41:27", "remaining_time": "5:20:35", "throughput": 64375.9, "total_tokens": 4795189760} {"current_steps": 12270, "total_steps": 15426, "loss": 0.2594, "lr": 3.3505773374628225e-05, "epoch": 2.386268598657979, "percentage": 79.54, "elapsed_time": "20:42:24", "remaining_time": "5:19:33", "throughput": 64380.74, "total_tokens": 4799199616} {"current_steps": 12280, "total_steps": 15426, "loss": 0.2597, "lr": 3.3498252944175354e-05, "epoch": 2.3882135563551494, "percentage": 79.61, "elapsed_time": "20:43:18", "remaining_time": "5:18:31", "throughput": 64386.23, "total_tokens": 4803088768} {"current_steps": 12290, "total_steps": 15426, "loss": 0.2568, "lr": 3.3490737575372326e-05, "epoch": 2.3901585140523194, "percentage": 79.67, "elapsed_time": "20:44:13", "remaining_time": "5:17:29", "throughput": 64391.64, "total_tokens": 4807039488} {"current_steps": 12300, "total_steps": 15426, "loss": 0.2581, "lr": 3.348322726254375e-05, "epoch": 2.3921034717494893, "percentage": 79.74, "elapsed_time": "20:45:07", "remaining_time": "5:16:26", "throughput": 64396.02, "total_tokens": 4810888192} {"current_steps": 12310, "total_steps": 15426, "loss": 0.2585, "lr": 3.347572200002315e-05, "epoch": 2.3940484294466593, "percentage": 79.8, "elapsed_time": "20:45:59", "remaining_time": "5:15:23", "throughput": 64403.65, "total_tokens": 4814807808} {"current_steps": 12320, "total_steps": 15426, "loss": 0.2591, "lr": 3.3468221782152924e-05, "epoch": 2.3959933871438297, "percentage": 79.87, "elapsed_time": "20:46:53", "remaining_time": "5:14:21", "throughput": 64410.17, "total_tokens": 4818727808} {"current_steps": 12330, "total_steps": 15426, "loss": 0.2558, "lr": 3.346072660328435e-05, "epoch": 2.3979383448409997, "percentage": 79.93, "elapsed_time": "20:47:49", "remaining_time": "5:13:19", "throughput": 64415.27, "total_tokens": 4822729216} {"current_steps": 12340, "total_steps": 15426, "loss": 0.2559, "lr": 3.345323645777756e-05, "epoch": 2.3998833025381696, "percentage": 79.99, "elapsed_time": "20:48:42", "remaining_time": "5:12:16", "throughput": 64421.6, "total_tokens": 4826633600} {"current_steps": 12350, "total_steps": 15426, "loss": 0.2604, "lr": 3.34457513400015e-05, "epoch": 2.40182826023534, "percentage": 80.06, "elapsed_time": "20:49:32", "remaining_time": "5:11:13", "throughput": 64428.85, "total_tokens": 4830393984} {"current_steps": 12360, "total_steps": 15426, "loss": 0.2566, "lr": 3.343827124433396e-05, "epoch": 2.40377321793251, "percentage": 80.12, "elapsed_time": "20:50:27", "remaining_time": "5:10:11", "throughput": 64433.4, "total_tokens": 4834270976} {"current_steps": 12370, "total_steps": 15426, "loss": 0.2574, "lr": 3.343079616516151e-05, "epoch": 2.40571817562968, "percentage": 80.19, "elapsed_time": "20:51:22", "remaining_time": "5:09:09", "throughput": 64437.99, "total_tokens": 4838177280} {"current_steps": 12380, "total_steps": 15426, "loss": 0.2554, "lr": 3.3423326096879495e-05, "epoch": 2.4076631333268503, "percentage": 80.25, "elapsed_time": "20:52:17", "remaining_time": "5:08:06", "throughput": 64443.25, "total_tokens": 4842103552} {"current_steps": 12390, "total_steps": 15426, "loss": 0.2605, "lr": 3.341586103389203e-05, "epoch": 2.4096080910240203, "percentage": 80.32, "elapsed_time": "20:53:07", "remaining_time": "5:07:03", "throughput": 64449.94, "total_tokens": 4845830272} {"current_steps": 12400, "total_steps": 15426, "loss": 0.2594, "lr": 3.3408400970611995e-05, "epoch": 2.4115530487211903, "percentage": 80.38, "elapsed_time": "20:54:01", "remaining_time": "5:06:01", "throughput": 64455.44, "total_tokens": 4849717376} {"current_steps": 12410, "total_steps": 15426, "loss": 0.2578, "lr": 3.340094590146095e-05, "epoch": 2.41349800641836, "percentage": 80.45, "elapsed_time": "20:54:56", "remaining_time": "5:04:59", "throughput": 64460.38, "total_tokens": 4853629696} {"current_steps": 12420, "total_steps": 15426, "loss": 0.259, "lr": 3.3393495820869215e-05, "epoch": 2.4154429641155306, "percentage": 80.51, "elapsed_time": "20:55:49", "remaining_time": "5:03:56", "throughput": 64466.78, "total_tokens": 4857531648} {"current_steps": 12430, "total_steps": 15426, "loss": 0.259, "lr": 3.338605072327576e-05, "epoch": 2.4173879218127006, "percentage": 80.58, "elapsed_time": "20:56:42", "remaining_time": "5:02:54", "throughput": 64472.68, "total_tokens": 4861411072} {"current_steps": 12440, "total_steps": 15426, "loss": 0.2593, "lr": 3.337861060312827e-05, "epoch": 2.4193328795098705, "percentage": 80.64, "elapsed_time": "20:57:40", "remaining_time": "5:01:52", "throughput": 64476.28, "total_tokens": 4865392384} {"current_steps": 12450, "total_steps": 15426, "loss": 0.2602, "lr": 3.337117545488306e-05, "epoch": 2.421277837207041, "percentage": 80.71, "elapsed_time": "20:58:33", "remaining_time": "5:00:50", "throughput": 64482.72, "total_tokens": 4869342848} {"current_steps": 12460, "total_steps": 15426, "loss": 0.2599, "lr": 3.33637452730051e-05, "epoch": 2.423222794904211, "percentage": 80.77, "elapsed_time": "20:59:27", "remaining_time": "4:59:48", "throughput": 64488.4, "total_tokens": 4873224064} {"current_steps": 12470, "total_steps": 15426, "loss": 0.259, "lr": 3.335632005196796e-05, "epoch": 2.425167752601381, "percentage": 80.84, "elapsed_time": "21:00:21", "remaining_time": "4:58:46", "throughput": 64493.81, "total_tokens": 4877129728} {"current_steps": 12480, "total_steps": 15426, "loss": 0.2567, "lr": 3.334889978625383e-05, "epoch": 2.427112710298551, "percentage": 80.9, "elapsed_time": "21:01:17", "remaining_time": "4:57:44", "throughput": 64497.58, "total_tokens": 4880984448} {"current_steps": 12490, "total_steps": 15426, "loss": 0.2608, "lr": 3.3341484470353515e-05, "epoch": 2.429057667995721, "percentage": 80.97, "elapsed_time": "21:02:11", "remaining_time": "4:56:42", "throughput": 64503.06, "total_tokens": 4884918912} {"current_steps": 12500, "total_steps": 15426, "loss": 0.2574, "lr": 3.333407409876635e-05, "epoch": 2.431002625692891, "percentage": 81.03, "elapsed_time": "21:03:03", "remaining_time": "4:55:39", "throughput": 64509.11, "total_tokens": 4888757376} {"current_steps": 12510, "total_steps": 15426, "loss": 0.2571, "lr": 3.332666866600024e-05, "epoch": 2.432947583390061, "percentage": 81.1, "elapsed_time": "21:04:00", "remaining_time": "4:54:37", "throughput": 64514.26, "total_tokens": 4892785408} {"current_steps": 12520, "total_steps": 15426, "loss": 0.2613, "lr": 3.331926816657162e-05, "epoch": 2.4348925410872315, "percentage": 81.16, "elapsed_time": "21:04:56", "remaining_time": "4:53:36", "throughput": 64519.03, "total_tokens": 4896764544} {"current_steps": 12530, "total_steps": 15426, "loss": 0.2618, "lr": 3.331187259500546e-05, "epoch": 2.4368374987844015, "percentage": 81.23, "elapsed_time": "21:05:49", "remaining_time": "4:52:33", "throughput": 64525.34, "total_tokens": 4900660608} {"current_steps": 12540, "total_steps": 15426, "loss": 0.2596, "lr": 3.3304481945835235e-05, "epoch": 2.4387824564815714, "percentage": 81.29, "elapsed_time": "21:06:46", "remaining_time": "4:51:32", "throughput": 64529.05, "total_tokens": 4904612352} {"current_steps": 12550, "total_steps": 15426, "loss": 0.2623, "lr": 3.329709621360288e-05, "epoch": 2.440727414178742, "percentage": 81.36, "elapsed_time": "21:07:38", "remaining_time": "4:50:29", "throughput": 64533.54, "total_tokens": 4908344576} {"current_steps": 12560, "total_steps": 15426, "loss": 0.2548, "lr": 3.328971539285882e-05, "epoch": 2.442672371875912, "percentage": 81.42, "elapsed_time": "21:08:35", "remaining_time": "4:49:28", "throughput": 64538.07, "total_tokens": 4912338944} {"current_steps": 12570, "total_steps": 15426, "loss": 0.2576, "lr": 3.3282339478161935e-05, "epoch": 2.4446173295730818, "percentage": 81.49, "elapsed_time": "21:09:26", "remaining_time": "4:48:25", "throughput": 64544.65, "total_tokens": 4916139648} {"current_steps": 12580, "total_steps": 15426, "loss": 0.2568, "lr": 3.327496846407953e-05, "epoch": 2.4465622872702517, "percentage": 81.55, "elapsed_time": "21:10:20", "remaining_time": "4:47:23", "throughput": 64550.52, "total_tokens": 4920092544} {"current_steps": 12590, "total_steps": 15426, "loss": 0.2604, "lr": 3.3267602345187304e-05, "epoch": 2.448507244967422, "percentage": 81.62, "elapsed_time": "21:11:14", "remaining_time": "4:46:21", "throughput": 64556.9, "total_tokens": 4924017664} {"current_steps": 12600, "total_steps": 15426, "loss": 0.2574, "lr": 3.326024111606942e-05, "epoch": 2.450452202664592, "percentage": 81.68, "elapsed_time": "21:12:07", "remaining_time": "4:45:19", "throughput": 64563.33, "total_tokens": 4927952896} {"current_steps": 12610, "total_steps": 15426, "loss": 0.2571, "lr": 3.325288477131839e-05, "epoch": 2.452397160361762, "percentage": 81.75, "elapsed_time": "21:13:01", "remaining_time": "4:44:17", "throughput": 64569.63, "total_tokens": 4931955328} {"current_steps": 12620, "total_steps": 15426, "loss": 0.2558, "lr": 3.324553330553507e-05, "epoch": 2.454342118058932, "percentage": 81.81, "elapsed_time": "21:13:57", "remaining_time": "4:43:15", "throughput": 64573.8, "total_tokens": 4935842816} {"current_steps": 12630, "total_steps": 15426, "loss": 0.2612, "lr": 3.323818671332871e-05, "epoch": 2.4562870757561024, "percentage": 81.87, "elapsed_time": "21:14:48", "remaining_time": "4:42:12", "throughput": 64581.82, "total_tokens": 4939746048} {"current_steps": 12640, "total_steps": 15426, "loss": 0.2594, "lr": 3.323084498931687e-05, "epoch": 2.4582320334532723, "percentage": 81.94, "elapsed_time": "21:15:40", "remaining_time": "4:41:10", "throughput": 64587.9, "total_tokens": 4943575168} {"current_steps": 12650, "total_steps": 15426, "loss": 0.2585, "lr": 3.322350812812545e-05, "epoch": 2.4601769911504423, "percentage": 82.0, "elapsed_time": "21:16:32", "remaining_time": "4:40:07", "throughput": 64594.54, "total_tokens": 4947445376} {"current_steps": 12660, "total_steps": 15426, "loss": 0.2576, "lr": 3.321617612438862e-05, "epoch": 2.4621219488476127, "percentage": 82.07, "elapsed_time": "21:17:24", "remaining_time": "4:39:05", "throughput": 64600.95, "total_tokens": 4951325312} {"current_steps": 12670, "total_steps": 15426, "loss": 0.2584, "lr": 3.320884897274886e-05, "epoch": 2.4640669065447827, "percentage": 82.13, "elapsed_time": "21:18:16", "remaining_time": "4:38:03", "throughput": 64607.82, "total_tokens": 4955173248} {"current_steps": 12680, "total_steps": 15426, "loss": 0.2558, "lr": 3.320152666785692e-05, "epoch": 2.4660118642419526, "percentage": 82.2, "elapsed_time": "21:19:10", "remaining_time": "4:37:01", "throughput": 64613.21, "total_tokens": 4959078656} {"current_steps": 12690, "total_steps": 15426, "loss": 0.2594, "lr": 3.319420920437179e-05, "epoch": 2.467956821939123, "percentage": 82.26, "elapsed_time": "21:20:03", "remaining_time": "4:35:59", "throughput": 64618.68, "total_tokens": 4962926080} {"current_steps": 12700, "total_steps": 15426, "loss": 0.2594, "lr": 3.31868965769607e-05, "epoch": 2.469901779636293, "percentage": 82.33, "elapsed_time": "21:20:55", "remaining_time": "4:34:56", "throughput": 64624.84, "total_tokens": 4966786816} {"current_steps": 12710, "total_steps": 15426, "loss": 0.2598, "lr": 3.317958878029911e-05, "epoch": 2.471846737333463, "percentage": 82.39, "elapsed_time": "21:21:49", "remaining_time": "4:33:54", "throughput": 64629.8, "total_tokens": 4970671616} {"current_steps": 12720, "total_steps": 15426, "loss": 0.2588, "lr": 3.3172285809070665e-05, "epoch": 2.473791695030633, "percentage": 82.46, "elapsed_time": "21:22:43", "remaining_time": "4:32:52", "throughput": 64634.7, "total_tokens": 4974535552} {"current_steps": 12730, "total_steps": 15426, "loss": 0.2575, "lr": 3.3164987657967214e-05, "epoch": 2.4757366527278033, "percentage": 82.52, "elapsed_time": "21:23:40", "remaining_time": "4:31:51", "throughput": 64638.19, "total_tokens": 4978454528} {"current_steps": 12740, "total_steps": 15426, "loss": 0.259, "lr": 3.315769432168877e-05, "epoch": 2.4776816104249733, "percentage": 82.59, "elapsed_time": "21:24:34", "remaining_time": "4:30:49", "throughput": 64643.87, "total_tokens": 4982363392} {"current_steps": 12750, "total_steps": 15426, "loss": 0.2588, "lr": 3.315040579494349e-05, "epoch": 2.479626568122143, "percentage": 82.65, "elapsed_time": "21:25:26", "remaining_time": "4:29:47", "throughput": 64649.77, "total_tokens": 4986203136} {"current_steps": 12760, "total_steps": 15426, "loss": 0.2604, "lr": 3.31431220724477e-05, "epoch": 2.4815715258193136, "percentage": 82.72, "elapsed_time": "21:26:20", "remaining_time": "4:28:45", "throughput": 64654.94, "total_tokens": 4990130944} {"current_steps": 12770, "total_steps": 15426, "loss": 0.2603, "lr": 3.3135843148925834e-05, "epoch": 2.4835164835164836, "percentage": 82.78, "elapsed_time": "21:27:15", "remaining_time": "4:27:44", "throughput": 64660.28, "total_tokens": 4994088320} {"current_steps": 12780, "total_steps": 15426, "loss": 0.2579, "lr": 3.3128569019110414e-05, "epoch": 2.4854614412136535, "percentage": 82.85, "elapsed_time": "21:28:11", "remaining_time": "4:26:42", "throughput": 64665.83, "total_tokens": 4998110592} {"current_steps": 12790, "total_steps": 15426, "loss": 0.2571, "lr": 3.312129967774207e-05, "epoch": 2.4874063989108235, "percentage": 82.91, "elapsed_time": "21:29:07", "remaining_time": "4:25:41", "throughput": 64670.49, "total_tokens": 5002080000} {"current_steps": 12800, "total_steps": 15426, "loss": 0.2564, "lr": 3.311403511956952e-05, "epoch": 2.489351356607994, "percentage": 82.98, "elapsed_time": "21:30:02", "remaining_time": "4:24:39", "throughput": 64675.17, "total_tokens": 5005989888} {"current_steps": 12810, "total_steps": 15426, "loss": 0.2576, "lr": 3.310677533934952e-05, "epoch": 2.491296314305164, "percentage": 83.04, "elapsed_time": "21:30:53", "remaining_time": "4:23:37", "throughput": 64681.27, "total_tokens": 5009811584} {"current_steps": 12820, "total_steps": 15426, "loss": 0.2573, "lr": 3.309952033184686e-05, "epoch": 2.493241272002334, "percentage": 83.11, "elapsed_time": "21:31:49", "remaining_time": "4:22:35", "throughput": 64687.41, "total_tokens": 5013880064} {"current_steps": 12830, "total_steps": 15426, "loss": 0.2605, "lr": 3.309227009183439e-05, "epoch": 2.495186229699504, "percentage": 83.17, "elapsed_time": "21:32:42", "remaining_time": "4:21:33", "throughput": 64693.91, "total_tokens": 5017840256} {"current_steps": 12840, "total_steps": 15426, "loss": 0.2566, "lr": 3.308502461409295e-05, "epoch": 2.497131187396674, "percentage": 83.24, "elapsed_time": "21:33:38", "remaining_time": "4:20:32", "throughput": 64698.62, "total_tokens": 5021806848} {"current_steps": 12850, "total_steps": 15426, "loss": 0.26, "lr": 3.3077783893411386e-05, "epoch": 2.499076145093844, "percentage": 83.3, "elapsed_time": "21:34:30", "remaining_time": "4:19:30", "throughput": 64705.61, "total_tokens": 5025738880} {"current_steps": 12860, "total_steps": 15426, "loss": 0.2607, "lr": 3.30705479245865e-05, "epoch": 2.5010211027910145, "percentage": 83.37, "elapsed_time": "21:35:19", "remaining_time": "4:18:27", "throughput": 64713.49, "total_tokens": 5029519104} {"current_steps": 12870, "total_steps": 15426, "loss": 0.2569, "lr": 3.3063316702423094e-05, "epoch": 2.5029660604881845, "percentage": 83.43, "elapsed_time": "21:36:13", "remaining_time": "4:17:26", "throughput": 64718.42, "total_tokens": 5033407360} {"current_steps": 12880, "total_steps": 15426, "loss": 0.2558, "lr": 3.305609022173388e-05, "epoch": 2.5049110181853544, "percentage": 83.5, "elapsed_time": "21:37:07", "remaining_time": "4:16:24", "throughput": 64724.24, "total_tokens": 5037321984} {"current_steps": 12890, "total_steps": 15426, "loss": 0.2588, "lr": 3.304886847733954e-05, "epoch": 2.5068559758825244, "percentage": 83.56, "elapsed_time": "21:38:01", "remaining_time": "4:15:22", "throughput": 64729.47, "total_tokens": 5041215360} {"current_steps": 12900, "total_steps": 15426, "loss": 0.26, "lr": 3.304165146406865e-05, "epoch": 2.508800933579695, "percentage": 83.63, "elapsed_time": "21:38:54", "remaining_time": "4:14:20", "throughput": 64735.38, "total_tokens": 5045102848} {"current_steps": 12910, "total_steps": 15426, "loss": 0.2549, "lr": 3.30344391767577e-05, "epoch": 2.5107458912768648, "percentage": 83.69, "elapsed_time": "21:39:49", "remaining_time": "4:13:19", "throughput": 64740.19, "total_tokens": 5049028992} {"current_steps": 12920, "total_steps": 15426, "loss": 0.2541, "lr": 3.302723161025104e-05, "epoch": 2.5126908489740347, "percentage": 83.75, "elapsed_time": "21:40:44", "remaining_time": "4:12:17", "throughput": 64745.26, "total_tokens": 5053017344} {"current_steps": 12930, "total_steps": 15426, "loss": 0.2586, "lr": 3.302002875940093e-05, "epoch": 2.5146358066712047, "percentage": 83.82, "elapsed_time": "21:41:37", "remaining_time": "4:11:15", "throughput": 64751.62, "total_tokens": 5056921984} {"current_steps": 12940, "total_steps": 15426, "loss": 0.2568, "lr": 3.3012830619067466e-05, "epoch": 2.516580764368375, "percentage": 83.88, "elapsed_time": "21:42:31", "remaining_time": "4:10:14", "throughput": 64757.11, "total_tokens": 5060885888} {"current_steps": 12950, "total_steps": 15426, "loss": 0.2583, "lr": 3.300563718411857e-05, "epoch": 2.518525722065545, "percentage": 83.95, "elapsed_time": "21:43:22", "remaining_time": "4:09:12", "throughput": 64764.64, "total_tokens": 5064754176} {"current_steps": 12960, "total_steps": 15426, "loss": 0.258, "lr": 3.299844844943e-05, "epoch": 2.520470679762715, "percentage": 84.01, "elapsed_time": "21:44:14", "remaining_time": "4:08:10", "throughput": 64769.63, "total_tokens": 5068529792} {"current_steps": 12970, "total_steps": 15426, "loss": 0.2589, "lr": 3.299126440988535e-05, "epoch": 2.5224156374598854, "percentage": 84.08, "elapsed_time": "21:45:07", "remaining_time": "4:07:08", "throughput": 64775.21, "total_tokens": 5072376448} {"current_steps": 12980, "total_steps": 15426, "loss": 0.256, "lr": 3.298408506037596e-05, "epoch": 2.5243605951570554, "percentage": 84.14, "elapsed_time": "21:46:01", "remaining_time": "4:06:06", "throughput": 64780.92, "total_tokens": 5076339840} {"current_steps": 12990, "total_steps": 15426, "loss": 0.2589, "lr": 3.297691039580097e-05, "epoch": 2.5263055528542253, "percentage": 84.21, "elapsed_time": "21:46:55", "remaining_time": "4:05:05", "throughput": 64785.77, "total_tokens": 5080210944} {"current_steps": 13000, "total_steps": 15426, "loss": 0.2545, "lr": 3.29697404110673e-05, "epoch": 2.5282505105513957, "percentage": 84.27, "elapsed_time": "21:47:51", "remaining_time": "4:04:03", "throughput": 64789.96, "total_tokens": 5084141952} {"current_steps": 13010, "total_steps": 15426, "loss": 0.2588, "lr": 3.2962575101089594e-05, "epoch": 2.5301954682485657, "percentage": 84.34, "elapsed_time": "21:48:43", "remaining_time": "4:03:02", "throughput": 64795.64, "total_tokens": 5087981952} {"current_steps": 13020, "total_steps": 15426, "loss": 0.2601, "lr": 3.295541446079024e-05, "epoch": 2.5321404259457356, "percentage": 84.4, "elapsed_time": "21:49:40", "remaining_time": "4:02:01", "throughput": 64799.77, "total_tokens": 5092026752} {"current_steps": 13030, "total_steps": 15426, "loss": 0.2547, "lr": 3.2948258485099336e-05, "epoch": 2.534085383642906, "percentage": 84.47, "elapsed_time": "21:50:36", "remaining_time": "4:00:59", "throughput": 64805.0, "total_tokens": 5096017280} {"current_steps": 13040, "total_steps": 15426, "loss": 0.2575, "lr": 3.29411071689547e-05, "epoch": 2.536030341340076, "percentage": 84.53, "elapsed_time": "21:51:27", "remaining_time": "3:59:57", "throughput": 64811.13, "total_tokens": 5099825024} {"current_steps": 13050, "total_steps": 15426, "loss": 0.2578, "lr": 3.2933960507301826e-05, "epoch": 2.537975299037246, "percentage": 84.6, "elapsed_time": "21:52:21", "remaining_time": "3:58:56", "throughput": 64816.34, "total_tokens": 5103728256} {"current_steps": 13060, "total_steps": 15426, "loss": 0.2563, "lr": 3.292681849509387e-05, "epoch": 2.539920256734416, "percentage": 84.66, "elapsed_time": "21:53:17", "remaining_time": "3:57:55", "throughput": 64821.5, "total_tokens": 5107758208} {"current_steps": 13070, "total_steps": 15426, "loss": 0.2599, "lr": 3.291968112729166e-05, "epoch": 2.541865214431586, "percentage": 84.73, "elapsed_time": "21:54:10", "remaining_time": "3:56:53", "throughput": 64827.81, "total_tokens": 5111684480} {"current_steps": 13080, "total_steps": 15426, "loss": 0.2573, "lr": 3.291254839886367e-05, "epoch": 2.5438101721287563, "percentage": 84.79, "elapsed_time": "21:55:03", "remaining_time": "3:55:52", "throughput": 64832.78, "total_tokens": 5115551616} {"current_steps": 13090, "total_steps": 15426, "loss": 0.2561, "lr": 3.2905420304785995e-05, "epoch": 2.545755129825926, "percentage": 84.86, "elapsed_time": "21:55:59", "remaining_time": "3:54:50", "throughput": 64838.04, "total_tokens": 5119572352} {"current_steps": 13100, "total_steps": 15426, "loss": 0.2614, "lr": 3.289829684004235e-05, "epoch": 2.547700087523096, "percentage": 84.92, "elapsed_time": "21:56:51", "remaining_time": "3:53:49", "throughput": 64843.38, "total_tokens": 5123359744} {"current_steps": 13110, "total_steps": 15426, "loss": 0.2589, "lr": 3.289117799962402e-05, "epoch": 2.5496450452202666, "percentage": 84.99, "elapsed_time": "21:57:43", "remaining_time": "3:52:47", "throughput": 64848.46, "total_tokens": 5127169536} {"current_steps": 13120, "total_steps": 15426, "loss": 0.2589, "lr": 3.2884063778529914e-05, "epoch": 2.5515900029174365, "percentage": 85.05, "elapsed_time": "21:58:39", "remaining_time": "3:51:46", "throughput": 64853.31, "total_tokens": 5131159936} {"current_steps": 13130, "total_steps": 15426, "loss": 0.259, "lr": 3.28769541717665e-05, "epoch": 2.5535349606146065, "percentage": 85.12, "elapsed_time": "21:59:32", "remaining_time": "3:50:44", "throughput": 64859.3, "total_tokens": 5135075840} {"current_steps": 13140, "total_steps": 15426, "loss": 0.2595, "lr": 3.2869849174347775e-05, "epoch": 2.555479918311777, "percentage": 85.18, "elapsed_time": "22:00:26", "remaining_time": "3:49:43", "throughput": 64864.0, "total_tokens": 5138950784} {"current_steps": 13150, "total_steps": 15426, "loss": 0.2602, "lr": 3.2862748781295294e-05, "epoch": 2.557424876008947, "percentage": 85.25, "elapsed_time": "22:01:21", "remaining_time": "3:48:42", "throughput": 64868.93, "total_tokens": 5142912000} {"current_steps": 13160, "total_steps": 15426, "loss": 0.2597, "lr": 3.2855652987638146e-05, "epoch": 2.559369833706117, "percentage": 85.31, "elapsed_time": "22:02:16", "remaining_time": "3:47:40", "throughput": 64873.81, "total_tokens": 5146855808} {"current_steps": 13170, "total_steps": 15426, "loss": 0.2532, "lr": 3.284856178841291e-05, "epoch": 2.561314791403287, "percentage": 85.38, "elapsed_time": "22:03:14", "remaining_time": "3:46:40", "throughput": 64877.11, "total_tokens": 5150877056} {"current_steps": 13180, "total_steps": 15426, "loss": 0.2599, "lr": 3.284147517866367e-05, "epoch": 2.563259749100457, "percentage": 85.44, "elapsed_time": "22:04:11", "remaining_time": "3:45:39", "throughput": 64880.58, "total_tokens": 5154878720} {"current_steps": 13190, "total_steps": 15426, "loss": 0.2603, "lr": 3.2834393153441976e-05, "epoch": 2.565204706797627, "percentage": 85.5, "elapsed_time": "22:05:06", "remaining_time": "3:44:38", "throughput": 64884.83, "total_tokens": 5158748288} {"current_steps": 13200, "total_steps": 15426, "loss": 0.2616, "lr": 3.282731570780689e-05, "epoch": 2.567149664494797, "percentage": 85.57, "elapsed_time": "22:05:58", "remaining_time": "3:43:36", "throughput": 64890.51, "total_tokens": 5162576512} {"current_steps": 13210, "total_steps": 15426, "loss": 0.2574, "lr": 3.2820242836824875e-05, "epoch": 2.569094622191967, "percentage": 85.63, "elapsed_time": "22:06:48", "remaining_time": "3:42:34", "throughput": 64898.06, "total_tokens": 5166434048} {"current_steps": 13220, "total_steps": 15426, "loss": 0.2599, "lr": 3.2813174535569854e-05, "epoch": 2.5710395798891374, "percentage": 85.7, "elapsed_time": "22:07:43", "remaining_time": "3:41:33", "throughput": 64902.63, "total_tokens": 5170379904} {"current_steps": 13230, "total_steps": 15426, "loss": 0.2582, "lr": 3.280611079912318e-05, "epoch": 2.5729845375863074, "percentage": 85.76, "elapsed_time": "22:08:36", "remaining_time": "3:40:31", "throughput": 64907.68, "total_tokens": 5174237696} {"current_steps": 13240, "total_steps": 15426, "loss": 0.2593, "lr": 3.279905162257358e-05, "epoch": 2.5749294952834774, "percentage": 85.83, "elapsed_time": "22:09:31", "remaining_time": "3:39:30", "throughput": 64911.57, "total_tokens": 5178097792} {"current_steps": 13250, "total_steps": 15426, "loss": 0.2577, "lr": 3.279199700101723e-05, "epoch": 2.5768744529806478, "percentage": 85.89, "elapsed_time": "22:10:26", "remaining_time": "3:38:29", "throughput": 64915.93, "total_tokens": 5182008064} {"current_steps": 13260, "total_steps": 15426, "loss": 0.2576, "lr": 3.2784946929557644e-05, "epoch": 2.5788194106778177, "percentage": 85.96, "elapsed_time": "22:11:19", "remaining_time": "3:37:28", "throughput": 64921.23, "total_tokens": 5185896832} {"current_steps": 13270, "total_steps": 15426, "loss": 0.2572, "lr": 3.277790140330571e-05, "epoch": 2.5807643683749877, "percentage": 86.02, "elapsed_time": "22:12:13", "remaining_time": "3:36:26", "throughput": 64926.63, "total_tokens": 5189812224} {"current_steps": 13280, "total_steps": 15426, "loss": 0.2561, "lr": 3.277086041737968e-05, "epoch": 2.582709326072158, "percentage": 86.09, "elapsed_time": "22:13:08", "remaining_time": "3:35:25", "throughput": 64931.83, "total_tokens": 5193768192} {"current_steps": 13290, "total_steps": 15426, "loss": 0.257, "lr": 3.276382396690513e-05, "epoch": 2.584654283769328, "percentage": 86.15, "elapsed_time": "22:13:58", "remaining_time": "3:34:24", "throughput": 64938.74, "total_tokens": 5197614848} {"current_steps": 13300, "total_steps": 15426, "loss": 0.2564, "lr": 3.275679204701496e-05, "epoch": 2.586599241466498, "percentage": 86.22, "elapsed_time": "22:14:51", "remaining_time": "3:33:22", "throughput": 64944.51, "total_tokens": 5201528192} {"current_steps": 13310, "total_steps": 15426, "loss": 0.2582, "lr": 3.274976465284939e-05, "epoch": 2.5885441991636684, "percentage": 86.28, "elapsed_time": "22:15:43", "remaining_time": "3:32:21", "throughput": 64950.75, "total_tokens": 5205407104} {"current_steps": 13320, "total_steps": 15426, "loss": 0.2587, "lr": 3.274274177955593e-05, "epoch": 2.5904891568608384, "percentage": 86.35, "elapsed_time": "22:16:39", "remaining_time": "3:31:20", "throughput": 64954.59, "total_tokens": 5209321856} {"current_steps": 13330, "total_steps": 15426, "loss": 0.2569, "lr": 3.273572342228937e-05, "epoch": 2.5924341145580083, "percentage": 86.41, "elapsed_time": "22:17:35", "remaining_time": "3:30:19", "throughput": 64959.13, "total_tokens": 5213316352} {"current_steps": 13340, "total_steps": 15426, "loss": 0.2634, "lr": 3.272870957621176e-05, "epoch": 2.5943790722551787, "percentage": 86.48, "elapsed_time": "22:18:31", "remaining_time": "3:29:18", "throughput": 64962.68, "total_tokens": 5217249408} {"current_steps": 13350, "total_steps": 15426, "loss": 0.2589, "lr": 3.2721700236492414e-05, "epoch": 2.5963240299523487, "percentage": 86.54, "elapsed_time": "22:19:24", "remaining_time": "3:28:17", "throughput": 64967.24, "total_tokens": 5221067136} {"current_steps": 13360, "total_steps": 15426, "loss": 0.2577, "lr": 3.271469539830788e-05, "epoch": 2.5982689876495186, "percentage": 86.61, "elapsed_time": "22:20:18", "remaining_time": "3:27:15", "throughput": 64972.16, "total_tokens": 5224966144} {"current_steps": 13370, "total_steps": 15426, "loss": 0.258, "lr": 3.270769505684193e-05, "epoch": 2.6002139453466886, "percentage": 86.67, "elapsed_time": "22:21:12", "remaining_time": "3:26:14", "throughput": 64978.1, "total_tokens": 5228929792} {"current_steps": 13380, "total_steps": 15426, "loss": 0.26, "lr": 3.2700699207285544e-05, "epoch": 2.6021589030438586, "percentage": 86.74, "elapsed_time": "22:22:09", "remaining_time": "3:25:14", "throughput": 64981.85, "total_tokens": 5232931456} {"current_steps": 13390, "total_steps": 15426, "loss": 0.2578, "lr": 3.269370784483691e-05, "epoch": 2.604103860741029, "percentage": 86.8, "elapsed_time": "22:23:03", "remaining_time": "3:24:13", "throughput": 64987.13, "total_tokens": 5236907136} {"current_steps": 13400, "total_steps": 15426, "loss": 0.2589, "lr": 3.268672096470138e-05, "epoch": 2.606048818438199, "percentage": 86.87, "elapsed_time": "22:23:57", "remaining_time": "3:23:11", "throughput": 64991.82, "total_tokens": 5240748288} {"current_steps": 13410, "total_steps": 15426, "loss": 0.2559, "lr": 3.2679738562091506e-05, "epoch": 2.607993776135369, "percentage": 86.93, "elapsed_time": "22:24:52", "remaining_time": "3:22:11", "throughput": 64996.67, "total_tokens": 5244765824} {"current_steps": 13420, "total_steps": 15426, "loss": 0.257, "lr": 3.2672760632226964e-05, "epoch": 2.6099387338325393, "percentage": 87.0, "elapsed_time": "22:25:47", "remaining_time": "3:21:09", "throughput": 65001.57, "total_tokens": 5248711424} {"current_steps": 13430, "total_steps": 15426, "loss": 0.2591, "lr": 3.266578717033458e-05, "epoch": 2.6118836915297092, "percentage": 87.06, "elapsed_time": "22:26:43", "remaining_time": "3:20:09", "throughput": 65004.97, "total_tokens": 5252625664} {"current_steps": 13440, "total_steps": 15426, "loss": 0.2582, "lr": 3.265881817164833e-05, "epoch": 2.613828649226879, "percentage": 87.13, "elapsed_time": "22:27:35", "remaining_time": "3:19:07", "throughput": 65011.08, "total_tokens": 5256530176} {"current_steps": 13450, "total_steps": 15426, "loss": 0.2566, "lr": 3.265185363140928e-05, "epoch": 2.6157736069240496, "percentage": 87.19, "elapsed_time": "22:28:28", "remaining_time": "3:18:06", "throughput": 65016.73, "total_tokens": 5260430592} {"current_steps": 13460, "total_steps": 15426, "loss": 0.2601, "lr": 3.26448935448656e-05, "epoch": 2.6177185646212195, "percentage": 87.26, "elapsed_time": "22:29:25", "remaining_time": "3:17:06", "throughput": 65021.45, "total_tokens": 5264490752} {"current_steps": 13470, "total_steps": 15426, "loss": 0.2584, "lr": 3.263793790727256e-05, "epoch": 2.6196635223183895, "percentage": 87.32, "elapsed_time": "22:30:19", "remaining_time": "3:16:04", "throughput": 65027.57, "total_tokens": 5268491904} {"current_steps": 13480, "total_steps": 15426, "loss": 0.2565, "lr": 3.2630986713892495e-05, "epoch": 2.62160848001556, "percentage": 87.38, "elapsed_time": "22:31:15", "remaining_time": "3:15:04", "throughput": 65031.6, "total_tokens": 5272486400} {"current_steps": 13490, "total_steps": 15426, "loss": 0.2596, "lr": 3.26240399599948e-05, "epoch": 2.62355343771273, "percentage": 87.45, "elapsed_time": "22:32:11", "remaining_time": "3:14:03", "throughput": 65034.78, "total_tokens": 5276383488} {"current_steps": 13500, "total_steps": 15426, "loss": 0.259, "lr": 3.2617097640855914e-05, "epoch": 2.6254983954099, "percentage": 87.51, "elapsed_time": "22:33:07", "remaining_time": "3:13:02", "throughput": 65039.34, "total_tokens": 5280353280} {"current_steps": 13510, "total_steps": 15426, "loss": 0.2558, "lr": 3.2610159751759314e-05, "epoch": 2.62744335310707, "percentage": 87.58, "elapsed_time": "22:34:00", "remaining_time": "3:12:01", "throughput": 65044.38, "total_tokens": 5284212224} {"current_steps": 13520, "total_steps": 15426, "loss": 0.2579, "lr": 3.26032262879955e-05, "epoch": 2.6293883108042397, "percentage": 87.64, "elapsed_time": "22:34:56", "remaining_time": "3:11:00", "throughput": 65047.78, "total_tokens": 5288135936} {"current_steps": 13530, "total_steps": 15426, "loss": 0.2561, "lr": 3.259629724486198e-05, "epoch": 2.63133326850141, "percentage": 87.71, "elapsed_time": "22:35:49", "remaining_time": "3:09:59", "throughput": 65052.89, "total_tokens": 5292032640} {"current_steps": 13540, "total_steps": 15426, "loss": 0.2591, "lr": 3.258937261766323e-05, "epoch": 2.63327822619858, "percentage": 87.77, "elapsed_time": "22:36:44", "remaining_time": "3:08:58", "throughput": 65057.16, "total_tokens": 5295948544} {"current_steps": 13550, "total_steps": 15426, "loss": 0.2562, "lr": 3.258245240171074e-05, "epoch": 2.63522318389575, "percentage": 87.84, "elapsed_time": "22:37:38", "remaining_time": "3:07:57", "throughput": 65063.04, "total_tokens": 5299926784} {"current_steps": 13560, "total_steps": 15426, "loss": 0.2545, "lr": 3.2575536592322935e-05, "epoch": 2.6371681415929205, "percentage": 87.9, "elapsed_time": "22:38:34", "remaining_time": "3:06:57", "throughput": 65067.1, "total_tokens": 5303930752} {"current_steps": 13570, "total_steps": 15426, "loss": 0.2566, "lr": 3.256862518482523e-05, "epoch": 2.6391130992900904, "percentage": 87.97, "elapsed_time": "22:39:30", "remaining_time": "3:05:56", "throughput": 65071.4, "total_tokens": 5307902336} {"current_steps": 13580, "total_steps": 15426, "loss": 0.2599, "lr": 3.256171817454994e-05, "epoch": 2.6410580569872604, "percentage": 88.03, "elapsed_time": "22:40:25", "remaining_time": "3:04:55", "throughput": 65075.77, "total_tokens": 5311828992} {"current_steps": 13590, "total_steps": 15426, "loss": 0.2564, "lr": 3.255481555683633e-05, "epoch": 2.6430030146844308, "percentage": 88.1, "elapsed_time": "22:41:21", "remaining_time": "3:03:55", "throughput": 65080.06, "total_tokens": 5315811712} {"current_steps": 13600, "total_steps": 15426, "loss": 0.2589, "lr": 3.254791732703057e-05, "epoch": 2.6449479723816007, "percentage": 88.16, "elapsed_time": "22:42:15", "remaining_time": "3:02:54", "throughput": 65084.52, "total_tokens": 5319712384} {"current_steps": 13610, "total_steps": 15426, "loss": 0.2536, "lr": 3.254102348048575e-05, "epoch": 2.6468929300787707, "percentage": 88.23, "elapsed_time": "22:43:08", "remaining_time": "3:01:53", "throughput": 65088.99, "total_tokens": 5323535104} {"current_steps": 13620, "total_steps": 15426, "loss": 0.2596, "lr": 3.25341340125618e-05, "epoch": 2.648837887775941, "percentage": 88.29, "elapsed_time": "22:44:03", "remaining_time": "3:00:52", "throughput": 65092.62, "total_tokens": 5327420416} {"current_steps": 13630, "total_steps": 15426, "loss": 0.2556, "lr": 3.2527248918625575e-05, "epoch": 2.650782845473111, "percentage": 88.36, "elapsed_time": "22:44:58", "remaining_time": "2:59:51", "throughput": 65096.78, "total_tokens": 5331301248} {"current_steps": 13640, "total_steps": 15426, "loss": 0.2578, "lr": 3.252036819405075e-05, "epoch": 2.652727803170281, "percentage": 88.42, "elapsed_time": "22:45:53", "remaining_time": "2:58:50", "throughput": 65101.33, "total_tokens": 5335293824} {"current_steps": 13650, "total_steps": 15426, "loss": 0.2609, "lr": 3.251349183421788e-05, "epoch": 2.6546727608674514, "percentage": 88.49, "elapsed_time": "22:46:46", "remaining_time": "2:57:49", "throughput": 65106.51, "total_tokens": 5339137664} {"current_steps": 13660, "total_steps": 15426, "loss": 0.2621, "lr": 3.250661983451434e-05, "epoch": 2.6566177185646214, "percentage": 88.55, "elapsed_time": "22:47:38", "remaining_time": "2:56:48", "throughput": 65110.86, "total_tokens": 5342928768} {"current_steps": 13670, "total_steps": 15426, "loss": 0.2581, "lr": 3.2499752190334326e-05, "epoch": 2.6585626762617913, "percentage": 88.62, "elapsed_time": "22:48:32", "remaining_time": "2:55:47", "throughput": 65116.15, "total_tokens": 5346823680} {"current_steps": 13680, "total_steps": 15426, "loss": 0.26, "lr": 3.2492888897078834e-05, "epoch": 2.6605076339589613, "percentage": 88.68, "elapsed_time": "22:49:23", "remaining_time": "2:54:46", "throughput": 65122.96, "total_tokens": 5350743808} {"current_steps": 13690, "total_steps": 15426, "loss": 0.2601, "lr": 3.248602995015567e-05, "epoch": 2.6624525916561312, "percentage": 88.75, "elapsed_time": "22:50:17", "remaining_time": "2:53:45", "throughput": 65127.83, "total_tokens": 5354643712} {"current_steps": 13700, "total_steps": 15426, "loss": 0.2551, "lr": 3.247917534497943e-05, "epoch": 2.6643975493533016, "percentage": 88.81, "elapsed_time": "22:51:10", "remaining_time": "2:52:44", "throughput": 65133.3, "total_tokens": 5358542080} {"current_steps": 13710, "total_steps": 15426, "loss": 0.2588, "lr": 3.247232507697145e-05, "epoch": 2.6663425070504716, "percentage": 88.88, "elapsed_time": "22:52:03", "remaining_time": "2:51:43", "throughput": 65138.43, "total_tokens": 5362414080} {"current_steps": 13720, "total_steps": 15426, "loss": 0.2523, "lr": 3.246547914155985e-05, "epoch": 2.6682874647476416, "percentage": 88.94, "elapsed_time": "22:52:58", "remaining_time": "2:50:43", "throughput": 65142.98, "total_tokens": 5366402176} {"current_steps": 13730, "total_steps": 15426, "loss": 0.2584, "lr": 3.245863753417949e-05, "epoch": 2.670232422444812, "percentage": 89.01, "elapsed_time": "22:53:52", "remaining_time": "2:49:42", "throughput": 65147.64, "total_tokens": 5370262144} {"current_steps": 13740, "total_steps": 15426, "loss": 0.2573, "lr": 3.2451800250271944e-05, "epoch": 2.672177380141982, "percentage": 89.07, "elapsed_time": "22:54:46", "remaining_time": "2:48:41", "throughput": 65152.62, "total_tokens": 5374186368} {"current_steps": 13750, "total_steps": 15426, "loss": 0.2588, "lr": 3.244496728528553e-05, "epoch": 2.674122337839152, "percentage": 89.14, "elapsed_time": "22:55:41", "remaining_time": "2:47:41", "throughput": 65156.54, "total_tokens": 5378099584} {"current_steps": 13760, "total_steps": 15426, "loss": 0.2571, "lr": 3.243813863467525e-05, "epoch": 2.6760672955363223, "percentage": 89.2, "elapsed_time": "22:56:33", "remaining_time": "2:46:40", "throughput": 65162.18, "total_tokens": 5381987456} {"current_steps": 13770, "total_steps": 15426, "loss": 0.257, "lr": 3.243131429390281e-05, "epoch": 2.6780122532334922, "percentage": 89.26, "elapsed_time": "22:57:26", "remaining_time": "2:45:39", "throughput": 65167.22, "total_tokens": 5385871104} {"current_steps": 13780, "total_steps": 15426, "loss": 0.2568, "lr": 3.2424494258436594e-05, "epoch": 2.679957210930662, "percentage": 89.33, "elapsed_time": "22:58:20", "remaining_time": "2:44:38", "throughput": 65172.65, "total_tokens": 5389781248} {"current_steps": 13790, "total_steps": 15426, "loss": 0.2577, "lr": 3.241767852375166e-05, "epoch": 2.6819021686278326, "percentage": 89.39, "elapsed_time": "22:59:13", "remaining_time": "2:43:37", "throughput": 65178.09, "total_tokens": 5393686784} {"current_steps": 13800, "total_steps": 15426, "loss": 0.2576, "lr": 3.241086708532971e-05, "epoch": 2.6838471263250026, "percentage": 89.46, "elapsed_time": "23:00:06", "remaining_time": "2:42:36", "throughput": 65182.91, "total_tokens": 5397565184} {"current_steps": 13810, "total_steps": 15426, "loss": 0.2598, "lr": 3.24040599386591e-05, "epoch": 2.6857920840221725, "percentage": 89.52, "elapsed_time": "23:01:00", "remaining_time": "2:41:36", "throughput": 65186.76, "total_tokens": 5401381376} {"current_steps": 13820, "total_steps": 15426, "loss": 0.2544, "lr": 3.23972570792348e-05, "epoch": 2.6877370417193425, "percentage": 89.59, "elapsed_time": "23:01:53", "remaining_time": "2:40:35", "throughput": 65192.09, "total_tokens": 5405316480} {"current_steps": 13830, "total_steps": 15426, "loss": 0.2576, "lr": 3.239045850255842e-05, "epoch": 2.6896819994165124, "percentage": 89.65, "elapsed_time": "23:02:46", "remaining_time": "2:39:34", "throughput": 65197.64, "total_tokens": 5409200640} {"current_steps": 13840, "total_steps": 15426, "loss": 0.2577, "lr": 3.238366420413817e-05, "epoch": 2.691626957113683, "percentage": 89.72, "elapsed_time": "23:03:36", "remaining_time": "2:38:33", "throughput": 65204.71, "total_tokens": 5413056512} {"current_steps": 13850, "total_steps": 15426, "loss": 0.2538, "lr": 3.237687417948882e-05, "epoch": 2.693571914810853, "percentage": 89.78, "elapsed_time": "23:04:30", "remaining_time": "2:37:32", "throughput": 65209.9, "total_tokens": 5417023872} {"current_steps": 13860, "total_steps": 15426, "loss": 0.2575, "lr": 3.2370088424131776e-05, "epoch": 2.6955168725080227, "percentage": 89.85, "elapsed_time": "23:05:25", "remaining_time": "2:36:32", "throughput": 65215.02, "total_tokens": 5421002240} {"current_steps": 13870, "total_steps": 15426, "loss": 0.2575, "lr": 3.236330693359497e-05, "epoch": 2.697461830205193, "percentage": 89.91, "elapsed_time": "23:06:17", "remaining_time": "2:35:31", "throughput": 65219.69, "total_tokens": 5424823808} {"current_steps": 13880, "total_steps": 15426, "loss": 0.2559, "lr": 3.2356529703412894e-05, "epoch": 2.699406787902363, "percentage": 89.98, "elapsed_time": "23:07:08", "remaining_time": "2:34:30", "throughput": 65225.52, "total_tokens": 5428632192} {"current_steps": 13890, "total_steps": 15426, "loss": 0.2551, "lr": 3.234975672912661e-05, "epoch": 2.701351745599533, "percentage": 90.04, "elapsed_time": "23:08:01", "remaining_time": "2:33:29", "throughput": 65230.33, "total_tokens": 5432471168} {"current_steps": 13900, "total_steps": 15426, "loss": 0.2572, "lr": 3.234298800628368e-05, "epoch": 2.7032967032967035, "percentage": 90.11, "elapsed_time": "23:08:56", "remaining_time": "2:32:28", "throughput": 65234.8, "total_tokens": 5436417792} {"current_steps": 13910, "total_steps": 15426, "loss": 0.2608, "lr": 3.2336223530438195e-05, "epoch": 2.7052416609938734, "percentage": 90.17, "elapsed_time": "23:09:50", "remaining_time": "2:31:28", "throughput": 65239.35, "total_tokens": 5440319616} {"current_steps": 13920, "total_steps": 15426, "loss": 0.2558, "lr": 3.232946329715076e-05, "epoch": 2.7071866186910434, "percentage": 90.24, "elapsed_time": "23:10:45", "remaining_time": "2:30:27", "throughput": 65243.82, "total_tokens": 5444301312} {"current_steps": 13930, "total_steps": 15426, "loss": 0.256, "lr": 3.2322707301988456e-05, "epoch": 2.709131576388214, "percentage": 90.3, "elapsed_time": "23:11:39", "remaining_time": "2:29:27", "throughput": 65248.35, "total_tokens": 5448219264} {"current_steps": 13940, "total_steps": 15426, "loss": 0.2581, "lr": 3.231595554052488e-05, "epoch": 2.7110765340853837, "percentage": 90.37, "elapsed_time": "23:12:33", "remaining_time": "2:28:26", "throughput": 65253.03, "total_tokens": 5452126976} {"current_steps": 13950, "total_steps": 15426, "loss": 0.2572, "lr": 3.230920800834005e-05, "epoch": 2.7130214917825537, "percentage": 90.43, "elapsed_time": "23:13:27", "remaining_time": "2:27:26", "throughput": 65257.72, "total_tokens": 5456035968} {"current_steps": 13960, "total_steps": 15426, "loss": 0.2571, "lr": 3.2302464701020486e-05, "epoch": 2.7149664494797237, "percentage": 90.5, "elapsed_time": "23:14:23", "remaining_time": "2:26:25", "throughput": 65261.43, "total_tokens": 5459987584} {"current_steps": 13970, "total_steps": 15426, "loss": 0.2621, "lr": 3.2295725614159126e-05, "epoch": 2.716911407176894, "percentage": 90.56, "elapsed_time": "23:15:19", "remaining_time": "2:25:25", "throughput": 65265.27, "total_tokens": 5463953152} {"current_steps": 13980, "total_steps": 15426, "loss": 0.2639, "lr": 3.228899074335536e-05, "epoch": 2.718856364874064, "percentage": 90.63, "elapsed_time": "23:16:11", "remaining_time": "2:24:24", "throughput": 65269.62, "total_tokens": 5467710848} {"current_steps": 13990, "total_steps": 15426, "loss": 0.2602, "lr": 3.228226008421498e-05, "epoch": 2.720801322571234, "percentage": 90.69, "elapsed_time": "23:17:01", "remaining_time": "2:23:23", "throughput": 65276.36, "total_tokens": 5471548800} {"current_steps": 14000, "total_steps": 15426, "loss": 0.2596, "lr": 3.2275533632350193e-05, "epoch": 2.722746280268404, "percentage": 90.76, "elapsed_time": "23:17:53", "remaining_time": "2:22:23", "throughput": 65282.78, "total_tokens": 5475501824} {"current_steps": 14010, "total_steps": 15426, "loss": 0.2574, "lr": 3.226881138337963e-05, "epoch": 2.7246912379655743, "percentage": 90.82, "elapsed_time": "23:18:47", "remaining_time": "2:21:22", "throughput": 65287.48, "total_tokens": 5479410304} {"current_steps": 14020, "total_steps": 15426, "loss": 0.2579, "lr": 3.2262093332928256e-05, "epoch": 2.7266361956627443, "percentage": 90.89, "elapsed_time": "23:19:41", "remaining_time": "2:20:22", "throughput": 65292.34, "total_tokens": 5483318528} {"current_steps": 14030, "total_steps": 15426, "loss": 0.2572, "lr": 3.225537947662746e-05, "epoch": 2.7285811533599142, "percentage": 90.95, "elapsed_time": "23:20:36", "remaining_time": "2:19:21", "throughput": 65297.15, "total_tokens": 5487326720} {"current_steps": 14040, "total_steps": 15426, "loss": 0.2581, "lr": 3.224866981011494e-05, "epoch": 2.7305261110570846, "percentage": 91.02, "elapsed_time": "23:21:29", "remaining_time": "2:18:21", "throughput": 65301.86, "total_tokens": 5491187328} {"current_steps": 14050, "total_steps": 15426, "loss": 0.2605, "lr": 3.22419643290348e-05, "epoch": 2.7324710687542546, "percentage": 91.08, "elapsed_time": "23:22:20", "remaining_time": "2:17:20", "throughput": 65308.07, "total_tokens": 5495069312} {"current_steps": 14060, "total_steps": 15426, "loss": 0.2579, "lr": 3.2235263029037446e-05, "epoch": 2.7344160264514246, "percentage": 91.14, "elapsed_time": "23:23:14", "remaining_time": "2:16:19", "throughput": 65312.41, "total_tokens": 5498943488} {"current_steps": 14070, "total_steps": 15426, "loss": 0.2586, "lr": 3.222856590577962e-05, "epoch": 2.736360984148595, "percentage": 91.21, "elapsed_time": "23:24:09", "remaining_time": "2:15:19", "throughput": 65316.75, "total_tokens": 5502917632} {"current_steps": 14080, "total_steps": 15426, "loss": 0.2568, "lr": 3.222187295492436e-05, "epoch": 2.738305941845765, "percentage": 91.27, "elapsed_time": "23:24:59", "remaining_time": "2:14:18", "throughput": 65323.82, "total_tokens": 5506789504} {"current_steps": 14090, "total_steps": 15426, "loss": 0.2594, "lr": 3.221518417214104e-05, "epoch": 2.740250899542935, "percentage": 91.34, "elapsed_time": "23:25:53", "remaining_time": "2:13:18", "throughput": 65328.17, "total_tokens": 5510655104} {"current_steps": 14100, "total_steps": 15426, "loss": 0.256, "lr": 3.22084995531053e-05, "epoch": 2.7421958572401053, "percentage": 91.4, "elapsed_time": "23:26:49", "remaining_time": "2:12:18", "throughput": 65331.51, "total_tokens": 5514623360} {"current_steps": 14110, "total_steps": 15426, "loss": 0.2577, "lr": 3.220181909349907e-05, "epoch": 2.7441408149372752, "percentage": 91.47, "elapsed_time": "23:27:40", "remaining_time": "2:11:17", "throughput": 65337.13, "total_tokens": 5518399616} {"current_steps": 14120, "total_steps": 15426, "loss": 0.2558, "lr": 3.219514278901053e-05, "epoch": 2.746085772634445, "percentage": 91.53, "elapsed_time": "23:28:34", "remaining_time": "2:10:17", "throughput": 65341.35, "total_tokens": 5522299520} {"current_steps": 14130, "total_steps": 15426, "loss": 0.2557, "lr": 3.218847063533413e-05, "epoch": 2.748030730331615, "percentage": 91.6, "elapsed_time": "23:29:30", "remaining_time": "2:09:16", "throughput": 65345.89, "total_tokens": 5526311168} {"current_steps": 14140, "total_steps": 15426, "loss": 0.2553, "lr": 3.218180262817055e-05, "epoch": 2.749975688028785, "percentage": 91.66, "elapsed_time": "23:30:26", "remaining_time": "2:08:16", "throughput": 65349.35, "total_tokens": 5530296448} {"current_steps": 14150, "total_steps": 15426, "loss": 0.2578, "lr": 3.217513876322674e-05, "epoch": 2.7519206457259555, "percentage": 91.73, "elapsed_time": "23:31:21", "remaining_time": "2:07:16", "throughput": 65353.14, "total_tokens": 5534222976} {"current_steps": 14160, "total_steps": 15426, "loss": 0.2585, "lr": 3.216847903621581e-05, "epoch": 2.7538656034231255, "percentage": 91.79, "elapsed_time": "23:32:16", "remaining_time": "2:06:16", "throughput": 65357.33, "total_tokens": 5538150528} {"current_steps": 14170, "total_steps": 15426, "loss": 0.2566, "lr": 3.216182344285713e-05, "epoch": 2.7558105611202954, "percentage": 91.86, "elapsed_time": "23:33:11", "remaining_time": "2:05:15", "throughput": 65360.66, "total_tokens": 5541997824} {"current_steps": 14180, "total_steps": 15426, "loss": 0.2545, "lr": 3.215517197887625e-05, "epoch": 2.757755518817466, "percentage": 91.92, "elapsed_time": "23:34:03", "remaining_time": "2:04:15", "throughput": 65366.86, "total_tokens": 5545939456} {"current_steps": 14190, "total_steps": 15426, "loss": 0.2552, "lr": 3.214852464000488e-05, "epoch": 2.759700476514636, "percentage": 91.99, "elapsed_time": "23:34:57", "remaining_time": "2:03:14", "throughput": 65371.07, "total_tokens": 5549853696} {"current_steps": 14200, "total_steps": 15426, "loss": 0.2577, "lr": 3.2141881421980945e-05, "epoch": 2.7616454342118057, "percentage": 92.05, "elapsed_time": "23:35:51", "remaining_time": "2:02:14", "throughput": 65376.05, "total_tokens": 5553802880} {"current_steps": 14210, "total_steps": 15426, "loss": 0.2571, "lr": 3.213524232054851e-05, "epoch": 2.763590391908976, "percentage": 92.12, "elapsed_time": "23:36:47", "remaining_time": "2:01:14", "throughput": 65380.12, "total_tokens": 5557812992} {"current_steps": 14220, "total_steps": 15426, "loss": 0.2596, "lr": 3.21286073314578e-05, "epoch": 2.765535349606146, "percentage": 92.18, "elapsed_time": "23:37:43", "remaining_time": "2:00:14", "throughput": 65383.53, "total_tokens": 5561776640} {"current_steps": 14230, "total_steps": 15426, "loss": 0.2604, "lr": 3.2121976450465155e-05, "epoch": 2.767480307303316, "percentage": 92.25, "elapsed_time": "23:38:37", "remaining_time": "1:59:13", "throughput": 65387.56, "total_tokens": 5565622272} {"current_steps": 14240, "total_steps": 15426, "loss": 0.2536, "lr": 3.211534967333308e-05, "epoch": 2.7694252650004865, "percentage": 92.31, "elapsed_time": "23:39:36", "remaining_time": "1:58:14", "throughput": 65389.28, "total_tokens": 5569612544} {"current_steps": 14250, "total_steps": 15426, "loss": 0.2587, "lr": 3.210872699583019e-05, "epoch": 2.7713702226976564, "percentage": 92.38, "elapsed_time": "23:40:28", "remaining_time": "1:57:13", "throughput": 65394.07, "total_tokens": 5573413888} {"current_steps": 14260, "total_steps": 15426, "loss": 0.2548, "lr": 3.210210841373118e-05, "epoch": 2.7733151803948264, "percentage": 92.44, "elapsed_time": "23:41:21", "remaining_time": "1:56:13", "throughput": 65399.6, "total_tokens": 5577374336} {"current_steps": 14270, "total_steps": 15426, "loss": 0.2555, "lr": 3.2095493922816855e-05, "epoch": 2.7752601380919963, "percentage": 92.51, "elapsed_time": "23:42:12", "remaining_time": "1:55:12", "throughput": 65405.97, "total_tokens": 5581286016} {"current_steps": 14280, "total_steps": 15426, "loss": 0.2573, "lr": 3.2088883518874105e-05, "epoch": 2.7772050957891667, "percentage": 92.57, "elapsed_time": "23:43:04", "remaining_time": "1:54:12", "throughput": 65412.34, "total_tokens": 5585183616} {"current_steps": 14290, "total_steps": 15426, "loss": 0.2588, "lr": 3.208227719769589e-05, "epoch": 2.7791500534863367, "percentage": 92.64, "elapsed_time": "23:43:56", "remaining_time": "1:53:11", "throughput": 65418.0, "total_tokens": 5589094400} {"current_steps": 14300, "total_steps": 15426, "loss": 0.2553, "lr": 3.207567495508124e-05, "epoch": 2.7810950111835067, "percentage": 92.7, "elapsed_time": "23:44:49", "remaining_time": "1:52:11", "throughput": 65422.75, "total_tokens": 5592929536} {"current_steps": 14310, "total_steps": 15426, "loss": 0.2586, "lr": 3.2069076786835205e-05, "epoch": 2.7830399688806766, "percentage": 92.77, "elapsed_time": "23:45:44", "remaining_time": "1:51:11", "throughput": 65426.98, "total_tokens": 5596910592} {"current_steps": 14320, "total_steps": 15426, "loss": 0.2593, "lr": 3.2062482688768904e-05, "epoch": 2.784984926577847, "percentage": 92.83, "elapsed_time": "23:46:36", "remaining_time": "1:50:11", "throughput": 65431.28, "total_tokens": 5600688384} {"current_steps": 14330, "total_steps": 15426, "loss": 0.2578, "lr": 3.205589265669947e-05, "epoch": 2.786929884275017, "percentage": 92.9, "elapsed_time": "23:47:31", "remaining_time": "1:49:10", "throughput": 65435.03, "total_tokens": 5604606080} {"current_steps": 14340, "total_steps": 15426, "loss": 0.2559, "lr": 3.204930668645005e-05, "epoch": 2.788874841972187, "percentage": 92.96, "elapsed_time": "23:48:30", "remaining_time": "1:48:11", "throughput": 65437.26, "total_tokens": 5608634496} {"current_steps": 14350, "total_steps": 15426, "loss": 0.2575, "lr": 3.20427247738498e-05, "epoch": 2.7908197996693573, "percentage": 93.02, "elapsed_time": "23:49:24", "remaining_time": "1:47:10", "throughput": 65441.79, "total_tokens": 5612568448} {"current_steps": 14360, "total_steps": 15426, "loss": 0.2587, "lr": 3.2036146914733854e-05, "epoch": 2.7927647573665273, "percentage": 93.09, "elapsed_time": "23:50:18", "remaining_time": "1:46:10", "throughput": 65445.25, "total_tokens": 5616385280} {"current_steps": 14370, "total_steps": 15426, "loss": 0.2548, "lr": 3.202957310494336e-05, "epoch": 2.7947097150636973, "percentage": 93.15, "elapsed_time": "23:51:11", "remaining_time": "1:45:10", "throughput": 65449.67, "total_tokens": 5620282112} {"current_steps": 14380, "total_steps": 15426, "loss": 0.2588, "lr": 3.202300334032542e-05, "epoch": 2.7966546727608677, "percentage": 93.22, "elapsed_time": "23:52:05", "remaining_time": "1:44:10", "throughput": 65453.95, "total_tokens": 5624143616} {"current_steps": 14390, "total_steps": 15426, "loss": 0.2546, "lr": 3.201643761673308e-05, "epoch": 2.7985996304580376, "percentage": 93.28, "elapsed_time": "23:53:00", "remaining_time": "1:43:10", "throughput": 65457.13, "total_tokens": 5628017536} {"current_steps": 14400, "total_steps": 15426, "loss": 0.2578, "lr": 3.200987593002536e-05, "epoch": 2.8005445881552076, "percentage": 93.35, "elapsed_time": "23:53:54", "remaining_time": "1:42:09", "throughput": 65460.91, "total_tokens": 5631864320} {"current_steps": 14410, "total_steps": 15426, "loss": 0.2612, "lr": 3.200331827606721e-05, "epoch": 2.802489545852378, "percentage": 93.41, "elapsed_time": "23:54:48", "remaining_time": "1:41:09", "throughput": 65464.95, "total_tokens": 5635783936} {"current_steps": 14420, "total_steps": 15426, "loss": 0.2615, "lr": 3.199676465072951e-05, "epoch": 2.804434503549548, "percentage": 93.48, "elapsed_time": "23:55:39", "remaining_time": "1:40:09", "throughput": 65470.36, "total_tokens": 5639606400} {"current_steps": 14430, "total_steps": 15426, "loss": 0.255, "lr": 3.1990215049889046e-05, "epoch": 2.806379461246718, "percentage": 93.54, "elapsed_time": "23:56:32", "remaining_time": "1:39:09", "throughput": 65475.24, "total_tokens": 5643472128} {"current_steps": 14440, "total_steps": 15426, "loss": 0.2567, "lr": 3.198366946942851e-05, "epoch": 2.808324418943888, "percentage": 93.61, "elapsed_time": "23:57:26", "remaining_time": "1:38:09", "throughput": 65479.43, "total_tokens": 5647344512} {"current_steps": 14450, "total_steps": 15426, "loss": 0.2542, "lr": 3.1977127905236514e-05, "epoch": 2.810269376641058, "percentage": 93.67, "elapsed_time": "23:58:23", "remaining_time": "1:37:09", "throughput": 65482.23, "total_tokens": 5651337728} {"current_steps": 14460, "total_steps": 15426, "loss": 0.2587, "lr": 3.197059035320752e-05, "epoch": 2.812214334338228, "percentage": 93.74, "elapsed_time": "23:59:18", "remaining_time": "1:36:09", "throughput": 65485.72, "total_tokens": 5655228416} {"current_steps": 14470, "total_steps": 15426, "loss": 0.2608, "lr": 3.196405680924189e-05, "epoch": 2.814159292035398, "percentage": 93.8, "elapsed_time": "1 day, 0:00:11", "remaining_time": "1:35:09", "throughput": 65490.43, "total_tokens": 5659151744} {"current_steps": 14480, "total_steps": 15426, "loss": 0.2546, "lr": 3.195752726924582e-05, "epoch": 2.816104249732568, "percentage": 93.87, "elapsed_time": "1 day, 0:01:03", "remaining_time": "1:34:08", "throughput": 65495.84, "total_tokens": 5662995200} {"current_steps": 14490, "total_steps": 15426, "loss": 0.2598, "lr": 3.195100172913139e-05, "epoch": 2.8180492074297385, "percentage": 93.93, "elapsed_time": "1 day, 0:01:57", "remaining_time": "1:33:08", "throughput": 65499.67, "total_tokens": 5666859392} {"current_steps": 14500, "total_steps": 15426, "loss": 0.2563, "lr": 3.19444801848165e-05, "epoch": 2.8199941651269085, "percentage": 94.0, "elapsed_time": "1 day, 0:02:51", "remaining_time": "1:32:08", "throughput": 65503.95, "total_tokens": 5670748800} {"current_steps": 14510, "total_steps": 15426, "loss": 0.2542, "lr": 3.1937962632224885e-05, "epoch": 2.8219391228240784, "percentage": 94.06, "elapsed_time": "1 day, 0:03:46", "remaining_time": "1:31:08", "throughput": 65507.97, "total_tokens": 5674703616} {"current_steps": 14520, "total_steps": 15426, "loss": 0.2563, "lr": 3.193144906728609e-05, "epoch": 2.823884080521249, "percentage": 94.13, "elapsed_time": "1 day, 0:04:40", "remaining_time": "1:30:08", "throughput": 65511.71, "total_tokens": 5678612736} {"current_steps": 14530, "total_steps": 15426, "loss": 0.255, "lr": 3.1924939485935494e-05, "epoch": 2.825829038218419, "percentage": 94.19, "elapsed_time": "1 day, 0:05:37", "remaining_time": "1:29:08", "throughput": 65514.75, "total_tokens": 5682591360} {"current_steps": 14540, "total_steps": 15426, "loss": 0.2567, "lr": 3.1918433884114253e-05, "epoch": 2.8277739959155888, "percentage": 94.26, "elapsed_time": "1 day, 0:06:31", "remaining_time": "1:28:08", "throughput": 65519.23, "total_tokens": 5686496896} {"current_steps": 14550, "total_steps": 15426, "loss": 0.2581, "lr": 3.191193225776931e-05, "epoch": 2.829718953612759, "percentage": 94.32, "elapsed_time": "1 day, 0:07:27", "remaining_time": "1:27:08", "throughput": 65523.77, "total_tokens": 5690545792} {"current_steps": 14560, "total_steps": 15426, "loss": 0.2594, "lr": 3.190543460285339e-05, "epoch": 2.831663911309929, "percentage": 94.39, "elapsed_time": "1 day, 0:08:20", "remaining_time": "1:26:08", "throughput": 65528.36, "total_tokens": 5694441472} {"current_steps": 14570, "total_steps": 15426, "loss": 0.2574, "lr": 3.189894091532499e-05, "epoch": 2.833608869007099, "percentage": 94.45, "elapsed_time": "1 day, 0:09:15", "remaining_time": "1:25:08", "throughput": 65531.75, "total_tokens": 5698370432} {"current_steps": 14580, "total_steps": 15426, "loss": 0.2594, "lr": 3.1892451191148346e-05, "epoch": 2.835553826704269, "percentage": 94.52, "elapsed_time": "1 day, 0:10:08", "remaining_time": "1:24:08", "throughput": 65537.63, "total_tokens": 5702314496} {"current_steps": 14590, "total_steps": 15426, "loss": 0.2548, "lr": 3.1885965426293465e-05, "epoch": 2.8374987844014394, "percentage": 94.58, "elapsed_time": "1 day, 0:11:01", "remaining_time": "1:23:08", "throughput": 65542.88, "total_tokens": 5706239872} {"current_steps": 14600, "total_steps": 15426, "loss": 0.2572, "lr": 3.187948361673606e-05, "epoch": 2.8394437420986094, "percentage": 94.65, "elapsed_time": "1 day, 0:11:54", "remaining_time": "1:22:08", "throughput": 65547.43, "total_tokens": 5710112256} {"current_steps": 14610, "total_steps": 15426, "loss": 0.2536, "lr": 3.187300575845759e-05, "epoch": 2.8413886997957793, "percentage": 94.71, "elapsed_time": "1 day, 0:12:49", "remaining_time": "1:21:08", "throughput": 65550.42, "total_tokens": 5714025216} {"current_steps": 14620, "total_steps": 15426, "loss": 0.2594, "lr": 3.186653184744521e-05, "epoch": 2.8433336574929493, "percentage": 94.78, "elapsed_time": "1 day, 0:13:41", "remaining_time": "1:20:08", "throughput": 65556.33, "total_tokens": 5717898496} {"current_steps": 14630, "total_steps": 15426, "loss": 0.2586, "lr": 3.18600618796918e-05, "epoch": 2.8452786151901197, "percentage": 94.84, "elapsed_time": "1 day, 0:14:34", "remaining_time": "1:19:08", "throughput": 65560.41, "total_tokens": 5721783552} {"current_steps": 14640, "total_steps": 15426, "loss": 0.2539, "lr": 3.185359585119591e-05, "epoch": 2.8472235728872897, "percentage": 94.9, "elapsed_time": "1 day, 0:15:31", "remaining_time": "1:18:08", "throughput": 65564.22, "total_tokens": 5725827840} {"current_steps": 14650, "total_steps": 15426, "loss": 0.253, "lr": 3.184713375796178e-05, "epoch": 2.8491685305844596, "percentage": 94.97, "elapsed_time": "1 day, 0:16:24", "remaining_time": "1:17:08", "throughput": 65568.18, "total_tokens": 5729671296} {"current_steps": 14660, "total_steps": 15426, "loss": 0.2569, "lr": 3.1840675595999344e-05, "epoch": 2.85111348828163, "percentage": 95.03, "elapsed_time": "1 day, 0:17:17", "remaining_time": "1:16:08", "throughput": 65573.82, "total_tokens": 5733591168} {"current_steps": 14670, "total_steps": 15426, "loss": 0.2544, "lr": 3.1834221361324155e-05, "epoch": 2.8530584459788, "percentage": 95.1, "elapsed_time": "1 day, 0:18:10", "remaining_time": "1:15:08", "throughput": 65579.09, "total_tokens": 5737535360} {"current_steps": 14680, "total_steps": 15426, "loss": 0.2589, "lr": 3.182777104995744e-05, "epoch": 2.85500340367597, "percentage": 95.16, "elapsed_time": "1 day, 0:19:05", "remaining_time": "1:14:08", "throughput": 65583.06, "total_tokens": 5741533696} {"current_steps": 14690, "total_steps": 15426, "loss": 0.2575, "lr": 3.182132465792609e-05, "epoch": 2.8569483613731403, "percentage": 95.23, "elapsed_time": "1 day, 0:19:56", "remaining_time": "1:13:08", "throughput": 65588.77, "total_tokens": 5745376256} {"current_steps": 14700, "total_steps": 15426, "loss": 0.2567, "lr": 3.181488218126259e-05, "epoch": 2.8588933190703103, "percentage": 95.29, "elapsed_time": "1 day, 0:20:50", "remaining_time": "1:12:08", "throughput": 65593.23, "total_tokens": 5749308928} {"current_steps": 14710, "total_steps": 15426, "loss": 0.259, "lr": 3.180844361600506e-05, "epoch": 2.8608382767674803, "percentage": 95.36, "elapsed_time": "1 day, 0:21:44", "remaining_time": "1:11:08", "throughput": 65597.25, "total_tokens": 5753196160} {"current_steps": 14720, "total_steps": 15426, "loss": 0.2561, "lr": 3.180200895819722e-05, "epoch": 2.8627832344646507, "percentage": 95.42, "elapsed_time": "1 day, 0:22:40", "remaining_time": "1:10:09", "throughput": 65600.4, "total_tokens": 5757155584} {"current_steps": 14730, "total_steps": 15426, "loss": 0.2587, "lr": 3.1795578203888424e-05, "epoch": 2.8647281921618206, "percentage": 95.49, "elapsed_time": "1 day, 0:23:33", "remaining_time": "1:09:09", "throughput": 65605.38, "total_tokens": 5761047680} {"current_steps": 14740, "total_steps": 15426, "loss": 0.2581, "lr": 3.178915134913357e-05, "epoch": 2.8666731498589906, "percentage": 95.55, "elapsed_time": "1 day, 0:24:28", "remaining_time": "1:08:09", "throughput": 65609.2, "total_tokens": 5764979584} {"current_steps": 14750, "total_steps": 15426, "loss": 0.2551, "lr": 3.178272838999316e-05, "epoch": 2.8686181075561605, "percentage": 95.62, "elapsed_time": "1 day, 0:25:24", "remaining_time": "1:07:09", "throughput": 65612.28, "total_tokens": 5768906240} {"current_steps": 14760, "total_steps": 15426, "loss": 0.257, "lr": 3.1776309322533274e-05, "epoch": 2.8705630652533305, "percentage": 95.68, "elapsed_time": "1 day, 0:26:21", "remaining_time": "1:06:09", "throughput": 65614.65, "total_tokens": 5772898688} {"current_steps": 14770, "total_steps": 15426, "loss": 0.2587, "lr": 3.1769894142825536e-05, "epoch": 2.872508022950501, "percentage": 95.75, "elapsed_time": "1 day, 0:27:15", "remaining_time": "1:05:10", "throughput": 65618.98, "total_tokens": 5776782976} {"current_steps": 14780, "total_steps": 15426, "loss": 0.2549, "lr": 3.176348284694712e-05, "epoch": 2.874452980647671, "percentage": 95.81, "elapsed_time": "1 day, 0:28:11", "remaining_time": "1:04:10", "throughput": 65621.64, "total_tokens": 5780723456} {"current_steps": 14790, "total_steps": 15426, "loss": 0.2606, "lr": 3.175707543098075e-05, "epoch": 2.876397938344841, "percentage": 95.88, "elapsed_time": "1 day, 0:29:04", "remaining_time": "1:03:10", "throughput": 65625.86, "total_tokens": 5784590720} {"current_steps": 14800, "total_steps": 15426, "loss": 0.2576, "lr": 3.1750671891014653e-05, "epoch": 2.878342896042011, "percentage": 95.94, "elapsed_time": "1 day, 0:29:57", "remaining_time": "1:02:10", "throughput": 65631.02, "total_tokens": 5788471296} {"current_steps": 14810, "total_steps": 15426, "loss": 0.2573, "lr": 3.174427222314262e-05, "epoch": 2.880287853739181, "percentage": 96.01, "elapsed_time": "1 day, 0:30:50", "remaining_time": "1:01:10", "throughput": 65635.42, "total_tokens": 5792332672} {"current_steps": 14820, "total_steps": 15426, "loss": 0.2554, "lr": 3.173787642346391e-05, "epoch": 2.882232811436351, "percentage": 96.07, "elapsed_time": "1 day, 0:31:42", "remaining_time": "1:00:10", "throughput": 65640.22, "total_tokens": 5796179968} {"current_steps": 14830, "total_steps": 15426, "loss": 0.2574, "lr": 3.173148448808331e-05, "epoch": 2.8841777691335215, "percentage": 96.14, "elapsed_time": "1 day, 0:32:37", "remaining_time": "0:59:10", "throughput": 65642.93, "total_tokens": 5800055552} {"current_steps": 14840, "total_steps": 15426, "loss": 0.2565, "lr": 3.172509641311107e-05, "epoch": 2.8861227268306915, "percentage": 96.2, "elapsed_time": "1 day, 0:33:30", "remaining_time": "0:58:11", "throughput": 65647.31, "total_tokens": 5803908736} {"current_steps": 14850, "total_steps": 15426, "loss": 0.2546, "lr": 3.171871219466293e-05, "epoch": 2.8880676845278614, "percentage": 96.27, "elapsed_time": "1 day, 0:34:23", "remaining_time": "0:57:11", "throughput": 65651.12, "total_tokens": 5807751808} {"current_steps": 14860, "total_steps": 15426, "loss": 0.2595, "lr": 3.171233182886011e-05, "epoch": 2.890012642225032, "percentage": 96.33, "elapsed_time": "1 day, 0:35:16", "remaining_time": "0:56:11", "throughput": 65655.86, "total_tokens": 5811595904} {"current_steps": 14870, "total_steps": 15426, "loss": 0.2567, "lr": 3.170595531182928e-05, "epoch": 2.891957599922202, "percentage": 96.4, "elapsed_time": "1 day, 0:36:07", "remaining_time": "0:55:11", "throughput": 65661.18, "total_tokens": 5815440128} {"current_steps": 14880, "total_steps": 15426, "loss": 0.2554, "lr": 3.169958263970256e-05, "epoch": 2.8939025576193718, "percentage": 96.46, "elapsed_time": "1 day, 0:37:01", "remaining_time": "0:54:11", "throughput": 65665.57, "total_tokens": 5819379712} {"current_steps": 14890, "total_steps": 15426, "loss": 0.2615, "lr": 3.169321380861751e-05, "epoch": 2.8958475153165417, "percentage": 96.53, "elapsed_time": "1 day, 0:37:56", "remaining_time": "0:53:12", "throughput": 65669.71, "total_tokens": 5823327616} {"current_steps": 14900, "total_steps": 15426, "loss": 0.2592, "lr": 3.168684881471711e-05, "epoch": 2.8977924730137117, "percentage": 96.59, "elapsed_time": "1 day, 0:38:48", "remaining_time": "0:52:12", "throughput": 65674.66, "total_tokens": 5827224320} {"current_steps": 14910, "total_steps": 15426, "loss": 0.256, "lr": 3.168048765414979e-05, "epoch": 2.899737430710882, "percentage": 96.65, "elapsed_time": "1 day, 0:39:42", "remaining_time": "0:51:12", "throughput": 65678.92, "total_tokens": 5831113088} {"current_steps": 14920, "total_steps": 15426, "loss": 0.2579, "lr": 3.167413032306936e-05, "epoch": 2.901682388408052, "percentage": 96.72, "elapsed_time": "1 day, 0:40:37", "remaining_time": "0:50:12", "throughput": 65682.61, "total_tokens": 5835048832} {"current_steps": 14930, "total_steps": 15426, "loss": 0.26, "lr": 3.166777681763504e-05, "epoch": 2.903627346105222, "percentage": 96.78, "elapsed_time": "1 day, 0:41:30", "remaining_time": "0:49:13", "throughput": 65687.0, "total_tokens": 5838959104} {"current_steps": 14940, "total_steps": 15426, "loss": 0.2576, "lr": 3.166142713401144e-05, "epoch": 2.9055723038023924, "percentage": 96.85, "elapsed_time": "1 day, 0:42:25", "remaining_time": "0:48:13", "throughput": 65691.3, "total_tokens": 5842917760} {"current_steps": 14950, "total_steps": 15426, "loss": 0.2575, "lr": 3.165508126836857e-05, "epoch": 2.9075172614995624, "percentage": 96.91, "elapsed_time": "1 day, 0:43:19", "remaining_time": "0:47:13", "throughput": 65695.29, "total_tokens": 5846829568} {"current_steps": 14960, "total_steps": 15426, "loss": 0.2567, "lr": 3.164873921688177e-05, "epoch": 2.9094622191967323, "percentage": 96.98, "elapsed_time": "1 day, 0:44:10", "remaining_time": "0:46:13", "throughput": 65700.37, "total_tokens": 5850667008} {"current_steps": 14970, "total_steps": 15426, "loss": 0.2556, "lr": 3.164240097573178e-05, "epoch": 2.9114071768939027, "percentage": 97.04, "elapsed_time": "1 day, 0:45:03", "remaining_time": "0:45:14", "throughput": 65705.1, "total_tokens": 5854586752} {"current_steps": 14980, "total_steps": 15426, "loss": 0.2591, "lr": 3.163606654110467e-05, "epoch": 2.9133521345910727, "percentage": 97.11, "elapsed_time": "1 day, 0:45:55", "remaining_time": "0:44:14", "throughput": 65709.42, "total_tokens": 5858384512} {"current_steps": 14990, "total_steps": 15426, "loss": 0.2584, "lr": 3.162973590919187e-05, "epoch": 2.9152970922882426, "percentage": 97.17, "elapsed_time": "1 day, 0:46:48", "remaining_time": "0:43:14", "throughput": 65713.81, "total_tokens": 5862253440} {"current_steps": 15000, "total_steps": 15426, "loss": 0.2539, "lr": 3.162340907619012e-05, "epoch": 2.917242049985413, "percentage": 97.24, "elapsed_time": "1 day, 0:47:43", "remaining_time": "0:42:15", "throughput": 65718.06, "total_tokens": 5866198656} {"current_steps": 15000, "total_steps": 15426, "eval_loss": 0.2619342803955078, "epoch": 2.917242049985413, "percentage": 97.24, "elapsed_time": "1 day, 0:47:44", "remaining_time": "0:42:15", "throughput": 65717.23, "total_tokens": 5866198656} {"current_steps": 15010, "total_steps": 15426, "loss": 0.26, "lr": 3.1617086038301516e-05, "epoch": 2.919187007682583, "percentage": 97.3, "elapsed_time": "1 day, 0:48:54", "remaining_time": "0:41:15", "throughput": 65709.89, "total_tokens": 5870169856} {"current_steps": 15020, "total_steps": 15426, "loss": 0.258, "lr": 3.161076679173344e-05, "epoch": 2.921131965379753, "percentage": 97.37, "elapsed_time": "1 day, 0:49:48", "remaining_time": "0:40:16", "throughput": 65714.62, "total_tokens": 5874101760} {"current_steps": 15030, "total_steps": 15426, "loss": 0.2592, "lr": 3.1604451332698575e-05, "epoch": 2.9230769230769234, "percentage": 97.43, "elapsed_time": "1 day, 0:50:43", "remaining_time": "0:39:16", "throughput": 65718.11, "total_tokens": 5878042752} {"current_steps": 15040, "total_steps": 15426, "loss": 0.2583, "lr": 3.1598139657414923e-05, "epoch": 2.9250218807740933, "percentage": 97.5, "elapsed_time": "1 day, 0:51:42", "remaining_time": "0:38:17", "throughput": 65718.9, "total_tokens": 5882013952} {"current_steps": 15050, "total_steps": 15426, "loss": 0.2575, "lr": 3.159183176210574e-05, "epoch": 2.9269668384712633, "percentage": 97.56, "elapsed_time": "1 day, 0:52:37", "remaining_time": "0:37:17", "throughput": 65722.94, "total_tokens": 5885991040} {"current_steps": 15060, "total_steps": 15426, "loss": 0.2576, "lr": 3.1585527642999595e-05, "epoch": 2.9289117961684332, "percentage": 97.63, "elapsed_time": "1 day, 0:53:32", "remaining_time": "0:36:17", "throughput": 65726.68, "total_tokens": 5889917184} {"current_steps": 15070, "total_steps": 15426, "loss": 0.2554, "lr": 3.1579227296330294e-05, "epoch": 2.930856753865603, "percentage": 97.69, "elapsed_time": "1 day, 0:54:26", "remaining_time": "0:35:18", "throughput": 65730.74, "total_tokens": 5893827712} {"current_steps": 15080, "total_steps": 15426, "loss": 0.2579, "lr": 3.157293071833691e-05, "epoch": 2.9328017115627736, "percentage": 97.76, "elapsed_time": "1 day, 0:55:20", "remaining_time": "0:34:18", "throughput": 65734.48, "total_tokens": 5897743616} {"current_steps": 15090, "total_steps": 15426, "loss": 0.2574, "lr": 3.156663790526375e-05, "epoch": 2.9347466692599435, "percentage": 97.82, "elapsed_time": "1 day, 0:56:14", "remaining_time": "0:33:18", "throughput": 65737.95, "total_tokens": 5901572352} {"current_steps": 15100, "total_steps": 15426, "loss": 0.2558, "lr": 3.156034885336039e-05, "epoch": 2.9366916269571135, "percentage": 97.89, "elapsed_time": "1 day, 0:57:08", "remaining_time": "0:32:19", "throughput": 65742.19, "total_tokens": 5905496064} {"current_steps": 15110, "total_steps": 15426, "loss": 0.2569, "lr": 3.155406355888161e-05, "epoch": 2.938636584654284, "percentage": 97.95, "elapsed_time": "1 day, 0:58:01", "remaining_time": "0:31:19", "throughput": 65746.6, "total_tokens": 5909425152} {"current_steps": 15120, "total_steps": 15426, "loss": 0.2556, "lr": 3.1547782018087407e-05, "epoch": 2.940581542351454, "percentage": 98.02, "elapsed_time": "1 day, 0:58:56", "remaining_time": "0:30:20", "throughput": 65751.37, "total_tokens": 5913457024} {"current_steps": 15130, "total_steps": 15426, "loss": 0.2577, "lr": 3.154150422724299e-05, "epoch": 2.942526500048624, "percentage": 98.08, "elapsed_time": "1 day, 0:59:50", "remaining_time": "0:29:20", "throughput": 65755.39, "total_tokens": 5917375616} {"current_steps": 15140, "total_steps": 15426, "loss": 0.2609, "lr": 3.1535230182618783e-05, "epoch": 2.944471457745794, "percentage": 98.15, "elapsed_time": "1 day, 1:00:44", "remaining_time": "0:28:20", "throughput": 65758.98, "total_tokens": 5921220352} {"current_steps": 15150, "total_steps": 15426, "loss": 0.2578, "lr": 3.1528959880490387e-05, "epoch": 2.946416415442964, "percentage": 98.21, "elapsed_time": "1 day, 1:01:38", "remaining_time": "0:27:21", "throughput": 65763.61, "total_tokens": 5925211776} {"current_steps": 15160, "total_steps": 15426, "loss": 0.2589, "lr": 3.152269331713859e-05, "epoch": 2.948361373140134, "percentage": 98.28, "elapsed_time": "1 day, 1:02:32", "remaining_time": "0:26:21", "throughput": 65767.56, "total_tokens": 5929122048} {"current_steps": 15170, "total_steps": 15426, "loss": 0.2552, "lr": 3.151643048884935e-05, "epoch": 2.9503063308373045, "percentage": 98.34, "elapsed_time": "1 day, 1:03:22", "remaining_time": "0:25:22", "throughput": 65773.06, "total_tokens": 5932917888} {"current_steps": 15180, "total_steps": 15426, "loss": 0.2554, "lr": 3.151017139191379e-05, "epoch": 2.9522512885344745, "percentage": 98.41, "elapsed_time": "1 day, 1:04:13", "remaining_time": "0:24:22", "throughput": 65778.91, "total_tokens": 5936774400} {"current_steps": 15190, "total_steps": 15426, "loss": 0.258, "lr": 3.150391602262818e-05, "epoch": 2.9541962462316445, "percentage": 98.47, "elapsed_time": "1 day, 1:05:05", "remaining_time": "0:23:23", "throughput": 65783.2, "total_tokens": 5940609024} {"current_steps": 15200, "total_steps": 15426, "loss": 0.2565, "lr": 3.149766437729394e-05, "epoch": 2.9561412039288144, "percentage": 98.53, "elapsed_time": "1 day, 1:05:59", "remaining_time": "0:22:23", "throughput": 65786.82, "total_tokens": 5944446976} {"current_steps": 15210, "total_steps": 15426, "loss": 0.2576, "lr": 3.1491416452217635e-05, "epoch": 2.9580861616259844, "percentage": 98.6, "elapsed_time": "1 day, 1:06:52", "remaining_time": "0:21:23", "throughput": 65791.51, "total_tokens": 5948365440} {"current_steps": 15220, "total_steps": 15426, "loss": 0.2555, "lr": 3.1485172243710954e-05, "epoch": 2.9600311193231548, "percentage": 98.66, "elapsed_time": "1 day, 1:07:48", "remaining_time": "0:20:24", "throughput": 65794.89, "total_tokens": 5952354432} {"current_steps": 15230, "total_steps": 15426, "loss": 0.2569, "lr": 3.1478931748090676e-05, "epoch": 2.9619760770203247, "percentage": 98.73, "elapsed_time": "1 day, 1:08:39", "remaining_time": "0:19:24", "throughput": 65800.45, "total_tokens": 5956203008} {"current_steps": 15240, "total_steps": 15426, "loss": 0.2595, "lr": 3.147269496167873e-05, "epoch": 2.9639210347174947, "percentage": 98.79, "elapsed_time": "1 day, 1:09:35", "remaining_time": "0:18:25", "throughput": 65802.89, "total_tokens": 5960142848} {"current_steps": 15250, "total_steps": 15426, "loss": 0.2549, "lr": 3.1466461880802105e-05, "epoch": 2.965865992414665, "percentage": 98.86, "elapsed_time": "1 day, 1:10:30", "remaining_time": "0:17:25", "throughput": 65806.53, "total_tokens": 5964111616} {"current_steps": 15260, "total_steps": 15426, "loss": 0.2542, "lr": 3.146023250179291e-05, "epoch": 2.967810950111835, "percentage": 98.92, "elapsed_time": "1 day, 1:11:25", "remaining_time": "0:16:26", "throughput": 65810.9, "total_tokens": 5968062592} {"current_steps": 15270, "total_steps": 15426, "loss": 0.2566, "lr": 3.145400682098833e-05, "epoch": 2.969755907809005, "percentage": 98.99, "elapsed_time": "1 day, 1:12:18", "remaining_time": "0:15:26", "throughput": 65815.71, "total_tokens": 5972003840} {"current_steps": 15280, "total_steps": 15426, "loss": 0.2575, "lr": 3.14477848347306e-05, "epoch": 2.9717008655061754, "percentage": 99.05, "elapsed_time": "1 day, 1:13:12", "remaining_time": "0:14:27", "throughput": 65819.65, "total_tokens": 5975931264} {"current_steps": 15290, "total_steps": 15426, "loss": 0.2571, "lr": 3.144156653936703e-05, "epoch": 2.9736458232033454, "percentage": 99.12, "elapsed_time": "1 day, 1:14:07", "remaining_time": "0:13:28", "throughput": 65822.99, "total_tokens": 5979877888} {"current_steps": 15300, "total_steps": 15426, "loss": 0.2556, "lr": 3.1435351931250004e-05, "epoch": 2.9755907809005153, "percentage": 99.18, "elapsed_time": "1 day, 1:15:01", "remaining_time": "0:12:28", "throughput": 65827.36, "total_tokens": 5983829376} {"current_steps": 15310, "total_steps": 15426, "loss": 0.2589, "lr": 3.142914100673692e-05, "epoch": 2.9775357385976857, "percentage": 99.25, "elapsed_time": "1 day, 1:15:56", "remaining_time": "0:11:29", "throughput": 65831.54, "total_tokens": 5987802752} {"current_steps": 15320, "total_steps": 15426, "loss": 0.2585, "lr": 3.1422933762190235e-05, "epoch": 2.9794806962948557, "percentage": 99.31, "elapsed_time": "1 day, 1:16:50", "remaining_time": "0:10:29", "throughput": 65835.8, "total_tokens": 5991729536} {"current_steps": 15330, "total_steps": 15426, "loss": 0.2571, "lr": 3.141673019397741e-05, "epoch": 2.9814256539920256, "percentage": 99.38, "elapsed_time": "1 day, 1:17:45", "remaining_time": "0:09:30", "throughput": 65839.94, "total_tokens": 5995736448} {"current_steps": 15340, "total_steps": 15426, "loss": 0.2574, "lr": 3.141053029847095e-05, "epoch": 2.9833706116891956, "percentage": 99.44, "elapsed_time": "1 day, 1:18:37", "remaining_time": "0:08:30", "throughput": 65844.35, "total_tokens": 5999552896} {"current_steps": 15350, "total_steps": 15426, "loss": 0.2598, "lr": 3.140433407204835e-05, "epoch": 2.985315569386366, "percentage": 99.51, "elapsed_time": "1 day, 1:19:31", "remaining_time": "0:07:31", "throughput": 65848.35, "total_tokens": 6003470848} {"current_steps": 15360, "total_steps": 15426, "loss": 0.26, "lr": 3.1398141511092124e-05, "epoch": 2.987260527083536, "percentage": 99.57, "elapsed_time": "1 day, 1:20:25", "remaining_time": "0:06:31", "throughput": 65852.41, "total_tokens": 6007394304} {"current_steps": 15370, "total_steps": 15426, "loss": 0.2578, "lr": 3.1391952611989736e-05, "epoch": 2.989205484780706, "percentage": 99.64, "elapsed_time": "1 day, 1:21:17", "remaining_time": "0:05:32", "throughput": 65856.84, "total_tokens": 6011248256} {"current_steps": 15380, "total_steps": 15426, "loss": 0.2588, "lr": 3.138576737113369e-05, "epoch": 2.991150442477876, "percentage": 99.7, "elapsed_time": "1 day, 1:22:14", "remaining_time": "0:04:33", "throughput": 65859.79, "total_tokens": 6015245440} {"current_steps": 15390, "total_steps": 15426, "loss": 0.2569, "lr": 3.137958578492143e-05, "epoch": 2.9930954001750463, "percentage": 99.77, "elapsed_time": "1 day, 1:23:07", "remaining_time": "0:03:33", "throughput": 65863.87, "total_tokens": 6019151360} {"current_steps": 15400, "total_steps": 15426, "loss": 0.2541, "lr": 3.137340784975535e-05, "epoch": 2.9950403578722162, "percentage": 99.83, "elapsed_time": "1 day, 1:24:01", "remaining_time": "0:02:34", "throughput": 65868.2, "total_tokens": 6023083904} {"current_steps": 15410, "total_steps": 15426, "loss": 0.2569, "lr": 3.136723356204285e-05, "epoch": 2.996985315569386, "percentage": 99.9, "elapsed_time": "1 day, 1:24:56", "remaining_time": "0:01:34", "throughput": 65871.96, "total_tokens": 6027023488} {"current_steps": 15420, "total_steps": 15426, "loss": 0.2594, "lr": 3.136106291819622e-05, "epoch": 2.9989302732665566, "percentage": 99.96, "elapsed_time": "1 day, 1:25:50", "remaining_time": "0:00:35", "throughput": 65876.59, "total_tokens": 6031011456} {"current_steps": 15426, "total_steps": 15426, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1 day, 1:28:46", "remaining_time": "0:00:00", "throughput": 65773.1, "total_tokens": 6033116672}