| {"current_steps": 10, "total_steps": 14493, "loss": 1.3759, "lr": 4.9977515176118345e-05, "epoch": 0.0020703397945187755, "percentage": 0.07, "elapsed_time": "0:01:06", "remaining_time": "1 day, 2:42:41", "throughput": 54940.73, "total_tokens": 3647872} |
| {"current_steps": 20, "total_steps": 14493, "loss": 0.7328, "lr": 4.9952567580506e-05, "epoch": 0.004140679589037551, "percentage": 0.14, "elapsed_time": "0:02:28", "remaining_time": "1 day, 5:55:44", "throughput": 48134.84, "total_tokens": 7166848} |
| {"current_steps": 30, "total_steps": 14493, "loss": 0.5783, "lr": 4.992765730738634e-05, "epoch": 0.006211019383556326, "percentage": 0.21, "elapsed_time": "0:03:32", "remaining_time": "1 day, 4:30:14", "throughput": 50421.93, "total_tokens": 10732288} |
| {"current_steps": 40, "total_steps": 14493, "loss": 0.5205, "lr": 4.9902784263792476e-05, "epoch": 0.008281359178075102, "percentage": 0.28, "elapsed_time": "0:04:31", "remaining_time": "1 day, 3:14:27", "throughput": 52838.58, "total_tokens": 14340992} |
| {"current_steps": 50, "total_steps": 14493, "loss": 0.4906, "lr": 4.987794835708133e-05, "epoch": 0.010351698972593876, "percentage": 0.34, "elapsed_time": "0:05:26", "remaining_time": "1 day, 2:12:41", "throughput": 54831.47, "total_tokens": 17911680} |
| {"current_steps": 60, "total_steps": 14493, "loss": 0.4716, "lr": 4.985314949493234e-05, "epoch": 0.012422038767112653, "percentage": 0.41, "elapsed_time": "0:06:26", "remaining_time": "1 day, 1:49:12", "throughput": 55756.84, "total_tokens": 21545472} |
| {"current_steps": 70, "total_steps": 14493, "loss": 0.4557, "lr": 4.982838758534584e-05, "epoch": 0.014492378561631427, "percentage": 0.48, "elapsed_time": "0:07:29", "remaining_time": "1 day, 1:43:47", "throughput": 55653.68, "total_tokens": 25019392} |
| {"current_steps": 80, "total_steps": 14493, "loss": 0.44, "lr": 4.980366253664179e-05, "epoch": 0.016562718356150204, "percentage": 0.55, "elapsed_time": "0:09:16", "remaining_time": "1 day, 3:50:29", "throughput": 51429.76, "total_tokens": 28611968} |
| {"current_steps": 90, "total_steps": 14493, "loss": 0.4327, "lr": 4.977897425745825e-05, "epoch": 0.018633058150668978, "percentage": 0.62, "elapsed_time": "0:10:13", "remaining_time": "1 day, 3:17:07", "throughput": 52415.35, "total_tokens": 32172160} |
| {"current_steps": 100, "total_steps": 14493, "loss": 0.426, "lr": 4.975432265674997e-05, "epoch": 0.020703397945187753, "percentage": 0.69, "elapsed_time": "0:12:35", "remaining_time": "1 day, 6:13:24", "throughput": 47255.93, "total_tokens": 35723264} |
| {"current_steps": 110, "total_steps": 14493, "loss": 0.4176, "lr": 4.972970764378705e-05, "epoch": 0.02277373773970653, "percentage": 0.76, "elapsed_time": "0:15:23", "remaining_time": "1 day, 9:32:14", "throughput": 42511.83, "total_tokens": 39254144} |
| {"current_steps": 120, "total_steps": 14493, "loss": 0.4126, "lr": 4.970512912815344e-05, "epoch": 0.024844077534225305, "percentage": 0.83, "elapsed_time": "0:18:35", "remaining_time": "1 day, 13:07:20", "throughput": 38420.2, "total_tokens": 42867840} |
| {"current_steps": 130, "total_steps": 14493, "loss": 0.4026, "lr": 4.968058701974564e-05, "epoch": 0.02691441732874408, "percentage": 0.9, "elapsed_time": "0:21:13", "remaining_time": "1 day, 15:05:48", "throughput": 36490.39, "total_tokens": 46485888} |
| {"current_steps": 140, "total_steps": 14493, "loss": 0.4011, "lr": 4.96560812287712e-05, "epoch": 0.028984757123262855, "percentage": 0.97, "elapsed_time": "0:24:17", "remaining_time": "1 day, 17:30:13", "throughput": 34396.95, "total_tokens": 50129664} |
| {"current_steps": 150, "total_steps": 14493, "loss": 0.3964, "lr": 4.963161166574748e-05, "epoch": 0.03105509691778163, "percentage": 1.03, "elapsed_time": "0:27:15", "remaining_time": "1 day, 19:26:37", "throughput": 32844.43, "total_tokens": 53720832} |
| {"current_steps": 160, "total_steps": 14493, "loss": 0.3912, "lr": 4.960717824150013e-05, "epoch": 0.03312543671230041, "percentage": 1.1, "elapsed_time": "0:29:45", "remaining_time": "1 day, 20:25:06", "throughput": 32151.81, "total_tokens": 57392384} |
| {"current_steps": 170, "total_steps": 14493, "loss": 0.3867, "lr": 4.9582780867161893e-05, "epoch": 0.03519577650681918, "percentage": 1.17, "elapsed_time": "0:32:21", "remaining_time": "1 day, 21:25:41", "throughput": 31383.56, "total_tokens": 60918016} |
| {"current_steps": 180, "total_steps": 14493, "loss": 0.3891, "lr": 4.955841945417105e-05, "epoch": 0.037266116301337956, "percentage": 1.24, "elapsed_time": "0:33:50", "remaining_time": "1 day, 20:50:35", "throughput": 31757.13, "total_tokens": 64473600} |
| {"current_steps": 190, "total_steps": 14493, "loss": 0.3813, "lr": 4.953409391427024e-05, "epoch": 0.03933645609585673, "percentage": 1.31, "elapsed_time": "0:34:46", "remaining_time": "1 day, 19:37:22", "throughput": 32617.73, "total_tokens": 68045056} |
| {"current_steps": 200, "total_steps": 14493, "loss": 0.3831, "lr": 4.950980415950502e-05, "epoch": 0.041406795890375506, "percentage": 1.38, "elapsed_time": "0:35:44", "remaining_time": "1 day, 18:34:05", "throughput": 33453.51, "total_tokens": 71735936} |
| {"current_steps": 210, "total_steps": 14493, "loss": 0.3758, "lr": 4.9485550102222575e-05, "epoch": 0.04347713568489428, "percentage": 1.45, "elapsed_time": "0:36:38", "remaining_time": "1 day, 17:32:36", "throughput": 34277.39, "total_tokens": 75372544} |
| {"current_steps": 220, "total_steps": 14493, "loss": 0.3729, "lr": 4.946133165507037e-05, "epoch": 0.04554747547941306, "percentage": 1.52, "elapsed_time": "0:37:38", "remaining_time": "1 day, 16:41:54", "throughput": 35000.31, "total_tokens": 79042176} |
| {"current_steps": 230, "total_steps": 14493, "loss": 0.3698, "lr": 4.943714873099483e-05, "epoch": 0.047617815273931836, "percentage": 1.59, "elapsed_time": "0:38:36", "remaining_time": "1 day, 15:54:08", "throughput": 35676.98, "total_tokens": 82642944} |
| {"current_steps": 240, "total_steps": 14493, "loss": 0.3727, "lr": 4.9413001243240024e-05, "epoch": 0.04968815506845061, "percentage": 1.66, "elapsed_time": "0:39:29", "remaining_time": "1 day, 15:05:41", "throughput": 36347.61, "total_tokens": 86139392} |
| {"current_steps": 250, "total_steps": 14493, "loss": 0.3685, "lr": 4.938888910534637e-05, "epoch": 0.051758494862969386, "percentage": 1.72, "elapsed_time": "0:40:25", "remaining_time": "1 day, 14:23:23", "throughput": 36980.25, "total_tokens": 89707520} |
| {"current_steps": 260, "total_steps": 14493, "loss": 0.361, "lr": 4.936481223114932e-05, "epoch": 0.05382883465748816, "percentage": 1.79, "elapsed_time": "0:41:18", "remaining_time": "1 day, 13:41:38", "throughput": 37597.95, "total_tokens": 93199872} |
| {"current_steps": 270, "total_steps": 14493, "loss": 0.3638, "lr": 4.934077053477808e-05, "epoch": 0.055899174452006935, "percentage": 1.86, "elapsed_time": "0:42:14", "remaining_time": "1 day, 13:05:03", "throughput": 38158.98, "total_tokens": 96707840} |
| {"current_steps": 280, "total_steps": 14493, "loss": 0.3609, "lr": 4.931676393065431e-05, "epoch": 0.05796951424652571, "percentage": 1.93, "elapsed_time": "0:43:11", "remaining_time": "1 day, 12:32:07", "throughput": 38676.45, "total_tokens": 100215936} |
| {"current_steps": 290, "total_steps": 14493, "loss": 0.3586, "lr": 4.929279233349088e-05, "epoch": 0.060039854041044484, "percentage": 2.0, "elapsed_time": "0:44:15", "remaining_time": "1 day, 12:07:13", "throughput": 39112.58, "total_tokens": 103845760} |
| {"current_steps": 300, "total_steps": 14493, "loss": 0.3597, "lr": 4.926885565829051e-05, "epoch": 0.06211019383556326, "percentage": 2.07, "elapsed_time": "0:46:23", "remaining_time": "1 day, 12:34:32", "throughput": 38569.5, "total_tokens": 107346176} |
| {"current_steps": 310, "total_steps": 14493, "loss": 0.358, "lr": 4.924495382034461e-05, "epoch": 0.06418053363008204, "percentage": 2.14, "elapsed_time": "0:48:37", "remaining_time": "1 day, 13:04:41", "throughput": 38004.2, "total_tokens": 110878208} |
| {"current_steps": 320, "total_steps": 14493, "loss": 0.3545, "lr": 4.9221086735231975e-05, "epoch": 0.06625087342460081, "percentage": 2.21, "elapsed_time": "0:50:20", "remaining_time": "1 day, 13:09:26", "throughput": 37876.17, "total_tokens": 114393472} |
| {"current_steps": 330, "total_steps": 14493, "loss": 0.3541, "lr": 4.919725431881751e-05, "epoch": 0.06832121321911959, "percentage": 2.28, "elapsed_time": "0:52:18", "remaining_time": "1 day, 13:24:52", "throughput": 37569.11, "total_tokens": 117905152} |
| {"current_steps": 340, "total_steps": 14493, "loss": 0.3508, "lr": 4.917345648725101e-05, "epoch": 0.07039155301363836, "percentage": 2.35, "elapsed_time": "0:54:24", "remaining_time": "1 day, 13:45:07", "throughput": 37238.07, "total_tokens": 121579520} |
| {"current_steps": 350, "total_steps": 14493, "loss": 0.3513, "lr": 4.914969315696596e-05, "epoch": 0.07246189280815714, "percentage": 2.41, "elapsed_time": "0:55:57", "remaining_time": "1 day, 13:41:15", "throughput": 37258.73, "total_tokens": 125099264} |
| {"current_steps": 360, "total_steps": 14493, "loss": 0.349, "lr": 4.912596424467818e-05, "epoch": 0.07453223260267591, "percentage": 2.48, "elapsed_time": "0:56:54", "remaining_time": "1 day, 13:14:17", "throughput": 37688.64, "total_tokens": 128697728} |
| {"current_steps": 370, "total_steps": 14493, "loss": 0.3474, "lr": 4.910226966738475e-05, "epoch": 0.07660257239719469, "percentage": 2.55, "elapsed_time": "0:57:49", "remaining_time": "1 day, 12:46:55", "throughput": 38131.93, "total_tokens": 132282112} |
| {"current_steps": 380, "total_steps": 14493, "loss": 0.3468, "lr": 4.9078609342362666e-05, "epoch": 0.07867291219171346, "percentage": 2.62, "elapsed_time": "0:58:45", "remaining_time": "1 day, 12:22:20", "throughput": 38564.19, "total_tokens": 135963776} |
| {"current_steps": 390, "total_steps": 14493, "loss": 0.343, "lr": 4.905498318716775e-05, "epoch": 0.08074325198623224, "percentage": 2.69, "elapsed_time": "0:59:35", "remaining_time": "1 day, 11:54:40", "throughput": 38992.25, "total_tokens": 139400192} |
| {"current_steps": 400, "total_steps": 14493, "loss": 0.3461, "lr": 4.9031391119633295e-05, "epoch": 0.08281359178075101, "percentage": 2.76, "elapsed_time": "1:00:39", "remaining_time": "1 day, 11:37:13", "throughput": 39292.31, "total_tokens": 143009280} |
| {"current_steps": 410, "total_steps": 14493, "loss": 0.3462, "lr": 4.9007833057869e-05, "epoch": 0.08488393157526979, "percentage": 2.83, "elapsed_time": "1:01:35", "remaining_time": "1 day, 11:15:24", "throughput": 39678.39, "total_tokens": 146618624} |
| {"current_steps": 420, "total_steps": 14493, "loss": 0.3426, "lr": 4.898430892025967e-05, "epoch": 0.08695427136978856, "percentage": 2.9, "elapsed_time": "1:02:26", "remaining_time": "1 day, 10:52:20", "throughput": 40083.63, "total_tokens": 150180480} |
| {"current_steps": 430, "total_steps": 14493, "loss": 0.3391, "lr": 4.896081862546415e-05, "epoch": 0.08902461116430734, "percentage": 2.97, "elapsed_time": "1:03:44", "remaining_time": "1 day, 10:44:30", "throughput": 40214.32, "total_tokens": 153789824} |
| {"current_steps": 440, "total_steps": 14493, "loss": 0.34, "lr": 4.8937362092414e-05, "epoch": 0.09109495095882612, "percentage": 3.04, "elapsed_time": "1:04:46", "remaining_time": "1 day, 10:28:51", "throughput": 40473.02, "total_tokens": 157301504} |
| {"current_steps": 450, "total_steps": 14493, "loss": 0.333, "lr": 4.891393924031244e-05, "epoch": 0.0931652907533449, "percentage": 3.1, "elapsed_time": "1:05:46", "remaining_time": "1 day, 10:12:28", "throughput": 40742.82, "total_tokens": 160780032} |
| {"current_steps": 460, "total_steps": 14493, "loss": 0.3417, "lr": 4.8890549988633095e-05, "epoch": 0.09523563054786367, "percentage": 3.17, "elapsed_time": "1:06:47", "remaining_time": "1 day, 9:57:43", "throughput": 41015.6, "total_tokens": 164380928} |
| {"current_steps": 470, "total_steps": 14493, "loss": 0.3396, "lr": 4.8867194257118907e-05, "epoch": 0.09730597034238245, "percentage": 3.24, "elapsed_time": "1:07:42", "remaining_time": "1 day, 9:40:15", "throughput": 41342.44, "total_tokens": 167962368} |
| {"current_steps": 480, "total_steps": 14493, "loss": 0.3369, "lr": 4.884387196578093e-05, "epoch": 0.09937631013690122, "percentage": 3.31, "elapsed_time": "1:08:34", "remaining_time": "1 day, 9:22:04", "throughput": 41672.73, "total_tokens": 171472640} |
| {"current_steps": 490, "total_steps": 14493, "loss": 0.3355, "lr": 4.882058303489718e-05, "epoch": 0.10144664993142, "percentage": 3.38, "elapsed_time": "1:09:28", "remaining_time": "1 day, 9:05:39", "throughput": 41980.5, "total_tokens": 175015552} |
| {"current_steps": 500, "total_steps": 14493, "loss": 0.3328, "lr": 4.8797327385011496e-05, "epoch": 0.10351698972593877, "percentage": 3.45, "elapsed_time": "1:10:50", "remaining_time": "1 day, 9:02:45", "throughput": 42019.27, "total_tokens": 178620032} |
| {"current_steps": 510, "total_steps": 14493, "loss": 0.3301, "lr": 4.8774104936932425e-05, "epoch": 0.10558732952045755, "percentage": 3.52, "elapsed_time": "1:12:33", "remaining_time": "1 day, 9:09:11", "throughput": 41855.6, "total_tokens": 182200832} |
| {"current_steps": 520, "total_steps": 14493, "loss": 0.3329, "lr": 4.8750915611732076e-05, "epoch": 0.10765766931497632, "percentage": 3.59, "elapsed_time": "1:14:43", "remaining_time": "1 day, 9:27:44", "throughput": 41411.92, "total_tokens": 185651968} |
| {"current_steps": 530, "total_steps": 14493, "loss": 0.3314, "lr": 4.8727759330744986e-05, "epoch": 0.1097280091094951, "percentage": 3.66, "elapsed_time": "1:15:47", "remaining_time": "1 day, 9:16:56", "throughput": 41586.94, "total_tokens": 189134592} |
| {"current_steps": 540, "total_steps": 14493, "loss": 0.3293, "lr": 4.870463601556696e-05, "epoch": 0.11179834890401387, "percentage": 3.73, "elapsed_time": "1:17:31", "remaining_time": "1 day, 9:23:12", "throughput": 41432.24, "total_tokens": 192726912} |
| {"current_steps": 550, "total_steps": 14493, "loss": 0.3285, "lr": 4.8681545588054075e-05, "epoch": 0.11386868869853264, "percentage": 3.79, "elapsed_time": "1:19:13", "remaining_time": "1 day, 9:28:31", "throughput": 41292.95, "total_tokens": 196295680} |
| {"current_steps": 560, "total_steps": 14493, "loss": 0.3294, "lr": 4.8658487970321404e-05, "epoch": 0.11593902849305142, "percentage": 3.86, "elapsed_time": "1:20:51", "remaining_time": "1 day, 9:31:45", "throughput": 41211.69, "total_tokens": 199936384} |
| {"current_steps": 570, "total_steps": 14493, "loss": 0.3283, "lr": 4.863546308474209e-05, "epoch": 0.1180093682875702, "percentage": 3.93, "elapsed_time": "1:21:51", "remaining_time": "1 day, 9:19:21", "throughput": 41426.05, "total_tokens": 203449088} |
| {"current_steps": 580, "total_steps": 14493, "loss": 0.3296, "lr": 4.86124708539461e-05, "epoch": 0.12007970808208897, "percentage": 4.0, "elapsed_time": "1:22:43", "remaining_time": "1 day, 9:04:31", "throughput": 41700.32, "total_tokens": 206992768} |
| {"current_steps": 590, "total_steps": 14493, "loss": 0.3295, "lr": 4.8589511200819216e-05, "epoch": 0.12215004787660774, "percentage": 4.07, "elapsed_time": "1:23:35", "remaining_time": "1 day, 8:49:54", "throughput": 41977.78, "total_tokens": 210553216} |
| {"current_steps": 600, "total_steps": 14493, "loss": 0.3224, "lr": 4.8566584048501926e-05, "epoch": 0.12422038767112652, "percentage": 4.14, "elapsed_time": "1:24:27", "remaining_time": "1 day, 8:35:45", "throughput": 42254.06, "total_tokens": 214135808} |
| {"current_steps": 610, "total_steps": 14493, "loss": 0.326, "lr": 4.854368932038835e-05, "epoch": 0.1262907274656453, "percentage": 4.21, "elapsed_time": "1:25:22", "remaining_time": "1 day, 8:23:03", "throughput": 42521.56, "total_tokens": 217816960} |
| {"current_steps": 620, "total_steps": 14493, "loss": 0.3231, "lr": 4.8520826940125144e-05, "epoch": 0.12836106726016408, "percentage": 4.28, "elapsed_time": "1:26:13", "remaining_time": "1 day, 8:09:24", "throughput": 42784.21, "total_tokens": 221351168} |
| {"current_steps": 630, "total_steps": 14493, "loss": 0.3224, "lr": 4.849799683161046e-05, "epoch": 0.13043140705468284, "percentage": 4.35, "elapsed_time": "1:27:05", "remaining_time": "1 day, 7:56:33", "throughput": 43051.92, "total_tokens": 224982528} |
| {"current_steps": 640, "total_steps": 14493, "loss": 0.3205, "lr": 4.8475198918992835e-05, "epoch": 0.13250174684920163, "percentage": 4.42, "elapsed_time": "1:27:58", "remaining_time": "1 day, 7:44:22", "throughput": 43308.45, "total_tokens": 228618496} |
| {"current_steps": 650, "total_steps": 14493, "loss": 0.3217, "lr": 4.845243312667023e-05, "epoch": 0.1345720866437204, "percentage": 4.48, "elapsed_time": "1:28:49", "remaining_time": "1 day, 7:31:34", "throughput": 43555.36, "total_tokens": 232112896} |
| {"current_steps": 660, "total_steps": 14493, "loss": 0.3259, "lr": 4.842969937928884e-05, "epoch": 0.13664242643823918, "percentage": 4.55, "elapsed_time": "1:29:40", "remaining_time": "1 day, 7:19:25", "throughput": 43804.36, "total_tokens": 235679872} |
| {"current_steps": 670, "total_steps": 14493, "loss": 0.3236, "lr": 4.840699760174217e-05, "epoch": 0.13871276623275794, "percentage": 4.62, "elapsed_time": "1:30:35", "remaining_time": "1 day, 7:09:03", "throughput": 44023.44, "total_tokens": 239293440} |
| {"current_steps": 680, "total_steps": 14493, "loss": 0.3231, "lr": 4.8384327719169906e-05, "epoch": 0.14078310602727673, "percentage": 4.69, "elapsed_time": "1:31:49", "remaining_time": "1 day, 7:05:16", "throughput": 44084.5, "total_tokens": 242885376} |
| {"current_steps": 690, "total_steps": 14493, "loss": 0.3202, "lr": 4.836168965695694e-05, "epoch": 0.1428534458217955, "percentage": 4.76, "elapsed_time": "1:32:49", "remaining_time": "1 day, 6:56:59", "throughput": 44250.16, "total_tokens": 246462208} |
| {"current_steps": 700, "total_steps": 14493, "loss": 0.3184, "lr": 4.8339083340732304e-05, "epoch": 0.14492378561631428, "percentage": 4.83, "elapsed_time": "1:33:43", "remaining_time": "1 day, 6:46:56", "throughput": 44452.37, "total_tokens": 249998592} |
| {"current_steps": 710, "total_steps": 14493, "loss": 0.3217, "lr": 4.8316508696368154e-05, "epoch": 0.14699412541083307, "percentage": 4.9, "elapsed_time": "1:34:38", "remaining_time": "1 day, 6:37:07", "throughput": 44661.95, "total_tokens": 253596288} |
| {"current_steps": 720, "total_steps": 14493, "loss": 0.3207, "lr": 4.8293965649978714e-05, "epoch": 0.14906446520535183, "percentage": 4.97, "elapsed_time": "1:35:32", "remaining_time": "1 day, 6:27:33", "throughput": 44874.1, "total_tokens": 257230464} |
| {"current_steps": 730, "total_steps": 14493, "loss": 0.3195, "lr": 4.8271454127919364e-05, "epoch": 0.15113480499987061, "percentage": 5.04, "elapsed_time": "1:36:24", "remaining_time": "1 day, 6:17:39", "throughput": 45085.47, "total_tokens": 260801536} |
| {"current_steps": 740, "total_steps": 14493, "loss": 0.3221, "lr": 4.824897405678549e-05, "epoch": 0.15320514479438938, "percentage": 5.11, "elapsed_time": "1:37:15", "remaining_time": "1 day, 6:07:32", "throughput": 45302.43, "total_tokens": 264360448} |
| {"current_steps": 750, "total_steps": 14493, "loss": 0.3197, "lr": 4.8226525363411576e-05, "epoch": 0.15527548458890816, "percentage": 5.17, "elapsed_time": "1:38:07", "remaining_time": "1 day, 5:57:56", "throughput": 45504.17, "total_tokens": 267889792} |
| {"current_steps": 760, "total_steps": 14493, "loss": 0.3162, "lr": 4.820410797487017e-05, "epoch": 0.15734582438342692, "percentage": 5.24, "elapsed_time": "1:38:58", "remaining_time": "1 day, 5:48:30", "throughput": 45706.41, "total_tokens": 271434880} |
| {"current_steps": 770, "total_steps": 14493, "loss": 0.3163, "lr": 4.818172181847091e-05, "epoch": 0.1594161641779457, "percentage": 5.31, "elapsed_time": "1:39:51", "remaining_time": "1 day, 5:39:49", "throughput": 45898.59, "total_tokens": 275023872} |
| {"current_steps": 780, "total_steps": 14493, "loss": 0.3196, "lr": 4.81593668217595e-05, "epoch": 0.16148650397246447, "percentage": 5.38, "elapsed_time": "1:40:45", "remaining_time": "1 day, 5:31:23", "throughput": 46089.27, "total_tokens": 278630400} |
| {"current_steps": 790, "total_steps": 14493, "loss": 0.3149, "lr": 4.813704291251675e-05, "epoch": 0.16355684376698326, "percentage": 5.45, "elapsed_time": "1:41:37", "remaining_time": "1 day, 5:22:37", "throughput": 46278.37, "total_tokens": 282163456} |
| {"current_steps": 800, "total_steps": 14493, "loss": 0.3184, "lr": 4.811475001875759e-05, "epoch": 0.16562718356150202, "percentage": 5.52, "elapsed_time": "1:42:30", "remaining_time": "1 day, 5:14:40", "throughput": 46462.82, "total_tokens": 285788672} |
| {"current_steps": 810, "total_steps": 14493, "loss": 0.3171, "lr": 4.8092488068730105e-05, "epoch": 0.1676975233560208, "percentage": 5.59, "elapsed_time": "1:43:26", "remaining_time": "1 day, 5:07:19", "throughput": 46632.48, "total_tokens": 289412480} |
| {"current_steps": 820, "total_steps": 14493, "loss": 0.3166, "lr": 4.807025699091452e-05, "epoch": 0.16976786315053957, "percentage": 5.66, "elapsed_time": "1:44:15", "remaining_time": "1 day, 4:58:26", "throughput": 46822.01, "total_tokens": 292894720} |
| {"current_steps": 830, "total_steps": 14493, "loss": 0.3128, "lr": 4.8048056714022325e-05, "epoch": 0.17183820294505836, "percentage": 5.73, "elapsed_time": "1:45:09", "remaining_time": "1 day, 4:51:09", "throughput": 46989.11, "total_tokens": 296495616} |
| {"current_steps": 840, "total_steps": 14493, "loss": 0.3112, "lr": 4.802588716699519e-05, "epoch": 0.17390854273957712, "percentage": 5.8, "elapsed_time": "1:46:05", "remaining_time": "1 day, 4:44:14", "throughput": 47138.2, "total_tokens": 300037504} |
| {"current_steps": 850, "total_steps": 14493, "loss": 0.3163, "lr": 4.8003748279004156e-05, "epoch": 0.1759788825340959, "percentage": 5.86, "elapsed_time": "1:46:59", "remaining_time": "1 day, 4:37:11", "throughput": 47285.9, "total_tokens": 303537280} |
| {"current_steps": 860, "total_steps": 14493, "loss": 0.3135, "lr": 4.798163997944854e-05, "epoch": 0.17804922232861467, "percentage": 5.93, "elapsed_time": "1:47:52", "remaining_time": "1 day, 4:30:02", "throughput": 47450.93, "total_tokens": 307119744} |
| {"current_steps": 870, "total_steps": 14493, "loss": 0.3109, "lr": 4.79595621979551e-05, "epoch": 0.18011956212313346, "percentage": 6.0, "elapsed_time": "1:48:44", "remaining_time": "1 day, 4:22:48", "throughput": 47615.56, "total_tokens": 310678784} |
| {"current_steps": 880, "total_steps": 14493, "loss": 0.3126, "lr": 4.793751486437702e-05, "epoch": 0.18218990191765225, "percentage": 6.07, "elapsed_time": "1:49:37", "remaining_time": "1 day, 4:15:56", "throughput": 47765.56, "total_tokens": 314201088} |
| {"current_steps": 890, "total_steps": 14493, "loss": 0.3124, "lr": 4.7915497908793064e-05, "epoch": 0.184260241712171, "percentage": 6.14, "elapsed_time": "1:50:29", "remaining_time": "1 day, 4:08:47", "throughput": 47922.84, "total_tokens": 317705600} |
| {"current_steps": 900, "total_steps": 14493, "loss": 0.3134, "lr": 4.7893511261506516e-05, "epoch": 0.1863305815066898, "percentage": 6.21, "elapsed_time": "1:51:19", "remaining_time": "1 day, 4:01:25", "throughput": 48090.01, "total_tokens": 321226880} |
| {"current_steps": 910, "total_steps": 14493, "loss": 0.3107, "lr": 4.787155485304435e-05, "epoch": 0.18840092130120856, "percentage": 6.28, "elapsed_time": "1:52:13", "remaining_time": "1 day, 3:55:13", "throughput": 48231.58, "total_tokens": 324790528} |
| {"current_steps": 920, "total_steps": 14493, "loss": 0.3113, "lr": 4.784962861415629e-05, "epoch": 0.19047126109572735, "percentage": 6.35, "elapsed_time": "1:53:15", "remaining_time": "1 day, 3:50:55", "throughput": 48334.5, "total_tokens": 328456960} |
| {"current_steps": 930, "total_steps": 14493, "loss": 0.3095, "lr": 4.7827732475813884e-05, "epoch": 0.1925416008902461, "percentage": 6.42, "elapsed_time": "1:54:07", "remaining_time": "1 day, 3:44:29", "throughput": 48493.75, "total_tokens": 332082688} |
| {"current_steps": 940, "total_steps": 14493, "loss": 0.3111, "lr": 4.7805866369209576e-05, "epoch": 0.1946119406847649, "percentage": 6.49, "elapsed_time": "1:55:09", "remaining_time": "1 day, 3:40:17", "throughput": 48602.11, "total_tokens": 335800576} |
| {"current_steps": 950, "total_steps": 14493, "loss": 0.3101, "lr": 4.778403022575583e-05, "epoch": 0.19668228047928366, "percentage": 6.55, "elapsed_time": "1:56:03", "remaining_time": "1 day, 3:34:23", "throughput": 48741.12, "total_tokens": 339384576} |
| {"current_steps": 960, "total_steps": 14493, "loss": 0.3123, "lr": 4.7762223977084195e-05, "epoch": 0.19875262027380244, "percentage": 6.62, "elapsed_time": "1:56:51", "remaining_time": "1 day, 3:27:26", "throughput": 48899.03, "total_tokens": 342876544} |
| {"current_steps": 970, "total_steps": 14493, "loss": 0.3097, "lr": 4.774044755504444e-05, "epoch": 0.2008229600683212, "percentage": 6.69, "elapsed_time": "1:57:45", "remaining_time": "1 day, 3:21:47", "throughput": 49034.88, "total_tokens": 346475520} |
| {"current_steps": 980, "total_steps": 14493, "loss": 0.3071, "lr": 4.7718700891703616e-05, "epoch": 0.20289329986284, "percentage": 6.76, "elapsed_time": "1:58:44", "remaining_time": "1 day, 3:17:22", "throughput": 49146.56, "total_tokens": 350161536} |
| {"current_steps": 990, "total_steps": 14493, "loss": 0.3072, "lr": 4.7696983919345215e-05, "epoch": 0.20496363965735875, "percentage": 6.83, "elapsed_time": "1:59:42", "remaining_time": "1 day, 3:12:46", "throughput": 49247.9, "total_tokens": 353728896} |
| {"current_steps": 1000, "total_steps": 14493, "loss": 0.3068, "lr": 4.7675296570468216e-05, "epoch": 0.20703397945187754, "percentage": 6.9, "elapsed_time": "2:00:34", "remaining_time": "1 day, 3:07:01", "throughput": 49388.56, "total_tokens": 357324416} |
| {"current_steps": 1010, "total_steps": 14493, "loss": 0.3061, "lr": 4.76536387777863e-05, "epoch": 0.2091043192463963, "percentage": 6.97, "elapsed_time": "2:01:28", "remaining_time": "1 day, 3:01:44", "throughput": 49521.02, "total_tokens": 360957696} |
| {"current_steps": 1020, "total_steps": 14493, "loss": 0.3075, "lr": 4.7632010474226915e-05, "epoch": 0.2111746590409151, "percentage": 7.04, "elapsed_time": "2:02:21", "remaining_time": "1 day, 2:56:08", "throughput": 49658.93, "total_tokens": 364556672} |
| {"current_steps": 1030, "total_steps": 14493, "loss": 0.3075, "lr": 4.761041159293035e-05, "epoch": 0.21324499883543385, "percentage": 7.11, "elapsed_time": "2:03:12", "remaining_time": "1 day, 2:50:23", "throughput": 49794.05, "total_tokens": 368092288} |
| {"current_steps": 1040, "total_steps": 14493, "loss": 0.3058, "lr": 4.7588842067249e-05, "epoch": 0.21531533862995264, "percentage": 7.18, "elapsed_time": "2:04:05", "remaining_time": "1 day, 2:45:12", "throughput": 49927.22, "total_tokens": 371734144} |
| {"current_steps": 1050, "total_steps": 14493, "loss": 0.3071, "lr": 4.756730183074637e-05, "epoch": 0.21738567842447143, "percentage": 7.24, "elapsed_time": "2:04:59", "remaining_time": "1 day, 2:40:15", "throughput": 50047.21, "total_tokens": 375329152} |
| {"current_steps": 1060, "total_steps": 14493, "loss": 0.305, "lr": 4.7545790817196314e-05, "epoch": 0.2194560182189902, "percentage": 7.31, "elapsed_time": "2:05:51", "remaining_time": "1 day, 2:35:00", "throughput": 50173.67, "total_tokens": 378898432} |
| {"current_steps": 1070, "total_steps": 14493, "loss": 0.305, "lr": 4.752430896058212e-05, "epoch": 0.22152635801350898, "percentage": 7.38, "elapsed_time": "2:06:45", "remaining_time": "1 day, 2:30:05", "throughput": 50296.69, "total_tokens": 382512384} |
| {"current_steps": 1080, "total_steps": 14493, "loss": 0.3051, "lr": 4.750285619509567e-05, "epoch": 0.22359669780802774, "percentage": 7.45, "elapsed_time": "2:07:38", "remaining_time": "1 day, 2:25:17", "throughput": 50405.91, "total_tokens": 386044544} |
| {"current_steps": 1090, "total_steps": 14493, "loss": 0.3048, "lr": 4.7481432455136644e-05, "epoch": 0.22566703760254653, "percentage": 7.52, "elapsed_time": "2:08:32", "remaining_time": "1 day, 2:20:30", "throughput": 50528.12, "total_tokens": 389678208} |
| {"current_steps": 1100, "total_steps": 14493, "loss": 0.3026, "lr": 4.7460037675311584e-05, "epoch": 0.2277373773970653, "percentage": 7.59, "elapsed_time": "2:09:23", "remaining_time": "1 day, 2:15:24", "throughput": 50653.74, "total_tokens": 393251712} |
| {"current_steps": 1110, "total_steps": 14493, "loss": 0.3064, "lr": 4.7438671790433126e-05, "epoch": 0.22980771719158408, "percentage": 7.66, "elapsed_time": "2:10:16", "remaining_time": "1 day, 2:10:42", "throughput": 50769.26, "total_tokens": 396843264} |
| {"current_steps": 1120, "total_steps": 14493, "loss": 0.301, "lr": 4.741733473551915e-05, "epoch": 0.23187805698610284, "percentage": 7.73, "elapsed_time": "2:11:08", "remaining_time": "1 day, 2:05:46", "throughput": 50890.5, "total_tokens": 400410240} |
| {"current_steps": 1130, "total_steps": 14493, "loss": 0.3031, "lr": 4.7396026445791966e-05, "epoch": 0.23394839678062163, "percentage": 7.8, "elapsed_time": "2:11:59", "remaining_time": "1 day, 2:00:53", "throughput": 51014.11, "total_tokens": 404008192} |
| {"current_steps": 1140, "total_steps": 14493, "loss": 0.3039, "lr": 4.737474685667742e-05, "epoch": 0.2360187365751404, "percentage": 7.87, "elapsed_time": "2:12:49", "remaining_time": "1 day, 1:55:52", "throughput": 51133.3, "total_tokens": 407528064} |
| {"current_steps": 1150, "total_steps": 14493, "loss": 0.3053, "lr": 4.7353495903804165e-05, "epoch": 0.23808907636965917, "percentage": 7.93, "elapsed_time": "2:13:44", "remaining_time": "1 day, 1:51:43", "throughput": 51226.35, "total_tokens": 411058816} |
| {"current_steps": 1160, "total_steps": 14493, "loss": 0.3034, "lr": 4.733227352300277e-05, "epoch": 0.24015941616417794, "percentage": 8.0, "elapsed_time": "2:14:35", "remaining_time": "1 day, 1:46:57", "throughput": 51327.38, "total_tokens": 414485504} |
| {"current_steps": 1170, "total_steps": 14493, "loss": 0.3055, "lr": 4.731107965030496e-05, "epoch": 0.24222975595869672, "percentage": 8.07, "elapsed_time": "2:15:27", "remaining_time": "1 day, 1:42:30", "throughput": 51440.02, "total_tokens": 418084992} |
| {"current_steps": 1180, "total_steps": 14493, "loss": 0.3009, "lr": 4.728991422194278e-05, "epoch": 0.24430009575321548, "percentage": 8.14, "elapsed_time": "2:16:23", "remaining_time": "1 day, 1:38:50", "throughput": 51538.72, "total_tokens": 421778304} |
| {"current_steps": 1190, "total_steps": 14493, "loss": 0.3028, "lr": 4.726877717434773e-05, "epoch": 0.24637043554773427, "percentage": 8.21, "elapsed_time": "2:17:17", "remaining_time": "1 day, 1:34:47", "throughput": 51642.55, "total_tokens": 425406720} |
| {"current_steps": 1200, "total_steps": 14493, "loss": 0.3038, "lr": 4.724766844415013e-05, "epoch": 0.24844077534225303, "percentage": 8.28, "elapsed_time": "2:18:11", "remaining_time": "1 day, 1:30:46", "throughput": 51744.45, "total_tokens": 429027456} |
| {"current_steps": 1210, "total_steps": 14493, "loss": 0.2999, "lr": 4.722658796817813e-05, "epoch": 0.2505111151367718, "percentage": 8.35, "elapsed_time": "2:19:02", "remaining_time": "1 day, 1:26:17", "throughput": 51855.15, "total_tokens": 432585472} |
| {"current_steps": 1220, "total_steps": 14493, "loss": 0.3015, "lr": 4.7205535683457044e-05, "epoch": 0.2525814549312906, "percentage": 8.42, "elapsed_time": "2:19:53", "remaining_time": "1 day, 1:22:00", "throughput": 51954.78, "total_tokens": 436097920} |
| {"current_steps": 1230, "total_steps": 14493, "loss": 0.299, "lr": 4.7184511527208484e-05, "epoch": 0.2546517947258094, "percentage": 8.49, "elapsed_time": "2:20:46", "remaining_time": "1 day, 1:17:55", "throughput": 52061.79, "total_tokens": 439727872} |
| {"current_steps": 1240, "total_steps": 14493, "loss": 0.2987, "lr": 4.7163515436849644e-05, "epoch": 0.25672213452032816, "percentage": 8.56, "elapsed_time": "2:21:40", "remaining_time": "1 day, 1:14:10", "throughput": 52165.05, "total_tokens": 443417216} |
| {"current_steps": 1250, "total_steps": 14493, "loss": 0.2971, "lr": 4.714254734999245e-05, "epoch": 0.2587924743148469, "percentage": 8.62, "elapsed_time": "2:22:30", "remaining_time": "1 day, 1:09:42", "throughput": 52274.32, "total_tokens": 446946304} |
| {"current_steps": 1260, "total_steps": 14493, "loss": 0.2994, "lr": 4.712160720444284e-05, "epoch": 0.2608628141093657, "percentage": 8.69, "elapsed_time": "2:23:18", "remaining_time": "1 day, 1:05:01", "throughput": 52381.83, "total_tokens": 450387456} |
| {"current_steps": 1270, "total_steps": 14493, "loss": 0.2987, "lr": 4.710069493819992e-05, "epoch": 0.2629331539038845, "percentage": 8.76, "elapsed_time": "2:24:08", "remaining_time": "1 day, 1:00:48", "throughput": 52491.36, "total_tokens": 453982848} |
| {"current_steps": 1280, "total_steps": 14493, "loss": 0.3013, "lr": 4.70798104894553e-05, "epoch": 0.26500349369840326, "percentage": 8.83, "elapsed_time": "2:25:03", "remaining_time": "1 day, 0:57:19", "throughput": 52583.69, "total_tokens": 457641600} |
| {"current_steps": 1290, "total_steps": 14493, "loss": 0.3009, "lr": 4.705895379659219e-05, "epoch": 0.267073833492922, "percentage": 8.9, "elapsed_time": "2:25:52", "remaining_time": "1 day, 0:53:03", "throughput": 52691.04, "total_tokens": 461191168} |
| {"current_steps": 1300, "total_steps": 14493, "loss": 0.2989, "lr": 4.7038124798184766e-05, "epoch": 0.2691441732874408, "percentage": 8.97, "elapsed_time": "2:27:05", "remaining_time": "1 day, 0:52:44", "throughput": 52656.23, "total_tokens": 464715008} |
| {"current_steps": 1310, "total_steps": 14493, "loss": 0.2969, "lr": 4.7017323432997304e-05, "epoch": 0.2712145130819596, "percentage": 9.04, "elapsed_time": "2:28:04", "remaining_time": "1 day, 0:50:07", "throughput": 52725.86, "total_tokens": 468440576} |
| {"current_steps": 1320, "total_steps": 14493, "loss": 0.2974, "lr": 4.6996549639983506e-05, "epoch": 0.27328485287647836, "percentage": 9.11, "elapsed_time": "2:28:57", "remaining_time": "1 day, 0:46:32", "throughput": 52811.15, "total_tokens": 472001664} |
| {"current_steps": 1330, "total_steps": 14493, "loss": 0.2975, "lr": 4.697580335828569e-05, "epoch": 0.2753551926709971, "percentage": 9.18, "elapsed_time": "2:29:49", "remaining_time": "1 day, 0:42:52", "throughput": 52903.92, "total_tokens": 475600384} |
| {"current_steps": 1340, "total_steps": 14493, "loss": 0.299, "lr": 4.6955084527234076e-05, "epoch": 0.2774255324655159, "percentage": 9.25, "elapsed_time": "2:30:41", "remaining_time": "1 day, 0:39:06", "throughput": 52998.3, "total_tokens": 479173504} |
| {"current_steps": 1350, "total_steps": 14493, "loss": 0.2984, "lr": 4.6934393086346034e-05, "epoch": 0.2794958722600347, "percentage": 9.31, "elapsed_time": "2:31:33", "remaining_time": "1 day, 0:35:28", "throughput": 53086.98, "total_tokens": 482738560} |
| {"current_steps": 1360, "total_steps": 14493, "loss": 0.2977, "lr": 4.6913728975325324e-05, "epoch": 0.28156621205455346, "percentage": 9.38, "elapsed_time": "2:32:23", "remaining_time": "1 day, 0:31:35", "throughput": 53180.08, "total_tokens": 486252672} |
| {"current_steps": 1370, "total_steps": 14493, "loss": 0.295, "lr": 4.6893092134061393e-05, "epoch": 0.2836365518490722, "percentage": 9.45, "elapsed_time": "2:33:14", "remaining_time": "1 day, 0:27:56", "throughput": 53271.75, "total_tokens": 489830912} |
| {"current_steps": 1380, "total_steps": 14493, "loss": 0.2965, "lr": 4.687248250262859e-05, "epoch": 0.285706891643591, "percentage": 9.52, "elapsed_time": "2:34:06", "remaining_time": "1 day, 0:24:17", "throughput": 53360.82, "total_tokens": 493376256} |
| {"current_steps": 1390, "total_steps": 14493, "loss": 0.2965, "lr": 4.685190002128548e-05, "epoch": 0.2877772314381098, "percentage": 9.59, "elapsed_time": "2:35:01", "remaining_time": "1 day, 0:21:23", "throughput": 53443.52, "total_tokens": 497112832} |
| {"current_steps": 1400, "total_steps": 14493, "loss": 0.2988, "lr": 4.6831344630474114e-05, "epoch": 0.28984757123262855, "percentage": 9.66, "elapsed_time": "2:35:50", "remaining_time": "1 day, 0:17:29", "throughput": 53540.2, "total_tokens": 500643328} |
| {"current_steps": 1410, "total_steps": 14493, "loss": 0.2978, "lr": 4.6810816270819276e-05, "epoch": 0.2919179110271473, "percentage": 9.73, "elapsed_time": "2:36:45", "remaining_time": "1 day, 0:14:30", "throughput": 53607.44, "total_tokens": 504201728} |
| {"current_steps": 1420, "total_steps": 14493, "loss": 0.2977, "lr": 4.679031488312777e-05, "epoch": 0.29398825082166613, "percentage": 9.8, "elapsed_time": "2:37:45", "remaining_time": "1 day, 0:12:26", "throughput": 53653.55, "total_tokens": 507879552} |
| {"current_steps": 1430, "total_steps": 14493, "loss": 0.2968, "lr": 4.6769840408387717e-05, "epoch": 0.2960585906161849, "percentage": 9.87, "elapsed_time": "2:38:36", "remaining_time": "1 day, 0:08:55", "throughput": 53743.79, "total_tokens": 511465344} |
| {"current_steps": 1440, "total_steps": 14493, "loss": 0.2987, "lr": 4.674939278776787e-05, "epoch": 0.29812893041070365, "percentage": 9.94, "elapsed_time": "2:39:27", "remaining_time": "1 day, 0:05:24", "throughput": 53836.38, "total_tokens": 515076608} |
| {"current_steps": 1450, "total_steps": 14493, "loss": 0.295, "lr": 4.672897196261683e-05, "epoch": 0.3001992702052224, "percentage": 10.0, "elapsed_time": "2:40:19", "remaining_time": "1 day, 0:02:07", "throughput": 53916.84, "total_tokens": 518643584} |
| {"current_steps": 1460, "total_steps": 14493, "loss": 0.2957, "lr": 4.670857787446238e-05, "epoch": 0.30226960999974123, "percentage": 10.07, "elapsed_time": "2:41:05", "remaining_time": "23:58:05", "throughput": 54009.59, "total_tokens": 522054272} |
| {"current_steps": 1470, "total_steps": 14493, "loss": 0.2938, "lr": 4.668821046501082e-05, "epoch": 0.30433994979426, "percentage": 10.14, "elapsed_time": "2:41:53", "remaining_time": "23:54:12", "throughput": 54101.87, "total_tokens": 525509504} |
| {"current_steps": 1480, "total_steps": 14493, "loss": 0.2931, "lr": 4.6667869676146194e-05, "epoch": 0.30641028958877875, "percentage": 10.21, "elapsed_time": "2:42:43", "remaining_time": "23:50:45", "throughput": 54183.98, "total_tokens": 529021952} |
| {"current_steps": 1490, "total_steps": 14493, "loss": 0.2957, "lr": 4.6647555449929645e-05, "epoch": 0.3084806293832975, "percentage": 10.28, "elapsed_time": "2:43:33", "remaining_time": "23:47:22", "throughput": 54267.59, "total_tokens": 532564608} |
| {"current_steps": 1500, "total_steps": 14493, "loss": 0.2962, "lr": 4.662726772859869e-05, "epoch": 0.3105509691778163, "percentage": 10.35, "elapsed_time": "2:44:26", "remaining_time": "23:44:21", "throughput": 54352.71, "total_tokens": 536257024} |
| {"current_steps": 1510, "total_steps": 14493, "loss": 0.2941, "lr": 4.660700645456655e-05, "epoch": 0.3126213089723351, "percentage": 10.42, "elapsed_time": "2:45:18", "remaining_time": "23:41:16", "throughput": 54431.42, "total_tokens": 539858688} |
| {"current_steps": 1520, "total_steps": 14493, "loss": 0.295, "lr": 4.658677157042149e-05, "epoch": 0.31469164876685385, "percentage": 10.49, "elapsed_time": "2:46:10", "remaining_time": "23:38:19", "throughput": 54496.84, "total_tokens": 543379840} |
| {"current_steps": 1530, "total_steps": 14493, "loss": 0.2961, "lr": 4.656656301892605e-05, "epoch": 0.3167619885613726, "percentage": 10.56, "elapsed_time": "2:46:57", "remaining_time": "23:34:37", "throughput": 54596.99, "total_tokens": 546952064} |
| {"current_steps": 1540, "total_steps": 14493, "loss": 0.2921, "lr": 4.6546380743016465e-05, "epoch": 0.3188323283558914, "percentage": 10.63, "elapsed_time": "2:47:46", "remaining_time": "23:31:12", "throughput": 54673.98, "total_tokens": 550392960} |
| {"current_steps": 1550, "total_steps": 14493, "loss": 0.2928, "lr": 4.652622468580193e-05, "epoch": 0.3209026681504102, "percentage": 10.69, "elapsed_time": "2:48:42", "remaining_time": "23:28:44", "throughput": 54726.39, "total_tokens": 553958016} |
| {"current_steps": 1560, "total_steps": 14493, "loss": 0.2915, "lr": 4.650609479056392e-05, "epoch": 0.32297300794492895, "percentage": 10.76, "elapsed_time": "2:49:35", "remaining_time": "23:26:00", "throughput": 54794.52, "total_tokens": 557571200} |
| {"current_steps": 1570, "total_steps": 14493, "loss": 0.2929, "lr": 4.648599100075556e-05, "epoch": 0.32504334773944776, "percentage": 10.83, "elapsed_time": "2:50:28", "remaining_time": "23:23:11", "throughput": 54863.13, "total_tokens": 561154816} |
| {"current_steps": 1580, "total_steps": 14493, "loss": 0.2944, "lr": 4.6465913260000945e-05, "epoch": 0.3271136875339665, "percentage": 10.9, "elapsed_time": "2:51:18", "remaining_time": "23:20:05", "throughput": 54939.85, "total_tokens": 564707712} |
| {"current_steps": 1590, "total_steps": 14493, "loss": 0.291, "lr": 4.644586151209444e-05, "epoch": 0.3291840273284853, "percentage": 10.97, "elapsed_time": "2:52:10", "remaining_time": "23:17:11", "throughput": 55021.48, "total_tokens": 568388992} |
| {"current_steps": 1600, "total_steps": 14493, "loss": 0.2899, "lr": 4.6425835701000084e-05, "epoch": 0.33125436712300405, "percentage": 11.04, "elapsed_time": "2:53:05", "remaining_time": "23:14:48", "throughput": 55080.98, "total_tokens": 572050560} |
| {"current_steps": 1610, "total_steps": 14493, "loss": 0.2908, "lr": 4.640583577085084e-05, "epoch": 0.33332470691752286, "percentage": 11.11, "elapsed_time": "2:53:58", "remaining_time": "23:12:04", "throughput": 55146.6, "total_tokens": 575630336} |
| {"current_steps": 1620, "total_steps": 14493, "loss": 0.2901, "lr": 4.638586166594806e-05, "epoch": 0.3353950467120416, "percentage": 11.18, "elapsed_time": "2:54:46", "remaining_time": "23:08:49", "throughput": 55232.28, "total_tokens": 579197440} |
| {"current_steps": 1630, "total_steps": 14493, "loss": 0.2906, "lr": 4.6365913330760726e-05, "epoch": 0.3374653865065604, "percentage": 11.25, "elapsed_time": "2:55:37", "remaining_time": "23:05:54", "throughput": 55310.99, "total_tokens": 582829952} |
| {"current_steps": 1640, "total_steps": 14493, "loss": 0.2924, "lr": 4.6345990709924855e-05, "epoch": 0.33953572630107914, "percentage": 11.32, "elapsed_time": "2:56:25", "remaining_time": "23:02:42", "throughput": 55385.54, "total_tokens": 586296192} |
| {"current_steps": 1650, "total_steps": 14493, "loss": 0.2892, "lr": 4.632609374824284e-05, "epoch": 0.34160606609559796, "percentage": 11.38, "elapsed_time": "2:57:20", "remaining_time": "23:00:21", "throughput": 55432.66, "total_tokens": 589829120} |
| {"current_steps": 1660, "total_steps": 14493, "loss": 0.2901, "lr": 4.630622239068285e-05, "epoch": 0.3436764058901167, "percentage": 11.45, "elapsed_time": "2:58:11", "remaining_time": "22:57:34", "throughput": 55509.24, "total_tokens": 593488896} |
| {"current_steps": 1670, "total_steps": 14493, "loss": 0.2897, "lr": 4.628637658237808e-05, "epoch": 0.3457467456846355, "percentage": 11.52, "elapsed_time": "2:59:02", "remaining_time": "22:54:45", "throughput": 55579.53, "total_tokens": 597059840} |
| {"current_steps": 1680, "total_steps": 14493, "loss": 0.2873, "lr": 4.626655626862625e-05, "epoch": 0.34781708547915424, "percentage": 11.59, "elapsed_time": "2:59:50", "remaining_time": "22:51:38", "throughput": 55660.95, "total_tokens": 600625152} |
| {"current_steps": 1690, "total_steps": 14493, "loss": 0.2886, "lr": 4.624676139488888e-05, "epoch": 0.34988742527367306, "percentage": 11.66, "elapsed_time": "3:00:43", "remaining_time": "22:49:07", "throughput": 55728.77, "total_tokens": 604296448} |
| {"current_steps": 1700, "total_steps": 14493, "loss": 0.2894, "lr": 4.6226991906790686e-05, "epoch": 0.3519577650681918, "percentage": 11.73, "elapsed_time": "3:01:31", "remaining_time": "22:46:02", "throughput": 55806.11, "total_tokens": 607818368} |
| {"current_steps": 1710, "total_steps": 14493, "loss": 0.2898, "lr": 4.620724775011897e-05, "epoch": 0.3540281048627106, "percentage": 11.8, "elapsed_time": "3:02:27", "remaining_time": "22:43:56", "throughput": 55856.59, "total_tokens": 611486464} |
| {"current_steps": 1720, "total_steps": 14493, "loss": 0.2906, "lr": 4.618752887082297e-05, "epoch": 0.35609844465722934, "percentage": 11.87, "elapsed_time": "3:03:33", "remaining_time": "22:43:10", "throughput": 55844.01, "total_tokens": 615059328} |
| {"current_steps": 1730, "total_steps": 14493, "loss": 0.2888, "lr": 4.616783521501325e-05, "epoch": 0.35816878445174816, "percentage": 11.94, "elapsed_time": "3:04:50", "remaining_time": "22:43:38", "throughput": 55786.99, "total_tokens": 618697344} |
| {"current_steps": 1740, "total_steps": 14493, "loss": 0.2896, "lr": 4.614816672896108e-05, "epoch": 0.3602391242462669, "percentage": 12.01, "elapsed_time": "3:06:10", "remaining_time": "22:44:34", "throughput": 55709.85, "total_tokens": 622327680} |
| {"current_steps": 1750, "total_steps": 14493, "loss": 0.2887, "lr": 4.612852335909782e-05, "epoch": 0.3623094640407857, "percentage": 12.07, "elapsed_time": "3:07:12", "remaining_time": "22:43:13", "throughput": 55717.58, "total_tokens": 625858304} |
| {"current_steps": 1760, "total_steps": 14493, "loss": 0.2874, "lr": 4.6108905052014323e-05, "epoch": 0.3643798038353045, "percentage": 12.14, "elapsed_time": "3:08:25", "remaining_time": "22:43:13", "throughput": 55673.55, "total_tokens": 629435520} |
| {"current_steps": 1770, "total_steps": 14493, "loss": 0.2875, "lr": 4.608931175446027e-05, "epoch": 0.36645014362982326, "percentage": 12.21, "elapsed_time": "3:09:23", "remaining_time": "22:41:20", "throughput": 55706.83, "total_tokens": 633011712} |
| {"current_steps": 1780, "total_steps": 14493, "loss": 0.291, "lr": 4.606974341334367e-05, "epoch": 0.368520483424342, "percentage": 12.28, "elapsed_time": "3:10:27", "remaining_time": "22:40:13", "throughput": 55707.81, "total_tokens": 636574848} |
| {"current_steps": 1790, "total_steps": 14493, "loss": 0.2883, "lr": 4.605019997573011e-05, "epoch": 0.3705908232188608, "percentage": 12.35, "elapsed_time": "3:11:33", "remaining_time": "22:39:25", "throughput": 55698.86, "total_tokens": 640173824} |
| {"current_steps": 1800, "total_steps": 14493, "loss": 0.2896, "lr": 4.603068138884229e-05, "epoch": 0.3726611630133796, "percentage": 12.42, "elapsed_time": "3:13:03", "remaining_time": "22:41:25", "throughput": 55565.58, "total_tokens": 643666304} |
| {"current_steps": 1810, "total_steps": 14493, "loss": 0.2906, "lr": 4.6011187600059345e-05, "epoch": 0.37473150280789835, "percentage": 12.49, "elapsed_time": "3:14:11", "remaining_time": "22:40:45", "throughput": 55544.48, "total_tokens": 647190528} |
| {"current_steps": 1820, "total_steps": 14493, "loss": 0.2872, "lr": 4.599171855691629e-05, "epoch": 0.3768018426024171, "percentage": 12.56, "elapsed_time": "3:15:22", "remaining_time": "22:40:22", "throughput": 55511.62, "total_tokens": 650710656} |
| {"current_steps": 1830, "total_steps": 14493, "loss": 0.2878, "lr": 4.597227420710335e-05, "epoch": 0.3788721823969359, "percentage": 12.63, "elapsed_time": "3:16:29", "remaining_time": "22:39:39", "throughput": 55494.2, "total_tokens": 654252416} |
| {"current_steps": 1840, "total_steps": 14493, "loss": 0.2874, "lr": 4.595285449846551e-05, "epoch": 0.3809425221914547, "percentage": 12.7, "elapsed_time": "3:17:42", "remaining_time": "22:39:31", "throughput": 55451.18, "total_tokens": 657771264} |
| {"current_steps": 1850, "total_steps": 14493, "loss": 0.2879, "lr": 4.593345937900178e-05, "epoch": 0.38301286198597345, "percentage": 12.76, "elapsed_time": "3:18:37", "remaining_time": "22:37:27", "throughput": 55495.16, "total_tokens": 661384064} |
| {"current_steps": 1860, "total_steps": 14493, "loss": 0.2903, "lr": 4.591408879686472e-05, "epoch": 0.3850832017804922, "percentage": 12.83, "elapsed_time": "3:19:31", "remaining_time": "22:35:09", "throughput": 55541.28, "total_tokens": 664907904} |
| {"current_steps": 1870, "total_steps": 14493, "loss": 0.2864, "lr": 4.5894742700359775e-05, "epoch": 0.387153541575011, "percentage": 12.9, "elapsed_time": "3:20:20", "remaining_time": "22:32:23", "throughput": 55609.27, "total_tokens": 668465408} |
| {"current_steps": 1880, "total_steps": 14493, "loss": 0.2881, "lr": 4.587542103794477e-05, "epoch": 0.3892238813695298, "percentage": 12.97, "elapsed_time": "3:21:10", "remaining_time": "22:29:39", "throughput": 55675.76, "total_tokens": 672017152} |
| {"current_steps": 1890, "total_steps": 14493, "loss": 0.2856, "lr": 4.5856123758229247e-05, "epoch": 0.39129422116404855, "percentage": 13.04, "elapsed_time": "3:21:58", "remaining_time": "22:26:51", "throughput": 55749.57, "total_tokens": 675616768} |
| {"current_steps": 1900, "total_steps": 14493, "loss": 0.2872, "lr": 4.5836850809973993e-05, "epoch": 0.3933645609585673, "percentage": 13.11, "elapsed_time": "3:22:46", "remaining_time": "22:23:59", "throughput": 55819.63, "total_tokens": 679137408} |
| {"current_steps": 1910, "total_steps": 14493, "loss": 0.2882, "lr": 4.5817602142090385e-05, "epoch": 0.3954349007530861, "percentage": 13.18, "elapsed_time": "3:23:38", "remaining_time": "22:21:37", "throughput": 55876.21, "total_tokens": 682744960} |
| {"current_steps": 1920, "total_steps": 14493, "loss": 0.2871, "lr": 4.579837770363989e-05, "epoch": 0.3975052405476049, "percentage": 13.25, "elapsed_time": "3:24:32", "remaining_time": "22:19:27", "throughput": 55921.35, "total_tokens": 686308736} |
| {"current_steps": 1930, "total_steps": 14493, "loss": 0.2872, "lr": 4.57791774438334e-05, "epoch": 0.39957558034212365, "percentage": 13.32, "elapsed_time": "3:25:22", "remaining_time": "22:16:48", "throughput": 55977.74, "total_tokens": 689760640} |
| {"current_steps": 1940, "total_steps": 14493, "loss": 0.2864, "lr": 4.576000131203078e-05, "epoch": 0.4016459201366424, "percentage": 13.39, "elapsed_time": "3:26:17", "remaining_time": "22:14:47", "throughput": 56016.95, "total_tokens": 693324672} |
| {"current_steps": 1950, "total_steps": 14493, "loss": 0.2855, "lr": 4.574084925774023e-05, "epoch": 0.4037162599311612, "percentage": 13.45, "elapsed_time": "3:27:01", "remaining_time": "22:11:38", "throughput": 56095.34, "total_tokens": 696787840} |
| {"current_steps": 1960, "total_steps": 14493, "loss": 0.284, "lr": 4.5721721230617795e-05, "epoch": 0.40578659972568, "percentage": 13.52, "elapsed_time": "3:27:53", "remaining_time": "22:09:19", "throughput": 56156.15, "total_tokens": 700453120} |
| {"current_steps": 1970, "total_steps": 14493, "loss": 0.2863, "lr": 4.57026171804667e-05, "epoch": 0.40785693952019875, "percentage": 13.59, "elapsed_time": "3:28:45", "remaining_time": "22:07:00", "throughput": 56214.06, "total_tokens": 704088704} |
| {"current_steps": 1980, "total_steps": 14493, "loss": 0.286, "lr": 4.568353705723692e-05, "epoch": 0.4099272793147175, "percentage": 13.66, "elapsed_time": "3:29:42", "remaining_time": "22:05:15", "throughput": 56260.81, "total_tokens": 707884544} |
| {"current_steps": 1990, "total_steps": 14493, "loss": 0.2839, "lr": 4.566448081102455e-05, "epoch": 0.4119976191092363, "percentage": 13.73, "elapsed_time": "3:30:38", "remaining_time": "22:03:25", "throughput": 56299.12, "total_tokens": 711528832} |
| {"current_steps": 2000, "total_steps": 14493, "loss": 0.2856, "lr": 4.564544839207128e-05, "epoch": 0.4140679589037551, "percentage": 13.8, "elapsed_time": "3:31:34", "remaining_time": "22:01:33", "throughput": 56336.1, "total_tokens": 715135488} |
| {"current_steps": 2010, "total_steps": 14493, "loss": 0.2859, "lr": 4.562643975076387e-05, "epoch": 0.41613829869827385, "percentage": 13.87, "elapsed_time": "3:32:41", "remaining_time": "22:00:57", "throughput": 56311.87, "total_tokens": 718652032} |
| {"current_steps": 2020, "total_steps": 14493, "loss": 0.282, "lr": 4.560745483763357e-05, "epoch": 0.4182086384927926, "percentage": 13.94, "elapsed_time": "3:33:57", "remaining_time": "22:01:09", "throughput": 56252.42, "total_tokens": 722150144} |
| {"current_steps": 2030, "total_steps": 14493, "loss": 0.2833, "lr": 4.5588493603355595e-05, "epoch": 0.4202789782873114, "percentage": 14.01, "elapsed_time": "3:35:14", "remaining_time": "22:01:25", "throughput": 56194.64, "total_tokens": 725704320} |
| {"current_steps": 2040, "total_steps": 14493, "loss": 0.2841, "lr": 4.556955599874859e-05, "epoch": 0.4223493180818302, "percentage": 14.08, "elapsed_time": "3:36:35", "remaining_time": "22:02:08", "throughput": 56119.43, "total_tokens": 729286144} |
| {"current_steps": 2050, "total_steps": 14493, "loss": 0.2863, "lr": 4.555064197477409e-05, "epoch": 0.42441965787634894, "percentage": 14.14, "elapsed_time": "3:38:18", "remaining_time": "22:05:04", "throughput": 55958.22, "total_tokens": 732969856} |
| {"current_steps": 2060, "total_steps": 14493, "loss": 0.2827, "lr": 4.5531751482536e-05, "epoch": 0.4264899976708677, "percentage": 14.21, "elapsed_time": "3:39:34", "remaining_time": "22:05:12", "throughput": 55915.63, "total_tokens": 736649856} |
| {"current_steps": 2070, "total_steps": 14493, "loss": 0.2833, "lr": 4.5512884473280024e-05, "epoch": 0.4285603374653865, "percentage": 14.28, "elapsed_time": "3:41:00", "remaining_time": "22:06:23", "throughput": 55814.85, "total_tokens": 740141056} |
| {"current_steps": 2080, "total_steps": 14493, "loss": 0.2829, "lr": 4.549404089839322e-05, "epoch": 0.4306306772599053, "percentage": 14.35, "elapsed_time": "3:42:06", "remaining_time": "22:05:28", "throughput": 55804.24, "total_tokens": 743667328} |
| {"current_steps": 2090, "total_steps": 14493, "loss": 0.2832, "lr": 4.547522070940335e-05, "epoch": 0.43270101705442404, "percentage": 14.42, "elapsed_time": "3:43:15", "remaining_time": "22:04:56", "throughput": 55777.03, "total_tokens": 747178752} |
| {"current_steps": 2100, "total_steps": 14493, "loss": 0.2859, "lr": 4.545642385797848e-05, "epoch": 0.43477135684894286, "percentage": 14.49, "elapsed_time": "3:44:18", "remaining_time": "22:03:44", "throughput": 55778.64, "total_tokens": 750697088} |
| {"current_steps": 2110, "total_steps": 14493, "loss": 0.284, "lr": 4.543765029592637e-05, "epoch": 0.4368416966434616, "percentage": 14.56, "elapsed_time": "3:45:56", "remaining_time": "22:05:58", "throughput": 55641.33, "total_tokens": 754297344} |
| {"current_steps": 2120, "total_steps": 14493, "loss": 0.2824, "lr": 4.541889997519403e-05, "epoch": 0.4389120364379804, "percentage": 14.63, "elapsed_time": "3:47:02", "remaining_time": "22:05:02", "throughput": 55638.65, "total_tokens": 757914240} |
| {"current_steps": 2130, "total_steps": 14493, "loss": 0.2851, "lr": 4.5400172847867095e-05, "epoch": 0.44098237623249914, "percentage": 14.7, "elapsed_time": "3:48:16", "remaining_time": "22:04:57", "throughput": 55593.39, "total_tokens": 761435648} |
| {"current_steps": 2140, "total_steps": 14493, "loss": 0.2844, "lr": 4.5381468866169466e-05, "epoch": 0.44305271602701796, "percentage": 14.77, "elapsed_time": "3:49:14", "remaining_time": "22:03:15", "throughput": 55616.32, "total_tokens": 764963840} |
| {"current_steps": 2150, "total_steps": 14493, "loss": 0.2815, "lr": 4.5362787982462616e-05, "epoch": 0.4451230558215367, "percentage": 14.83, "elapsed_time": "3:50:36", "remaining_time": "22:03:55", "throughput": 55541.2, "total_tokens": 768507392} |
| {"current_steps": 2160, "total_steps": 14493, "loss": 0.2818, "lr": 4.5344130149245275e-05, "epoch": 0.4471933956160555, "percentage": 14.9, "elapsed_time": "3:51:50", "remaining_time": "22:03:44", "throughput": 55496.13, "total_tokens": 771975296} |
| {"current_steps": 2170, "total_steps": 14493, "loss": 0.2802, "lr": 4.5325495319152715e-05, "epoch": 0.44926373541057424, "percentage": 14.97, "elapsed_time": "3:53:03", "remaining_time": "22:03:27", "throughput": 55459.4, "total_tokens": 775500032} |
| {"current_steps": 2180, "total_steps": 14493, "loss": 0.2825, "lr": 4.530688344495644e-05, "epoch": 0.45133407520509305, "percentage": 15.04, "elapsed_time": "3:53:56", "remaining_time": "22:01:23", "throughput": 55503.99, "total_tokens": 779107072} |
| {"current_steps": 2190, "total_steps": 14493, "loss": 0.2827, "lr": 4.528829447956357e-05, "epoch": 0.4534044149996118, "percentage": 15.11, "elapsed_time": "3:54:47", "remaining_time": "21:59:01", "throughput": 55555.54, "total_tokens": 782642432} |
| {"current_steps": 2200, "total_steps": 14493, "loss": 0.2817, "lr": 4.526972837601633e-05, "epoch": 0.4554747547941306, "percentage": 15.18, "elapsed_time": "3:55:36", "remaining_time": "21:56:32", "throughput": 55609.97, "total_tokens": 786146944} |
| {"current_steps": 2210, "total_steps": 14493, "loss": 0.2845, "lr": 4.525118508749165e-05, "epoch": 0.45754509458864934, "percentage": 15.25, "elapsed_time": "3:56:30", "remaining_time": "21:54:31", "throughput": 55657.39, "total_tokens": 789823232} |
| {"current_steps": 2220, "total_steps": 14493, "loss": 0.2827, "lr": 4.5232664567300546e-05, "epoch": 0.45961543438316815, "percentage": 15.32, "elapsed_time": "3:57:20", "remaining_time": "21:52:04", "throughput": 55714.93, "total_tokens": 793381504} |
| {"current_steps": 2230, "total_steps": 14493, "loss": 0.2802, "lr": 4.521416676888773e-05, "epoch": 0.4616857741776869, "percentage": 15.39, "elapsed_time": "3:58:10", "remaining_time": "21:49:47", "throughput": 55771.43, "total_tokens": 797024640} |
| {"current_steps": 2240, "total_steps": 14493, "loss": 0.2795, "lr": 4.519569164583107e-05, "epoch": 0.4637561139722057, "percentage": 15.46, "elapsed_time": "3:59:00", "remaining_time": "21:47:23", "throughput": 55828.0, "total_tokens": 800593536} |
| {"current_steps": 2250, "total_steps": 14493, "loss": 0.2836, "lr": 4.517723915184109e-05, "epoch": 0.4658264537667245, "percentage": 15.52, "elapsed_time": "3:59:53", "remaining_time": "21:45:19", "throughput": 55875.21, "total_tokens": 804231680} |
| {"current_steps": 2260, "total_steps": 14493, "loss": 0.2817, "lr": 4.5158809240760506e-05, "epoch": 0.46789679356124325, "percentage": 15.59, "elapsed_time": "4:00:41", "remaining_time": "21:42:48", "throughput": 55936.18, "total_tokens": 807793664} |
| {"current_steps": 2270, "total_steps": 14493, "loss": 0.282, "lr": 4.514040186656375e-05, "epoch": 0.469967133355762, "percentage": 15.66, "elapsed_time": "4:01:29", "remaining_time": "21:40:20", "throughput": 55991.83, "total_tokens": 811304320} |
| {"current_steps": 2280, "total_steps": 14493, "loss": 0.2796, "lr": 4.512201698335644e-05, "epoch": 0.4720374731502808, "percentage": 15.73, "elapsed_time": "4:02:18", "remaining_time": "21:37:56", "throughput": 56042.58, "total_tokens": 814775680} |
| {"current_steps": 2290, "total_steps": 14493, "loss": 0.2817, "lr": 4.510365454537496e-05, "epoch": 0.4741078129447996, "percentage": 15.8, "elapsed_time": "4:03:06", "remaining_time": "21:35:27", "throughput": 56097.22, "total_tokens": 818246400} |
| {"current_steps": 2300, "total_steps": 14493, "loss": 0.2811, "lr": 4.5085314506985945e-05, "epoch": 0.47617815273931835, "percentage": 15.87, "elapsed_time": "4:03:56", "remaining_time": "21:33:14", "throughput": 56149.3, "total_tokens": 821847680} |
| {"current_steps": 2310, "total_steps": 14493, "loss": 0.2809, "lr": 4.50669968226858e-05, "epoch": 0.4782484925338371, "percentage": 15.94, "elapsed_time": "4:04:48", "remaining_time": "21:31:07", "throughput": 56196.24, "total_tokens": 825441536} |
| {"current_steps": 2320, "total_steps": 14493, "loss": 0.281, "lr": 4.504870144710027e-05, "epoch": 0.48031883232835587, "percentage": 16.01, "elapsed_time": "4:05:37", "remaining_time": "21:28:49", "throughput": 56249.82, "total_tokens": 829007616} |
| {"current_steps": 2330, "total_steps": 14493, "loss": 0.2815, "lr": 4.5030428334983884e-05, "epoch": 0.4823891721228747, "percentage": 16.08, "elapsed_time": "4:06:28", "remaining_time": "21:26:38", "throughput": 56299.17, "total_tokens": 832581376} |
| {"current_steps": 2340, "total_steps": 14493, "loss": 0.2822, "lr": 4.501217744121959e-05, "epoch": 0.48445951191739345, "percentage": 16.15, "elapsed_time": "4:07:22", "remaining_time": "21:24:43", "throughput": 56335.59, "total_tokens": 836132992} |
| {"current_steps": 2350, "total_steps": 14493, "loss": 0.2786, "lr": 4.499394872081821e-05, "epoch": 0.4865298517119122, "percentage": 16.21, "elapsed_time": "4:08:15", "remaining_time": "21:22:50", "throughput": 56375.25, "total_tokens": 839756672} |
| {"current_steps": 2360, "total_steps": 14493, "loss": 0.2816, "lr": 4.4975742128918e-05, "epoch": 0.48860019150643097, "percentage": 16.28, "elapsed_time": "4:09:06", "remaining_time": "21:20:43", "throughput": 56419.77, "total_tokens": 843296128} |
| {"current_steps": 2370, "total_steps": 14493, "loss": 0.2814, "lr": 4.495755762078418e-05, "epoch": 0.4906705313009498, "percentage": 16.35, "elapsed_time": "4:09:57", "remaining_time": "21:18:35", "throughput": 56473.41, "total_tokens": 846963968} |
| {"current_steps": 2380, "total_steps": 14493, "loss": 0.2763, "lr": 4.49393951518085e-05, "epoch": 0.49274087109546855, "percentage": 16.42, "elapsed_time": "4:10:44", "remaining_time": "21:16:09", "throughput": 56528.4, "total_tokens": 850444672} |
| {"current_steps": 2390, "total_steps": 14493, "loss": 0.2811, "lr": 4.4921254677508716e-05, "epoch": 0.4948112108899873, "percentage": 16.49, "elapsed_time": "4:11:37", "remaining_time": "21:14:14", "throughput": 56569.56, "total_tokens": 854062848} |
| {"current_steps": 2400, "total_steps": 14493, "loss": 0.2779, "lr": 4.490313615352821e-05, "epoch": 0.49688155068450607, "percentage": 16.56, "elapsed_time": "4:12:26", "remaining_time": "21:12:00", "throughput": 56620.75, "total_tokens": 857621248} |
| {"current_steps": 2410, "total_steps": 14493, "loss": 0.2792, "lr": 4.48850395356355e-05, "epoch": 0.4989518904790249, "percentage": 16.63, "elapsed_time": "4:13:14", "remaining_time": "21:09:42", "throughput": 56676.27, "total_tokens": 861190272} |
| {"current_steps": 2420, "total_steps": 14493, "loss": 0.2782, "lr": 4.486696477972375e-05, "epoch": 0.5010222302735436, "percentage": 16.7, "elapsed_time": "4:14:06", "remaining_time": "21:07:44", "throughput": 56721.37, "total_tokens": 864821632} |
| {"current_steps": 2430, "total_steps": 14493, "loss": 0.2801, "lr": 4.484891184181041e-05, "epoch": 0.5030925700680624, "percentage": 16.77, "elapsed_time": "4:14:54", "remaining_time": "21:05:22", "throughput": 56779.49, "total_tokens": 868389120} |
| {"current_steps": 2440, "total_steps": 14493, "loss": 0.2793, "lr": 4.483088067803662e-05, "epoch": 0.5051629098625812, "percentage": 16.84, "elapsed_time": "4:15:43", "remaining_time": "21:03:12", "throughput": 56827.0, "total_tokens": 871920000} |
| {"current_steps": 2450, "total_steps": 14493, "loss": 0.2774, "lr": 4.481287124466697e-05, "epoch": 0.5072332496570999, "percentage": 16.9, "elapsed_time": "4:16:32", "remaining_time": "21:01:01", "throughput": 56876.02, "total_tokens": 875457280} |
| {"current_steps": 2460, "total_steps": 14493, "loss": 0.2799, "lr": 4.479488349808885e-05, "epoch": 0.5093035894516188, "percentage": 16.97, "elapsed_time": "4:17:21", "remaining_time": "20:58:51", "throughput": 56925.71, "total_tokens": 879018240} |
| {"current_steps": 2470, "total_steps": 14493, "loss": 0.281, "lr": 4.4776917394812114e-05, "epoch": 0.5113739292461376, "percentage": 17.04, "elapsed_time": "4:18:11", "remaining_time": "20:56:47", "throughput": 56974.98, "total_tokens": 882633472} |
| {"current_steps": 2480, "total_steps": 14493, "loss": 0.2805, "lr": 4.475897289146862e-05, "epoch": 0.5134442690406563, "percentage": 17.11, "elapsed_time": "4:19:00", "remaining_time": "20:54:36", "throughput": 57025.05, "total_tokens": 886185216} |
| {"current_steps": 2490, "total_steps": 14493, "loss": 0.2803, "lr": 4.4741049944811806e-05, "epoch": 0.5155146088351751, "percentage": 17.18, "elapsed_time": "4:19:52", "remaining_time": "20:52:41", "throughput": 57071.12, "total_tokens": 889862656} |
| {"current_steps": 2500, "total_steps": 14493, "loss": 0.2777, "lr": 4.472314851171621e-05, "epoch": 0.5175849486296938, "percentage": 17.25, "elapsed_time": "4:20:44", "remaining_time": "20:50:47", "throughput": 57111.41, "total_tokens": 893455360} |
| {"current_steps": 2510, "total_steps": 14493, "loss": 0.2772, "lr": 4.4705268549177084e-05, "epoch": 0.5196552884242126, "percentage": 17.32, "elapsed_time": "4:21:36", "remaining_time": "20:48:57", "throughput": 57142.28, "total_tokens": 896947072} |
| {"current_steps": 2520, "total_steps": 14493, "loss": 0.279, "lr": 4.468741001430989e-05, "epoch": 0.5217256282187314, "percentage": 17.39, "elapsed_time": "4:22:27", "remaining_time": "20:47:01", "throughput": 57183.6, "total_tokens": 900521984} |
| {"current_steps": 2530, "total_steps": 14493, "loss": 0.277, "lr": 4.466957286434997e-05, "epoch": 0.5237959680132501, "percentage": 17.46, "elapsed_time": "4:23:17", "remaining_time": "20:44:58", "throughput": 57231.38, "total_tokens": 904121344} |
| {"current_steps": 2540, "total_steps": 14493, "loss": 0.2764, "lr": 4.4651757056652e-05, "epoch": 0.525866307807769, "percentage": 17.53, "elapsed_time": "4:24:06", "remaining_time": "20:42:49", "throughput": 57279.68, "total_tokens": 907654272} |
| {"current_steps": 2550, "total_steps": 14493, "loss": 0.2786, "lr": 4.463396254868968e-05, "epoch": 0.5279366476022878, "percentage": 17.59, "elapsed_time": "4:24:55", "remaining_time": "20:40:48", "throughput": 57324.06, "total_tokens": 911217920} |
| {"current_steps": 2560, "total_steps": 14493, "loss": 0.2787, "lr": 4.461618929805519e-05, "epoch": 0.5300069873968065, "percentage": 17.66, "elapsed_time": "4:25:46", "remaining_time": "20:38:52", "throughput": 57370.73, "total_tokens": 914869632} |
| {"current_steps": 2570, "total_steps": 14493, "loss": 0.2806, "lr": 4.459843726245888e-05, "epoch": 0.5320773271913253, "percentage": 17.73, "elapsed_time": "4:26:37", "remaining_time": "20:36:58", "throughput": 57416.58, "total_tokens": 918542976} |
| {"current_steps": 2580, "total_steps": 14493, "loss": 0.2776, "lr": 4.458070639972875e-05, "epoch": 0.534147666985844, "percentage": 17.8, "elapsed_time": "4:27:28", "remaining_time": "20:35:02", "throughput": 57459.85, "total_tokens": 922139904} |
| {"current_steps": 2590, "total_steps": 14493, "loss": 0.2772, "lr": 4.456299666781007e-05, "epoch": 0.5362180067803628, "percentage": 17.87, "elapsed_time": "4:28:18", "remaining_time": "20:33:03", "throughput": 57505.71, "total_tokens": 925744384} |
| {"current_steps": 2600, "total_steps": 14493, "loss": 0.2718, "lr": 4.4545308024764984e-05, "epoch": 0.5382883465748816, "percentage": 17.94, "elapsed_time": "4:29:07", "remaining_time": "20:31:00", "throughput": 57552.12, "total_tokens": 929298944} |
| {"current_steps": 2610, "total_steps": 14493, "loss": 0.2792, "lr": 4.452764042877207e-05, "epoch": 0.5403586863694004, "percentage": 18.01, "elapsed_time": "4:29:59", "remaining_time": "20:29:16", "throughput": 57591.9, "total_tokens": 932988032} |
| {"current_steps": 2620, "total_steps": 14493, "loss": 0.2777, "lr": 4.45099938381259e-05, "epoch": 0.5424290261639192, "percentage": 18.08, "elapsed_time": "4:30:51", "remaining_time": "20:27:26", "throughput": 57633.12, "total_tokens": 936625408} |
| {"current_steps": 2630, "total_steps": 14493, "loss": 0.2785, "lr": 4.449236821123667e-05, "epoch": 0.544499365958438, "percentage": 18.15, "elapsed_time": "4:31:41", "remaining_time": "20:25:30", "throughput": 57674.67, "total_tokens": 940188160} |
| {"current_steps": 2640, "total_steps": 14493, "loss": 0.2775, "lr": 4.447476350662976e-05, "epoch": 0.5465697057529567, "percentage": 18.22, "elapsed_time": "4:32:32", "remaining_time": "20:23:37", "throughput": 57716.19, "total_tokens": 943781504} |
| {"current_steps": 2650, "total_steps": 14493, "loss": 0.2783, "lr": 4.4457179682945346e-05, "epoch": 0.5486400455474755, "percentage": 18.28, "elapsed_time": "4:33:22", "remaining_time": "20:21:45", "throughput": 57751.78, "total_tokens": 947296640} |
| {"current_steps": 2660, "total_steps": 14493, "loss": 0.2781, "lr": 4.443961669893798e-05, "epoch": 0.5507103853419942, "percentage": 18.35, "elapsed_time": "4:34:11", "remaining_time": "20:19:45", "throughput": 57794.6, "total_tokens": 950815744} |
| {"current_steps": 2670, "total_steps": 14493, "loss": 0.2781, "lr": 4.4422074513476155e-05, "epoch": 0.552780725136513, "percentage": 18.42, "elapsed_time": "4:35:02", "remaining_time": "20:17:55", "throughput": 57833.59, "total_tokens": 954414336} |
| {"current_steps": 2680, "total_steps": 14493, "loss": 0.2775, "lr": 4.4404553085541955e-05, "epoch": 0.5548510649310318, "percentage": 18.49, "elapsed_time": "4:35:49", "remaining_time": "20:15:46", "throughput": 57883.13, "total_tokens": 957918720} |
| {"current_steps": 2690, "total_steps": 14493, "loss": 0.2782, "lr": 4.438705237423063e-05, "epoch": 0.5569214047255506, "percentage": 18.56, "elapsed_time": "4:36:36", "remaining_time": "20:13:39", "throughput": 57931.35, "total_tokens": 961434624} |
| {"current_steps": 2700, "total_steps": 14493, "loss": 0.2771, "lr": 4.436957233875017e-05, "epoch": 0.5589917445200694, "percentage": 18.63, "elapsed_time": "4:37:27", "remaining_time": "20:11:54", "throughput": 57969.38, "total_tokens": 965068672} |
| {"current_steps": 2710, "total_steps": 14493, "loss": 0.2769, "lr": 4.4352112938420956e-05, "epoch": 0.5610620843145881, "percentage": 18.7, "elapsed_time": "4:38:22", "remaining_time": "20:10:21", "throughput": 57997.62, "total_tokens": 968704896} |
| {"current_steps": 2720, "total_steps": 14493, "loss": 0.2758, "lr": 4.433467413267529e-05, "epoch": 0.5631324241091069, "percentage": 18.77, "elapsed_time": "4:39:10", "remaining_time": "20:08:21", "throughput": 58040.95, "total_tokens": 972216576} |
| {"current_steps": 2730, "total_steps": 14493, "loss": 0.2803, "lr": 4.431725588105708e-05, "epoch": 0.5652027639036257, "percentage": 18.84, "elapsed_time": "4:40:00", "remaining_time": "20:06:30", "throughput": 58080.46, "total_tokens": 975795584} |
| {"current_steps": 2740, "total_steps": 14493, "loss": 0.2762, "lr": 4.4299858143221377e-05, "epoch": 0.5672731036981444, "percentage": 18.91, "elapsed_time": "4:40:47", "remaining_time": "20:04:26", "throughput": 58123.03, "total_tokens": 979240448} |
| {"current_steps": 2750, "total_steps": 14493, "loss": 0.2739, "lr": 4.4282480878934065e-05, "epoch": 0.5693434434926632, "percentage": 18.97, "elapsed_time": "4:41:33", "remaining_time": "20:02:17", "throughput": 58168.64, "total_tokens": 982660480} |
| {"current_steps": 2760, "total_steps": 14493, "loss": 0.2753, "lr": 4.4265124048071346e-05, "epoch": 0.571413783287182, "percentage": 19.04, "elapsed_time": "4:42:22", "remaining_time": "20:00:24", "throughput": 58208.61, "total_tokens": 986211200} |
| {"current_steps": 2770, "total_steps": 14493, "loss": 0.2767, "lr": 4.4247787610619477e-05, "epoch": 0.5734841230817008, "percentage": 19.11, "elapsed_time": "4:43:13", "remaining_time": "19:58:36", "throughput": 58247.11, "total_tokens": 989795200} |
| {"current_steps": 2780, "total_steps": 14493, "loss": 0.2748, "lr": 4.42304715266743e-05, "epoch": 0.5755544628762196, "percentage": 19.18, "elapsed_time": "4:44:00", "remaining_time": "19:56:38", "throughput": 58292.15, "total_tokens": 993351040} |
| {"current_steps": 2790, "total_steps": 14493, "loss": 0.2747, "lr": 4.421317575644092e-05, "epoch": 0.5776248026707383, "percentage": 19.25, "elapsed_time": "4:44:52", "remaining_time": "19:54:55", "throughput": 58326.72, "total_tokens": 996928896} |
| {"current_steps": 2800, "total_steps": 14493, "loss": 0.2768, "lr": 4.419590026023325e-05, "epoch": 0.5796951424652571, "percentage": 19.32, "elapsed_time": "4:45:53", "remaining_time": "19:53:54", "throughput": 58327.29, "total_tokens": 1000523392} |
| {"current_steps": 2810, "total_steps": 14493, "loss": 0.2753, "lr": 4.417864499847368e-05, "epoch": 0.5817654822597759, "percentage": 19.39, "elapsed_time": "4:47:03", "remaining_time": "19:53:29", "throughput": 58300.23, "total_tokens": 1004138624} |
| {"current_steps": 2820, "total_steps": 14493, "loss": 0.2734, "lr": 4.4161409931692676e-05, "epoch": 0.5838358220542946, "percentage": 19.46, "elapsed_time": "4:47:54", "remaining_time": "19:51:46", "throughput": 58329.78, "total_tokens": 1007637504} |
| {"current_steps": 2830, "total_steps": 14493, "loss": 0.2753, "lr": 4.414419502052841e-05, "epoch": 0.5859061618488134, "percentage": 19.53, "elapsed_time": "4:49:00", "remaining_time": "19:51:01", "throughput": 58319.43, "total_tokens": 1011261824} |
| {"current_steps": 2840, "total_steps": 14493, "loss": 0.2771, "lr": 4.412700022572637e-05, "epoch": 0.5879765016433323, "percentage": 19.6, "elapsed_time": "4:49:56", "remaining_time": "19:49:42", "throughput": 58335.17, "total_tokens": 1014851584} |
| {"current_steps": 2850, "total_steps": 14493, "loss": 0.2743, "lr": 4.410982550813902e-05, "epoch": 0.590046841437851, "percentage": 19.66, "elapsed_time": "4:50:47", "remaining_time": "19:47:56", "throughput": 58369.48, "total_tokens": 1018387456} |
| {"current_steps": 2860, "total_steps": 14493, "loss": 0.2758, "lr": 4.409267082872535e-05, "epoch": 0.5921171812323698, "percentage": 19.73, "elapsed_time": "4:51:34", "remaining_time": "19:45:58", "throughput": 58413.6, "total_tokens": 1021910912} |
| {"current_steps": 2870, "total_steps": 14493, "loss": 0.2753, "lr": 4.407553614855059e-05, "epoch": 0.5941875210268885, "percentage": 19.8, "elapsed_time": "4:52:21", "remaining_time": "19:44:00", "throughput": 58456.57, "total_tokens": 1025415680} |
| {"current_steps": 2880, "total_steps": 14493, "loss": 0.2745, "lr": 4.405842142878579e-05, "epoch": 0.5962578608214073, "percentage": 19.87, "elapsed_time": "4:53:11", "remaining_time": "19:42:13", "throughput": 58496.95, "total_tokens": 1029038336} |
| {"current_steps": 2890, "total_steps": 14493, "loss": 0.2736, "lr": 4.404132663070745e-05, "epoch": 0.5983282006159261, "percentage": 19.94, "elapsed_time": "4:53:57", "remaining_time": "19:40:11", "throughput": 58540.86, "total_tokens": 1032499072} |
| {"current_steps": 2900, "total_steps": 14493, "loss": 0.2769, "lr": 4.402425171569716e-05, "epoch": 0.6003985404104448, "percentage": 20.01, "elapsed_time": "4:54:45", "remaining_time": "19:38:20", "throughput": 58583.41, "total_tokens": 1036087680} |
| {"current_steps": 2910, "total_steps": 14493, "loss": 0.2754, "lr": 4.400719664524127e-05, "epoch": 0.6024688802049636, "percentage": 20.08, "elapsed_time": "4:55:36", "remaining_time": "19:36:38", "throughput": 58618.76, "total_tokens": 1039684096} |
| {"current_steps": 2920, "total_steps": 14493, "loss": 0.276, "lr": 4.399016138093044e-05, "epoch": 0.6045392199994825, "percentage": 20.15, "elapsed_time": "4:56:23", "remaining_time": "19:34:43", "throughput": 58661.71, "total_tokens": 1043234304} |
| {"current_steps": 2930, "total_steps": 14493, "loss": 0.2742, "lr": 4.397314588445937e-05, "epoch": 0.6066095597940012, "percentage": 20.22, "elapsed_time": "4:57:14", "remaining_time": "19:33:01", "throughput": 58694.78, "total_tokens": 1046773760} |
| {"current_steps": 2940, "total_steps": 14493, "loss": 0.2725, "lr": 4.395615011762637e-05, "epoch": 0.60867989958852, "percentage": 20.29, "elapsed_time": "4:58:03", "remaining_time": "19:31:16", "throughput": 58733.88, "total_tokens": 1050390656} |
| {"current_steps": 2950, "total_steps": 14493, "loss": 0.2745, "lr": 4.3939174042333057e-05, "epoch": 0.6107502393830387, "percentage": 20.35, "elapsed_time": "4:58:50", "remaining_time": "19:29:20", "throughput": 58777.22, "total_tokens": 1053918592} |
| {"current_steps": 2960, "total_steps": 14493, "loss": 0.2753, "lr": 4.3922217620583904e-05, "epoch": 0.6128205791775575, "percentage": 20.42, "elapsed_time": "4:59:41", "remaining_time": "19:27:40", "throughput": 58812.24, "total_tokens": 1057529088} |
| {"current_steps": 2970, "total_steps": 14493, "loss": 0.2756, "lr": 4.3905280814486025e-05, "epoch": 0.6148909189720763, "percentage": 20.49, "elapsed_time": "5:00:30", "remaining_time": "19:25:55", "throughput": 58854.38, "total_tokens": 1061189120} |
| {"current_steps": 2980, "total_steps": 14493, "loss": 0.2727, "lr": 4.388836358624867e-05, "epoch": 0.616961258766595, "percentage": 20.56, "elapsed_time": "5:01:22", "remaining_time": "19:24:21", "throughput": 58885.62, "total_tokens": 1064817024} |
| {"current_steps": 2990, "total_steps": 14493, "loss": 0.2741, "lr": 4.3871465898182976e-05, "epoch": 0.6190315985611139, "percentage": 20.63, "elapsed_time": "5:02:11", "remaining_time": "19:22:36", "throughput": 58920.21, "total_tokens": 1068335104} |
| {"current_steps": 3000, "total_steps": 14493, "loss": 0.2712, "lr": 4.385458771270156e-05, "epoch": 0.6211019383556327, "percentage": 20.7, "elapsed_time": "5:03:00", "remaining_time": "19:20:49", "throughput": 58958.09, "total_tokens": 1071894528} |
| {"current_steps": 3010, "total_steps": 14493, "loss": 0.2711, "lr": 4.3837728992318205e-05, "epoch": 0.6231722781501514, "percentage": 20.77, "elapsed_time": "5:03:53", "remaining_time": "19:19:21", "throughput": 58981.44, "total_tokens": 1075463552} |
| {"current_steps": 3020, "total_steps": 14493, "loss": 0.2713, "lr": 4.382088969964746e-05, "epoch": 0.6252426179446702, "percentage": 20.84, "elapsed_time": "5:04:42", "remaining_time": "19:17:36", "throughput": 59018.67, "total_tokens": 1079024896} |
| {"current_steps": 3030, "total_steps": 14493, "loss": 0.2719, "lr": 4.380406979740436e-05, "epoch": 0.6273129577391889, "percentage": 20.91, "elapsed_time": "5:05:31", "remaining_time": "19:15:51", "throughput": 59055.34, "total_tokens": 1082577024} |
| {"current_steps": 3040, "total_steps": 14493, "loss": 0.2725, "lr": 4.3787269248403994e-05, "epoch": 0.6293832975337077, "percentage": 20.98, "elapsed_time": "5:06:17", "remaining_time": "19:13:56", "throughput": 59097.22, "total_tokens": 1086070528} |
| {"current_steps": 3050, "total_steps": 14493, "loss": 0.2726, "lr": 4.377048801556126e-05, "epoch": 0.6314536373282265, "percentage": 21.04, "elapsed_time": "5:07:05", "remaining_time": "19:12:09", "throughput": 59132.9, "total_tokens": 1089566848} |
| {"current_steps": 3060, "total_steps": 14493, "loss": 0.2757, "lr": 4.3753726061890446e-05, "epoch": 0.6335239771227452, "percentage": 21.11, "elapsed_time": "5:07:58", "remaining_time": "19:10:41", "throughput": 59161.23, "total_tokens": 1093230336} |
| {"current_steps": 3070, "total_steps": 14493, "loss": 0.2725, "lr": 4.373698335050488e-05, "epoch": 0.6355943169172641, "percentage": 21.18, "elapsed_time": "5:08:47", "remaining_time": "19:08:57", "throughput": 59196.2, "total_tokens": 1096747008} |
| {"current_steps": 3080, "total_steps": 14493, "loss": 0.2715, "lr": 4.372025984461667e-05, "epoch": 0.6376646567117829, "percentage": 21.25, "elapsed_time": "5:09:37", "remaining_time": "19:07:17", "throughput": 59231.59, "total_tokens": 1100349184} |
| {"current_steps": 3090, "total_steps": 14493, "loss": 0.2731, "lr": 4.370355550753629e-05, "epoch": 0.6397349965063016, "percentage": 21.32, "elapsed_time": "5:10:28", "remaining_time": "19:05:46", "throughput": 59254.77, "total_tokens": 1103856768} |
| {"current_steps": 3100, "total_steps": 14493, "loss": 0.2736, "lr": 4.368687030267226e-05, "epoch": 0.6418053363008204, "percentage": 21.39, "elapsed_time": "5:11:24", "remaining_time": "19:04:29", "throughput": 59271.3, "total_tokens": 1107475840} |
| {"current_steps": 3110, "total_steps": 14493, "loss": 0.2724, "lr": 4.367020419353081e-05, "epoch": 0.6438756760953391, "percentage": 21.46, "elapsed_time": "5:12:29", "remaining_time": "19:03:44", "throughput": 59256.88, "total_tokens": 1111017728} |
| {"current_steps": 3120, "total_steps": 14493, "loss": 0.2703, "lr": 4.365355714371558e-05, "epoch": 0.6459460158898579, "percentage": 21.53, "elapsed_time": "5:13:19", "remaining_time": "19:02:09", "throughput": 59288.46, "total_tokens": 1114622720} |
| {"current_steps": 3130, "total_steps": 14493, "loss": 0.2746, "lr": 4.3636929116927235e-05, "epoch": 0.6480163556843767, "percentage": 21.6, "elapsed_time": "5:14:14", "remaining_time": "19:00:46", "throughput": 59308.13, "total_tokens": 1118200704} |
| {"current_steps": 3140, "total_steps": 14493, "loss": 0.2714, "lr": 4.362032007696314e-05, "epoch": 0.6500866954788955, "percentage": 21.67, "elapsed_time": "5:15:01", "remaining_time": "18:59:01", "throughput": 59348.22, "total_tokens": 1121782144} |
| {"current_steps": 3150, "total_steps": 14493, "loss": 0.2729, "lr": 4.360372998771707e-05, "epoch": 0.6521570352734143, "percentage": 21.73, "elapsed_time": "5:15:51", "remaining_time": "18:57:23", "throughput": 59380.06, "total_tokens": 1125341568} |
| {"current_steps": 3160, "total_steps": 14493, "loss": 0.273, "lr": 4.358715881317884e-05, "epoch": 0.654227375067933, "percentage": 21.8, "elapsed_time": "5:16:39", "remaining_time": "18:55:40", "throughput": 59415.78, "total_tokens": 1128880768} |
| {"current_steps": 3170, "total_steps": 14493, "loss": 0.2732, "lr": 4.357060651743399e-05, "epoch": 0.6562977148624518, "percentage": 21.87, "elapsed_time": "5:17:27", "remaining_time": "18:53:55", "throughput": 59451.11, "total_tokens": 1132390784} |
| {"current_steps": 3180, "total_steps": 14493, "loss": 0.2709, "lr": 4.3554073064663454e-05, "epoch": 0.6583680546569706, "percentage": 21.94, "elapsed_time": "5:18:19", "remaining_time": "18:52:26", "throughput": 59479.2, "total_tokens": 1136014976} |
| {"current_steps": 3190, "total_steps": 14493, "loss": 0.2697, "lr": 4.353755841914325e-05, "epoch": 0.6604383944514893, "percentage": 22.01, "elapsed_time": "5:19:07", "remaining_time": "18:50:44", "throughput": 59514.21, "total_tokens": 1139547776} |
| {"current_steps": 3200, "total_steps": 14493, "loss": 0.274, "lr": 4.3521062545244116e-05, "epoch": 0.6625087342460081, "percentage": 22.08, "elapsed_time": "5:19:59", "remaining_time": "18:49:15", "throughput": 59542.05, "total_tokens": 1143173120} |
| {"current_steps": 3210, "total_steps": 14493, "loss": 0.2734, "lr": 4.350458540743126e-05, "epoch": 0.6645790740405269, "percentage": 22.15, "elapsed_time": "5:20:49", "remaining_time": "18:47:39", "throughput": 59575.62, "total_tokens": 1146777472} |
| {"current_steps": 3220, "total_steps": 14493, "loss": 0.2736, "lr": 4.3488126970263955e-05, "epoch": 0.6666494138350457, "percentage": 22.22, "elapsed_time": "5:21:38", "remaining_time": "18:46:03", "throughput": 59606.85, "total_tokens": 1150330368} |
| {"current_steps": 3230, "total_steps": 14493, "loss": 0.2715, "lr": 4.347168719839527e-05, "epoch": 0.6687197536295645, "percentage": 22.29, "elapsed_time": "5:22:29", "remaining_time": "18:44:30", "throughput": 59636.32, "total_tokens": 1153920384} |
| {"current_steps": 3240, "total_steps": 14493, "loss": 0.2734, "lr": 4.345526605657173e-05, "epoch": 0.6707900934240832, "percentage": 22.36, "elapsed_time": "5:23:19", "remaining_time": "18:42:56", "throughput": 59667.19, "total_tokens": 1157505024} |
| {"current_steps": 3250, "total_steps": 14493, "loss": 0.273, "lr": 4.343886350963304e-05, "epoch": 0.672860433218602, "percentage": 22.42, "elapsed_time": "5:24:08", "remaining_time": "18:41:20", "throughput": 59701.18, "total_tokens": 1161115392} |
| {"current_steps": 3260, "total_steps": 14493, "loss": 0.2706, "lr": 4.3422479522511697e-05, "epoch": 0.6749307730131208, "percentage": 22.49, "elapsed_time": "5:25:00", "remaining_time": "18:39:54", "throughput": 59729.97, "total_tokens": 1164783232} |
| {"current_steps": 3270, "total_steps": 14493, "loss": 0.2725, "lr": 4.340611406023272e-05, "epoch": 0.6770011128076395, "percentage": 22.56, "elapsed_time": "5:25:48", "remaining_time": "18:38:13", "throughput": 59764.12, "total_tokens": 1168308480} |
| {"current_steps": 3280, "total_steps": 14493, "loss": 0.2683, "lr": 4.338976708791336e-05, "epoch": 0.6790714526021583, "percentage": 22.63, "elapsed_time": "5:26:37", "remaining_time": "18:36:37", "throughput": 59798.4, "total_tokens": 1171921792} |
| {"current_steps": 3290, "total_steps": 14493, "loss": 0.2704, "lr": 4.337343857076272e-05, "epoch": 0.6811417923966772, "percentage": 22.7, "elapsed_time": "5:27:26", "remaining_time": "18:35:00", "throughput": 59830.68, "total_tokens": 1175485184} |
| {"current_steps": 3300, "total_steps": 14493, "loss": 0.2759, "lr": 4.33571284740815e-05, "epoch": 0.6832121321911959, "percentage": 22.77, "elapsed_time": "5:28:16", "remaining_time": "18:33:27", "throughput": 59860.87, "total_tokens": 1179055232} |
| {"current_steps": 3310, "total_steps": 14493, "loss": 0.2728, "lr": 4.3340836763261675e-05, "epoch": 0.6852824719857147, "percentage": 22.84, "elapsed_time": "5:29:04", "remaining_time": "18:31:47", "throughput": 59897.84, "total_tokens": 1182652032} |
| {"current_steps": 3320, "total_steps": 14493, "loss": 0.2713, "lr": 4.332456340378618e-05, "epoch": 0.6873528117802334, "percentage": 22.91, "elapsed_time": "5:29:56", "remaining_time": "18:30:22", "throughput": 59925.36, "total_tokens": 1186313600} |
| {"current_steps": 3330, "total_steps": 14493, "loss": 0.2701, "lr": 4.3308308361228586e-05, "epoch": 0.6894231515747522, "percentage": 22.98, "elapsed_time": "5:30:45", "remaining_time": "18:28:45", "throughput": 59958.59, "total_tokens": 1189882112} |
| {"current_steps": 3340, "total_steps": 14493, "loss": 0.2727, "lr": 4.329207160125282e-05, "epoch": 0.691493491369271, "percentage": 23.05, "elapsed_time": "5:31:31", "remaining_time": "18:27:02", "throughput": 59994.3, "total_tokens": 1193379968} |
| {"current_steps": 3350, "total_steps": 14493, "loss": 0.2718, "lr": 4.327585308961287e-05, "epoch": 0.6935638311637897, "percentage": 23.11, "elapsed_time": "5:32:21", "remaining_time": "18:25:30", "throughput": 60026.81, "total_tokens": 1197020544} |
| {"current_steps": 3360, "total_steps": 14493, "loss": 0.2698, "lr": 4.325965279215243e-05, "epoch": 0.6956341709583085, "percentage": 23.18, "elapsed_time": "5:33:12", "remaining_time": "18:24:03", "throughput": 60053.54, "total_tokens": 1200623744} |
| {"current_steps": 3370, "total_steps": 14493, "loss": 0.2709, "lr": 4.3243470674804686e-05, "epoch": 0.6977045107528274, "percentage": 23.25, "elapsed_time": "5:34:03", "remaining_time": "18:22:35", "throughput": 60082.08, "total_tokens": 1204256512} |
| {"current_steps": 3380, "total_steps": 14493, "loss": 0.271, "lr": 4.3227306703591904e-05, "epoch": 0.6997748505473461, "percentage": 23.32, "elapsed_time": "5:34:51", "remaining_time": "18:20:58", "throughput": 60113.83, "total_tokens": 1207775232} |
| {"current_steps": 3390, "total_steps": 14493, "loss": 0.2697, "lr": 4.32111608446252e-05, "epoch": 0.7018451903418649, "percentage": 23.39, "elapsed_time": "5:35:41", "remaining_time": "18:19:26", "throughput": 60142.03, "total_tokens": 1211334400} |
| {"current_steps": 3400, "total_steps": 14493, "loss": 0.2728, "lr": 4.319503306410426e-05, "epoch": 0.7039155301363836, "percentage": 23.46, "elapsed_time": "5:36:34", "remaining_time": "18:18:07", "throughput": 60165.75, "total_tokens": 1215009408} |
| {"current_steps": 3410, "total_steps": 14493, "loss": 0.2701, "lr": 4.317892332831699e-05, "epoch": 0.7059858699309024, "percentage": 23.53, "elapsed_time": "5:37:23", "remaining_time": "18:16:35", "throughput": 60196.34, "total_tokens": 1218598272} |
| {"current_steps": 3420, "total_steps": 14493, "loss": 0.2705, "lr": 4.316283160363922e-05, "epoch": 0.7080562097254212, "percentage": 23.6, "elapsed_time": "5:38:10", "remaining_time": "18:14:54", "throughput": 60233.41, "total_tokens": 1222163072} |
| {"current_steps": 3430, "total_steps": 14493, "loss": 0.2715, "lr": 4.314675785653447e-05, "epoch": 0.7101265495199399, "percentage": 23.67, "elapsed_time": "5:39:00", "remaining_time": "18:13:25", "throughput": 60262.56, "total_tokens": 1225762432} |
| {"current_steps": 3440, "total_steps": 14493, "loss": 0.2691, "lr": 4.3130702053553606e-05, "epoch": 0.7121968893144587, "percentage": 23.74, "elapsed_time": "5:39:49", "remaining_time": "18:11:54", "throughput": 60291.96, "total_tokens": 1229346688} |
| {"current_steps": 3450, "total_steps": 14493, "loss": 0.2685, "lr": 4.3114664161334546e-05, "epoch": 0.7142672291089776, "percentage": 23.8, "elapsed_time": "5:40:54", "remaining_time": "18:11:11", "throughput": 60278.46, "total_tokens": 1232954752} |
| {"current_steps": 3460, "total_steps": 14493, "loss": 0.2671, "lr": 4.3098644146601984e-05, "epoch": 0.7163375689034963, "percentage": 23.87, "elapsed_time": "5:42:01", "remaining_time": "18:10:38", "throughput": 60256.51, "total_tokens": 1236574464} |
| {"current_steps": 3470, "total_steps": 14493, "loss": 0.2715, "lr": 4.30826419761671e-05, "epoch": 0.7184079086980151, "percentage": 23.94, "elapsed_time": "5:42:57", "remaining_time": "18:09:29", "throughput": 60266.51, "total_tokens": 1240162944} |
| {"current_steps": 3480, "total_steps": 14493, "loss": 0.2702, "lr": 4.30666576169273e-05, "epoch": 0.7204782484925338, "percentage": 24.01, "elapsed_time": "5:45:19", "remaining_time": "18:12:48", "throughput": 60030.97, "total_tokens": 1243784960} |
| {"current_steps": 3490, "total_steps": 14493, "loss": 0.2689, "lr": 4.305069103586585e-05, "epoch": 0.7225485882870526, "percentage": 24.08, "elapsed_time": "5:46:44", "remaining_time": "18:13:09", "throughput": 59956.17, "total_tokens": 1247337728} |
| {"current_steps": 3500, "total_steps": 14493, "loss": 0.2675, "lr": 4.303474220005164e-05, "epoch": 0.7246189280815714, "percentage": 24.15, "elapsed_time": "5:47:32", "remaining_time": "18:11:34", "throughput": 59987.12, "total_tokens": 1250872192} |
| {"current_steps": 3510, "total_steps": 14493, "loss": 0.2685, "lr": 4.3018811076638944e-05, "epoch": 0.7266892678760901, "percentage": 24.22, "elapsed_time": "5:48:23", "remaining_time": "18:10:07", "throughput": 60011.06, "total_tokens": 1254434560} |
| {"current_steps": 3520, "total_steps": 14493, "loss": 0.2709, "lr": 4.300289763286704e-05, "epoch": 0.728759607670609, "percentage": 24.29, "elapsed_time": "5:49:13", "remaining_time": "18:08:38", "throughput": 60039.71, "total_tokens": 1258040064} |
| {"current_steps": 3530, "total_steps": 14493, "loss": 0.2733, "lr": 4.298700183606e-05, "epoch": 0.7308299474651277, "percentage": 24.36, "elapsed_time": "5:50:08", "remaining_time": "18:07:26", "throughput": 60052.02, "total_tokens": 1261619584} |
| {"current_steps": 3540, "total_steps": 14493, "loss": 0.271, "lr": 4.297112365362637e-05, "epoch": 0.7329002872596465, "percentage": 24.43, "elapsed_time": "5:51:20", "remaining_time": "18:07:03", "throughput": 60019.62, "total_tokens": 1265218560} |
| {"current_steps": 3550, "total_steps": 14493, "loss": 0.2721, "lr": 4.295526305305891e-05, "epoch": 0.7349706270541653, "percentage": 24.49, "elapsed_time": "5:52:24", "remaining_time": "18:06:19", "throughput": 60003.36, "total_tokens": 1268753280} |
| {"current_steps": 3560, "total_steps": 14493, "loss": 0.2724, "lr": 4.293942000193429e-05, "epoch": 0.737040966848684, "percentage": 24.56, "elapsed_time": "5:53:28", "remaining_time": "18:05:33", "throughput": 59994.58, "total_tokens": 1272412416} |
| {"current_steps": 3570, "total_steps": 14493, "loss": 0.2671, "lr": 4.2923594467912866e-05, "epoch": 0.7391113066432028, "percentage": 24.63, "elapsed_time": "5:54:38", "remaining_time": "18:05:05", "throughput": 59959.9, "total_tokens": 1275868416} |
| {"current_steps": 3580, "total_steps": 14493, "loss": 0.2719, "lr": 4.290778641873832e-05, "epoch": 0.7411816464377216, "percentage": 24.7, "elapsed_time": "5:55:41", "remaining_time": "18:04:15", "throughput": 59950.8, "total_tokens": 1279427968} |
| {"current_steps": 3590, "total_steps": 14493, "loss": 0.2689, "lr": 4.2891995822237455e-05, "epoch": 0.7432519862322403, "percentage": 24.77, "elapsed_time": "5:57:27", "remaining_time": "18:05:38", "throughput": 59820.24, "total_tokens": 1283022592} |
| {"current_steps": 3600, "total_steps": 14493, "loss": 0.2654, "lr": 4.28762226463199e-05, "epoch": 0.7453223260267592, "percentage": 24.84, "elapsed_time": "5:58:51", "remaining_time": "18:05:50", "throughput": 59757.72, "total_tokens": 1286669312} |
| {"current_steps": 3610, "total_steps": 14493, "loss": 0.267, "lr": 4.286046685897781e-05, "epoch": 0.747392665821278, "percentage": 24.91, "elapsed_time": "6:00:02", "remaining_time": "18:05:25", "throughput": 59726.79, "total_tokens": 1290265472} |
| {"current_steps": 3620, "total_steps": 14493, "loss": 0.269, "lr": 4.284472842828562e-05, "epoch": 0.7494630056157967, "percentage": 24.98, "elapsed_time": "6:01:15", "remaining_time": "18:05:05", "throughput": 59692.28, "total_tokens": 1293877760} |
| {"current_steps": 3630, "total_steps": 14493, "loss": 0.2708, "lr": 4.282900732239977e-05, "epoch": 0.7515333454103155, "percentage": 25.05, "elapsed_time": "6:02:27", "remaining_time": "18:04:39", "throughput": 59660.91, "total_tokens": 1297455104} |
| {"current_steps": 3640, "total_steps": 14493, "loss": 0.2709, "lr": 4.281330350955845e-05, "epoch": 0.7536036852048342, "percentage": 25.12, "elapsed_time": "6:04:37", "remaining_time": "18:07:09", "throughput": 59470.31, "total_tokens": 1301056768} |
| {"current_steps": 3650, "total_steps": 14493, "loss": 0.2679, "lr": 4.279761695808125e-05, "epoch": 0.755674024999353, "percentage": 25.18, "elapsed_time": "6:06:15", "remaining_time": "18:08:00", "throughput": 59365.96, "total_tokens": 1304569728} |
| {"current_steps": 3660, "total_steps": 14493, "loss": 0.2699, "lr": 4.278194763636904e-05, "epoch": 0.7577443647938717, "percentage": 25.25, "elapsed_time": "6:08:04", "remaining_time": "18:09:26", "throughput": 59240.23, "total_tokens": 1308287232} |
| {"current_steps": 3670, "total_steps": 14493, "loss": 0.2716, "lr": 4.276629551290354e-05, "epoch": 0.7598147045883906, "percentage": 25.32, "elapsed_time": "6:08:57", "remaining_time": "18:08:03", "throughput": 59265.05, "total_tokens": 1311957888} |
| {"current_steps": 3680, "total_steps": 14493, "loss": 0.2687, "lr": 4.2750660556247175e-05, "epoch": 0.7618850443829094, "percentage": 25.39, "elapsed_time": "6:10:06", "remaining_time": "18:07:28", "throughput": 59239.86, "total_tokens": 1315487744} |
| {"current_steps": 3690, "total_steps": 14493, "loss": 0.2684, "lr": 4.273504273504274e-05, "epoch": 0.7639553841774281, "percentage": 25.46, "elapsed_time": "6:11:15", "remaining_time": "18:06:53", "throughput": 59217.67, "total_tokens": 1319084672} |
| {"current_steps": 3700, "total_steps": 14493, "loss": 0.2688, "lr": 4.271944201801317e-05, "epoch": 0.7660257239719469, "percentage": 25.53, "elapsed_time": "6:12:12", "remaining_time": "18:05:43", "throughput": 59229.56, "total_tokens": 1322730880} |
| {"current_steps": 3710, "total_steps": 14493, "loss": 0.2678, "lr": 4.270385837396127e-05, "epoch": 0.7680960637664657, "percentage": 25.6, "elapsed_time": "6:13:21", "remaining_time": "18:05:08", "throughput": 59204.08, "total_tokens": 1326243200} |
| {"current_steps": 3720, "total_steps": 14493, "loss": 0.2694, "lr": 4.268829177176945e-05, "epoch": 0.7701664035609844, "percentage": 25.67, "elapsed_time": "6:14:15", "remaining_time": "18:03:50", "throughput": 59219.87, "total_tokens": 1329804416} |
| {"current_steps": 3730, "total_steps": 14493, "loss": 0.2668, "lr": 4.2672742180399455e-05, "epoch": 0.7722367433555032, "percentage": 25.74, "elapsed_time": "6:15:05", "remaining_time": "18:02:19", "throughput": 59246.83, "total_tokens": 1333368064} |
| {"current_steps": 3740, "total_steps": 14493, "loss": 0.2682, "lr": 4.265720956889213e-05, "epoch": 0.774307083150022, "percentage": 25.81, "elapsed_time": "6:15:54", "remaining_time": "18:00:45", "throughput": 59278.25, "total_tokens": 1336963328} |
| {"current_steps": 3750, "total_steps": 14493, "loss": 0.2669, "lr": 4.2641693906367113e-05, "epoch": 0.7763774229445408, "percentage": 25.87, "elapsed_time": "6:16:42", "remaining_time": "17:59:12", "throughput": 59309.17, "total_tokens": 1340556032} |
| {"current_steps": 3760, "total_steps": 14493, "loss": 0.2702, "lr": 4.2626195162022646e-05, "epoch": 0.7784477627390596, "percentage": 25.94, "elapsed_time": "6:17:33", "remaining_time": "17:57:46", "throughput": 59334.1, "total_tokens": 1344154496} |
| {"current_steps": 3770, "total_steps": 14493, "loss": 0.2668, "lr": 4.2610713305135255e-05, "epoch": 0.7805181025335783, "percentage": 26.01, "elapsed_time": "6:18:25", "remaining_time": "17:56:20", "throughput": 59353.48, "total_tokens": 1347636864} |
| {"current_steps": 3780, "total_steps": 14493, "loss": 0.267, "lr": 4.2595248305059546e-05, "epoch": 0.7825884423280971, "percentage": 26.08, "elapsed_time": "6:19:19", "remaining_time": "17:55:04", "throughput": 59369.34, "total_tokens": 1351243392} |
| {"current_steps": 3790, "total_steps": 14493, "loss": 0.2663, "lr": 4.2579800131227916e-05, "epoch": 0.7846587821226159, "percentage": 26.15, "elapsed_time": "6:20:10", "remaining_time": "17:53:35", "throughput": 59396.39, "total_tokens": 1354832640} |
| {"current_steps": 3800, "total_steps": 14493, "loss": 0.2669, "lr": 4.256436875315028e-05, "epoch": 0.7867291219171346, "percentage": 26.22, "elapsed_time": "6:20:58", "remaining_time": "17:52:03", "throughput": 59425.67, "total_tokens": 1358401792} |
| {"current_steps": 3810, "total_steps": 14493, "loss": 0.2688, "lr": 4.2548954140413895e-05, "epoch": 0.7887994617116534, "percentage": 26.29, "elapsed_time": "6:21:48", "remaining_time": "17:50:33", "throughput": 59453.02, "total_tokens": 1361976576} |
| {"current_steps": 3820, "total_steps": 14493, "loss": 0.2682, "lr": 4.253355626268302e-05, "epoch": 0.7908698015061723, "percentage": 26.36, "elapsed_time": "6:22:39", "remaining_time": "17:49:09", "throughput": 59479.75, "total_tokens": 1365642752} |
| {"current_steps": 3830, "total_steps": 14493, "loss": 0.2674, "lr": 4.2518175089698716e-05, "epoch": 0.792940141300691, "percentage": 26.43, "elapsed_time": "6:23:30", "remaining_time": "17:47:42", "throughput": 59504.19, "total_tokens": 1369211904} |
| {"current_steps": 3840, "total_steps": 14493, "loss": 0.2672, "lr": 4.25028105912786e-05, "epoch": 0.7950104810952098, "percentage": 26.5, "elapsed_time": "6:24:30", "remaining_time": "17:46:42", "throughput": 59505.2, "total_tokens": 1372817152} |
| {"current_steps": 3850, "total_steps": 14493, "loss": 0.2694, "lr": 4.2487462737316565e-05, "epoch": 0.7970808208897285, "percentage": 26.56, "elapsed_time": "6:25:20", "remaining_time": "17:45:14", "throughput": 59531.7, "total_tokens": 1376393984} |
| {"current_steps": 3860, "total_steps": 14493, "loss": 0.2689, "lr": 4.2472131497782555e-05, "epoch": 0.7991511606842473, "percentage": 26.63, "elapsed_time": "6:26:10", "remaining_time": "17:43:47", "throughput": 59557.77, "total_tokens": 1379995136} |
| {"current_steps": 3870, "total_steps": 14493, "loss": 0.269, "lr": 4.245681684272231e-05, "epoch": 0.8012215004787661, "percentage": 26.7, "elapsed_time": "6:27:00", "remaining_time": "17:42:20", "throughput": 59584.59, "total_tokens": 1383600128} |
| {"current_steps": 3880, "total_steps": 14493, "loss": 0.266, "lr": 4.244151874225712e-05, "epoch": 0.8032918402732848, "percentage": 26.77, "elapsed_time": "6:27:49", "remaining_time": "17:40:49", "throughput": 59613.94, "total_tokens": 1387183488} |
| {"current_steps": 3890, "total_steps": 14493, "loss": 0.2678, "lr": 4.2426237166583596e-05, "epoch": 0.8053621800678036, "percentage": 26.84, "elapsed_time": "6:28:38", "remaining_time": "17:39:19", "throughput": 59641.31, "total_tokens": 1390740096} |
| {"current_steps": 3900, "total_steps": 14493, "loss": 0.2663, "lr": 4.241097208597339e-05, "epoch": 0.8074325198623225, "percentage": 26.91, "elapsed_time": "6:29:28", "remaining_time": "17:37:53", "throughput": 59667.0, "total_tokens": 1394350592} |
| {"current_steps": 3910, "total_steps": 14493, "loss": 0.2654, "lr": 4.2395723470773005e-05, "epoch": 0.8095028596568412, "percentage": 26.98, "elapsed_time": "6:30:15", "remaining_time": "17:36:16", "throughput": 59697.42, "total_tokens": 1397827328} |
| {"current_steps": 3920, "total_steps": 14493, "loss": 0.2655, "lr": 4.238049129140347e-05, "epoch": 0.81157319945136, "percentage": 27.05, "elapsed_time": "6:31:03", "remaining_time": "17:34:44", "throughput": 59727.4, "total_tokens": 1401384320} |
| {"current_steps": 3930, "total_steps": 14493, "loss": 0.2654, "lr": 4.236527551836022e-05, "epoch": 0.8136435392458787, "percentage": 27.12, "elapsed_time": "6:31:51", "remaining_time": "17:33:13", "throughput": 59754.52, "total_tokens": 1404907776} |
| {"current_steps": 3940, "total_steps": 14493, "loss": 0.2638, "lr": 4.235007612221274e-05, "epoch": 0.8157138790403975, "percentage": 27.19, "elapsed_time": "6:32:40", "remaining_time": "17:31:46", "throughput": 59780.5, "total_tokens": 1408479488} |
| {"current_steps": 3950, "total_steps": 14493, "loss": 0.2675, "lr": 4.2334893073604386e-05, "epoch": 0.8177842188349163, "percentage": 27.25, "elapsed_time": "6:33:28", "remaining_time": "17:30:14", "throughput": 59809.98, "total_tokens": 1412036736} |
| {"current_steps": 3960, "total_steps": 14493, "loss": 0.2642, "lr": 4.231972634325214e-05, "epoch": 0.819854558629435, "percentage": 27.32, "elapsed_time": "6:34:17", "remaining_time": "17:28:45", "throughput": 59834.27, "total_tokens": 1415525760} |
| {"current_steps": 3970, "total_steps": 14493, "loss": 0.2677, "lr": 4.230457590194635e-05, "epoch": 0.8219248984239539, "percentage": 27.39, "elapsed_time": "6:35:07", "remaining_time": "17:27:20", "throughput": 59858.95, "total_tokens": 1419117952} |
| {"current_steps": 3980, "total_steps": 14493, "loss": 0.271, "lr": 4.228944172055053e-05, "epoch": 0.8239952382184726, "percentage": 27.46, "elapsed_time": "6:36:00", "remaining_time": "17:26:01", "throughput": 59880.52, "total_tokens": 1422763136} |
| {"current_steps": 3990, "total_steps": 14493, "loss": 0.2672, "lr": 4.22743237700011e-05, "epoch": 0.8260655780129914, "percentage": 27.53, "elapsed_time": "6:36:47", "remaining_time": "17:24:29", "throughput": 59911.38, "total_tokens": 1426354560} |
| {"current_steps": 4000, "total_steps": 14493, "loss": 0.2663, "lr": 4.225922202130716e-05, "epoch": 0.8281359178075102, "percentage": 27.6, "elapsed_time": "6:37:36", "remaining_time": "17:23:01", "throughput": 59937.19, "total_tokens": 1429886208} |
| {"current_steps": 4010, "total_steps": 14493, "loss": 0.2683, "lr": 4.224413644555024e-05, "epoch": 0.8302062576020289, "percentage": 27.67, "elapsed_time": "6:38:25", "remaining_time": "17:21:34", "throughput": 59960.74, "total_tokens": 1433392256} |
| {"current_steps": 4020, "total_steps": 14493, "loss": 0.2646, "lr": 4.222906701388411e-05, "epoch": 0.8322765973965477, "percentage": 27.74, "elapsed_time": "6:39:13", "remaining_time": "17:20:03", "throughput": 59990.65, "total_tokens": 1436978944} |
| {"current_steps": 4030, "total_steps": 14493, "loss": 0.2679, "lr": 4.2214013697534466e-05, "epoch": 0.8343469371910665, "percentage": 27.81, "elapsed_time": "6:40:07", "remaining_time": "17:18:51", "throughput": 60006.06, "total_tokens": 1440622848} |
| {"current_steps": 4040, "total_steps": 14493, "loss": 0.2623, "lr": 4.219897646779882e-05, "epoch": 0.8364172769855852, "percentage": 27.88, "elapsed_time": "6:40:53", "remaining_time": "17:17:16", "throughput": 60037.97, "total_tokens": 1444144768} |
| {"current_steps": 4050, "total_steps": 14493, "loss": 0.2639, "lr": 4.2183955296046145e-05, "epoch": 0.8384876167801041, "percentage": 27.94, "elapsed_time": "6:41:40", "remaining_time": "17:15:43", "throughput": 60066.35, "total_tokens": 1447633280} |
| {"current_steps": 4060, "total_steps": 14493, "loss": 0.2675, "lr": 4.2168950153716746e-05, "epoch": 0.8405579565746228, "percentage": 28.01, "elapsed_time": "6:42:29", "remaining_time": "17:14:18", "throughput": 60090.22, "total_tokens": 1451174016} |
| {"current_steps": 4070, "total_steps": 14493, "loss": 0.2638, "lr": 4.215396101232197e-05, "epoch": 0.8426282963691416, "percentage": 28.08, "elapsed_time": "6:43:18", "remaining_time": "17:12:49", "throughput": 60116.98, "total_tokens": 1454722688} |
| {"current_steps": 4080, "total_steps": 14493, "loss": 0.2667, "lr": 4.213898784344398e-05, "epoch": 0.8446986361636604, "percentage": 28.15, "elapsed_time": "6:44:10", "remaining_time": "17:11:31", "throughput": 60137.37, "total_tokens": 1458351232} |
| {"current_steps": 4090, "total_steps": 14493, "loss": 0.2659, "lr": 4.21240306187356e-05, "epoch": 0.8467689759581791, "percentage": 28.22, "elapsed_time": "6:44:58", "remaining_time": "17:10:02", "throughput": 60164.69, "total_tokens": 1461884416} |
| {"current_steps": 4100, "total_steps": 14493, "loss": 0.2668, "lr": 4.2109089309919967e-05, "epoch": 0.8488393157526979, "percentage": 28.29, "elapsed_time": "6:45:47", "remaining_time": "17:08:38", "throughput": 60188.18, "total_tokens": 1465451392} |
| {"current_steps": 4110, "total_steps": 14493, "loss": 0.2655, "lr": 4.2094163888790445e-05, "epoch": 0.8509096555472166, "percentage": 28.36, "elapsed_time": "6:46:38", "remaining_time": "17:07:16", "throughput": 60209.13, "total_tokens": 1468983040} |
| {"current_steps": 4120, "total_steps": 14493, "loss": 0.265, "lr": 4.2079254327210294e-05, "epoch": 0.8529799953417354, "percentage": 28.43, "elapsed_time": "6:47:28", "remaining_time": "17:05:53", "throughput": 60234.87, "total_tokens": 1472632192} |
| {"current_steps": 4130, "total_steps": 14493, "loss": 0.2656, "lr": 4.206436059711249e-05, "epoch": 0.8550503351362543, "percentage": 28.5, "elapsed_time": "6:48:14", "remaining_time": "17:04:21", "throughput": 60264.82, "total_tokens": 1476151296} |
| {"current_steps": 4140, "total_steps": 14493, "loss": 0.2686, "lr": 4.20494826704995e-05, "epoch": 0.857120674930773, "percentage": 28.57, "elapsed_time": "6:49:02", "remaining_time": "17:02:54", "throughput": 60289.84, "total_tokens": 1479667584} |
| {"current_steps": 4150, "total_steps": 14493, "loss": 0.2642, "lr": 4.203462051944307e-05, "epoch": 0.8591910147252918, "percentage": 28.63, "elapsed_time": "6:49:51", "remaining_time": "17:01:29", "throughput": 60313.75, "total_tokens": 1483212032} |
| {"current_steps": 4160, "total_steps": 14493, "loss": 0.2649, "lr": 4.201977411608398e-05, "epoch": 0.8612613545198106, "percentage": 28.7, "elapsed_time": "6:50:42", "remaining_time": "17:00:09", "throughput": 60336.8, "total_tokens": 1486856448} |
| {"current_steps": 4170, "total_steps": 14493, "loss": 0.2664, "lr": 4.200494343263185e-05, "epoch": 0.8633316943143293, "percentage": 28.77, "elapsed_time": "6:51:31", "remaining_time": "16:58:46", "throughput": 60362.94, "total_tokens": 1490481152} |
| {"current_steps": 4180, "total_steps": 14493, "loss": 0.2646, "lr": 4.1990128441364914e-05, "epoch": 0.8654020341088481, "percentage": 28.84, "elapsed_time": "6:52:18", "remaining_time": "16:57:15", "throughput": 60392.34, "total_tokens": 1494014976} |
| {"current_steps": 4190, "total_steps": 14493, "loss": 0.2652, "lr": 4.197532911462977e-05, "epoch": 0.8674723739033668, "percentage": 28.91, "elapsed_time": "6:53:06", "remaining_time": "16:55:49", "throughput": 60416.13, "total_tokens": 1497513344} |
| {"current_steps": 4200, "total_steps": 14493, "loss": 0.2665, "lr": 4.196054542484125e-05, "epoch": 0.8695427136978857, "percentage": 28.98, "elapsed_time": "6:53:57", "remaining_time": "16:54:29", "throughput": 60438.03, "total_tokens": 1501124480} |
| {"current_steps": 4210, "total_steps": 14493, "loss": 0.2658, "lr": 4.1945777344482084e-05, "epoch": 0.8716130534924045, "percentage": 29.05, "elapsed_time": "6:54:45", "remaining_time": "16:53:03", "throughput": 60463.27, "total_tokens": 1504659968} |
| {"current_steps": 4220, "total_steps": 14493, "loss": 0.2648, "lr": 4.19310248461028e-05, "epoch": 0.8736833932869232, "percentage": 29.12, "elapsed_time": "6:55:33", "remaining_time": "16:51:37", "throughput": 60487.59, "total_tokens": 1508165120} |
| {"current_steps": 4230, "total_steps": 14493, "loss": 0.2649, "lr": 4.1916287902321405e-05, "epoch": 0.875753733081442, "percentage": 29.19, "elapsed_time": "6:56:23", "remaining_time": "16:50:17", "throughput": 60510.21, "total_tokens": 1511783680} |
| {"current_steps": 4240, "total_steps": 14493, "loss": 0.2646, "lr": 4.190156648582328e-05, "epoch": 0.8778240728759608, "percentage": 29.26, "elapsed_time": "6:57:12", "remaining_time": "16:48:52", "throughput": 60534.92, "total_tokens": 1515329792} |
| {"current_steps": 4250, "total_steps": 14493, "loss": 0.2666, "lr": 4.188686056936087e-05, "epoch": 0.8798944126704795, "percentage": 29.32, "elapsed_time": "6:57:59", "remaining_time": "16:47:25", "throughput": 60560.95, "total_tokens": 1518859648} |
| {"current_steps": 4260, "total_steps": 14493, "loss": 0.2656, "lr": 4.187217012575352e-05, "epoch": 0.8819647524649983, "percentage": 29.39, "elapsed_time": "6:58:47", "remaining_time": "16:46:00", "throughput": 60588.85, "total_tokens": 1522472576} |
| {"current_steps": 4270, "total_steps": 14493, "loss": 0.2631, "lr": 4.185749512788727e-05, "epoch": 0.884035092259517, "percentage": 29.46, "elapsed_time": "6:59:37", "remaining_time": "16:44:37", "throughput": 60616.33, "total_tokens": 1526149504} |
| {"current_steps": 4280, "total_steps": 14493, "loss": 0.2643, "lr": 4.184283554871462e-05, "epoch": 0.8861054320540359, "percentage": 29.53, "elapsed_time": "7:00:25", "remaining_time": "16:43:13", "throughput": 60638.33, "total_tokens": 1529629440} |
| {"current_steps": 4290, "total_steps": 14493, "loss": 0.2663, "lr": 4.1828191361254344e-05, "epoch": 0.8881757718485547, "percentage": 29.6, "elapsed_time": "7:01:15", "remaining_time": "16:41:53", "throughput": 60660.81, "total_tokens": 1533225472} |
| {"current_steps": 4300, "total_steps": 14493, "loss": 0.2656, "lr": 4.181356253859127e-05, "epoch": 0.8902461116430734, "percentage": 29.67, "elapsed_time": "7:02:04", "remaining_time": "16:40:29", "throughput": 60684.18, "total_tokens": 1536766464} |
| {"current_steps": 4310, "total_steps": 14493, "loss": 0.2665, "lr": 4.179894905387606e-05, "epoch": 0.8923164514375922, "percentage": 29.74, "elapsed_time": "7:02:52", "remaining_time": "16:39:06", "throughput": 60707.82, "total_tokens": 1540328320} |
| {"current_steps": 4320, "total_steps": 14493, "loss": 0.2659, "lr": 4.178435088032502e-05, "epoch": 0.894386791232111, "percentage": 29.81, "elapsed_time": "7:03:42", "remaining_time": "16:37:45", "throughput": 60729.84, "total_tokens": 1543875456} |
| {"current_steps": 4330, "total_steps": 14493, "loss": 0.2655, "lr": 4.176976799121989e-05, "epoch": 0.8964571310266297, "percentage": 29.88, "elapsed_time": "7:04:31", "remaining_time": "16:36:24", "throughput": 60751.54, "total_tokens": 1547420800} |
| {"current_steps": 4340, "total_steps": 14493, "loss": 0.2649, "lr": 4.1755200359907657e-05, "epoch": 0.8985274708211485, "percentage": 29.95, "elapsed_time": "7:05:19", "remaining_time": "16:35:00", "throughput": 60775.43, "total_tokens": 1550967680} |
| {"current_steps": 4350, "total_steps": 14493, "loss": 0.2654, "lr": 4.174064795980028e-05, "epoch": 0.9005978106156673, "percentage": 30.01, "elapsed_time": "7:06:08", "remaining_time": "16:33:37", "throughput": 60797.71, "total_tokens": 1554476032} |
| {"current_steps": 4360, "total_steps": 14493, "loss": 0.2667, "lr": 4.17261107643746e-05, "epoch": 0.9026681504101861, "percentage": 30.08, "elapsed_time": "7:06:57", "remaining_time": "16:32:16", "throughput": 60818.66, "total_tokens": 1558005248} |
| {"current_steps": 4370, "total_steps": 14493, "loss": 0.2647, "lr": 4.171158874717204e-05, "epoch": 0.9047384902047049, "percentage": 30.15, "elapsed_time": "7:07:47", "remaining_time": "16:30:57", "throughput": 60842.24, "total_tokens": 1561657088} |
| {"current_steps": 4380, "total_steps": 14493, "loss": 0.2657, "lr": 4.169708188179844e-05, "epoch": 0.9068088299992236, "percentage": 30.22, "elapsed_time": "7:08:35", "remaining_time": "16:29:35", "throughput": 60865.97, "total_tokens": 1565217920} |
| {"current_steps": 4390, "total_steps": 14493, "loss": 0.2623, "lr": 4.1682590141923846e-05, "epoch": 0.9088791697937424, "percentage": 30.29, "elapsed_time": "7:09:27", "remaining_time": "16:28:20", "throughput": 60884.48, "total_tokens": 1568841984} |
| {"current_steps": 4400, "total_steps": 14493, "loss": 0.2656, "lr": 4.1668113501282335e-05, "epoch": 0.9109495095882612, "percentage": 30.36, "elapsed_time": "7:10:14", "remaining_time": "16:26:55", "throughput": 60907.72, "total_tokens": 1572328832} |
| {"current_steps": 4410, "total_steps": 14493, "loss": 0.2634, "lr": 4.165365193367178e-05, "epoch": 0.9130198493827799, "percentage": 30.43, "elapsed_time": "7:11:01", "remaining_time": "16:25:30", "throughput": 60936.62, "total_tokens": 1575942528} |
| {"current_steps": 4420, "total_steps": 14493, "loss": 0.2645, "lr": 4.163920541295369e-05, "epoch": 0.9150901891772987, "percentage": 30.5, "elapsed_time": "7:11:48", "remaining_time": "16:24:05", "throughput": 60959.92, "total_tokens": 1579410304} |
| {"current_steps": 4430, "total_steps": 14493, "loss": 0.2647, "lr": 4.1624773913052946e-05, "epoch": 0.9171605289718175, "percentage": 30.57, "elapsed_time": "7:12:37", "remaining_time": "16:22:44", "throughput": 60982.96, "total_tokens": 1582991232} |
| {"current_steps": 4440, "total_steps": 14493, "loss": 0.2672, "lr": 4.161035740795769e-05, "epoch": 0.9192308687663363, "percentage": 30.64, "elapsed_time": "7:13:27", "remaining_time": "16:21:26", "throughput": 61003.38, "total_tokens": 1586562560} |
| {"current_steps": 4450, "total_steps": 14493, "loss": 0.2631, "lr": 4.1595955871719055e-05, "epoch": 0.9213012085608551, "percentage": 30.7, "elapsed_time": "7:14:15", "remaining_time": "16:20:04", "throughput": 61026.06, "total_tokens": 1590081280} |
| {"current_steps": 4460, "total_steps": 14493, "loss": 0.2669, "lr": 4.158156927845101e-05, "epoch": 0.9233715483553738, "percentage": 30.77, "elapsed_time": "7:15:04", "remaining_time": "16:18:44", "throughput": 61047.81, "total_tokens": 1593652224} |
| {"current_steps": 4470, "total_steps": 14493, "loss": 0.2642, "lr": 4.156719760233016e-05, "epoch": 0.9254418881498926, "percentage": 30.84, "elapsed_time": "7:15:54", "remaining_time": "16:17:25", "throughput": 61072.12, "total_tokens": 1597293696} |
| {"current_steps": 4480, "total_steps": 14493, "loss": 0.2636, "lr": 4.155284081759552e-05, "epoch": 0.9275122279444113, "percentage": 30.91, "elapsed_time": "7:16:41", "remaining_time": "16:16:00", "throughput": 61097.15, "total_tokens": 1600821888} |
| {"current_steps": 4490, "total_steps": 14493, "loss": 0.2683, "lr": 4.1538498898548356e-05, "epoch": 0.9295825677389301, "percentage": 30.98, "elapsed_time": "7:17:27", "remaining_time": "16:14:35", "throughput": 61123.64, "total_tokens": 1604356224} |
| {"current_steps": 4500, "total_steps": 14493, "loss": 0.2642, "lr": 4.1524171819552e-05, "epoch": 0.931652907533449, "percentage": 31.05, "elapsed_time": "7:18:16", "remaining_time": "16:13:16", "throughput": 61145.66, "total_tokens": 1607927040} |
| {"current_steps": 4510, "total_steps": 14493, "loss": 0.2639, "lr": 4.15098595550316e-05, "epoch": 0.9337232473279677, "percentage": 31.12, "elapsed_time": "7:19:06", "remaining_time": "16:11:58", "throughput": 61167.84, "total_tokens": 1611549312} |
| {"current_steps": 4520, "total_steps": 14493, "loss": 0.2642, "lr": 4.1495562079474e-05, "epoch": 0.9357935871224865, "percentage": 31.19, "elapsed_time": "7:19:54", "remaining_time": "16:10:37", "throughput": 61189.87, "total_tokens": 1615078016} |
| {"current_steps": 4530, "total_steps": 14493, "loss": 0.2677, "lr": 4.148127936742749e-05, "epoch": 0.9378639269170053, "percentage": 31.26, "elapsed_time": "7:20:44", "remaining_time": "16:09:19", "throughput": 61212.21, "total_tokens": 1618714112} |
| {"current_steps": 4540, "total_steps": 14493, "loss": 0.2616, "lr": 4.146701139350166e-05, "epoch": 0.939934266711524, "percentage": 31.33, "elapsed_time": "7:21:32", "remaining_time": "16:07:58", "throughput": 61234.15, "total_tokens": 1622235520} |
| {"current_steps": 4550, "total_steps": 14493, "loss": 0.2628, "lr": 4.1452758132367196e-05, "epoch": 0.9420046065060428, "percentage": 31.39, "elapsed_time": "7:22:24", "remaining_time": "16:06:46", "throughput": 61251.09, "total_tokens": 1625868672} |
| {"current_steps": 4560, "total_steps": 14493, "loss": 0.2629, "lr": 4.1438519558755656e-05, "epoch": 0.9440749463005615, "percentage": 31.46, "elapsed_time": "7:23:15", "remaining_time": "16:05:31", "throughput": 61271.38, "total_tokens": 1629513344} |
| {"current_steps": 4570, "total_steps": 14493, "loss": 0.2614, "lr": 4.1424295647459336e-05, "epoch": 0.9461452860950803, "percentage": 31.53, "elapsed_time": "7:24:01", "remaining_time": "16:04:08", "throughput": 61294.08, "total_tokens": 1632985856} |
| {"current_steps": 4580, "total_steps": 14493, "loss": 0.2629, "lr": 4.141008637333106e-05, "epoch": 0.9482156258895992, "percentage": 31.6, "elapsed_time": "7:24:47", "remaining_time": "16:02:43", "throughput": 61319.76, "total_tokens": 1636497664} |
| {"current_steps": 4590, "total_steps": 14493, "loss": 0.2618, "lr": 4.1395891711283974e-05, "epoch": 0.9502859656841179, "percentage": 31.67, "elapsed_time": "7:25:37", "remaining_time": "16:01:27", "throughput": 61340.19, "total_tokens": 1640107008} |
| {"current_steps": 4600, "total_steps": 14493, "loss": 0.2612, "lr": 4.1381711636291395e-05, "epoch": 0.9523563054786367, "percentage": 31.74, "elapsed_time": "7:26:28", "remaining_time": "16:00:13", "throughput": 61359.72, "total_tokens": 1643746560} |
| {"current_steps": 4610, "total_steps": 14493, "loss": 0.2616, "lr": 4.1367546123386604e-05, "epoch": 0.9544266452731555, "percentage": 31.81, "elapsed_time": "7:27:17", "remaining_time": "15:58:55", "throughput": 61382.84, "total_tokens": 1647379072} |
| {"current_steps": 4620, "total_steps": 14493, "loss": 0.2653, "lr": 4.1353395147662673e-05, "epoch": 0.9564969850676742, "percentage": 31.88, "elapsed_time": "7:28:09", "remaining_time": "15:57:43", "throughput": 61399.1, "total_tokens": 1650993536} |
| {"current_steps": 4630, "total_steps": 14493, "loss": 0.2654, "lr": 4.133925868427225e-05, "epoch": 0.958567324862193, "percentage": 31.95, "elapsed_time": "7:28:59", "remaining_time": "15:56:27", "throughput": 61417.48, "total_tokens": 1654554880} |
| {"current_steps": 4640, "total_steps": 14493, "loss": 0.2637, "lr": 4.132513670842744e-05, "epoch": 0.9606376646567117, "percentage": 32.02, "elapsed_time": "7:29:49", "remaining_time": "15:55:11", "throughput": 61434.85, "total_tokens": 1658092928} |
| {"current_steps": 4650, "total_steps": 14493, "loss": 0.2611, "lr": 4.1311029195399534e-05, "epoch": 0.9627080044512305, "percentage": 32.08, "elapsed_time": "7:30:36", "remaining_time": "15:53:49", "throughput": 61458.19, "total_tokens": 1661606784} |
| {"current_steps": 4660, "total_steps": 14493, "loss": 0.264, "lr": 4.129693612051892e-05, "epoch": 0.9647783442457494, "percentage": 32.15, "elapsed_time": "7:31:27", "remaining_time": "15:52:36", "throughput": 61472.92, "total_tokens": 1665139712} |
| {"current_steps": 4670, "total_steps": 14493, "loss": 0.2617, "lr": 4.1282857459174826e-05, "epoch": 0.9668486840402681, "percentage": 32.22, "elapsed_time": "7:33:45", "remaining_time": "15:54:27", "throughput": 61289.79, "total_tokens": 1668670080} |
| {"current_steps": 4680, "total_steps": 14493, "loss": 0.2619, "lr": 4.1268793186815184e-05, "epoch": 0.9689190238347869, "percentage": 32.29, "elapsed_time": "7:36:42", "remaining_time": "15:57:38", "throughput": 61021.52, "total_tokens": 1672169216} |
| {"current_steps": 4690, "total_steps": 14493, "loss": 0.2631, "lr": 4.1254743278946456e-05, "epoch": 0.9709893636293057, "percentage": 32.36, "elapsed_time": "7:40:15", "remaining_time": "16:02:01", "throughput": 60682.4, "total_tokens": 1675783424} |
| {"current_steps": 4700, "total_steps": 14493, "loss": 0.2628, "lr": 4.1240707711133394e-05, "epoch": 0.9730597034238244, "percentage": 32.43, "elapsed_time": "7:45:04", "remaining_time": "16:09:03", "throughput": 60185.17, "total_tokens": 1679461632} |
| {"current_steps": 4710, "total_steps": 14493, "loss": 0.2645, "lr": 4.122668645899893e-05, "epoch": 0.9751300432183432, "percentage": 32.5, "elapsed_time": "7:50:31", "remaining_time": "16:17:19", "throughput": 59614.87, "total_tokens": 1683031040} |
| {"current_steps": 4720, "total_steps": 14493, "loss": 0.2625, "lr": 4.1212679498223975e-05, "epoch": 0.9772003830128619, "percentage": 32.57, "elapsed_time": "7:54:19", "remaining_time": "16:22:06", "throughput": 59264.73, "total_tokens": 1686634752} |
| {"current_steps": 4730, "total_steps": 14493, "loss": 0.2638, "lr": 4.1198686804547215e-05, "epoch": 0.9792707228073808, "percentage": 32.64, "elapsed_time": "7:56:48", "remaining_time": "16:24:10", "throughput": 59080.89, "total_tokens": 1690243200} |
| {"current_steps": 4740, "total_steps": 14493, "loss": 0.2634, "lr": 4.118470835376499e-05, "epoch": 0.9813410626018996, "percentage": 32.71, "elapsed_time": "7:58:54", "remaining_time": "16:25:23", "throughput": 58946.6, "total_tokens": 1693794688} |
| {"current_steps": 4750, "total_steps": 14493, "loss": 0.2617, "lr": 4.117074412173107e-05, "epoch": 0.9834114023964183, "percentage": 32.77, "elapsed_time": "8:01:46", "remaining_time": "16:28:11", "throughput": 58719.61, "total_tokens": 1697373952} |
| {"current_steps": 4760, "total_steps": 14493, "loss": 0.2621, "lr": 4.115679408435648e-05, "epoch": 0.9854817421909371, "percentage": 32.84, "elapsed_time": "8:04:37", "remaining_time": "16:30:55", "throughput": 58499.23, "total_tokens": 1700991488} |
| {"current_steps": 4770, "total_steps": 14493, "loss": 0.2629, "lr": 4.114285821760937e-05, "epoch": 0.9875520819854559, "percentage": 32.91, "elapsed_time": "8:08:44", "remaining_time": "16:36:14", "throughput": 58124.52, "total_tokens": 1704497152} |
| {"current_steps": 4780, "total_steps": 14493, "loss": 0.2623, "lr": 4.11289364975148e-05, "epoch": 0.9896224217799746, "percentage": 32.98, "elapsed_time": "8:11:49", "remaining_time": "16:39:22", "throughput": 57882.13, "total_tokens": 1708043904} |
| {"current_steps": 4790, "total_steps": 14493, "loss": 0.2634, "lr": 4.111502890015456e-05, "epoch": 0.9916927615744934, "percentage": 33.05, "elapsed_time": "8:13:13", "remaining_time": "16:39:06", "throughput": 57836.71, "total_tokens": 1711590016} |
| {"current_steps": 4800, "total_steps": 14493, "loss": 0.2635, "lr": 4.1101135401667056e-05, "epoch": 0.9937631013690121, "percentage": 33.12, "elapsed_time": "8:14:08", "remaining_time": "16:37:50", "throughput": 57847.84, "total_tokens": 1715088256} |
| {"current_steps": 4810, "total_steps": 14493, "loss": 0.2635, "lr": 4.108725597824708e-05, "epoch": 0.995833441163531, "percentage": 33.19, "elapsed_time": "8:15:04", "remaining_time": "16:36:37", "throughput": 57860.36, "total_tokens": 1718697600} |
| {"current_steps": 4820, "total_steps": 14493, "loss": 0.2634, "lr": 4.107339060614564e-05, "epoch": 0.9979037809580498, "percentage": 33.26, "elapsed_time": "8:15:59", "remaining_time": "16:35:22", "throughput": 57872.29, "total_tokens": 1722238720} |
| {"current_steps": 4830, "total_steps": 14493, "loss": 0.2639, "lr": 4.1059539261669825e-05, "epoch": 0.9999741207525685, "percentage": 33.33, "elapsed_time": "8:16:50", "remaining_time": "16:34:00", "throughput": 57887.93, "total_tokens": 1725687040} |
| {"current_steps": 4840, "total_steps": 14493, "loss": 0.2538, "lr": 4.104570192118262e-05, "epoch": 1.001863305815067, "percentage": 33.4, "elapsed_time": "8:17:42", "remaining_time": "16:32:37", "throughput": 57894.71, "total_tokens": 1728858880} |
| {"current_steps": 4850, "total_steps": 14493, "loss": 0.2467, "lr": 4.1031878561102714e-05, "epoch": 1.0039336456095858, "percentage": 33.46, "elapsed_time": "8:18:36", "remaining_time": "16:31:21", "throughput": 57908.77, "total_tokens": 1732439808} |
| {"current_steps": 4860, "total_steps": 14493, "loss": 0.2459, "lr": 4.1018069157904385e-05, "epoch": 1.0060039854041045, "percentage": 33.53, "elapsed_time": "8:19:34", "remaining_time": "16:30:11", "throughput": 57917.34, "total_tokens": 1736028672} |
| {"current_steps": 4870, "total_steps": 14493, "loss": 0.2501, "lr": 4.100427368811727e-05, "epoch": 1.0080743251986233, "percentage": 33.6, "elapsed_time": "8:20:27", "remaining_time": "16:28:52", "throughput": 57934.84, "total_tokens": 1739611648} |
| {"current_steps": 4880, "total_steps": 14493, "loss": 0.2503, "lr": 4.099049212832622e-05, "epoch": 1.010144664993142, "percentage": 33.67, "elapsed_time": "8:21:21", "remaining_time": "16:27:36", "throughput": 57950.39, "total_tokens": 1743210240} |
| {"current_steps": 4890, "total_steps": 14493, "loss": 0.2499, "lr": 4.0976724455171155e-05, "epoch": 1.0122150047876608, "percentage": 33.74, "elapsed_time": "8:22:14", "remaining_time": "16:26:18", "throughput": 57968.1, "total_tokens": 1746841984} |
| {"current_steps": 4900, "total_steps": 14493, "loss": 0.2463, "lr": 4.096297064534688e-05, "epoch": 1.0142853445821796, "percentage": 33.81, "elapsed_time": "8:23:11", "remaining_time": "16:25:06", "throughput": 57977.27, "total_tokens": 1750397952} |
| {"current_steps": 4910, "total_steps": 14493, "loss": 0.249, "lr": 4.0949230675602904e-05, "epoch": 1.0163556843766983, "percentage": 33.88, "elapsed_time": "8:24:04", "remaining_time": "16:23:48", "throughput": 57996.29, "total_tokens": 1754045440} |
| {"current_steps": 4920, "total_steps": 14493, "loss": 0.2469, "lr": 4.09355045227433e-05, "epoch": 1.018426024171217, "percentage": 33.95, "elapsed_time": "8:25:09", "remaining_time": "16:22:54", "throughput": 57986.48, "total_tokens": 1757559808} |
| {"current_steps": 4930, "total_steps": 14493, "loss": 0.2462, "lr": 4.092179216362654e-05, "epoch": 1.0204963639657358, "percentage": 34.02, "elapsed_time": "8:26:07", "remaining_time": "16:21:46", "throughput": 57995.86, "total_tokens": 1761207168} |
| {"current_steps": 4940, "total_steps": 14493, "loss": 0.2461, "lr": 4.090809357516532e-05, "epoch": 1.0225667037602546, "percentage": 34.09, "elapsed_time": "8:27:02", "remaining_time": "16:20:31", "throughput": 58008.67, "total_tokens": 1764765056} |
| {"current_steps": 4950, "total_steps": 14493, "loss": 0.2499, "lr": 4.089440873432638e-05, "epoch": 1.0246370435547734, "percentage": 34.15, "elapsed_time": "8:27:57", "remaining_time": "16:19:17", "throughput": 58020.14, "total_tokens": 1768333056} |
| {"current_steps": 4960, "total_steps": 14493, "loss": 0.2466, "lr": 4.088073761813037e-05, "epoch": 1.0267073833492921, "percentage": 34.22, "elapsed_time": "8:29:16", "remaining_time": "16:18:49", "throughput": 57987.55, "total_tokens": 1771913856} |
| {"current_steps": 4970, "total_steps": 14493, "loss": 0.247, "lr": 4.086708020365172e-05, "epoch": 1.0287777231438109, "percentage": 34.29, "elapsed_time": "8:30:35", "remaining_time": "16:18:19", "throughput": 57956.77, "total_tokens": 1775512704} |
| {"current_steps": 4980, "total_steps": 14493, "loss": 0.2493, "lr": 4.0853436468018354e-05, "epoch": 1.0308480629383296, "percentage": 34.36, "elapsed_time": "8:32:06", "remaining_time": "16:18:15", "throughput": 57899.16, "total_tokens": 1779052416} |
| {"current_steps": 4990, "total_steps": 14493, "loss": 0.2476, "lr": 4.0839806388411686e-05, "epoch": 1.0329184027328486, "percentage": 34.43, "elapsed_time": "8:34:38", "remaining_time": "16:20:04", "throughput": 57731.43, "total_tokens": 1782633216} |
| {"current_steps": 5000, "total_steps": 14493, "loss": 0.2468, "lr": 4.0826189942066346e-05, "epoch": 1.0349887425273674, "percentage": 34.5, "elapsed_time": "8:37:56", "remaining_time": "16:23:22", "throughput": 57478.15, "total_tokens": 1786236544} |
| {"current_steps": 5000, "total_steps": 14493, "eval_loss": 0.23064059019088745, "epoch": 1.0349887425273674, "percentage": 34.5, "elapsed_time": "8:37:58", "remaining_time": "16:23:24", "throughput": 57475.74, "total_tokens": 1786236544} |
| {"current_steps": 5010, "total_steps": 14493, "loss": 0.2466, "lr": 4.081258710627008e-05, "epoch": 1.0370590823218861, "percentage": 34.57, "elapsed_time": "8:42:01", "remaining_time": "16:28:06", "throughput": 57143.11, "total_tokens": 1789827072} |
| {"current_steps": 5020, "total_steps": 14493, "loss": 0.2462, "lr": 4.0798997858363557e-05, "epoch": 1.039129422116405, "percentage": 34.64, "elapsed_time": "8:43:52", "remaining_time": "16:28:34", "throughput": 57055.65, "total_tokens": 1793398400} |
| {"current_steps": 5030, "total_steps": 14493, "loss": 0.2458, "lr": 4.078542217574024e-05, "epoch": 1.0411997619109237, "percentage": 34.71, "elapsed_time": "8:45:35", "remaining_time": "16:28:47", "throughput": 56985.93, "total_tokens": 1797072000} |
| {"current_steps": 5040, "total_steps": 14493, "loss": 0.2505, "lr": 4.0771860035846196e-05, "epoch": 1.0432701017054424, "percentage": 34.78, "elapsed_time": "8:47:12", "remaining_time": "16:28:49", "throughput": 56921.86, "total_tokens": 1800560640} |
| {"current_steps": 5050, "total_steps": 14493, "loss": 0.2471, "lr": 4.0758311416179965e-05, "epoch": 1.0453404414999612, "percentage": 34.84, "elapsed_time": "8:49:04", "remaining_time": "16:29:18", "throughput": 56833.87, "total_tokens": 1804138112} |
| {"current_steps": 5060, "total_steps": 14493, "loss": 0.2477, "lr": 4.0744776294292386e-05, "epoch": 1.04741078129448, "percentage": 34.91, "elapsed_time": "8:50:45", "remaining_time": "16:29:27", "throughput": 56765.07, "total_tokens": 1807718656} |
| {"current_steps": 5070, "total_steps": 14493, "loss": 0.2464, "lr": 4.073125464778646e-05, "epoch": 1.0494811210889987, "percentage": 34.98, "elapsed_time": "8:51:55", "remaining_time": "16:28:36", "throughput": 56751.81, "total_tokens": 1811239296} |
| {"current_steps": 5080, "total_steps": 14493, "loss": 0.2493, "lr": 4.071774645431717e-05, "epoch": 1.0515514608835175, "percentage": 35.05, "elapsed_time": "8:52:59", "remaining_time": "16:27:36", "throughput": 56747.59, "total_tokens": 1814749952} |
| {"current_steps": 5090, "total_steps": 14493, "loss": 0.2491, "lr": 4.070425169159135e-05, "epoch": 1.0536218006780362, "percentage": 35.12, "elapsed_time": "8:53:56", "remaining_time": "16:26:23", "throughput": 56757.0, "total_tokens": 1818322944} |
| {"current_steps": 5100, "total_steps": 14493, "loss": 0.2446, "lr": 4.069077033736751e-05, "epoch": 1.055692140472555, "percentage": 35.19, "elapsed_time": "8:54:52", "remaining_time": "16:25:06", "throughput": 56771.48, "total_tokens": 1821935488} |
| {"current_steps": 5110, "total_steps": 14493, "loss": 0.2494, "lr": 4.06773023694557e-05, "epoch": 1.0577624802670738, "percentage": 35.26, "elapsed_time": "8:55:41", "remaining_time": "16:23:38", "throughput": 56793.27, "total_tokens": 1825431424} |
| {"current_steps": 5120, "total_steps": 14493, "loss": 0.2488, "lr": 4.066384776571732e-05, "epoch": 1.0598328200615925, "percentage": 35.33, "elapsed_time": "8:56:33", "remaining_time": "16:22:14", "throughput": 56811.75, "total_tokens": 1828952320} |
| {"current_steps": 5130, "total_steps": 14493, "loss": 0.246, "lr": 4.065040650406504e-05, "epoch": 1.0619031598561113, "percentage": 35.4, "elapsed_time": "8:57:23", "remaining_time": "16:20:49", "throughput": 56830.68, "total_tokens": 1832444544} |
| {"current_steps": 5140, "total_steps": 14493, "loss": 0.2478, "lr": 4.0636978562462576e-05, "epoch": 1.0639734996506303, "percentage": 35.47, "elapsed_time": "8:58:32", "remaining_time": "16:19:58", "throughput": 56821.55, "total_tokens": 1836072448} |
| {"current_steps": 5150, "total_steps": 14493, "loss": 0.2476, "lr": 4.062356391892456e-05, "epoch": 1.066043839445149, "percentage": 35.53, "elapsed_time": "8:59:59", "remaining_time": "16:19:37", "throughput": 56778.35, "total_tokens": 1839570176} |
| {"current_steps": 5160, "total_steps": 14493, "loss": 0.2471, "lr": 4.0610162551516395e-05, "epoch": 1.0681141792396678, "percentage": 35.6, "elapsed_time": "9:02:24", "remaining_time": "16:21:03", "throughput": 56633.06, "total_tokens": 1843072896} |
| {"current_steps": 5170, "total_steps": 14493, "loss": 0.2456, "lr": 4.059677443835412e-05, "epoch": 1.0701845190341865, "percentage": 35.67, "elapsed_time": "9:04:04", "remaining_time": "16:21:07", "throughput": 56568.64, "total_tokens": 1846659712} |
| {"current_steps": 5180, "total_steps": 14493, "loss": 0.2487, "lr": 4.058339955760423e-05, "epoch": 1.0722548588287053, "percentage": 35.74, "elapsed_time": "9:04:58", "remaining_time": "16:19:48", "throughput": 56586.82, "total_tokens": 1850309760} |
| {"current_steps": 5190, "total_steps": 14493, "loss": 0.249, "lr": 4.0570037887483535e-05, "epoch": 1.074325198623224, "percentage": 35.81, "elapsed_time": "9:05:54", "remaining_time": "16:18:32", "throughput": 56601.83, "total_tokens": 1853987840} |
| {"current_steps": 5200, "total_steps": 14493, "loss": 0.2492, "lr": 4.0556689406259025e-05, "epoch": 1.0763955384177428, "percentage": 35.88, "elapsed_time": "9:06:47", "remaining_time": "16:17:11", "throughput": 56618.53, "total_tokens": 1857522816} |
| {"current_steps": 5210, "total_steps": 14493, "loss": 0.2473, "lr": 4.054335409224771e-05, "epoch": 1.0784658782122616, "percentage": 35.95, "elapsed_time": "9:07:39", "remaining_time": "16:15:47", "throughput": 56639.18, "total_tokens": 1861137152} |
| {"current_steps": 5220, "total_steps": 14493, "loss": 0.2474, "lr": 4.053003192381646e-05, "epoch": 1.0805362180067803, "percentage": 36.02, "elapsed_time": "9:08:35", "remaining_time": "16:14:32", "throughput": 56654.79, "total_tokens": 1864816896} |
| {"current_steps": 5230, "total_steps": 14493, "loss": 0.2474, "lr": 4.051672287938189e-05, "epoch": 1.082606557801299, "percentage": 36.09, "elapsed_time": "9:09:31", "remaining_time": "16:13:15", "throughput": 56670.08, "total_tokens": 1868473088} |
| {"current_steps": 5240, "total_steps": 14493, "loss": 0.2481, "lr": 4.050342693741019e-05, "epoch": 1.0846768975958179, "percentage": 36.16, "elapsed_time": "9:10:24", "remaining_time": "16:11:55", "throughput": 56689.4, "total_tokens": 1872113408} |
| {"current_steps": 5250, "total_steps": 14493, "loss": 0.2467, "lr": 4.049014407641699e-05, "epoch": 1.0867472373903366, "percentage": 36.22, "elapsed_time": "9:11:26", "remaining_time": "16:10:51", "throughput": 56690.29, "total_tokens": 1875709824} |
| {"current_steps": 5260, "total_steps": 14493, "loss": 0.247, "lr": 4.047687427496717e-05, "epoch": 1.0888175771848554, "percentage": 36.29, "elapsed_time": "9:12:28", "remaining_time": "16:09:46", "throughput": 56696.28, "total_tokens": 1879393664} |
| {"current_steps": 5270, "total_steps": 14493, "loss": 0.248, "lr": 4.046361751167479e-05, "epoch": 1.0908879169793742, "percentage": 36.36, "elapsed_time": "9:13:28", "remaining_time": "16:08:38", "throughput": 56703.52, "total_tokens": 1883039488} |
| {"current_steps": 5280, "total_steps": 14493, "loss": 0.2469, "lr": 4.045037376520292e-05, "epoch": 1.0929582567738931, "percentage": 36.43, "elapsed_time": "9:14:21", "remaining_time": "16:07:18", "throughput": 56715.73, "total_tokens": 1886475520} |
| {"current_steps": 5290, "total_steps": 14493, "loss": 0.2485, "lr": 4.043714301426344e-05, "epoch": 1.095028596568412, "percentage": 36.5, "elapsed_time": "9:15:18", "remaining_time": "16:06:04", "throughput": 56726.14, "total_tokens": 1890044288} |
| {"current_steps": 5300, "total_steps": 14493, "loss": 0.2473, "lr": 4.042392523761696e-05, "epoch": 1.0970989363629307, "percentage": 36.57, "elapsed_time": "9:16:18", "remaining_time": "16:04:56", "throughput": 56734.11, "total_tokens": 1893721216} |
| {"current_steps": 5310, "total_steps": 14493, "loss": 0.2462, "lr": 4.041072041407267e-05, "epoch": 1.0991692761574494, "percentage": 36.64, "elapsed_time": "9:18:30", "remaining_time": "16:05:52", "throughput": 56617.32, "total_tokens": 1897285120} |
| {"current_steps": 5320, "total_steps": 14493, "loss": 0.2462, "lr": 4.039752852248815e-05, "epoch": 1.1012396159519682, "percentage": 36.71, "elapsed_time": "9:20:24", "remaining_time": "16:06:16", "throughput": 56533.71, "total_tokens": 1900905728} |
| {"current_steps": 5330, "total_steps": 14493, "loss": 0.2494, "lr": 4.0384349541769286e-05, "epoch": 1.103309955746487, "percentage": 36.78, "elapsed_time": "9:21:31", "remaining_time": "16:05:20", "throughput": 56529.23, "total_tokens": 1904568448} |
| {"current_steps": 5340, "total_steps": 14493, "loss": 0.2471, "lr": 4.037118345087011e-05, "epoch": 1.1053802955410057, "percentage": 36.85, "elapsed_time": "9:22:30", "remaining_time": "16:04:09", "throughput": 56539.71, "total_tokens": 1908217344} |
| {"current_steps": 5350, "total_steps": 14493, "loss": 0.2474, "lr": 4.0358030228792636e-05, "epoch": 1.1074506353355245, "percentage": 36.91, "elapsed_time": "9:23:26", "remaining_time": "16:02:55", "throughput": 56550.6, "total_tokens": 1911805568} |
| {"current_steps": 5360, "total_steps": 14493, "loss": 0.2477, "lr": 4.034488985458673e-05, "epoch": 1.1095209751300432, "percentage": 36.98, "elapsed_time": "9:24:24", "remaining_time": "16:01:42", "throughput": 56561.14, "total_tokens": 1915404544} |
| {"current_steps": 5370, "total_steps": 14493, "loss": 0.2486, "lr": 4.033176230735001e-05, "epoch": 1.111591314924562, "percentage": 37.05, "elapsed_time": "9:25:42", "remaining_time": "16:01:04", "throughput": 56532.44, "total_tokens": 1918870400} |
| {"current_steps": 5380, "total_steps": 14493, "loss": 0.2475, "lr": 4.0318647566227626e-05, "epoch": 1.1136616547190807, "percentage": 37.12, "elapsed_time": "9:27:07", "remaining_time": "16:00:37", "throughput": 56497.43, "total_tokens": 1922461440} |
| {"current_steps": 5390, "total_steps": 14493, "loss": 0.2483, "lr": 4.0305545610412205e-05, "epoch": 1.1157319945135995, "percentage": 37.19, "elapsed_time": "9:29:44", "remaining_time": "16:02:12", "throughput": 56344.45, "total_tokens": 1926087424} |
| {"current_steps": 5400, "total_steps": 14493, "loss": 0.2474, "lr": 4.029245641914365e-05, "epoch": 1.1178023343081183, "percentage": 37.26, "elapsed_time": "9:31:52", "remaining_time": "16:02:58", "throughput": 56239.77, "total_tokens": 1929720064} |
| {"current_steps": 5410, "total_steps": 14493, "loss": 0.2461, "lr": 4.027937997170904e-05, "epoch": 1.119872674102637, "percentage": 37.33, "elapsed_time": "9:33:05", "remaining_time": "16:02:10", "throughput": 56222.54, "total_tokens": 1933237120} |
| {"current_steps": 5420, "total_steps": 14493, "loss": 0.2473, "lr": 4.026631624744247e-05, "epoch": 1.1219430138971558, "percentage": 37.4, "elapsed_time": "9:34:06", "remaining_time": "16:01:02", "throughput": 56226.97, "total_tokens": 1936820352} |
| {"current_steps": 5430, "total_steps": 14493, "loss": 0.2465, "lr": 4.025326522572493e-05, "epoch": 1.1240133536916745, "percentage": 37.47, "elapsed_time": "9:35:22", "remaining_time": "16:00:20", "throughput": 56207.91, "total_tokens": 1940437760} |
| {"current_steps": 5440, "total_steps": 14493, "loss": 0.2474, "lr": 4.024022688598415e-05, "epoch": 1.1260836934861933, "percentage": 37.54, "elapsed_time": "9:36:20", "remaining_time": "15:59:07", "throughput": 56220.17, "total_tokens": 1944131584} |
| {"current_steps": 5450, "total_steps": 14493, "loss": 0.2464, "lr": 4.0227201207694494e-05, "epoch": 1.1281540332807123, "percentage": 37.6, "elapsed_time": "9:37:17", "remaining_time": "15:57:52", "throughput": 56232.91, "total_tokens": 1947748224} |
| {"current_steps": 5460, "total_steps": 14493, "loss": 0.2503, "lr": 4.021418817037677e-05, "epoch": 1.130224373075231, "percentage": 37.67, "elapsed_time": "9:38:19", "remaining_time": "15:56:46", "throughput": 56235.97, "total_tokens": 1951345920} |
| {"current_steps": 5470, "total_steps": 14493, "loss": 0.2463, "lr": 4.0201187753598174e-05, "epoch": 1.1322947128697498, "percentage": 37.74, "elapsed_time": "9:39:18", "remaining_time": "15:55:35", "throughput": 56242.74, "total_tokens": 1954894208} |
| {"current_steps": 5480, "total_steps": 14493, "loss": 0.2489, "lr": 4.018819993697208e-05, "epoch": 1.1343650526642686, "percentage": 37.81, "elapsed_time": "9:40:17", "remaining_time": "15:54:24", "throughput": 56250.33, "total_tokens": 1958508416} |
| {"current_steps": 5490, "total_steps": 14493, "loss": 0.2465, "lr": 4.017522470015793e-05, "epoch": 1.1364353924587873, "percentage": 37.88, "elapsed_time": "9:41:14", "remaining_time": "15:53:10", "throughput": 56259.97, "total_tokens": 1962052992} |
| {"current_steps": 5500, "total_steps": 14493, "loss": 0.247, "lr": 4.0162262022861144e-05, "epoch": 1.138505732253306, "percentage": 37.95, "elapsed_time": "9:42:11", "remaining_time": "15:51:55", "throughput": 56272.88, "total_tokens": 1965682944} |
| {"current_steps": 5510, "total_steps": 14493, "loss": 0.2472, "lr": 4.0149311884832906e-05, "epoch": 1.1405760720478249, "percentage": 38.02, "elapsed_time": "9:43:07", "remaining_time": "15:50:39", "throughput": 56285.3, "total_tokens": 1969265536} |
| {"current_steps": 5520, "total_steps": 14493, "loss": 0.2488, "lr": 4.0136374265870116e-05, "epoch": 1.1426464118423436, "percentage": 38.09, "elapsed_time": "9:44:04", "remaining_time": "15:49:26", "throughput": 56295.51, "total_tokens": 1972857984} |
| {"current_steps": 5530, "total_steps": 14493, "loss": 0.2484, "lr": 4.0123449145815174e-05, "epoch": 1.1447167516368624, "percentage": 38.16, "elapsed_time": "9:45:00", "remaining_time": "15:48:11", "throughput": 56306.74, "total_tokens": 1976408832} |
| {"current_steps": 5540, "total_steps": 14493, "loss": 0.2476, "lr": 4.011053650455592e-05, "epoch": 1.1467870914313811, "percentage": 38.23, "elapsed_time": "9:45:58", "remaining_time": "15:46:58", "throughput": 56315.17, "total_tokens": 1979956224} |
| {"current_steps": 5550, "total_steps": 14493, "loss": 0.2491, "lr": 4.0097636322025466e-05, "epoch": 1.1488574312259, "percentage": 38.29, "elapsed_time": "9:46:53", "remaining_time": "15:45:42", "throughput": 56328.82, "total_tokens": 1983561728} |
| {"current_steps": 5560, "total_steps": 14493, "loss": 0.247, "lr": 4.008474857820206e-05, "epoch": 1.1509277710204187, "percentage": 38.36, "elapsed_time": "9:47:49", "remaining_time": "15:44:26", "throughput": 56342.61, "total_tokens": 1987190656} |
| {"current_steps": 5570, "total_steps": 14493, "loss": 0.2472, "lr": 4.007187325310899e-05, "epoch": 1.1529981108149374, "percentage": 38.43, "elapsed_time": "9:48:45", "remaining_time": "15:43:09", "throughput": 56354.54, "total_tokens": 1990730624} |
| {"current_steps": 5580, "total_steps": 14493, "loss": 0.2466, "lr": 4.00590103268144e-05, "epoch": 1.1550684506094564, "percentage": 38.5, "elapsed_time": "9:49:37", "remaining_time": "15:41:49", "throughput": 56370.99, "total_tokens": 1994279936} |
| {"current_steps": 5590, "total_steps": 14493, "loss": 0.2458, "lr": 4.004615977943124e-05, "epoch": 1.157138790403975, "percentage": 38.57, "elapsed_time": "9:50:30", "remaining_time": "15:40:29", "throughput": 56388.83, "total_tokens": 1997890944} |
| {"current_steps": 5600, "total_steps": 14493, "loss": 0.2493, "lr": 4.0033321591117025e-05, "epoch": 1.159209130198494, "percentage": 38.64, "elapsed_time": "9:51:23", "remaining_time": "15:39:09", "throughput": 56404.95, "total_tokens": 2001446656} |
| {"current_steps": 5610, "total_steps": 14493, "loss": 0.2474, "lr": 4.002049574207381e-05, "epoch": 1.1612794699930127, "percentage": 38.71, "elapsed_time": "9:52:26", "remaining_time": "15:38:04", "throughput": 56409.64, "total_tokens": 2005145344} |
| {"current_steps": 5620, "total_steps": 14493, "loss": 0.2482, "lr": 4.000768221254803e-05, "epoch": 1.1633498097875314, "percentage": 38.78, "elapsed_time": "9:53:30", "remaining_time": "15:37:02", "throughput": 56407.96, "total_tokens": 2008710272} |
| {"current_steps": 5630, "total_steps": 14493, "loss": 0.2451, "lr": 3.999488098283034e-05, "epoch": 1.1654201495820502, "percentage": 38.85, "elapsed_time": "9:54:48", "remaining_time": "15:36:23", "throughput": 56384.59, "total_tokens": 2012307968} |
| {"current_steps": 5640, "total_steps": 14493, "loss": 0.2471, "lr": 3.9982092033255506e-05, "epoch": 1.167490489376569, "percentage": 38.92, "elapsed_time": "9:56:45", "remaining_time": "15:36:43", "throughput": 56300.07, "total_tokens": 2015878912} |
| {"current_steps": 5650, "total_steps": 14493, "loss": 0.2455, "lr": 3.996931534420232e-05, "epoch": 1.1695608291710877, "percentage": 38.98, "elapsed_time": "9:58:21", "remaining_time": "15:36:30", "throughput": 56250.1, "total_tokens": 2019451136} |
| {"current_steps": 5660, "total_steps": 14493, "loss": 0.2463, "lr": 3.995655089609339e-05, "epoch": 1.1716311689656065, "percentage": 39.05, "elapsed_time": "9:59:15", "remaining_time": "15:35:12", "throughput": 56263.92, "total_tokens": 2023020288} |
| {"current_steps": 5670, "total_steps": 14493, "loss": 0.2471, "lr": 3.994379866939511e-05, "epoch": 1.1737015087601252, "percentage": 39.12, "elapsed_time": "10:00:08", "remaining_time": "15:33:53", "throughput": 56279.18, "total_tokens": 2026556288} |
| {"current_steps": 5680, "total_steps": 14493, "loss": 0.2476, "lr": 3.993105864461745e-05, "epoch": 1.175771848554644, "percentage": 39.19, "elapsed_time": "10:01:00", "remaining_time": "15:32:30", "throughput": 56296.89, "total_tokens": 2030087424} |
| {"current_steps": 5690, "total_steps": 14493, "loss": 0.2469, "lr": 3.9918330802313866e-05, "epoch": 1.1778421883491628, "percentage": 39.26, "elapsed_time": "10:01:56", "remaining_time": "15:31:15", "throughput": 56311.48, "total_tokens": 2033778048} |
| {"current_steps": 5700, "total_steps": 14493, "loss": 0.2483, "lr": 3.9905615123081206e-05, "epoch": 1.1799125281436815, "percentage": 39.33, "elapsed_time": "10:02:49", "remaining_time": "15:29:55", "throughput": 56327.02, "total_tokens": 2037302784} |
| {"current_steps": 5710, "total_steps": 14493, "loss": 0.2504, "lr": 3.989291158755953e-05, "epoch": 1.1819828679382003, "percentage": 39.4, "elapsed_time": "10:03:41", "remaining_time": "15:28:35", "throughput": 56342.29, "total_tokens": 2040823296} |
| {"current_steps": 5720, "total_steps": 14493, "loss": 0.2483, "lr": 3.988022017643201e-05, "epoch": 1.184053207732719, "percentage": 39.47, "elapsed_time": "10:04:34", "remaining_time": "15:27:15", "throughput": 56359.53, "total_tokens": 2044410496} |
| {"current_steps": 5730, "total_steps": 14493, "loss": 0.243, "lr": 3.9867540870424826e-05, "epoch": 1.186123547527238, "percentage": 39.54, "elapsed_time": "10:05:31", "remaining_time": "15:26:02", "throughput": 56371.49, "total_tokens": 2048070144} |
| {"current_steps": 5740, "total_steps": 14493, "loss": 0.2484, "lr": 3.985487365030702e-05, "epoch": 1.1881938873217566, "percentage": 39.61, "elapsed_time": "10:06:24", "remaining_time": "15:24:43", "throughput": 56388.04, "total_tokens": 2051650944} |
| {"current_steps": 5750, "total_steps": 14493, "loss": 0.2474, "lr": 3.984221849689036e-05, "epoch": 1.1902642271162756, "percentage": 39.67, "elapsed_time": "10:07:16", "remaining_time": "15:23:22", "throughput": 56403.96, "total_tokens": 2055165696} |
| {"current_steps": 5760, "total_steps": 14493, "loss": 0.2468, "lr": 3.982957539102927e-05, "epoch": 1.1923345669107943, "percentage": 39.74, "elapsed_time": "10:08:14", "remaining_time": "15:22:10", "throughput": 56418.0, "total_tokens": 2058944256} |
| {"current_steps": 5770, "total_steps": 14493, "loss": 0.2463, "lr": 3.981694431362065e-05, "epoch": 1.194404906705313, "percentage": 39.81, "elapsed_time": "10:09:09", "remaining_time": "15:20:54", "throughput": 56433.08, "total_tokens": 2062574080} |
| {"current_steps": 5780, "total_steps": 14493, "loss": 0.2471, "lr": 3.9804325245603786e-05, "epoch": 1.1964752464998318, "percentage": 39.88, "elapsed_time": "10:09:59", "remaining_time": "15:19:31", "throughput": 56451.51, "total_tokens": 2066080640} |
| {"current_steps": 5790, "total_steps": 14493, "loss": 0.2452, "lr": 3.9791718167960226e-05, "epoch": 1.1985455862943506, "percentage": 39.95, "elapsed_time": "10:10:53", "remaining_time": "15:18:14", "throughput": 56465.79, "total_tokens": 2069667328} |
| {"current_steps": 5800, "total_steps": 14493, "loss": 0.2449, "lr": 3.9779123061713665e-05, "epoch": 1.2006159260888694, "percentage": 40.02, "elapsed_time": "10:11:46", "remaining_time": "15:16:55", "throughput": 56478.92, "total_tokens": 2073160448} |
| {"current_steps": 5810, "total_steps": 14493, "loss": 0.2486, "lr": 3.976653990792979e-05, "epoch": 1.2026862658833881, "percentage": 40.09, "elapsed_time": "10:12:39", "remaining_time": "15:15:36", "throughput": 56495.86, "total_tokens": 2076758144} |
| {"current_steps": 5820, "total_steps": 14493, "loss": 0.2434, "lr": 3.9753968687716206e-05, "epoch": 1.2047566056779069, "percentage": 40.16, "elapsed_time": "10:13:33", "remaining_time": "15:14:19", "throughput": 56511.94, "total_tokens": 2080397312} |
| {"current_steps": 5830, "total_steps": 14493, "loss": 0.2452, "lr": 3.974140938222232e-05, "epoch": 1.2068269454724256, "percentage": 40.23, "elapsed_time": "10:14:27", "remaining_time": "15:13:02", "throughput": 56527.7, "total_tokens": 2084019328} |
| {"current_steps": 5840, "total_steps": 14493, "loss": 0.2462, "lr": 3.972886197263915e-05, "epoch": 1.2088972852669444, "percentage": 40.3, "elapsed_time": "10:15:19", "remaining_time": "15:11:43", "throughput": 56543.7, "total_tokens": 2087588224} |
| {"current_steps": 5850, "total_steps": 14493, "loss": 0.246, "lr": 3.97163264401993e-05, "epoch": 1.2109676250614632, "percentage": 40.36, "elapsed_time": "10:16:13", "remaining_time": "15:10:25", "throughput": 56560.61, "total_tokens": 2091242496} |
| {"current_steps": 5860, "total_steps": 14493, "loss": 0.2477, "lr": 3.970380276617677e-05, "epoch": 1.213037964855982, "percentage": 40.43, "elapsed_time": "10:17:07", "remaining_time": "15:09:09", "throughput": 56575.05, "total_tokens": 2094847104} |
| {"current_steps": 5870, "total_steps": 14493, "loss": 0.245, "lr": 3.96912909318869e-05, "epoch": 1.2151083046505007, "percentage": 40.5, "elapsed_time": "10:18:04", "remaining_time": "15:07:57", "throughput": 56586.85, "total_tokens": 2098497280} |
| {"current_steps": 5880, "total_steps": 14493, "loss": 0.2487, "lr": 3.96787909186862e-05, "epoch": 1.2171786444450194, "percentage": 40.57, "elapsed_time": "10:19:11", "remaining_time": "15:06:59", "throughput": 56580.46, "total_tokens": 2102071808} |
| {"current_steps": 5890, "total_steps": 14493, "loss": 0.2455, "lr": 3.9666302707972244e-05, "epoch": 1.2192489842395382, "percentage": 40.64, "elapsed_time": "10:20:35", "remaining_time": "15:06:27", "throughput": 56550.23, "total_tokens": 2105694976} |
| {"current_steps": 5900, "total_steps": 14493, "loss": 0.2455, "lr": 3.965382628118358e-05, "epoch": 1.2213193240340572, "percentage": 40.71, "elapsed_time": "10:22:58", "remaining_time": "15:07:20", "throughput": 56428.59, "total_tokens": 2109240576} |
| {"current_steps": 5910, "total_steps": 14493, "loss": 0.2465, "lr": 3.964136161979959e-05, "epoch": 1.223389663828576, "percentage": 40.78, "elapsed_time": "10:25:45", "remaining_time": "15:08:46", "throughput": 56274.74, "total_tokens": 2112851328} |
| {"current_steps": 5920, "total_steps": 14493, "loss": 0.2512, "lr": 3.9628908705340406e-05, "epoch": 1.2254600036230947, "percentage": 40.85, "elapsed_time": "10:27:46", "remaining_time": "15:09:06", "throughput": 56187.75, "total_tokens": 2116386560} |
| {"current_steps": 5930, "total_steps": 14493, "loss": 0.2458, "lr": 3.961646751936673e-05, "epoch": 1.2275303434176135, "percentage": 40.92, "elapsed_time": "10:29:30", "remaining_time": "15:09:00", "throughput": 56127.61, "total_tokens": 2119949952} |
| {"current_steps": 5940, "total_steps": 14493, "loss": 0.2458, "lr": 3.960403804347979e-05, "epoch": 1.2296006832121322, "percentage": 40.99, "elapsed_time": "10:30:58", "remaining_time": "15:08:32", "throughput": 56090.26, "total_tokens": 2123511936} |
| {"current_steps": 5950, "total_steps": 14493, "loss": 0.2468, "lr": 3.959162025932119e-05, "epoch": 1.231671023006651, "percentage": 41.05, "elapsed_time": "10:32:28", "remaining_time": "15:08:06", "throughput": 56051.72, "total_tokens": 2127088384} |
| {"current_steps": 5960, "total_steps": 14493, "loss": 0.2471, "lr": 3.95792141485728e-05, "epoch": 1.2337413628011697, "percentage": 41.12, "elapsed_time": "10:33:44", "remaining_time": "15:07:19", "throughput": 56032.89, "total_tokens": 2130615040} |
| {"current_steps": 5970, "total_steps": 14493, "loss": 0.2484, "lr": 3.956681969295664e-05, "epoch": 1.2358117025956885, "percentage": 41.19, "elapsed_time": "10:35:11", "remaining_time": "15:06:50", "throughput": 55997.82, "total_tokens": 2134187904} |
| {"current_steps": 5980, "total_steps": 14493, "loss": 0.2477, "lr": 3.955443687423479e-05, "epoch": 1.2378820423902073, "percentage": 41.26, "elapsed_time": "10:36:28", "remaining_time": "15:06:04", "throughput": 55977.14, "total_tokens": 2137700608} |
| {"current_steps": 5990, "total_steps": 14493, "loss": 0.2462, "lr": 3.954206567420924e-05, "epoch": 1.239952382184726, "percentage": 41.33, "elapsed_time": "10:37:53", "remaining_time": "15:05:30", "throughput": 55946.22, "total_tokens": 2141240576} |
| {"current_steps": 6000, "total_steps": 14493, "loss": 0.2471, "lr": 3.952970607472179e-05, "epoch": 1.2420227219792448, "percentage": 41.4, "elapsed_time": "10:39:18", "remaining_time": "15:04:56", "throughput": 55916.69, "total_tokens": 2144892160} |
| {"current_steps": 6010, "total_steps": 14493, "loss": 0.2477, "lr": 3.951735805765399e-05, "epoch": 1.2440930617737636, "percentage": 41.47, "elapsed_time": "10:40:30", "remaining_time": "15:04:04", "throughput": 55905.0, "total_tokens": 2148480640} |
| {"current_steps": 6020, "total_steps": 14493, "loss": 0.2481, "lr": 3.950502160492692e-05, "epoch": 1.2461634015682823, "percentage": 41.54, "elapsed_time": "10:41:26", "remaining_time": "15:02:48", "throughput": 55917.71, "total_tokens": 2152082688} |
| {"current_steps": 6030, "total_steps": 14493, "loss": 0.2472, "lr": 3.9492696698501205e-05, "epoch": 1.248233741362801, "percentage": 41.61, "elapsed_time": "10:42:19", "remaining_time": "15:01:29", "throughput": 55935.48, "total_tokens": 2155719168} |
| {"current_steps": 6040, "total_steps": 14493, "loss": 0.2441, "lr": 3.9480383320376784e-05, "epoch": 1.2503040811573198, "percentage": 41.68, "elapsed_time": "10:43:07", "remaining_time": "15:00:03", "throughput": 55956.79, "total_tokens": 2159248384} |
| {"current_steps": 6050, "total_steps": 14493, "loss": 0.2461, "lr": 3.94680814525929e-05, "epoch": 1.2523744209518388, "percentage": 41.74, "elapsed_time": "10:44:00", "remaining_time": "14:58:44", "throughput": 55973.31, "total_tokens": 2162855040} |
| {"current_steps": 6060, "total_steps": 14493, "loss": 0.2488, "lr": 3.945579107722792e-05, "epoch": 1.2544447607463576, "percentage": 41.81, "elapsed_time": "10:44:51", "remaining_time": "14:57:23", "throughput": 55991.24, "total_tokens": 2166411520} |
| {"current_steps": 6070, "total_steps": 14493, "loss": 0.2464, "lr": 3.9443512176399276e-05, "epoch": 1.2565151005408763, "percentage": 41.88, "elapsed_time": "10:45:45", "remaining_time": "14:56:05", "throughput": 56008.29, "total_tokens": 2170075264} |
| {"current_steps": 6080, "total_steps": 14493, "loss": 0.2454, "lr": 3.9431244732263307e-05, "epoch": 1.258585440335395, "percentage": 41.95, "elapsed_time": "10:46:34", "remaining_time": "14:54:40", "throughput": 56028.62, "total_tokens": 2173609472} |
| {"current_steps": 6090, "total_steps": 14493, "loss": 0.2505, "lr": 3.941898872701519e-05, "epoch": 1.2606557801299139, "percentage": 42.02, "elapsed_time": "10:47:25", "remaining_time": "14:53:19", "throughput": 56046.88, "total_tokens": 2177168256} |
| {"current_steps": 6100, "total_steps": 14493, "loss": 0.2471, "lr": 3.940674414288882e-05, "epoch": 1.2627261199244326, "percentage": 42.09, "elapsed_time": "10:48:26", "remaining_time": "14:52:12", "throughput": 56050.34, "total_tokens": 2180748288} |
| {"current_steps": 6110, "total_steps": 14493, "loss": 0.2449, "lr": 3.939451096215668e-05, "epoch": 1.2647964597189514, "percentage": 42.16, "elapsed_time": "10:49:20", "remaining_time": "14:50:53", "throughput": 56065.04, "total_tokens": 2184295680} |
| {"current_steps": 6120, "total_steps": 14493, "loss": 0.2468, "lr": 3.938228916712978e-05, "epoch": 1.2668667995134701, "percentage": 42.23, "elapsed_time": "10:50:31", "remaining_time": "14:50:01", "throughput": 56055.94, "total_tokens": 2187970688} |
| {"current_steps": 6130, "total_steps": 14493, "loss": 0.2452, "lr": 3.937007874015748e-05, "epoch": 1.268937139307989, "percentage": 42.3, "elapsed_time": "10:52:21", "remaining_time": "14:49:59", "throughput": 55991.66, "total_tokens": 2191573248} |
| {"current_steps": 6140, "total_steps": 14493, "loss": 0.2488, "lr": 3.935787966362748e-05, "epoch": 1.2710074791025077, "percentage": 42.37, "elapsed_time": "10:54:11", "remaining_time": "14:49:59", "throughput": 55925.51, "total_tokens": 2195178112} |
| {"current_steps": 6150, "total_steps": 14493, "loss": 0.2473, "lr": 3.9345691919965595e-05, "epoch": 1.2730778188970264, "percentage": 42.43, "elapsed_time": "10:55:24", "remaining_time": "14:49:06", "throughput": 55914.5, "total_tokens": 2198787840} |
| {"current_steps": 6160, "total_steps": 14493, "loss": 0.2453, "lr": 3.9333515491635764e-05, "epoch": 1.2751481586915452, "percentage": 42.5, "elapsed_time": "10:56:22", "remaining_time": "14:47:55", "throughput": 55921.97, "total_tokens": 2202349952} |
| {"current_steps": 6170, "total_steps": 14493, "loss": 0.2472, "lr": 3.932135036113987e-05, "epoch": 1.277218498486064, "percentage": 42.57, "elapsed_time": "10:57:13", "remaining_time": "14:46:33", "throughput": 55938.65, "total_tokens": 2205867008} |
| {"current_steps": 6180, "total_steps": 14493, "loss": 0.2486, "lr": 3.930919651101764e-05, "epoch": 1.279288838280583, "percentage": 42.64, "elapsed_time": "10:58:03", "remaining_time": "14:45:11", "throughput": 55957.1, "total_tokens": 2209390208} |
| {"current_steps": 6190, "total_steps": 14493, "loss": 0.2474, "lr": 3.9297053923846576e-05, "epoch": 1.2813591780751015, "percentage": 42.71, "elapsed_time": "10:59:00", "remaining_time": "14:43:57", "throughput": 55967.47, "total_tokens": 2212965376} |
| {"current_steps": 6200, "total_steps": 14493, "loss": 0.2503, "lr": 3.928492258224183e-05, "epoch": 1.2834295178696205, "percentage": 42.78, "elapsed_time": "11:00:00", "remaining_time": "14:42:48", "throughput": 55971.98, "total_tokens": 2216504192} |
| {"current_steps": 6210, "total_steps": 14493, "loss": 0.2456, "lr": 3.927280246885609e-05, "epoch": 1.285499857664139, "percentage": 42.85, "elapsed_time": "11:00:49", "remaining_time": "14:41:25", "throughput": 55990.13, "total_tokens": 2219997184} |
| {"current_steps": 6220, "total_steps": 14493, "loss": 0.2414, "lr": 3.9260693566379486e-05, "epoch": 1.287570197458658, "percentage": 42.92, "elapsed_time": "11:01:40", "remaining_time": "14:40:04", "throughput": 56010.03, "total_tokens": 2223617280} |
| {"current_steps": 6230, "total_steps": 14493, "loss": 0.2475, "lr": 3.924859585753948e-05, "epoch": 1.2896405372531767, "percentage": 42.99, "elapsed_time": "11:02:33", "remaining_time": "14:38:45", "throughput": 56025.36, "total_tokens": 2227188992} |
| {"current_steps": 6240, "total_steps": 14493, "loss": 0.2465, "lr": 3.923650932510079e-05, "epoch": 1.2917108770476955, "percentage": 43.06, "elapsed_time": "11:03:22", "remaining_time": "14:37:22", "throughput": 56045.06, "total_tokens": 2230740992} |
| {"current_steps": 6250, "total_steps": 14493, "loss": 0.245, "lr": 3.9224433951865215e-05, "epoch": 1.2937812168422143, "percentage": 43.12, "elapsed_time": "11:04:12", "remaining_time": "14:36:00", "throughput": 56063.49, "total_tokens": 2234242304} |
| {"current_steps": 6260, "total_steps": 14493, "loss": 0.2458, "lr": 3.921236972067165e-05, "epoch": 1.295851556636733, "percentage": 43.19, "elapsed_time": "11:05:04", "remaining_time": "14:34:40", "throughput": 56078.18, "total_tokens": 2237749248} |
| {"current_steps": 6270, "total_steps": 14493, "loss": 0.246, "lr": 3.920031661439585e-05, "epoch": 1.2979218964312518, "percentage": 43.26, "elapsed_time": "11:05:54", "remaining_time": "14:33:19", "throughput": 56095.06, "total_tokens": 2241259520} |
| {"current_steps": 6280, "total_steps": 14493, "loss": 0.2468, "lr": 3.918827461595045e-05, "epoch": 1.2999922362257705, "percentage": 43.33, "elapsed_time": "11:06:47", "remaining_time": "14:32:01", "throughput": 56111.54, "total_tokens": 2244876928} |
| {"current_steps": 6290, "total_steps": 14493, "loss": 0.2462, "lr": 3.9176243708284746e-05, "epoch": 1.3020625760202893, "percentage": 43.4, "elapsed_time": "11:07:35", "remaining_time": "14:30:38", "throughput": 56131.27, "total_tokens": 2248378880} |
| {"current_steps": 6300, "total_steps": 14493, "loss": 0.246, "lr": 3.9164223874384715e-05, "epoch": 1.304132915814808, "percentage": 43.47, "elapsed_time": "11:08:26", "remaining_time": "14:29:17", "throughput": 56149.26, "total_tokens": 2251934592} |
| {"current_steps": 6310, "total_steps": 14493, "loss": 0.2449, "lr": 3.91522150972728e-05, "epoch": 1.3062032556093268, "percentage": 43.54, "elapsed_time": "11:09:14", "remaining_time": "14:27:53", "throughput": 56169.53, "total_tokens": 2255441408} |
| {"current_steps": 6320, "total_steps": 14493, "loss": 0.2451, "lr": 3.9140217360007896e-05, "epoch": 1.3082735954038456, "percentage": 43.61, "elapsed_time": "11:10:02", "remaining_time": "14:26:29", "throughput": 56191.01, "total_tokens": 2259027584} |
| {"current_steps": 6330, "total_steps": 14493, "loss": 0.2463, "lr": 3.912823064568521e-05, "epoch": 1.3103439351983646, "percentage": 43.68, "elapsed_time": "11:10:53", "remaining_time": "14:25:09", "throughput": 56208.74, "total_tokens": 2262581120} |
| {"current_steps": 6340, "total_steps": 14493, "loss": 0.246, "lr": 3.9116254937436155e-05, "epoch": 1.312414274992883, "percentage": 43.75, "elapsed_time": "11:11:41", "remaining_time": "14:23:46", "throughput": 56229.64, "total_tokens": 2266147968} |
| {"current_steps": 6350, "total_steps": 14493, "loss": 0.2482, "lr": 3.910429021842825e-05, "epoch": 1.314484614787402, "percentage": 43.81, "elapsed_time": "11:12:31", "remaining_time": "14:22:25", "throughput": 56248.18, "total_tokens": 2269719040} |
| {"current_steps": 6360, "total_steps": 14493, "loss": 0.2464, "lr": 3.9092336471865084e-05, "epoch": 1.3165549545819206, "percentage": 43.88, "elapsed_time": "11:13:23", "remaining_time": "14:21:06", "throughput": 56264.15, "total_tokens": 2273262080} |
| {"current_steps": 6370, "total_steps": 14493, "loss": 0.2478, "lr": 3.908039368098611e-05, "epoch": 1.3186252943764396, "percentage": 43.95, "elapsed_time": "11:14:13", "remaining_time": "14:19:46", "throughput": 56282.18, "total_tokens": 2276835840} |
| {"current_steps": 6380, "total_steps": 14493, "loss": 0.2467, "lr": 3.9068461829066633e-05, "epoch": 1.3206956341709584, "percentage": 44.02, "elapsed_time": "11:15:04", "remaining_time": "14:18:27", "throughput": 56300.31, "total_tokens": 2280434048} |
| {"current_steps": 6390, "total_steps": 14493, "loss": 0.2451, "lr": 3.9056540899417656e-05, "epoch": 1.3227659739654771, "percentage": 44.09, "elapsed_time": "11:15:58", "remaining_time": "14:17:10", "throughput": 56314.61, "total_tokens": 2284024320} |
| {"current_steps": 6400, "total_steps": 14493, "loss": 0.2459, "lr": 3.904463087538585e-05, "epoch": 1.3248363137599959, "percentage": 44.16, "elapsed_time": "11:16:50", "remaining_time": "14:15:53", "throughput": 56327.81, "total_tokens": 2287520384} |
| {"current_steps": 6410, "total_steps": 14493, "loss": 0.2462, "lr": 3.903273174035336e-05, "epoch": 1.3269066535545146, "percentage": 44.23, "elapsed_time": "11:17:52", "remaining_time": "14:14:47", "throughput": 56327.97, "total_tokens": 2290987136} |
| {"current_steps": 6420, "total_steps": 14493, "loss": 0.2454, "lr": 3.902084347773779e-05, "epoch": 1.3289769933490334, "percentage": 44.3, "elapsed_time": "11:19:03", "remaining_time": "14:13:54", "throughput": 56315.03, "total_tokens": 2294490752} |
| {"current_steps": 6430, "total_steps": 14493, "loss": 0.2456, "lr": 3.900896607099207e-05, "epoch": 1.3310473331435522, "percentage": 44.37, "elapsed_time": "11:20:17", "remaining_time": "14:13:03", "throughput": 56300.81, "total_tokens": 2298045952} |
| {"current_steps": 6440, "total_steps": 14493, "loss": 0.2485, "lr": 3.899709950360437e-05, "epoch": 1.333117672938071, "percentage": 44.44, "elapsed_time": "11:21:13", "remaining_time": "14:11:50", "throughput": 56310.0, "total_tokens": 2301581824} |
| {"current_steps": 6450, "total_steps": 14493, "loss": 0.2448, "lr": 3.8985243759097997e-05, "epoch": 1.3351880127325897, "percentage": 44.5, "elapsed_time": "11:22:05", "remaining_time": "14:10:33", "throughput": 56326.54, "total_tokens": 2305192960} |
| {"current_steps": 6460, "total_steps": 14493, "loss": 0.2467, "lr": 3.897339882103129e-05, "epoch": 1.3372583525271085, "percentage": 44.57, "elapsed_time": "11:22:59", "remaining_time": "14:09:17", "throughput": 56341.36, "total_tokens": 2308841600} |
| {"current_steps": 6470, "total_steps": 14493, "loss": 0.2454, "lr": 3.8961564672997544e-05, "epoch": 1.3393286923216272, "percentage": 44.64, "elapsed_time": "11:23:49", "remaining_time": "14:07:57", "throughput": 56359.01, "total_tokens": 2312361856} |
| {"current_steps": 6480, "total_steps": 14493, "loss": 0.2441, "lr": 3.8949741298624924e-05, "epoch": 1.3413990321161462, "percentage": 44.71, "elapsed_time": "11:24:39", "remaining_time": "14:06:38", "throughput": 56376.88, "total_tokens": 2315962112} |
| {"current_steps": 6490, "total_steps": 14493, "loss": 0.2456, "lr": 3.8937928681576305e-05, "epoch": 1.3434693719106647, "percentage": 44.78, "elapsed_time": "11:25:27", "remaining_time": "14:05:15", "throughput": 56396.73, "total_tokens": 2319478144} |
| {"current_steps": 6500, "total_steps": 14493, "loss": 0.2499, "lr": 3.8926126805549276e-05, "epoch": 1.3455397117051837, "percentage": 44.85, "elapsed_time": "11:26:20", "remaining_time": "14:03:59", "throughput": 56412.54, "total_tokens": 2323117440} |
| {"current_steps": 6510, "total_steps": 14493, "loss": 0.2451, "lr": 3.891433565427596e-05, "epoch": 1.3476100514997023, "percentage": 44.92, "elapsed_time": "11:27:12", "remaining_time": "14:02:41", "throughput": 56429.12, "total_tokens": 2326702208} |
| {"current_steps": 6520, "total_steps": 14493, "loss": 0.2469, "lr": 3.8902555211522964e-05, "epoch": 1.3496803912942212, "percentage": 44.99, "elapsed_time": "11:28:02", "remaining_time": "14:01:22", "throughput": 56445.9, "total_tokens": 2330223616} |
| {"current_steps": 6530, "total_steps": 14493, "loss": 0.2448, "lr": 3.889078546109127e-05, "epoch": 1.35175073108874, "percentage": 45.06, "elapsed_time": "11:28:53", "remaining_time": "14:00:04", "throughput": 56463.37, "total_tokens": 2333847808} |
| {"current_steps": 6540, "total_steps": 14493, "loss": 0.2456, "lr": 3.887902638681616e-05, "epoch": 1.3538210708832588, "percentage": 45.13, "elapsed_time": "11:29:47", "remaining_time": "13:58:49", "throughput": 56478.16, "total_tokens": 2337492864} |
| {"current_steps": 6550, "total_steps": 14493, "loss": 0.2438, "lr": 3.886727797256707e-05, "epoch": 1.3558914106777775, "percentage": 45.19, "elapsed_time": "11:30:36", "remaining_time": "13:57:28", "throughput": 56497.87, "total_tokens": 2341070464} |
| {"current_steps": 6560, "total_steps": 14493, "loss": 0.2454, "lr": 3.88555402022476e-05, "epoch": 1.3579617504722963, "percentage": 45.26, "elapsed_time": "11:31:27", "remaining_time": "13:56:10", "throughput": 56514.16, "total_tokens": 2344626944} |
| {"current_steps": 6570, "total_steps": 14493, "loss": 0.2459, "lr": 3.884381305979528e-05, "epoch": 1.360032090266815, "percentage": 45.33, "elapsed_time": "11:32:18", "remaining_time": "13:54:52", "throughput": 56530.19, "total_tokens": 2348162560} |
| {"current_steps": 6580, "total_steps": 14493, "loss": 0.2462, "lr": 3.883209652918163e-05, "epoch": 1.3621024300613338, "percentage": 45.4, "elapsed_time": "11:33:08", "remaining_time": "13:53:33", "throughput": 56548.6, "total_tokens": 2351750912} |
| {"current_steps": 6590, "total_steps": 14493, "loss": 0.2429, "lr": 3.8820390594411935e-05, "epoch": 1.3641727698558526, "percentage": 45.47, "elapsed_time": "11:33:57", "remaining_time": "13:52:13", "throughput": 56568.79, "total_tokens": 2355377664} |
| {"current_steps": 6600, "total_steps": 14493, "loss": 0.2477, "lr": 3.880869523952524e-05, "epoch": 1.3662431096503713, "percentage": 45.54, "elapsed_time": "11:34:50", "remaining_time": "13:50:58", "throughput": 56584.26, "total_tokens": 2359026432} |
| {"current_steps": 6610, "total_steps": 14493, "loss": 0.2487, "lr": 3.879701044859422e-05, "epoch": 1.36831344944489, "percentage": 45.61, "elapsed_time": "11:35:42", "remaining_time": "13:49:42", "throughput": 56599.68, "total_tokens": 2362635392} |
| {"current_steps": 6620, "total_steps": 14493, "loss": 0.2443, "lr": 3.87853362057251e-05, "epoch": 1.3703837892394088, "percentage": 45.68, "elapsed_time": "11:36:38", "remaining_time": "13:48:29", "throughput": 56611.84, "total_tokens": 2366280576} |
| {"current_steps": 6630, "total_steps": 14493, "loss": 0.2459, "lr": 3.8773672495057576e-05, "epoch": 1.3724541290339278, "percentage": 45.75, "elapsed_time": "11:37:33", "remaining_time": "13:47:16", "throughput": 56621.26, "total_tokens": 2369785728} |
| {"current_steps": 6640, "total_steps": 14493, "loss": 0.2447, "lr": 3.8762019300764674e-05, "epoch": 1.3745244688284464, "percentage": 45.82, "elapsed_time": "11:38:29", "remaining_time": "13:46:05", "throughput": 56630.38, "total_tokens": 2373359872} |
| {"current_steps": 6650, "total_steps": 14493, "loss": 0.243, "lr": 3.875037660705273e-05, "epoch": 1.3765948086229653, "percentage": 45.88, "elapsed_time": "11:39:21", "remaining_time": "13:44:49", "throughput": 56646.55, "total_tokens": 2376976512} |
| {"current_steps": 6660, "total_steps": 14493, "loss": 0.245, "lr": 3.873874439816127e-05, "epoch": 1.3786651484174839, "percentage": 45.95, "elapsed_time": "11:40:09", "remaining_time": "13:43:28", "throughput": 56665.76, "total_tokens": 2380516096} |
| {"current_steps": 6670, "total_steps": 14493, "loss": 0.2444, "lr": 3.872712265836289e-05, "epoch": 1.3807354882120029, "percentage": 46.02, "elapsed_time": "11:40:59", "remaining_time": "13:42:10", "throughput": 56682.45, "total_tokens": 2384044928} |
| {"current_steps": 6680, "total_steps": 14493, "loss": 0.2457, "lr": 3.8715511371963225e-05, "epoch": 1.3828058280065216, "percentage": 46.09, "elapsed_time": "11:41:50", "remaining_time": "13:40:52", "throughput": 56699.39, "total_tokens": 2387612032} |
| {"current_steps": 6690, "total_steps": 14493, "loss": 0.2446, "lr": 3.87039105233008e-05, "epoch": 1.3848761678010404, "percentage": 46.16, "elapsed_time": "11:42:48", "remaining_time": "13:39:43", "throughput": 56704.8, "total_tokens": 2391144576} |
| {"current_steps": 6700, "total_steps": 14493, "loss": 0.2454, "lr": 3.8692320096746975e-05, "epoch": 1.3869465075955592, "percentage": 46.23, "elapsed_time": "11:43:41", "remaining_time": "13:38:28", "throughput": 56719.41, "total_tokens": 2394753536} |
| {"current_steps": 6710, "total_steps": 14493, "loss": 0.2473, "lr": 3.868074007670589e-05, "epoch": 1.389016847390078, "percentage": 46.3, "elapsed_time": "11:44:47", "remaining_time": "13:37:29", "throughput": 56715.76, "total_tokens": 2398357248} |
| {"current_steps": 6720, "total_steps": 14493, "loss": 0.2453, "lr": 3.866917044761428e-05, "epoch": 1.3910871871845967, "percentage": 46.37, "elapsed_time": "11:45:57", "remaining_time": "13:36:34", "throughput": 56707.49, "total_tokens": 2401979776} |
| {"current_steps": 6730, "total_steps": 14493, "loss": 0.248, "lr": 3.8657611193941486e-05, "epoch": 1.3931575269791154, "percentage": 46.44, "elapsed_time": "11:46:58", "remaining_time": "13:35:29", "throughput": 56709.95, "total_tokens": 2405555328} |
| {"current_steps": 6740, "total_steps": 14493, "loss": 0.2448, "lr": 3.8646062300189315e-05, "epoch": 1.3952278667736342, "percentage": 46.51, "elapsed_time": "11:47:51", "remaining_time": "13:34:14", "throughput": 56724.4, "total_tokens": 2409142912} |
| {"current_steps": 6750, "total_steps": 14493, "loss": 0.2437, "lr": 3.8634523750891984e-05, "epoch": 1.397298206568153, "percentage": 46.57, "elapsed_time": "11:48:42", "remaining_time": "13:32:58", "throughput": 56741.59, "total_tokens": 2412794368} |
| {"current_steps": 6760, "total_steps": 14493, "loss": 0.2441, "lr": 3.862299553061597e-05, "epoch": 1.3993685463626717, "percentage": 46.64, "elapsed_time": "11:49:32", "remaining_time": "13:31:39", "throughput": 56759.32, "total_tokens": 2416374144} |
| {"current_steps": 6770, "total_steps": 14493, "loss": 0.2423, "lr": 3.861147762396e-05, "epoch": 1.4014388861571905, "percentage": 46.71, "elapsed_time": "11:50:23", "remaining_time": "13:30:23", "throughput": 56776.33, "total_tokens": 2419987072} |
| {"current_steps": 6780, "total_steps": 14493, "loss": 0.2436, "lr": 3.859997001555494e-05, "epoch": 1.4035092259517095, "percentage": 46.78, "elapsed_time": "11:51:15", "remaining_time": "13:29:07", "throughput": 56791.08, "total_tokens": 2423563008} |
| {"current_steps": 6790, "total_steps": 14493, "loss": 0.2448, "lr": 3.8588472690063676e-05, "epoch": 1.405579565746228, "percentage": 46.85, "elapsed_time": "11:52:03", "remaining_time": "13:27:48", "throughput": 56808.88, "total_tokens": 2427079296} |
| {"current_steps": 6800, "total_steps": 14493, "loss": 0.2477, "lr": 3.857698563218106e-05, "epoch": 1.407649905540747, "percentage": 46.92, "elapsed_time": "11:52:53", "remaining_time": "13:26:30", "throughput": 56826.7, "total_tokens": 2430656000} |
| {"current_steps": 6810, "total_steps": 14493, "loss": 0.2445, "lr": 3.8565508826633836e-05, "epoch": 1.4097202453352655, "percentage": 46.99, "elapsed_time": "11:53:46", "remaining_time": "13:25:16", "throughput": 56842.25, "total_tokens": 2434333312} |
| {"current_steps": 6820, "total_steps": 14493, "loss": 0.2461, "lr": 3.855404225818049e-05, "epoch": 1.4117905851297845, "percentage": 47.06, "elapsed_time": "11:54:36", "remaining_time": "13:23:59", "throughput": 56858.55, "total_tokens": 2437921664} |
| {"current_steps": 6830, "total_steps": 14493, "loss": 0.2456, "lr": 3.8542585911611286e-05, "epoch": 1.4138609249243033, "percentage": 47.13, "elapsed_time": "11:55:25", "remaining_time": "13:22:41", "throughput": 56875.86, "total_tokens": 2441441792} |
| {"current_steps": 6840, "total_steps": 14493, "loss": 0.2462, "lr": 3.853113977174803e-05, "epoch": 1.415931264718822, "percentage": 47.2, "elapsed_time": "11:56:20", "remaining_time": "13:21:29", "throughput": 56886.56, "total_tokens": 2445017600} |
| {"current_steps": 6850, "total_steps": 14493, "loss": 0.2472, "lr": 3.851970382344411e-05, "epoch": 1.4180016045133408, "percentage": 47.26, "elapsed_time": "11:57:12", "remaining_time": "13:20:13", "throughput": 56902.24, "total_tokens": 2448633856} |
| {"current_steps": 6860, "total_steps": 14493, "loss": 0.2457, "lr": 3.850827805158433e-05, "epoch": 1.4200719443078595, "percentage": 47.33, "elapsed_time": "11:58:01", "remaining_time": "13:18:56", "throughput": 56918.85, "total_tokens": 2452161152} |
| {"current_steps": 6870, "total_steps": 14493, "loss": 0.2463, "lr": 3.8496862441084896e-05, "epoch": 1.4221422841023783, "percentage": 47.4, "elapsed_time": "11:58:52", "remaining_time": "13:17:40", "throughput": 56934.74, "total_tokens": 2455738624} |
| {"current_steps": 6880, "total_steps": 14493, "loss": 0.2433, "lr": 3.848545697689328e-05, "epoch": 1.424212623896897, "percentage": 47.47, "elapsed_time": "11:59:41", "remaining_time": "13:16:21", "throughput": 56953.08, "total_tokens": 2459293056} |
| {"current_steps": 6890, "total_steps": 14493, "loss": 0.2458, "lr": 3.8474061643988136e-05, "epoch": 1.4262829636914158, "percentage": 47.54, "elapsed_time": "12:00:29", "remaining_time": "13:15:02", "throughput": 56971.65, "total_tokens": 2462838528} |
| {"current_steps": 6900, "total_steps": 14493, "loss": 0.2458, "lr": 3.846267642737925e-05, "epoch": 1.4283533034859346, "percentage": 47.61, "elapsed_time": "12:01:20", "remaining_time": "13:13:47", "throughput": 56987.13, "total_tokens": 2466444928} |
| {"current_steps": 6910, "total_steps": 14493, "loss": 0.2449, "lr": 3.8451301312107455e-05, "epoch": 1.4304236432804533, "percentage": 47.68, "elapsed_time": "12:02:09", "remaining_time": "13:12:29", "throughput": 57003.86, "total_tokens": 2469957504} |
| {"current_steps": 6920, "total_steps": 14493, "loss": 0.2462, "lr": 3.843993628324451e-05, "epoch": 1.432493983074972, "percentage": 47.75, "elapsed_time": "12:02:58", "remaining_time": "13:11:11", "throughput": 57021.87, "total_tokens": 2473520384} |
| {"current_steps": 6930, "total_steps": 14493, "loss": 0.2452, "lr": 3.8428581325893034e-05, "epoch": 1.434564322869491, "percentage": 47.82, "elapsed_time": "12:03:52", "remaining_time": "13:09:59", "throughput": 57034.99, "total_tokens": 2477171584} |
| {"current_steps": 6940, "total_steps": 14493, "loss": 0.2426, "lr": 3.8417236425186484e-05, "epoch": 1.4366346626640096, "percentage": 47.89, "elapsed_time": "12:04:41", "remaining_time": "13:08:41", "throughput": 57051.94, "total_tokens": 2480691968} |
| {"current_steps": 6950, "total_steps": 14493, "loss": 0.2451, "lr": 3.840590156628895e-05, "epoch": 1.4387050024585286, "percentage": 47.95, "elapsed_time": "12:05:33", "remaining_time": "13:07:27", "throughput": 57068.04, "total_tokens": 2484355968} |
| {"current_steps": 6960, "total_steps": 14493, "loss": 0.2446, "lr": 3.8394576734395205e-05, "epoch": 1.4407753422530472, "percentage": 48.02, "elapsed_time": "12:06:20", "remaining_time": "13:06:08", "throughput": 57086.4, "total_tokens": 2487874304} |
| {"current_steps": 6970, "total_steps": 14493, "loss": 0.2466, "lr": 3.838326191473054e-05, "epoch": 1.4428456820475661, "percentage": 48.09, "elapsed_time": "12:07:10", "remaining_time": "13:04:52", "throughput": 57102.61, "total_tokens": 2491408640} |
| {"current_steps": 6980, "total_steps": 14493, "loss": 0.2451, "lr": 3.837195709255069e-05, "epoch": 1.444916021842085, "percentage": 48.16, "elapsed_time": "12:07:58", "remaining_time": "13:03:33", "throughput": 57119.0, "total_tokens": 2494856960} |
| {"current_steps": 6990, "total_steps": 14493, "loss": 0.2477, "lr": 3.8360662253141796e-05, "epoch": 1.4469863616366037, "percentage": 48.23, "elapsed_time": "12:08:44", "remaining_time": "13:02:13", "throughput": 57136.78, "total_tokens": 2498264448} |
| {"current_steps": 7000, "total_steps": 14493, "loss": 0.2451, "lr": 3.834937738182029e-05, "epoch": 1.4490567014311224, "percentage": 48.3, "elapsed_time": "12:09:38", "remaining_time": "13:01:02", "throughput": 57146.15, "total_tokens": 2501790976} |
| {"current_steps": 7010, "total_steps": 14493, "loss": 0.2435, "lr": 3.833810246393281e-05, "epoch": 1.4511270412256412, "percentage": 48.37, "elapsed_time": "12:10:33", "remaining_time": "12:59:51", "throughput": 57157.92, "total_tokens": 2505442304} |
| {"current_steps": 7020, "total_steps": 14493, "loss": 0.2428, "lr": 3.832683748485616e-05, "epoch": 1.45319738102016, "percentage": 48.44, "elapsed_time": "12:11:44", "remaining_time": "12:58:57", "throughput": 57146.81, "total_tokens": 2508978688} |
| {"current_steps": 7030, "total_steps": 14493, "loss": 0.2441, "lr": 3.8315582429997184e-05, "epoch": 1.4552677208146787, "percentage": 48.51, "elapsed_time": "12:12:39", "remaining_time": "12:57:47", "throughput": 57154.28, "total_tokens": 2512476928} |
| {"current_steps": 7040, "total_steps": 14493, "loss": 0.2458, "lr": 3.830433728479272e-05, "epoch": 1.4573380606091975, "percentage": 48.58, "elapsed_time": "12:13:48", "remaining_time": "12:56:51", "throughput": 57146.0, "total_tokens": 2516059392} |
| {"current_steps": 7050, "total_steps": 14493, "loss": 0.2452, "lr": 3.829310203470948e-05, "epoch": 1.4594084004037162, "percentage": 48.64, "elapsed_time": "12:14:39", "remaining_time": "12:55:37", "throughput": 57160.65, "total_tokens": 2519639168} |
| {"current_steps": 7060, "total_steps": 14493, "loss": 0.2451, "lr": 3.828187666524403e-05, "epoch": 1.461478740198235, "percentage": 48.71, "elapsed_time": "12:15:27", "remaining_time": "12:54:18", "throughput": 57178.99, "total_tokens": 2523147008} |
| {"current_steps": 7070, "total_steps": 14493, "loss": 0.2445, "lr": 3.827066116192266e-05, "epoch": 1.4635490799927537, "percentage": 48.78, "elapsed_time": "12:16:21", "remaining_time": "12:53:07", "throughput": 57188.89, "total_tokens": 2526715520} |
| {"current_steps": 7080, "total_steps": 14493, "loss": 0.2474, "lr": 3.825945551030135e-05, "epoch": 1.4656194197872725, "percentage": 48.85, "elapsed_time": "12:17:12", "remaining_time": "12:51:53", "throughput": 57204.04, "total_tokens": 2530282752} |
| {"current_steps": 7090, "total_steps": 14493, "loss": 0.2444, "lr": 3.824825969596561e-05, "epoch": 1.4676897595817913, "percentage": 48.92, "elapsed_time": "12:18:02", "remaining_time": "12:50:37", "throughput": 57220.23, "total_tokens": 2533843840} |
| {"current_steps": 7100, "total_steps": 14493, "loss": 0.2469, "lr": 3.823707370453054e-05, "epoch": 1.4697600993763102, "percentage": 48.99, "elapsed_time": "12:18:51", "remaining_time": "12:49:21", "throughput": 57236.67, "total_tokens": 2537407232} |
| {"current_steps": 7110, "total_steps": 14493, "loss": 0.2449, "lr": 3.8225897521640614e-05, "epoch": 1.4718304391708288, "percentage": 49.06, "elapsed_time": "12:19:43", "remaining_time": "12:48:07", "throughput": 57251.82, "total_tokens": 2541047040} |
| {"current_steps": 7120, "total_steps": 14493, "loss": 0.2435, "lr": 3.8214731132969675e-05, "epoch": 1.4739007789653478, "percentage": 49.13, "elapsed_time": "12:20:33", "remaining_time": "12:46:52", "throughput": 57266.71, "total_tokens": 2544581504} |
| {"current_steps": 7130, "total_steps": 14493, "loss": 0.2459, "lr": 3.820357452422084e-05, "epoch": 1.4759711187598665, "percentage": 49.2, "elapsed_time": "12:21:24", "remaining_time": "12:45:37", "throughput": 57283.47, "total_tokens": 2548210048} |
| {"current_steps": 7140, "total_steps": 14493, "loss": 0.2447, "lr": 3.8192427681126445e-05, "epoch": 1.4780414585543853, "percentage": 49.27, "elapsed_time": "12:22:14", "remaining_time": "12:44:22", "throughput": 57299.9, "total_tokens": 2551817344} |
| {"current_steps": 7150, "total_steps": 14493, "loss": 0.243, "lr": 3.818129058944793e-05, "epoch": 1.480111798348904, "percentage": 49.33, "elapsed_time": "12:23:04", "remaining_time": "12:43:07", "throughput": 57314.72, "total_tokens": 2555343744} |
| {"current_steps": 7160, "total_steps": 14493, "loss": 0.2449, "lr": 3.817016323497578e-05, "epoch": 1.4821821381434228, "percentage": 49.4, "elapsed_time": "12:23:55", "remaining_time": "12:41:53", "throughput": 57330.22, "total_tokens": 2558939904} |
| {"current_steps": 7170, "total_steps": 14493, "loss": 0.2451, "lr": 3.8159045603529455e-05, "epoch": 1.4842524779379416, "percentage": 49.47, "elapsed_time": "12:24:44", "remaining_time": "12:40:37", "throughput": 57345.28, "total_tokens": 2562428416} |
| {"current_steps": 7180, "total_steps": 14493, "loss": 0.2432, "lr": 3.8147937680957334e-05, "epoch": 1.4863228177324603, "percentage": 49.54, "elapsed_time": "12:25:31", "remaining_time": "12:39:20", "throughput": 57362.88, "total_tokens": 2565951104} |
| {"current_steps": 7190, "total_steps": 14493, "loss": 0.2437, "lr": 3.813683945313658e-05, "epoch": 1.488393157526979, "percentage": 49.61, "elapsed_time": "12:26:23", "remaining_time": "12:38:07", "throughput": 57377.66, "total_tokens": 2569595648} |
| {"current_steps": 7200, "total_steps": 14493, "loss": 0.2433, "lr": 3.812575090597313e-05, "epoch": 1.4904634973214979, "percentage": 49.68, "elapsed_time": "12:27:12", "remaining_time": "12:36:52", "throughput": 57395.23, "total_tokens": 2573195904} |
| {"current_steps": 7210, "total_steps": 14493, "loss": 0.2427, "lr": 3.811467202540156e-05, "epoch": 1.4925338371160166, "percentage": 49.75, "elapsed_time": "12:28:02", "remaining_time": "12:35:36", "throughput": 57411.68, "total_tokens": 2576763392} |
| {"current_steps": 7220, "total_steps": 14493, "loss": 0.2444, "lr": 3.810360279738507e-05, "epoch": 1.4946041769105354, "percentage": 49.82, "elapsed_time": "12:28:53", "remaining_time": "12:34:23", "throughput": 57426.44, "total_tokens": 2580369408} |
| {"current_steps": 7230, "total_steps": 14493, "loss": 0.2462, "lr": 3.809254320791535e-05, "epoch": 1.4966745167050541, "percentage": 49.89, "elapsed_time": "12:29:44", "remaining_time": "12:33:09", "throughput": 57441.59, "total_tokens": 2583984256} |
| {"current_steps": 7240, "total_steps": 14493, "loss": 0.2427, "lr": 3.808149324301256e-05, "epoch": 1.498744856499573, "percentage": 49.96, "elapsed_time": "12:30:36", "remaining_time": "12:31:57", "throughput": 57455.07, "total_tokens": 2587581824} |
| {"current_steps": 7250, "total_steps": 14493, "loss": 0.2438, "lr": 3.807045288872522e-05, "epoch": 1.5008151962940919, "percentage": 50.02, "elapsed_time": "12:31:27", "remaining_time": "12:30:43", "throughput": 57470.39, "total_tokens": 2591176576} |
| {"current_steps": 7260, "total_steps": 14493, "loss": 0.2435, "lr": 3.805942213113015e-05, "epoch": 1.5028855360886104, "percentage": 50.09, "elapsed_time": "12:32:15", "remaining_time": "12:29:28", "throughput": 57487.86, "total_tokens": 2594769024} |
| {"current_steps": 7270, "total_steps": 14493, "loss": 0.2455, "lr": 3.8048400956332385e-05, "epoch": 1.5049558758831294, "percentage": 50.16, "elapsed_time": "12:33:04", "remaining_time": "12:28:11", "throughput": 57505.14, "total_tokens": 2598316928} |
| {"current_steps": 7280, "total_steps": 14493, "loss": 0.2451, "lr": 3.803738935046512e-05, "epoch": 1.507026215677648, "percentage": 50.23, "elapsed_time": "12:33:57", "remaining_time": "12:27:01", "throughput": 57518.78, "total_tokens": 2602032128} |
| {"current_steps": 7290, "total_steps": 14493, "loss": 0.2435, "lr": 3.802638729968962e-05, "epoch": 1.509096555472167, "percentage": 50.3, "elapsed_time": "12:34:46", "remaining_time": "12:25:46", "throughput": 57535.69, "total_tokens": 2605607680} |
| {"current_steps": 7300, "total_steps": 14493, "loss": 0.246, "lr": 3.8015394790195145e-05, "epoch": 1.5111668952666857, "percentage": 50.37, "elapsed_time": "12:35:41", "remaining_time": "12:24:37", "throughput": 57544.93, "total_tokens": 2609185920} |
| {"current_steps": 7310, "total_steps": 14493, "loss": 0.2425, "lr": 3.800441180819891e-05, "epoch": 1.5132372350612044, "percentage": 50.44, "elapsed_time": "12:36:32", "remaining_time": "12:23:23", "throughput": 57559.54, "total_tokens": 2612767360} |
| {"current_steps": 7320, "total_steps": 14493, "loss": 0.2452, "lr": 3.7993438339945965e-05, "epoch": 1.5153075748557232, "percentage": 50.51, "elapsed_time": "12:37:32", "remaining_time": "12:22:19", "throughput": 57562.82, "total_tokens": 2616365056} |
| {"current_steps": 7330, "total_steps": 14493, "loss": 0.2444, "lr": 3.798247437170914e-05, "epoch": 1.517377914650242, "percentage": 50.58, "elapsed_time": "12:38:34", "remaining_time": "12:21:17", "throughput": 57561.09, "total_tokens": 2619883392} |
| {"current_steps": 7340, "total_steps": 14493, "loss": 0.245, "lr": 3.797151988978901e-05, "epoch": 1.5194482544447607, "percentage": 50.65, "elapsed_time": "12:39:37", "remaining_time": "12:20:15", "throughput": 57562.04, "total_tokens": 2623513088} |
| {"current_steps": 7350, "total_steps": 14493, "loss": 0.2433, "lr": 3.796057488051377e-05, "epoch": 1.5215185942392795, "percentage": 50.71, "elapsed_time": "12:40:41", "remaining_time": "12:19:16", "throughput": 57560.46, "total_tokens": 2627169408} |
| {"current_steps": 7360, "total_steps": 14493, "loss": 0.2465, "lr": 3.794963933023918e-05, "epoch": 1.5235889340337982, "percentage": 50.78, "elapsed_time": "12:41:39", "remaining_time": "12:18:10", "throughput": 57566.2, "total_tokens": 2630768384} |
| {"current_steps": 7370, "total_steps": 14493, "loss": 0.2456, "lr": 3.79387132253485e-05, "epoch": 1.525659273828317, "percentage": 50.85, "elapsed_time": "12:42:26", "remaining_time": "12:16:53", "throughput": 57583.93, "total_tokens": 2634268160} |
| {"current_steps": 7380, "total_steps": 14493, "loss": 0.2418, "lr": 3.792779655225243e-05, "epoch": 1.527729613622836, "percentage": 50.92, "elapsed_time": "12:43:14", "remaining_time": "12:15:37", "throughput": 57600.23, "total_tokens": 2637746176} |
| {"current_steps": 7390, "total_steps": 14493, "loss": 0.2433, "lr": 3.791688929738902e-05, "epoch": 1.5297999534173545, "percentage": 50.99, "elapsed_time": "12:44:03", "remaining_time": "12:14:22", "throughput": 57615.62, "total_tokens": 2641288064} |
| {"current_steps": 7400, "total_steps": 14493, "loss": 0.2456, "lr": 3.79059914472236e-05, "epoch": 1.5318702932118735, "percentage": 51.06, "elapsed_time": "12:44:52", "remaining_time": "12:13:08", "throughput": 57631.0, "total_tokens": 2644830464} |
| {"current_steps": 7410, "total_steps": 14493, "loss": 0.2456, "lr": 3.7895102988248716e-05, "epoch": 1.533940633006392, "percentage": 51.13, "elapsed_time": "12:45:42", "remaining_time": "12:11:55", "throughput": 57645.78, "total_tokens": 2648393472} |
| {"current_steps": 7420, "total_steps": 14493, "loss": 0.2456, "lr": 3.7884223906984064e-05, "epoch": 1.536010972800911, "percentage": 51.2, "elapsed_time": "12:46:30", "remaining_time": "12:10:40", "throughput": 57660.67, "total_tokens": 2651868160} |
| {"current_steps": 7430, "total_steps": 14493, "loss": 0.243, "lr": 3.787335418997641e-05, "epoch": 1.5380813125954296, "percentage": 51.27, "elapsed_time": "12:47:20", "remaining_time": "12:09:26", "throughput": 57677.12, "total_tokens": 2655469824} |
| {"current_steps": 7440, "total_steps": 14493, "loss": 0.244, "lr": 3.786249382379952e-05, "epoch": 1.5401516523899486, "percentage": 51.34, "elapsed_time": "12:48:08", "remaining_time": "12:08:10", "throughput": 57693.25, "total_tokens": 2658980992} |
| {"current_steps": 7450, "total_steps": 14493, "loss": 0.2452, "lr": 3.785164279505411e-05, "epoch": 1.5422219921844673, "percentage": 51.4, "elapsed_time": "12:48:56", "remaining_time": "12:06:56", "throughput": 57708.9, "total_tokens": 2662489984} |
| {"current_steps": 7460, "total_steps": 14493, "loss": 0.2443, "lr": 3.7840801090367744e-05, "epoch": 1.544292331978986, "percentage": 51.47, "elapsed_time": "12:49:46", "remaining_time": "12:05:42", "throughput": 57723.67, "total_tokens": 2666027904} |
| {"current_steps": 7470, "total_steps": 14493, "loss": 0.2462, "lr": 3.782996869639479e-05, "epoch": 1.5463626717735048, "percentage": 51.54, "elapsed_time": "12:50:36", "remaining_time": "12:04:29", "throughput": 57737.36, "total_tokens": 2669558912} |
| {"current_steps": 7480, "total_steps": 14493, "loss": 0.2432, "lr": 3.7819145599816354e-05, "epoch": 1.5484330115680236, "percentage": 51.61, "elapsed_time": "12:51:25", "remaining_time": "12:03:15", "throughput": 57752.53, "total_tokens": 2673107712} |
| {"current_steps": 7490, "total_steps": 14493, "loss": 0.2416, "lr": 3.780833178734018e-05, "epoch": 1.5505033513625424, "percentage": 51.68, "elapsed_time": "12:52:15", "remaining_time": "12:02:02", "throughput": 57767.68, "total_tokens": 2676696704} |
| {"current_steps": 7500, "total_steps": 14493, "loss": 0.2451, "lr": 3.77975272457006e-05, "epoch": 1.5525736911570611, "percentage": 51.75, "elapsed_time": "12:53:04", "remaining_time": "12:00:49", "throughput": 57784.53, "total_tokens": 2680325632} |
| {"current_steps": 7510, "total_steps": 14493, "loss": 0.2428, "lr": 3.778673196165851e-05, "epoch": 1.5546440309515799, "percentage": 51.82, "elapsed_time": "12:53:55", "remaining_time": "11:59:36", "throughput": 57799.11, "total_tokens": 2683906432} |
| {"current_steps": 7520, "total_steps": 14493, "loss": 0.2423, "lr": 3.7775945922001186e-05, "epoch": 1.5567143707460986, "percentage": 51.89, "elapsed_time": "12:54:46", "remaining_time": "11:58:25", "throughput": 57813.33, "total_tokens": 2687534976} |
| {"current_steps": 7530, "total_steps": 14493, "loss": 0.2452, "lr": 3.776516911354236e-05, "epoch": 1.5587847105406176, "percentage": 51.96, "elapsed_time": "12:55:40", "remaining_time": "11:57:15", "throughput": 57826.89, "total_tokens": 2691268992} |
| {"current_steps": 7540, "total_steps": 14493, "loss": 0.2449, "lr": 3.775440152312205e-05, "epoch": 1.5608550503351362, "percentage": 52.03, "elapsed_time": "12:56:31", "remaining_time": "11:56:04", "throughput": 57840.54, "total_tokens": 2694872320} |
| {"current_steps": 7550, "total_steps": 14493, "loss": 0.2432, "lr": 3.774364313760652e-05, "epoch": 1.5629253901296551, "percentage": 52.09, "elapsed_time": "12:57:23", "remaining_time": "11:54:53", "throughput": 57853.46, "total_tokens": 2698465408} |
| {"current_steps": 7560, "total_steps": 14493, "loss": 0.2438, "lr": 3.7732893943888224e-05, "epoch": 1.5649957299241737, "percentage": 52.16, "elapsed_time": "12:58:13", "remaining_time": "11:53:41", "throughput": 57868.26, "total_tokens": 2702086144} |
| {"current_steps": 7570, "total_steps": 14493, "loss": 0.2456, "lr": 3.772215392888574e-05, "epoch": 1.5670660697186927, "percentage": 52.23, "elapsed_time": "12:59:06", "remaining_time": "11:52:31", "throughput": 57881.35, "total_tokens": 2705748864} |
| {"current_steps": 7580, "total_steps": 14493, "loss": 0.2414, "lr": 3.771142307954368e-05, "epoch": 1.5691364095132112, "percentage": 52.3, "elapsed_time": "12:59:58", "remaining_time": "11:51:20", "throughput": 57895.12, "total_tokens": 2709402752} |
| {"current_steps": 7590, "total_steps": 14493, "loss": 0.2433, "lr": 3.770070138283264e-05, "epoch": 1.5712067493077302, "percentage": 52.37, "elapsed_time": "13:00:50", "remaining_time": "11:50:09", "throughput": 57909.74, "total_tokens": 2713085696} |
| {"current_steps": 7600, "total_steps": 14493, "loss": 0.2447, "lr": 3.768998882574915e-05, "epoch": 1.573277089102249, "percentage": 52.44, "elapsed_time": "13:01:45", "remaining_time": "11:49:01", "throughput": 57920.26, "total_tokens": 2716772608} |
| {"current_steps": 7610, "total_steps": 14493, "loss": 0.2433, "lr": 3.767928539531557e-05, "epoch": 1.5753474288967677, "percentage": 52.51, "elapsed_time": "13:02:39", "remaining_time": "11:47:53", "throughput": 57931.14, "total_tokens": 2720420096} |
| {"current_steps": 7620, "total_steps": 14493, "loss": 0.2458, "lr": 3.7668591078580055e-05, "epoch": 1.5774177686912865, "percentage": 52.58, "elapsed_time": "13:03:34", "remaining_time": "11:46:45", "throughput": 57938.92, "total_tokens": 2723959040} |
| {"current_steps": 7630, "total_steps": 14493, "loss": 0.2451, "lr": 3.765790586261647e-05, "epoch": 1.5794881084858052, "percentage": 52.65, "elapsed_time": "13:04:39", "remaining_time": "11:45:46", "throughput": 57935.84, "total_tokens": 2727566720} |
| {"current_steps": 7640, "total_steps": 14493, "loss": 0.2414, "lr": 3.7647229734524326e-05, "epoch": 1.581558448280324, "percentage": 52.72, "elapsed_time": "13:05:33", "remaining_time": "11:44:38", "throughput": 57943.37, "total_tokens": 2731062784} |
| {"current_steps": 7650, "total_steps": 14493, "loss": 0.2432, "lr": 3.7636562681428744e-05, "epoch": 1.5836287880748428, "percentage": 52.78, "elapsed_time": "13:06:24", "remaining_time": "11:43:26", "throughput": 57956.07, "total_tokens": 2734613504} |
| {"current_steps": 7660, "total_steps": 14493, "loss": 0.2431, "lr": 3.7625904690480346e-05, "epoch": 1.5856991278693615, "percentage": 52.85, "elapsed_time": "13:07:23", "remaining_time": "11:42:22", "throughput": 57963.04, "total_tokens": 2738370816} |
| {"current_steps": 7670, "total_steps": 14493, "loss": 0.241, "lr": 3.7615255748855224e-05, "epoch": 1.5877694676638803, "percentage": 52.92, "elapsed_time": "13:08:12", "remaining_time": "11:41:10", "throughput": 57976.66, "total_tokens": 2741879424} |
| {"current_steps": 7680, "total_steps": 14493, "loss": 0.243, "lr": 3.7604615843754845e-05, "epoch": 1.5898398074583993, "percentage": 52.99, "elapsed_time": "13:09:00", "remaining_time": "11:39:56", "throughput": 57992.45, "total_tokens": 2745407232} |
| {"current_steps": 7690, "total_steps": 14493, "loss": 0.2455, "lr": 3.759398496240601e-05, "epoch": 1.5919101472529178, "percentage": 53.06, "elapsed_time": "13:09:48", "remaining_time": "11:38:42", "throughput": 58008.43, "total_tokens": 2748938752} |
| {"current_steps": 7700, "total_steps": 14493, "loss": 0.244, "lr": 3.7583363092060815e-05, "epoch": 1.5939804870474368, "percentage": 53.13, "elapsed_time": "13:10:38", "remaining_time": "11:37:30", "throughput": 58023.24, "total_tokens": 2752559104} |
| {"current_steps": 7710, "total_steps": 14493, "loss": 0.2431, "lr": 3.757275021999649e-05, "epoch": 1.5960508268419553, "percentage": 53.2, "elapsed_time": "13:11:27", "remaining_time": "11:36:17", "throughput": 58037.16, "total_tokens": 2756039424} |
| {"current_steps": 7720, "total_steps": 14493, "loss": 0.2429, "lr": 3.7562146333515445e-05, "epoch": 1.5981211666364743, "percentage": 53.27, "elapsed_time": "13:12:14", "remaining_time": "11:35:03", "throughput": 58054.27, "total_tokens": 2759586048} |
| {"current_steps": 7730, "total_steps": 14493, "loss": 0.2462, "lr": 3.7551551419945167e-05, "epoch": 1.6001915064309928, "percentage": 53.34, "elapsed_time": "13:13:02", "remaining_time": "11:33:50", "throughput": 58069.37, "total_tokens": 2763111040} |
| {"current_steps": 7740, "total_steps": 14493, "loss": 0.245, "lr": 3.7540965466638104e-05, "epoch": 1.6022618462255118, "percentage": 53.41, "elapsed_time": "13:13:50", "remaining_time": "11:32:36", "throughput": 58085.05, "total_tokens": 2766621696} |
| {"current_steps": 7750, "total_steps": 14493, "loss": 0.2426, "lr": 3.753038846097172e-05, "epoch": 1.6043321860200306, "percentage": 53.47, "elapsed_time": "13:14:41", "remaining_time": "11:31:26", "throughput": 58098.58, "total_tokens": 2770246784} |
| {"current_steps": 7760, "total_steps": 14493, "loss": 0.244, "lr": 3.751982039034827e-05, "epoch": 1.6064025258145493, "percentage": 53.54, "elapsed_time": "13:15:28", "remaining_time": "11:30:12", "throughput": 58113.56, "total_tokens": 2773695488} |
| {"current_steps": 7770, "total_steps": 14493, "loss": 0.2442, "lr": 3.75092612421949e-05, "epoch": 1.608472865609068, "percentage": 53.61, "elapsed_time": "13:16:14", "remaining_time": "11:28:56", "throughput": 58130.89, "total_tokens": 2777163904} |
| {"current_steps": 7780, "total_steps": 14493, "loss": 0.2429, "lr": 3.7498711003963475e-05, "epoch": 1.6105432054035869, "percentage": 53.68, "elapsed_time": "13:17:03", "remaining_time": "11:27:45", "throughput": 58144.11, "total_tokens": 2780681728} |
| {"current_steps": 7790, "total_steps": 14493, "loss": 0.2448, "lr": 3.748816966313058e-05, "epoch": 1.6126135451981056, "percentage": 53.75, "elapsed_time": "13:17:53", "remaining_time": "11:26:33", "throughput": 58159.49, "total_tokens": 2784296448} |
| {"current_steps": 7800, "total_steps": 14493, "loss": 0.2436, "lr": 3.7477637207197374e-05, "epoch": 1.6146838849926244, "percentage": 53.82, "elapsed_time": "13:18:44", "remaining_time": "11:25:23", "throughput": 58173.37, "total_tokens": 2787953152} |
| {"current_steps": 7810, "total_steps": 14493, "loss": 0.2429, "lr": 3.7467113623689666e-05, "epoch": 1.6167542247871431, "percentage": 53.89, "elapsed_time": "13:19:34", "remaining_time": "11:24:11", "throughput": 58188.26, "total_tokens": 2791524608} |
| {"current_steps": 7820, "total_steps": 14493, "loss": 0.2454, "lr": 3.745659890015768e-05, "epoch": 1.618824564581662, "percentage": 53.96, "elapsed_time": "13:20:22", "remaining_time": "11:22:59", "throughput": 58202.93, "total_tokens": 2795072896} |
| {"current_steps": 7830, "total_steps": 14493, "loss": 0.2446, "lr": 3.744609302417615e-05, "epoch": 1.620894904376181, "percentage": 54.03, "elapsed_time": "13:21:16", "remaining_time": "11:21:51", "throughput": 58213.92, "total_tokens": 2798743552} |
| {"current_steps": 7840, "total_steps": 14493, "loss": 0.2436, "lr": 3.7435595983344175e-05, "epoch": 1.6229652441706994, "percentage": 54.1, "elapsed_time": "13:22:03", "remaining_time": "11:20:37", "throughput": 58231.19, "total_tokens": 2802270848} |
| {"current_steps": 7850, "total_steps": 14493, "loss": 0.2449, "lr": 3.7425107765285155e-05, "epoch": 1.6250355839652184, "percentage": 54.16, "elapsed_time": "13:22:52", "remaining_time": "11:19:25", "throughput": 58244.77, "total_tokens": 2805819904} |
| {"current_steps": 7860, "total_steps": 14493, "loss": 0.2428, "lr": 3.741462835764676e-05, "epoch": 1.627105923759737, "percentage": 54.23, "elapsed_time": "13:23:43", "remaining_time": "11:18:15", "throughput": 58258.75, "total_tokens": 2809440640} |
| {"current_steps": 7870, "total_steps": 14493, "loss": 0.2442, "lr": 3.740415774810088e-05, "epoch": 1.629176263554256, "percentage": 54.3, "elapsed_time": "13:24:31", "remaining_time": "11:17:03", "throughput": 58273.52, "total_tokens": 2812960384} |
| {"current_steps": 7880, "total_steps": 14493, "loss": 0.2447, "lr": 3.739369592434351e-05, "epoch": 1.6312466033487745, "percentage": 54.37, "elapsed_time": "13:25:23", "remaining_time": "11:15:53", "throughput": 58285.8, "total_tokens": 2816577280} |
| {"current_steps": 7890, "total_steps": 14493, "loss": 0.2438, "lr": 3.738324287409473e-05, "epoch": 1.6333169431432935, "percentage": 54.44, "elapsed_time": "13:26:11", "remaining_time": "11:14:41", "throughput": 58299.99, "total_tokens": 2820048896} |
| {"current_steps": 7900, "total_steps": 14493, "loss": 0.2442, "lr": 3.7372798585098644e-05, "epoch": 1.6353872829378122, "percentage": 54.51, "elapsed_time": "13:27:04", "remaining_time": "11:13:33", "throughput": 58311.09, "total_tokens": 2823700224} |
| {"current_steps": 7910, "total_steps": 14493, "loss": 0.2435, "lr": 3.736236304512331e-05, "epoch": 1.637457622732331, "percentage": 54.58, "elapsed_time": "13:27:53", "remaining_time": "11:12:21", "throughput": 58326.14, "total_tokens": 2827285760} |
| {"current_steps": 7920, "total_steps": 14493, "loss": 0.2421, "lr": 3.735193624196067e-05, "epoch": 1.6395279625268497, "percentage": 54.65, "elapsed_time": "13:28:41", "remaining_time": "11:11:09", "throughput": 58339.93, "total_tokens": 2830761344} |
| {"current_steps": 7930, "total_steps": 14493, "loss": 0.2422, "lr": 3.7341518163426514e-05, "epoch": 1.6415983023213685, "percentage": 54.72, "elapsed_time": "13:29:31", "remaining_time": "11:09:58", "throughput": 58354.88, "total_tokens": 2834373120} |
| {"current_steps": 7940, "total_steps": 14493, "loss": 0.242, "lr": 3.73311087973604e-05, "epoch": 1.6436686421158873, "percentage": 54.79, "elapsed_time": "13:30:25", "remaining_time": "11:08:51", "throughput": 58362.44, "total_tokens": 2837891328} |
| {"current_steps": 7950, "total_steps": 14493, "loss": 0.2431, "lr": 3.732070813162561e-05, "epoch": 1.645738981910406, "percentage": 54.85, "elapsed_time": "13:31:12", "remaining_time": "11:07:38", "throughput": 58377.94, "total_tokens": 2841428864} |
| {"current_steps": 7960, "total_steps": 14493, "loss": 0.2437, "lr": 3.731031615410908e-05, "epoch": 1.6478093217049248, "percentage": 54.92, "elapsed_time": "13:32:09", "remaining_time": "11:06:33", "throughput": 58384.4, "total_tokens": 2845026816} |
| {"current_steps": 7970, "total_steps": 14493, "loss": 0.2448, "lr": 3.729993285272132e-05, "epoch": 1.6498796614994435, "percentage": 54.99, "elapsed_time": "13:33:08", "remaining_time": "11:05:30", "throughput": 58385.08, "total_tokens": 2848507264} |
| {"current_steps": 7980, "total_steps": 14493, "loss": 0.2422, "lr": 3.7289558215396414e-05, "epoch": 1.6519500012939625, "percentage": 55.06, "elapsed_time": "13:34:12", "remaining_time": "11:04:31", "throughput": 58380.85, "total_tokens": 2852054784} |
| {"current_steps": 7990, "total_steps": 14493, "loss": 0.2437, "lr": 3.727919223009191e-05, "epoch": 1.654020341088481, "percentage": 55.13, "elapsed_time": "13:35:04", "remaining_time": "11:03:22", "throughput": 58390.9, "total_tokens": 2855571840} |
| {"current_steps": 8000, "total_steps": 14493, "loss": 0.2428, "lr": 3.726883488478877e-05, "epoch": 1.656090680883, "percentage": 55.2, "elapsed_time": "13:35:54", "remaining_time": "11:02:12", "throughput": 58403.68, "total_tokens": 2859101056} |
| {"current_steps": 8010, "total_steps": 14493, "loss": 0.2447, "lr": 3.7258486167491323e-05, "epoch": 1.6581610206775186, "percentage": 55.27, "elapsed_time": "13:36:45", "remaining_time": "11:01:03", "throughput": 58415.51, "total_tokens": 2862703360} |
| {"current_steps": 8020, "total_steps": 14493, "loss": 0.2424, "lr": 3.724814606622721e-05, "epoch": 1.6602313604720376, "percentage": 55.34, "elapsed_time": "13:37:33", "remaining_time": "10:59:51", "throughput": 58430.99, "total_tokens": 2866248960} |
| {"current_steps": 8030, "total_steps": 14493, "loss": 0.2431, "lr": 3.7237814569047294e-05, "epoch": 1.662301700266556, "percentage": 55.41, "elapsed_time": "13:38:23", "remaining_time": "10:58:40", "throughput": 58443.33, "total_tokens": 2869743360} |
| {"current_steps": 8040, "total_steps": 14493, "loss": 0.2443, "lr": 3.7227491664025656e-05, "epoch": 1.664372040061075, "percentage": 55.48, "elapsed_time": "13:39:13", "remaining_time": "10:57:31", "throughput": 58456.61, "total_tokens": 2873353600} |
| {"current_steps": 8050, "total_steps": 14493, "loss": 0.246, "lr": 3.721717733925948e-05, "epoch": 1.6664423798555938, "percentage": 55.54, "elapsed_time": "13:40:02", "remaining_time": "10:56:20", "throughput": 58470.77, "total_tokens": 2876908416} |
| {"current_steps": 8060, "total_steps": 14493, "loss": 0.2406, "lr": 3.720687158286904e-05, "epoch": 1.6685127196501126, "percentage": 55.61, "elapsed_time": "13:40:48", "remaining_time": "10:55:07", "throughput": 58486.32, "total_tokens": 2880385792} |
| {"current_steps": 8070, "total_steps": 14493, "loss": 0.2446, "lr": 3.719657438299762e-05, "epoch": 1.6705830594446314, "percentage": 55.68, "elapsed_time": "13:41:34", "remaining_time": "10:53:53", "throughput": 58503.65, "total_tokens": 2883895296} |
| {"current_steps": 8080, "total_steps": 14493, "loss": 0.2428, "lr": 3.7186285727811446e-05, "epoch": 1.6726533992391501, "percentage": 55.75, "elapsed_time": "13:42:23", "remaining_time": "10:52:43", "throughput": 58519.75, "total_tokens": 2887555712} |
| {"current_steps": 8090, "total_steps": 14493, "loss": 0.2421, "lr": 3.717600560549967e-05, "epoch": 1.674723739033669, "percentage": 55.82, "elapsed_time": "13:43:12", "remaining_time": "10:51:32", "throughput": 58534.58, "total_tokens": 2891149440} |
| {"current_steps": 8100, "total_steps": 14493, "loss": 0.2438, "lr": 3.716573400427426e-05, "epoch": 1.6767940788281877, "percentage": 55.89, "elapsed_time": "13:44:03", "remaining_time": "10:50:24", "throughput": 58546.27, "total_tokens": 2894753664} |
| {"current_steps": 8110, "total_steps": 14493, "loss": 0.2402, "lr": 3.7155470912370004e-05, "epoch": 1.6788644186227064, "percentage": 55.96, "elapsed_time": "13:44:54", "remaining_time": "10:49:14", "throughput": 58560.19, "total_tokens": 2898389504} |
| {"current_steps": 8120, "total_steps": 14493, "loss": 0.2416, "lr": 3.714521631804439e-05, "epoch": 1.6809347584172252, "percentage": 56.03, "elapsed_time": "13:45:46", "remaining_time": "10:48:06", "throughput": 58571.18, "total_tokens": 2901985920} |
| {"current_steps": 8130, "total_steps": 14493, "loss": 0.2428, "lr": 3.713497020957759e-05, "epoch": 1.6830050982117442, "percentage": 56.1, "elapsed_time": "13:46:36", "remaining_time": "10:46:57", "throughput": 58583.4, "total_tokens": 2905550848} |
| {"current_steps": 8140, "total_steps": 14493, "loss": 0.2427, "lr": 3.712473257527238e-05, "epoch": 1.6850754380062627, "percentage": 56.17, "elapsed_time": "13:47:25", "remaining_time": "10:45:46", "throughput": 58597.73, "total_tokens": 2909115904} |
| {"current_steps": 8150, "total_steps": 14493, "loss": 0.2442, "lr": 3.711450340345412e-05, "epoch": 1.6871457778007817, "percentage": 56.23, "elapsed_time": "13:48:14", "remaining_time": "10:44:36", "throughput": 58611.54, "total_tokens": 2912673536} |
| {"current_steps": 8160, "total_steps": 14493, "loss": 0.2427, "lr": 3.710428268247067e-05, "epoch": 1.6892161175953002, "percentage": 56.3, "elapsed_time": "13:49:02", "remaining_time": "10:43:25", "throughput": 58626.3, "total_tokens": 2916227840} |
| {"current_steps": 8170, "total_steps": 14493, "loss": 0.245, "lr": 3.709407040069233e-05, "epoch": 1.6912864573898192, "percentage": 56.37, "elapsed_time": "13:49:53", "remaining_time": "10:42:16", "throughput": 58639.53, "total_tokens": 2919850880} |
| {"current_steps": 8180, "total_steps": 14493, "loss": 0.2457, "lr": 3.708386654651179e-05, "epoch": 1.6933567971843377, "percentage": 56.44, "elapsed_time": "13:50:41", "remaining_time": "10:41:05", "throughput": 58654.12, "total_tokens": 2923413376} |
| {"current_steps": 8190, "total_steps": 14493, "loss": 0.2437, "lr": 3.707367110834409e-05, "epoch": 1.6954271369788567, "percentage": 56.51, "elapsed_time": "13:51:29", "remaining_time": "10:39:54", "throughput": 58668.19, "total_tokens": 2926910720} |
| {"current_steps": 8200, "total_steps": 14493, "loss": 0.2404, "lr": 3.7063484074626555e-05, "epoch": 1.6974974767733755, "percentage": 56.58, "elapsed_time": "13:52:20", "remaining_time": "10:38:45", "throughput": 58680.6, "total_tokens": 2930514304} |
| {"current_steps": 8210, "total_steps": 14493, "loss": 0.2396, "lr": 3.7053305433818725e-05, "epoch": 1.6995678165678942, "percentage": 56.65, "elapsed_time": "13:53:09", "remaining_time": "10:37:36", "throughput": 58695.18, "total_tokens": 2934135296} |
| {"current_steps": 8220, "total_steps": 14493, "loss": 0.2437, "lr": 3.704313517440232e-05, "epoch": 1.701638156362413, "percentage": 56.72, "elapsed_time": "13:54:01", "remaining_time": "10:36:28", "throughput": 58707.3, "total_tokens": 2937812096} |
| {"current_steps": 8230, "total_steps": 14493, "loss": 0.2394, "lr": 3.703297328488118e-05, "epoch": 1.7037084961569318, "percentage": 56.79, "elapsed_time": "13:54:49", "remaining_time": "10:35:17", "throughput": 58720.64, "total_tokens": 2941290112} |
| {"current_steps": 8240, "total_steps": 14493, "loss": 0.2403, "lr": 3.70228197537812e-05, "epoch": 1.7057788359514505, "percentage": 56.86, "elapsed_time": "13:55:38", "remaining_time": "10:34:08", "throughput": 58733.98, "total_tokens": 2944847360} |
| {"current_steps": 8250, "total_steps": 14493, "loss": 0.2436, "lr": 3.7012674569650305e-05, "epoch": 1.7078491757459693, "percentage": 56.92, "elapsed_time": "13:56:28", "remaining_time": "10:32:59", "throughput": 58747.1, "total_tokens": 2948440576} |
| {"current_steps": 8260, "total_steps": 14493, "loss": 0.2414, "lr": 3.700253772105835e-05, "epoch": 1.709919515540488, "percentage": 56.99, "elapsed_time": "13:57:20", "remaining_time": "10:31:51", "throughput": 58758.17, "total_tokens": 2952018944} |
| {"current_steps": 8270, "total_steps": 14493, "loss": 0.2427, "lr": 3.699240919659711e-05, "epoch": 1.7119898553350068, "percentage": 57.06, "elapsed_time": "13:58:12", "remaining_time": "10:30:43", "throughput": 58769.05, "total_tokens": 2955615360} |
| {"current_steps": 8280, "total_steps": 14493, "loss": 0.2478, "lr": 3.698228898488019e-05, "epoch": 1.7140601951295258, "percentage": 57.13, "elapsed_time": "13:59:03", "remaining_time": "10:29:36", "throughput": 58778.75, "total_tokens": 2959144832} |
| {"current_steps": 8290, "total_steps": 14493, "loss": 0.2419, "lr": 3.6972177074543e-05, "epoch": 1.7161305349240443, "percentage": 57.2, "elapsed_time": "14:00:03", "remaining_time": "10:28:34", "throughput": 58780.09, "total_tokens": 2962702080} |
| {"current_steps": 8300, "total_steps": 14493, "loss": 0.2417, "lr": 3.69620734542427e-05, "epoch": 1.7182008747185633, "percentage": 57.27, "elapsed_time": "14:00:51", "remaining_time": "10:27:24", "throughput": 58794.62, "total_tokens": 2966294016} |
| {"current_steps": 8310, "total_steps": 14493, "loss": 0.2408, "lr": 3.695197811265811e-05, "epoch": 1.7202712145130818, "percentage": 57.34, "elapsed_time": "14:01:39", "remaining_time": "10:26:13", "throughput": 58810.36, "total_tokens": 2969867392} |
| {"current_steps": 8320, "total_steps": 14493, "loss": 0.2439, "lr": 3.6941891038489694e-05, "epoch": 1.7223415543076008, "percentage": 57.41, "elapsed_time": "14:02:28", "remaining_time": "10:25:04", "throughput": 58823.27, "total_tokens": 2973414400} |
| {"current_steps": 8330, "total_steps": 14493, "loss": 0.2446, "lr": 3.693181222045952e-05, "epoch": 1.7244118941021194, "percentage": 57.48, "elapsed_time": "14:03:20", "remaining_time": "10:23:56", "throughput": 58834.13, "total_tokens": 2977025408} |
| {"current_steps": 8340, "total_steps": 14493, "loss": 0.2441, "lr": 3.692174164731113e-05, "epoch": 1.7264822338966384, "percentage": 57.55, "elapsed_time": "14:04:08", "remaining_time": "10:22:46", "throughput": 58849.29, "total_tokens": 2980628352} |
| {"current_steps": 8350, "total_steps": 14493, "loss": 0.2409, "lr": 3.6911679307809595e-05, "epoch": 1.7285525736911571, "percentage": 57.61, "elapsed_time": "14:04:57", "remaining_time": "10:21:37", "throughput": 58862.75, "total_tokens": 2984207104} |
| {"current_steps": 8360, "total_steps": 14493, "loss": 0.2439, "lr": 3.690162519074137e-05, "epoch": 1.7306229134856759, "percentage": 57.68, "elapsed_time": "14:05:44", "remaining_time": "10:20:26", "throughput": 58878.79, "total_tokens": 2987778816} |
| {"current_steps": 8370, "total_steps": 14493, "loss": 0.2448, "lr": 3.689157928491431e-05, "epoch": 1.7326932532801946, "percentage": 57.75, "elapsed_time": "14:06:35", "remaining_time": "10:19:18", "throughput": 58889.99, "total_tokens": 2991323776} |
| {"current_steps": 8380, "total_steps": 14493, "loss": 0.2429, "lr": 3.6881541579157566e-05, "epoch": 1.7347635930747134, "percentage": 57.82, "elapsed_time": "14:07:25", "remaining_time": "10:18:10", "throughput": 58903.11, "total_tokens": 2994972032} |
| {"current_steps": 8390, "total_steps": 14493, "loss": 0.2416, "lr": 3.687151206232154e-05, "epoch": 1.7368339328692322, "percentage": 57.89, "elapsed_time": "14:08:16", "remaining_time": "10:17:02", "throughput": 58916.61, "total_tokens": 2998642048} |
| {"current_steps": 8400, "total_steps": 14493, "loss": 0.2409, "lr": 3.686149072327788e-05, "epoch": 1.738904272663751, "percentage": 57.96, "elapsed_time": "14:09:07", "remaining_time": "10:15:55", "throughput": 58928.67, "total_tokens": 3002269568} |
| {"current_steps": 8410, "total_steps": 14493, "loss": 0.2406, "lr": 3.685147755091937e-05, "epoch": 1.7409746124582697, "percentage": 58.03, "elapsed_time": "14:09:54", "remaining_time": "10:14:44", "throughput": 58941.9, "total_tokens": 3005709824} |
| {"current_steps": 8420, "total_steps": 14493, "loss": 0.2426, "lr": 3.684147253415992e-05, "epoch": 1.7430449522527884, "percentage": 58.1, "elapsed_time": "14:10:49", "remaining_time": "10:13:40", "throughput": 58948.12, "total_tokens": 3009297408} |
| {"current_steps": 8430, "total_steps": 14493, "loss": 0.2436, "lr": 3.683147566193448e-05, "epoch": 1.7451152920473074, "percentage": 58.17, "elapsed_time": "14:11:41", "remaining_time": "10:12:33", "throughput": 58958.23, "total_tokens": 3012883584} |
| {"current_steps": 8440, "total_steps": 14493, "loss": 0.241, "lr": 3.6821486923199025e-05, "epoch": 1.747185631841826, "percentage": 58.24, "elapsed_time": "14:12:33", "remaining_time": "10:11:26", "throughput": 58969.82, "total_tokens": 3016532864} |
| {"current_steps": 8450, "total_steps": 14493, "loss": 0.242, "lr": 3.681150630693046e-05, "epoch": 1.749255971636345, "percentage": 58.3, "elapsed_time": "14:13:24", "remaining_time": "10:10:18", "throughput": 58981.05, "total_tokens": 3020104704} |
| {"current_steps": 8460, "total_steps": 14493, "loss": 0.241, "lr": 3.6801533802126615e-05, "epoch": 1.7513263114308635, "percentage": 58.37, "elapsed_time": "14:14:14", "remaining_time": "10:09:10", "throughput": 58994.17, "total_tokens": 3023738880} |
| {"current_steps": 8470, "total_steps": 14493, "loss": 0.241, "lr": 3.679156939780617e-05, "epoch": 1.7533966512253825, "percentage": 58.44, "elapsed_time": "14:15:06", "remaining_time": "10:08:04", "throughput": 59004.74, "total_tokens": 3027335680} |
| {"current_steps": 8480, "total_steps": 14493, "loss": 0.2426, "lr": 3.6781613083008594e-05, "epoch": 1.755466991019901, "percentage": 58.51, "elapsed_time": "14:15:53", "remaining_time": "10:06:54", "throughput": 59019.19, "total_tokens": 3030863872} |
| {"current_steps": 8490, "total_steps": 14493, "loss": 0.2418, "lr": 3.677166484679412e-05, "epoch": 1.75753733081442, "percentage": 58.58, "elapsed_time": "14:16:42", "remaining_time": "10:05:45", "throughput": 59033.02, "total_tokens": 3034466304} |
| {"current_steps": 8500, "total_steps": 14493, "loss": 0.2419, "lr": 3.676172467824368e-05, "epoch": 1.7596076706089387, "percentage": 58.65, "elapsed_time": "14:17:32", "remaining_time": "10:04:37", "throughput": 59044.86, "total_tokens": 3038017792} |
| {"current_steps": 8510, "total_steps": 14493, "loss": 0.2407, "lr": 3.675179256645885e-05, "epoch": 1.7616780104034575, "percentage": 58.72, "elapsed_time": "14:18:20", "remaining_time": "10:03:27", "throughput": 59058.97, "total_tokens": 3041562368} |
| {"current_steps": 8520, "total_steps": 14493, "loss": 0.2443, "lr": 3.674186850056181e-05, "epoch": 1.7637483501979763, "percentage": 58.79, "elapsed_time": "14:19:10", "remaining_time": "10:02:20", "throughput": 59069.72, "total_tokens": 3045091840} |
| {"current_steps": 8530, "total_steps": 14493, "loss": 0.2415, "lr": 3.67319524696953e-05, "epoch": 1.765818689992495, "percentage": 58.86, "elapsed_time": "14:19:57", "remaining_time": "10:01:09", "throughput": 59085.96, "total_tokens": 3048685056} |
| {"current_steps": 8540, "total_steps": 14493, "loss": 0.2433, "lr": 3.6722044463022536e-05, "epoch": 1.7678890297870138, "percentage": 58.92, "elapsed_time": "14:20:44", "remaining_time": "9:59:59", "throughput": 59099.3, "total_tokens": 3052143104} |
| {"current_steps": 8550, "total_steps": 14493, "loss": 0.2436, "lr": 3.6712144469727214e-05, "epoch": 1.7699593695815325, "percentage": 58.99, "elapsed_time": "14:21:32", "remaining_time": "9:58:50", "throughput": 59111.53, "total_tokens": 3055617280} |
| {"current_steps": 8560, "total_steps": 14493, "loss": 0.2423, "lr": 3.67022524790134e-05, "epoch": 1.7720297093760513, "percentage": 59.06, "elapsed_time": "14:22:20", "remaining_time": "9:57:41", "throughput": 59124.29, "total_tokens": 3059138176} |
| {"current_steps": 8570, "total_steps": 14493, "loss": 0.2417, "lr": 3.6692368480105546e-05, "epoch": 1.77410004917057, "percentage": 59.13, "elapsed_time": "14:23:14", "remaining_time": "9:56:36", "throughput": 59133.09, "total_tokens": 3062743680} |
| {"current_steps": 8580, "total_steps": 14493, "loss": 0.2449, "lr": 3.6682492462248374e-05, "epoch": 1.776170388965089, "percentage": 59.2, "elapsed_time": "14:24:05", "remaining_time": "9:55:29", "throughput": 59144.39, "total_tokens": 3066344448} |
| {"current_steps": 8590, "total_steps": 14493, "loss": 0.2415, "lr": 3.667262441470689e-05, "epoch": 1.7782407287596076, "percentage": 59.27, "elapsed_time": "14:24:52", "remaining_time": "9:54:19", "throughput": 59158.81, "total_tokens": 3069871360} |
| {"current_steps": 8600, "total_steps": 14493, "loss": 0.2405, "lr": 3.6662764326766255e-05, "epoch": 1.7803110685541266, "percentage": 59.34, "elapsed_time": "14:25:41", "remaining_time": "9:53:11", "throughput": 59171.12, "total_tokens": 3073431296} |
| {"current_steps": 8610, "total_steps": 14493, "loss": 0.2434, "lr": 3.665291218773185e-05, "epoch": 1.7823814083486451, "percentage": 59.41, "elapsed_time": "14:26:30", "remaining_time": "9:52:03", "throughput": 59185.06, "total_tokens": 3077049088} |
| {"current_steps": 8620, "total_steps": 14493, "loss": 0.2403, "lr": 3.664306798692912e-05, "epoch": 1.784451748143164, "percentage": 59.48, "elapsed_time": "14:27:18", "remaining_time": "9:50:55", "throughput": 59198.09, "total_tokens": 3080582016} |
| {"current_steps": 8630, "total_steps": 14493, "loss": 0.2436, "lr": 3.6633231713703576e-05, "epoch": 1.7865220879376826, "percentage": 59.55, "elapsed_time": "14:28:07", "remaining_time": "9:49:47", "throughput": 59210.86, "total_tokens": 3084170496} |
| {"current_steps": 8640, "total_steps": 14493, "loss": 0.2423, "lr": 3.6623403357420745e-05, "epoch": 1.7885924277322016, "percentage": 59.61, "elapsed_time": "14:28:59", "remaining_time": "9:48:40", "throughput": 59221.71, "total_tokens": 3087791744} |
| {"current_steps": 8650, "total_steps": 14493, "loss": 0.2424, "lr": 3.661358290746611e-05, "epoch": 1.7906627675267204, "percentage": 59.68, "elapsed_time": "14:29:50", "remaining_time": "9:47:34", "throughput": 59232.04, "total_tokens": 3091361152} |
| {"current_steps": 8660, "total_steps": 14493, "loss": 0.2433, "lr": 3.6603770353245056e-05, "epoch": 1.7927331073212391, "percentage": 59.75, "elapsed_time": "14:30:40", "remaining_time": "9:46:27", "throughput": 59243.77, "total_tokens": 3094944000} |
| {"current_steps": 8670, "total_steps": 14493, "loss": 0.2431, "lr": 3.659396568418286e-05, "epoch": 1.794803447115758, "percentage": 59.82, "elapsed_time": "14:31:28", "remaining_time": "9:45:18", "throughput": 59257.52, "total_tokens": 3098469120} |
| {"current_steps": 8680, "total_steps": 14493, "loss": 0.2406, "lr": 3.658416888972459e-05, "epoch": 1.7968737869102767, "percentage": 59.89, "elapsed_time": "14:32:18", "remaining_time": "9:44:10", "throughput": 59270.51, "total_tokens": 3102102272} |
| {"current_steps": 8690, "total_steps": 14493, "loss": 0.2414, "lr": 3.6574379959335106e-05, "epoch": 1.7989441267047954, "percentage": 59.96, "elapsed_time": "14:33:06", "remaining_time": "9:43:02", "throughput": 59284.31, "total_tokens": 3105721088} |
| {"current_steps": 8700, "total_steps": 14493, "loss": 0.2428, "lr": 3.6564598882498976e-05, "epoch": 1.8010144664993142, "percentage": 60.03, "elapsed_time": "14:33:54", "remaining_time": "9:41:54", "throughput": 59299.22, "total_tokens": 3109334016} |
| {"current_steps": 8710, "total_steps": 14493, "loss": 0.2428, "lr": 3.655482564872043e-05, "epoch": 1.803084806293833, "percentage": 60.1, "elapsed_time": "14:34:44", "remaining_time": "9:40:46", "throughput": 59311.79, "total_tokens": 3112943872} |
| {"current_steps": 8720, "total_steps": 14493, "loss": 0.2422, "lr": 3.654506024752336e-05, "epoch": 1.8051551460883517, "percentage": 60.17, "elapsed_time": "14:35:35", "remaining_time": "9:39:40", "throughput": 59322.75, "total_tokens": 3116569216} |
| {"current_steps": 8730, "total_steps": 14493, "loss": 0.2408, "lr": 3.653530266845121e-05, "epoch": 1.8072254858828707, "percentage": 60.24, "elapsed_time": "14:36:24", "remaining_time": "9:38:33", "throughput": 59335.63, "total_tokens": 3120163200} |
| {"current_steps": 8740, "total_steps": 14493, "loss": 0.2405, "lr": 3.652555290106696e-05, "epoch": 1.8092958256773892, "percentage": 60.3, "elapsed_time": "14:37:12", "remaining_time": "9:37:24", "throughput": 59349.05, "total_tokens": 3123674624} |
| {"current_steps": 8750, "total_steps": 14493, "loss": 0.2423, "lr": 3.6515810934953084e-05, "epoch": 1.8113661654719082, "percentage": 60.37, "elapsed_time": "14:38:03", "remaining_time": "9:36:18", "throughput": 59360.23, "total_tokens": 3127282688} |
| {"current_steps": 8760, "total_steps": 14493, "loss": 0.2428, "lr": 3.650607675971151e-05, "epoch": 1.8134365052664267, "percentage": 60.44, "elapsed_time": "14:38:51", "remaining_time": "9:35:09", "throughput": 59374.47, "total_tokens": 3130876416} |
| {"current_steps": 8770, "total_steps": 14493, "loss": 0.2422, "lr": 3.649635036496351e-05, "epoch": 1.8155068450609457, "percentage": 60.51, "elapsed_time": "14:39:37", "remaining_time": "9:34:01", "throughput": 59388.34, "total_tokens": 3134393856} |
| {"current_steps": 8780, "total_steps": 14493, "loss": 0.2425, "lr": 3.6486631740349746e-05, "epoch": 1.8175771848554643, "percentage": 60.58, "elapsed_time": "14:40:29", "remaining_time": "9:32:55", "throughput": 59398.31, "total_tokens": 3137991936} |
| {"current_steps": 8790, "total_steps": 14493, "loss": 0.2427, "lr": 3.647692087553018e-05, "epoch": 1.8196475246499833, "percentage": 60.65, "elapsed_time": "14:41:17", "remaining_time": "9:31:47", "throughput": 59411.87, "total_tokens": 3141558144} |
| {"current_steps": 8800, "total_steps": 14493, "loss": 0.2431, "lr": 3.6467217760184005e-05, "epoch": 1.8217178644445018, "percentage": 60.72, "elapsed_time": "14:42:05", "remaining_time": "9:30:39", "throughput": 59424.63, "total_tokens": 3145066752} |
| {"current_steps": 8810, "total_steps": 14493, "loss": 0.2428, "lr": 3.6457522384009625e-05, "epoch": 1.8237882042390208, "percentage": 60.79, "elapsed_time": "14:42:52", "remaining_time": "9:29:30", "throughput": 59438.57, "total_tokens": 3148634752} |
| {"current_steps": 8820, "total_steps": 14493, "loss": 0.2416, "lr": 3.644783473672462e-05, "epoch": 1.8258585440335395, "percentage": 60.86, "elapsed_time": "14:43:41", "remaining_time": "9:28:23", "throughput": 59450.92, "total_tokens": 3152198528} |
| {"current_steps": 8830, "total_steps": 14493, "loss": 0.2428, "lr": 3.643815480806568e-05, "epoch": 1.8279288838280583, "percentage": 60.93, "elapsed_time": "14:44:30", "remaining_time": "9:27:15", "throughput": 59463.06, "total_tokens": 3155719040} |
| {"current_steps": 8840, "total_steps": 14493, "loss": 0.2451, "lr": 3.6428482587788555e-05, "epoch": 1.829999223622577, "percentage": 60.99, "elapsed_time": "14:45:19", "remaining_time": "9:26:08", "throughput": 59475.14, "total_tokens": 3159294848} |
| {"current_steps": 8850, "total_steps": 14493, "loss": 0.2431, "lr": 3.641881806566803e-05, "epoch": 1.8320695634170958, "percentage": 61.06, "elapsed_time": "14:46:06", "remaining_time": "9:25:00", "throughput": 59488.02, "total_tokens": 3162761984} |
| {"current_steps": 8860, "total_steps": 14493, "loss": 0.2413, "lr": 3.640916123149788e-05, "epoch": 1.8341399032116146, "percentage": 61.13, "elapsed_time": "14:46:52", "remaining_time": "9:23:51", "throughput": 59501.71, "total_tokens": 3166260352} |
| {"current_steps": 8870, "total_steps": 14493, "loss": 0.2409, "lr": 3.639951207509079e-05, "epoch": 1.8362102430061333, "percentage": 61.2, "elapsed_time": "14:47:39", "remaining_time": "9:22:42", "throughput": 59516.03, "total_tokens": 3169789184} |
| {"current_steps": 8880, "total_steps": 14493, "loss": 0.2415, "lr": 3.6389870586278333e-05, "epoch": 1.8382805828006523, "percentage": 61.27, "elapsed_time": "14:48:27", "remaining_time": "9:21:35", "throughput": 59528.91, "total_tokens": 3173335296} |
| {"current_steps": 8890, "total_steps": 14493, "loss": 0.2421, "lr": 3.6380236754910965e-05, "epoch": 1.8403509225951709, "percentage": 61.34, "elapsed_time": "14:49:18", "remaining_time": "9:20:29", "throughput": 59539.99, "total_tokens": 3176971648} |
| {"current_steps": 8900, "total_steps": 14493, "loss": 0.242, "lr": 3.6370610570857897e-05, "epoch": 1.8424212623896898, "percentage": 61.41, "elapsed_time": "14:50:05", "remaining_time": "9:19:21", "throughput": 59552.64, "total_tokens": 3180451200} |
| {"current_steps": 8910, "total_steps": 14493, "loss": 0.2438, "lr": 3.6360992024007114e-05, "epoch": 1.8444916021842084, "percentage": 61.48, "elapsed_time": "14:50:54", "remaining_time": "9:18:14", "throughput": 59564.57, "total_tokens": 3183976064} |
| {"current_steps": 8920, "total_steps": 14493, "loss": 0.2402, "lr": 3.6351381104265304e-05, "epoch": 1.8465619419787274, "percentage": 61.55, "elapsed_time": "14:51:44", "remaining_time": "9:17:08", "throughput": 59574.95, "total_tokens": 3187517824} |
| {"current_steps": 8930, "total_steps": 14493, "loss": 0.2412, "lr": 3.634177780155783e-05, "epoch": 1.848632281773246, "percentage": 61.62, "elapsed_time": "14:52:32", "remaining_time": "9:16:00", "throughput": 59587.48, "total_tokens": 3191029120} |
| {"current_steps": 8940, "total_steps": 14493, "loss": 0.2422, "lr": 3.633218210582867e-05, "epoch": 1.8507026215677649, "percentage": 61.68, "elapsed_time": "14:53:19", "remaining_time": "9:14:52", "throughput": 59599.94, "total_tokens": 3194536576} |
| {"current_steps": 8950, "total_steps": 14493, "loss": 0.2399, "lr": 3.6322594007040376e-05, "epoch": 1.8527729613622834, "percentage": 61.75, "elapsed_time": "14:54:08", "remaining_time": "9:13:46", "throughput": 59611.64, "total_tokens": 3198096512} |
| {"current_steps": 8960, "total_steps": 14493, "loss": 0.2433, "lr": 3.631301349517403e-05, "epoch": 1.8548433011568024, "percentage": 61.82, "elapsed_time": "14:54:56", "remaining_time": "9:12:38", "throughput": 59625.22, "total_tokens": 3201680768} |
| {"current_steps": 8970, "total_steps": 14493, "loss": 0.2418, "lr": 3.6303440560229216e-05, "epoch": 1.8569136409513212, "percentage": 61.89, "elapsed_time": "14:55:43", "remaining_time": "9:11:30", "throughput": 59638.24, "total_tokens": 3205157120} |
| {"current_steps": 8980, "total_steps": 14493, "loss": 0.2418, "lr": 3.629387519222395e-05, "epoch": 1.85898398074584, "percentage": 61.96, "elapsed_time": "14:56:30", "remaining_time": "9:10:23", "throughput": 59651.8, "total_tokens": 3208725504} |
| {"current_steps": 8990, "total_steps": 14493, "loss": 0.2397, "lr": 3.628431738119464e-05, "epoch": 1.8610543205403587, "percentage": 62.03, "elapsed_time": "14:57:21", "remaining_time": "9:09:17", "throughput": 59664.28, "total_tokens": 3212390912} |
| {"current_steps": 9000, "total_steps": 14493, "loss": 0.2433, "lr": 3.62747671171961e-05, "epoch": 1.8631246603348774, "percentage": 62.1, "elapsed_time": "14:58:11", "remaining_time": "9:08:11", "throughput": 59676.05, "total_tokens": 3216019840} |
| {"current_steps": 9010, "total_steps": 14493, "loss": 0.2424, "lr": 3.626522439030138e-05, "epoch": 1.8651950001293962, "percentage": 62.17, "elapsed_time": "14:58:59", "remaining_time": "9:07:04", "throughput": 59688.93, "total_tokens": 3219575040} |
| {"current_steps": 9020, "total_steps": 14493, "loss": 0.2424, "lr": 3.6255689190601863e-05, "epoch": 1.867265339923915, "percentage": 62.24, "elapsed_time": "14:59:47", "remaining_time": "9:05:57", "throughput": 59701.42, "total_tokens": 3223128064} |
| {"current_steps": 9030, "total_steps": 14493, "loss": 0.2406, "lr": 3.624616150820714e-05, "epoch": 1.869335679718434, "percentage": 62.31, "elapsed_time": "15:00:36", "remaining_time": "9:04:51", "throughput": 59712.71, "total_tokens": 3226676224} |
| {"current_steps": 9040, "total_steps": 14493, "loss": 0.2421, "lr": 3.623664133324499e-05, "epoch": 1.8714060195129525, "percentage": 62.37, "elapsed_time": "15:01:26", "remaining_time": "9:03:45", "throughput": 59724.71, "total_tokens": 3230300672} |
| {"current_steps": 9050, "total_steps": 14493, "loss": 0.2435, "lr": 3.622712865586131e-05, "epoch": 1.8734763593074715, "percentage": 62.44, "elapsed_time": "15:02:18", "remaining_time": "9:02:41", "throughput": 59734.61, "total_tokens": 3233970432} |
| {"current_steps": 9060, "total_steps": 14493, "loss": 0.2409, "lr": 3.621762346622014e-05, "epoch": 1.87554669910199, "percentage": 62.51, "elapsed_time": "15:03:09", "remaining_time": "9:01:35", "throughput": 59745.85, "total_tokens": 3237616768} |
| {"current_steps": 9070, "total_steps": 14493, "loss": 0.2429, "lr": 3.620812575450352e-05, "epoch": 1.877617038896509, "percentage": 62.58, "elapsed_time": "15:03:58", "remaining_time": "9:00:29", "throughput": 59758.63, "total_tokens": 3241240448} |
| {"current_steps": 9080, "total_steps": 14493, "loss": 0.2415, "lr": 3.6198635510911556e-05, "epoch": 1.8796873786910275, "percentage": 62.65, "elapsed_time": "15:04:50", "remaining_time": "8:59:24", "throughput": 59768.75, "total_tokens": 3244864384} |
| {"current_steps": 9090, "total_steps": 14493, "loss": 0.2432, "lr": 3.618915272566228e-05, "epoch": 1.8817577184855465, "percentage": 62.72, "elapsed_time": "15:05:37", "remaining_time": "8:58:17", "throughput": 59782.06, "total_tokens": 3248398080} |
| {"current_steps": 9100, "total_steps": 14493, "loss": 0.2457, "lr": 3.6179677388991694e-05, "epoch": 1.883828058280065, "percentage": 62.79, "elapsed_time": "15:06:25", "remaining_time": "8:57:10", "throughput": 59793.41, "total_tokens": 3251905408} |
| {"current_steps": 9110, "total_steps": 14493, "loss": 0.2411, "lr": 3.617020949115366e-05, "epoch": 1.885898398074584, "percentage": 62.86, "elapsed_time": "15:07:14", "remaining_time": "8:56:04", "throughput": 59805.58, "total_tokens": 3255483392} |
| {"current_steps": 9120, "total_steps": 14493, "loss": 0.2403, "lr": 3.6160749022419886e-05, "epoch": 1.8879687378691028, "percentage": 62.93, "elapsed_time": "15:08:03", "remaining_time": "8:54:58", "throughput": 59817.28, "total_tokens": 3259033216} |
| {"current_steps": 9130, "total_steps": 14493, "loss": 0.2403, "lr": 3.6151295973079887e-05, "epoch": 1.8900390776636216, "percentage": 63.0, "elapsed_time": "15:08:53", "remaining_time": "8:53:52", "throughput": 59827.66, "total_tokens": 3262584192} |
| {"current_steps": 9140, "total_steps": 14493, "loss": 0.2431, "lr": 3.6141850333440934e-05, "epoch": 1.8921094174581403, "percentage": 63.06, "elapsed_time": "15:09:40", "remaining_time": "8:52:46", "throughput": 59839.65, "total_tokens": 3266100864} |
| {"current_steps": 9150, "total_steps": 14493, "loss": 0.2423, "lr": 3.613241209382803e-05, "epoch": 1.894179757252659, "percentage": 63.13, "elapsed_time": "15:10:29", "remaining_time": "8:51:39", "throughput": 59852.28, "total_tokens": 3269680640} |
| {"current_steps": 9160, "total_steps": 14493, "loss": 0.2441, "lr": 3.6122981244583834e-05, "epoch": 1.8962500970471778, "percentage": 63.2, "elapsed_time": "15:11:18", "remaining_time": "8:50:33", "throughput": 59863.15, "total_tokens": 3273215744} |
| {"current_steps": 9170, "total_steps": 14493, "loss": 0.2403, "lr": 3.6113557776068644e-05, "epoch": 1.8983204368416966, "percentage": 63.27, "elapsed_time": "15:12:07", "remaining_time": "8:49:28", "throughput": 59875.29, "total_tokens": 3276828928} |
| {"current_steps": 9180, "total_steps": 14493, "loss": 0.2427, "lr": 3.6104141678660386e-05, "epoch": 1.9003907766362156, "percentage": 63.34, "elapsed_time": "15:12:56", "remaining_time": "8:48:22", "throughput": 59886.67, "total_tokens": 3280357632} |
| {"current_steps": 9190, "total_steps": 14493, "loss": 0.242, "lr": 3.6094732942754487e-05, "epoch": 1.9024611164307341, "percentage": 63.41, "elapsed_time": "15:13:49", "remaining_time": "8:47:18", "throughput": 59894.82, "total_tokens": 3283981184} |
| {"current_steps": 9200, "total_steps": 14493, "loss": 0.2414, "lr": 3.60853315587639e-05, "epoch": 1.904531456225253, "percentage": 63.48, "elapsed_time": "15:14:37", "remaining_time": "8:46:12", "throughput": 59906.81, "total_tokens": 3287550976} |
| {"current_steps": 9210, "total_steps": 14493, "loss": 0.2427, "lr": 3.607593751711909e-05, "epoch": 1.9066017960197716, "percentage": 63.55, "elapsed_time": "15:15:27", "remaining_time": "8:45:07", "throughput": 59917.44, "total_tokens": 3291128064} |
| {"current_steps": 9220, "total_steps": 14493, "loss": 0.2427, "lr": 3.60665508082679e-05, "epoch": 1.9086721358142906, "percentage": 63.62, "elapsed_time": "15:16:14", "remaining_time": "8:44:00", "throughput": 59927.91, "total_tokens": 3294508544} |
| {"current_steps": 9230, "total_steps": 14493, "loss": 0.2432, "lr": 3.6057171422675585e-05, "epoch": 1.9107424756088092, "percentage": 63.69, "elapsed_time": "15:17:02", "remaining_time": "8:42:54", "throughput": 59939.64, "total_tokens": 3298055040} |
| {"current_steps": 9240, "total_steps": 14493, "loss": 0.2407, "lr": 3.604779935082474e-05, "epoch": 1.9128128154033281, "percentage": 63.75, "elapsed_time": "15:17:53", "remaining_time": "8:41:49", "throughput": 59950.09, "total_tokens": 3301646464} |
| {"current_steps": 9250, "total_steps": 14493, "loss": 0.2443, "lr": 3.603843458321526e-05, "epoch": 1.9148831551978467, "percentage": 63.82, "elapsed_time": "15:18:42", "remaining_time": "8:40:44", "throughput": 59961.12, "total_tokens": 3305225472} |
| {"current_steps": 9260, "total_steps": 14493, "loss": 0.241, "lr": 3.6029077110364355e-05, "epoch": 1.9169534949923657, "percentage": 63.89, "elapsed_time": "15:19:32", "remaining_time": "8:39:38", "throughput": 59972.17, "total_tokens": 3308794112} |
| {"current_steps": 9270, "total_steps": 14493, "loss": 0.2399, "lr": 3.60197269228064e-05, "epoch": 1.9190238347868844, "percentage": 63.96, "elapsed_time": "15:20:19", "remaining_time": "8:38:32", "throughput": 59984.3, "total_tokens": 3312314240} |
| {"current_steps": 9280, "total_steps": 14493, "loss": 0.2405, "lr": 3.601038401109299e-05, "epoch": 1.9210941745814032, "percentage": 64.03, "elapsed_time": "15:21:05", "remaining_time": "8:37:25", "throughput": 59997.67, "total_tokens": 3315809792} |
| {"current_steps": 9290, "total_steps": 14493, "loss": 0.2382, "lr": 3.6001048365792846e-05, "epoch": 1.923164514375922, "percentage": 64.1, "elapsed_time": "15:21:57", "remaining_time": "8:36:21", "throughput": 60007.12, "total_tokens": 3319414656} |
| {"current_steps": 9300, "total_steps": 14493, "loss": 0.2403, "lr": 3.599171997749182e-05, "epoch": 1.9252348541704407, "percentage": 64.17, "elapsed_time": "15:22:48", "remaining_time": "8:35:17", "throughput": 60017.22, "total_tokens": 3323079808} |
| {"current_steps": 9310, "total_steps": 14493, "loss": 0.2412, "lr": 3.598239883679281e-05, "epoch": 1.9273051939649595, "percentage": 64.24, "elapsed_time": "15:23:38", "remaining_time": "8:34:12", "throughput": 60028.51, "total_tokens": 3326708352} |
| {"current_steps": 9320, "total_steps": 14493, "loss": 0.2416, "lr": 3.597308493431576e-05, "epoch": 1.9293755337594782, "percentage": 64.31, "elapsed_time": "15:24:27", "remaining_time": "8:33:07", "throughput": 60038.85, "total_tokens": 3330231680} |
| {"current_steps": 9330, "total_steps": 14493, "loss": 0.2397, "lr": 3.596377826069758e-05, "epoch": 1.931445873553997, "percentage": 64.38, "elapsed_time": "15:25:18", "remaining_time": "8:32:02", "throughput": 60048.53, "total_tokens": 3333815680} |
| {"current_steps": 9340, "total_steps": 14493, "loss": 0.2418, "lr": 3.5954478806592155e-05, "epoch": 1.9335162133485158, "percentage": 64.44, "elapsed_time": "15:26:07", "remaining_time": "8:30:57", "throughput": 60060.09, "total_tokens": 3337383808} |
| {"current_steps": 9350, "total_steps": 14493, "loss": 0.2431, "lr": 3.594518656267024e-05, "epoch": 1.9355865531430347, "percentage": 64.51, "elapsed_time": "15:26:56", "remaining_time": "8:29:51", "throughput": 60071.39, "total_tokens": 3340950400} |
| {"current_steps": 9360, "total_steps": 14493, "loss": 0.2411, "lr": 3.5935901519619496e-05, "epoch": 1.9376568929375533, "percentage": 64.58, "elapsed_time": "15:27:46", "remaining_time": "8:28:47", "throughput": 60082.91, "total_tokens": 3344601728} |
| {"current_steps": 9370, "total_steps": 14493, "loss": 0.241, "lr": 3.5926623668144385e-05, "epoch": 1.9397272327320723, "percentage": 64.65, "elapsed_time": "15:28:33", "remaining_time": "8:27:41", "throughput": 60094.66, "total_tokens": 3348107264} |
| {"current_steps": 9380, "total_steps": 14493, "loss": 0.2406, "lr": 3.5917352998966194e-05, "epoch": 1.9417975725265908, "percentage": 64.72, "elapsed_time": "15:29:24", "remaining_time": "8:26:37", "throughput": 60105.12, "total_tokens": 3351732224} |
| {"current_steps": 9390, "total_steps": 14493, "loss": 0.2412, "lr": 3.5908089502822914e-05, "epoch": 1.9438679123211098, "percentage": 64.79, "elapsed_time": "15:30:10", "remaining_time": "8:25:30", "throughput": 60117.92, "total_tokens": 3355201024} |
| {"current_steps": 9400, "total_steps": 14493, "loss": 0.2409, "lr": 3.589883317046929e-05, "epoch": 1.9459382521156283, "percentage": 64.86, "elapsed_time": "15:30:58", "remaining_time": "8:24:24", "throughput": 60128.96, "total_tokens": 3358720512} |
| {"current_steps": 9410, "total_steps": 14493, "loss": 0.2409, "lr": 3.5889583992676715e-05, "epoch": 1.9480085919101473, "percentage": 64.93, "elapsed_time": "15:31:45", "remaining_time": "8:23:18", "throughput": 60141.18, "total_tokens": 3362222848} |
| {"current_steps": 9420, "total_steps": 14493, "loss": 0.2427, "lr": 3.5880341960233244e-05, "epoch": 1.950078931704666, "percentage": 65.0, "elapsed_time": "15:32:35", "remaining_time": "8:22:13", "throughput": 60152.46, "total_tokens": 3365834240} |
| {"current_steps": 9430, "total_steps": 14493, "loss": 0.2404, "lr": 3.58711070639435e-05, "epoch": 1.9521492714991848, "percentage": 65.07, "elapsed_time": "15:33:26", "remaining_time": "8:21:10", "throughput": 60161.65, "total_tokens": 3369467776} |
| {"current_steps": 9440, "total_steps": 14493, "loss": 0.24, "lr": 3.586187929462869e-05, "epoch": 1.9542196112937036, "percentage": 65.13, "elapsed_time": "15:34:14", "remaining_time": "8:20:04", "throughput": 60173.99, "total_tokens": 3373022592} |
| {"current_steps": 9450, "total_steps": 14493, "loss": 0.2398, "lr": 3.585265864312651e-05, "epoch": 1.9562899510882223, "percentage": 65.2, "elapsed_time": "15:35:05", "remaining_time": "8:19:00", "throughput": 60183.81, "total_tokens": 3376652928} |
| {"current_steps": 9460, "total_steps": 14493, "loss": 0.2415, "lr": 3.584344510029118e-05, "epoch": 1.958360290882741, "percentage": 65.27, "elapsed_time": "15:35:52", "remaining_time": "8:17:54", "throughput": 60195.52, "total_tokens": 3380149632} |
| {"current_steps": 9470, "total_steps": 14493, "loss": 0.2441, "lr": 3.583423865699333e-05, "epoch": 1.9604306306772599, "percentage": 65.34, "elapsed_time": "15:36:40", "remaining_time": "8:16:49", "throughput": 60207.45, "total_tokens": 3383705088} |
| {"current_steps": 9480, "total_steps": 14493, "loss": 0.2416, "lr": 3.5825039304119994e-05, "epoch": 1.9625009704717786, "percentage": 65.41, "elapsed_time": "15:37:32", "remaining_time": "8:15:45", "throughput": 60217.63, "total_tokens": 3387363328} |
| {"current_steps": 9490, "total_steps": 14493, "loss": 0.243, "lr": 3.581584703257461e-05, "epoch": 1.9645713102662974, "percentage": 65.48, "elapsed_time": "15:38:21", "remaining_time": "8:14:41", "throughput": 60228.23, "total_tokens": 3390930688} |
| {"current_steps": 9500, "total_steps": 14493, "loss": 0.2417, "lr": 3.580666183327689e-05, "epoch": 1.9666416500608164, "percentage": 65.55, "elapsed_time": "15:39:09", "remaining_time": "8:13:36", "throughput": 60240.43, "total_tokens": 3394545408} |
| {"current_steps": 9510, "total_steps": 14493, "loss": 0.2398, "lr": 3.5797483697162906e-05, "epoch": 1.968711989855335, "percentage": 65.62, "elapsed_time": "15:39:59", "remaining_time": "8:12:32", "throughput": 60250.87, "total_tokens": 3398137472} |
| {"current_steps": 9520, "total_steps": 14493, "loss": 0.2401, "lr": 3.5788312615184936e-05, "epoch": 1.970782329649854, "percentage": 65.69, "elapsed_time": "15:40:48", "remaining_time": "8:11:27", "throughput": 60261.04, "total_tokens": 3401660416} |
| {"current_steps": 9530, "total_steps": 14493, "loss": 0.2398, "lr": 3.5779148578311476e-05, "epoch": 1.9728526694443724, "percentage": 65.76, "elapsed_time": "15:41:34", "remaining_time": "8:10:21", "throughput": 60273.15, "total_tokens": 3405101440} |
| {"current_steps": 9540, "total_steps": 14493, "loss": 0.2412, "lr": 3.5769991577527236e-05, "epoch": 1.9749230092388914, "percentage": 65.82, "elapsed_time": "15:42:29", "remaining_time": "8:09:19", "throughput": 60279.06, "total_tokens": 3408727552} |
| {"current_steps": 9550, "total_steps": 14493, "loss": 0.2406, "lr": 3.5760841603833034e-05, "epoch": 1.97699334903341, "percentage": 65.89, "elapsed_time": "15:43:18", "remaining_time": "8:08:14", "throughput": 60290.49, "total_tokens": 3412340736} |
| {"current_steps": 9560, "total_steps": 14493, "loss": 0.2427, "lr": 3.5751698648245814e-05, "epoch": 1.979063688827929, "percentage": 65.96, "elapsed_time": "15:44:09", "remaining_time": "8:07:11", "throughput": 60300.93, "total_tokens": 3416036736} |
| {"current_steps": 9570, "total_steps": 14493, "loss": 0.2414, "lr": 3.574256270179857e-05, "epoch": 1.9811340286224477, "percentage": 66.03, "elapsed_time": "15:45:00", "remaining_time": "8:06:07", "throughput": 60311.07, "total_tokens": 3419646848} |
| {"current_steps": 9580, "total_steps": 14493, "loss": 0.2427, "lr": 3.573343375554037e-05, "epoch": 1.9832043684169665, "percentage": 66.1, "elapsed_time": "15:45:49", "remaining_time": "8:05:03", "throughput": 60321.68, "total_tokens": 3423223040} |
| {"current_steps": 9590, "total_steps": 14493, "loss": 0.2392, "lr": 3.572431180053621e-05, "epoch": 1.9852747082114852, "percentage": 66.17, "elapsed_time": "15:46:42", "remaining_time": "8:04:00", "throughput": 60329.48, "total_tokens": 3426869504} |
| {"current_steps": 9600, "total_steps": 14493, "loss": 0.241, "lr": 3.571519682786711e-05, "epoch": 1.987345048006004, "percentage": 66.24, "elapsed_time": "15:47:30", "remaining_time": "8:02:55", "throughput": 60339.95, "total_tokens": 3430354688} |
| {"current_steps": 9610, "total_steps": 14493, "loss": 0.2415, "lr": 3.570608882862996e-05, "epoch": 1.9894153878005227, "percentage": 66.31, "elapsed_time": "15:48:19", "remaining_time": "8:01:51", "throughput": 60349.94, "total_tokens": 3433896576} |
| {"current_steps": 9620, "total_steps": 14493, "loss": 0.2396, "lr": 3.569698779393757e-05, "epoch": 1.9914857275950415, "percentage": 66.38, "elapsed_time": "15:49:06", "remaining_time": "8:00:46", "throughput": 60362.49, "total_tokens": 3437435904} |
| {"current_steps": 9630, "total_steps": 14493, "loss": 0.2401, "lr": 3.568789371491859e-05, "epoch": 1.9935560673895603, "percentage": 66.45, "elapsed_time": "15:49:57", "remaining_time": "7:59:42", "throughput": 60372.86, "total_tokens": 3441108608} |
| {"current_steps": 9640, "total_steps": 14493, "loss": 0.2392, "lr": 3.567880658271748e-05, "epoch": 1.995626407184079, "percentage": 66.51, "elapsed_time": "15:50:46", "remaining_time": "7:58:38", "throughput": 60385.09, "total_tokens": 3444741376} |
| {"current_steps": 9650, "total_steps": 14493, "loss": 0.2393, "lr": 3.566972638849445e-05, "epoch": 1.997696746978598, "percentage": 66.58, "elapsed_time": "15:51:36", "remaining_time": "7:57:34", "throughput": 60395.57, "total_tokens": 3448381440} |
| {"current_steps": 9660, "total_steps": 14493, "loss": 0.2396, "lr": 3.566065312342551e-05, "epoch": 1.9997670867731165, "percentage": 66.65, "elapsed_time": "15:52:25", "remaining_time": "7:56:30", "throughput": 60407.3, "total_tokens": 3451983872} |
| {"current_steps": 9670, "total_steps": 14493, "loss": 0.229, "lr": 3.565158677870231e-05, "epoch": 2.001656271835615, "percentage": 66.72, "elapsed_time": "15:53:09", "remaining_time": "7:55:23", "throughput": 60416.63, "total_tokens": 3455174784} |
| {"current_steps": 9680, "total_steps": 14493, "loss": 0.2311, "lr": 3.564252734553221e-05, "epoch": 2.003726611630134, "percentage": 66.79, "elapsed_time": "15:54:00", "remaining_time": "7:54:20", "throughput": 60424.95, "total_tokens": 3458759168} |
| {"current_steps": 9690, "total_steps": 14493, "loss": 0.2293, "lr": 3.563347481513818e-05, "epoch": 2.0057969514246525, "percentage": 66.86, "elapsed_time": "15:54:50", "remaining_time": "7:53:17", "throughput": 60434.85, "total_tokens": 3462372864} |
| {"current_steps": 9700, "total_steps": 14493, "loss": 0.2279, "lr": 3.56244291787588e-05, "epoch": 2.0078672912191715, "percentage": 66.93, "elapsed_time": "15:55:42", "remaining_time": "7:52:14", "throughput": 60444.04, "total_tokens": 3466011392} |
| {"current_steps": 9710, "total_steps": 14493, "loss": 0.2251, "lr": 3.5615390427648216e-05, "epoch": 2.00993763101369, "percentage": 67.0, "elapsed_time": "15:56:30", "remaining_time": "7:51:09", "throughput": 60455.23, "total_tokens": 3469548544} |
| {"current_steps": 9720, "total_steps": 14493, "loss": 0.2263, "lr": 3.5606358553076075e-05, "epoch": 2.012007970808209, "percentage": 67.07, "elapsed_time": "15:57:19", "remaining_time": "7:50:05", "throughput": 60466.3, "total_tokens": 3473171072} |
| {"current_steps": 9730, "total_steps": 14493, "loss": 0.2286, "lr": 3.5597333546327526e-05, "epoch": 2.0140783106027276, "percentage": 67.14, "elapsed_time": "15:58:07", "remaining_time": "7:49:00", "throughput": 60478.35, "total_tokens": 3476735744} |
| {"current_steps": 9740, "total_steps": 14493, "loss": 0.227, "lr": 3.5588315398703186e-05, "epoch": 2.0161486503972466, "percentage": 67.2, "elapsed_time": "15:58:55", "remaining_time": "7:47:56", "throughput": 60488.26, "total_tokens": 3480196864} |
| {"current_steps": 9750, "total_steps": 14493, "loss": 0.2288, "lr": 3.557930410151907e-05, "epoch": 2.018218990191765, "percentage": 67.27, "elapsed_time": "15:59:43", "remaining_time": "7:46:52", "throughput": 60498.87, "total_tokens": 3483753472} |
| {"current_steps": 9760, "total_steps": 14493, "loss": 0.2281, "lr": 3.5570299646106606e-05, "epoch": 2.020289329986284, "percentage": 67.34, "elapsed_time": "16:00:31", "remaining_time": "7:45:47", "throughput": 60509.73, "total_tokens": 3487289472} |
| {"current_steps": 9770, "total_steps": 14493, "loss": 0.2285, "lr": 3.556130202381253e-05, "epoch": 2.0223596697808026, "percentage": 67.41, "elapsed_time": "16:01:25", "remaining_time": "7:44:46", "throughput": 60516.91, "total_tokens": 3490973056} |
| {"current_steps": 9780, "total_steps": 14493, "loss": 0.2287, "lr": 3.555231122599892e-05, "epoch": 2.0244300095753216, "percentage": 67.48, "elapsed_time": "16:02:15", "remaining_time": "7:43:42", "throughput": 60527.81, "total_tokens": 3494582400} |
| {"current_steps": 9790, "total_steps": 14493, "loss": 0.2277, "lr": 3.554332724404313e-05, "epoch": 2.02650034936984, "percentage": 67.55, "elapsed_time": "16:03:04", "remaining_time": "7:42:38", "throughput": 60538.7, "total_tokens": 3498178048} |
| {"current_steps": 9800, "total_steps": 14493, "loss": 0.2298, "lr": 3.553435006933777e-05, "epoch": 2.028570689164359, "percentage": 67.62, "elapsed_time": "16:03:53", "remaining_time": "7:41:35", "throughput": 60549.89, "total_tokens": 3501792768} |
| {"current_steps": 9810, "total_steps": 14493, "loss": 0.2286, "lr": 3.5525379693290626e-05, "epoch": 2.0306410289588777, "percentage": 67.69, "elapsed_time": "16:04:41", "remaining_time": "7:40:31", "throughput": 60560.49, "total_tokens": 3505348224} |
| {"current_steps": 9820, "total_steps": 14493, "loss": 0.228, "lr": 3.551641610732469e-05, "epoch": 2.0327113687533966, "percentage": 67.76, "elapsed_time": "16:05:30", "remaining_time": "7:39:27", "throughput": 60570.38, "total_tokens": 3508883328} |
| {"current_steps": 9830, "total_steps": 14493, "loss": 0.2279, "lr": 3.55074593028781e-05, "epoch": 2.0347817085479156, "percentage": 67.83, "elapsed_time": "16:06:21", "remaining_time": "7:38:24", "throughput": 60579.58, "total_tokens": 3512516224} |
| {"current_steps": 9840, "total_steps": 14493, "loss": 0.2295, "lr": 3.5498509271404065e-05, "epoch": 2.036852048342434, "percentage": 67.89, "elapsed_time": "16:07:13", "remaining_time": "7:37:22", "throughput": 60588.15, "total_tokens": 3516168064} |
| {"current_steps": 9850, "total_steps": 14493, "loss": 0.2298, "lr": 3.5489566004370893e-05, "epoch": 2.038922388136953, "percentage": 67.96, "elapsed_time": "16:08:00", "remaining_time": "7:36:17", "throughput": 60600.19, "total_tokens": 3519705728} |
| {"current_steps": 9860, "total_steps": 14493, "loss": 0.2289, "lr": 3.548062949326194e-05, "epoch": 2.0409927279314717, "percentage": 68.03, "elapsed_time": "16:08:47", "remaining_time": "7:35:13", "throughput": 60611.75, "total_tokens": 3523238016} |
| {"current_steps": 9870, "total_steps": 14493, "loss": 0.2301, "lr": 3.547169972957554e-05, "epoch": 2.0430630677259907, "percentage": 68.1, "elapsed_time": "16:09:38", "remaining_time": "7:34:10", "throughput": 60619.92, "total_tokens": 3526767232} |
| {"current_steps": 9880, "total_steps": 14493, "loss": 0.2263, "lr": 3.5462776704825e-05, "epoch": 2.045133407520509, "percentage": 68.17, "elapsed_time": "16:10:28", "remaining_time": "7:33:07", "throughput": 60629.62, "total_tokens": 3530369664} |
| {"current_steps": 9890, "total_steps": 14493, "loss": 0.2239, "lr": 3.5453860410538594e-05, "epoch": 2.047203747315028, "percentage": 68.24, "elapsed_time": "16:11:15", "remaining_time": "7:32:02", "throughput": 60641.79, "total_tokens": 3533943040} |
| {"current_steps": 9900, "total_steps": 14493, "loss": 0.2294, "lr": 3.5444950838259455e-05, "epoch": 2.0492740871095467, "percentage": 68.31, "elapsed_time": "16:12:06", "remaining_time": "7:30:59", "throughput": 60652.52, "total_tokens": 3537622528} |
| {"current_steps": 9910, "total_steps": 14493, "loss": 0.2309, "lr": 3.543604797954563e-05, "epoch": 2.0513444269040657, "percentage": 68.38, "elapsed_time": "16:12:55", "remaining_time": "7:29:56", "throughput": 60662.05, "total_tokens": 3541196544} |
| {"current_steps": 9920, "total_steps": 14493, "loss": 0.228, "lr": 3.542715182596996e-05, "epoch": 2.0534147666985842, "percentage": 68.45, "elapsed_time": "16:13:46", "remaining_time": "7:28:53", "throughput": 60671.53, "total_tokens": 3544825472} |
| {"current_steps": 9930, "total_steps": 14493, "loss": 0.2265, "lr": 3.5418262369120115e-05, "epoch": 2.0554851064931032, "percentage": 68.52, "elapsed_time": "16:14:35", "remaining_time": "7:27:50", "throughput": 60681.1, "total_tokens": 3548347520} |
| {"current_steps": 9940, "total_steps": 14493, "loss": 0.229, "lr": 3.5409379600598526e-05, "epoch": 2.0575554462876218, "percentage": 68.58, "elapsed_time": "16:15:26", "remaining_time": "7:26:47", "throughput": 60691.6, "total_tokens": 3552057088} |
| {"current_steps": 9950, "total_steps": 14493, "loss": 0.2274, "lr": 3.540050351202235e-05, "epoch": 2.0596257860821408, "percentage": 68.65, "elapsed_time": "16:16:12", "remaining_time": "7:25:43", "throughput": 60703.89, "total_tokens": 3555590016} |
| {"current_steps": 9960, "total_steps": 14493, "loss": 0.23, "lr": 3.539163409502347e-05, "epoch": 2.0616961258766593, "percentage": 68.72, "elapsed_time": "16:17:02", "remaining_time": "7:24:40", "throughput": 60712.93, "total_tokens": 3559161216} |
| {"current_steps": 9970, "total_steps": 14493, "loss": 0.2304, "lr": 3.5382771341248416e-05, "epoch": 2.0637664656711783, "percentage": 68.79, "elapsed_time": "16:17:52", "remaining_time": "7:23:37", "throughput": 60722.91, "total_tokens": 3562754432} |
| {"current_steps": 9980, "total_steps": 14493, "loss": 0.229, "lr": 3.537391524235835e-05, "epoch": 2.0658368054656973, "percentage": 68.86, "elapsed_time": "16:18:41", "remaining_time": "7:22:33", "throughput": 60732.82, "total_tokens": 3566292352} |
| {"current_steps": 9990, "total_steps": 14493, "loss": 0.2299, "lr": 3.5365065790029055e-05, "epoch": 2.067907145260216, "percentage": 68.93, "elapsed_time": "16:19:27", "remaining_time": "7:21:29", "throughput": 60745.35, "total_tokens": 3569875584} |
| {"current_steps": 10000, "total_steps": 14493, "loss": 0.2283, "lr": 3.535622297595087e-05, "epoch": 2.069977485054735, "percentage": 69.0, "elapsed_time": "16:20:14", "remaining_time": "7:20:25", "throughput": 60756.59, "total_tokens": 3573371648} |
| {"current_steps": 10000, "total_steps": 14493, "eval_loss": 0.22761163115501404, "epoch": 2.069977485054735, "percentage": 69.0, "elapsed_time": "16:20:15", "remaining_time": "7:20:25", "throughput": 60755.24, "total_tokens": 3573371648} |
| {"current_steps": 10010, "total_steps": 14493, "loss": 0.2277, "lr": 3.534738679182869e-05, "epoch": 2.0720478248492533, "percentage": 69.07, "elapsed_time": "16:21:23", "remaining_time": "7:19:31", "throughput": 60745.23, "total_tokens": 3576878464} |
| {"current_steps": 10020, "total_steps": 14493, "loss": 0.2291, "lr": 3.533855722938188e-05, "epoch": 2.0741181646437723, "percentage": 69.14, "elapsed_time": "16:22:14", "remaining_time": "7:18:28", "throughput": 60753.08, "total_tokens": 3580426624} |
| {"current_steps": 10030, "total_steps": 14493, "loss": 0.2311, "lr": 3.5329734280344325e-05, "epoch": 2.076188504438291, "percentage": 69.21, "elapsed_time": "16:23:03", "remaining_time": "7:17:25", "throughput": 60762.8, "total_tokens": 3583993344} |
| {"current_steps": 10040, "total_steps": 14493, "loss": 0.2257, "lr": 3.5320917936464294e-05, "epoch": 2.07825884423281, "percentage": 69.27, "elapsed_time": "16:23:51", "remaining_time": "7:16:22", "throughput": 60773.92, "total_tokens": 3587597568} |
| {"current_steps": 10050, "total_steps": 14493, "loss": 0.228, "lr": 3.5312108189504505e-05, "epoch": 2.0803291840273284, "percentage": 69.34, "elapsed_time": "16:24:40", "remaining_time": "7:15:19", "throughput": 60783.56, "total_tokens": 3591146880} |
| {"current_steps": 10060, "total_steps": 14493, "loss": 0.229, "lr": 3.530330503124204e-05, "epoch": 2.0823995238218473, "percentage": 69.41, "elapsed_time": "16:25:32", "remaining_time": "7:14:16", "throughput": 60792.61, "total_tokens": 3594805760} |
| {"current_steps": 10070, "total_steps": 14493, "loss": 0.229, "lr": 3.5294508453468325e-05, "epoch": 2.084469863616366, "percentage": 69.48, "elapsed_time": "16:26:21", "remaining_time": "7:13:13", "throughput": 60802.73, "total_tokens": 3598370304} |
| {"current_steps": 10080, "total_steps": 14493, "loss": 0.2265, "lr": 3.528571844798908e-05, "epoch": 2.086540203410885, "percentage": 69.55, "elapsed_time": "16:27:09", "remaining_time": "7:12:10", "throughput": 60812.19, "total_tokens": 3601894400} |
| {"current_steps": 10090, "total_steps": 14493, "loss": 0.2276, "lr": 3.527693500662431e-05, "epoch": 2.0886105432054034, "percentage": 69.62, "elapsed_time": "16:27:59", "remaining_time": "7:11:08", "throughput": 60822.18, "total_tokens": 3605528704} |
| {"current_steps": 10100, "total_steps": 14493, "loss": 0.2254, "lr": 3.5268158121208294e-05, "epoch": 2.0906808829999224, "percentage": 69.69, "elapsed_time": "16:28:48", "remaining_time": "7:10:04", "throughput": 60833.31, "total_tokens": 3609146880} |
| {"current_steps": 10110, "total_steps": 14493, "loss": 0.2265, "lr": 3.525938778358949e-05, "epoch": 2.092751222794441, "percentage": 69.76, "elapsed_time": "16:29:35", "remaining_time": "7:09:01", "throughput": 60844.64, "total_tokens": 3612695040} |
| {"current_steps": 10120, "total_steps": 14493, "loss": 0.2313, "lr": 3.5250623985630537e-05, "epoch": 2.09482156258896, "percentage": 69.83, "elapsed_time": "16:30:26", "remaining_time": "7:07:58", "throughput": 60853.27, "total_tokens": 3616273792} |
| {"current_steps": 10130, "total_steps": 14493, "loss": 0.2297, "lr": 3.524186671920826e-05, "epoch": 2.096891902383479, "percentage": 69.9, "elapsed_time": "16:31:15", "remaining_time": "7:06:56", "throughput": 60863.22, "total_tokens": 3619861376} |
| {"current_steps": 10140, "total_steps": 14493, "loss": 0.2273, "lr": 3.523311597621358e-05, "epoch": 2.0989622421779974, "percentage": 69.96, "elapsed_time": "16:32:03", "remaining_time": "7:05:52", "throughput": 60874.01, "total_tokens": 3623440768} |
| {"current_steps": 10150, "total_steps": 14493, "loss": 0.2294, "lr": 3.5224371748551505e-05, "epoch": 2.1010325819725164, "percentage": 70.03, "elapsed_time": "16:32:53", "remaining_time": "7:04:50", "throughput": 60882.51, "total_tokens": 3626994944} |
| {"current_steps": 10160, "total_steps": 14493, "loss": 0.2261, "lr": 3.521563402814109e-05, "epoch": 2.103102921767035, "percentage": 70.1, "elapsed_time": "16:33:44", "remaining_time": "7:03:48", "throughput": 60892.17, "total_tokens": 3630650880} |
| {"current_steps": 10170, "total_steps": 14493, "loss": 0.2277, "lr": 3.5206902806915436e-05, "epoch": 2.105173261561554, "percentage": 70.17, "elapsed_time": "16:34:32", "remaining_time": "7:02:45", "throughput": 60901.33, "total_tokens": 3634160128} |
| {"current_steps": 10180, "total_steps": 14493, "loss": 0.231, "lr": 3.5198178076821644e-05, "epoch": 2.1072436013560725, "percentage": 70.24, "elapsed_time": "16:35:23", "remaining_time": "7:01:43", "throughput": 60909.37, "total_tokens": 3637745152} |
| {"current_steps": 10190, "total_steps": 14493, "loss": 0.23, "lr": 3.5189459829820743e-05, "epoch": 2.1093139411505915, "percentage": 70.31, "elapsed_time": "16:36:13", "remaining_time": "7:00:40", "throughput": 60919.01, "total_tokens": 3641321088} |
| {"current_steps": 10200, "total_steps": 14493, "loss": 0.2316, "lr": 3.5180748057887714e-05, "epoch": 2.11138428094511, "percentage": 70.38, "elapsed_time": "16:37:03", "remaining_time": "6:59:38", "throughput": 60928.29, "total_tokens": 3644936960} |
| {"current_steps": 10210, "total_steps": 14493, "loss": 0.2309, "lr": 3.517204275301144e-05, "epoch": 2.113454620739629, "percentage": 70.45, "elapsed_time": "16:37:53", "remaining_time": "6:58:36", "throughput": 60937.67, "total_tokens": 3648554368} |
| {"current_steps": 10220, "total_steps": 14493, "loss": 0.2267, "lr": 3.5163343907194676e-05, "epoch": 2.1155249605341475, "percentage": 70.52, "elapsed_time": "16:38:42", "remaining_time": "6:57:33", "throughput": 60946.32, "total_tokens": 3652028544} |
| {"current_steps": 10230, "total_steps": 14493, "loss": 0.2261, "lr": 3.5154651512453995e-05, "epoch": 2.1175953003286665, "percentage": 70.59, "elapsed_time": "16:39:29", "remaining_time": "6:56:30", "throughput": 60957.12, "total_tokens": 3655585024} |
| {"current_steps": 10240, "total_steps": 14493, "loss": 0.2259, "lr": 3.514596556081981e-05, "epoch": 2.119665640123185, "percentage": 70.65, "elapsed_time": "16:40:17", "remaining_time": "6:55:27", "throughput": 60968.21, "total_tokens": 3659145856} |
| {"current_steps": 10250, "total_steps": 14493, "loss": 0.2287, "lr": 3.513728604433628e-05, "epoch": 2.121735979917704, "percentage": 70.72, "elapsed_time": "16:41:06", "remaining_time": "6:54:24", "throughput": 60977.29, "total_tokens": 3662686720} |
| {"current_steps": 10260, "total_steps": 14493, "loss": 0.2288, "lr": 3.5128612955061334e-05, "epoch": 2.1238063197122226, "percentage": 70.79, "elapsed_time": "16:41:55", "remaining_time": "6:53:22", "throughput": 60986.33, "total_tokens": 3666249216} |
| {"current_steps": 10270, "total_steps": 14493, "loss": 0.2289, "lr": 3.5119946285066595e-05, "epoch": 2.1258766595067415, "percentage": 70.86, "elapsed_time": "16:42:45", "remaining_time": "6:52:20", "throughput": 60996.16, "total_tokens": 3669881600} |
| {"current_steps": 10280, "total_steps": 14493, "loss": 0.2283, "lr": 3.511128602643739e-05, "epoch": 2.1279469993012605, "percentage": 70.93, "elapsed_time": "16:43:32", "remaining_time": "6:51:16", "throughput": 61006.69, "total_tokens": 3673388800} |
| {"current_steps": 10290, "total_steps": 14493, "loss": 0.228, "lr": 3.510263217127269e-05, "epoch": 2.130017339095779, "percentage": 71.0, "elapsed_time": "16:44:19", "remaining_time": "6:50:13", "throughput": 61016.98, "total_tokens": 3676875264} |
| {"current_steps": 10300, "total_steps": 14493, "loss": 0.2285, "lr": 3.50939847116851e-05, "epoch": 2.132087678890298, "percentage": 71.07, "elapsed_time": "16:45:06", "remaining_time": "6:49:10", "throughput": 61027.95, "total_tokens": 3680411392} |
| {"current_steps": 10310, "total_steps": 14493, "loss": 0.2305, "lr": 3.508534363980081e-05, "epoch": 2.1341580186848166, "percentage": 71.14, "elapsed_time": "16:45:56", "remaining_time": "6:48:08", "throughput": 61037.61, "total_tokens": 3684043776} |
| {"current_steps": 10320, "total_steps": 14493, "loss": 0.2299, "lr": 3.507670894775958e-05, "epoch": 2.1362283584793356, "percentage": 71.21, "elapsed_time": "16:46:47", "remaining_time": "6:47:06", "throughput": 61046.98, "total_tokens": 3687676416} |
| {"current_steps": 10330, "total_steps": 14493, "loss": 0.2285, "lr": 3.506808062771471e-05, "epoch": 2.138298698273854, "percentage": 71.28, "elapsed_time": "16:47:37", "remaining_time": "6:46:04", "throughput": 61055.79, "total_tokens": 3691309696} |
| {"current_steps": 10340, "total_steps": 14493, "loss": 0.2287, "lr": 3.505945867183298e-05, "epoch": 2.140369038068373, "percentage": 71.34, "elapsed_time": "16:48:26", "remaining_time": "6:45:01", "throughput": 61066.19, "total_tokens": 3694877952} |
| {"current_steps": 10350, "total_steps": 14493, "loss": 0.2298, "lr": 3.505084307229468e-05, "epoch": 2.1424393778628916, "percentage": 71.41, "elapsed_time": "16:49:12", "remaining_time": "6:43:58", "throughput": 61077.06, "total_tokens": 3698346240} |
| {"current_steps": 10360, "total_steps": 14493, "loss": 0.2286, "lr": 3.5042233821293525e-05, "epoch": 2.1445097176574106, "percentage": 71.48, "elapsed_time": "16:49:59", "remaining_time": "6:42:55", "throughput": 61088.37, "total_tokens": 3701933440} |
| {"current_steps": 10370, "total_steps": 14493, "loss": 0.2302, "lr": 3.503363091103664e-05, "epoch": 2.146580057451929, "percentage": 71.55, "elapsed_time": "16:50:49", "remaining_time": "6:41:53", "throughput": 61097.84, "total_tokens": 3705531264} |
| {"current_steps": 10380, "total_steps": 14493, "loss": 0.2271, "lr": 3.5025034333744545e-05, "epoch": 2.148650397246448, "percentage": 71.62, "elapsed_time": "16:51:39", "remaining_time": "6:40:51", "throughput": 61107.74, "total_tokens": 3709181184} |
| {"current_steps": 10390, "total_steps": 14493, "loss": 0.227, "lr": 3.501644408165112e-05, "epoch": 2.1507207370409667, "percentage": 71.69, "elapsed_time": "16:52:27", "remaining_time": "6:39:49", "throughput": 61117.95, "total_tokens": 3712752640} |
| {"current_steps": 10400, "total_steps": 14493, "loss": 0.2279, "lr": 3.500786014700357e-05, "epoch": 2.1527910768354857, "percentage": 71.76, "elapsed_time": "16:53:17", "remaining_time": "6:38:47", "throughput": 61127.24, "total_tokens": 3716370560} |
| {"current_steps": 10410, "total_steps": 14493, "loss": 0.2284, "lr": 3.499928252206237e-05, "epoch": 2.1548614166300046, "percentage": 71.83, "elapsed_time": "16:54:06", "remaining_time": "6:37:45", "throughput": 61136.87, "total_tokens": 3719979008} |
| {"current_steps": 10420, "total_steps": 14493, "loss": 0.2291, "lr": 3.499071119910131e-05, "epoch": 2.156931756424523, "percentage": 71.9, "elapsed_time": "16:54:57", "remaining_time": "6:36:43", "throughput": 61144.97, "total_tokens": 3723578368} |
| {"current_steps": 10430, "total_steps": 14493, "loss": 0.2289, "lr": 3.498214617040739e-05, "epoch": 2.159002096219042, "percentage": 71.97, "elapsed_time": "16:55:45", "remaining_time": "6:35:41", "throughput": 61155.18, "total_tokens": 3727159552} |
| {"current_steps": 10440, "total_steps": 14493, "loss": 0.2281, "lr": 3.49735874282808e-05, "epoch": 2.1610724360135607, "percentage": 72.03, "elapsed_time": "16:56:35", "remaining_time": "6:34:39", "throughput": 61165.24, "total_tokens": 3730814336} |
| {"current_steps": 10450, "total_steps": 14493, "loss": 0.2287, "lr": 3.4965034965034965e-05, "epoch": 2.1631427758080797, "percentage": 72.1, "elapsed_time": "16:57:29", "remaining_time": "6:33:39", "throughput": 61171.25, "total_tokens": 3734489984} |
| {"current_steps": 10460, "total_steps": 14493, "loss": 0.2268, "lr": 3.495648877299642e-05, "epoch": 2.165213115602598, "percentage": 72.17, "elapsed_time": "16:58:17", "remaining_time": "6:32:37", "throughput": 61181.06, "total_tokens": 3738036736} |
| {"current_steps": 10470, "total_steps": 14493, "loss": 0.2272, "lr": 3.494794884450483e-05, "epoch": 2.167283455397117, "percentage": 72.24, "elapsed_time": "16:59:06", "remaining_time": "6:31:35", "throughput": 61190.85, "total_tokens": 3741631360} |
| {"current_steps": 10480, "total_steps": 14493, "loss": 0.2298, "lr": 3.4939415171912954e-05, "epoch": 2.1693537951916357, "percentage": 72.31, "elapsed_time": "16:59:53", "remaining_time": "6:30:32", "throughput": 61200.62, "total_tokens": 3745078656} |
| {"current_steps": 10490, "total_steps": 14493, "loss": 0.2267, "lr": 3.4930887747586616e-05, "epoch": 2.1714241349861547, "percentage": 72.38, "elapsed_time": "17:00:43", "remaining_time": "6:29:30", "throughput": 61210.79, "total_tokens": 3748740864} |
| {"current_steps": 10500, "total_steps": 14493, "loss": 0.2305, "lr": 3.492236656390469e-05, "epoch": 2.1734944747806733, "percentage": 72.45, "elapsed_time": "17:01:32", "remaining_time": "6:28:28", "throughput": 61219.39, "total_tokens": 3752293120} |
| {"current_steps": 10510, "total_steps": 14493, "loss": 0.2298, "lr": 3.4913851613259034e-05, "epoch": 2.1755648145751922, "percentage": 72.52, "elapsed_time": "17:02:21", "remaining_time": "6:27:26", "throughput": 61228.85, "total_tokens": 3755849728} |
| {"current_steps": 10520, "total_steps": 14493, "loss": 0.2289, "lr": 3.490534288805452e-05, "epoch": 2.177635154369711, "percentage": 72.59, "elapsed_time": "17:03:10", "remaining_time": "6:26:24", "throughput": 61238.03, "total_tokens": 3759414016} |
| {"current_steps": 10530, "total_steps": 14493, "loss": 0.2293, "lr": 3.489684038070891e-05, "epoch": 2.1797054941642298, "percentage": 72.66, "elapsed_time": "17:04:01", "remaining_time": "6:25:23", "throughput": 61245.62, "total_tokens": 3762996864} |
| {"current_steps": 10540, "total_steps": 14493, "loss": 0.23, "lr": 3.488834408365296e-05, "epoch": 2.1817758339587483, "percentage": 72.72, "elapsed_time": "17:04:50", "remaining_time": "6:24:21", "throughput": 61254.84, "total_tokens": 3766577152} |
| {"current_steps": 10550, "total_steps": 14493, "loss": 0.2296, "lr": 3.487985398933027e-05, "epoch": 2.1838461737532673, "percentage": 72.79, "elapsed_time": "17:05:38", "remaining_time": "6:23:19", "throughput": 61264.22, "total_tokens": 3770110976} |
| {"current_steps": 10560, "total_steps": 14493, "loss": 0.2277, "lr": 3.4871370090197324e-05, "epoch": 2.1859165135477863, "percentage": 72.86, "elapsed_time": "17:06:28", "remaining_time": "6:22:18", "throughput": 61272.4, "total_tokens": 3773659904} |
| {"current_steps": 10570, "total_steps": 14493, "loss": 0.2295, "lr": 3.486289237872343e-05, "epoch": 2.187986853342305, "percentage": 72.93, "elapsed_time": "17:07:18", "remaining_time": "6:21:16", "throughput": 61281.53, "total_tokens": 3777309952} |
| {"current_steps": 10580, "total_steps": 14493, "loss": 0.2293, "lr": 3.485442084739075e-05, "epoch": 2.190057193136824, "percentage": 73.0, "elapsed_time": "17:08:05", "remaining_time": "6:20:14", "throughput": 61291.31, "total_tokens": 3780801920} |
| {"current_steps": 10590, "total_steps": 14493, "loss": 0.2281, "lr": 3.484595548869416e-05, "epoch": 2.1921275329313423, "percentage": 73.07, "elapsed_time": "17:08:53", "remaining_time": "6:19:12", "throughput": 61301.56, "total_tokens": 3784351360} |
| {"current_steps": 10600, "total_steps": 14493, "loss": 0.2288, "lr": 3.4837496295141335e-05, "epoch": 2.1941978727258613, "percentage": 73.14, "elapsed_time": "17:09:45", "remaining_time": "6:18:11", "throughput": 61309.03, "total_tokens": 3788026240} |
| {"current_steps": 10610, "total_steps": 14493, "loss": 0.2304, "lr": 3.482904325925266e-05, "epoch": 2.19626821252038, "percentage": 73.21, "elapsed_time": "17:10:34", "remaining_time": "6:17:10", "throughput": 61318.36, "total_tokens": 3791619712} |
| {"current_steps": 10620, "total_steps": 14493, "loss": 0.2295, "lr": 3.482059637356124e-05, "epoch": 2.198338552314899, "percentage": 73.28, "elapsed_time": "17:11:24", "remaining_time": "6:16:08", "throughput": 61327.48, "total_tokens": 3795199744} |
| {"current_steps": 10630, "total_steps": 14493, "loss": 0.2282, "lr": 3.481215563061281e-05, "epoch": 2.2004088921094174, "percentage": 73.35, "elapsed_time": "17:12:10", "remaining_time": "6:15:05", "throughput": 61337.66, "total_tokens": 3798661248} |
| {"current_steps": 10640, "total_steps": 14493, "loss": 0.2305, "lr": 3.4803721022965785e-05, "epoch": 2.2024792319039364, "percentage": 73.41, "elapsed_time": "17:12:58", "remaining_time": "6:14:03", "throughput": 61347.76, "total_tokens": 3802230144} |
| {"current_steps": 10650, "total_steps": 14493, "loss": 0.2287, "lr": 3.479529254319117e-05, "epoch": 2.204549571698455, "percentage": 73.48, "elapsed_time": "17:13:47", "remaining_time": "6:13:02", "throughput": 61356.51, "total_tokens": 3805815936} |
| {"current_steps": 10660, "total_steps": 14493, "loss": 0.2292, "lr": 3.478687018387257e-05, "epoch": 2.206619911492974, "percentage": 73.55, "elapsed_time": "17:14:37", "remaining_time": "6:12:01", "throughput": 61365.58, "total_tokens": 3809406464} |
| {"current_steps": 10670, "total_steps": 14493, "loss": 0.2302, "lr": 3.477845393760616e-05, "epoch": 2.2086902512874924, "percentage": 73.62, "elapsed_time": "17:15:25", "remaining_time": "6:10:59", "throughput": 61374.85, "total_tokens": 3812930944} |
| {"current_steps": 10680, "total_steps": 14493, "loss": 0.2288, "lr": 3.4770043797000614e-05, "epoch": 2.2107605910820114, "percentage": 73.69, "elapsed_time": "17:16:13", "remaining_time": "6:09:57", "throughput": 61384.04, "total_tokens": 3816475264} |
| {"current_steps": 10690, "total_steps": 14493, "loss": 0.2294, "lr": 3.4761639754677146e-05, "epoch": 2.21283093087653, "percentage": 73.76, "elapsed_time": "17:17:02", "remaining_time": "6:08:55", "throughput": 61393.81, "total_tokens": 3820085632} |
| {"current_steps": 10700, "total_steps": 14493, "loss": 0.2284, "lr": 3.4753241803269435e-05, "epoch": 2.214901270671049, "percentage": 73.83, "elapsed_time": "17:17:51", "remaining_time": "6:07:54", "throughput": 61402.75, "total_tokens": 3823644672} |
| {"current_steps": 10710, "total_steps": 14493, "loss": 0.2275, "lr": 3.474484993542361e-05, "epoch": 2.2169716104655675, "percentage": 73.9, "elapsed_time": "17:18:41", "remaining_time": "6:06:53", "throughput": 61411.3, "total_tokens": 3827226624} |
| {"current_steps": 10720, "total_steps": 14493, "loss": 0.2265, "lr": 3.473646414379822e-05, "epoch": 2.2190419502600864, "percentage": 73.97, "elapsed_time": "17:19:31", "remaining_time": "6:05:52", "throughput": 61418.28, "total_tokens": 3830763776} |
| {"current_steps": 10730, "total_steps": 14493, "loss": 0.2301, "lr": 3.472808442106422e-05, "epoch": 2.221112290054605, "percentage": 74.04, "elapsed_time": "17:20:20", "remaining_time": "6:04:50", "throughput": 61427.13, "total_tokens": 3834340608} |
| {"current_steps": 10740, "total_steps": 14493, "loss": 0.232, "lr": 3.4719710759904936e-05, "epoch": 2.223182629849124, "percentage": 74.1, "elapsed_time": "17:21:10", "remaining_time": "6:03:49", "throughput": 61435.29, "total_tokens": 3837874176} |
| {"current_steps": 10750, "total_steps": 14493, "loss": 0.2331, "lr": 3.471134315301603e-05, "epoch": 2.225252969643643, "percentage": 74.17, "elapsed_time": "17:22:01", "remaining_time": "6:02:49", "throughput": 61442.68, "total_tokens": 3841507712} |
| {"current_steps": 10760, "total_steps": 14493, "loss": 0.2273, "lr": 3.470298159310549e-05, "epoch": 2.2273233094381615, "percentage": 74.24, "elapsed_time": "17:22:46", "remaining_time": "6:01:46", "throughput": 61453.31, "total_tokens": 3844926336} |
| {"current_steps": 10770, "total_steps": 14493, "loss": 0.2281, "lr": 3.4694626072893585e-05, "epoch": 2.2293936492326805, "percentage": 74.31, "elapsed_time": "17:23:37", "remaining_time": "6:00:45", "throughput": 61461.29, "total_tokens": 3848577152} |
| {"current_steps": 10780, "total_steps": 14493, "loss": 0.231, "lr": 3.468627658511285e-05, "epoch": 2.231463989027199, "percentage": 74.38, "elapsed_time": "17:24:26", "remaining_time": "5:59:44", "throughput": 61469.02, "total_tokens": 3852067968} |
| {"current_steps": 10790, "total_steps": 14493, "loss": 0.2307, "lr": 3.467793312250806e-05, "epoch": 2.233534328821718, "percentage": 74.45, "elapsed_time": "17:25:19", "remaining_time": "5:58:44", "throughput": 61475.42, "total_tokens": 3855698048} |
| {"current_steps": 10800, "total_steps": 14493, "loss": 0.2281, "lr": 3.466959567783619e-05, "epoch": 2.2356046686162365, "percentage": 74.52, "elapsed_time": "17:26:09", "remaining_time": "5:57:43", "throughput": 61484.58, "total_tokens": 3859345280} |
| {"current_steps": 10810, "total_steps": 14493, "loss": 0.2287, "lr": 3.466126424386642e-05, "epoch": 2.2376750084107555, "percentage": 74.59, "elapsed_time": "17:27:02", "remaining_time": "5:56:43", "throughput": 61492.74, "total_tokens": 3863102976} |
| {"current_steps": 10820, "total_steps": 14493, "loss": 0.2298, "lr": 3.4652938813380056e-05, "epoch": 2.239745348205274, "percentage": 74.66, "elapsed_time": "17:27:50", "remaining_time": "5:55:42", "throughput": 61501.2, "total_tokens": 3866618752} |
| {"current_steps": 10830, "total_steps": 14493, "loss": 0.2285, "lr": 3.464461937917057e-05, "epoch": 2.241815687999793, "percentage": 74.73, "elapsed_time": "17:28:40", "remaining_time": "5:54:41", "throughput": 61510.48, "total_tokens": 3870257280} |
| {"current_steps": 10840, "total_steps": 14493, "loss": 0.2282, "lr": 3.4636305934043525e-05, "epoch": 2.2438860277943116, "percentage": 74.79, "elapsed_time": "17:29:26", "remaining_time": "5:53:39", "throughput": 61520.97, "total_tokens": 3873769216} |
| {"current_steps": 10850, "total_steps": 14493, "loss": 0.2284, "lr": 3.4627998470816544e-05, "epoch": 2.2459563675888305, "percentage": 74.86, "elapsed_time": "17:30:14", "remaining_time": "5:52:37", "throughput": 61531.28, "total_tokens": 3877383296} |
| {"current_steps": 10860, "total_steps": 14493, "loss": 0.229, "lr": 3.4619696982319334e-05, "epoch": 2.248026707383349, "percentage": 74.93, "elapsed_time": "17:31:05", "remaining_time": "5:51:37", "throughput": 61539.3, "total_tokens": 3881023104} |
| {"current_steps": 10870, "total_steps": 14493, "loss": 0.2287, "lr": 3.461140146139361e-05, "epoch": 2.250097047177868, "percentage": 75.0, "elapsed_time": "17:31:52", "remaining_time": "5:50:35", "throughput": 61549.89, "total_tokens": 3884567680} |
| {"current_steps": 10880, "total_steps": 14493, "loss": 0.2297, "lr": 3.460311190089309e-05, "epoch": 2.2521673869723866, "percentage": 75.07, "elapsed_time": "17:32:41", "remaining_time": "5:49:34", "throughput": 61559.28, "total_tokens": 3888158336} |
| {"current_steps": 10890, "total_steps": 14493, "loss": 0.2303, "lr": 3.459482829368348e-05, "epoch": 2.2542377267669056, "percentage": 75.14, "elapsed_time": "17:33:28", "remaining_time": "5:48:32", "throughput": 61569.01, "total_tokens": 3891672576} |
| {"current_steps": 10900, "total_steps": 14493, "loss": 0.2282, "lr": 3.4586550632642425e-05, "epoch": 2.2563080665614246, "percentage": 75.21, "elapsed_time": "17:34:17", "remaining_time": "5:47:31", "throughput": 61577.31, "total_tokens": 3895234944} |
| {"current_steps": 10910, "total_steps": 14493, "loss": 0.2287, "lr": 3.457827891065949e-05, "epoch": 2.258378406355943, "percentage": 75.28, "elapsed_time": "17:35:07", "remaining_time": "5:46:31", "throughput": 61585.41, "total_tokens": 3898848640} |
| {"current_steps": 10920, "total_steps": 14493, "loss": 0.2317, "lr": 3.457001312063614e-05, "epoch": 2.260448746150462, "percentage": 75.35, "elapsed_time": "17:35:57", "remaining_time": "5:45:30", "throughput": 61594.24, "total_tokens": 3902434304} |
| {"current_steps": 10930, "total_steps": 14493, "loss": 0.2285, "lr": 3.45617532554857e-05, "epoch": 2.2625190859449806, "percentage": 75.42, "elapsed_time": "17:36:46", "remaining_time": "5:44:29", "throughput": 61602.24, "total_tokens": 3905980288} |
| {"current_steps": 10940, "total_steps": 14493, "loss": 0.2285, "lr": 3.455349930813339e-05, "epoch": 2.2645894257394996, "percentage": 75.48, "elapsed_time": "17:37:38", "remaining_time": "5:43:29", "throughput": 61608.83, "total_tokens": 3909626880} |
| {"current_steps": 10950, "total_steps": 14493, "loss": 0.2292, "lr": 3.45452512715162e-05, "epoch": 2.266659765534018, "percentage": 75.55, "elapsed_time": "17:38:25", "remaining_time": "5:42:27", "throughput": 61619.27, "total_tokens": 3913141248} |
| {"current_steps": 10960, "total_steps": 14493, "loss": 0.2301, "lr": 3.4537009138582935e-05, "epoch": 2.268730105328537, "percentage": 75.62, "elapsed_time": "17:39:14", "remaining_time": "5:41:26", "throughput": 61628.36, "total_tokens": 3916737536} |
| {"current_steps": 10970, "total_steps": 14493, "loss": 0.2271, "lr": 3.4528772902294174e-05, "epoch": 2.2708004451230557, "percentage": 75.69, "elapsed_time": "17:40:05", "remaining_time": "5:40:26", "throughput": 61635.55, "total_tokens": 3920368896} |
| {"current_steps": 10980, "total_steps": 14493, "loss": 0.2291, "lr": 3.452054255562222e-05, "epoch": 2.2728707849175747, "percentage": 75.76, "elapsed_time": "17:40:56", "remaining_time": "5:39:26", "throughput": 61643.17, "total_tokens": 3924016000} |
| {"current_steps": 10990, "total_steps": 14493, "loss": 0.2299, "lr": 3.451231809155115e-05, "epoch": 2.274941124712093, "percentage": 75.83, "elapsed_time": "17:41:45", "remaining_time": "5:38:25", "throughput": 61652.42, "total_tokens": 3927591552} |
| {"current_steps": 11000, "total_steps": 14493, "loss": 0.2306, "lr": 3.450409950307666e-05, "epoch": 2.277011464506612, "percentage": 75.9, "elapsed_time": "17:42:36", "remaining_time": "5:37:25", "throughput": 61659.82, "total_tokens": 3931202048} |
| {"current_steps": 11010, "total_steps": 14493, "loss": 0.2283, "lr": 3.449588678320619e-05, "epoch": 2.279081804301131, "percentage": 75.97, "elapsed_time": "17:43:27", "remaining_time": "5:36:25", "throughput": 61667.1, "total_tokens": 3934836736} |
| {"current_steps": 11020, "total_steps": 14493, "loss": 0.2283, "lr": 3.4487679924958767e-05, "epoch": 2.2811521440956497, "percentage": 76.04, "elapsed_time": "17:44:14", "remaining_time": "5:35:24", "throughput": 61677.36, "total_tokens": 3938392704} |
| {"current_steps": 11030, "total_steps": 14493, "loss": 0.2266, "lr": 3.4479478921365076e-05, "epoch": 2.2832224838901682, "percentage": 76.11, "elapsed_time": "17:45:02", "remaining_time": "5:34:23", "throughput": 61686.75, "total_tokens": 3941953152} |
| {"current_steps": 11040, "total_steps": 14493, "loss": 0.2276, "lr": 3.447128376546738e-05, "epoch": 2.2852928236846872, "percentage": 76.17, "elapsed_time": "17:45:48", "remaining_time": "5:33:21", "throughput": 61697.78, "total_tokens": 3945496576} |
| {"current_steps": 11050, "total_steps": 14493, "loss": 0.2298, "lr": 3.4463094450319505e-05, "epoch": 2.287363163479206, "percentage": 76.24, "elapsed_time": "17:46:36", "remaining_time": "5:32:20", "throughput": 61706.76, "total_tokens": 3949007360} |
| {"current_steps": 11060, "total_steps": 14493, "loss": 0.2296, "lr": 3.4454910968986855e-05, "epoch": 2.2894335032737247, "percentage": 76.31, "elapsed_time": "17:47:22", "remaining_time": "5:31:18", "throughput": 61717.31, "total_tokens": 3952543232} |
| {"current_steps": 11070, "total_steps": 14493, "loss": 0.2294, "lr": 3.4446733314546336e-05, "epoch": 2.2915038430682437, "percentage": 76.38, "elapsed_time": "17:48:12", "remaining_time": "5:30:18", "throughput": 61725.46, "total_tokens": 3956154496} |
| {"current_steps": 11080, "total_steps": 14493, "loss": 0.2313, "lr": 3.443856148008633e-05, "epoch": 2.2935741828627623, "percentage": 76.45, "elapsed_time": "17:49:04", "remaining_time": "5:29:18", "throughput": 61731.39, "total_tokens": 3959711488} |
| {"current_steps": 11090, "total_steps": 14493, "loss": 0.2311, "lr": 3.443039545870672e-05, "epoch": 2.2956445226572813, "percentage": 76.52, "elapsed_time": "17:49:50", "remaining_time": "5:28:17", "throughput": 61740.77, "total_tokens": 3963163136} |
| {"current_steps": 11100, "total_steps": 14493, "loss": 0.2283, "lr": 3.442223524351883e-05, "epoch": 2.2977148624518, "percentage": 76.59, "elapsed_time": "17:50:38", "remaining_time": "5:27:16", "throughput": 61748.91, "total_tokens": 3966647552} |
| {"current_steps": 11110, "total_steps": 14493, "loss": 0.2302, "lr": 3.44140808276454e-05, "epoch": 2.2997852022463188, "percentage": 76.66, "elapsed_time": "17:51:26", "remaining_time": "5:26:15", "throughput": 61758.08, "total_tokens": 3970224384} |
| {"current_steps": 11120, "total_steps": 14493, "loss": 0.2282, "lr": 3.4405932204220575e-05, "epoch": 2.3018555420408373, "percentage": 76.73, "elapsed_time": "17:52:14", "remaining_time": "5:25:14", "throughput": 61767.13, "total_tokens": 3973758976} |
| {"current_steps": 11130, "total_steps": 14493, "loss": 0.2311, "lr": 3.4397789366389876e-05, "epoch": 2.3039258818353563, "percentage": 76.8, "elapsed_time": "17:53:03", "remaining_time": "5:24:13", "throughput": 61776.69, "total_tokens": 3977388544} |
| {"current_steps": 11140, "total_steps": 14493, "loss": 0.23, "lr": 3.438965230731016e-05, "epoch": 2.305996221629875, "percentage": 76.86, "elapsed_time": "17:53:48", "remaining_time": "5:23:12", "throughput": 61786.66, "total_tokens": 3980850688} |
| {"current_steps": 11150, "total_steps": 14493, "loss": 0.2288, "lr": 3.438152102014964e-05, "epoch": 2.308066561424394, "percentage": 76.93, "elapsed_time": "17:54:37", "remaining_time": "5:22:11", "throughput": 61795.46, "total_tokens": 3984395264} |
| {"current_steps": 11160, "total_steps": 14493, "loss": 0.2284, "lr": 3.437339549808778e-05, "epoch": 2.310136901218913, "percentage": 77.0, "elapsed_time": "17:55:26", "remaining_time": "5:21:11", "throughput": 61804.15, "total_tokens": 3987983872} |
| {"current_steps": 11170, "total_steps": 14493, "loss": 0.2279, "lr": 3.43652757343154e-05, "epoch": 2.3122072410134313, "percentage": 77.07, "elapsed_time": "17:56:16", "remaining_time": "5:20:10", "throughput": 61812.07, "total_tokens": 3991591296} |
| {"current_steps": 11180, "total_steps": 14493, "loss": 0.2297, "lr": 3.435716172203449e-05, "epoch": 2.31427758080795, "percentage": 77.14, "elapsed_time": "17:57:05", "remaining_time": "5:19:10", "throughput": 61820.26, "total_tokens": 3995176576} |
| {"current_steps": 11190, "total_steps": 14493, "loss": 0.2291, "lr": 3.434905345445833e-05, "epoch": 2.316347920602469, "percentage": 77.21, "elapsed_time": "17:57:53", "remaining_time": "5:18:09", "throughput": 61828.96, "total_tokens": 3998687616} |
| {"current_steps": 11200, "total_steps": 14493, "loss": 0.2291, "lr": 3.4340950924811374e-05, "epoch": 2.318418260396988, "percentage": 77.28, "elapsed_time": "17:58:40", "remaining_time": "5:17:09", "throughput": 61838.53, "total_tokens": 4002230272} |
| {"current_steps": 11210, "total_steps": 14493, "loss": 0.2269, "lr": 3.433285412632927e-05, "epoch": 2.3204886001915064, "percentage": 77.35, "elapsed_time": "17:59:26", "remaining_time": "5:16:07", "throughput": 61848.53, "total_tokens": 4005740288} |
| {"current_steps": 11220, "total_steps": 14493, "loss": 0.2271, "lr": 3.4324763052258835e-05, "epoch": 2.3225589399860254, "percentage": 77.42, "elapsed_time": "18:00:18", "remaining_time": "5:15:08", "throughput": 61855.95, "total_tokens": 4009427968} |
| {"current_steps": 11230, "total_steps": 14493, "loss": 0.2284, "lr": 3.4316677695858003e-05, "epoch": 2.324629279780544, "percentage": 77.49, "elapsed_time": "18:01:07", "remaining_time": "5:14:07", "throughput": 61863.85, "total_tokens": 4012959104} |
| {"current_steps": 11240, "total_steps": 14493, "loss": 0.2291, "lr": 3.430859805039583e-05, "epoch": 2.326699619575063, "percentage": 77.55, "elapsed_time": "18:01:55", "remaining_time": "5:13:07", "throughput": 61874.22, "total_tokens": 4016571648} |
| {"current_steps": 11250, "total_steps": 14493, "loss": 0.231, "lr": 3.430052410915246e-05, "epoch": 2.3287699593695814, "percentage": 77.62, "elapsed_time": "18:02:44", "remaining_time": "5:12:06", "throughput": 61883.26, "total_tokens": 4020184704} |
| {"current_steps": 11260, "total_steps": 14493, "loss": 0.2293, "lr": 3.4292455865419086e-05, "epoch": 2.3308402991641004, "percentage": 77.69, "elapsed_time": "18:03:31", "remaining_time": "5:11:06", "throughput": 61892.36, "total_tokens": 4023738368} |
| {"current_steps": 11270, "total_steps": 14493, "loss": 0.229, "lr": 3.4284393312497973e-05, "epoch": 2.332910638958619, "percentage": 77.76, "elapsed_time": "18:04:20", "remaining_time": "5:10:06", "throughput": 61900.21, "total_tokens": 4027276544} |
| {"current_steps": 11280, "total_steps": 14493, "loss": 0.2316, "lr": 3.427633644370238e-05, "epoch": 2.334980978753138, "percentage": 77.83, "elapsed_time": "18:05:11", "remaining_time": "5:09:06", "throughput": 61906.72, "total_tokens": 4030833024} |
| {"current_steps": 11290, "total_steps": 14493, "loss": 0.2281, "lr": 3.4268285252356564e-05, "epoch": 2.3370513185476565, "percentage": 77.9, "elapsed_time": "18:05:59", "remaining_time": "5:08:05", "throughput": 61915.31, "total_tokens": 4034375424} |
| {"current_steps": 11300, "total_steps": 14493, "loss": 0.2302, "lr": 3.426023973179575e-05, "epoch": 2.3391216583421754, "percentage": 77.97, "elapsed_time": "18:06:45", "remaining_time": "5:07:04", "throughput": 61923.95, "total_tokens": 4037775744} |
| {"current_steps": 11310, "total_steps": 14493, "loss": 0.2283, "lr": 3.425219987536614e-05, "epoch": 2.3411919981366944, "percentage": 78.04, "elapsed_time": "18:07:31", "remaining_time": "5:06:03", "throughput": 61933.87, "total_tokens": 4041276160} |
| {"current_steps": 11320, "total_steps": 14493, "loss": 0.2315, "lr": 3.4244165676424815e-05, "epoch": 2.343262337931213, "percentage": 78.11, "elapsed_time": "18:08:20", "remaining_time": "5:05:03", "throughput": 61942.15, "total_tokens": 4044844416} |
| {"current_steps": 11330, "total_steps": 14493, "loss": 0.2318, "lr": 3.423613712833979e-05, "epoch": 2.3453326777257315, "percentage": 78.18, "elapsed_time": "18:09:09", "remaining_time": "5:04:03", "throughput": 61950.27, "total_tokens": 4048437376} |
| {"current_steps": 11340, "total_steps": 14493, "loss": 0.2279, "lr": 3.422811422448995e-05, "epoch": 2.3474030175202505, "percentage": 78.24, "elapsed_time": "18:09:58", "remaining_time": "5:03:03", "throughput": 61958.46, "total_tokens": 4051975680} |
| {"current_steps": 11350, "total_steps": 14493, "loss": 0.2255, "lr": 3.422009695826503e-05, "epoch": 2.3494733573147695, "percentage": 78.31, "elapsed_time": "18:10:45", "remaining_time": "5:02:02", "throughput": 61966.84, "total_tokens": 4055463168} |
| {"current_steps": 11360, "total_steps": 14493, "loss": 0.2305, "lr": 3.4212085323065626e-05, "epoch": 2.351543697109288, "percentage": 78.38, "elapsed_time": "18:11:32", "remaining_time": "5:01:02", "throughput": 61976.64, "total_tokens": 4059026688} |
| {"current_steps": 11370, "total_steps": 14493, "loss": 0.2293, "lr": 3.4204079312303103e-05, "epoch": 2.353614036903807, "percentage": 78.45, "elapsed_time": "18:12:23", "remaining_time": "5:00:02", "throughput": 61985.01, "total_tokens": 4062736128} |
| {"current_steps": 11380, "total_steps": 14493, "loss": 0.2295, "lr": 3.419607891939964e-05, "epoch": 2.3556843766983255, "percentage": 78.52, "elapsed_time": "18:13:12", "remaining_time": "4:59:02", "throughput": 61993.42, "total_tokens": 4066275456} |
| {"current_steps": 11390, "total_steps": 14493, "loss": 0.2314, "lr": 3.4188084137788166e-05, "epoch": 2.3577547164928445, "percentage": 78.59, "elapsed_time": "18:13:59", "remaining_time": "4:58:02", "throughput": 62002.69, "total_tokens": 4069850880} |
| {"current_steps": 11400, "total_steps": 14493, "loss": 0.2277, "lr": 3.418009496091238e-05, "epoch": 2.359825056287363, "percentage": 78.66, "elapsed_time": "18:14:45", "remaining_time": "4:57:01", "throughput": 62012.1, "total_tokens": 4073278976} |
| {"current_steps": 11410, "total_steps": 14493, "loss": 0.2309, "lr": 3.417211138222666e-05, "epoch": 2.361895396081882, "percentage": 78.73, "elapsed_time": "18:15:35", "remaining_time": "4:56:01", "throughput": 62019.73, "total_tokens": 4076869376} |
| {"current_steps": 11420, "total_steps": 14493, "loss": 0.2294, "lr": 3.416413339519612e-05, "epoch": 2.3639657358764006, "percentage": 78.8, "elapsed_time": "18:16:20", "remaining_time": "4:55:00", "throughput": 62030.07, "total_tokens": 4080374528} |
| {"current_steps": 11430, "total_steps": 14493, "loss": 0.2287, "lr": 3.4156160993296524e-05, "epoch": 2.3660360756709196, "percentage": 78.87, "elapsed_time": "18:17:10", "remaining_time": "4:54:01", "throughput": 62037.88, "total_tokens": 4083975168} |
| {"current_steps": 11440, "total_steps": 14493, "loss": 0.2306, "lr": 3.4148194170014295e-05, "epoch": 2.368106415465438, "percentage": 78.93, "elapsed_time": "18:18:00", "remaining_time": "4:53:01", "throughput": 62045.29, "total_tokens": 4087592192} |
| {"current_steps": 11450, "total_steps": 14493, "loss": 0.2311, "lr": 3.4140232918846484e-05, "epoch": 2.370176755259957, "percentage": 79.0, "elapsed_time": "18:18:48", "remaining_time": "4:52:01", "throughput": 62054.42, "total_tokens": 4091126016} |
| {"current_steps": 11460, "total_steps": 14493, "loss": 0.2295, "lr": 3.4132277233300753e-05, "epoch": 2.372247095054476, "percentage": 79.07, "elapsed_time": "18:19:37", "remaining_time": "4:51:01", "throughput": 62062.31, "total_tokens": 4094697216} |
| {"current_steps": 11470, "total_steps": 14493, "loss": 0.2295, "lr": 3.4124327106895356e-05, "epoch": 2.3743174348489946, "percentage": 79.14, "elapsed_time": "18:20:22", "remaining_time": "4:50:00", "throughput": 62071.27, "total_tokens": 4098084480} |
| {"current_steps": 11480, "total_steps": 14493, "loss": 0.2273, "lr": 3.4116382533159097e-05, "epoch": 2.376387774643513, "percentage": 79.21, "elapsed_time": "18:21:14", "remaining_time": "4:49:01", "throughput": 62077.12, "total_tokens": 4101687040} |
| {"current_steps": 11490, "total_steps": 14493, "loss": 0.2291, "lr": 3.4108443505631335e-05, "epoch": 2.378458114438032, "percentage": 79.28, "elapsed_time": "18:22:03", "remaining_time": "4:48:01", "throughput": 62085.12, "total_tokens": 4105302912} |
| {"current_steps": 11500, "total_steps": 14493, "loss": 0.2275, "lr": 3.410051001786192e-05, "epoch": 2.380528454232551, "percentage": 79.35, "elapsed_time": "18:22:53", "remaining_time": "4:47:02", "throughput": 62093.07, "total_tokens": 4108918912} |
| {"current_steps": 11510, "total_steps": 14493, "loss": 0.2278, "lr": 3.409258206341124e-05, "epoch": 2.3825987940270696, "percentage": 79.42, "elapsed_time": "18:23:44", "remaining_time": "4:46:03", "throughput": 62100.54, "total_tokens": 4112603520} |
| {"current_steps": 11520, "total_steps": 14493, "loss": 0.2282, "lr": 3.4084659635850134e-05, "epoch": 2.3846691338215886, "percentage": 79.49, "elapsed_time": "18:24:35", "remaining_time": "4:45:03", "throughput": 62108.06, "total_tokens": 4116241664} |
| {"current_steps": 11530, "total_steps": 14493, "loss": 0.228, "lr": 3.40767427287599e-05, "epoch": 2.386739473616107, "percentage": 79.56, "elapsed_time": "18:25:21", "remaining_time": "4:44:03", "throughput": 62116.41, "total_tokens": 4119672448} |
| {"current_steps": 11540, "total_steps": 14493, "loss": 0.2275, "lr": 3.406883133573224e-05, "epoch": 2.388809813410626, "percentage": 79.62, "elapsed_time": "18:26:13", "remaining_time": "4:43:04", "throughput": 62123.33, "total_tokens": 4123360000} |
| {"current_steps": 11550, "total_steps": 14493, "loss": 0.2256, "lr": 3.406092545036932e-05, "epoch": 2.3908801532051447, "percentage": 79.69, "elapsed_time": "18:27:04", "remaining_time": "4:42:05", "throughput": 62130.14, "total_tokens": 4126977024} |
| {"current_steps": 11560, "total_steps": 14493, "loss": 0.2297, "lr": 3.405302506628365e-05, "epoch": 2.3929504929996637, "percentage": 79.76, "elapsed_time": "18:27:53", "remaining_time": "4:41:05", "throughput": 62138.08, "total_tokens": 4130540544} |
| {"current_steps": 11570, "total_steps": 14493, "loss": 0.2271, "lr": 3.404513017709813e-05, "epoch": 2.395020832794182, "percentage": 79.83, "elapsed_time": "18:28:42", "remaining_time": "4:40:06", "throughput": 62145.96, "total_tokens": 4134123648} |
| {"current_steps": 11580, "total_steps": 14493, "loss": 0.2297, "lr": 3.403724077644598e-05, "epoch": 2.397091172588701, "percentage": 79.9, "elapsed_time": "18:29:31", "remaining_time": "4:39:06", "throughput": 62153.98, "total_tokens": 4137696256} |
| {"current_steps": 11590, "total_steps": 14493, "loss": 0.2268, "lr": 3.402935685797077e-05, "epoch": 2.3991615123832197, "percentage": 79.97, "elapsed_time": "18:30:18", "remaining_time": "4:38:06", "throughput": 62163.26, "total_tokens": 4141232000} |
| {"current_steps": 11600, "total_steps": 14493, "loss": 0.2274, "lr": 3.4021478415326355e-05, "epoch": 2.4012318521777387, "percentage": 80.04, "elapsed_time": "18:31:05", "remaining_time": "4:37:06", "throughput": 62172.61, "total_tokens": 4144783744} |
| {"current_steps": 11610, "total_steps": 14493, "loss": 0.2284, "lr": 3.401360544217687e-05, "epoch": 2.4033021919722577, "percentage": 80.11, "elapsed_time": "18:31:56", "remaining_time": "4:36:07", "throughput": 62179.47, "total_tokens": 4148422784} |
| {"current_steps": 11620, "total_steps": 14493, "loss": 0.2291, "lr": 3.400573793219672e-05, "epoch": 2.4053725317667762, "percentage": 80.18, "elapsed_time": "18:32:44", "remaining_time": "4:35:07", "throughput": 62188.91, "total_tokens": 4152014080} |
| {"current_steps": 11630, "total_steps": 14493, "loss": 0.2294, "lr": 3.3997875879070546e-05, "epoch": 2.4074428715612948, "percentage": 80.25, "elapsed_time": "18:33:32", "remaining_time": "4:34:07", "throughput": 62196.91, "total_tokens": 4155513856} |
| {"current_steps": 11640, "total_steps": 14493, "loss": 0.2298, "lr": 3.399001927649318e-05, "epoch": 2.4095132113558138, "percentage": 80.31, "elapsed_time": "18:34:20", "remaining_time": "4:33:07", "throughput": 62204.99, "total_tokens": 4159080576} |
| {"current_steps": 11650, "total_steps": 14493, "loss": 0.2264, "lr": 3.398216811816968e-05, "epoch": 2.4115835511503327, "percentage": 80.38, "elapsed_time": "18:35:09", "remaining_time": "4:32:08", "throughput": 62212.48, "total_tokens": 4162610816} |
| {"current_steps": 11660, "total_steps": 14493, "loss": 0.231, "lr": 3.397432239781527e-05, "epoch": 2.4136538909448513, "percentage": 80.45, "elapsed_time": "18:35:55", "remaining_time": "4:31:08", "throughput": 62221.72, "total_tokens": 4166091264} |
| {"current_steps": 11670, "total_steps": 14493, "loss": 0.229, "lr": 3.396648210915531e-05, "epoch": 2.4157242307393703, "percentage": 80.52, "elapsed_time": "18:36:43", "remaining_time": "4:30:08", "throughput": 62230.07, "total_tokens": 4169616000} |
| {"current_steps": 11680, "total_steps": 14493, "loss": 0.2304, "lr": 3.3958647245925315e-05, "epoch": 2.417794570533889, "percentage": 80.59, "elapsed_time": "18:37:37", "remaining_time": "4:29:10", "throughput": 62235.44, "total_tokens": 4173361152} |
| {"current_steps": 11690, "total_steps": 14493, "loss": 0.2294, "lr": 3.3950817801870885e-05, "epoch": 2.419864910328408, "percentage": 80.66, "elapsed_time": "18:38:27", "remaining_time": "4:28:10", "throughput": 62241.85, "total_tokens": 4176920320} |
| {"current_steps": 11700, "total_steps": 14493, "loss": 0.2303, "lr": 3.3942993770747735e-05, "epoch": 2.4219352501229263, "percentage": 80.73, "elapsed_time": "18:39:18", "remaining_time": "4:27:12", "throughput": 62248.92, "total_tokens": 4180563200} |
| {"current_steps": 11710, "total_steps": 14493, "loss": 0.229, "lr": 3.3935175146321626e-05, "epoch": 2.4240055899174453, "percentage": 80.8, "elapsed_time": "18:40:07", "remaining_time": "4:26:12", "throughput": 62256.8, "total_tokens": 4184135424} |
| {"current_steps": 11720, "total_steps": 14493, "loss": 0.2305, "lr": 3.392736192236839e-05, "epoch": 2.426075929711964, "percentage": 80.87, "elapsed_time": "18:40:56", "remaining_time": "4:25:13", "throughput": 62263.85, "total_tokens": 4187677824} |
| {"current_steps": 11730, "total_steps": 14493, "loss": 0.2274, "lr": 3.391955409267387e-05, "epoch": 2.428146269506483, "percentage": 80.94, "elapsed_time": "18:41:47", "remaining_time": "4:24:14", "throughput": 62270.63, "total_tokens": 4191262720} |
| {"current_steps": 11740, "total_steps": 14493, "loss": 0.2332, "lr": 3.3911751651033896e-05, "epoch": 2.4302166093010014, "percentage": 81.0, "elapsed_time": "18:42:37", "remaining_time": "4:23:15", "throughput": 62277.63, "total_tokens": 4194862464} |
| {"current_steps": 11750, "total_steps": 14493, "loss": 0.228, "lr": 3.3903954591254334e-05, "epoch": 2.4322869490955203, "percentage": 81.07, "elapsed_time": "18:43:29", "remaining_time": "4:22:16", "throughput": 62283.58, "total_tokens": 4198496384} |
| {"current_steps": 11760, "total_steps": 14493, "loss": 0.2314, "lr": 3.389616290715097e-05, "epoch": 2.434357288890039, "percentage": 81.14, "elapsed_time": "18:44:18", "remaining_time": "4:21:17", "throughput": 62291.4, "total_tokens": 4202054016} |
| {"current_steps": 11770, "total_steps": 14493, "loss": 0.2279, "lr": 3.388837659254955e-05, "epoch": 2.436427628684558, "percentage": 81.21, "elapsed_time": "18:45:05", "remaining_time": "4:20:17", "throughput": 62299.69, "total_tokens": 4205601536} |
| {"current_steps": 11780, "total_steps": 14493, "loss": 0.231, "lr": 3.3880595641285746e-05, "epoch": 2.4384979684790764, "percentage": 81.28, "elapsed_time": "18:45:54", "remaining_time": "4:19:18", "throughput": 62308.11, "total_tokens": 4209172480} |
| {"current_steps": 11790, "total_steps": 14493, "loss": 0.2278, "lr": 3.387282004720513e-05, "epoch": 2.4405683082735954, "percentage": 81.35, "elapsed_time": "18:46:43", "remaining_time": "4:18:18", "throughput": 62315.51, "total_tokens": 4212724352} |
| {"current_steps": 11800, "total_steps": 14493, "loss": 0.2297, "lr": 3.386504980416316e-05, "epoch": 2.4426386480681144, "percentage": 81.42, "elapsed_time": "18:47:33", "remaining_time": "4:17:19", "throughput": 62322.2, "total_tokens": 4216308352} |
| {"current_steps": 11810, "total_steps": 14493, "loss": 0.2303, "lr": 3.385728490602515e-05, "epoch": 2.444708987862633, "percentage": 81.49, "elapsed_time": "18:48:22", "remaining_time": "4:16:20", "throughput": 62329.41, "total_tokens": 4219881728} |
| {"current_steps": 11820, "total_steps": 14493, "loss": 0.229, "lr": 3.384952534666625e-05, "epoch": 2.446779327657152, "percentage": 81.56, "elapsed_time": "18:49:14", "remaining_time": "4:15:22", "throughput": 62335.91, "total_tokens": 4223528320} |
| {"current_steps": 11830, "total_steps": 14493, "loss": 0.2303, "lr": 3.3841771119971455e-05, "epoch": 2.4488496674516704, "percentage": 81.63, "elapsed_time": "18:50:04", "remaining_time": "4:14:23", "throughput": 62342.82, "total_tokens": 4227110272} |
| {"current_steps": 11840, "total_steps": 14493, "loss": 0.2277, "lr": 3.383402221983554e-05, "epoch": 2.4509200072461894, "percentage": 81.69, "elapsed_time": "18:50:54", "remaining_time": "4:13:24", "throughput": 62349.6, "total_tokens": 4230703104} |
| {"current_steps": 11850, "total_steps": 14493, "loss": 0.2281, "lr": 3.3826278640163064e-05, "epoch": 2.452990347040708, "percentage": 81.76, "elapsed_time": "18:51:43", "remaining_time": "4:12:25", "throughput": 62356.72, "total_tokens": 4234244096} |
| {"current_steps": 11860, "total_steps": 14493, "loss": 0.2265, "lr": 3.3818540374868354e-05, "epoch": 2.455060686835227, "percentage": 81.83, "elapsed_time": "18:52:33", "remaining_time": "4:11:26", "throughput": 62364.21, "total_tokens": 4237859456} |
| {"current_steps": 11870, "total_steps": 14493, "loss": 0.2268, "lr": 3.381080741787547e-05, "epoch": 2.4571310266297455, "percentage": 81.9, "elapsed_time": "18:53:21", "remaining_time": "4:10:26", "throughput": 62371.83, "total_tokens": 4241400832} |
| {"current_steps": 11880, "total_steps": 14493, "loss": 0.2264, "lr": 3.38030797631182e-05, "epoch": 2.4592013664242645, "percentage": 81.97, "elapsed_time": "18:54:10", "remaining_time": "4:09:27", "throughput": 62379.61, "total_tokens": 4244989568} |
| {"current_steps": 11890, "total_steps": 14493, "loss": 0.226, "lr": 3.379535740454003e-05, "epoch": 2.461271706218783, "percentage": 82.04, "elapsed_time": "18:55:02", "remaining_time": "4:08:29", "throughput": 62385.34, "total_tokens": 4248602240} |
| {"current_steps": 11900, "total_steps": 14493, "loss": 0.2291, "lr": 3.3787640336094126e-05, "epoch": 2.463342046013302, "percentage": 82.11, "elapsed_time": "18:55:52", "remaining_time": "4:07:30", "throughput": 62393.26, "total_tokens": 4252233984} |
| {"current_steps": 11910, "total_steps": 14493, "loss": 0.2286, "lr": 3.3779928551743325e-05, "epoch": 2.4654123858078205, "percentage": 82.18, "elapsed_time": "18:56:44", "remaining_time": "4:06:31", "throughput": 62399.0, "total_tokens": 4255895680} |
| {"current_steps": 11920, "total_steps": 14493, "loss": 0.2263, "lr": 3.3772222045460084e-05, "epoch": 2.4674827256023395, "percentage": 82.25, "elapsed_time": "18:57:34", "remaining_time": "4:05:33", "throughput": 62405.86, "total_tokens": 4259508608} |
| {"current_steps": 11930, "total_steps": 14493, "loss": 0.2295, "lr": 3.37645208112265e-05, "epoch": 2.469553065396858, "percentage": 82.32, "elapsed_time": "18:58:23", "remaining_time": "4:04:34", "throughput": 62413.62, "total_tokens": 4263071616} |
| {"current_steps": 11940, "total_steps": 14493, "loss": 0.2282, "lr": 3.3756824843034255e-05, "epoch": 2.471623405191377, "percentage": 82.38, "elapsed_time": "18:59:12", "remaining_time": "4:03:34", "throughput": 62421.46, "total_tokens": 4266633856} |
| {"current_steps": 11950, "total_steps": 14493, "loss": 0.2312, "lr": 3.374913413488464e-05, "epoch": 2.473693744985896, "percentage": 82.45, "elapsed_time": "19:00:01", "remaining_time": "4:02:35", "throughput": 62429.37, "total_tokens": 4270238208} |
| {"current_steps": 11960, "total_steps": 14493, "loss": 0.229, "lr": 3.374144868078848e-05, "epoch": 2.4757640847804145, "percentage": 82.52, "elapsed_time": "19:00:50", "remaining_time": "4:01:37", "throughput": 62435.84, "total_tokens": 4273752576} |
| {"current_steps": 11970, "total_steps": 14493, "loss": 0.228, "lr": 3.373376847476615e-05, "epoch": 2.4778344245749335, "percentage": 82.59, "elapsed_time": "19:01:36", "remaining_time": "4:00:37", "throughput": 62444.65, "total_tokens": 4277244544} |
| {"current_steps": 11980, "total_steps": 14493, "loss": 0.2286, "lr": 3.3726093510847566e-05, "epoch": 2.479904764369452, "percentage": 82.66, "elapsed_time": "19:02:24", "remaining_time": "3:59:38", "throughput": 62453.07, "total_tokens": 4280839168} |
| {"current_steps": 11990, "total_steps": 14493, "loss": 0.229, "lr": 3.371842378307212e-05, "epoch": 2.481975104163971, "percentage": 82.73, "elapsed_time": "19:03:16", "remaining_time": "3:58:39", "throughput": 62459.52, "total_tokens": 4284490368} |
| {"current_steps": 12000, "total_steps": 14493, "loss": 0.229, "lr": 3.371075928548872e-05, "epoch": 2.4840454439584896, "percentage": 82.8, "elapsed_time": "19:04:07", "remaining_time": "3:57:41", "throughput": 62465.52, "total_tokens": 4288099456} |
| {"current_steps": 12010, "total_steps": 14493, "loss": 0.2293, "lr": 3.37031000121557e-05, "epoch": 2.4861157837530086, "percentage": 82.87, "elapsed_time": "19:04:58", "remaining_time": "3:56:42", "throughput": 62472.06, "total_tokens": 4291707648} |
| {"current_steps": 12020, "total_steps": 14493, "loss": 0.2325, "lr": 3.369544595714088e-05, "epoch": 2.488186123547527, "percentage": 82.94, "elapsed_time": "19:05:49", "remaining_time": "3:55:44", "throughput": 62478.34, "total_tokens": 4295343616} |
| {"current_steps": 12030, "total_steps": 14493, "loss": 0.2276, "lr": 3.368779711452148e-05, "epoch": 2.490256463342046, "percentage": 83.01, "elapsed_time": "19:06:38", "remaining_time": "3:54:45", "throughput": 62485.32, "total_tokens": 4298894080} |
| {"current_steps": 12040, "total_steps": 14493, "loss": 0.23, "lr": 3.368015347838413e-05, "epoch": 2.4923268031365646, "percentage": 83.07, "elapsed_time": "19:07:27", "remaining_time": "3:53:46", "throughput": 62492.42, "total_tokens": 4302460672} |
| {"current_steps": 12050, "total_steps": 14493, "loss": 0.23, "lr": 3.3672515042824855e-05, "epoch": 2.4943971429310836, "percentage": 83.14, "elapsed_time": "19:08:14", "remaining_time": "3:52:47", "throughput": 62500.28, "total_tokens": 4305900288} |
| {"current_steps": 12060, "total_steps": 14493, "loss": 0.2296, "lr": 3.366488180194904e-05, "epoch": 2.496467482725602, "percentage": 83.21, "elapsed_time": "19:09:00", "remaining_time": "3:51:48", "throughput": 62509.87, "total_tokens": 4309473536} |
| {"current_steps": 12070, "total_steps": 14493, "loss": 0.2291, "lr": 3.365725374987143e-05, "epoch": 2.498537822520121, "percentage": 83.28, "elapsed_time": "19:09:47", "remaining_time": "3:50:48", "throughput": 62518.73, "total_tokens": 4312995456} |
| {"current_steps": 12080, "total_steps": 14493, "loss": 0.2304, "lr": 3.36496308807161e-05, "epoch": 2.5006081623146397, "percentage": 83.35, "elapsed_time": "19:10:39", "remaining_time": "3:49:50", "throughput": 62524.56, "total_tokens": 4316634240} |
| {"current_steps": 12090, "total_steps": 14493, "loss": 0.2301, "lr": 3.3642013188616426e-05, "epoch": 2.5026785021091587, "percentage": 83.42, "elapsed_time": "19:11:26", "remaining_time": "3:48:51", "throughput": 62532.32, "total_tokens": 4320130816} |
| {"current_steps": 12100, "total_steps": 14493, "loss": 0.2287, "lr": 3.3634400667715074e-05, "epoch": 2.5047488419036776, "percentage": 83.49, "elapsed_time": "19:12:14", "remaining_time": "3:47:52", "throughput": 62540.03, "total_tokens": 4323703936} |
| {"current_steps": 12110, "total_steps": 14493, "loss": 0.2298, "lr": 3.3626793312164013e-05, "epoch": 2.506819181698196, "percentage": 83.56, "elapsed_time": "19:13:04", "remaining_time": "3:46:54", "throughput": 62546.46, "total_tokens": 4327259392} |
| {"current_steps": 12120, "total_steps": 14493, "loss": 0.2284, "lr": 3.361919111612443e-05, "epoch": 2.508889521492715, "percentage": 83.63, "elapsed_time": "19:13:52", "remaining_time": "3:45:55", "throughput": 62554.18, "total_tokens": 4330797440} |
| {"current_steps": 12130, "total_steps": 14493, "loss": 0.2275, "lr": 3.361159407376678e-05, "epoch": 2.5109598612872337, "percentage": 83.7, "elapsed_time": "19:14:42", "remaining_time": "3:44:56", "throughput": 62560.98, "total_tokens": 4334392320} |
| {"current_steps": 12140, "total_steps": 14493, "loss": 0.2296, "lr": 3.3604002179270685e-05, "epoch": 2.5130302010817527, "percentage": 83.76, "elapsed_time": "19:15:31", "remaining_time": "3:43:57", "throughput": 62568.92, "total_tokens": 4337975424} |
| {"current_steps": 12150, "total_steps": 14493, "loss": 0.228, "lr": 3.359641542682504e-05, "epoch": 2.515100540876271, "percentage": 83.83, "elapsed_time": "19:16:20", "remaining_time": "3:42:59", "throughput": 62575.74, "total_tokens": 4341510528} |
| {"current_steps": 12160, "total_steps": 14493, "loss": 0.2303, "lr": 3.3588833810627854e-05, "epoch": 2.51717088067079, "percentage": 83.9, "elapsed_time": "19:17:12", "remaining_time": "3:42:01", "throughput": 62580.65, "total_tokens": 4345133312} |
| {"current_steps": 12170, "total_steps": 14493, "loss": 0.2283, "lr": 3.358125732488632e-05, "epoch": 2.5192412204653087, "percentage": 83.97, "elapsed_time": "19:18:00", "remaining_time": "3:41:02", "throughput": 62587.16, "total_tokens": 4348585472} |
| {"current_steps": 12180, "total_steps": 14493, "loss": 0.2309, "lr": 3.357368596381679e-05, "epoch": 2.5213115602598277, "percentage": 84.04, "elapsed_time": "19:18:50", "remaining_time": "3:40:03", "throughput": 62595.16, "total_tokens": 4352254848} |
| {"current_steps": 12190, "total_steps": 14493, "loss": 0.2273, "lr": 3.356611972164471e-05, "epoch": 2.5233819000543463, "percentage": 84.11, "elapsed_time": "19:19:40", "remaining_time": "3:39:05", "throughput": 62602.91, "total_tokens": 4355914880} |
| {"current_steps": 12200, "total_steps": 14493, "loss": 0.2283, "lr": 3.355855859260466e-05, "epoch": 2.5254522398488652, "percentage": 84.18, "elapsed_time": "19:20:27", "remaining_time": "3:38:06", "throughput": 62611.01, "total_tokens": 4359472768} |
| {"current_steps": 12210, "total_steps": 14493, "loss": 0.2294, "lr": 3.3551002570940285e-05, "epoch": 2.5275225796433842, "percentage": 84.25, "elapsed_time": "19:21:18", "remaining_time": "3:37:08", "throughput": 62617.02, "total_tokens": 4363040896} |
| {"current_steps": 12220, "total_steps": 14493, "loss": 0.2306, "lr": 3.354345165090431e-05, "epoch": 2.5295929194379028, "percentage": 84.32, "elapsed_time": "19:22:05", "remaining_time": "3:36:09", "throughput": 62625.63, "total_tokens": 4366630144} |
| {"current_steps": 12230, "total_steps": 14493, "loss": 0.2287, "lr": 3.3535905826758515e-05, "epoch": 2.5316632592324213, "percentage": 84.39, "elapsed_time": "19:22:53", "remaining_time": "3:35:10", "throughput": 62633.77, "total_tokens": 4370198784} |
| {"current_steps": 12240, "total_steps": 14493, "loss": 0.2299, "lr": 3.352836509277369e-05, "epoch": 2.5337335990269403, "percentage": 84.45, "elapsed_time": "19:23:43", "remaining_time": "3:34:12", "throughput": 62640.68, "total_tokens": 4373768960} |
| {"current_steps": 12250, "total_steps": 14493, "loss": 0.2296, "lr": 3.352082944322966e-05, "epoch": 2.5358039388214593, "percentage": 84.52, "elapsed_time": "19:24:35", "remaining_time": "3:33:14", "throughput": 62645.6, "total_tokens": 4377393536} |
| {"current_steps": 12260, "total_steps": 14493, "loss": 0.2289, "lr": 3.351329887241524e-05, "epoch": 2.537874278615978, "percentage": 84.59, "elapsed_time": "19:25:23", "remaining_time": "3:32:15", "throughput": 62652.94, "total_tokens": 4380903680} |
| {"current_steps": 12270, "total_steps": 14493, "loss": 0.2281, "lr": 3.3505773374628225e-05, "epoch": 2.5399446184104963, "percentage": 84.66, "elapsed_time": "19:26:10", "remaining_time": "3:31:16", "throughput": 62661.65, "total_tokens": 4384450048} |
| {"current_steps": 12280, "total_steps": 14493, "loss": 0.2271, "lr": 3.3498252944175354e-05, "epoch": 2.5420149582050153, "percentage": 84.73, "elapsed_time": "19:26:59", "remaining_time": "3:30:18", "throughput": 62669.07, "total_tokens": 4388082304} |
| {"current_steps": 12290, "total_steps": 14493, "loss": 0.2279, "lr": 3.3490737575372326e-05, "epoch": 2.5440852979995343, "percentage": 84.8, "elapsed_time": "19:27:46", "remaining_time": "3:29:19", "throughput": 62677.71, "total_tokens": 4391597312} |
| {"current_steps": 12300, "total_steps": 14493, "loss": 0.2283, "lr": 3.348322726254375e-05, "epoch": 2.546155637794053, "percentage": 84.87, "elapsed_time": "19:28:36", "remaining_time": "3:28:21", "throughput": 62683.86, "total_tokens": 4395175296} |
| {"current_steps": 12310, "total_steps": 14493, "loss": 0.2281, "lr": 3.347572200002315e-05, "epoch": 2.548225977588572, "percentage": 84.94, "elapsed_time": "19:29:27", "remaining_time": "3:27:23", "throughput": 62690.47, "total_tokens": 4398829568} |
| {"current_steps": 12320, "total_steps": 14493, "loss": 0.2274, "lr": 3.3468221782152924e-05, "epoch": 2.5502963173830904, "percentage": 85.01, "elapsed_time": "19:30:17", "remaining_time": "3:26:25", "throughput": 62696.77, "total_tokens": 4402436224} |
| {"current_steps": 12330, "total_steps": 14493, "loss": 0.2311, "lr": 3.346072660328435e-05, "epoch": 2.5523666571776094, "percentage": 85.08, "elapsed_time": "19:31:07", "remaining_time": "3:25:26", "throughput": 62703.55, "total_tokens": 4406001792} |
| {"current_steps": 12340, "total_steps": 14493, "loss": 0.2297, "lr": 3.345323645777756e-05, "epoch": 2.554436996972128, "percentage": 85.14, "elapsed_time": "19:31:56", "remaining_time": "3:24:28", "throughput": 62710.59, "total_tokens": 4409588096} |
| {"current_steps": 12350, "total_steps": 14493, "loss": 0.2289, "lr": 3.34457513400015e-05, "epoch": 2.556507336766647, "percentage": 85.21, "elapsed_time": "19:32:48", "remaining_time": "3:23:30", "throughput": 62715.12, "total_tokens": 4413176448} |
| {"current_steps": 12360, "total_steps": 14493, "loss": 0.2271, "lr": 3.343827124433396e-05, "epoch": 2.558577676561166, "percentage": 85.28, "elapsed_time": "19:33:36", "remaining_time": "3:22:31", "throughput": 62723.02, "total_tokens": 4416734720} |
| {"current_steps": 12370, "total_steps": 14493, "loss": 0.231, "lr": 3.343079616516151e-05, "epoch": 2.5606480163556844, "percentage": 85.35, "elapsed_time": "19:34:25", "remaining_time": "3:21:33", "throughput": 62730.22, "total_tokens": 4420293120} |
| {"current_steps": 12380, "total_steps": 14493, "loss": 0.2287, "lr": 3.3423326096879495e-05, "epoch": 2.562718356150203, "percentage": 85.42, "elapsed_time": "19:35:14", "remaining_time": "3:20:35", "throughput": 62737.18, "total_tokens": 4423858048} |
| {"current_steps": 12390, "total_steps": 14493, "loss": 0.2308, "lr": 3.341586103389203e-05, "epoch": 2.564788695944722, "percentage": 85.49, "elapsed_time": "19:36:04", "remaining_time": "3:19:37", "throughput": 62744.49, "total_tokens": 4427520128} |
| {"current_steps": 12400, "total_steps": 14493, "loss": 0.2308, "lr": 3.3408400970611995e-05, "epoch": 2.566859035739241, "percentage": 85.56, "elapsed_time": "19:36:51", "remaining_time": "3:18:38", "throughput": 62751.98, "total_tokens": 4431037696} |
| {"current_steps": 12410, "total_steps": 14493, "loss": 0.2285, "lr": 3.340094590146095e-05, "epoch": 2.5689293755337594, "percentage": 85.63, "elapsed_time": "19:37:39", "remaining_time": "3:17:40", "throughput": 62759.7, "total_tokens": 4434582016} |
| {"current_steps": 12420, "total_steps": 14493, "loss": 0.2283, "lr": 3.3393495820869215e-05, "epoch": 2.570999715328278, "percentage": 85.7, "elapsed_time": "19:38:30", "remaining_time": "3:16:42", "throughput": 62765.08, "total_tokens": 4438175360} |
| {"current_steps": 12430, "total_steps": 14493, "loss": 0.2283, "lr": 3.338605072327576e-05, "epoch": 2.573070055122797, "percentage": 85.77, "elapsed_time": "19:39:17", "remaining_time": "3:15:43", "throughput": 62774.16, "total_tokens": 4441721856} |
| {"current_steps": 12440, "total_steps": 14493, "loss": 0.2287, "lr": 3.337861060312827e-05, "epoch": 2.575140394917316, "percentage": 85.83, "elapsed_time": "19:40:07", "remaining_time": "3:14:45", "throughput": 62779.92, "total_tokens": 4445304960} |
| {"current_steps": 12450, "total_steps": 14493, "loss": 0.2269, "lr": 3.337117545488306e-05, "epoch": 2.5772107347118345, "percentage": 85.9, "elapsed_time": "19:40:54", "remaining_time": "3:13:46", "throughput": 62787.88, "total_tokens": 4448787328} |
| {"current_steps": 12460, "total_steps": 14493, "loss": 0.232, "lr": 3.33637452730051e-05, "epoch": 2.5792810745063535, "percentage": 85.97, "elapsed_time": "19:41:40", "remaining_time": "3:12:48", "throughput": 62795.28, "total_tokens": 4452225408} |
| {"current_steps": 12470, "total_steps": 14493, "loss": 0.2266, "lr": 3.335632005196796e-05, "epoch": 2.581351414300872, "percentage": 86.04, "elapsed_time": "19:42:31", "remaining_time": "3:11:50", "throughput": 62801.55, "total_tokens": 4455878656} |
| {"current_steps": 12480, "total_steps": 14493, "loss": 0.2284, "lr": 3.334889978625383e-05, "epoch": 2.583421754095391, "percentage": 86.11, "elapsed_time": "19:43:21", "remaining_time": "3:10:52", "throughput": 62806.29, "total_tokens": 4459370624} |
| {"current_steps": 12490, "total_steps": 14493, "loss": 0.232, "lr": 3.3341484470353515e-05, "epoch": 2.5854920938899095, "percentage": 86.18, "elapsed_time": "19:44:08", "remaining_time": "3:09:53", "throughput": 62814.4, "total_tokens": 4462849920} |
| {"current_steps": 12500, "total_steps": 14493, "loss": 0.2294, "lr": 3.333407409876635e-05, "epoch": 2.5875624336844285, "percentage": 86.25, "elapsed_time": "19:44:57", "remaining_time": "3:08:55", "throughput": 62820.66, "total_tokens": 4466421248} |
| {"current_steps": 12510, "total_steps": 14493, "loss": 0.2315, "lr": 3.332666866600024e-05, "epoch": 2.5896327734789475, "percentage": 86.32, "elapsed_time": "19:45:46", "remaining_time": "3:07:57", "throughput": 62827.9, "total_tokens": 4469972480} |
| {"current_steps": 12520, "total_steps": 14493, "loss": 0.2289, "lr": 3.331926816657162e-05, "epoch": 2.591703113273466, "percentage": 86.39, "elapsed_time": "19:46:35", "remaining_time": "3:06:59", "throughput": 62834.72, "total_tokens": 4473555200} |
| {"current_steps": 12530, "total_steps": 14493, "loss": 0.2286, "lr": 3.331187259500546e-05, "epoch": 2.5937734530679846, "percentage": 86.46, "elapsed_time": "19:47:24", "remaining_time": "3:06:01", "throughput": 62842.07, "total_tokens": 4477131904} |
| {"current_steps": 12540, "total_steps": 14493, "loss": 0.2308, "lr": 3.3304481945835235e-05, "epoch": 2.5958437928625036, "percentage": 86.52, "elapsed_time": "19:48:11", "remaining_time": "3:05:03", "throughput": 62850.38, "total_tokens": 4480691968} |
| {"current_steps": 12550, "total_steps": 14493, "loss": 0.2307, "lr": 3.329709621360288e-05, "epoch": 2.5979141326570225, "percentage": 86.59, "elapsed_time": "19:48:59", "remaining_time": "3:04:04", "throughput": 62857.83, "total_tokens": 4484247040} |
| {"current_steps": 12560, "total_steps": 14493, "loss": 0.229, "lr": 3.328971539285882e-05, "epoch": 2.599984472451541, "percentage": 86.66, "elapsed_time": "19:49:47", "remaining_time": "3:03:06", "throughput": 62865.57, "total_tokens": 4487790080} |
| {"current_steps": 12570, "total_steps": 14493, "loss": 0.2286, "lr": 3.3282339478161935e-05, "epoch": 2.6020548122460596, "percentage": 86.73, "elapsed_time": "19:50:37", "remaining_time": "3:02:08", "throughput": 62871.09, "total_tokens": 4491343616} |
| {"current_steps": 12580, "total_steps": 14493, "loss": 0.2283, "lr": 3.327496846407953e-05, "epoch": 2.6041251520405786, "percentage": 86.8, "elapsed_time": "19:51:26", "remaining_time": "3:01:10", "throughput": 62878.67, "total_tokens": 4494954240} |
| {"current_steps": 12590, "total_steps": 14493, "loss": 0.228, "lr": 3.3267602345187304e-05, "epoch": 2.6061954918350976, "percentage": 86.87, "elapsed_time": "19:52:14", "remaining_time": "3:00:12", "throughput": 62885.49, "total_tokens": 4498501120} |
| {"current_steps": 12600, "total_steps": 14493, "loss": 0.2266, "lr": 3.326024111606942e-05, "epoch": 2.608265831629616, "percentage": 86.94, "elapsed_time": "19:53:04", "remaining_time": "2:59:14", "throughput": 62892.42, "total_tokens": 4502132224} |
| {"current_steps": 12610, "total_steps": 14493, "loss": 0.2293, "lr": 3.325288477131839e-05, "epoch": 2.610336171424135, "percentage": 87.01, "elapsed_time": "19:53:55", "remaining_time": "2:58:17", "throughput": 62898.58, "total_tokens": 4505767040} |
| {"current_steps": 12620, "total_steps": 14493, "loss": 0.2293, "lr": 3.324553330553507e-05, "epoch": 2.6124065112186536, "percentage": 87.08, "elapsed_time": "19:54:45", "remaining_time": "2:57:19", "throughput": 62905.27, "total_tokens": 4509382016} |
| {"current_steps": 12630, "total_steps": 14493, "loss": 0.2304, "lr": 3.323818671332871e-05, "epoch": 2.6144768510131726, "percentage": 87.15, "elapsed_time": "19:55:37", "remaining_time": "2:56:21", "throughput": 62910.02, "total_tokens": 4513013120} |
| {"current_steps": 12640, "total_steps": 14493, "loss": 0.2305, "lr": 3.323084498931687e-05, "epoch": 2.616547190807691, "percentage": 87.21, "elapsed_time": "19:56:27", "remaining_time": "2:55:23", "throughput": 62916.99, "total_tokens": 4516636800} |
| {"current_steps": 12650, "total_steps": 14493, "loss": 0.2264, "lr": 3.322350812812545e-05, "epoch": 2.61861753060221, "percentage": 87.28, "elapsed_time": "19:57:16", "remaining_time": "2:54:25", "throughput": 62923.97, "total_tokens": 4520244096} |
| {"current_steps": 12660, "total_steps": 14493, "loss": 0.2287, "lr": 3.321617612438862e-05, "epoch": 2.620687870396729, "percentage": 87.35, "elapsed_time": "19:58:04", "remaining_time": "2:53:27", "throughput": 62930.96, "total_tokens": 4523739008} |
| {"current_steps": 12670, "total_steps": 14493, "loss": 0.2298, "lr": 3.320884897274886e-05, "epoch": 2.6227582101912477, "percentage": 87.42, "elapsed_time": "19:58:51", "remaining_time": "2:52:29", "throughput": 62938.79, "total_tokens": 4527307520} |
| {"current_steps": 12680, "total_steps": 14493, "loss": 0.2303, "lr": 3.320152666785692e-05, "epoch": 2.624828549985766, "percentage": 87.49, "elapsed_time": "19:59:42", "remaining_time": "2:51:32", "throughput": 62944.42, "total_tokens": 4530882688} |
| {"current_steps": 12690, "total_steps": 14493, "loss": 0.2305, "lr": 3.319420920437179e-05, "epoch": 2.626898889780285, "percentage": 87.56, "elapsed_time": "20:00:32", "remaining_time": "2:50:34", "throughput": 62950.45, "total_tokens": 4534505216} |
| {"current_steps": 12700, "total_steps": 14493, "loss": 0.2303, "lr": 3.31868965769607e-05, "epoch": 2.628969229574804, "percentage": 87.63, "elapsed_time": "20:01:20", "remaining_time": "2:49:36", "throughput": 62958.1, "total_tokens": 4538035968} |
| {"current_steps": 12710, "total_steps": 14493, "loss": 0.2306, "lr": 3.317958878029911e-05, "epoch": 2.6310395693693227, "percentage": 87.7, "elapsed_time": "20:02:06", "remaining_time": "2:48:38", "throughput": 62965.99, "total_tokens": 4541537920} |
| {"current_steps": 12720, "total_steps": 14493, "loss": 0.2294, "lr": 3.3172285809070665e-05, "epoch": 2.6331099091638412, "percentage": 87.77, "elapsed_time": "20:02:53", "remaining_time": "2:47:40", "throughput": 62974.23, "total_tokens": 4545096064} |
| {"current_steps": 12730, "total_steps": 14493, "loss": 0.2287, "lr": 3.3164987657967214e-05, "epoch": 2.6351802489583602, "percentage": 87.84, "elapsed_time": "20:03:41", "remaining_time": "2:46:42", "throughput": 62980.69, "total_tokens": 4548588672} |
| {"current_steps": 12740, "total_steps": 14493, "loss": 0.2287, "lr": 3.315769432168877e-05, "epoch": 2.637250588752879, "percentage": 87.9, "elapsed_time": "20:04:31", "remaining_time": "2:45:44", "throughput": 62986.03, "total_tokens": 4552072448} |
| {"current_steps": 12750, "total_steps": 14493, "loss": 0.2301, "lr": 3.315040579494349e-05, "epoch": 2.6393209285473977, "percentage": 87.97, "elapsed_time": "20:05:20", "remaining_time": "2:44:46", "throughput": 62992.43, "total_tokens": 4555661312} |
| {"current_steps": 12760, "total_steps": 14493, "loss": 0.2287, "lr": 3.31431220724477e-05, "epoch": 2.6413912683419167, "percentage": 88.04, "elapsed_time": "20:06:09", "remaining_time": "2:43:48", "throughput": 62999.85, "total_tokens": 4559292160} |
| {"current_steps": 12770, "total_steps": 14493, "loss": 0.2292, "lr": 3.3135843148925834e-05, "epoch": 2.6434616081364353, "percentage": 88.11, "elapsed_time": "20:06:56", "remaining_time": "2:42:50", "throughput": 63008.11, "total_tokens": 4562835328} |
| {"current_steps": 12780, "total_steps": 14493, "loss": 0.2275, "lr": 3.3128569019110414e-05, "epoch": 2.6455319479309543, "percentage": 88.18, "elapsed_time": "20:07:46", "remaining_time": "2:41:53", "throughput": 63014.55, "total_tokens": 4566431104} |
| {"current_steps": 12790, "total_steps": 14493, "loss": 0.23, "lr": 3.312129967774207e-05, "epoch": 2.647602287725473, "percentage": 88.25, "elapsed_time": "20:08:33", "remaining_time": "2:40:55", "throughput": 63022.18, "total_tokens": 4569936256} |
| {"current_steps": 12800, "total_steps": 14493, "loss": 0.2279, "lr": 3.311403511956952e-05, "epoch": 2.6496726275199918, "percentage": 88.32, "elapsed_time": "20:09:22", "remaining_time": "2:39:57", "throughput": 63028.06, "total_tokens": 4573501312} |
| {"current_steps": 12810, "total_steps": 14493, "loss": 0.2282, "lr": 3.310677533934952e-05, "epoch": 2.6517429673145108, "percentage": 88.39, "elapsed_time": "20:10:09", "remaining_time": "2:38:59", "throughput": 63036.16, "total_tokens": 4577029888} |
| {"current_steps": 12820, "total_steps": 14493, "loss": 0.2287, "lr": 3.309952033184686e-05, "epoch": 2.6538133071090293, "percentage": 88.46, "elapsed_time": "20:10:55", "remaining_time": "2:38:01", "throughput": 63044.03, "total_tokens": 4580498688} |
| {"current_steps": 12830, "total_steps": 14493, "loss": 0.2321, "lr": 3.309227009183439e-05, "epoch": 2.655883646903548, "percentage": 88.53, "elapsed_time": "20:11:44", "remaining_time": "2:37:03", "throughput": 63049.69, "total_tokens": 4583975808} |
| {"current_steps": 12840, "total_steps": 14493, "loss": 0.2277, "lr": 3.308502461409295e-05, "epoch": 2.657953986698067, "percentage": 88.59, "elapsed_time": "20:12:32", "remaining_time": "2:36:05", "throughput": 63056.66, "total_tokens": 4587509120} |
| {"current_steps": 12850, "total_steps": 14493, "loss": 0.2289, "lr": 3.3077783893411386e-05, "epoch": 2.660024326492586, "percentage": 88.66, "elapsed_time": "20:13:21", "remaining_time": "2:35:08", "throughput": 63063.32, "total_tokens": 4591076096} |
| {"current_steps": 12860, "total_steps": 14493, "loss": 0.2317, "lr": 3.30705479245865e-05, "epoch": 2.6620946662871043, "percentage": 88.73, "elapsed_time": "20:14:09", "remaining_time": "2:34:10", "throughput": 63069.63, "total_tokens": 4594581632} |
| {"current_steps": 12870, "total_steps": 14493, "loss": 0.231, "lr": 3.3063316702423094e-05, "epoch": 2.664165006081623, "percentage": 88.8, "elapsed_time": "20:14:56", "remaining_time": "2:33:12", "throughput": 63077.92, "total_tokens": 4598174720} |
| {"current_steps": 12880, "total_steps": 14493, "loss": 0.2303, "lr": 3.305609022173388e-05, "epoch": 2.666235345876142, "percentage": 88.87, "elapsed_time": "20:15:44", "remaining_time": "2:32:15", "throughput": 63085.26, "total_tokens": 4601745152} |
| {"current_steps": 12890, "total_steps": 14493, "loss": 0.2296, "lr": 3.304886847733954e-05, "epoch": 2.668305685670661, "percentage": 88.94, "elapsed_time": "20:16:34", "remaining_time": "2:31:17", "throughput": 63091.47, "total_tokens": 4605339136} |
| {"current_steps": 12900, "total_steps": 14493, "loss": 0.2289, "lr": 3.304165146406865e-05, "epoch": 2.6703760254651794, "percentage": 89.01, "elapsed_time": "20:17:21", "remaining_time": "2:30:19", "throughput": 63098.64, "total_tokens": 4608833280} |
| {"current_steps": 12910, "total_steps": 14493, "loss": 0.2258, "lr": 3.30344391767577e-05, "epoch": 2.6724463652596984, "percentage": 89.08, "elapsed_time": "20:18:16", "remaining_time": "2:29:22", "throughput": 63102.84, "total_tokens": 4612594944} |
| {"current_steps": 12920, "total_steps": 14493, "loss": 0.2293, "lr": 3.302723161025104e-05, "epoch": 2.674516705054217, "percentage": 89.15, "elapsed_time": "20:19:07", "remaining_time": "2:28:25", "throughput": 63109.94, "total_tokens": 4616319360} |
| {"current_steps": 12930, "total_steps": 14493, "loss": 0.2265, "lr": 3.302002875940093e-05, "epoch": 2.676587044848736, "percentage": 89.22, "elapsed_time": "20:19:54", "remaining_time": "2:27:27", "throughput": 63117.49, "total_tokens": 4619865216} |
| {"current_steps": 12940, "total_steps": 14493, "loss": 0.2278, "lr": 3.3012830619067466e-05, "epoch": 2.6786573846432544, "percentage": 89.28, "elapsed_time": "20:20:45", "remaining_time": "2:26:30", "throughput": 63123.4, "total_tokens": 4623509504} |
| {"current_steps": 12950, "total_steps": 14493, "loss": 0.2292, "lr": 3.300563718411857e-05, "epoch": 2.6807277244377734, "percentage": 89.35, "elapsed_time": "20:21:36", "remaining_time": "2:25:33", "throughput": 63127.77, "total_tokens": 4627041664} |
| {"current_steps": 12960, "total_steps": 14493, "loss": 0.2304, "lr": 3.299844844943e-05, "epoch": 2.6827980642322924, "percentage": 89.42, "elapsed_time": "20:22:27", "remaining_time": "2:24:36", "throughput": 63132.43, "total_tokens": 4630616320} |
| {"current_steps": 12970, "total_steps": 14493, "loss": 0.2293, "lr": 3.299126440988535e-05, "epoch": 2.684868404026811, "percentage": 89.49, "elapsed_time": "20:23:18", "remaining_time": "2:23:38", "throughput": 63138.3, "total_tokens": 4634239616} |
| {"current_steps": 12980, "total_steps": 14493, "loss": 0.2289, "lr": 3.298408506037596e-05, "epoch": 2.6869387438213295, "percentage": 89.56, "elapsed_time": "20:24:08", "remaining_time": "2:22:41", "throughput": 63144.07, "total_tokens": 4637832576} |
| {"current_steps": 12990, "total_steps": 14493, "loss": 0.2257, "lr": 3.297691039580097e-05, "epoch": 2.6890090836158484, "percentage": 89.63, "elapsed_time": "20:24:56", "remaining_time": "2:21:43", "throughput": 63151.23, "total_tokens": 4641422976} |
| {"current_steps": 13000, "total_steps": 14493, "loss": 0.2283, "lr": 3.29697404110673e-05, "epoch": 2.6910794234103674, "percentage": 89.7, "elapsed_time": "20:25:46", "remaining_time": "2:20:46", "throughput": 63157.5, "total_tokens": 4645002240} |
| {"current_steps": 13010, "total_steps": 14493, "loss": 0.2272, "lr": 3.2962575101089594e-05, "epoch": 2.693149763204886, "percentage": 89.77, "elapsed_time": "20:26:38", "remaining_time": "2:19:49", "throughput": 63162.34, "total_tokens": 4648625408} |
| {"current_steps": 13020, "total_steps": 14493, "loss": 0.2266, "lr": 3.295541446079024e-05, "epoch": 2.6952201029994045, "percentage": 89.84, "elapsed_time": "20:27:28", "remaining_time": "2:18:52", "throughput": 63167.42, "total_tokens": 4652178304} |
| {"current_steps": 13030, "total_steps": 14493, "loss": 0.2307, "lr": 3.2948258485099336e-05, "epoch": 2.6972904427939235, "percentage": 89.91, "elapsed_time": "20:28:19", "remaining_time": "2:17:54", "throughput": 63173.14, "total_tokens": 4655836416} |
| {"current_steps": 13040, "total_steps": 14493, "loss": 0.228, "lr": 3.29411071689547e-05, "epoch": 2.6993607825884425, "percentage": 89.97, "elapsed_time": "20:29:09", "remaining_time": "2:16:57", "throughput": 63179.28, "total_tokens": 4659464576} |
| {"current_steps": 13050, "total_steps": 14493, "loss": 0.2278, "lr": 3.2933960507301826e-05, "epoch": 2.701431122382961, "percentage": 90.04, "elapsed_time": "20:29:58", "remaining_time": "2:16:00", "throughput": 63186.48, "total_tokens": 4663066880} |
| {"current_steps": 13060, "total_steps": 14493, "loss": 0.2286, "lr": 3.292681849509387e-05, "epoch": 2.70350146217748, "percentage": 90.11, "elapsed_time": "20:30:47", "remaining_time": "2:15:02", "throughput": 63192.46, "total_tokens": 4666587136} |
| {"current_steps": 13070, "total_steps": 14493, "loss": 0.228, "lr": 3.291968112729166e-05, "epoch": 2.7055718019719985, "percentage": 90.18, "elapsed_time": "20:31:38", "remaining_time": "2:14:05", "throughput": 63198.7, "total_tokens": 4670269440} |
| {"current_steps": 13080, "total_steps": 14493, "loss": 0.2292, "lr": 3.291254839886367e-05, "epoch": 2.7076421417665175, "percentage": 90.25, "elapsed_time": "20:32:27", "remaining_time": "2:13:08", "throughput": 63204.98, "total_tokens": 4673854080} |
| {"current_steps": 13090, "total_steps": 14493, "loss": 0.228, "lr": 3.2905420304785995e-05, "epoch": 2.709712481561036, "percentage": 90.32, "elapsed_time": "20:33:19", "remaining_time": "2:12:11", "throughput": 63210.96, "total_tokens": 4677565568} |
| {"current_steps": 13100, "total_steps": 14493, "loss": 0.2273, "lr": 3.289829684004235e-05, "epoch": 2.711782821355555, "percentage": 90.39, "elapsed_time": "20:34:07", "remaining_time": "2:11:13", "throughput": 63217.85, "total_tokens": 4681140608} |
| {"current_steps": 13110, "total_steps": 14493, "loss": 0.2264, "lr": 3.289117799962402e-05, "epoch": 2.713853161150074, "percentage": 90.46, "elapsed_time": "20:34:58", "remaining_time": "2:10:16", "throughput": 63223.04, "total_tokens": 4684752896} |
| {"current_steps": 13120, "total_steps": 14493, "loss": 0.2283, "lr": 3.2884063778529914e-05, "epoch": 2.7159235009445926, "percentage": 90.53, "elapsed_time": "20:35:46", "remaining_time": "2:09:19", "throughput": 63230.38, "total_tokens": 4688298496} |
| {"current_steps": 13130, "total_steps": 14493, "loss": 0.2286, "lr": 3.28769541717665e-05, "epoch": 2.717993840739111, "percentage": 90.6, "elapsed_time": "20:36:35", "remaining_time": "2:08:22", "throughput": 63237.79, "total_tokens": 4691954048} |
| {"current_steps": 13140, "total_steps": 14493, "loss": 0.229, "lr": 3.2869849174347775e-05, "epoch": 2.72006418053363, "percentage": 90.66, "elapsed_time": "20:37:21", "remaining_time": "2:07:24", "throughput": 63245.7, "total_tokens": 4695479552} |
| {"current_steps": 13150, "total_steps": 14493, "loss": 0.2293, "lr": 3.2862748781295294e-05, "epoch": 2.722134520328149, "percentage": 90.73, "elapsed_time": "20:38:14", "remaining_time": "2:06:27", "throughput": 63248.88, "total_tokens": 4699070336} |
| {"current_steps": 13160, "total_steps": 14493, "loss": 0.2315, "lr": 3.2855652987638146e-05, "epoch": 2.7242048601226676, "percentage": 90.8, "elapsed_time": "20:39:04", "remaining_time": "2:05:30", "throughput": 63254.9, "total_tokens": 4702627200} |
| {"current_steps": 13170, "total_steps": 14493, "loss": 0.2297, "lr": 3.284856178841291e-05, "epoch": 2.726275199917186, "percentage": 90.87, "elapsed_time": "20:39:53", "remaining_time": "2:04:33", "throughput": 63260.83, "total_tokens": 4706176384} |
| {"current_steps": 13180, "total_steps": 14493, "loss": 0.2318, "lr": 3.284147517866367e-05, "epoch": 2.728345539711705, "percentage": 90.94, "elapsed_time": "20:40:43", "remaining_time": "2:03:36", "throughput": 63266.39, "total_tokens": 4709802496} |
| {"current_steps": 13190, "total_steps": 14493, "loss": 0.2286, "lr": 3.2834393153441976e-05, "epoch": 2.730415879506224, "percentage": 91.01, "elapsed_time": "20:41:33", "remaining_time": "2:02:38", "throughput": 63273.27, "total_tokens": 4713426048} |
| {"current_steps": 13200, "total_steps": 14493, "loss": 0.2296, "lr": 3.282731570780689e-05, "epoch": 2.7324862193007426, "percentage": 91.08, "elapsed_time": "20:42:21", "remaining_time": "2:01:41", "throughput": 63280.46, "total_tokens": 4716994688} |
| {"current_steps": 13210, "total_steps": 14493, "loss": 0.2294, "lr": 3.2820242836824875e-05, "epoch": 2.7345565590952616, "percentage": 91.15, "elapsed_time": "20:43:08", "remaining_time": "2:00:44", "throughput": 63287.74, "total_tokens": 4720535680} |
| {"current_steps": 13220, "total_steps": 14493, "loss": 0.2272, "lr": 3.2813174535569854e-05, "epoch": 2.73662689888978, "percentage": 91.22, "elapsed_time": "20:43:57", "remaining_time": "1:59:47", "throughput": 63294.02, "total_tokens": 4724110592} |
| {"current_steps": 13230, "total_steps": 14493, "loss": 0.2289, "lr": 3.280611079912318e-05, "epoch": 2.738697238684299, "percentage": 91.29, "elapsed_time": "20:44:46", "remaining_time": "1:58:49", "throughput": 63300.76, "total_tokens": 4727724160} |
| {"current_steps": 13240, "total_steps": 14493, "loss": 0.2315, "lr": 3.279905162257358e-05, "epoch": 2.7407675784788177, "percentage": 91.35, "elapsed_time": "20:45:35", "remaining_time": "1:57:52", "throughput": 63306.54, "total_tokens": 4731251840} |
| {"current_steps": 13250, "total_steps": 14493, "loss": 0.2272, "lr": 3.279199700101723e-05, "epoch": 2.7428379182733367, "percentage": 91.42, "elapsed_time": "20:46:21", "remaining_time": "1:56:55", "throughput": 63315.28, "total_tokens": 4734807168} |
| {"current_steps": 13260, "total_steps": 14493, "loss": 0.2281, "lr": 3.2784946929557644e-05, "epoch": 2.7449082580678557, "percentage": 91.49, "elapsed_time": "20:47:10", "remaining_time": "1:55:58", "throughput": 63321.63, "total_tokens": 4738386688} |
| {"current_steps": 13270, "total_steps": 14493, "loss": 0.2286, "lr": 3.277790140330571e-05, "epoch": 2.746978597862374, "percentage": 91.56, "elapsed_time": "20:47:58", "remaining_time": "1:55:01", "throughput": 63327.54, "total_tokens": 4741889280} |
| {"current_steps": 13280, "total_steps": 14493, "loss": 0.2288, "lr": 3.277086041737968e-05, "epoch": 2.7490489376568927, "percentage": 91.63, "elapsed_time": "20:48:46", "remaining_time": "1:54:03", "throughput": 63334.49, "total_tokens": 4745444992} |
| {"current_steps": 13290, "total_steps": 14493, "loss": 0.2271, "lr": 3.276382396690513e-05, "epoch": 2.7511192774514117, "percentage": 91.7, "elapsed_time": "20:49:36", "remaining_time": "1:53:06", "throughput": 63339.5, "total_tokens": 4748987264} |
| {"current_steps": 13300, "total_steps": 14493, "loss": 0.2272, "lr": 3.275679204701496e-05, "epoch": 2.7531896172459307, "percentage": 91.77, "elapsed_time": "20:50:27", "remaining_time": "1:52:09", "throughput": 63345.18, "total_tokens": 4752621568} |
| {"current_steps": 13310, "total_steps": 14493, "loss": 0.2275, "lr": 3.274976465284939e-05, "epoch": 2.7552599570404492, "percentage": 91.84, "elapsed_time": "20:51:15", "remaining_time": "1:51:12", "throughput": 63351.49, "total_tokens": 4756172544} |
| {"current_steps": 13320, "total_steps": 14493, "loss": 0.229, "lr": 3.274274177955593e-05, "epoch": 2.7573302968349678, "percentage": 91.91, "elapsed_time": "20:52:04", "remaining_time": "1:50:15", "throughput": 63358.09, "total_tokens": 4759714816} |
| {"current_steps": 13330, "total_steps": 14493, "loss": 0.229, "lr": 3.273572342228937e-05, "epoch": 2.7594006366294868, "percentage": 91.98, "elapsed_time": "20:52:50", "remaining_time": "1:49:18", "throughput": 63364.86, "total_tokens": 4763155072} |
| {"current_steps": 13340, "total_steps": 14493, "loss": 0.2277, "lr": 3.272870957621176e-05, "epoch": 2.7614709764240057, "percentage": 92.04, "elapsed_time": "20:53:39", "remaining_time": "1:48:21", "throughput": 63371.54, "total_tokens": 4766745472} |
| {"current_steps": 13350, "total_steps": 14493, "loss": 0.2295, "lr": 3.2721700236492414e-05, "epoch": 2.7635413162185243, "percentage": 92.11, "elapsed_time": "20:54:28", "remaining_time": "1:47:24", "throughput": 63377.3, "total_tokens": 4770323840} |
| {"current_steps": 13360, "total_steps": 14493, "loss": 0.2284, "lr": 3.271469539830788e-05, "epoch": 2.7656116560130433, "percentage": 92.18, "elapsed_time": "20:55:14", "remaining_time": "1:46:27", "throughput": 63384.96, "total_tokens": 4773809792} |
| {"current_steps": 13370, "total_steps": 14493, "loss": 0.2283, "lr": 3.270769505684193e-05, "epoch": 2.767681995807562, "percentage": 92.25, "elapsed_time": "20:56:03", "remaining_time": "1:45:30", "throughput": 63390.71, "total_tokens": 4777342080} |
| {"current_steps": 13380, "total_steps": 14493, "loss": 0.2316, "lr": 3.2700699207285544e-05, "epoch": 2.769752335602081, "percentage": 92.32, "elapsed_time": "20:56:49", "remaining_time": "1:44:32", "throughput": 63398.58, "total_tokens": 4780850816} |
| {"current_steps": 13390, "total_steps": 14493, "loss": 0.2291, "lr": 3.269370784483691e-05, "epoch": 2.7718226753965993, "percentage": 92.39, "elapsed_time": "20:57:37", "remaining_time": "1:43:35", "throughput": 63405.22, "total_tokens": 4784421376} |
| {"current_steps": 13400, "total_steps": 14493, "loss": 0.2271, "lr": 3.268672096470138e-05, "epoch": 2.7738930151911183, "percentage": 92.46, "elapsed_time": "20:58:27", "remaining_time": "1:42:38", "throughput": 63411.55, "total_tokens": 4788026880} |
| {"current_steps": 13410, "total_steps": 14493, "loss": 0.2278, "lr": 3.2679738562091506e-05, "epoch": 2.7759633549856373, "percentage": 92.53, "elapsed_time": "20:59:19", "remaining_time": "1:41:42", "throughput": 63415.11, "total_tokens": 4791638784} |
| {"current_steps": 13420, "total_steps": 14493, "loss": 0.227, "lr": 3.2672760632226964e-05, "epoch": 2.778033694780156, "percentage": 92.6, "elapsed_time": "21:00:08", "remaining_time": "1:40:45", "throughput": 63421.58, "total_tokens": 4795221760} |
| {"current_steps": 13430, "total_steps": 14493, "loss": 0.2316, "lr": 3.266578717033458e-05, "epoch": 2.7801040345746744, "percentage": 92.67, "elapsed_time": "21:00:59", "remaining_time": "1:39:48", "throughput": 63426.44, "total_tokens": 4798825984} |
| {"current_steps": 13440, "total_steps": 14493, "loss": 0.2299, "lr": 3.265881817164833e-05, "epoch": 2.7821743743691933, "percentage": 92.73, "elapsed_time": "21:01:48", "remaining_time": "1:38:51", "throughput": 63432.32, "total_tokens": 4802381952} |
| {"current_steps": 13450, "total_steps": 14493, "loss": 0.228, "lr": 3.265185363140928e-05, "epoch": 2.7842447141637123, "percentage": 92.8, "elapsed_time": "21:02:35", "remaining_time": "1:37:54", "throughput": 63439.16, "total_tokens": 4805868800} |
| {"current_steps": 13460, "total_steps": 14493, "loss": 0.2285, "lr": 3.26448935448656e-05, "epoch": 2.786315053958231, "percentage": 92.87, "elapsed_time": "21:03:27", "remaining_time": "1:36:57", "throughput": 63444.15, "total_tokens": 4809520512} |
| {"current_steps": 13470, "total_steps": 14493, "loss": 0.2295, "lr": 3.263793790727256e-05, "epoch": 2.7883853937527494, "percentage": 92.94, "elapsed_time": "21:04:16", "remaining_time": "1:36:01", "throughput": 63449.66, "total_tokens": 4813060096} |
| {"current_steps": 13480, "total_steps": 14493, "loss": 0.2286, "lr": 3.2630986713892495e-05, "epoch": 2.7904557335472684, "percentage": 93.01, "elapsed_time": "21:05:06", "remaining_time": "1:35:04", "throughput": 63455.07, "total_tokens": 4816640384} |
| {"current_steps": 13490, "total_steps": 14493, "loss": 0.2274, "lr": 3.26240399599948e-05, "epoch": 2.7925260733417874, "percentage": 93.08, "elapsed_time": "21:05:53", "remaining_time": "1:34:07", "throughput": 63462.1, "total_tokens": 4820197504} |
| {"current_steps": 13500, "total_steps": 14493, "loss": 0.2278, "lr": 3.2617097640855914e-05, "epoch": 2.794596413136306, "percentage": 93.15, "elapsed_time": "21:06:43", "remaining_time": "1:33:10", "throughput": 63468.08, "total_tokens": 4823768320} |
| {"current_steps": 13510, "total_steps": 14493, "loss": 0.2278, "lr": 3.2610159751759314e-05, "epoch": 2.796666752930825, "percentage": 93.22, "elapsed_time": "21:07:32", "remaining_time": "1:32:13", "throughput": 63473.78, "total_tokens": 4827355008} |
| {"current_steps": 13520, "total_steps": 14493, "loss": 0.2296, "lr": 3.26032262879955e-05, "epoch": 2.7987370927253434, "percentage": 93.29, "elapsed_time": "21:08:21", "remaining_time": "1:31:16", "throughput": 63480.0, "total_tokens": 4830933888} |
| {"current_steps": 13530, "total_steps": 14493, "loss": 0.2272, "lr": 3.259629724486198e-05, "epoch": 2.8008074325198624, "percentage": 93.36, "elapsed_time": "21:09:10", "remaining_time": "1:30:20", "throughput": 63486.47, "total_tokens": 4834513152} |
| {"current_steps": 13540, "total_steps": 14493, "loss": 0.2272, "lr": 3.258937261766323e-05, "epoch": 2.802877772314381, "percentage": 93.42, "elapsed_time": "21:09:58", "remaining_time": "1:29:23", "throughput": 63492.23, "total_tokens": 4838040320} |
| {"current_steps": 13550, "total_steps": 14493, "loss": 0.229, "lr": 3.258245240171074e-05, "epoch": 2.8049481121089, "percentage": 93.49, "elapsed_time": "21:10:47", "remaining_time": "1:28:26", "throughput": 63498.82, "total_tokens": 4841627008} |
| {"current_steps": 13560, "total_steps": 14493, "loss": 0.2261, "lr": 3.2575536592322935e-05, "epoch": 2.807018451903419, "percentage": 93.56, "elapsed_time": "21:11:35", "remaining_time": "1:27:29", "throughput": 63505.68, "total_tokens": 4845221632} |
| {"current_steps": 13570, "total_steps": 14493, "loss": 0.2282, "lr": 3.256862518482523e-05, "epoch": 2.8090887916979375, "percentage": 93.63, "elapsed_time": "21:12:25", "remaining_time": "1:26:32", "throughput": 63511.72, "total_tokens": 4848850944} |
| {"current_steps": 13580, "total_steps": 14493, "loss": 0.2282, "lr": 3.256171817454994e-05, "epoch": 2.811159131492456, "percentage": 93.7, "elapsed_time": "21:13:13", "remaining_time": "1:25:35", "throughput": 63519.34, "total_tokens": 4852435456} |
| {"current_steps": 13590, "total_steps": 14493, "loss": 0.229, "lr": 3.255481555683633e-05, "epoch": 2.813229471286975, "percentage": 93.77, "elapsed_time": "21:14:00", "remaining_time": "1:24:39", "throughput": 63525.93, "total_tokens": 4855949952} |
| {"current_steps": 13600, "total_steps": 14493, "loss": 0.2274, "lr": 3.254791732703057e-05, "epoch": 2.815299811081494, "percentage": 93.84, "elapsed_time": "21:14:49", "remaining_time": "1:23:42", "throughput": 63532.21, "total_tokens": 4859569152} |
| {"current_steps": 13610, "total_steps": 14493, "loss": 0.2284, "lr": 3.254102348048575e-05, "epoch": 2.8173701508760125, "percentage": 93.91, "elapsed_time": "21:15:39", "remaining_time": "1:22:45", "throughput": 63538.0, "total_tokens": 4863158528} |
| {"current_steps": 13620, "total_steps": 14493, "loss": 0.2287, "lr": 3.25341340125618e-05, "epoch": 2.819440490670531, "percentage": 93.98, "elapsed_time": "21:16:31", "remaining_time": "1:21:49", "throughput": 63543.13, "total_tokens": 4866850176} |
| {"current_steps": 13630, "total_steps": 14493, "loss": 0.2279, "lr": 3.2527248918625575e-05, "epoch": 2.82151083046505, "percentage": 94.05, "elapsed_time": "21:17:18", "remaining_time": "1:20:52", "throughput": 63549.28, "total_tokens": 4870330240} |
| {"current_steps": 13640, "total_steps": 14493, "loss": 0.2283, "lr": 3.252036819405075e-05, "epoch": 2.823581170259569, "percentage": 94.11, "elapsed_time": "21:18:04", "remaining_time": "1:19:55", "throughput": 63557.42, "total_tokens": 4873863680} |
| {"current_steps": 13650, "total_steps": 14493, "loss": 0.2274, "lr": 3.251349183421788e-05, "epoch": 2.8256515100540875, "percentage": 94.18, "elapsed_time": "21:18:52", "remaining_time": "1:18:58", "throughput": 63564.01, "total_tokens": 4877403520} |
| {"current_steps": 13660, "total_steps": 14493, "loss": 0.2292, "lr": 3.250661983451434e-05, "epoch": 2.8277218498486065, "percentage": 94.25, "elapsed_time": "21:19:39", "remaining_time": "1:18:02", "throughput": 63570.29, "total_tokens": 4880922752} |
| {"current_steps": 13670, "total_steps": 14493, "loss": 0.2287, "lr": 3.2499752190334326e-05, "epoch": 2.829792189643125, "percentage": 94.32, "elapsed_time": "21:20:28", "remaining_time": "1:17:05", "throughput": 63576.33, "total_tokens": 4884486656} |
| {"current_steps": 13680, "total_steps": 14493, "loss": 0.2278, "lr": 3.2492888897078834e-05, "epoch": 2.831862529437644, "percentage": 94.39, "elapsed_time": "21:21:18", "remaining_time": "1:16:08", "throughput": 63581.77, "total_tokens": 4888045824} |
| {"current_steps": 13690, "total_steps": 14493, "loss": 0.2296, "lr": 3.248602995015567e-05, "epoch": 2.8339328692321626, "percentage": 94.46, "elapsed_time": "21:22:09", "remaining_time": "1:15:12", "throughput": 63586.8, "total_tokens": 4891671552} |
| {"current_steps": 13700, "total_steps": 14493, "loss": 0.2297, "lr": 3.247917534497943e-05, "epoch": 2.8360032090266816, "percentage": 94.53, "elapsed_time": "21:22:58", "remaining_time": "1:14:15", "throughput": 63592.65, "total_tokens": 4895241600} |
| {"current_steps": 13710, "total_steps": 14493, "loss": 0.2292, "lr": 3.247232507697145e-05, "epoch": 2.8380735488212006, "percentage": 94.6, "elapsed_time": "21:23:46", "remaining_time": "1:13:19", "throughput": 63600.31, "total_tokens": 4898908544} |
| {"current_steps": 13720, "total_steps": 14493, "loss": 0.2292, "lr": 3.246547914155985e-05, "epoch": 2.840143888615719, "percentage": 94.67, "elapsed_time": "21:24:36", "remaining_time": "1:12:22", "throughput": 63606.25, "total_tokens": 4902523648} |
| {"current_steps": 13730, "total_steps": 14493, "loss": 0.2271, "lr": 3.245863753417949e-05, "epoch": 2.8422142284102376, "percentage": 94.74, "elapsed_time": "21:25:24", "remaining_time": "1:11:25", "throughput": 63611.95, "total_tokens": 4906065280} |
| {"current_steps": 13740, "total_steps": 14493, "loss": 0.2298, "lr": 3.2451800250271944e-05, "epoch": 2.8442845682047566, "percentage": 94.8, "elapsed_time": "21:26:15", "remaining_time": "1:10:29", "throughput": 63617.02, "total_tokens": 4909645952} |
| {"current_steps": 13750, "total_steps": 14493, "loss": 0.2301, "lr": 3.244496728528553e-05, "epoch": 2.8463549079992756, "percentage": 94.87, "elapsed_time": "21:27:07", "remaining_time": "1:09:33", "throughput": 63621.77, "total_tokens": 4913324800} |
| {"current_steps": 13760, "total_steps": 14493, "loss": 0.2289, "lr": 3.243813863467525e-05, "epoch": 2.848425247793794, "percentage": 94.94, "elapsed_time": "21:27:57", "remaining_time": "1:08:36", "throughput": 63627.32, "total_tokens": 4916930432} |
| {"current_steps": 13770, "total_steps": 14493, "loss": 0.2275, "lr": 3.243131429390281e-05, "epoch": 2.8504955875883127, "percentage": 95.01, "elapsed_time": "21:28:44", "remaining_time": "1:07:39", "throughput": 63634.64, "total_tokens": 4920517120} |
| {"current_steps": 13780, "total_steps": 14493, "loss": 0.2303, "lr": 3.2424494258436594e-05, "epoch": 2.8525659273828317, "percentage": 95.08, "elapsed_time": "21:29:35", "remaining_time": "1:06:43", "throughput": 63638.94, "total_tokens": 4924121984} |
| {"current_steps": 13790, "total_steps": 14493, "loss": 0.2279, "lr": 3.241767852375166e-05, "epoch": 2.8546362671773506, "percentage": 95.15, "elapsed_time": "21:30:27", "remaining_time": "1:05:47", "throughput": 63643.99, "total_tokens": 4927791232} |
| {"current_steps": 13800, "total_steps": 14493, "loss": 0.227, "lr": 3.241086708532971e-05, "epoch": 2.856706606971869, "percentage": 95.22, "elapsed_time": "21:31:18", "remaining_time": "1:04:50", "throughput": 63648.67, "total_tokens": 4931373952} |
| {"current_steps": 13810, "total_steps": 14493, "loss": 0.2288, "lr": 3.24040599386591e-05, "epoch": 2.858776946766388, "percentage": 95.29, "elapsed_time": "21:32:07", "remaining_time": "1:03:54", "throughput": 63654.28, "total_tokens": 4934933120} |
| {"current_steps": 13820, "total_steps": 14493, "loss": 0.2272, "lr": 3.23972570792348e-05, "epoch": 2.8608472865609067, "percentage": 95.36, "elapsed_time": "21:32:54", "remaining_time": "1:02:57", "throughput": 63660.35, "total_tokens": 4938412416} |
| {"current_steps": 13830, "total_steps": 14493, "loss": 0.2285, "lr": 3.239045850255842e-05, "epoch": 2.8629176263554257, "percentage": 95.43, "elapsed_time": "21:33:45", "remaining_time": "1:02:01", "throughput": 63665.31, "total_tokens": 4942048512} |
| {"current_steps": 13840, "total_steps": 14493, "loss": 0.2272, "lr": 3.238366420413817e-05, "epoch": 2.864987966149944, "percentage": 95.49, "elapsed_time": "21:34:34", "remaining_time": "1:01:04", "throughput": 63671.14, "total_tokens": 4945645184} |
| {"current_steps": 13850, "total_steps": 14493, "loss": 0.2306, "lr": 3.237687417948882e-05, "epoch": 2.867058305944463, "percentage": 95.56, "elapsed_time": "21:35:24", "remaining_time": "1:00:08", "throughput": 63675.88, "total_tokens": 4949189376} |
| {"current_steps": 13860, "total_steps": 14493, "loss": 0.2281, "lr": 3.2370088424131776e-05, "epoch": 2.869128645738982, "percentage": 95.63, "elapsed_time": "21:36:15", "remaining_time": "0:59:12", "throughput": 63680.9, "total_tokens": 4952816640} |
| {"current_steps": 13870, "total_steps": 14493, "loss": 0.2301, "lr": 3.236330693359497e-05, "epoch": 2.8711989855335007, "percentage": 95.7, "elapsed_time": "21:37:03", "remaining_time": "0:58:15", "throughput": 63687.32, "total_tokens": 4956341120} |
| {"current_steps": 13880, "total_steps": 14493, "loss": 0.2302, "lr": 3.2356529703412894e-05, "epoch": 2.8732693253280193, "percentage": 95.77, "elapsed_time": "21:37:52", "remaining_time": "0:57:19", "throughput": 63693.02, "total_tokens": 4959944064} |
| {"current_steps": 13890, "total_steps": 14493, "loss": 0.229, "lr": 3.234975672912661e-05, "epoch": 2.8753396651225382, "percentage": 95.84, "elapsed_time": "21:38:44", "remaining_time": "0:56:22", "throughput": 63698.3, "total_tokens": 4963646464} |
| {"current_steps": 13900, "total_steps": 14493, "loss": 0.2301, "lr": 3.234298800628368e-05, "epoch": 2.8774100049170572, "percentage": 95.91, "elapsed_time": "21:39:36", "remaining_time": "0:55:26", "throughput": 63702.43, "total_tokens": 4967321216} |
| {"current_steps": 13910, "total_steps": 14493, "loss": 0.2283, "lr": 3.2336223530438195e-05, "epoch": 2.8794803447115758, "percentage": 95.98, "elapsed_time": "21:40:23", "remaining_time": "0:54:30", "throughput": 63709.96, "total_tokens": 4970843264} |
| {"current_steps": 13920, "total_steps": 14493, "loss": 0.2262, "lr": 3.232946329715076e-05, "epoch": 2.8815506845060943, "percentage": 96.05, "elapsed_time": "21:41:11", "remaining_time": "0:53:33", "throughput": 63715.76, "total_tokens": 4974406400} |
| {"current_steps": 13930, "total_steps": 14493, "loss": 0.2261, "lr": 3.2322707301988456e-05, "epoch": 2.8836210243006133, "percentage": 96.12, "elapsed_time": "21:42:01", "remaining_time": "0:52:37", "throughput": 63720.78, "total_tokens": 4977989376} |
| {"current_steps": 13940, "total_steps": 14493, "loss": 0.2277, "lr": 3.231595554052488e-05, "epoch": 2.8856913640951323, "percentage": 96.18, "elapsed_time": "21:42:50", "remaining_time": "0:51:41", "throughput": 63726.63, "total_tokens": 4981553536} |
| {"current_steps": 13950, "total_steps": 14493, "loss": 0.2295, "lr": 3.230920800834005e-05, "epoch": 2.887761703889651, "percentage": 96.25, "elapsed_time": "21:43:40", "remaining_time": "0:50:44", "throughput": 63732.23, "total_tokens": 4985170944} |
| {"current_steps": 13960, "total_steps": 14493, "loss": 0.2289, "lr": 3.2302464701020486e-05, "epoch": 2.88983204368417, "percentage": 96.32, "elapsed_time": "21:44:29", "remaining_time": "0:49:48", "throughput": 63737.84, "total_tokens": 4988749824} |
| {"current_steps": 13970, "total_steps": 14493, "loss": 0.2282, "lr": 3.2295725614159126e-05, "epoch": 2.8919023834786883, "percentage": 96.39, "elapsed_time": "21:45:18", "remaining_time": "0:48:52", "throughput": 63743.28, "total_tokens": 4992286464} |
| {"current_steps": 13980, "total_steps": 14493, "loss": 0.2269, "lr": 3.228899074335536e-05, "epoch": 2.8939727232732073, "percentage": 96.46, "elapsed_time": "21:46:07", "remaining_time": "0:47:55", "throughput": 63749.2, "total_tokens": 4995865216} |
| {"current_steps": 13990, "total_steps": 14493, "loss": 0.2285, "lr": 3.228226008421498e-05, "epoch": 2.896043063067726, "percentage": 96.53, "elapsed_time": "21:46:53", "remaining_time": "0:46:59", "throughput": 63756.8, "total_tokens": 4999389952} |
| {"current_steps": 14000, "total_steps": 14493, "loss": 0.2291, "lr": 3.2275533632350193e-05, "epoch": 2.898113402862245, "percentage": 96.6, "elapsed_time": "21:47:39", "remaining_time": "0:46:02", "throughput": 63764.2, "total_tokens": 5002905856} |
| {"current_steps": 14010, "total_steps": 14493, "loss": 0.2267, "lr": 3.226881138337963e-05, "epoch": 2.9001837426567634, "percentage": 96.67, "elapsed_time": "21:48:28", "remaining_time": "0:45:06", "throughput": 63769.62, "total_tokens": 5006487040} |
| {"current_steps": 14020, "total_steps": 14493, "loss": 0.2301, "lr": 3.2262093332928256e-05, "epoch": 2.9022540824512824, "percentage": 96.74, "elapsed_time": "21:49:20", "remaining_time": "0:44:10", "throughput": 63773.55, "total_tokens": 5010058880} |
| {"current_steps": 14030, "total_steps": 14493, "loss": 0.2293, "lr": 3.225537947662746e-05, "epoch": 2.904324422245801, "percentage": 96.81, "elapsed_time": "21:50:09", "remaining_time": "0:43:14", "throughput": 63779.04, "total_tokens": 5013626112} |
| {"current_steps": 14040, "total_steps": 14493, "loss": 0.2269, "lr": 3.224866981011494e-05, "epoch": 2.90639476204032, "percentage": 96.87, "elapsed_time": "21:50:58", "remaining_time": "0:42:17", "throughput": 63784.64, "total_tokens": 5017215872} |
| {"current_steps": 14050, "total_steps": 14493, "loss": 0.229, "lr": 3.22419643290348e-05, "epoch": 2.908465101834839, "percentage": 96.94, "elapsed_time": "21:51:50", "remaining_time": "0:41:21", "throughput": 63789.52, "total_tokens": 5020904832} |
| {"current_steps": 14060, "total_steps": 14493, "loss": 0.2275, "lr": 3.2235263029037446e-05, "epoch": 2.9105354416293574, "percentage": 97.01, "elapsed_time": "21:52:38", "remaining_time": "0:40:25", "throughput": 63795.12, "total_tokens": 5024432000} |
| {"current_steps": 14070, "total_steps": 14493, "loss": 0.23, "lr": 3.222856590577962e-05, "epoch": 2.912605781423876, "percentage": 97.08, "elapsed_time": "21:53:30", "remaining_time": "0:39:29", "throughput": 63800.14, "total_tokens": 5028099840} |
| {"current_steps": 14080, "total_steps": 14493, "loss": 0.2279, "lr": 3.222187295492436e-05, "epoch": 2.914676121218395, "percentage": 97.15, "elapsed_time": "21:54:15", "remaining_time": "0:38:33", "throughput": 63807.17, "total_tokens": 5031572096} |
| {"current_steps": 14090, "total_steps": 14493, "loss": 0.2295, "lr": 3.221518417214104e-05, "epoch": 2.916746461012914, "percentage": 97.22, "elapsed_time": "21:55:02", "remaining_time": "0:37:36", "throughput": 63814.56, "total_tokens": 5035134848} |
| {"current_steps": 14100, "total_steps": 14493, "loss": 0.2267, "lr": 3.22084995531053e-05, "epoch": 2.9188168008074324, "percentage": 97.29, "elapsed_time": "21:55:50", "remaining_time": "0:36:40", "throughput": 63820.93, "total_tokens": 5038719360} |
| {"current_steps": 14110, "total_steps": 14493, "loss": 0.2278, "lr": 3.220181909349907e-05, "epoch": 2.9208871406019514, "percentage": 97.36, "elapsed_time": "21:56:40", "remaining_time": "0:35:44", "throughput": 63826.58, "total_tokens": 5042349824} |
| {"current_steps": 14120, "total_steps": 14493, "loss": 0.2253, "lr": 3.219514278901053e-05, "epoch": 2.92295748039647, "percentage": 97.43, "elapsed_time": "21:57:30", "remaining_time": "0:34:48", "throughput": 63832.05, "total_tokens": 5045953024} |
| {"current_steps": 14130, "total_steps": 14493, "loss": 0.2273, "lr": 3.218847063533413e-05, "epoch": 2.925027820190989, "percentage": 97.5, "elapsed_time": "21:58:19", "remaining_time": "0:33:52", "throughput": 63837.45, "total_tokens": 5049532160} |
| {"current_steps": 14140, "total_steps": 14493, "loss": 0.2303, "lr": 3.218180262817055e-05, "epoch": 2.9270981599855075, "percentage": 97.56, "elapsed_time": "21:59:09", "remaining_time": "0:32:55", "throughput": 63842.27, "total_tokens": 5053076608} |
| {"current_steps": 14150, "total_steps": 14493, "loss": 0.2278, "lr": 3.217513876322674e-05, "epoch": 2.9291684997800265, "percentage": 97.63, "elapsed_time": "21:59:58", "remaining_time": "0:31:59", "throughput": 63848.02, "total_tokens": 5056675328} |
| {"current_steps": 14160, "total_steps": 14493, "loss": 0.2271, "lr": 3.216847903621581e-05, "epoch": 2.931238839574545, "percentage": 97.7, "elapsed_time": "22:00:47", "remaining_time": "0:31:03", "throughput": 63853.82, "total_tokens": 5060270080} |
| {"current_steps": 14170, "total_steps": 14493, "loss": 0.2306, "lr": 3.216182344285713e-05, "epoch": 2.933309179369064, "percentage": 97.77, "elapsed_time": "22:01:35", "remaining_time": "0:30:07", "throughput": 63858.89, "total_tokens": 5063728256} |
| {"current_steps": 14180, "total_steps": 14493, "loss": 0.2275, "lr": 3.215517197887625e-05, "epoch": 2.9353795191635825, "percentage": 97.84, "elapsed_time": "22:02:26", "remaining_time": "0:29:11", "throughput": 63863.18, "total_tokens": 5067351168} |
| {"current_steps": 14190, "total_steps": 14493, "loss": 0.2269, "lr": 3.214852464000488e-05, "epoch": 2.9374498589581015, "percentage": 97.91, "elapsed_time": "22:03:16", "remaining_time": "0:28:15", "throughput": 63867.86, "total_tokens": 5070880128} |
| {"current_steps": 14200, "total_steps": 14493, "loss": 0.2263, "lr": 3.2141881421980945e-05, "epoch": 2.9395201987526205, "percentage": 97.98, "elapsed_time": "22:04:06", "remaining_time": "0:27:19", "throughput": 63872.82, "total_tokens": 5074482688} |
| {"current_steps": 14210, "total_steps": 14493, "loss": 0.2288, "lr": 3.213524232054851e-05, "epoch": 2.941590538547139, "percentage": 98.05, "elapsed_time": "22:04:54", "remaining_time": "0:26:23", "throughput": 63878.59, "total_tokens": 5078012928} |
| {"current_steps": 14220, "total_steps": 14493, "loss": 0.2301, "lr": 3.21286073314578e-05, "epoch": 2.9436608783416576, "percentage": 98.12, "elapsed_time": "22:05:43", "remaining_time": "0:25:27", "throughput": 63884.32, "total_tokens": 5081556608} |
| {"current_steps": 14230, "total_steps": 14493, "loss": 0.2303, "lr": 3.2121976450465155e-05, "epoch": 2.9457312181361766, "percentage": 98.19, "elapsed_time": "22:06:33", "remaining_time": "0:24:31", "throughput": 63889.06, "total_tokens": 5085159680} |
| {"current_steps": 14240, "total_steps": 14493, "loss": 0.2296, "lr": 3.211534967333308e-05, "epoch": 2.9478015579306955, "percentage": 98.25, "elapsed_time": "22:07:19", "remaining_time": "0:23:34", "throughput": 63896.88, "total_tokens": 5088685440} |
| {"current_steps": 14250, "total_steps": 14493, "loss": 0.2291, "lr": 3.210872699583019e-05, "epoch": 2.949871897725214, "percentage": 98.32, "elapsed_time": "22:08:09", "remaining_time": "0:22:38", "throughput": 63901.76, "total_tokens": 5092267776} |
| {"current_steps": 14260, "total_steps": 14493, "loss": 0.2275, "lr": 3.210210841373118e-05, "epoch": 2.951942237519733, "percentage": 98.39, "elapsed_time": "22:08:58", "remaining_time": "0:21:42", "throughput": 63907.06, "total_tokens": 5095844352} |
| {"current_steps": 14270, "total_steps": 14493, "loss": 0.2262, "lr": 3.2095493922816855e-05, "epoch": 2.9540125773142516, "percentage": 98.46, "elapsed_time": "22:09:47", "remaining_time": "0:20:46", "throughput": 63911.73, "total_tokens": 5099327616} |
| {"current_steps": 14280, "total_steps": 14493, "loss": 0.2287, "lr": 3.2088883518874105e-05, "epoch": 2.9560829171087706, "percentage": 98.53, "elapsed_time": "22:10:35", "remaining_time": "0:19:50", "throughput": 63917.14, "total_tokens": 5102841344} |
| {"current_steps": 14290, "total_steps": 14493, "loss": 0.2294, "lr": 3.208227719769589e-05, "epoch": 2.958153256903289, "percentage": 98.6, "elapsed_time": "22:11:26", "remaining_time": "0:18:54", "throughput": 63921.64, "total_tokens": 5106494208} |
| {"current_steps": 14300, "total_steps": 14493, "loss": 0.2273, "lr": 3.207567495508124e-05, "epoch": 2.960223596697808, "percentage": 98.67, "elapsed_time": "22:12:13", "remaining_time": "0:17:58", "throughput": 63928.0, "total_tokens": 5109989120} |
| {"current_steps": 14310, "total_steps": 14493, "loss": 0.2288, "lr": 3.2069076786835205e-05, "epoch": 2.9622939364923266, "percentage": 98.74, "elapsed_time": "22:13:01", "remaining_time": "0:17:02", "throughput": 63934.25, "total_tokens": 5113557248} |
| {"current_steps": 14320, "total_steps": 14493, "loss": 0.2276, "lr": 3.2062482688768904e-05, "epoch": 2.9643642762868456, "percentage": 98.81, "elapsed_time": "22:13:48", "remaining_time": "0:16:06", "throughput": 63940.32, "total_tokens": 5117071616} |
| {"current_steps": 14330, "total_steps": 14493, "loss": 0.2277, "lr": 3.205589265669947e-05, "epoch": 2.966434616081364, "percentage": 98.88, "elapsed_time": "22:14:38", "remaining_time": "0:15:10", "throughput": 63944.63, "total_tokens": 5120601728} |
| {"current_steps": 14340, "total_steps": 14493, "loss": 0.2281, "lr": 3.204930668645005e-05, "epoch": 2.968504955875883, "percentage": 98.94, "elapsed_time": "22:15:28", "remaining_time": "0:14:14", "throughput": 63950.03, "total_tokens": 5124235392} |
| {"current_steps": 14350, "total_steps": 14493, "loss": 0.2289, "lr": 3.20427247738498e-05, "epoch": 2.970575295670402, "percentage": 99.01, "elapsed_time": "22:16:16", "remaining_time": "0:13:18", "throughput": 63955.77, "total_tokens": 5127764224} |
| {"current_steps": 14360, "total_steps": 14493, "loss": 0.229, "lr": 3.2036146914733854e-05, "epoch": 2.9726456354649207, "percentage": 99.08, "elapsed_time": "22:17:03", "remaining_time": "0:12:23", "throughput": 63962.05, "total_tokens": 5131229952} |
| {"current_steps": 14370, "total_steps": 14493, "loss": 0.2273, "lr": 3.202957310494336e-05, "epoch": 2.974715975259439, "percentage": 99.15, "elapsed_time": "22:17:51", "remaining_time": "0:11:27", "throughput": 63967.15, "total_tokens": 5134756864} |
| {"current_steps": 14380, "total_steps": 14493, "loss": 0.2297, "lr": 3.202300334032542e-05, "epoch": 2.976786315053958, "percentage": 99.22, "elapsed_time": "22:18:41", "remaining_time": "0:10:31", "throughput": 63972.46, "total_tokens": 5138350208} |
| {"current_steps": 14390, "total_steps": 14493, "loss": 0.2283, "lr": 3.201643761673308e-05, "epoch": 2.978856654848477, "percentage": 99.29, "elapsed_time": "22:19:28", "remaining_time": "0:09:35", "throughput": 63979.06, "total_tokens": 5141879040} |
| {"current_steps": 14400, "total_steps": 14493, "loss": 0.2272, "lr": 3.200987593002536e-05, "epoch": 2.9809269946429957, "percentage": 99.36, "elapsed_time": "22:20:14", "remaining_time": "0:08:39", "throughput": 63985.1, "total_tokens": 5145345664} |
| {"current_steps": 14410, "total_steps": 14493, "loss": 0.2306, "lr": 3.200331827606721e-05, "epoch": 2.9829973344375147, "percentage": 99.43, "elapsed_time": "22:21:01", "remaining_time": "0:07:43", "throughput": 63991.78, "total_tokens": 5148865280} |
| {"current_steps": 14420, "total_steps": 14493, "loss": 0.2265, "lr": 3.199676465072951e-05, "epoch": 2.9850676742320332, "percentage": 99.5, "elapsed_time": "22:21:51", "remaining_time": "0:06:47", "throughput": 63996.15, "total_tokens": 5152433664} |
| {"current_steps": 14430, "total_steps": 14493, "loss": 0.229, "lr": 3.1990215049889046e-05, "epoch": 2.987138014026552, "percentage": 99.57, "elapsed_time": "22:22:40", "remaining_time": "0:05:51", "throughput": 64000.39, "total_tokens": 5155914880} |
| {"current_steps": 14440, "total_steps": 14493, "loss": 0.2285, "lr": 3.198366946942851e-05, "epoch": 2.9892083538210708, "percentage": 99.63, "elapsed_time": "22:23:32", "remaining_time": "0:04:55", "throughput": 64004.64, "total_tokens": 5159564288} |
| {"current_steps": 14450, "total_steps": 14493, "loss": 0.2305, "lr": 3.1977127905236514e-05, "epoch": 2.9912786936155897, "percentage": 99.7, "elapsed_time": "22:24:20", "remaining_time": "0:04:00", "throughput": 64010.73, "total_tokens": 5163115008} |
| {"current_steps": 14460, "total_steps": 14493, "loss": 0.2285, "lr": 3.197059035320752e-05, "epoch": 2.9933490334101083, "percentage": 99.77, "elapsed_time": "22:25:11", "remaining_time": "0:03:04", "throughput": 64014.97, "total_tokens": 5166720896} |
| {"current_steps": 14470, "total_steps": 14493, "loss": 0.2269, "lr": 3.196405680924189e-05, "epoch": 2.9954193732046273, "percentage": 99.84, "elapsed_time": "22:26:02", "remaining_time": "0:02:08", "throughput": 64019.29, "total_tokens": 5170340352} |
| {"current_steps": 14480, "total_steps": 14493, "loss": 0.2296, "lr": 3.195752726924582e-05, "epoch": 2.997489712999146, "percentage": 99.91, "elapsed_time": "22:26:51", "remaining_time": "0:01:12", "throughput": 64024.18, "total_tokens": 5173915648} |
| {"current_steps": 14490, "total_steps": 14493, "loss": 0.2276, "lr": 3.195100172913139e-05, "epoch": 2.9995600527936648, "percentage": 99.98, "elapsed_time": "22:27:40", "remaining_time": "0:00:16", "throughput": 64030.0, "total_tokens": 5177502976} |
| {"current_steps": 14493, "total_steps": 14493, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "22:28:34", "remaining_time": "0:00:00", "throughput": 63996.97, "total_tokens": 5178280448} |
|
|