{"current_steps": 1, "total_steps": 906, "loss": 0.5378947257995605, "lr": 5e-05, "epoch": 0.0033208800332088003, "percentage": 0.11, "elapsed_time": "0:02:34", "remaining_time": "1 day, 14:56:11", "throughput": 1341.58, "total_tokens": 207792} {"current_steps": 2, "total_steps": 906, "loss": 1.0608220100402832, "lr": 4.9999849702094696e-05, "epoch": 0.006641760066417601, "percentage": 0.22, "elapsed_time": "0:05:54", "remaining_time": "1 day, 20:32:09", "throughput": 1153.75, "total_tokens": 409248} {"current_steps": 3, "total_steps": 906, "loss": 0.9686721563339233, "lr": 4.999939881018594e-05, "epoch": 0.009962640099626401, "percentage": 0.33, "elapsed_time": "0:11:21", "remaining_time": "2 days, 8:56:42", "throughput": 898.89, "total_tokens": 612208} {"current_steps": 4, "total_steps": 906, "loss": 0.93868488073349, "lr": 4.999864732969518e-05, "epoch": 0.013283520132835201, "percentage": 0.44, "elapsed_time": "0:18:12", "remaining_time": "2 days, 20:24:58", "throughput": 756.93, "total_tokens": 826744} {"current_steps": 5, "total_steps": 906, "loss": 0.7522749900817871, "lr": 4.999759526965809e-05, "epoch": 0.016604400166044003, "percentage": 0.55, "elapsed_time": "0:24:05", "remaining_time": "3 days, 0:22:31", "throughput": 712.51, "total_tokens": 1030224} {"current_steps": 6, "total_steps": 906, "loss": 0.671746015548706, "lr": 4.999624264272447e-05, "epoch": 0.019925280199252802, "percentage": 0.66, "elapsed_time": "0:30:48", "remaining_time": "3 days, 5:01:33", "throughput": 672.39, "total_tokens": 1242992} {"current_steps": 7, "total_steps": 906, "loss": 0.599233865737915, "lr": 4.999458946515808e-05, "epoch": 0.023246160232461604, "percentage": 0.77, "elapsed_time": "0:37:28", "remaining_time": "3 days, 8:13:24", "throughput": 648.85, "total_tokens": 1459104} {"current_steps": 8, "total_steps": 906, "loss": 0.5814499855041504, "lr": 4.9992635756836436e-05, "epoch": 0.026567040265670402, "percentage": 0.88, "elapsed_time": "0:43:40", "remaining_time": "3 days, 9:43:04", "throughput": 638.23, "total_tokens": 1672680} {"current_steps": 9, "total_steps": 906, "loss": 0.5495998859405518, "lr": 4.999038154125061e-05, "epoch": 0.029887920298879204, "percentage": 0.99, "elapsed_time": "0:49:28", "remaining_time": "3 days, 10:11:32", "throughput": 633.37, "total_tokens": 1880360} {"current_steps": 10, "total_steps": 906, "loss": 0.5153144598007202, "lr": 4.9987826845504914e-05, "epoch": 0.033208800332088007, "percentage": 1.1, "elapsed_time": "0:55:19", "remaining_time": "3 days, 10:36:38", "throughput": 628.92, "total_tokens": 2087496} {"current_steps": 11, "total_steps": 906, "loss": 0.5035845041275024, "lr": 4.998497170031657e-05, "epoch": 0.0365296803652968, "percentage": 1.21, "elapsed_time": "1:01:20", "remaining_time": "3 days, 11:10:21", "throughput": 623.0, "total_tokens": 2292672} {"current_steps": 12, "total_steps": 906, "loss": 0.48510533571243286, "lr": 4.9981816140015393e-05, "epoch": 0.039850560398505604, "percentage": 1.32, "elapsed_time": "1:07:13", "remaining_time": "3 days, 11:28:48", "throughput": 621.26, "total_tokens": 2506128} {"current_steps": 13, "total_steps": 906, "loss": 0.4942867159843445, "lr": 4.997836020254328e-05, "epoch": 0.043171440431714406, "percentage": 1.43, "elapsed_time": "1:12:54", "remaining_time": "3 days, 11:28:03", "throughput": 621.17, "total_tokens": 2717216} {"current_steps": 14, "total_steps": 906, "loss": 0.47794872522354126, "lr": 4.9974603929453857e-05, "epoch": 0.04649232046492321, "percentage": 1.55, "elapsed_time": "1:19:07", "remaining_time": "3 days, 12:01:04", "throughput": 616.18, "total_tokens": 2925136} {"current_steps": 15, "total_steps": 906, "loss": 0.4823008179664612, "lr": 4.9970547365911925e-05, "epoch": 0.049813200498132, "percentage": 1.66, "elapsed_time": "1:25:47", "remaining_time": "3 days, 12:55:34", "throughput": 609.07, "total_tokens": 3134936} {"current_steps": 16, "total_steps": 906, "loss": 0.4785187244415283, "lr": 4.996619056069291e-05, "epoch": 0.053134080531340805, "percentage": 1.77, "elapsed_time": "1:32:19", "remaining_time": "3 days, 13:35:26", "throughput": 604.62, "total_tokens": 3349208} {"current_steps": 17, "total_steps": 906, "loss": 0.48796018958091736, "lr": 4.996153356618233e-05, "epoch": 0.05645496056454961, "percentage": 1.88, "elapsed_time": "1:38:44", "remaining_time": "3 days, 14:03:35", "throughput": 601.09, "total_tokens": 3561152} {"current_steps": 18, "total_steps": 906, "loss": 0.46969473361968994, "lr": 4.9956576438375095e-05, "epoch": 0.05977584059775841, "percentage": 1.99, "elapsed_time": "1:45:16", "remaining_time": "3 days, 14:33:53", "throughput": 597.32, "total_tokens": 3773184} {"current_steps": 19, "total_steps": 906, "loss": 0.46969425678253174, "lr": 4.995131923687488e-05, "epoch": 0.0630967206309672, "percentage": 2.1, "elapsed_time": "1:51:58", "remaining_time": "3 days, 15:07:48", "throughput": 592.86, "total_tokens": 3983408} {"current_steps": 20, "total_steps": 906, "loss": 0.4789154529571533, "lr": 4.994576202489339e-05, "epoch": 0.06641760066417601, "percentage": 2.21, "elapsed_time": "1:58:46", "remaining_time": "3 days, 15:41:56", "throughput": 588.42, "total_tokens": 4193504} {"current_steps": 21, "total_steps": 906, "loss": 0.4771980047225952, "lr": 4.9939904869249616e-05, "epoch": 0.06973848069738481, "percentage": 2.32, "elapsed_time": "2:05:17", "remaining_time": "3 days, 16:00:22", "throughput": 585.52, "total_tokens": 4401856} {"current_steps": 22, "total_steps": 906, "loss": 0.4744207262992859, "lr": 4.9933747840369015e-05, "epoch": 0.0730593607305936, "percentage": 2.43, "elapsed_time": "2:11:26", "remaining_time": "3 days, 16:01:28", "throughput": 584.99, "total_tokens": 4613472} {"current_steps": 23, "total_steps": 906, "loss": 0.4628908038139343, "lr": 4.992729101228267e-05, "epoch": 0.07638024076380241, "percentage": 2.54, "elapsed_time": "2:17:42", "remaining_time": "3 days, 16:06:55", "throughput": 583.71, "total_tokens": 4823000} {"current_steps": 24, "total_steps": 906, "loss": 0.46453869342803955, "lr": 4.99205344626264e-05, "epoch": 0.07970112079701121, "percentage": 2.65, "elapsed_time": "2:24:36", "remaining_time": "3 days, 16:34:19", "throughput": 579.99, "total_tokens": 5032232} {"current_steps": 25, "total_steps": 906, "loss": 0.46282365918159485, "lr": 4.991347827263982e-05, "epoch": 0.08302200083022, "percentage": 2.76, "elapsed_time": "2:30:35", "remaining_time": "3 days, 16:26:34", "throughput": 579.9, "total_tokens": 5239424} {"current_steps": 26, "total_steps": 906, "loss": 0.47802141308784485, "lr": 4.9906122527165395e-05, "epoch": 0.08634288086342881, "percentage": 2.87, "elapsed_time": "2:36:46", "remaining_time": "3 days, 16:26:21", "throughput": 579.31, "total_tokens": 5449400} {"current_steps": 27, "total_steps": 906, "loss": 0.47468101978302, "lr": 4.9898467314647356e-05, "epoch": 0.0896637608966376, "percentage": 2.98, "elapsed_time": "2:43:47", "remaining_time": "3 days, 16:52:09", "throughput": 575.66, "total_tokens": 5657128} {"current_steps": 28, "total_steps": 906, "loss": 0.46311408281326294, "lr": 4.98905127271307e-05, "epoch": 0.09298464092984642, "percentage": 3.09, "elapsed_time": "2:50:07", "remaining_time": "3 days, 16:54:27", "throughput": 574.23, "total_tokens": 5861312} {"current_steps": 29, "total_steps": 906, "loss": 0.4600064754486084, "lr": 4.9882258860260065e-05, "epoch": 0.09630552096305521, "percentage": 3.2, "elapsed_time": "2:56:38", "remaining_time": "3 days, 17:01:39", "throughput": 572.61, "total_tokens": 6068552} {"current_steps": 30, "total_steps": 906, "loss": 0.4781966209411621, "lr": 4.9873705813278546e-05, "epoch": 0.099626400996264, "percentage": 3.31, "elapsed_time": "3:03:38", "remaining_time": "3 days, 17:22:24", "throughput": 569.62, "total_tokens": 6276440} {"current_steps": 31, "total_steps": 906, "loss": 0.4618116021156311, "lr": 4.9864853689026556e-05, "epoch": 0.10294728102947281, "percentage": 3.42, "elapsed_time": "3:10:12", "remaining_time": "3 days, 17:28:33", "throughput": 568.54, "total_tokens": 6488168} {"current_steps": 32, "total_steps": 906, "loss": 0.45203810930252075, "lr": 4.9855702593940556e-05, "epoch": 0.10626816106268161, "percentage": 3.53, "elapsed_time": "3:17:04", "remaining_time": "3 days, 17:42:23", "throughput": 566.02, "total_tokens": 6692640} {"current_steps": 33, "total_steps": 906, "loss": 0.45655691623687744, "lr": 4.984625263805178e-05, "epoch": 0.1095890410958904, "percentage": 3.64, "elapsed_time": "3:23:14", "remaining_time": "3 days, 17:36:39", "throughput": 566.56, "total_tokens": 6908856} {"current_steps": 34, "total_steps": 906, "loss": 0.452237069606781, "lr": 4.98365039349849e-05, "epoch": 0.11290992112909921, "percentage": 3.75, "elapsed_time": "3:30:02", "remaining_time": "3 days, 17:46:56", "throughput": 564.74, "total_tokens": 7117152} {"current_steps": 35, "total_steps": 906, "loss": 0.46304643154144287, "lr": 4.982645660195671e-05, "epoch": 0.11623080116230801, "percentage": 3.86, "elapsed_time": "3:37:12", "remaining_time": "3 days, 18:05:22", "throughput": 562.11, "total_tokens": 7325648} {"current_steps": 36, "total_steps": 906, "loss": 0.4689868092536926, "lr": 4.981611075977465e-05, "epoch": 0.11955168119551682, "percentage": 3.97, "elapsed_time": "3:44:42", "remaining_time": "3 days, 18:30:26", "throughput": 558.94, "total_tokens": 7535960} {"current_steps": 37, "total_steps": 906, "loss": 0.4629165530204773, "lr": 4.9805466532835376e-05, "epoch": 0.12287256122872561, "percentage": 4.08, "elapsed_time": "3:52:17", "remaining_time": "3 days, 18:55:47", "throughput": 555.84, "total_tokens": 7747184} {"current_steps": 38, "total_steps": 906, "loss": 0.4757240414619446, "lr": 4.9794524049123315e-05, "epoch": 0.1261934412619344, "percentage": 4.19, "elapsed_time": "3:59:19", "remaining_time": "3 days, 19:06:49", "throughput": 554.0, "total_tokens": 7955312} {"current_steps": 39, "total_steps": 906, "loss": 0.44948646426200867, "lr": 4.978328344020904e-05, "epoch": 0.1295143212951432, "percentage": 4.3, "elapsed_time": "4:05:45", "remaining_time": "3 days, 19:03:33", "throughput": 553.99, "total_tokens": 8169056} {"current_steps": 40, "total_steps": 906, "loss": 0.4762452244758606, "lr": 4.9771744841247756e-05, "epoch": 0.13283520132835203, "percentage": 4.42, "elapsed_time": "4:12:42", "remaining_time": "3 days, 19:11:01", "throughput": 552.28, "total_tokens": 8373792} {"current_steps": 41, "total_steps": 906, "loss": 0.4602937698364258, "lr": 4.975990839097764e-05, "epoch": 0.13615608136156082, "percentage": 4.53, "elapsed_time": "4:19:55", "remaining_time": "3 days, 19:23:53", "throughput": 550.03, "total_tokens": 8578168} {"current_steps": 42, "total_steps": 906, "loss": 0.4572892189025879, "lr": 4.9747774231718196e-05, "epoch": 0.13947696139476962, "percentage": 4.64, "elapsed_time": "4:26:44", "remaining_time": "3 days, 19:27:06", "throughput": 549.32, "total_tokens": 8791280} {"current_steps": 43, "total_steps": 906, "loss": 0.45722487568855286, "lr": 4.973534250936851e-05, "epoch": 0.1427978414279784, "percentage": 4.75, "elapsed_time": "4:33:50", "remaining_time": "3 days, 19:35:54", "throughput": 547.79, "total_tokens": 9000368} {"current_steps": 44, "total_steps": 906, "loss": 0.4636663794517517, "lr": 4.9722613373405536e-05, "epoch": 0.1461187214611872, "percentage": 4.86, "elapsed_time": "4:39:42", "remaining_time": "3 days, 19:19:47", "throughput": 548.42, "total_tokens": 9203936} {"current_steps": 45, "total_steps": 906, "loss": 0.4485476613044739, "lr": 4.970958697688226e-05, "epoch": 0.149439601494396, "percentage": 4.97, "elapsed_time": "4:45:56", "remaining_time": "3 days, 19:10:56", "throughput": 548.68, "total_tokens": 9413304} {"current_steps": 46, "total_steps": 906, "loss": 0.4744018316268921, "lr": 4.9696263476425905e-05, "epoch": 0.15276048152760482, "percentage": 5.08, "elapsed_time": "4:52:45", "remaining_time": "3 days, 19:13:26", "throughput": 548.08, "total_tokens": 9627504} {"current_steps": 47, "total_steps": 906, "loss": 0.44982996582984924, "lr": 4.9682643032235996e-05, "epoch": 0.15608136156081362, "percentage": 5.19, "elapsed_time": "4:59:23", "remaining_time": "3 days, 19:11:53", "throughput": 547.87, "total_tokens": 9841624} {"current_steps": 48, "total_steps": 906, "loss": 0.44015663862228394, "lr": 4.9668725808082486e-05, "epoch": 0.15940224159402241, "percentage": 5.3, "elapsed_time": "5:05:52", "remaining_time": "3 days, 19:07:28", "throughput": 547.67, "total_tokens": 10051056} {"current_steps": 49, "total_steps": 906, "loss": 0.4502023458480835, "lr": 4.965451197130373e-05, "epoch": 0.1627231216272312, "percentage": 5.41, "elapsed_time": "5:13:05", "remaining_time": "3 days, 19:15:50", "throughput": 546.25, "total_tokens": 10261536} {"current_steps": 50, "total_steps": 906, "loss": 0.4449482262134552, "lr": 4.9640001692804526e-05, "epoch": 0.16604400166044, "percentage": 5.52, "elapsed_time": "5:19:56", "remaining_time": "3 days, 19:17:31", "throughput": 545.57, "total_tokens": 10473216} {"current_steps": 51, "total_steps": 906, "loss": 0.46474742889404297, "lr": 4.9625195147054034e-05, "epoch": 0.16936488169364883, "percentage": 5.63, "elapsed_time": "5:27:03", "remaining_time": "3 days, 19:23:04", "throughput": 544.43, "total_tokens": 10683600} {"current_steps": 52, "total_steps": 906, "loss": 0.4434038996696472, "lr": 4.961009251208368e-05, "epoch": 0.17268576172685762, "percentage": 5.74, "elapsed_time": "5:33:31", "remaining_time": "3 days, 19:17:27", "throughput": 544.24, "total_tokens": 10891032} {"current_steps": 53, "total_steps": 906, "loss": 0.4552285075187683, "lr": 4.9594693969485006e-05, "epoch": 0.17600664176006642, "percentage": 5.85, "elapsed_time": "5:40:33", "remaining_time": "3 days, 19:20:57", "throughput": 543.2, "total_tokens": 11099160} {"current_steps": 54, "total_steps": 906, "loss": 0.4416283369064331, "lr": 4.957899970440752e-05, "epoch": 0.1793275217932752, "percentage": 5.96, "elapsed_time": "5:47:33", "remaining_time": "3 days, 19:23:46", "throughput": 542.16, "total_tokens": 11306176} {"current_steps": 55, "total_steps": 906, "loss": 0.4536556601524353, "lr": 4.956300990555643e-05, "epoch": 0.182648401826484, "percentage": 6.07, "elapsed_time": "5:54:23", "remaining_time": "3 days, 19:23:27", "throughput": 541.88, "total_tokens": 11522384} {"current_steps": 56, "total_steps": 906, "loss": 0.4556847810745239, "lr": 4.954672476519039e-05, "epoch": 0.18596928185969283, "percentage": 6.18, "elapsed_time": "6:00:46", "remaining_time": "3 days, 19:16:07", "throughput": 542.1, "total_tokens": 11734840} {"current_steps": 57, "total_steps": 906, "loss": 0.4614197015762329, "lr": 4.9530144479119215e-05, "epoch": 0.18929016189290163, "percentage": 6.29, "elapsed_time": "6:07:22", "remaining_time": "3 days, 19:11:57", "throughput": 541.98, "total_tokens": 11946520} {"current_steps": 58, "total_steps": 906, "loss": 0.4480130672454834, "lr": 4.951326924670148e-05, "epoch": 0.19261104192611042, "percentage": 6.4, "elapsed_time": "6:13:56", "remaining_time": "3 days, 19:07:16", "throughput": 541.84, "total_tokens": 12157000} {"current_steps": 59, "total_steps": 906, "loss": 0.45938652753829956, "lr": 4.9496099270842145e-05, "epoch": 0.19593192195931922, "percentage": 6.51, "elapsed_time": "6:20:05", "remaining_time": "3 days, 18:56:30", "throughput": 542.39, "total_tokens": 12369304} {"current_steps": 60, "total_steps": 906, "loss": 0.4392789602279663, "lr": 4.947863475799013e-05, "epoch": 0.199252801992528, "percentage": 6.62, "elapsed_time": "6:26:28", "remaining_time": "3 days, 18:49:21", "throughput": 542.75, "total_tokens": 12585656} {"current_steps": 61, "total_steps": 906, "loss": 0.45277348160743713, "lr": 4.9460875918135804e-05, "epoch": 0.2025736820257368, "percentage": 6.73, "elapsed_time": "6:32:53", "remaining_time": "3 days, 18:42:32", "throughput": 542.86, "total_tokens": 12797224} {"current_steps": 62, "total_steps": 906, "loss": 0.4558771252632141, "lr": 4.944282296480849e-05, "epoch": 0.20589456205894563, "percentage": 6.84, "elapsed_time": "6:40:31", "remaining_time": "3 days, 18:52:12", "throughput": 541.49, "total_tokens": 13012600} {"current_steps": 63, "total_steps": 906, "loss": 0.4451424777507782, "lr": 4.942447611507386e-05, "epoch": 0.20921544209215442, "percentage": 6.95, "elapsed_time": "6:47:51", "remaining_time": "3 days, 18:57:37", "throughput": 540.28, "total_tokens": 13221736} {"current_steps": 64, "total_steps": 906, "loss": 0.44465193152427673, "lr": 4.940583558953138e-05, "epoch": 0.21253632212536322, "percentage": 7.06, "elapsed_time": "6:55:17", "remaining_time": "3 days, 19:03:44", "throughput": 539.23, "total_tokens": 13436320} {"current_steps": 65, "total_steps": 906, "loss": 0.4602610468864441, "lr": 4.938690161231159e-05, "epoch": 0.21585720215857201, "percentage": 7.17, "elapsed_time": "7:02:36", "remaining_time": "3 days, 19:07:55", "throughput": 538.21, "total_tokens": 13647296} {"current_steps": 66, "total_steps": 906, "loss": 0.43508481979370117, "lr": 4.936767441107346e-05, "epoch": 0.2191780821917808, "percentage": 7.28, "elapsed_time": "7:09:55", "remaining_time": "3 days, 19:11:45", "throughput": 537.0, "total_tokens": 13852152} {"current_steps": 67, "total_steps": 906, "loss": 0.4550328850746155, "lr": 4.934815421700165e-05, "epoch": 0.22249896222498963, "percentage": 7.4, "elapsed_time": "7:16:51", "remaining_time": "3 days, 19:10:27", "throughput": 536.25, "total_tokens": 14055800} {"current_steps": 68, "total_steps": 906, "loss": 0.44379085302352905, "lr": 4.932834126480369e-05, "epoch": 0.22581984225819843, "percentage": 7.51, "elapsed_time": "7:23:43", "remaining_time": "3 days, 19:08:20", "throughput": 535.56, "total_tokens": 14258800} {"current_steps": 69, "total_steps": 906, "loss": 0.4452861547470093, "lr": 4.9308235792707194e-05, "epoch": 0.22914072229140722, "percentage": 7.62, "elapsed_time": "7:30:49", "remaining_time": "3 days, 19:08:38", "throughput": 535.15, "total_tokens": 14475376} {"current_steps": 70, "total_steps": 906, "loss": 0.4533378481864929, "lr": 4.9287838042456994e-05, "epoch": 0.23246160232461602, "percentage": 7.73, "elapsed_time": "7:37:50", "remaining_time": "3 days, 19:08:01", "throughput": 534.68, "total_tokens": 14688208} {"current_steps": 71, "total_steps": 906, "loss": 0.46097898483276367, "lr": 4.9267148259312224e-05, "epoch": 0.2357824823578248, "percentage": 7.84, "elapsed_time": "7:45:32", "remaining_time": "3 days, 19:15:05", "throughput": 533.3, "total_tokens": 14896536} {"current_steps": 72, "total_steps": 906, "loss": 0.4466809034347534, "lr": 4.924616669204337e-05, "epoch": 0.23910336239103364, "percentage": 7.95, "elapsed_time": "7:53:29", "remaining_time": "3 days, 19:24:33", "throughput": 531.81, "total_tokens": 15108192} {"current_steps": 73, "total_steps": 906, "loss": 0.44482558965682983, "lr": 4.9224893592929275e-05, "epoch": 0.24242424242424243, "percentage": 8.06, "elapsed_time": "8:00:26", "remaining_time": "3 days, 19:22:16", "throughput": 531.4, "total_tokens": 15318296} {"current_steps": 74, "total_steps": 906, "loss": 0.43905580043792725, "lr": 4.920332921775412e-05, "epoch": 0.24574512245745123, "percentage": 8.17, "elapsed_time": "8:06:22", "remaining_time": "3 days, 19:08:22", "throughput": 532.04, "total_tokens": 15526200} {"current_steps": 75, "total_steps": 906, "loss": 0.4451100528240204, "lr": 4.9181473825804346e-05, "epoch": 0.24906600249066002, "percentage": 8.28, "elapsed_time": "8:12:44", "remaining_time": "3 days, 18:59:34", "throughput": 532.17, "total_tokens": 15733400} {"current_steps": 76, "total_steps": 906, "loss": 0.453909695148468, "lr": 4.9159327679865516e-05, "epoch": 0.2523868825238688, "percentage": 8.39, "elapsed_time": "8:18:29", "remaining_time": "3 days, 18:43:58", "throughput": 532.84, "total_tokens": 15936648} {"current_steps": 77, "total_steps": 906, "loss": 0.4480288624763489, "lr": 4.913689104621917e-05, "epoch": 0.2557077625570776, "percentage": 8.5, "elapsed_time": "8:24:51", "remaining_time": "3 days, 18:35:29", "throughput": 533.11, "total_tokens": 16149016} {"current_steps": 78, "total_steps": 906, "loss": 0.4482975900173187, "lr": 4.9114164194639646e-05, "epoch": 0.2590286425902864, "percentage": 8.61, "elapsed_time": "8:31:34", "remaining_time": "3 days, 18:30:34", "throughput": 532.89, "total_tokens": 16356872} {"current_steps": 79, "total_steps": 906, "loss": 0.43813836574554443, "lr": 4.909114739839079e-05, "epoch": 0.2623495226234952, "percentage": 8.72, "elapsed_time": "8:37:49", "remaining_time": "3 days, 18:20:50", "throughput": 533.53, "total_tokens": 16576632} {"current_steps": 80, "total_steps": 906, "loss": 0.44829070568084717, "lr": 4.9067840934222705e-05, "epoch": 0.26567040265670405, "percentage": 8.83, "elapsed_time": "8:44:02", "remaining_time": "3 days, 18:10:41", "throughput": 533.88, "total_tokens": 16786416} {"current_steps": 81, "total_steps": 906, "loss": 0.4352768659591675, "lr": 4.9044245082368415e-05, "epoch": 0.26899128268991285, "percentage": 8.94, "elapsed_time": "8:49:17", "remaining_time": "3 days, 17:50:54", "throughput": 535.26, "total_tokens": 16998336} {"current_steps": 82, "total_steps": 906, "loss": 0.4634632468223572, "lr": 4.9020360126540474e-05, "epoch": 0.27231216272312164, "percentage": 9.05, "elapsed_time": "8:55:18", "remaining_time": "3 days, 17:39:15", "throughput": 535.72, "total_tokens": 17206720} {"current_steps": 83, "total_steps": 906, "loss": 0.4414184093475342, "lr": 4.8996186353927606e-05, "epoch": 0.27563304275633044, "percentage": 9.16, "elapsed_time": "9:01:18", "remaining_time": "3 days, 17:27:25", "throughput": 536.14, "total_tokens": 17412896} {"current_steps": 84, "total_steps": 906, "loss": 0.44793516397476196, "lr": 4.897172405519119e-05, "epoch": 0.27895392278953923, "percentage": 9.27, "elapsed_time": "9:07:57", "remaining_time": "3 days, 17:22:05", "throughput": 536.13, "total_tokens": 17626504} {"current_steps": 85, "total_steps": 906, "loss": 0.4464322030544281, "lr": 4.894697352446182e-05, "epoch": 0.282274802822748, "percentage": 9.38, "elapsed_time": "9:13:44", "remaining_time": "3 days, 17:08:30", "throughput": 536.94, "total_tokens": 17839720} {"current_steps": 86, "total_steps": 906, "loss": 0.4390932321548462, "lr": 4.892193505933572e-05, "epoch": 0.2855956828559568, "percentage": 9.49, "elapsed_time": "9:19:47", "remaining_time": "3 days, 16:57:29", "throughput": 537.53, "total_tokens": 18054216} {"current_steps": 87, "total_steps": 906, "loss": 0.4580715596675873, "lr": 4.889660896087119e-05, "epoch": 0.2889165628891656, "percentage": 9.6, "elapsed_time": "9:25:29", "remaining_time": "3 days, 16:43:21", "throughput": 538.27, "total_tokens": 18262984} {"current_steps": 88, "total_steps": 906, "loss": 0.4441770315170288, "lr": 4.887099553358502e-05, "epoch": 0.2922374429223744, "percentage": 9.71, "elapsed_time": "9:31:34", "remaining_time": "3 days, 16:33:00", "throughput": 538.95, "total_tokens": 18482720} {"current_steps": 89, "total_steps": 906, "loss": 0.4445023536682129, "lr": 4.884509508544874e-05, "epoch": 0.2955583229555832, "percentage": 9.82, "elapsed_time": "9:37:37", "remaining_time": "3 days, 16:22:23", "throughput": 539.35, "total_tokens": 18692240} {"current_steps": 90, "total_steps": 906, "loss": 0.43760842084884644, "lr": 4.8818907927885014e-05, "epoch": 0.298879202988792, "percentage": 9.93, "elapsed_time": "9:43:11", "remaining_time": "3 days, 16:07:40", "throughput": 540.26, "total_tokens": 18904696} {"current_steps": 91, "total_steps": 906, "loss": 0.45703399181365967, "lr": 4.879243437576383e-05, "epoch": 0.30220008302200085, "percentage": 10.04, "elapsed_time": "9:48:32", "remaining_time": "3 days, 15:51:04", "throughput": 541.02, "total_tokens": 19104848} {"current_steps": 92, "total_steps": 906, "loss": 0.4443628787994385, "lr": 4.876567474739875e-05, "epoch": 0.30552096305520965, "percentage": 10.15, "elapsed_time": "9:53:48", "remaining_time": "3 days, 15:33:51", "throughput": 542.17, "total_tokens": 19316456} {"current_steps": 93, "total_steps": 906, "loss": 0.45608752965927124, "lr": 4.8738629364543045e-05, "epoch": 0.30884184308841844, "percentage": 10.26, "elapsed_time": "9:59:07", "remaining_time": "3 days, 15:17:28", "throughput": 543.3, "total_tokens": 19529968} {"current_steps": 94, "total_steps": 906, "loss": 0.45944929122924805, "lr": 4.8711298552385886e-05, "epoch": 0.31216272312162724, "percentage": 10.38, "elapsed_time": "10:04:03", "remaining_time": "3 days, 14:58:04", "throughput": 544.61, "total_tokens": 19738568} {"current_steps": 95, "total_steps": 906, "loss": 0.44822442531585693, "lr": 4.8683682639548365e-05, "epoch": 0.31548360315483603, "percentage": 10.49, "elapsed_time": "10:09:07", "remaining_time": "3 days, 14:39:59", "throughput": 545.87, "total_tokens": 19950248} {"current_steps": 96, "total_steps": 906, "loss": 0.4578169584274292, "lr": 4.8655781958079594e-05, "epoch": 0.31880448318804483, "percentage": 10.6, "elapsed_time": "10:14:13", "remaining_time": "3 days, 14:22:30", "throughput": 547.09, "total_tokens": 20162200} {"current_steps": 97, "total_steps": 906, "loss": 0.45215484499931335, "lr": 4.862759684345269e-05, "epoch": 0.3221253632212536, "percentage": 10.71, "elapsed_time": "10:19:27", "remaining_time": "3 days, 14:06:28", "throughput": 548.02, "total_tokens": 20368784} {"current_steps": 98, "total_steps": 906, "loss": 0.4573412537574768, "lr": 4.859912763456076e-05, "epoch": 0.3254462432544624, "percentage": 10.82, "elapsed_time": "10:24:56", "remaining_time": "3 days, 13:52:33", "throughput": 548.64, "total_tokens": 20571880} {"current_steps": 99, "total_steps": 906, "loss": 0.43494826555252075, "lr": 4.857037467371278e-05, "epoch": 0.3287671232876712, "percentage": 10.93, "elapsed_time": "10:30:39", "remaining_time": "3 days, 13:40:49", "throughput": 549.06, "total_tokens": 20776240} {"current_steps": 100, "total_steps": 906, "loss": 0.4539799094200134, "lr": 4.8541338306629545e-05, "epoch": 0.33208800332088, "percentage": 11.04, "elapsed_time": "10:36:12", "remaining_time": "3 days, 13:27:48", "throughput": 549.58, "total_tokens": 20978664} {"current_steps": 101, "total_steps": 906, "loss": 0.4432840347290039, "lr": 4.8512018882439475e-05, "epoch": 0.33540888335408886, "percentage": 11.15, "elapsed_time": "10:41:44", "remaining_time": "3 days, 13:14:53", "throughput": 550.25, "total_tokens": 21187080} {"current_steps": 102, "total_steps": 906, "loss": 0.4450823664665222, "lr": 4.84824167536744e-05, "epoch": 0.33872976338729766, "percentage": 11.26, "elapsed_time": "10:47:22", "remaining_time": "3 days, 13:02:53", "throughput": 550.94, "total_tokens": 21400168} {"current_steps": 103, "total_steps": 906, "loss": 0.4405674338340759, "lr": 4.8452532276265364e-05, "epoch": 0.34205064342050645, "percentage": 11.37, "elapsed_time": "10:52:44", "remaining_time": "3 days, 12:48:47", "throughput": 551.76, "total_tokens": 21609024} {"current_steps": 104, "total_steps": 906, "loss": 0.44187235832214355, "lr": 4.84223658095383e-05, "epoch": 0.34537152345371525, "percentage": 11.48, "elapsed_time": "10:58:44", "remaining_time": "3 days, 12:39:54", "throughput": 552.06, "total_tokens": 21820032} {"current_steps": 105, "total_steps": 906, "loss": 0.42703860998153687, "lr": 4.8391917716209765e-05, "epoch": 0.34869240348692404, "percentage": 11.59, "elapsed_time": "11:05:22", "remaining_time": "3 days, 12:35:51", "throughput": 551.84, "total_tokens": 22031008} {"current_steps": 106, "total_steps": 906, "loss": 0.4403926134109497, "lr": 4.836118836238253e-05, "epoch": 0.35201328352013284, "percentage": 11.7, "elapsed_time": "11:11:33", "remaining_time": "3 days, 12:28:22", "throughput": 552.18, "total_tokens": 22249104} {"current_steps": 107, "total_steps": 906, "loss": 0.4441004693508148, "lr": 4.833017811754119e-05, "epoch": 0.35533416355334163, "percentage": 11.81, "elapsed_time": "11:17:37", "remaining_time": "3 days, 12:20:04", "throughput": 552.53, "total_tokens": 22464824} {"current_steps": 108, "total_steps": 906, "loss": 0.44408392906188965, "lr": 4.829888735454773e-05, "epoch": 0.3586550435865504, "percentage": 11.92, "elapsed_time": "11:23:14", "remaining_time": "3 days, 12:08:21", "throughput": 553.11, "total_tokens": 22674264} {"current_steps": 109, "total_steps": 906, "loss": 0.4447093605995178, "lr": 4.8267316449637054e-05, "epoch": 0.3619759236197592, "percentage": 12.03, "elapsed_time": "11:28:45", "remaining_time": "3 days, 11:56:05", "throughput": 553.68, "total_tokens": 22880992} {"current_steps": 110, "total_steps": 906, "loss": 0.4409634470939636, "lr": 4.823546578241242e-05, "epoch": 0.365296803652968, "percentage": 12.14, "elapsed_time": "11:34:40", "remaining_time": "3 days, 11:46:56", "throughput": 554.0, "total_tokens": 23090920} {"current_steps": 111, "total_steps": 906, "loss": 0.4509497284889221, "lr": 4.820333573584091e-05, "epoch": 0.3686176836861768, "percentage": 12.25, "elapsed_time": "11:40:17", "remaining_time": "3 days, 11:35:34", "throughput": 554.53, "total_tokens": 23299840} {"current_steps": 112, "total_steps": 906, "loss": 0.45462414622306824, "lr": 4.817092669624883e-05, "epoch": 0.37193856371938566, "percentage": 12.36, "elapsed_time": "11:46:52", "remaining_time": "3 days, 11:31:12", "throughput": 554.42, "total_tokens": 23513992} {"current_steps": 113, "total_steps": 906, "loss": 0.45549196004867554, "lr": 4.813823905331704e-05, "epoch": 0.37525944375259446, "percentage": 12.47, "elapsed_time": "11:53:41", "remaining_time": "3 days, 11:28:31", "throughput": 554.08, "total_tokens": 23726736} {"current_steps": 114, "total_steps": 906, "loss": 0.4397251605987549, "lr": 4.810527320007627e-05, "epoch": 0.37858032378580325, "percentage": 12.58, "elapsed_time": "12:00:18", "remaining_time": "3 days, 11:24:12", "throughput": 553.99, "total_tokens": 23942584} {"current_steps": 115, "total_steps": 906, "loss": 0.4477549195289612, "lr": 4.8072029532902426e-05, "epoch": 0.38190120381901205, "percentage": 12.69, "elapsed_time": "12:05:53", "remaining_time": "3 days, 11:12:49", "throughput": 554.5, "total_tokens": 24150000} {"current_steps": 116, "total_steps": 906, "loss": 0.4334121644496918, "lr": 4.80385084515118e-05, "epoch": 0.38522208385222084, "percentage": 12.8, "elapsed_time": "12:11:42", "remaining_time": "3 days, 11:03:12", "throughput": 554.86, "total_tokens": 24359712} {"current_steps": 117, "total_steps": 906, "loss": 0.4370808005332947, "lr": 4.800471035895624e-05, "epoch": 0.38854296388542964, "percentage": 12.91, "elapsed_time": "12:18:15", "remaining_time": "3 days, 10:58:33", "throughput": 554.57, "total_tokens": 24565128} {"current_steps": 118, "total_steps": 906, "loss": 0.44406652450561523, "lr": 4.797063566161834e-05, "epoch": 0.39186384391863843, "percentage": 13.02, "elapsed_time": "12:24:56", "remaining_time": "3 days, 10:54:42", "throughput": 554.23, "total_tokens": 24772408} {"current_steps": 119, "total_steps": 906, "loss": 0.435397744178772, "lr": 4.7936284769206584e-05, "epoch": 0.3951847239518472, "percentage": 13.13, "elapsed_time": "12:30:53", "remaining_time": "3 days, 10:45:57", "throughput": 554.36, "total_tokens": 24975888} {"current_steps": 120, "total_steps": 906, "loss": 0.4524025619029999, "lr": 4.790165809475031e-05, "epoch": 0.398505603985056, "percentage": 13.25, "elapsed_time": "12:37:07", "remaining_time": "3 days, 10:39:12", "throughput": 554.35, "total_tokens": 25183072} {"current_steps": 121, "total_steps": 906, "loss": 0.4324600100517273, "lr": 4.786675605459487e-05, "epoch": 0.4018264840182648, "percentage": 13.36, "elapsed_time": "12:43:29", "remaining_time": "3 days, 10:33:13", "throughput": 554.36, "total_tokens": 25394712} {"current_steps": 122, "total_steps": 906, "loss": 0.43515023589134216, "lr": 4.783157906839655e-05, "epoch": 0.4051473640514736, "percentage": 13.47, "elapsed_time": "12:49:27", "remaining_time": "3 days, 10:24:42", "throughput": 554.49, "total_tokens": 25599232} {"current_steps": 123, "total_steps": 906, "loss": 0.45275765657424927, "lr": 4.779612755911752e-05, "epoch": 0.40846824408468246, "percentage": 13.58, "elapsed_time": "12:55:57", "remaining_time": "3 days, 10:19:38", "throughput": 554.45, "total_tokens": 25813984} {"current_steps": 124, "total_steps": 906, "loss": 0.42968207597732544, "lr": 4.77604019530208e-05, "epoch": 0.41178912411789126, "percentage": 13.69, "elapsed_time": "13:02:21", "remaining_time": "3 days, 10:13:51", "throughput": 554.43, "total_tokens": 26025368} {"current_steps": 125, "total_steps": 906, "loss": 0.4436509311199188, "lr": 4.772440267966508e-05, "epoch": 0.41511000415110005, "percentage": 13.8, "elapsed_time": "13:08:00", "remaining_time": "3 days, 10:03:27", "throughput": 554.84, "total_tokens": 26233184} {"current_steps": 126, "total_steps": 906, "loss": 0.4539909064769745, "lr": 4.7688130171899594e-05, "epoch": 0.41843088418430885, "percentage": 13.91, "elapsed_time": "13:13:42", "remaining_time": "3 days, 9:53:27", "throughput": 555.17, "total_tokens": 26438704} {"current_steps": 127, "total_steps": 906, "loss": 0.4468457102775574, "lr": 4.76515848658589e-05, "epoch": 0.42175176421751764, "percentage": 14.02, "elapsed_time": "13:20:11", "remaining_time": "3 days, 9:48:16", "throughput": 555.07, "total_tokens": 26649984} {"current_steps": 128, "total_steps": 906, "loss": 0.44136855006217957, "lr": 4.761476720095764e-05, "epoch": 0.42507264425072644, "percentage": 14.13, "elapsed_time": "13:26:23", "remaining_time": "3 days, 9:41:18", "throughput": 555.26, "total_tokens": 26865064} {"current_steps": 129, "total_steps": 906, "loss": 0.45262420177459717, "lr": 4.7577677619885234e-05, "epoch": 0.42839352428393523, "percentage": 14.24, "elapsed_time": "13:32:19", "remaining_time": "3 days, 9:32:49", "throughput": 555.45, "total_tokens": 27072168} {"current_steps": 130, "total_steps": 906, "loss": 0.44716838002204895, "lr": 4.754031656860059e-05, "epoch": 0.43171440431714403, "percentage": 14.35, "elapsed_time": "13:38:57", "remaining_time": "3 days, 9:28:33", "throughput": 555.31, "total_tokens": 27286552} {"current_steps": 131, "total_steps": 906, "loss": 0.447284072637558, "lr": 4.7502684496326746e-05, "epoch": 0.4350352843503528, "percentage": 14.46, "elapsed_time": "13:45:46", "remaining_time": "3 days, 9:25:16", "throughput": 555.03, "total_tokens": 27499640} {"current_steps": 132, "total_steps": 906, "loss": 0.44308850169181824, "lr": 4.746478185554541e-05, "epoch": 0.4383561643835616, "percentage": 14.57, "elapsed_time": "13:51:47", "remaining_time": "3 days, 9:17:19", "throughput": 555.21, "total_tokens": 27709024} {"current_steps": 133, "total_steps": 906, "loss": 0.44187185168266296, "lr": 4.7426609101991605e-05, "epoch": 0.44167704441677047, "percentage": 14.68, "elapsed_time": "13:57:59", "remaining_time": "3 days, 9:10:25", "throughput": 555.3, "total_tokens": 27920048} {"current_steps": 134, "total_steps": 906, "loss": 0.4379861354827881, "lr": 4.73881666946481e-05, "epoch": 0.44499792444997927, "percentage": 14.79, "elapsed_time": "14:04:06", "remaining_time": "3 days, 9:03:05", "throughput": 555.39, "total_tokens": 28128512} {"current_steps": 135, "total_steps": 906, "loss": 0.45955541729927063, "lr": 4.734945509573997e-05, "epoch": 0.44831880448318806, "percentage": 14.9, "elapsed_time": "14:09:50", "remaining_time": "3 days, 8:53:30", "throughput": 555.75, "total_tokens": 28337864} {"current_steps": 136, "total_steps": 906, "loss": 0.44429993629455566, "lr": 4.7310474770729e-05, "epoch": 0.45163968451639686, "percentage": 15.01, "elapsed_time": "14:15:53", "remaining_time": "3 days, 8:45:49", "throughput": 555.85, "total_tokens": 28544840} {"current_steps": 137, "total_steps": 906, "loss": 0.43550848960876465, "lr": 4.727122618830808e-05, "epoch": 0.45496056454960565, "percentage": 15.12, "elapsed_time": "14:21:57", "remaining_time": "3 days, 8:38:17", "throughput": 556.07, "total_tokens": 28758408} {"current_steps": 138, "total_steps": 906, "loss": 0.44725221395492554, "lr": 4.723170982039558e-05, "epoch": 0.45828144458281445, "percentage": 15.23, "elapsed_time": "14:27:50", "remaining_time": "3 days, 8:29:44", "throughput": 556.39, "total_tokens": 28971880} {"current_steps": 139, "total_steps": 906, "loss": 0.4348328709602356, "lr": 4.719192614212969e-05, "epoch": 0.46160232461602324, "percentage": 15.34, "elapsed_time": "14:34:19", "remaining_time": "3 days, 8:24:29", "throughput": 556.25, "total_tokens": 29180432} {"current_steps": 140, "total_steps": 906, "loss": 0.44152069091796875, "lr": 4.715187563186271e-05, "epoch": 0.46492320464923204, "percentage": 15.45, "elapsed_time": "14:41:05", "remaining_time": "3 days, 8:20:47", "throughput": 555.81, "total_tokens": 29382856} {"current_steps": 141, "total_steps": 906, "loss": 0.436160147190094, "lr": 4.711155877115523e-05, "epoch": 0.46824408468244083, "percentage": 15.56, "elapsed_time": "14:47:02", "remaining_time": "3 days, 8:12:41", "throughput": 555.97, "total_tokens": 29590312} {"current_steps": 142, "total_steps": 906, "loss": 0.4471568465232849, "lr": 4.707097604477045e-05, "epoch": 0.4715649647156496, "percentage": 15.67, "elapsed_time": "14:53:19", "remaining_time": "3 days, 8:06:21", "throughput": 556.06, "total_tokens": 29804528} {"current_steps": 143, "total_steps": 906, "loss": 0.45743924379348755, "lr": 4.703012794066827e-05, "epoch": 0.4748858447488584, "percentage": 15.78, "elapsed_time": "14:59:38", "remaining_time": "3 days, 8:00:10", "throughput": 555.94, "total_tokens": 30008576} {"current_steps": 144, "total_steps": 906, "loss": 0.44465208053588867, "lr": 4.6989014949999436e-05, "epoch": 0.47820672478206727, "percentage": 15.89, "elapsed_time": "15:05:42", "remaining_time": "3 days, 7:52:43", "throughput": 556.06, "total_tokens": 30217968} {"current_steps": 145, "total_steps": 906, "loss": 0.4434838891029358, "lr": 4.694763756709967e-05, "epoch": 0.48152760481527607, "percentage": 16.0, "elapsed_time": "15:11:55", "remaining_time": "3 days, 7:46:03", "throughput": 556.06, "total_tokens": 30425288} {"current_steps": 146, "total_steps": 906, "loss": 0.4252302050590515, "lr": 4.690599628948369e-05, "epoch": 0.48484848484848486, "percentage": 16.11, "elapsed_time": "15:17:55", "remaining_time": "3 days, 7:38:12", "throughput": 556.35, "total_tokens": 30640824} {"current_steps": 147, "total_steps": 906, "loss": 0.4438859820365906, "lr": 4.6864091617839235e-05, "epoch": 0.48816936488169366, "percentage": 16.23, "elapsed_time": "15:23:53", "remaining_time": "3 days, 7:30:18", "throughput": 556.48, "total_tokens": 30847888} {"current_steps": 148, "total_steps": 906, "loss": 0.4435650110244751, "lr": 4.682192405602106e-05, "epoch": 0.49149024491490245, "percentage": 16.34, "elapsed_time": "15:30:22", "remaining_time": "3 days, 7:25:00", "throughput": 556.48, "total_tokens": 31064104} {"current_steps": 149, "total_steps": 906, "loss": 0.43432003259658813, "lr": 4.677949411104485e-05, "epoch": 0.49481112494811125, "percentage": 16.45, "elapsed_time": "15:36:32", "remaining_time": "3 days, 7:18:08", "throughput": 556.48, "total_tokens": 31270280} {"current_steps": 150, "total_steps": 906, "loss": 0.43058010935783386, "lr": 4.673680229308117e-05, "epoch": 0.49813200498132004, "percentage": 16.56, "elapsed_time": "15:42:26", "remaining_time": "3 days, 7:09:53", "throughput": 556.8, "total_tokens": 31484800} {"current_steps": 151, "total_steps": 906, "loss": 0.4515884518623352, "lr": 4.669384911544927e-05, "epoch": 0.5014528850145289, "percentage": 16.67, "elapsed_time": "15:48:21", "remaining_time": "3 days, 7:01:47", "throughput": 556.9, "total_tokens": 31688168} {"current_steps": 152, "total_steps": 906, "loss": 0.44337350130081177, "lr": 4.665063509461097e-05, "epoch": 0.5047737650477376, "percentage": 16.78, "elapsed_time": "15:53:41", "remaining_time": "3 days, 6:50:49", "throughput": 557.47, "total_tokens": 31899192} {"current_steps": 153, "total_steps": 906, "loss": 0.42944586277008057, "lr": 4.660716075016442e-05, "epoch": 0.5080946450809465, "percentage": 16.89, "elapsed_time": "15:59:43", "remaining_time": "3 days, 6:43:20", "throughput": 557.71, "total_tokens": 32114600} {"current_steps": 154, "total_steps": 906, "loss": 0.43536609411239624, "lr": 4.656342660483782e-05, "epoch": 0.5114155251141552, "percentage": 17.0, "elapsed_time": "16:05:18", "remaining_time": "3 days, 6:33:41", "throughput": 558.09, "total_tokens": 32323696} {"current_steps": 155, "total_steps": 906, "loss": 0.4376128017902374, "lr": 4.6519433184483245e-05, "epoch": 0.5147364051473641, "percentage": 17.11, "elapsed_time": "16:10:38", "remaining_time": "3 days, 6:22:53", "throughput": 558.68, "total_tokens": 32536696} {"current_steps": 156, "total_steps": 906, "loss": 0.4368232488632202, "lr": 4.647518101807019e-05, "epoch": 0.5180572851805728, "percentage": 17.22, "elapsed_time": "16:15:50", "remaining_time": "3 days, 6:11:32", "throughput": 559.3, "total_tokens": 32747280} {"current_steps": 157, "total_steps": 906, "loss": 0.42630359530448914, "lr": 4.6430670637679295e-05, "epoch": 0.5213781652137817, "percentage": 17.33, "elapsed_time": "16:21:11", "remaining_time": "3 days, 6:00:57", "throughput": 559.85, "total_tokens": 32959224} {"current_steps": 158, "total_steps": 906, "loss": 0.4541800022125244, "lr": 4.638590257849591e-05, "epoch": 0.5246990452469904, "percentage": 17.44, "elapsed_time": "16:26:25", "remaining_time": "3 days, 5:49:56", "throughput": 560.37, "total_tokens": 33165992} {"current_steps": 159, "total_steps": 906, "loss": 0.4372981786727905, "lr": 4.634087737880367e-05, "epoch": 0.5280199252801993, "percentage": 17.55, "elapsed_time": "16:32:00", "remaining_time": "3 days, 5:40:33", "throughput": 560.75, "total_tokens": 33375824} {"current_steps": 160, "total_steps": 906, "loss": 0.4468112885951996, "lr": 4.6295595579978046e-05, "epoch": 0.5313408053134081, "percentage": 17.66, "elapsed_time": "16:37:04", "remaining_time": "3 days, 5:28:50", "throughput": 561.46, "total_tokens": 33589176} {"current_steps": 161, "total_steps": 906, "loss": 0.45006150007247925, "lr": 4.625005772647979e-05, "epoch": 0.5346616853466168, "percentage": 17.77, "elapsed_time": "16:42:23", "remaining_time": "3 days, 5:18:25", "throughput": 561.95, "total_tokens": 33797608} {"current_steps": 162, "total_steps": 906, "loss": 0.43324458599090576, "lr": 4.6204264365848426e-05, "epoch": 0.5379825653798257, "percentage": 17.88, "elapsed_time": "16:47:32", "remaining_time": "3 days, 5:07:14", "throughput": 562.41, "total_tokens": 33999224} {"current_steps": 163, "total_steps": 906, "loss": 0.4437130093574524, "lr": 4.615821604869564e-05, "epoch": 0.5413034454130344, "percentage": 17.99, "elapsed_time": "16:52:36", "remaining_time": "3 days, 4:55:46", "throughput": 563.1, "total_tokens": 34212168} {"current_steps": 164, "total_steps": 906, "loss": 0.4397727847099304, "lr": 4.611191332869869e-05, "epoch": 0.5446243254462433, "percentage": 18.1, "elapsed_time": "16:57:23", "remaining_time": "3 days, 4:43:03", "throughput": 563.86, "total_tokens": 34419888} {"current_steps": 165, "total_steps": 906, "loss": 0.4515122175216675, "lr": 4.606535676259372e-05, "epoch": 0.547945205479452, "percentage": 18.21, "elapsed_time": "17:02:55", "remaining_time": "3 days, 4:33:50", "throughput": 564.26, "total_tokens": 34631784} {"current_steps": 166, "total_steps": 906, "loss": 0.4467068612575531, "lr": 4.601854691016907e-05, "epoch": 0.5512660855126609, "percentage": 18.32, "elapsed_time": "17:08:07", "remaining_time": "3 days, 4:23:13", "throughput": 564.73, "total_tokens": 34836768} {"current_steps": 167, "total_steps": 906, "loss": 0.4417882263660431, "lr": 4.597148433425857e-05, "epoch": 0.5545869655458696, "percentage": 18.43, "elapsed_time": "17:13:40", "remaining_time": "3 days, 4:14:10", "throughput": 565.09, "total_tokens": 35047288} {"current_steps": 168, "total_steps": 906, "loss": 0.442172110080719, "lr": 4.5924169600734745e-05, "epoch": 0.5579078455790785, "percentage": 18.54, "elapsed_time": "17:18:50", "remaining_time": "3 days, 4:03:28", "throughput": 565.57, "total_tokens": 35252000} {"current_steps": 169, "total_steps": 906, "loss": 0.43838340044021606, "lr": 4.587660327850203e-05, "epoch": 0.5612287256122872, "percentage": 18.65, "elapsed_time": "17:23:52", "remaining_time": "3 days, 3:52:15", "throughput": 566.27, "total_tokens": 35466456} {"current_steps": 170, "total_steps": 906, "loss": 0.434292197227478, "lr": 4.5828785939489897e-05, "epoch": 0.564549605645496, "percentage": 18.76, "elapsed_time": "17:29:03", "remaining_time": "3 days, 3:41:49", "throughput": 566.78, "total_tokens": 35675000} {"current_steps": 171, "total_steps": 906, "loss": 0.4416734278202057, "lr": 4.578071815864602e-05, "epoch": 0.5678704856787049, "percentage": 18.87, "elapsed_time": "17:33:56", "remaining_time": "3 days, 3:30:07", "throughput": 567.36, "total_tokens": 35878176} {"current_steps": 172, "total_steps": 906, "loss": 0.4213865399360657, "lr": 4.573240051392935e-05, "epoch": 0.5711913657119136, "percentage": 18.98, "elapsed_time": "17:39:19", "remaining_time": "3 days, 3:20:38", "throughput": 567.8, "total_tokens": 36089504} {"current_steps": 173, "total_steps": 906, "loss": 0.43653762340545654, "lr": 4.5683833586303157e-05, "epoch": 0.5745122457451225, "percentage": 19.09, "elapsed_time": "17:44:30", "remaining_time": "3 days, 3:10:19", "throughput": 568.38, "total_tokens": 36302584} {"current_steps": 174, "total_steps": 906, "loss": 0.4446670114994049, "lr": 4.5635017959728024e-05, "epoch": 0.5778331257783312, "percentage": 19.21, "elapsed_time": "17:50:11", "remaining_time": "3 days, 3:02:11", "throughput": 568.6, "total_tokens": 36510368} {"current_steps": 175, "total_steps": 906, "loss": 0.43610668182373047, "lr": 4.5585954221154856e-05, "epoch": 0.5811540058115401, "percentage": 19.32, "elapsed_time": "17:56:11", "remaining_time": "3 days, 2:55:23", "throughput": 568.72, "total_tokens": 36722920} {"current_steps": 176, "total_steps": 906, "loss": 0.44354474544525146, "lr": 4.553664296051785e-05, "epoch": 0.5844748858447488, "percentage": 19.43, "elapsed_time": "18:01:50", "remaining_time": "3 days, 2:47:11", "throughput": 568.98, "total_tokens": 36932736} {"current_steps": 177, "total_steps": 906, "loss": 0.43920040130615234, "lr": 4.548708477072733e-05, "epoch": 0.5877957658779577, "percentage": 19.54, "elapsed_time": "18:07:27", "remaining_time": "3 days, 2:38:50", "throughput": 569.23, "total_tokens": 37140936} {"current_steps": 178, "total_steps": 906, "loss": 0.4473230838775635, "lr": 4.543728024766265e-05, "epoch": 0.5911166459111664, "percentage": 19.65, "elapsed_time": "18:13:08", "remaining_time": "3 days, 2:30:50", "throughput": 569.5, "total_tokens": 37352928} {"current_steps": 179, "total_steps": 906, "loss": 0.44290798902511597, "lr": 4.5387229990165073e-05, "epoch": 0.5944375259443753, "percentage": 19.76, "elapsed_time": "18:18:59", "remaining_time": "3 days, 2:23:31", "throughput": 569.77, "total_tokens": 37570288} {"current_steps": 180, "total_steps": 906, "loss": 0.4382040500640869, "lr": 4.53369346000305e-05, "epoch": 0.597758405977584, "percentage": 19.87, "elapsed_time": "18:24:44", "remaining_time": "3 days, 2:15:49", "throughput": 570.07, "total_tokens": 37786952} {"current_steps": 181, "total_steps": 906, "loss": 0.44450345635414124, "lr": 4.528639468200226e-05, "epoch": 0.6010792860107929, "percentage": 19.98, "elapsed_time": "18:30:09", "remaining_time": "3 days, 2:06:46", "throughput": 570.36, "total_tokens": 37991272} {"current_steps": 182, "total_steps": 906, "loss": 0.4293566942214966, "lr": 4.523561084376387e-05, "epoch": 0.6044001660440017, "percentage": 20.09, "elapsed_time": "18:35:47", "remaining_time": "3 days, 1:58:36", "throughput": 570.56, "total_tokens": 38196960} {"current_steps": 183, "total_steps": 906, "loss": 0.4395379424095154, "lr": 4.51845836959317e-05, "epoch": 0.6077210460772104, "percentage": 20.2, "elapsed_time": "18:41:37", "remaining_time": "3 days, 1:51:19", "throughput": 570.73, "total_tokens": 38408216} {"current_steps": 184, "total_steps": 906, "loss": 0.448405385017395, "lr": 4.513331385204761e-05, "epoch": 0.6110419261104193, "percentage": 20.31, "elapsed_time": "18:47:00", "remaining_time": "3 days, 1:42:16", "throughput": 571.06, "total_tokens": 38615056} {"current_steps": 185, "total_steps": 906, "loss": 0.43220552802085876, "lr": 4.508180192857162e-05, "epoch": 0.614362806143628, "percentage": 20.42, "elapsed_time": "18:51:51", "remaining_time": "3 days, 1:31:10", "throughput": 571.65, "total_tokens": 38821376} {"current_steps": 186, "total_steps": 906, "loss": 0.4433121681213379, "lr": 4.503004854487446e-05, "epoch": 0.6176836861768369, "percentage": 20.53, "elapsed_time": "18:56:49", "remaining_time": "3 days, 1:20:35", "throughput": 572.09, "total_tokens": 39021800} {"current_steps": 187, "total_steps": 906, "loss": 0.4427833557128906, "lr": 4.497805432323015e-05, "epoch": 0.6210045662100456, "percentage": 20.64, "elapsed_time": "19:01:42", "remaining_time": "3 days, 1:09:45", "throughput": 572.66, "total_tokens": 39228112} {"current_steps": 188, "total_steps": 906, "loss": 0.4331440329551697, "lr": 4.492581988880848e-05, "epoch": 0.6243254462432545, "percentage": 20.75, "elapsed_time": "19:06:49", "remaining_time": "3 days, 0:59:53", "throughput": 573.11, "total_tokens": 39435240} {"current_steps": 189, "total_steps": 906, "loss": 0.43456968665122986, "lr": 4.487334586966756e-05, "epoch": 0.6276463262764632, "percentage": 20.86, "elapsed_time": "19:12:19", "remaining_time": "3 days, 0:51:32", "throughput": 573.42, "total_tokens": 39646256} {"current_steps": 190, "total_steps": 906, "loss": 0.4365602135658264, "lr": 4.482063289674618e-05, "epoch": 0.6309672063096721, "percentage": 20.97, "elapsed_time": "19:17:40", "remaining_time": "3 days, 0:42:37", "throughput": 573.8, "total_tokens": 39856280} {"current_steps": 191, "total_steps": 906, "loss": 0.43585318326950073, "lr": 4.476768160385632e-05, "epoch": 0.6342880863428808, "percentage": 21.08, "elapsed_time": "19:22:54", "remaining_time": "3 days, 0:33:19", "throughput": 574.28, "total_tokens": 40070192} {"current_steps": 192, "total_steps": 906, "loss": 0.4303766191005707, "lr": 4.471449262767543e-05, "epoch": 0.6376089663760897, "percentage": 21.19, "elapsed_time": "19:28:07", "remaining_time": "3 days, 0:23:57", "throughput": 574.73, "total_tokens": 40281040} {"current_steps": 193, "total_steps": 906, "loss": 0.4471195340156555, "lr": 4.466106660773885e-05, "epoch": 0.6409298464092985, "percentage": 21.3, "elapsed_time": "19:32:50", "remaining_time": "3 days, 0:12:48", "throughput": 575.28, "total_tokens": 40482632} {"current_steps": 194, "total_steps": 906, "loss": 0.4175926148891449, "lr": 4.460740418643209e-05, "epoch": 0.6442507264425072, "percentage": 21.41, "elapsed_time": "19:37:35", "remaining_time": "3 days, 0:01:54", "throughput": 575.91, "total_tokens": 40691512} {"current_steps": 195, "total_steps": 906, "loss": 0.45054900646209717, "lr": 4.4553506008983126e-05, "epoch": 0.6475716064757161, "percentage": 21.52, "elapsed_time": "19:42:07", "remaining_time": "2 days, 23:50:11", "throughput": 576.53, "total_tokens": 40891680} {"current_steps": 196, "total_steps": 906, "loss": 0.43017148971557617, "lr": 4.44993727234546e-05, "epoch": 0.6508924865089248, "percentage": 21.63, "elapsed_time": "19:46:59", "remaining_time": "2 days, 23:39:48", "throughput": 577.01, "total_tokens": 41094240} {"current_steps": 197, "total_steps": 906, "loss": 0.43241363763809204, "lr": 4.4445004980736064e-05, "epoch": 0.6542133665421337, "percentage": 21.74, "elapsed_time": "19:51:55", "remaining_time": "2 days, 23:29:43", "throughput": 577.58, "total_tokens": 41305616} {"current_steps": 198, "total_steps": 906, "loss": 0.4237765073776245, "lr": 4.439040343453615e-05, "epoch": 0.6575342465753424, "percentage": 21.85, "elapsed_time": "19:56:43", "remaining_time": "2 days, 23:19:11", "throughput": 578.25, "total_tokens": 41520096} {"current_steps": 199, "total_steps": 906, "loss": 0.4452473521232605, "lr": 4.43355687413747e-05, "epoch": 0.6608551266085513, "percentage": 21.96, "elapsed_time": "20:01:39", "remaining_time": "2 days, 23:09:12", "throughput": 578.82, "total_tokens": 41732296} {"current_steps": 200, "total_steps": 906, "loss": 0.43828076124191284, "lr": 4.4280501560574875e-05, "epoch": 0.66417600664176, "percentage": 22.08, "elapsed_time": "20:06:28", "remaining_time": "2 days, 22:58:51", "throughput": 579.45, "total_tokens": 41945888} {"current_steps": 201, "total_steps": 906, "loss": 0.43148741126060486, "lr": 4.4225202554255227e-05, "epoch": 0.6674968866749689, "percentage": 22.19, "elapsed_time": "20:11:16", "remaining_time": "2 days, 22:48:28", "throughput": 580.03, "total_tokens": 42154560} {"current_steps": 202, "total_steps": 906, "loss": 0.4368186593055725, "lr": 4.4169672387321734e-05, "epoch": 0.6708177667081777, "percentage": 22.3, "elapsed_time": "20:16:05", "remaining_time": "2 days, 22:38:14", "throughput": 580.65, "total_tokens": 42367144} {"current_steps": 203, "total_steps": 906, "loss": 0.45101964473724365, "lr": 4.411391172745984e-05, "epoch": 0.6741386467413865, "percentage": 22.41, "elapsed_time": "20:21:36", "remaining_time": "2 days, 22:30:31", "throughput": 580.89, "total_tokens": 42577472} {"current_steps": 204, "total_steps": 906, "loss": 0.43886077404022217, "lr": 4.4057921245126356e-05, "epoch": 0.6774595267745953, "percentage": 22.52, "elapsed_time": "20:27:00", "remaining_time": "2 days, 22:22:20", "throughput": 581.28, "total_tokens": 42794168} {"current_steps": 205, "total_steps": 906, "loss": 0.4312041699886322, "lr": 4.4001701613541456e-05, "epoch": 0.680780406807804, "percentage": 22.63, "elapsed_time": "20:32:06", "remaining_time": "2 days, 22:13:11", "throughput": 581.55, "total_tokens": 42991984} {"current_steps": 206, "total_steps": 906, "loss": 0.4344322383403778, "lr": 4.394525350868059e-05, "epoch": 0.6841012868410129, "percentage": 22.74, "elapsed_time": "20:36:37", "remaining_time": "2 days, 22:02:09", "throughput": 582.24, "total_tokens": 43201320} {"current_steps": 207, "total_steps": 906, "loss": 0.45937955379486084, "lr": 4.388857760926629e-05, "epoch": 0.6874221668742216, "percentage": 22.85, "elapsed_time": "20:42:01", "remaining_time": "2 days, 21:54:03", "throughput": 582.58, "total_tokens": 43414368} {"current_steps": 208, "total_steps": 906, "loss": 0.42359888553619385, "lr": 4.3831674596760086e-05, "epoch": 0.6907430469074305, "percentage": 22.96, "elapsed_time": "20:47:00", "remaining_time": "2 days, 21:44:39", "throughput": 583.12, "total_tokens": 43629120} {"current_steps": 209, "total_steps": 906, "loss": 0.42763370275497437, "lr": 4.3774545155354254e-05, "epoch": 0.6940639269406392, "percentage": 23.07, "elapsed_time": "20:52:16", "remaining_time": "2 days, 21:36:13", "throughput": 583.52, "total_tokens": 43843256} {"current_steps": 210, "total_steps": 906, "loss": 0.43415167927742004, "lr": 4.371718997196364e-05, "epoch": 0.6973848069738481, "percentage": 23.18, "elapsed_time": "20:57:20", "remaining_time": "2 days, 21:27:11", "throughput": 583.92, "total_tokens": 44051496} {"current_steps": 211, "total_steps": 906, "loss": 0.4416137933731079, "lr": 4.3659609736217344e-05, "epoch": 0.7007056870070568, "percentage": 23.29, "elapsed_time": "21:02:15", "remaining_time": "2 days, 21:17:40", "throughput": 584.43, "total_tokens": 44262176} {"current_steps": 212, "total_steps": 906, "loss": 0.44875797629356384, "lr": 4.360180514045048e-05, "epoch": 0.7040265670402657, "percentage": 23.4, "elapsed_time": "21:07:25", "remaining_time": "2 days, 21:09:02", "throughput": 584.83, "total_tokens": 44473568} {"current_steps": 213, "total_steps": 906, "loss": 0.43782973289489746, "lr": 4.354377687969581e-05, "epoch": 0.7073474470734745, "percentage": 23.51, "elapsed_time": "21:13:09", "remaining_time": "2 days, 21:02:16", "throughput": 584.99, "total_tokens": 44687312} {"current_steps": 214, "total_steps": 906, "loss": 0.43622320890426636, "lr": 4.348552565167543e-05, "epoch": 0.7106683271066833, "percentage": 23.62, "elapsed_time": "21:18:56", "remaining_time": "2 days, 20:55:37", "throughput": 585.04, "total_tokens": 44893976} {"current_steps": 215, "total_steps": 906, "loss": 0.44460329413414, "lr": 4.342705215679232e-05, "epoch": 0.7139892071398921, "percentage": 23.73, "elapsed_time": "21:24:17", "remaining_time": "2 days, 20:47:38", "throughput": 585.35, "total_tokens": 45105256} {"current_steps": 216, "total_steps": 906, "loss": 0.4410194754600525, "lr": 4.336835709812202e-05, "epoch": 0.7173100871731009, "percentage": 23.84, "elapsed_time": "21:29:26", "remaining_time": "2 days, 20:39:02", "throughput": 585.67, "total_tokens": 45310816} {"current_steps": 217, "total_steps": 906, "loss": 0.4256168603897095, "lr": 4.330944118140407e-05, "epoch": 0.7206309672063097, "percentage": 23.95, "elapsed_time": "21:35:03", "remaining_time": "2 days, 20:31:58", "throughput": 585.8, "total_tokens": 45519120} {"current_steps": 218, "total_steps": 906, "loss": 0.44676870107650757, "lr": 4.3250305115033554e-05, "epoch": 0.7239518472395184, "percentage": 24.06, "elapsed_time": "21:40:21", "remaining_time": "2 days, 20:23:53", "throughput": 586.13, "total_tokens": 45731160} {"current_steps": 219, "total_steps": 906, "loss": 0.436279833316803, "lr": 4.3190949610052645e-05, "epoch": 0.7272727272727273, "percentage": 24.17, "elapsed_time": "21:45:34", "remaining_time": "2 days, 20:15:32", "throughput": 586.48, "total_tokens": 45941464} {"current_steps": 220, "total_steps": 906, "loss": 0.438388854265213, "lr": 4.3131375380141987e-05, "epoch": 0.730593607305936, "percentage": 24.28, "elapsed_time": "21:50:45", "remaining_time": "2 days, 20:07:11", "throughput": 586.77, "total_tokens": 46147016} {"current_steps": 221, "total_steps": 906, "loss": 0.41060367226600647, "lr": 4.3071583141612135e-05, "epoch": 0.7339144873391449, "percentage": 24.39, "elapsed_time": "21:55:57", "remaining_time": "2 days, 19:58:51", "throughput": 587.16, "total_tokens": 46360480} {"current_steps": 222, "total_steps": 906, "loss": 0.44280239939689636, "lr": 4.301157361339495e-05, "epoch": 0.7372353673723536, "percentage": 24.5, "elapsed_time": "22:01:29", "remaining_time": "2 days, 19:51:37", "throughput": 587.32, "total_tokens": 46568584} {"current_steps": 223, "total_steps": 906, "loss": 0.4437750577926636, "lr": 4.295134751703493e-05, "epoch": 0.7405562474055625, "percentage": 24.61, "elapsed_time": "22:06:30", "remaining_time": "2 days, 19:42:47", "throughput": 587.65, "total_tokens": 46771576} {"current_steps": 224, "total_steps": 906, "loss": 0.4321970045566559, "lr": 4.2890905576680576e-05, "epoch": 0.7438771274387713, "percentage": 24.72, "elapsed_time": "22:11:47", "remaining_time": "2 days, 19:34:49", "throughput": 587.99, "total_tokens": 46985008} {"current_steps": 225, "total_steps": 906, "loss": 0.4373015761375427, "lr": 4.283024851907565e-05, "epoch": 0.7471980074719801, "percentage": 24.83, "elapsed_time": "22:17:05", "remaining_time": "2 days, 19:26:55", "throughput": 588.31, "total_tokens": 47197040} {"current_steps": 226, "total_steps": 906, "loss": 0.43579328060150146, "lr": 4.276937707355044e-05, "epoch": 0.7505188875051889, "percentage": 24.94, "elapsed_time": "22:22:28", "remaining_time": "2 days, 19:19:19", "throughput": 588.59, "total_tokens": 47410648} {"current_steps": 227, "total_steps": 906, "loss": 0.4267618656158447, "lr": 4.2708291972013026e-05, "epoch": 0.7538397675383977, "percentage": 25.06, "elapsed_time": "22:27:47", "remaining_time": "2 days, 19:11:30", "throughput": 588.9, "total_tokens": 47622816} {"current_steps": 228, "total_steps": 906, "loss": 0.4380059838294983, "lr": 4.2646993948940404e-05, "epoch": 0.7571606475716065, "percentage": 25.17, "elapsed_time": "22:33:27", "remaining_time": "2 days, 19:04:46", "throughput": 589.0, "total_tokens": 47831208} {"current_steps": 229, "total_steps": 906, "loss": 0.4525393545627594, "lr": 4.2585483741369755e-05, "epoch": 0.7604815276048152, "percentage": 25.28, "elapsed_time": "22:38:37", "remaining_time": "2 days, 18:56:32", "throughput": 589.33, "total_tokens": 48040744} {"current_steps": 230, "total_steps": 906, "loss": 0.43285566568374634, "lr": 4.25237620888895e-05, "epoch": 0.7638024076380241, "percentage": 25.39, "elapsed_time": "22:44:06", "remaining_time": "2 days, 18:49:16", "throughput": 589.63, "total_tokens": 48259272} {"current_steps": 231, "total_steps": 906, "loss": 0.4323822855949402, "lr": 4.2461829733630435e-05, "epoch": 0.7671232876712328, "percentage": 25.5, "elapsed_time": "22:49:29", "remaining_time": "2 days, 18:41:44", "throughput": 589.82, "total_tokens": 48465344} {"current_steps": 232, "total_steps": 906, "loss": 0.42581987380981445, "lr": 4.239968742025684e-05, "epoch": 0.7704441677044417, "percentage": 25.61, "elapsed_time": "22:54:59", "remaining_time": "2 days, 18:34:35", "throughput": 589.99, "total_tokens": 48673880} {"current_steps": 233, "total_steps": 906, "loss": 0.4327796697616577, "lr": 4.233733589595746e-05, "epoch": 0.7737650477376504, "percentage": 25.72, "elapsed_time": "23:00:33", "remaining_time": "2 days, 18:27:37", "throughput": 590.13, "total_tokens": 48882616} {"current_steps": 234, "total_steps": 906, "loss": 0.4233633279800415, "lr": 4.227477591043659e-05, "epoch": 0.7770859277708593, "percentage": 25.83, "elapsed_time": "23:05:30", "remaining_time": "2 days, 18:18:52", "throughput": 590.54, "total_tokens": 49091960} {"current_steps": 235, "total_steps": 906, "loss": 0.42800650000572205, "lr": 4.2212008215905e-05, "epoch": 0.7804068078040681, "percentage": 25.94, "elapsed_time": "23:10:34", "remaining_time": "2 days, 18:10:31", "throughput": 590.89, "total_tokens": 49300768} {"current_steps": 236, "total_steps": 906, "loss": 0.41652315855026245, "lr": 4.2149033567070936e-05, "epoch": 0.7837276878372769, "percentage": 26.05, "elapsed_time": "23:16:05", "remaining_time": "2 days, 18:03:27", "throughput": 591.02, "total_tokens": 49506952} {"current_steps": 237, "total_steps": 906, "loss": 0.4363587498664856, "lr": 4.208585272113102e-05, "epoch": 0.7870485678704857, "percentage": 26.16, "elapsed_time": "23:21:36", "remaining_time": "2 days, 17:56:25", "throughput": 591.24, "total_tokens": 49721280} {"current_steps": 238, "total_steps": 906, "loss": 0.4244499206542969, "lr": 4.202246643776116e-05, "epoch": 0.7903694479036945, "percentage": 26.27, "elapsed_time": "23:27:40", "remaining_time": "2 days, 17:50:57", "throughput": 591.19, "total_tokens": 49932504} {"current_steps": 239, "total_steps": 906, "loss": 0.41660749912261963, "lr": 4.195887547910741e-05, "epoch": 0.7936903279369033, "percentage": 26.38, "elapsed_time": "23:33:27", "remaining_time": "2 days, 17:44:41", "throughput": 591.28, "total_tokens": 50145408} {"current_steps": 240, "total_steps": 906, "loss": 0.422029972076416, "lr": 4.189508060977678e-05, "epoch": 0.797011207970112, "percentage": 26.49, "elapsed_time": "23:38:52", "remaining_time": "2 days, 17:37:23", "throughput": 591.51, "total_tokens": 50356984} {"current_steps": 241, "total_steps": 906, "loss": 0.4356965124607086, "lr": 4.1831082596828106e-05, "epoch": 0.8003320880033209, "percentage": 26.6, "elapsed_time": "23:44:53", "remaining_time": "2 days, 17:31:45", "throughput": 591.57, "total_tokens": 50575256} {"current_steps": 242, "total_steps": 906, "loss": 0.4283129870891571, "lr": 4.176688220976277e-05, "epoch": 0.8036529680365296, "percentage": 26.71, "elapsed_time": "23:50:45", "remaining_time": "2 days, 17:25:42", "throughput": 591.57, "total_tokens": 50783848} {"current_steps": 243, "total_steps": 906, "loss": 0.43418729305267334, "lr": 4.1702480220515475e-05, "epoch": 0.8069738480697385, "percentage": 26.82, "elapsed_time": "23:56:00", "remaining_time": "2 days, 17:17:59", "throughput": 591.84, "total_tokens": 50992872} {"current_steps": 244, "total_steps": 906, "loss": 0.43433132767677307, "lr": 4.1637877403444924e-05, "epoch": 0.8102947281029472, "percentage": 26.93, "elapsed_time": "1 day, 0:01:38", "remaining_time": "2 days, 17:11:20", "throughput": 591.92, "total_tokens": 51200424} {"current_steps": 245, "total_steps": 906, "loss": 0.4251127243041992, "lr": 4.157307453532457e-05, "epoch": 0.8136156081361561, "percentage": 27.04, "elapsed_time": "1 day, 0:08:02", "remaining_time": "2 days, 17:06:45", "throughput": 591.76, "total_tokens": 51413432} {"current_steps": 246, "total_steps": 906, "loss": 0.4269641041755676, "lr": 4.150807239533326e-05, "epoch": 0.8169364881693649, "percentage": 27.15, "elapsed_time": "1 day, 0:13:57", "remaining_time": "2 days, 17:00:51", "throughput": 591.82, "total_tokens": 51628736} {"current_steps": 247, "total_steps": 906, "loss": 0.4357364773750305, "lr": 4.144287176504582e-05, "epoch": 0.8202573682025737, "percentage": 27.26, "elapsed_time": "1 day, 0:20:31", "remaining_time": "2 days, 16:56:42", "throughput": 591.57, "total_tokens": 51840264} {"current_steps": 248, "total_steps": 906, "loss": 0.4357312321662903, "lr": 4.1377473428423696e-05, "epoch": 0.8235782482357825, "percentage": 27.37, "elapsed_time": "1 day, 0:26:04", "remaining_time": "2 days, 16:49:49", "throughput": 591.67, "total_tokens": 52046288} {"current_steps": 249, "total_steps": 906, "loss": 0.44376251101493835, "lr": 4.131187817180554e-05, "epoch": 0.8268991282689913, "percentage": 27.48, "elapsed_time": "1 day, 0:32:16", "remaining_time": "2 days, 16:44:41", "throughput": 591.58, "total_tokens": 52258104} {"current_steps": 250, "total_steps": 906, "loss": 0.4338582754135132, "lr": 4.124608678389772e-05, "epoch": 0.8302200083022001, "percentage": 27.59, "elapsed_time": "1 day, 0:38:22", "remaining_time": "2 days, 16:39:16", "throughput": 591.5, "total_tokens": 52467344} {"current_steps": 251, "total_steps": 906, "loss": 0.4290063977241516, "lr": 4.118010005576485e-05, "epoch": 0.8335408883354088, "percentage": 27.7, "elapsed_time": "1 day, 0:43:24", "remaining_time": "2 days, 16:31:02", "throughput": 591.84, "total_tokens": 52676424} {"current_steps": 252, "total_steps": 906, "loss": 0.42551183700561523, "lr": 4.11139187808203e-05, "epoch": 0.8368617683686177, "percentage": 27.81, "elapsed_time": "1 day, 0:48:54", "remaining_time": "2 days, 16:24:04", "throughput": 592.03, "total_tokens": 52888768} {"current_steps": 253, "total_steps": 906, "loss": 0.4403475522994995, "lr": 4.104754375481664e-05, "epoch": 0.8401826484018264, "percentage": 27.92, "elapsed_time": "1 day, 0:54:13", "remaining_time": "2 days, 16:16:39", "throughput": 592.26, "total_tokens": 53097984} {"current_steps": 254, "total_steps": 906, "loss": 0.43381038308143616, "lr": 4.098097577583605e-05, "epoch": 0.8435035284350353, "percentage": 28.04, "elapsed_time": "1 day, 0:59:49", "remaining_time": "2 days, 16:09:56", "throughput": 592.34, "total_tokens": 53304584} {"current_steps": 255, "total_steps": 906, "loss": 0.4274643361568451, "lr": 4.0914215644280754e-05, "epoch": 0.8468244084682441, "percentage": 28.15, "elapsed_time": "1 day, 1:05:45", "remaining_time": "2 days, 16:04:06", "throughput": 592.38, "total_tokens": 53518560} {"current_steps": 256, "total_steps": 906, "loss": 0.4286618232727051, "lr": 4.0847264162863374e-05, "epoch": 0.8501452885014529, "percentage": 28.26, "elapsed_time": "1 day, 1:11:57", "remaining_time": "2 days, 15:58:58", "throughput": 592.3, "total_tokens": 53732472} {"current_steps": 257, "total_steps": 906, "loss": 0.42166805267333984, "lr": 4.0780122136597323e-05, "epoch": 0.8534661685346617, "percentage": 28.37, "elapsed_time": "1 day, 1:17:34", "remaining_time": "2 days, 15:52:18", "throughput": 592.42, "total_tokens": 53942328} {"current_steps": 258, "total_steps": 906, "loss": 0.4259738326072693, "lr": 4.071279037278706e-05, "epoch": 0.8567870485678705, "percentage": 28.48, "elapsed_time": "1 day, 1:23:05", "remaining_time": "2 days, 15:45:27", "throughput": 592.6, "total_tokens": 54155280} {"current_steps": 259, "total_steps": 906, "loss": 0.43134981393814087, "lr": 4.064526968101844e-05, "epoch": 0.8601079286010793, "percentage": 28.59, "elapsed_time": "1 day, 1:28:36", "remaining_time": "2 days, 15:38:33", "throughput": 592.72, "total_tokens": 54361816} {"current_steps": 260, "total_steps": 906, "loss": 0.42049890756607056, "lr": 4.0577560873148945e-05, "epoch": 0.8634288086342881, "percentage": 28.7, "elapsed_time": "1 day, 1:35:01", "remaining_time": "2 days, 15:33:56", "throughput": 592.51, "total_tokens": 54571312} {"current_steps": 261, "total_steps": 906, "loss": 0.4206635355949402, "lr": 4.050966476329793e-05, "epoch": 0.8667496886674969, "percentage": 28.81, "elapsed_time": "1 day, 1:40:58", "remaining_time": "2 days, 15:28:08", "throughput": 592.49, "total_tokens": 54780248} {"current_steps": 262, "total_steps": 906, "loss": 0.4227411448955536, "lr": 4.044158216783685e-05, "epoch": 0.8700705687007056, "percentage": 28.92, "elapsed_time": "1 day, 1:47:36", "remaining_time": "2 days, 15:24:02", "throughput": 592.26, "total_tokens": 54995344} {"current_steps": 263, "total_steps": 906, "loss": 0.44105619192123413, "lr": 4.037331390537939e-05, "epoch": 0.8733914487339145, "percentage": 29.03, "elapsed_time": "1 day, 1:53:23", "remaining_time": "2 days, 15:17:49", "throughput": 592.31, "total_tokens": 55205656} {"current_steps": 264, "total_steps": 906, "loss": 0.4170098602771759, "lr": 4.0304860796771745e-05, "epoch": 0.8767123287671232, "percentage": 29.14, "elapsed_time": "1 day, 1:59:23", "remaining_time": "2 days, 15:12:09", "throughput": 592.35, "total_tokens": 55422392} {"current_steps": 265, "total_steps": 906, "loss": 0.4379138946533203, "lr": 4.023622366508261e-05, "epoch": 0.8800332088003321, "percentage": 29.25, "elapsed_time": "1 day, 2:05:23", "remaining_time": "2 days, 15:06:28", "throughput": 592.31, "total_tokens": 55631840} {"current_steps": 266, "total_steps": 906, "loss": 0.42350104451179504, "lr": 4.0167403335593335e-05, "epoch": 0.8833540888335409, "percentage": 29.36, "elapsed_time": "1 day, 2:11:06", "remaining_time": "2 days, 15:00:06", "throughput": 592.38, "total_tokens": 55841632} {"current_steps": 267, "total_steps": 906, "loss": 0.4372592866420746, "lr": 4.0098400635788035e-05, "epoch": 0.8866749688667497, "percentage": 29.47, "elapsed_time": "1 day, 2:16:53", "remaining_time": "2 days, 14:53:54", "throughput": 592.39, "total_tokens": 56048016} {"current_steps": 268, "total_steps": 906, "loss": 0.42278414964675903, "lr": 4.002921639534362e-05, "epoch": 0.8899958488999585, "percentage": 29.58, "elapsed_time": "1 day, 2:22:34", "remaining_time": "2 days, 14:47:29", "throughput": 592.51, "total_tokens": 56261912} {"current_steps": 269, "total_steps": 906, "loss": 0.4389027953147888, "lr": 3.99598514461198e-05, "epoch": 0.8933167289331673, "percentage": 29.69, "elapsed_time": "1 day, 2:28:18", "remaining_time": "2 days, 14:41:09", "throughput": 592.57, "total_tokens": 56471328} {"current_steps": 270, "total_steps": 906, "loss": 0.42557549476623535, "lr": 3.98903066221491e-05, "epoch": 0.8966376089663761, "percentage": 29.8, "elapsed_time": "1 day, 2:34:02", "remaining_time": "2 days, 14:34:50", "throughput": 592.65, "total_tokens": 56682008} {"current_steps": 271, "total_steps": 906, "loss": 0.4394855797290802, "lr": 3.9820582759626825e-05, "epoch": 0.8999584889995849, "percentage": 29.91, "elapsed_time": "1 day, 2:39:37", "remaining_time": "2 days, 14:28:13", "throughput": 592.73, "total_tokens": 56889488} {"current_steps": 272, "total_steps": 906, "loss": 0.43113696575164795, "lr": 3.975068069690102e-05, "epoch": 0.9032793690327937, "percentage": 30.02, "elapsed_time": "1 day, 2:45:27", "remaining_time": "2 days, 14:22:08", "throughput": 592.7, "total_tokens": 57093032} {"current_steps": 273, "total_steps": 906, "loss": 0.42244070768356323, "lr": 3.968060127446236e-05, "epoch": 0.9066002490660025, "percentage": 30.13, "elapsed_time": "1 day, 2:51:04", "remaining_time": "2 days, 14:15:34", "throughput": 592.76, "total_tokens": 57299024} {"current_steps": 274, "total_steps": 906, "loss": 0.4271528422832489, "lr": 3.96103453349341e-05, "epoch": 0.9099211290992113, "percentage": 30.24, "elapsed_time": "1 day, 2:56:49", "remaining_time": "2 days, 14:09:18", "throughput": 592.76, "total_tokens": 57503240} {"current_steps": 275, "total_steps": 906, "loss": 0.4269882142543793, "lr": 3.953991372306186e-05, "epoch": 0.91324200913242, "percentage": 30.35, "elapsed_time": "1 day, 3:02:01", "remaining_time": "2 days, 14:01:48", "throughput": 592.96, "total_tokens": 57708112} {"current_steps": 276, "total_steps": 906, "loss": 0.42415356636047363, "lr": 3.946930728570355e-05, "epoch": 0.9165628891656289, "percentage": 30.46, "elapsed_time": "1 day, 3:08:05", "remaining_time": "2 days, 13:56:18", "throughput": 592.95, "total_tokens": 57922360} {"current_steps": 277, "total_steps": 906, "loss": 0.4297690689563751, "lr": 3.9398526871819154e-05, "epoch": 0.9198837691988377, "percentage": 30.57, "elapsed_time": "1 day, 3:14:43", "remaining_time": "2 days, 13:52:03", "throughput": 592.65, "total_tokens": 58128672} {"current_steps": 278, "total_steps": 906, "loss": 0.4301888346672058, "lr": 3.932757333246048e-05, "epoch": 0.9232046492320465, "percentage": 30.68, "elapsed_time": "1 day, 3:20:18", "remaining_time": "2 days, 13:45:26", "throughput": 592.74, "total_tokens": 58336344} {"current_steps": 279, "total_steps": 906, "loss": 0.4214772582054138, "lr": 3.925644752076101e-05, "epoch": 0.9265255292652553, "percentage": 30.79, "elapsed_time": "1 day, 3:26:04", "remaining_time": "2 days, 13:39:13", "throughput": 592.8, "total_tokens": 58546888} {"current_steps": 280, "total_steps": 906, "loss": 0.43122127652168274, "lr": 3.918515029192559e-05, "epoch": 0.9298464092984641, "percentage": 30.91, "elapsed_time": "1 day, 3:31:48", "remaining_time": "2 days, 13:32:58", "throughput": 592.8, "total_tokens": 58751824} {"current_steps": 281, "total_steps": 906, "loss": 0.42521238327026367, "lr": 3.911368250322014e-05, "epoch": 0.9331672893316729, "percentage": 31.02, "elapsed_time": "1 day, 3:37:23", "remaining_time": "2 days, 13:26:21", "throughput": 592.93, "total_tokens": 58962864} {"current_steps": 282, "total_steps": 906, "loss": 0.438882052898407, "lr": 3.9042045013961386e-05, "epoch": 0.9364881693648817, "percentage": 31.13, "elapsed_time": "1 day, 3:42:54", "remaining_time": "2 days, 13:19:38", "throughput": 593.07, "total_tokens": 59173856} {"current_steps": 283, "total_steps": 906, "loss": 0.42735034227371216, "lr": 3.897023868550649e-05, "epoch": 0.9398090493980905, "percentage": 31.24, "elapsed_time": "1 day, 3:48:23", "remaining_time": "2 days, 13:12:49", "throughput": 593.19, "total_tokens": 59380128} {"current_steps": 284, "total_steps": 906, "loss": 0.41743844747543335, "lr": 3.889826438124271e-05, "epoch": 0.9431299294312993, "percentage": 31.35, "elapsed_time": "1 day, 3:53:41", "remaining_time": "2 days, 13:05:36", "throughput": 593.47, "total_tokens": 59596624} {"current_steps": 285, "total_steps": 906, "loss": 0.4251156747341156, "lr": 3.882612296657701e-05, "epoch": 0.9464508094645081, "percentage": 31.46, "elapsed_time": "1 day, 3:59:15", "remaining_time": "2 days, 12:59:01", "throughput": 593.62, "total_tokens": 59810096} {"current_steps": 286, "total_steps": 906, "loss": 0.42936187982559204, "lr": 3.875381530892569e-05, "epoch": 0.9497716894977168, "percentage": 31.57, "elapsed_time": "1 day, 4:04:36", "remaining_time": "2 days, 12:51:57", "throughput": 593.83, "total_tokens": 60022264} {"current_steps": 287, "total_steps": 906, "loss": 0.42513227462768555, "lr": 3.8681342277703906e-05, "epoch": 0.9530925695309257, "percentage": 31.68, "elapsed_time": "1 day, 4:10:13", "remaining_time": "2 days, 12:45:28", "throughput": 593.94, "total_tokens": 60234256} {"current_steps": 288, "total_steps": 906, "loss": 0.4264582395553589, "lr": 3.860870474431521e-05, "epoch": 0.9564134495641345, "percentage": 31.79, "elapsed_time": "1 day, 4:16:02", "remaining_time": "2 days, 12:39:24", "throughput": 593.98, "total_tokens": 60444896} {"current_steps": 289, "total_steps": 906, "loss": 0.43254929780960083, "lr": 3.853590358214119e-05, "epoch": 0.9597343295973433, "percentage": 31.9, "elapsed_time": "1 day, 4:21:59", "remaining_time": "2 days, 12:33:40", "throughput": 593.91, "total_tokens": 60650528} {"current_steps": 290, "total_steps": 906, "loss": 0.42426615953445435, "lr": 3.846293966653076e-05, "epoch": 0.9630552096305521, "percentage": 32.01, "elapsed_time": "1 day, 4:27:30", "remaining_time": "2 days, 12:26:58", "throughput": 593.99, "total_tokens": 60854088} {"current_steps": 291, "total_steps": 906, "loss": 0.42260557413101196, "lr": 3.8389813874789856e-05, "epoch": 0.9663760896637609, "percentage": 32.12, "elapsed_time": "1 day, 4:33:12", "remaining_time": "2 days, 12:20:41", "throughput": 594.04, "total_tokens": 61063120} {"current_steps": 292, "total_steps": 906, "loss": 0.42293086647987366, "lr": 3.831652708617073e-05, "epoch": 0.9696969696969697, "percentage": 32.23, "elapsed_time": "1 day, 4:39:05", "remaining_time": "2 days, 12:14:48", "throughput": 594.01, "total_tokens": 61269568} {"current_steps": 293, "total_steps": 906, "loss": 0.4292466640472412, "lr": 3.8243080181861435e-05, "epoch": 0.9730178497301785, "percentage": 32.34, "elapsed_time": "1 day, 4:44:40", "remaining_time": "2 days, 12:08:16", "throughput": 594.12, "total_tokens": 61480384} {"current_steps": 294, "total_steps": 906, "loss": 0.43775731325149536, "lr": 3.816947404497525e-05, "epoch": 0.9763387297633873, "percentage": 32.45, "elapsed_time": "1 day, 4:49:59", "remaining_time": "2 days, 12:01:11", "throughput": 594.33, "total_tokens": 61691472} {"current_steps": 295, "total_steps": 906, "loss": 0.4230045676231384, "lr": 3.809570956054004e-05, "epoch": 0.979659609796596, "percentage": 32.56, "elapsed_time": "1 day, 4:55:25", "remaining_time": "2 days, 11:54:23", "throughput": 594.5, "total_tokens": 61902552} {"current_steps": 296, "total_steps": 906, "loss": 0.42893537878990173, "lr": 3.802178761548759e-05, "epoch": 0.9829804898298049, "percentage": 32.67, "elapsed_time": "1 day, 5:01:14", "remaining_time": "2 days, 11:48:23", "throughput": 594.57, "total_tokens": 62117136} {"current_steps": 297, "total_steps": 906, "loss": 0.42035895586013794, "lr": 3.794770909864298e-05, "epoch": 0.9863013698630136, "percentage": 32.78, "elapsed_time": "1 day, 5:07:20", "remaining_time": "2 days, 11:42:55", "throughput": 594.49, "total_tokens": 62326552} {"current_steps": 298, "total_steps": 906, "loss": 0.42545071244239807, "lr": 3.7873474900713895e-05, "epoch": 0.9896222498962225, "percentage": 32.89, "elapsed_time": "1 day, 5:12:30", "remaining_time": "2 days, 11:35:35", "throughput": 594.71, "total_tokens": 62534528} {"current_steps": 299, "total_steps": 906, "loss": 0.4190545380115509, "lr": 3.779908591427988e-05, "epoch": 0.9929431299294313, "percentage": 33.0, "elapsed_time": "1 day, 5:17:51", "remaining_time": "2 days, 11:28:38", "throughput": 594.86, "total_tokens": 62740888} {"current_steps": 300, "total_steps": 906, "loss": 0.4248197376728058, "lr": 3.772454303378166e-05, "epoch": 0.9962640099626401, "percentage": 33.11, "elapsed_time": "1 day, 5:23:07", "remaining_time": "2 days, 11:21:31", "throughput": 595.11, "total_tokens": 62955768} {"current_steps": 301, "total_steps": 906, "loss": 0.420073926448822, "lr": 3.764984715551032e-05, "epoch": 0.9995848899958489, "percentage": 33.22, "elapsed_time": "1 day, 5:29:08", "remaining_time": "2 days, 11:15:54", "throughput": 595.09, "total_tokens": 63168384} {"current_steps": 302, "total_steps": 906, "loss": 0.37945839762687683, "lr": 3.757499917759659e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1 day, 5:29:48", "remaining_time": "2 days, 10:59:36", "throughput": 595.12, "total_tokens": 63194912} {"current_steps": 303, "total_steps": 906, "loss": 0.30404990911483765, "lr": 3.7500000000000003e-05, "epoch": 1.0033208800332087, "percentage": 33.44, "elapsed_time": "1 day, 5:35:19", "remaining_time": "2 days, 10:53:05", "throughput": 595.21, "total_tokens": 63401624} {"current_steps": 304, "total_steps": 906, "loss": 0.2919006645679474, "lr": 3.742485052449812e-05, "epoch": 1.0066417600664177, "percentage": 33.55, "elapsed_time": "1 day, 5:40:42", "remaining_time": "2 days, 10:46:16", "throughput": 595.35, "total_tokens": 63609312} {"current_steps": 305, "total_steps": 906, "loss": 0.28770512342453003, "lr": 3.734955165467563e-05, "epoch": 1.0099626400996264, "percentage": 33.66, "elapsed_time": "1 day, 5:45:53", "remaining_time": "2 days, 10:39:04", "throughput": 595.65, "total_tokens": 63825640} {"current_steps": 306, "total_steps": 906, "loss": 0.2927480936050415, "lr": 3.727410429591353e-05, "epoch": 1.0132835201328352, "percentage": 33.77, "elapsed_time": "1 day, 5:51:14", "remaining_time": "2 days, 10:32:14", "throughput": 595.84, "total_tokens": 64037224} {"current_steps": 307, "total_steps": 906, "loss": 0.2891179025173187, "lr": 3.719850935537821e-05, "epoch": 1.016604400166044, "percentage": 33.89, "elapsed_time": "1 day, 5:56:37", "remaining_time": "2 days, 10:25:28", "throughput": 595.89, "total_tokens": 64235520} {"current_steps": 308, "total_steps": 906, "loss": 0.2905241847038269, "lr": 3.712276774201058e-05, "epoch": 1.0199252801992529, "percentage": 34.0, "elapsed_time": "1 day, 6:01:51", "remaining_time": "2 days, 10:18:23", "throughput": 596.11, "total_tokens": 64446048} {"current_steps": 309, "total_steps": 906, "loss": 0.2945302724838257, "lr": 3.70468803665151e-05, "epoch": 1.0232461602324616, "percentage": 34.11, "elapsed_time": "1 day, 6:07:49", "remaining_time": "2 days, 10:12:48", "throughput": 596.09, "total_tokens": 64657856} {"current_steps": 310, "total_steps": 906, "loss": 0.29261961579322815, "lr": 3.697084814134886e-05, "epoch": 1.0265670402656704, "percentage": 34.22, "elapsed_time": "1 day, 6:13:43", "remaining_time": "2 days, 10:07:01", "throughput": 596.07, "total_tokens": 64866088} {"current_steps": 311, "total_steps": 906, "loss": 0.28819987177848816, "lr": 3.6894671980710574e-05, "epoch": 1.029887920298879, "percentage": 34.33, "elapsed_time": "1 day, 6:19:36", "remaining_time": "2 days, 10:01:14", "throughput": 596.07, "total_tokens": 65076416} {"current_steps": 312, "total_steps": 906, "loss": 0.2864361107349396, "lr": 3.681835280052967e-05, "epoch": 1.033208800332088, "percentage": 34.44, "elapsed_time": "1 day, 6:25:14", "remaining_time": "2 days, 9:54:59", "throughput": 596.2, "total_tokens": 65292888} {"current_steps": 313, "total_steps": 906, "loss": 0.2746656537055969, "lr": 3.674189151845515e-05, "epoch": 1.0365296803652968, "percentage": 34.55, "elapsed_time": "1 day, 6:31:00", "remaining_time": "2 days, 9:48:59", "throughput": 596.19, "total_tokens": 65498224} {"current_steps": 314, "total_steps": 906, "loss": 0.2784012258052826, "lr": 3.666528905384467e-05, "epoch": 1.0398505603985055, "percentage": 34.66, "elapsed_time": "1 day, 6:36:43", "remaining_time": "2 days, 9:42:52", "throughput": 596.24, "total_tokens": 65707944} {"current_steps": 315, "total_steps": 906, "loss": 0.26996612548828125, "lr": 3.6588546327753425e-05, "epoch": 1.0431714404317145, "percentage": 34.77, "elapsed_time": "1 day, 6:42:21", "remaining_time": "2 days, 9:36:36", "throughput": 596.33, "total_tokens": 65919456} {"current_steps": 316, "total_steps": 906, "loss": 0.29366016387939453, "lr": 3.651166426292309e-05, "epoch": 1.0464923204649232, "percentage": 34.88, "elapsed_time": "1 day, 6:48:00", "remaining_time": "2 days, 9:30:23", "throughput": 596.47, "total_tokens": 66136744} {"current_steps": 317, "total_steps": 906, "loss": 0.28355640172958374, "lr": 3.6434643783770736e-05, "epoch": 1.049813200498132, "percentage": 34.99, "elapsed_time": "1 day, 6:53:24", "remaining_time": "2 days, 9:23:42", "throughput": 596.56, "total_tokens": 66340048} {"current_steps": 318, "total_steps": 906, "loss": 0.2831692099571228, "lr": 3.63574858163777e-05, "epoch": 1.0531340805313407, "percentage": 35.1, "elapsed_time": "1 day, 6:58:43", "remaining_time": "2 days, 9:16:53", "throughput": 596.72, "total_tokens": 66548192} {"current_steps": 319, "total_steps": 906, "loss": 0.27536556124687195, "lr": 3.6280191288478436e-05, "epoch": 1.0564549605645497, "percentage": 35.21, "elapsed_time": "1 day, 7:04:13", "remaining_time": "2 days, 9:10:24", "throughput": 596.8, "total_tokens": 66754128} {"current_steps": 320, "total_steps": 906, "loss": 0.2778305113315582, "lr": 3.620276112944941e-05, "epoch": 1.0597758405977584, "percentage": 35.32, "elapsed_time": "1 day, 7:09:48", "remaining_time": "2 days, 9:04:05", "throughput": 596.97, "total_tokens": 66972952} {"current_steps": 321, "total_steps": 906, "loss": 0.28065669536590576, "lr": 3.612519627029787e-05, "epoch": 1.0630967206309672, "percentage": 35.43, "elapsed_time": "1 day, 7:15:16", "remaining_time": "2 days, 8:57:34", "throughput": 597.07, "total_tokens": 67180352} {"current_steps": 322, "total_steps": 906, "loss": 0.2865450978279114, "lr": 3.604749764365069e-05, "epoch": 1.0664176006641761, "percentage": 35.54, "elapsed_time": "1 day, 7:20:55", "remaining_time": "2 days, 8:51:21", "throughput": 597.1, "total_tokens": 67385592} {"current_steps": 323, "total_steps": 906, "loss": 0.2833058536052704, "lr": 3.596966618374313e-05, "epoch": 1.0697384806973849, "percentage": 35.65, "elapsed_time": "1 day, 7:26:23", "remaining_time": "2 days, 8:44:50", "throughput": 597.22, "total_tokens": 67595592} {"current_steps": 324, "total_steps": 906, "loss": 0.27913883328437805, "lr": 3.5891702826407633e-05, "epoch": 1.0730593607305936, "percentage": 35.76, "elapsed_time": "1 day, 7:31:44", "remaining_time": "2 days, 8:38:08", "throughput": 597.32, "total_tokens": 67798704} {"current_steps": 325, "total_steps": 906, "loss": 0.2752624750137329, "lr": 3.5813608509062526e-05, "epoch": 1.0763802407638023, "percentage": 35.87, "elapsed_time": "1 day, 7:37:04", "remaining_time": "2 days, 8:31:23", "throughput": 597.48, "total_tokens": 68007752} {"current_steps": 326, "total_steps": 906, "loss": 0.2673056125640869, "lr": 3.5735384170700815e-05, "epoch": 1.0797011207970113, "percentage": 35.98, "elapsed_time": "1 day, 7:42:29", "remaining_time": "2 days, 8:24:48", "throughput": 597.59, "total_tokens": 68215152} {"current_steps": 327, "total_steps": 906, "loss": 0.2820720076560974, "lr": 3.5657030751878814e-05, "epoch": 1.08302200083022, "percentage": 36.09, "elapsed_time": "1 day, 7:47:58", "remaining_time": "2 days, 8:18:19", "throughput": 597.72, "total_tokens": 68426056} {"current_steps": 328, "total_steps": 906, "loss": 0.2856150269508362, "lr": 3.5578549194704915e-05, "epoch": 1.0863428808634288, "percentage": 36.2, "elapsed_time": "1 day, 7:53:29", "remaining_time": "2 days, 8:11:57", "throughput": 597.83, "total_tokens": 68636448} {"current_steps": 329, "total_steps": 906, "loss": 0.2782435715198517, "lr": 3.5499940442828206e-05, "epoch": 1.0896637608966375, "percentage": 36.31, "elapsed_time": "1 day, 7:58:51", "remaining_time": "2 days, 8:05:18", "throughput": 597.99, "total_tokens": 68848208} {"current_steps": 330, "total_steps": 906, "loss": 0.2769739627838135, "lr": 3.5421205441427154e-05, "epoch": 1.0929846409298465, "percentage": 36.42, "elapsed_time": "1 day, 8:04:38", "remaining_time": "2 days, 7:59:23", "throughput": 598.01, "total_tokens": 69057048} {"current_steps": 331, "total_steps": 906, "loss": 0.26873889565467834, "lr": 3.534234513719821e-05, "epoch": 1.0963055209630552, "percentage": 36.53, "elapsed_time": "1 day, 8:10:13", "remaining_time": "2 days, 7:53:07", "throughput": 598.09, "total_tokens": 69266936} {"current_steps": 332, "total_steps": 906, "loss": 0.27480942010879517, "lr": 3.526336047834445e-05, "epoch": 1.099626400996264, "percentage": 36.64, "elapsed_time": "1 day, 8:15:19", "remaining_time": "2 days, 7:46:00", "throughput": 598.39, "total_tokens": 69484600} {"current_steps": 333, "total_steps": 906, "loss": 0.28268882632255554, "lr": 3.51842524145642e-05, "epoch": 1.102947281029473, "percentage": 36.75, "elapsed_time": "1 day, 8:20:32", "remaining_time": "2 days, 7:39:08", "throughput": 598.62, "total_tokens": 69699400} {"current_steps": 334, "total_steps": 906, "loss": 0.269026517868042, "lr": 3.5105021897039544e-05, "epoch": 1.1062681610626817, "percentage": 36.87, "elapsed_time": "1 day, 8:26:01", "remaining_time": "2 days, 7:32:42", "throughput": 598.71, "total_tokens": 69906120} {"current_steps": 335, "total_steps": 906, "loss": 0.27428004145622253, "lr": 3.502566987842496e-05, "epoch": 1.1095890410958904, "percentage": 36.98, "elapsed_time": "1 day, 8:31:09", "remaining_time": "2 days, 7:25:41", "throughput": 598.96, "total_tokens": 70120272} {"current_steps": 336, "total_steps": 906, "loss": 0.2684640884399414, "lr": 3.494619731283581e-05, "epoch": 1.1129099211290991, "percentage": 37.09, "elapsed_time": "1 day, 8:36:31", "remaining_time": "2 days, 7:19:05", "throughput": 599.06, "total_tokens": 70324864} {"current_steps": 337, "total_steps": 906, "loss": 0.26904401183128357, "lr": 3.4866605155836915e-05, "epoch": 1.116230801162308, "percentage": 37.2, "elapsed_time": "1 day, 8:42:08", "remaining_time": "2 days, 7:12:56", "throughput": 599.07, "total_tokens": 70527400} {"current_steps": 338, "total_steps": 906, "loss": 0.2700223922729492, "lr": 3.478689436443102e-05, "epoch": 1.1195516811955168, "percentage": 37.31, "elapsed_time": "1 day, 8:47:56", "remaining_time": "2 days, 7:07:03", "throughput": 599.07, "total_tokens": 70736048} {"current_steps": 339, "total_steps": 906, "loss": 0.2767173647880554, "lr": 3.470706589704734e-05, "epoch": 1.1228725612287256, "percentage": 37.42, "elapsed_time": "1 day, 8:53:29", "remaining_time": "2 days, 7:00:48", "throughput": 599.14, "total_tokens": 70944064} {"current_steps": 340, "total_steps": 906, "loss": 0.2738657593727112, "lr": 3.4627120713529984e-05, "epoch": 1.1261934412619343, "percentage": 37.53, "elapsed_time": "1 day, 8:59:37", "remaining_time": "2 days, 6:55:30", "throughput": 599.05, "total_tokens": 71153928} {"current_steps": 341, "total_steps": 906, "loss": 0.2712458074092865, "lr": 3.4547059775126445e-05, "epoch": 1.1295143212951433, "percentage": 37.64, "elapsed_time": "1 day, 9:05:17", "remaining_time": "2 days, 6:49:23", "throughput": 599.08, "total_tokens": 71360176} {"current_steps": 342, "total_steps": 906, "loss": 0.27859729528427124, "lr": 3.446688404447601e-05, "epoch": 1.132835201328352, "percentage": 37.75, "elapsed_time": "1 day, 9:11:02", "remaining_time": "2 days, 6:43:28", "throughput": 599.1, "total_tokens": 71569832} {"current_steps": 343, "total_steps": 906, "loss": 0.27219098806381226, "lr": 3.438659448559825e-05, "epoch": 1.1361560813615608, "percentage": 37.86, "elapsed_time": "1 day, 9:16:51", "remaining_time": "2 days, 6:37:39", "throughput": 599.12, "total_tokens": 71781800} {"current_steps": 344, "total_steps": 906, "loss": 0.2708030343055725, "lr": 3.430619206388136e-05, "epoch": 1.1394769613947697, "percentage": 37.97, "elapsed_time": "1 day, 9:22:27", "remaining_time": "2 days, 6:31:27", "throughput": 599.19, "total_tokens": 71991624} {"current_steps": 345, "total_steps": 906, "loss": 0.27873820066452026, "lr": 3.422567774607058e-05, "epoch": 1.1427978414279785, "percentage": 38.08, "elapsed_time": "1 day, 9:28:03", "remaining_time": "2 days, 6:25:17", "throughput": 599.27, "total_tokens": 72202208} {"current_steps": 346, "total_steps": 906, "loss": 0.27958598732948303, "lr": 3.414505250025659e-05, "epoch": 1.1461187214611872, "percentage": 38.19, "elapsed_time": "1 day, 9:33:47", "remaining_time": "2 days, 6:19:19", "throughput": 599.25, "total_tokens": 72406480} {"current_steps": 347, "total_steps": 906, "loss": 0.2782125473022461, "lr": 3.406431729586382e-05, "epoch": 1.149439601494396, "percentage": 38.3, "elapsed_time": "1 day, 9:39:04", "remaining_time": "2 days, 6:12:37", "throughput": 599.49, "total_tokens": 72624512} {"current_steps": 348, "total_steps": 906, "loss": 0.2749646306037903, "lr": 3.398347310363884e-05, "epoch": 1.152760481527605, "percentage": 38.41, "elapsed_time": "1 day, 9:44:24", "remaining_time": "2 days, 6:06:02", "throughput": 599.61, "total_tokens": 72830976} {"current_steps": 349, "total_steps": 906, "loss": 0.2624763548374176, "lr": 3.390252089563867e-05, "epoch": 1.1560813615608136, "percentage": 38.52, "elapsed_time": "1 day, 9:49:46", "remaining_time": "2 days, 5:59:29", "throughput": 599.73, "total_tokens": 73039008} {"current_steps": 350, "total_steps": 906, "loss": 0.27640023827552795, "lr": 3.38214616452191e-05, "epoch": 1.1594022415940224, "percentage": 38.63, "elapsed_time": "1 day, 9:55:25", "remaining_time": "2 days, 5:53:25", "throughput": 599.8, "total_tokens": 73251288} {"current_steps": 351, "total_steps": 906, "loss": 0.280078649520874, "lr": 3.3740296327022984e-05, "epoch": 1.1627231216272311, "percentage": 38.74, "elapsed_time": "1 day, 10:01:12", "remaining_time": "2 days, 5:47:32", "throughput": 599.82, "total_tokens": 73461608} {"current_steps": 352, "total_steps": 906, "loss": 0.27999985218048096, "lr": 3.365902591696848e-05, "epoch": 1.16604400166044, "percentage": 38.85, "elapsed_time": "1 day, 10:06:50", "remaining_time": "2 days, 5:41:27", "throughput": 599.86, "total_tokens": 73669488} {"current_steps": 353, "total_steps": 906, "loss": 0.2793060839176178, "lr": 3.35776513922374e-05, "epoch": 1.1693648816936488, "percentage": 38.96, "elapsed_time": "1 day, 10:12:18", "remaining_time": "2 days, 5:35:04", "throughput": 599.99, "total_tokens": 73882160} {"current_steps": 354, "total_steps": 906, "loss": 0.28069770336151123, "lr": 3.3496173731263377e-05, "epoch": 1.1726857617268576, "percentage": 39.07, "elapsed_time": "1 day, 10:17:09", "remaining_time": "2 days, 5:27:45", "throughput": 600.29, "total_tokens": 74093192} {"current_steps": 355, "total_steps": 906, "loss": 0.27695173025131226, "lr": 3.341459391372016e-05, "epoch": 1.1760066417600665, "percentage": 39.18, "elapsed_time": "1 day, 10:22:13", "remaining_time": "2 days, 5:20:48", "throughput": 600.48, "total_tokens": 74299168} {"current_steps": 356, "total_steps": 906, "loss": 0.27618107199668884, "lr": 3.333291292050981e-05, "epoch": 1.1793275217932753, "percentage": 39.29, "elapsed_time": "1 day, 10:27:25", "remaining_time": "2 days, 5:14:03", "throughput": 600.7, "total_tokens": 74514120} {"current_steps": 357, "total_steps": 906, "loss": 0.2841775417327881, "lr": 3.32511317337509e-05, "epoch": 1.182648401826484, "percentage": 39.4, "elapsed_time": "1 day, 10:32:15", "remaining_time": "2 days, 5:06:44", "throughput": 600.97, "total_tokens": 74721888} {"current_steps": 358, "total_steps": 906, "loss": 0.272269070148468, "lr": 3.31692513367667e-05, "epoch": 1.1859692818596927, "percentage": 39.51, "elapsed_time": "1 day, 10:37:36", "remaining_time": "2 days, 5:00:14", "throughput": 601.15, "total_tokens": 74936984} {"current_steps": 359, "total_steps": 906, "loss": 0.2603960335254669, "lr": 3.30872727140734e-05, "epoch": 1.1892901618929017, "percentage": 39.62, "elapsed_time": "1 day, 10:42:05", "remaining_time": "2 days, 4:52:26", "throughput": 601.5, "total_tokens": 75143336} {"current_steps": 360, "total_steps": 906, "loss": 0.28243565559387207, "lr": 3.300519685136822e-05, "epoch": 1.1926110419261104, "percentage": 39.74, "elapsed_time": "1 day, 10:47:06", "remaining_time": "2 days, 4:45:26", "throughput": 601.72, "total_tokens": 75351112} {"current_steps": 361, "total_steps": 906, "loss": 0.2702184021472931, "lr": 3.292302473551757e-05, "epoch": 1.1959319219593192, "percentage": 39.85, "elapsed_time": "1 day, 10:52:18", "remaining_time": "2 days, 4:38:45", "throughput": 601.87, "total_tokens": 75557408} {"current_steps": 362, "total_steps": 906, "loss": 0.27533334493637085, "lr": 3.284075735454521e-05, "epoch": 1.199252801992528, "percentage": 39.96, "elapsed_time": "1 day, 10:57:24", "remaining_time": "2 days, 4:31:53", "throughput": 602.07, "total_tokens": 75767296} {"current_steps": 363, "total_steps": 906, "loss": 0.2790154218673706, "lr": 3.2758395697620334e-05, "epoch": 1.202573682025737, "percentage": 40.07, "elapsed_time": "1 day, 11:02:21", "remaining_time": "2 days, 4:24:51", "throughput": 602.32, "total_tokens": 75977360} {"current_steps": 364, "total_steps": 906, "loss": 0.2722439467906952, "lr": 3.267594075504572e-05, "epoch": 1.2058945620589456, "percentage": 40.18, "elapsed_time": "1 day, 11:07:12", "remaining_time": "2 days, 4:17:39", "throughput": 602.59, "total_tokens": 76187232} {"current_steps": 365, "total_steps": 906, "loss": 0.2734944224357605, "lr": 3.259339351824575e-05, "epoch": 1.2092154420921544, "percentage": 40.29, "elapsed_time": "1 day, 11:12:12", "remaining_time": "2 days, 4:10:42", "throughput": 602.82, "total_tokens": 76397096} {"current_steps": 366, "total_steps": 906, "loss": 0.2712152600288391, "lr": 3.2510754979754595e-05, "epoch": 1.2125363221253633, "percentage": 40.4, "elapsed_time": "1 day, 11:17:07", "remaining_time": "2 days, 4:03:37", "throughput": 603.09, "total_tokens": 76608960} {"current_steps": 367, "total_steps": 906, "loss": 0.27213454246520996, "lr": 3.2428026133204184e-05, "epoch": 1.215857202158572, "percentage": 40.51, "elapsed_time": "1 day, 11:22:21", "remaining_time": "2 days, 3:57:02", "throughput": 603.27, "total_tokens": 76820816} {"current_steps": 368, "total_steps": 906, "loss": 0.27443960309028625, "lr": 3.23452079733123e-05, "epoch": 1.2191780821917808, "percentage": 40.62, "elapsed_time": "1 day, 11:27:24", "remaining_time": "2 days, 3:50:09", "throughput": 603.49, "total_tokens": 77032072} {"current_steps": 369, "total_steps": 906, "loss": 0.27778327465057373, "lr": 3.226230149587063e-05, "epoch": 1.2224989622249895, "percentage": 40.73, "elapsed_time": "1 day, 11:31:59", "remaining_time": "2 days, 3:42:39", "throughput": 603.78, "total_tokens": 77235072} {"current_steps": 370, "total_steps": 906, "loss": 0.27579450607299805, "lr": 3.217930769773275e-05, "epoch": 1.2258198422581985, "percentage": 40.84, "elapsed_time": "1 day, 11:37:21", "remaining_time": "2 days, 3:36:16", "throughput": 603.87, "total_tokens": 77440800} {"current_steps": 371, "total_steps": 906, "loss": 0.2702082395553589, "lr": 3.20962275768022e-05, "epoch": 1.2291407222914073, "percentage": 40.95, "elapsed_time": "1 day, 11:42:45", "remaining_time": "2 days, 3:29:57", "throughput": 603.97, "total_tokens": 77649600} {"current_steps": 372, "total_steps": 906, "loss": 0.2788946032524109, "lr": 3.201306213202041e-05, "epoch": 1.232461602324616, "percentage": 41.06, "elapsed_time": "1 day, 11:48:23", "remaining_time": "2 days, 3:23:59", "throughput": 604.05, "total_tokens": 77863888} {"current_steps": 373, "total_steps": 906, "loss": 0.2840201258659363, "lr": 3.1929812363354766e-05, "epoch": 1.2357824823578247, "percentage": 41.17, "elapsed_time": "1 day, 11:53:55", "remaining_time": "2 days, 3:17:51", "throughput": 604.12, "total_tokens": 78074192} {"current_steps": 374, "total_steps": 906, "loss": 0.27590206265449524, "lr": 3.184647927178654e-05, "epoch": 1.2391033623910337, "percentage": 41.28, "elapsed_time": "1 day, 11:58:50", "remaining_time": "2 days, 3:10:51", "throughput": 604.37, "total_tokens": 78284336} {"current_steps": 375, "total_steps": 906, "loss": 0.2710535526275635, "lr": 3.1763063859298845e-05, "epoch": 1.2424242424242424, "percentage": 41.39, "elapsed_time": "1 day, 12:03:31", "remaining_time": "2 days, 3:03:32", "throughput": 604.66, "total_tokens": 78492168} {"current_steps": 376, "total_steps": 906, "loss": 0.2793447971343994, "lr": 3.167956712886463e-05, "epoch": 1.2457451224574512, "percentage": 41.5, "elapsed_time": "1 day, 12:08:17", "remaining_time": "2 days, 2:56:22", "throughput": 604.93, "total_tokens": 78699680} {"current_steps": 377, "total_steps": 906, "loss": 0.2739261984825134, "lr": 3.159599008443459e-05, "epoch": 1.2490660024906601, "percentage": 41.61, "elapsed_time": "1 day, 12:13:05", "remaining_time": "2 days, 2:49:14", "throughput": 605.2, "total_tokens": 78908672} {"current_steps": 378, "total_steps": 906, "loss": 0.27112993597984314, "lr": 3.151233373092511e-05, "epoch": 1.2523868825238689, "percentage": 41.72, "elapsed_time": "1 day, 12:17:44", "remaining_time": "2 days, 2:41:55", "throughput": 605.54, "total_tokens": 79123136} {"current_steps": 379, "total_steps": 906, "loss": 0.2774733901023865, "lr": 3.142859907420615e-05, "epoch": 1.2557077625570776, "percentage": 41.83, "elapsed_time": "1 day, 12:22:24", "remaining_time": "2 days, 2:34:38", "throughput": 605.83, "total_tokens": 79329632} {"current_steps": 380, "total_steps": 906, "loss": 0.2741287350654602, "lr": 3.1344787121089204e-05, "epoch": 1.2590286425902864, "percentage": 41.94, "elapsed_time": "1 day, 12:27:38", "remaining_time": "2 days, 2:28:09", "throughput": 605.97, "total_tokens": 79539320} {"current_steps": 381, "total_steps": 906, "loss": 0.2756434679031372, "lr": 3.126089887931515e-05, "epoch": 1.262349522623495, "percentage": 42.05, "elapsed_time": "1 day, 12:32:44", "remaining_time": "2 days, 2:21:29", "throughput": 606.14, "total_tokens": 79746632} {"current_steps": 382, "total_steps": 906, "loss": 0.28269442915916443, "lr": 3.117693535754213e-05, "epoch": 1.265670402656704, "percentage": 42.16, "elapsed_time": "1 day, 12:37:57", "remaining_time": "2 days, 2:14:59", "throughput": 606.3, "total_tokens": 79957024} {"current_steps": 383, "total_steps": 906, "loss": 0.2642611861228943, "lr": 3.109289756533349e-05, "epoch": 1.2689912826899128, "percentage": 42.27, "elapsed_time": "1 day, 12:42:39", "remaining_time": "2 days, 2:07:48", "throughput": 606.57, "total_tokens": 80164488} {"current_steps": 384, "total_steps": 906, "loss": 0.27799808979034424, "lr": 3.100878651314554e-05, "epoch": 1.2723121627231215, "percentage": 42.38, "elapsed_time": "1 day, 12:47:28", "remaining_time": "2 days, 2:00:46", "throughput": 606.79, "total_tokens": 80367968} {"current_steps": 385, "total_steps": 906, "loss": 0.2755585014820099, "lr": 3.092460321231547e-05, "epoch": 1.2756330427563305, "percentage": 42.49, "elapsed_time": "1 day, 12:52:07", "remaining_time": "2 days, 1:53:33", "throughput": 607.07, "total_tokens": 80575048} {"current_steps": 386, "total_steps": 906, "loss": 0.28033632040023804, "lr": 3.084034867504921e-05, "epoch": 1.2789539227895392, "percentage": 42.6, "elapsed_time": "1 day, 12:57:10", "remaining_time": "2 days, 1:46:52", "throughput": 607.31, "total_tokens": 80791136} {"current_steps": 387, "total_steps": 906, "loss": 0.2795390784740448, "lr": 3.075602391440918e-05, "epoch": 1.282274802822748, "percentage": 42.72, "elapsed_time": "1 day, 13:02:08", "remaining_time": "2 days, 1:40:04", "throughput": 607.56, "total_tokens": 81004208} {"current_steps": 388, "total_steps": 906, "loss": 0.27803707122802734, "lr": 3.0671629944302164e-05, "epoch": 1.285595682855957, "percentage": 42.83, "elapsed_time": "1 day, 13:07:02", "remaining_time": "2 days, 1:33:12", "throughput": 607.81, "total_tokens": 81216192} {"current_steps": 389, "total_steps": 906, "loss": 0.27945441007614136, "lr": 3.058716777946713e-05, "epoch": 1.2889165628891657, "percentage": 42.94, "elapsed_time": "1 day, 13:12:16", "remaining_time": "2 days, 1:26:48", "throughput": 608.01, "total_tokens": 81434112} {"current_steps": 390, "total_steps": 906, "loss": 0.2775178849697113, "lr": 3.0502638435462995e-05, "epoch": 1.2922374429223744, "percentage": 43.05, "elapsed_time": "1 day, 13:17:04", "remaining_time": "2 days, 1:19:49", "throughput": 608.23, "total_tokens": 81639880} {"current_steps": 391, "total_steps": 906, "loss": 0.2766043245792389, "lr": 3.0418042928656414e-05, "epoch": 1.2955583229555832, "percentage": 43.16, "elapsed_time": "1 day, 13:21:49", "remaining_time": "2 days, 1:12:47", "throughput": 608.53, "total_tokens": 81853120} {"current_steps": 392, "total_steps": 906, "loss": 0.27493974566459656, "lr": 3.0333382276209595e-05, "epoch": 1.298879202988792, "percentage": 43.27, "elapsed_time": "1 day, 13:26:32", "remaining_time": "2 days, 1:05:43", "throughput": 608.78, "total_tokens": 82059608} {"current_steps": 393, "total_steps": 906, "loss": 0.28059232234954834, "lr": 3.0248657496068027e-05, "epoch": 1.3022000830220009, "percentage": 43.38, "elapsed_time": "1 day, 13:31:22", "remaining_time": "2 days, 0:58:48", "throughput": 608.99, "total_tokens": 82263960} {"current_steps": 394, "total_steps": 906, "loss": 0.2766563296318054, "lr": 3.0163869606948275e-05, "epoch": 1.3055209630552096, "percentage": 43.49, "elapsed_time": "1 day, 13:35:56", "remaining_time": "2 days, 0:51:34", "throughput": 609.3, "total_tokens": 82472272} {"current_steps": 395, "total_steps": 906, "loss": 0.26600369811058044, "lr": 3.0079019628325706e-05, "epoch": 1.3088418430884183, "percentage": 43.6, "elapsed_time": "1 day, 13:40:59", "remaining_time": "2 days, 0:44:59", "throughput": 609.48, "total_tokens": 82682592} {"current_steps": 396, "total_steps": 906, "loss": 0.27596497535705566, "lr": 2.999410858042225e-05, "epoch": 1.3121627231216273, "percentage": 43.71, "elapsed_time": "1 day, 13:45:59", "remaining_time": "2 days, 0:38:18", "throughput": 609.72, "total_tokens": 82897328} {"current_steps": 397, "total_steps": 906, "loss": 0.2763836085796356, "lr": 2.990913748419411e-05, "epoch": 1.315483603154836, "percentage": 43.82, "elapsed_time": "1 day, 13:50:45", "remaining_time": "2 days, 0:31:23", "throughput": 609.98, "total_tokens": 83107152} {"current_steps": 398, "total_steps": 906, "loss": 0.2720406651496887, "lr": 2.9824107361319516e-05, "epoch": 1.3188044831880448, "percentage": 43.93, "elapsed_time": "1 day, 13:55:55", "remaining_time": "2 days, 0:24:57", "throughput": 610.16, "total_tokens": 83320536} {"current_steps": 399, "total_steps": 906, "loss": 0.2695067226886749, "lr": 2.97390192341864e-05, "epoch": 1.3221253632212537, "percentage": 44.04, "elapsed_time": "1 day, 14:00:43", "remaining_time": "2 days, 0:18:04", "throughput": 610.43, "total_tokens": 83533096} {"current_steps": 400, "total_steps": 906, "loss": 0.27491211891174316, "lr": 2.965387412588017e-05, "epoch": 1.3254462432544625, "percentage": 44.15, "elapsed_time": "1 day, 14:05:34", "remaining_time": "2 days, 0:11:15", "throughput": 610.62, "total_tokens": 83737664} {"current_steps": 401, "total_steps": 906, "loss": 0.26775655150413513, "lr": 2.9568673060171326e-05, "epoch": 1.3287671232876712, "percentage": 44.26, "elapsed_time": "1 day, 14:10:20", "remaining_time": "2 days, 0:04:21", "throughput": 610.89, "total_tokens": 83948872} {"current_steps": 402, "total_steps": 906, "loss": 0.26905345916748047, "lr": 2.94834170615032e-05, "epoch": 1.33208800332088, "percentage": 44.37, "elapsed_time": "1 day, 14:15:28", "remaining_time": "1 day, 23:57:54", "throughput": 611.08, "total_tokens": 84163496} {"current_steps": 403, "total_steps": 906, "loss": 0.27601978182792664, "lr": 2.9398107154979638e-05, "epoch": 1.335408883354089, "percentage": 44.48, "elapsed_time": "1 day, 14:20:27", "remaining_time": "1 day, 23:51:17", "throughput": 611.28, "total_tokens": 84374216} {"current_steps": 404, "total_steps": 906, "loss": 0.27592986822128296, "lr": 2.931274436635266e-05, "epoch": 1.3387297633872977, "percentage": 44.59, "elapsed_time": "1 day, 14:25:26", "remaining_time": "1 day, 23:44:40", "throughput": 611.49, "total_tokens": 84585680} {"current_steps": 405, "total_steps": 906, "loss": 0.2764306664466858, "lr": 2.922732972201014e-05, "epoch": 1.3420506434205064, "percentage": 44.7, "elapsed_time": "1 day, 14:30:30", "remaining_time": "1 day, 23:38:11", "throughput": 611.67, "total_tokens": 84796240} {"current_steps": 406, "total_steps": 906, "loss": 0.2820674180984497, "lr": 2.914186424896343e-05, "epoch": 1.3453715234537151, "percentage": 44.81, "elapsed_time": "1 day, 14:35:36", "remaining_time": "1 day, 23:31:44", "throughput": 611.83, "total_tokens": 85006112} {"current_steps": 407, "total_steps": 906, "loss": 0.2697965204715729, "lr": 2.9056348974835067e-05, "epoch": 1.348692403486924, "percentage": 44.92, "elapsed_time": "1 day, 14:40:32", "remaining_time": "1 day, 23:25:04", "throughput": 612.07, "total_tokens": 85219504} {"current_steps": 408, "total_steps": 906, "loss": 0.2750285863876343, "lr": 2.897078492784638e-05, "epoch": 1.3520132835201328, "percentage": 45.03, "elapsed_time": "1 day, 14:45:43", "remaining_time": "1 day, 23:18:45", "throughput": 612.22, "total_tokens": 85431864} {"current_steps": 409, "total_steps": 906, "loss": 0.27826839685440063, "lr": 2.8885173136805127e-05, "epoch": 1.3553341635533416, "percentage": 45.14, "elapsed_time": "1 day, 14:50:27", "remaining_time": "1 day, 23:11:53", "throughput": 612.47, "total_tokens": 85640848} {"current_steps": 410, "total_steps": 906, "loss": 0.2801903784275055, "lr": 2.879951463109313e-05, "epoch": 1.3586550435865505, "percentage": 45.25, "elapsed_time": "1 day, 14:54:53", "remaining_time": "1 day, 23:04:38", "throughput": 612.78, "total_tokens": 85846408} {"current_steps": 411, "total_steps": 906, "loss": 0.2678714394569397, "lr": 2.8713810440653926e-05, "epoch": 1.3619759236197593, "percentage": 45.36, "elapsed_time": "1 day, 14:59:16", "remaining_time": "1 day, 22:57:22", "throughput": 613.1, "total_tokens": 86052064} {"current_steps": 412, "total_steps": 906, "loss": 0.2706253230571747, "lr": 2.862806159598032e-05, "epoch": 1.365296803652968, "percentage": 45.47, "elapsed_time": "1 day, 15:03:46", "remaining_time": "1 day, 22:50:14", "throughput": 613.44, "total_tokens": 86265656} {"current_steps": 413, "total_steps": 906, "loss": 0.2835608422756195, "lr": 2.8542269128102063e-05, "epoch": 1.3686176836861768, "percentage": 45.58, "elapsed_time": "1 day, 15:08:38", "remaining_time": "1 day, 22:43:35", "throughput": 613.64, "total_tokens": 86473072} {"current_steps": 414, "total_steps": 906, "loss": 0.2807215750217438, "lr": 2.8456434068573406e-05, "epoch": 1.3719385637193857, "percentage": 45.7, "elapsed_time": "1 day, 15:13:36", "remaining_time": "1 day, 22:37:02", "throughput": 613.81, "total_tokens": 86680248} {"current_steps": 415, "total_steps": 906, "loss": 0.27627435326576233, "lr": 2.837055744946072e-05, "epoch": 1.3752594437525945, "percentage": 45.81, "elapsed_time": "1 day, 15:18:17", "remaining_time": "1 day, 22:30:09", "throughput": 614.08, "total_tokens": 86890064} {"current_steps": 416, "total_steps": 906, "loss": 0.26245152950286865, "lr": 2.828464030333009e-05, "epoch": 1.3785803237858032, "percentage": 45.92, "elapsed_time": "1 day, 15:23:42", "remaining_time": "1 day, 22:24:10", "throughput": 614.11, "total_tokens": 87095480} {"current_steps": 417, "total_steps": 906, "loss": 0.27233731746673584, "lr": 2.819868366323488e-05, "epoch": 1.381901203819012, "percentage": 46.03, "elapsed_time": "1 day, 15:29:02", "remaining_time": "1 day, 22:18:05", "throughput": 614.2, "total_tokens": 87304240} {"current_steps": 418, "total_steps": 906, "loss": 0.28139635920524597, "lr": 2.811268856270332e-05, "epoch": 1.385222083852221, "percentage": 46.14, "elapsed_time": "1 day, 15:34:07", "remaining_time": "1 day, 22:11:42", "throughput": 614.37, "total_tokens": 87515776} {"current_steps": 419, "total_steps": 906, "loss": 0.27290260791778564, "lr": 2.8026656035726095e-05, "epoch": 1.3885429638854296, "percentage": 46.25, "elapsed_time": "1 day, 15:39:01", "remaining_time": "1 day, 22:05:07", "throughput": 614.58, "total_tokens": 87726584} {"current_steps": 420, "total_steps": 906, "loss": 0.2759082019329071, "lr": 2.7940587116743894e-05, "epoch": 1.3918638439186384, "percentage": 46.36, "elapsed_time": "1 day, 15:43:54", "remaining_time": "1 day, 21:58:31", "throughput": 614.84, "total_tokens": 87943400} {"current_steps": 421, "total_steps": 906, "loss": 0.2684614956378937, "lr": 2.7854482840634965e-05, "epoch": 1.3951847239518473, "percentage": 46.47, "elapsed_time": "1 day, 15:49:32", "remaining_time": "1 day, 21:52:47", "throughput": 614.85, "total_tokens": 88153152} {"current_steps": 422, "total_steps": 906, "loss": 0.26988548040390015, "lr": 2.77683442427027e-05, "epoch": 1.398505603985056, "percentage": 46.58, "elapsed_time": "1 day, 15:54:05", "remaining_time": "1 day, 21:45:49", "throughput": 615.11, "total_tokens": 88357528} {"current_steps": 423, "total_steps": 906, "loss": 0.2713548541069031, "lr": 2.7682172358663173e-05, "epoch": 1.4018264840182648, "percentage": 46.69, "elapsed_time": "1 day, 15:59:26", "remaining_time": "1 day, 21:39:47", "throughput": 615.2, "total_tokens": 88567776} {"current_steps": 424, "total_steps": 906, "loss": 0.27689388394355774, "lr": 2.7595968224632674e-05, "epoch": 1.4051473640514736, "percentage": 46.8, "elapsed_time": "1 day, 16:04:30", "remaining_time": "1 day, 21:33:25", "throughput": 615.38, "total_tokens": 88780464} {"current_steps": 425, "total_steps": 906, "loss": 0.2730310559272766, "lr": 2.7509732877115257e-05, "epoch": 1.4084682440846825, "percentage": 46.91, "elapsed_time": "1 day, 16:09:41", "remaining_time": "1 day, 21:27:12", "throughput": 615.54, "total_tokens": 88995960} {"current_steps": 426, "total_steps": 906, "loss": 0.2728288471698761, "lr": 2.74234673529903e-05, "epoch": 1.4117891241178913, "percentage": 47.02, "elapsed_time": "1 day, 16:14:54", "remaining_time": "1 day, 21:21:01", "throughput": 615.68, "total_tokens": 89208040} {"current_steps": 427, "total_steps": 906, "loss": 0.28198131918907166, "lr": 2.73371726895e-05, "epoch": 1.4151100041511, "percentage": 47.13, "elapsed_time": "1 day, 16:20:23", "remaining_time": "1 day, 21:15:08", "throughput": 615.73, "total_tokens": 89418376} {"current_steps": 428, "total_steps": 906, "loss": 0.27948057651519775, "lr": 2.725084992423694e-05, "epoch": 1.4184308841843087, "percentage": 47.24, "elapsed_time": "1 day, 16:25:56", "remaining_time": "1 day, 21:09:20", "throughput": 615.74, "total_tokens": 89624360} {"current_steps": 429, "total_steps": 906, "loss": 0.2838206887245178, "lr": 2.716450009513158e-05, "epoch": 1.4217517642175177, "percentage": 47.35, "elapsed_time": "1 day, 16:31:16", "remaining_time": "1 day, 21:03:17", "throughput": 615.86, "total_tokens": 89839176} {"current_steps": 430, "total_steps": 906, "loss": 0.27308711409568787, "lr": 2.7078124240439795e-05, "epoch": 1.4250726442507264, "percentage": 47.46, "elapsed_time": "1 day, 16:36:37", "remaining_time": "1 day, 20:57:16", "throughput": 615.92, "total_tokens": 90045400} {"current_steps": 431, "total_steps": 906, "loss": 0.27352002263069153, "lr": 2.6991723398730383e-05, "epoch": 1.4283935242839352, "percentage": 47.57, "elapsed_time": "1 day, 16:41:32", "remaining_time": "1 day, 20:50:47", "throughput": 616.13, "total_tokens": 90259064} {"current_steps": 432, "total_steps": 906, "loss": 0.26953351497650146, "lr": 2.6905298608872588e-05, "epoch": 1.4317144043171441, "percentage": 47.68, "elapsed_time": "1 day, 16:46:32", "remaining_time": "1 day, 20:44:24", "throughput": 616.3, "total_tokens": 90468720} {"current_steps": 433, "total_steps": 906, "loss": 0.2790805995464325, "lr": 2.68188509100236e-05, "epoch": 1.4350352843503529, "percentage": 47.79, "elapsed_time": "1 day, 16:51:19", "remaining_time": "1 day, 20:37:46", "throughput": 616.52, "total_tokens": 90677544} {"current_steps": 434, "total_steps": 906, "loss": 0.2723555266857147, "lr": 2.6732381341616065e-05, "epoch": 1.4383561643835616, "percentage": 47.9, "elapsed_time": "1 day, 16:55:57", "remaining_time": "1 day, 20:30:59", "throughput": 616.79, "total_tokens": 90888704} {"current_steps": 435, "total_steps": 906, "loss": 0.26789337396621704, "lr": 2.6645890943345585e-05, "epoch": 1.4416770444167706, "percentage": 48.01, "elapsed_time": "1 day, 17:00:42", "remaining_time": "1 day, 20:24:21", "throughput": 616.97, "total_tokens": 91090856} {"current_steps": 436, "total_steps": 906, "loss": 0.28620174527168274, "lr": 2.6559380755158208e-05, "epoch": 1.4449979244499793, "percentage": 48.12, "elapsed_time": "1 day, 17:05:40", "remaining_time": "1 day, 20:17:57", "throughput": 617.15, "total_tokens": 91301944} {"current_steps": 437, "total_steps": 906, "loss": 0.27092844247817993, "lr": 2.6472851817237948e-05, "epoch": 1.448318804483188, "percentage": 48.23, "elapsed_time": "1 day, 17:10:12", "remaining_time": "1 day, 20:11:05", "throughput": 617.41, "total_tokens": 91508136} {"current_steps": 438, "total_steps": 906, "loss": 0.2821858525276184, "lr": 2.6386305169994256e-05, "epoch": 1.4516396845163968, "percentage": 48.34, "elapsed_time": "1 day, 17:14:49", "remaining_time": "1 day, 20:04:19", "throughput": 617.67, "total_tokens": 91717688} {"current_steps": 439, "total_steps": 906, "loss": 0.2690110206604004, "lr": 2.6299741854049508e-05, "epoch": 1.4549605645496055, "percentage": 48.45, "elapsed_time": "1 day, 17:19:30", "remaining_time": "1 day, 19:57:39", "throughput": 617.9, "total_tokens": 91925912} {"current_steps": 440, "total_steps": 906, "loss": 0.26425009965896606, "lr": 2.621316291022652e-05, "epoch": 1.4582814445828145, "percentage": 48.57, "elapsed_time": "1 day, 17:23:51", "remaining_time": "1 day, 19:50:37", "throughput": 618.23, "total_tokens": 92136264} {"current_steps": 441, "total_steps": 906, "loss": 0.2754976749420166, "lr": 2.6126569379535985e-05, "epoch": 1.4616023246160232, "percentage": 48.68, "elapsed_time": "1 day, 17:28:45", "remaining_time": "1 day, 19:44:11", "throughput": 618.4, "total_tokens": 92342792} {"current_steps": 442, "total_steps": 906, "loss": 0.2782744765281677, "lr": 2.6039962303164023e-05, "epoch": 1.464923204649232, "percentage": 48.79, "elapsed_time": "1 day, 17:34:04", "remaining_time": "1 day, 19:38:12", "throughput": 618.49, "total_tokens": 92554056} {"current_steps": 443, "total_steps": 906, "loss": 0.27722615003585815, "lr": 2.5953342722459594e-05, "epoch": 1.468244084682441, "percentage": 48.9, "elapsed_time": "1 day, 17:38:57", "remaining_time": "1 day, 19:31:46", "throughput": 618.66, "total_tokens": 92759472} {"current_steps": 444, "total_steps": 906, "loss": 0.27563533186912537, "lr": 2.5866711678922035e-05, "epoch": 1.4715649647156497, "percentage": 49.01, "elapsed_time": "1 day, 17:43:51", "remaining_time": "1 day, 19:25:21", "throughput": 618.83, "total_tokens": 92968024} {"current_steps": 445, "total_steps": 906, "loss": 0.2683257460594177, "lr": 2.5780070214188478e-05, "epoch": 1.4748858447488584, "percentage": 49.12, "elapsed_time": "1 day, 17:48:44", "remaining_time": "1 day, 19:18:57", "throughput": 619.05, "total_tokens": 93182904} {"current_steps": 446, "total_steps": 906, "loss": 0.27707743644714355, "lr": 2.5693419370021392e-05, "epoch": 1.4782067247820674, "percentage": 49.23, "elapsed_time": "1 day, 17:53:49", "remaining_time": "1 day, 19:12:44", "throughput": 619.21, "total_tokens": 93395352} {"current_steps": 447, "total_steps": 906, "loss": 0.285401314496994, "lr": 2.5606760188296004e-05, "epoch": 1.4815276048152761, "percentage": 49.34, "elapsed_time": "1 day, 17:59:16", "remaining_time": "1 day, 19:06:54", "throughput": 619.27, "total_tokens": 93606256} {"current_steps": 448, "total_steps": 906, "loss": 0.27463263273239136, "lr": 2.5520093710987785e-05, "epoch": 1.4848484848484849, "percentage": 49.45, "elapsed_time": "1 day, 18:03:56", "remaining_time": "1 day, 19:00:16", "throughput": 619.5, "total_tokens": 93814072} {"current_steps": 449, "total_steps": 906, "loss": 0.2858240008354187, "lr": 2.5433420980159944e-05, "epoch": 1.4881693648816936, "percentage": 49.56, "elapsed_time": "1 day, 18:09:27", "remaining_time": "1 day, 18:54:31", "throughput": 619.59, "total_tokens": 94033240} {"current_steps": 450, "total_steps": 906, "loss": 0.2770846486091614, "lr": 2.5346743037950864e-05, "epoch": 1.4914902449149023, "percentage": 49.67, "elapsed_time": "1 day, 18:14:05", "remaining_time": "1 day, 18:47:52", "throughput": 619.83, "total_tokens": 94242952} {"current_steps": 451, "total_steps": 906, "loss": 0.2803241014480591, "lr": 2.526006092656161e-05, "epoch": 1.4948111249481113, "percentage": 49.78, "elapsed_time": "1 day, 18:18:54", "remaining_time": "1 day, 18:41:25", "throughput": 620.04, "total_tokens": 94453584} {"current_steps": 452, "total_steps": 906, "loss": 0.2788984775543213, "lr": 2.5173375688243343e-05, "epoch": 1.49813200498132, "percentage": 49.89, "elapsed_time": "1 day, 18:24:02", "remaining_time": "1 day, 18:35:17", "throughput": 620.2, "total_tokens": 94668832} {"current_steps": 453, "total_steps": 906, "loss": 0.28381669521331787, "lr": 2.508668836528486e-05, "epoch": 1.5014528850145288, "percentage": 50.0, "elapsed_time": "1 day, 18:28:49", "remaining_time": "1 day, 18:28:49", "throughput": 620.45, "total_tokens": 94884536} {"current_steps": 454, "total_steps": 906, "loss": 0.2760803699493408, "lr": 2.5e-05, "epoch": 1.5047737650477377, "percentage": 50.11, "elapsed_time": "1 day, 18:33:28", "remaining_time": "1 day, 18:22:13", "throughput": 620.7, "total_tokens": 95096920} {"current_steps": 455, "total_steps": 906, "loss": 0.2771623730659485, "lr": 2.491331163471514e-05, "epoch": 1.5080946450809465, "percentage": 50.22, "elapsed_time": "1 day, 18:38:12", "remaining_time": "1 day, 18:15:43", "throughput": 620.93, "total_tokens": 95307944} {"current_steps": 456, "total_steps": 906, "loss": 0.28440573811531067, "lr": 2.482662431175666e-05, "epoch": 1.5114155251141552, "percentage": 50.33, "elapsed_time": "1 day, 18:43:21", "remaining_time": "1 day, 18:09:38", "throughput": 621.03, "total_tokens": 95515968} {"current_steps": 457, "total_steps": 906, "loss": 0.2825664281845093, "lr": 2.4739939073438397e-05, "epoch": 1.5147364051473642, "percentage": 50.44, "elapsed_time": "1 day, 18:48:19", "remaining_time": "1 day, 18:03:22", "throughput": 621.2, "total_tokens": 95726024} {"current_steps": 458, "total_steps": 906, "loss": 0.28354400396347046, "lr": 2.465325696204914e-05, "epoch": 1.5180572851805727, "percentage": 50.55, "elapsed_time": "1 day, 18:52:59", "remaining_time": "1 day, 17:56:48", "throughput": 621.43, "total_tokens": 95935816} {"current_steps": 459, "total_steps": 906, "loss": 0.2669481635093689, "lr": 2.456657901984006e-05, "epoch": 1.5213781652137817, "percentage": 50.66, "elapsed_time": "1 day, 18:57:52", "remaining_time": "1 day, 17:50:28", "throughput": 621.59, "total_tokens": 96142752} {"current_steps": 460, "total_steps": 906, "loss": 0.2789996862411499, "lr": 2.4479906289012218e-05, "epoch": 1.5246990452469904, "percentage": 50.77, "elapsed_time": "1 day, 19:03:09", "remaining_time": "1 day, 17:44:32", "throughput": 621.67, "total_tokens": 96352344} {"current_steps": 461, "total_steps": 906, "loss": 0.2797940671443939, "lr": 2.4393239811704e-05, "epoch": 1.5280199252801991, "percentage": 50.88, "elapsed_time": "1 day, 19:08:45", "remaining_time": "1 day, 17:38:54", "throughput": 621.66, "total_tokens": 96559576} {"current_steps": 462, "total_steps": 906, "loss": 0.2745603919029236, "lr": 2.430658062997861e-05, "epoch": 1.531340805313408, "percentage": 50.99, "elapsed_time": "1 day, 19:13:18", "remaining_time": "1 day, 17:32:16", "throughput": 621.91, "total_tokens": 96768232} {"current_steps": 463, "total_steps": 906, "loss": 0.2753414213657379, "lr": 2.4219929785811518e-05, "epoch": 1.5346616853466168, "percentage": 51.1, "elapsed_time": "1 day, 19:18:43", "remaining_time": "1 day, 17:26:28", "throughput": 621.98, "total_tokens": 96981512} {"current_steps": 464, "total_steps": 906, "loss": 0.2625735402107239, "lr": 2.4133288321077978e-05, "epoch": 1.5379825653798256, "percentage": 51.21, "elapsed_time": "1 day, 19:23:34", "remaining_time": "1 day, 17:20:07", "throughput": 622.15, "total_tokens": 97189136} {"current_steps": 465, "total_steps": 906, "loss": 0.27124154567718506, "lr": 2.4046657277540412e-05, "epoch": 1.5413034454130345, "percentage": 51.32, "elapsed_time": "1 day, 19:28:29", "remaining_time": "1 day, 17:13:51", "throughput": 622.35, "total_tokens": 97403824} {"current_steps": 466, "total_steps": 906, "loss": 0.27361199259757996, "lr": 2.3960037696835986e-05, "epoch": 1.5446243254462433, "percentage": 51.43, "elapsed_time": "1 day, 19:33:08", "remaining_time": "1 day, 17:07:20", "throughput": 622.53, "total_tokens": 97605736} {"current_steps": 467, "total_steps": 906, "loss": 0.2782898247241974, "lr": 2.3873430620464024e-05, "epoch": 1.547945205479452, "percentage": 51.55, "elapsed_time": "1 day, 19:38:03", "remaining_time": "1 day, 17:01:05", "throughput": 622.63, "total_tokens": 97805720} {"current_steps": 468, "total_steps": 906, "loss": 0.2831963896751404, "lr": 2.3786837089773494e-05, "epoch": 1.551266085512661, "percentage": 51.66, "elapsed_time": "1 day, 19:42:59", "remaining_time": "1 day, 16:54:51", "throughput": 622.77, "total_tokens": 98011824} {"current_steps": 469, "total_steps": 906, "loss": 0.27522018551826477, "lr": 2.3700258145950495e-05, "epoch": 1.5545869655458695, "percentage": 51.77, "elapsed_time": "1 day, 19:47:38", "remaining_time": "1 day, 16:48:21", "throughput": 622.99, "total_tokens": 98219592} {"current_steps": 470, "total_steps": 906, "loss": 0.2746099829673767, "lr": 2.361369483000575e-05, "epoch": 1.5579078455790785, "percentage": 51.88, "elapsed_time": "1 day, 19:52:25", "remaining_time": "1 day, 16:41:59", "throughput": 623.21, "total_tokens": 98433344} {"current_steps": 471, "total_steps": 906, "loss": 0.27125734090805054, "lr": 2.3527148182762054e-05, "epoch": 1.5612287256122872, "percentage": 51.99, "elapsed_time": "1 day, 19:57:40", "remaining_time": "1 day, 16:36:04", "throughput": 623.32, "total_tokens": 98647504} {"current_steps": 472, "total_steps": 906, "loss": 0.27807706594467163, "lr": 2.3440619244841798e-05, "epoch": 1.564549605645496, "percentage": 52.1, "elapsed_time": "1 day, 20:02:40", "remaining_time": "1 day, 16:29:54", "throughput": 623.43, "total_tokens": 98851664} {"current_steps": 473, "total_steps": 906, "loss": 0.2797778248786926, "lr": 2.335410905665442e-05, "epoch": 1.567870485678705, "percentage": 52.21, "elapsed_time": "1 day, 20:07:28", "remaining_time": "1 day, 16:23:35", "throughput": 623.63, "total_tokens": 99062624} {"current_steps": 474, "total_steps": 906, "loss": 0.2710762023925781, "lr": 2.3267618658383938e-05, "epoch": 1.5711913657119136, "percentage": 52.32, "elapsed_time": "1 day, 20:12:29", "remaining_time": "1 day, 16:17:27", "throughput": 623.8, "total_tokens": 99277088} {"current_steps": 475, "total_steps": 906, "loss": 0.2764275372028351, "lr": 2.3181149089976405e-05, "epoch": 1.5745122457451224, "percentage": 52.43, "elapsed_time": "1 day, 20:17:27", "remaining_time": "1 day, 16:11:17", "throughput": 623.95, "total_tokens": 99487256} {"current_steps": 476, "total_steps": 906, "loss": 0.2717147469520569, "lr": 2.3094701391127418e-05, "epoch": 1.5778331257783313, "percentage": 52.54, "elapsed_time": "1 day, 20:22:27", "remaining_time": "1 day, 16:05:09", "throughput": 624.11, "total_tokens": 99700256} {"current_steps": 477, "total_steps": 906, "loss": 0.2777535021305084, "lr": 2.3008276601269623e-05, "epoch": 1.58115400581154, "percentage": 52.65, "elapsed_time": "1 day, 20:27:31", "remaining_time": "1 day, 15:59:06", "throughput": 624.26, "total_tokens": 99914464} {"current_steps": 478, "total_steps": 906, "loss": 0.2830791771411896, "lr": 2.292187575956021e-05, "epoch": 1.5844748858447488, "percentage": 52.76, "elapsed_time": "1 day, 20:32:01", "remaining_time": "1 day, 15:52:31", "throughput": 624.5, "total_tokens": 100121368} {"current_steps": 479, "total_steps": 906, "loss": 0.2885296940803528, "lr": 2.283549990486842e-05, "epoch": 1.5877957658779578, "percentage": 52.87, "elapsed_time": "1 day, 20:37:14", "remaining_time": "1 day, 15:46:36", "throughput": 624.64, "total_tokens": 100339688} {"current_steps": 480, "total_steps": 906, "loss": 0.27374687790870667, "lr": 2.274915007576306e-05, "epoch": 1.5911166459111663, "percentage": 52.98, "elapsed_time": "1 day, 20:42:16", "remaining_time": "1 day, 15:40:30", "throughput": 624.79, "total_tokens": 100550928} {"current_steps": 481, "total_steps": 906, "loss": 0.28530970215797424, "lr": 2.2662827310499995e-05, "epoch": 1.5944375259443753, "percentage": 53.09, "elapsed_time": "1 day, 20:47:28", "remaining_time": "1 day, 15:34:35", "throughput": 624.87, "total_tokens": 100758768} {"current_steps": 482, "total_steps": 906, "loss": 0.26808488368988037, "lr": 2.2576532647009702e-05, "epoch": 1.597758405977584, "percentage": 53.2, "elapsed_time": "1 day, 20:52:06", "remaining_time": "1 day, 15:28:09", "throughput": 625.07, "total_tokens": 100964704} {"current_steps": 483, "total_steps": 906, "loss": 0.2740188539028168, "lr": 2.249026712288474e-05, "epoch": 1.6010792860107927, "percentage": 53.31, "elapsed_time": "1 day, 20:57:13", "remaining_time": "1 day, 15:22:09", "throughput": 625.19, "total_tokens": 101176872} {"current_steps": 484, "total_steps": 906, "loss": 0.2846457362174988, "lr": 2.2404031775367335e-05, "epoch": 1.6044001660440017, "percentage": 53.42, "elapsed_time": "1 day, 21:02:36", "remaining_time": "1 day, 15:16:24", "throughput": 625.24, "total_tokens": 101387376} {"current_steps": 485, "total_steps": 906, "loss": 0.27255263924598694, "lr": 2.2317827641336833e-05, "epoch": 1.6077210460772104, "percentage": 53.53, "elapsed_time": "1 day, 21:07:46", "remaining_time": "1 day, 15:10:27", "throughput": 625.36, "total_tokens": 101599408} {"current_steps": 486, "total_steps": 906, "loss": 0.27387329936027527, "lr": 2.2231655757297304e-05, "epoch": 1.6110419261104192, "percentage": 53.64, "elapsed_time": "1 day, 21:12:55", "remaining_time": "1 day, 15:04:30", "throughput": 625.47, "total_tokens": 101812048} {"current_steps": 487, "total_steps": 906, "loss": 0.28685835003852844, "lr": 2.2145517159365044e-05, "epoch": 1.6143628061436281, "percentage": 53.75, "elapsed_time": "1 day, 21:19:17", "remaining_time": "1 day, 14:59:36", "throughput": 625.34, "total_tokens": 102029232} {"current_steps": 488, "total_steps": 906, "loss": 0.26806920766830444, "lr": 2.205941288325612e-05, "epoch": 1.6176836861768369, "percentage": 53.86, "elapsed_time": "1 day, 21:24:47", "remaining_time": "1 day, 14:53:56", "throughput": 625.35, "total_tokens": 102236200} {"current_steps": 489, "total_steps": 906, "loss": 0.27260643243789673, "lr": 2.197334396427391e-05, "epoch": 1.6210045662100456, "percentage": 53.97, "elapsed_time": "1 day, 21:30:05", "remaining_time": "1 day, 14:48:06", "throughput": 625.39, "total_tokens": 102442192} {"current_steps": 490, "total_steps": 906, "loss": 0.28019481897354126, "lr": 2.1887311437296686e-05, "epoch": 1.6243254462432546, "percentage": 54.08, "elapsed_time": "1 day, 21:35:44", "remaining_time": "1 day, 14:42:35", "throughput": 625.37, "total_tokens": 102651352} {"current_steps": 491, "total_steps": 906, "loss": 0.27420860528945923, "lr": 2.1801316336765126e-05, "epoch": 1.627646326276463, "percentage": 54.19, "elapsed_time": "1 day, 21:41:14", "remaining_time": "1 day, 14:36:56", "throughput": 625.41, "total_tokens": 102863464} {"current_steps": 492, "total_steps": 906, "loss": 0.2780809998512268, "lr": 2.171535969666991e-05, "epoch": 1.630967206309672, "percentage": 54.3, "elapsed_time": "1 day, 21:46:58", "remaining_time": "1 day, 14:31:28", "throughput": 625.4, "total_tokens": 103077960} {"current_steps": 493, "total_steps": 906, "loss": 0.2749224305152893, "lr": 2.162944255053928e-05, "epoch": 1.6342880863428808, "percentage": 54.42, "elapsed_time": "1 day, 21:51:57", "remaining_time": "1 day, 14:25:23", "throughput": 625.52, "total_tokens": 103284040} {"current_steps": 494, "total_steps": 906, "loss": 0.2709444761276245, "lr": 2.15435659314266e-05, "epoch": 1.6376089663760895, "percentage": 54.53, "elapsed_time": "1 day, 21:56:49", "remaining_time": "1 day, 14:19:13", "throughput": 625.71, "total_tokens": 103498296} {"current_steps": 495, "total_steps": 906, "loss": 0.27598223090171814, "lr": 2.145773087189794e-05, "epoch": 1.6409298464092985, "percentage": 54.64, "elapsed_time": "1 day, 22:02:07", "remaining_time": "1 day, 14:13:24", "throughput": 625.77, "total_tokens": 103708136} {"current_steps": 496, "total_steps": 906, "loss": 0.2770792543888092, "lr": 2.137193840401968e-05, "epoch": 1.6442507264425072, "percentage": 54.75, "elapsed_time": "1 day, 22:07:52", "remaining_time": "1 day, 14:07:57", "throughput": 625.74, "total_tokens": 103917744} {"current_steps": 497, "total_steps": 906, "loss": 0.27650129795074463, "lr": 2.128618955934608e-05, "epoch": 1.647571606475716, "percentage": 54.86, "elapsed_time": "1 day, 22:13:12", "remaining_time": "1 day, 14:02:10", "throughput": 625.79, "total_tokens": 104127808} {"current_steps": 498, "total_steps": 906, "loss": 0.28428196907043457, "lr": 2.120048536890687e-05, "epoch": 1.650892486508925, "percentage": 54.97, "elapsed_time": "1 day, 22:18:46", "remaining_time": "1 day, 13:56:35", "throughput": 625.83, "total_tokens": 104341640} {"current_steps": 499, "total_steps": 906, "loss": 0.2710725665092468, "lr": 2.1114826863194882e-05, "epoch": 1.6542133665421337, "percentage": 55.08, "elapsed_time": "1 day, 22:23:53", "remaining_time": "1 day, 13:50:37", "throughput": 625.94, "total_tokens": 104553208} {"current_steps": 500, "total_steps": 906, "loss": 0.2692292332649231, "lr": 2.1029215072153617e-05, "epoch": 1.6575342465753424, "percentage": 55.19, "elapsed_time": "1 day, 22:28:56", "remaining_time": "1 day, 13:44:36", "throughput": 626.06, "total_tokens": 104762112} {"current_steps": 501, "total_steps": 906, "loss": 0.2653566002845764, "lr": 2.0943651025164932e-05, "epoch": 1.6608551266085514, "percentage": 55.3, "elapsed_time": "1 day, 22:34:03", "remaining_time": "1 day, 13:38:40", "throughput": 626.16, "total_tokens": 104971248} {"current_steps": 502, "total_steps": 906, "loss": 0.26822784543037415, "lr": 2.085813575103657e-05, "epoch": 1.66417600664176, "percentage": 55.41, "elapsed_time": "1 day, 22:39:07", "remaining_time": "1 day, 13:32:40", "throughput": 626.26, "total_tokens": 105178376} {"current_steps": 503, "total_steps": 906, "loss": 0.2750917077064514, "lr": 2.0772670277989864e-05, "epoch": 1.6674968866749689, "percentage": 55.52, "elapsed_time": "1 day, 22:44:06", "remaining_time": "1 day, 13:26:37", "throughput": 626.36, "total_tokens": 105382384} {"current_steps": 504, "total_steps": 906, "loss": 0.2742467522621155, "lr": 2.0687255633647348e-05, "epoch": 1.6708177667081778, "percentage": 55.63, "elapsed_time": "1 day, 22:49:33", "remaining_time": "1 day, 13:20:57", "throughput": 626.4, "total_tokens": 105594960} {"current_steps": 505, "total_steps": 906, "loss": 0.26418954133987427, "lr": 2.060189284502037e-05, "epoch": 1.6741386467413863, "percentage": 55.74, "elapsed_time": "1 day, 22:55:04", "remaining_time": "1 day, 13:15:19", "throughput": 626.41, "total_tokens": 105803760} {"current_steps": 506, "total_steps": 906, "loss": 0.27535632252693176, "lr": 2.0516582938496812e-05, "epoch": 1.6774595267745953, "percentage": 55.85, "elapsed_time": "1 day, 23:00:02", "remaining_time": "1 day, 13:09:16", "throughput": 626.55, "total_tokens": 106013416} {"current_steps": 507, "total_steps": 906, "loss": 0.2713829278945923, "lr": 2.0431326939828686e-05, "epoch": 1.680780406807804, "percentage": 55.96, "elapsed_time": "1 day, 23:05:39", "remaining_time": "1 day, 13:03:44", "throughput": 626.56, "total_tokens": 106226328} {"current_steps": 508, "total_steps": 906, "loss": 0.2774660587310791, "lr": 2.034612587411984e-05, "epoch": 1.6841012868410128, "percentage": 56.07, "elapsed_time": "1 day, 23:10:42", "remaining_time": "1 day, 12:57:45", "throughput": 626.68, "total_tokens": 106435936} {"current_steps": 509, "total_steps": 906, "loss": 0.27122774720191956, "lr": 2.0260980765813604e-05, "epoch": 1.6874221668742218, "percentage": 56.18, "elapsed_time": "1 day, 23:16:04", "remaining_time": "1 day, 12:52:01", "throughput": 626.7, "total_tokens": 106641640} {"current_steps": 510, "total_steps": 906, "loss": 0.26995688676834106, "lr": 2.0175892638680494e-05, "epoch": 1.6907430469074305, "percentage": 56.29, "elapsed_time": "1 day, 23:21:28", "remaining_time": "1 day, 12:46:19", "throughput": 626.74, "total_tokens": 106852216} {"current_steps": 511, "total_steps": 906, "loss": 0.2680545449256897, "lr": 2.0090862515805898e-05, "epoch": 1.6940639269406392, "percentage": 56.4, "elapsed_time": "1 day, 23:26:40", "remaining_time": "1 day, 12:40:27", "throughput": 626.77, "total_tokens": 107053248} {"current_steps": 512, "total_steps": 906, "loss": 0.26882126927375793, "lr": 2.0005891419577757e-05, "epoch": 1.6973848069738482, "percentage": 56.51, "elapsed_time": "1 day, 23:32:19", "remaining_time": "1 day, 12:34:56", "throughput": 626.76, "total_tokens": 107262992} {"current_steps": 513, "total_steps": 906, "loss": 0.27311110496520996, "lr": 1.99209803716743e-05, "epoch": 1.7007056870070567, "percentage": 56.62, "elapsed_time": "1 day, 23:38:12", "remaining_time": "1 day, 12:29:37", "throughput": 626.73, "total_tokens": 107478712} {"current_steps": 514, "total_steps": 906, "loss": 0.2756790518760681, "lr": 1.9836130393051734e-05, "epoch": 1.7040265670402657, "percentage": 56.73, "elapsed_time": "1 day, 23:43:45", "remaining_time": "1 day, 12:24:01", "throughput": 626.75, "total_tokens": 107691144} {"current_steps": 515, "total_steps": 906, "loss": 0.27489352226257324, "lr": 1.975134250393198e-05, "epoch": 1.7073474470734746, "percentage": 56.84, "elapsed_time": "1 day, 23:48:47", "remaining_time": "1 day, 12:18:02", "throughput": 626.87, "total_tokens": 107900672} {"current_steps": 516, "total_steps": 906, "loss": 0.2614770531654358, "lr": 1.966661772379041e-05, "epoch": 1.7106683271066832, "percentage": 56.95, "elapsed_time": "1 day, 23:53:59", "remaining_time": "1 day, 12:12:12", "throughput": 626.9, "total_tokens": 108103232} {"current_steps": 517, "total_steps": 906, "loss": 0.2652609050273895, "lr": 1.9581957071343592e-05, "epoch": 1.7139892071398921, "percentage": 57.06, "elapsed_time": "1 day, 23:58:51", "remaining_time": "1 day, 12:06:06", "throughput": 627.11, "total_tokens": 108321080} {"current_steps": 518, "total_steps": 906, "loss": 0.2724020481109619, "lr": 1.9497361564537008e-05, "epoch": 1.7173100871731009, "percentage": 57.17, "elapsed_time": "2 days, 0:03:49", "remaining_time": "1 day, 12:00:05", "throughput": 627.27, "total_tokens": 108536112} {"current_steps": 519, "total_steps": 906, "loss": 0.2700433135032654, "lr": 1.9412832220532867e-05, "epoch": 1.7206309672063096, "percentage": 57.28, "elapsed_time": "2 days, 0:09:14", "remaining_time": "1 day, 11:54:24", "throughput": 627.32, "total_tokens": 108748640} {"current_steps": 520, "total_steps": 906, "loss": 0.27248144149780273, "lr": 1.9328370055697835e-05, "epoch": 1.7239518472395186, "percentage": 57.4, "elapsed_time": "2 days, 0:15:11", "remaining_time": "1 day, 11:49:07", "throughput": 627.3, "total_tokens": 108969864} {"current_steps": 521, "total_steps": 906, "loss": 0.28080034255981445, "lr": 1.9243976085590824e-05, "epoch": 1.7272727272727273, "percentage": 57.51, "elapsed_time": "2 days, 0:20:29", "remaining_time": "1 day, 11:43:21", "throughput": 627.36, "total_tokens": 109179664} {"current_steps": 522, "total_steps": 906, "loss": 0.2854807674884796, "lr": 1.915965132495079e-05, "epoch": 1.730593607305936, "percentage": 57.62, "elapsed_time": "2 days, 0:25:52", "remaining_time": "1 day, 11:37:39", "throughput": 627.42, "total_tokens": 109392960} {"current_steps": 523, "total_steps": 906, "loss": 0.27152860164642334, "lr": 1.9075396787684533e-05, "epoch": 1.733914487339145, "percentage": 57.73, "elapsed_time": "2 days, 0:31:11", "remaining_time": "1 day, 11:31:54", "throughput": 627.47, "total_tokens": 109601552} {"current_steps": 524, "total_steps": 906, "loss": 0.27585625648498535, "lr": 1.899121348685447e-05, "epoch": 1.7372353673723535, "percentage": 57.84, "elapsed_time": "2 days, 0:36:18", "remaining_time": "1 day, 11:26:00", "throughput": 627.55, "total_tokens": 109808384} {"current_steps": 525, "total_steps": 906, "loss": 0.26380085945129395, "lr": 1.8907102434666523e-05, "epoch": 1.7405562474055625, "percentage": 57.95, "elapsed_time": "2 days, 0:41:15", "remaining_time": "1 day, 11:20:00", "throughput": 627.64, "total_tokens": 110010928} {"current_steps": 526, "total_steps": 906, "loss": 0.2714405953884125, "lr": 1.8823064642457876e-05, "epoch": 1.7438771274387714, "percentage": 58.06, "elapsed_time": "2 days, 0:46:25", "remaining_time": "1 day, 11:14:09", "throughput": 627.73, "total_tokens": 110221304} {"current_steps": 527, "total_steps": 906, "loss": 0.271285742521286, "lr": 1.8739101120684866e-05, "epoch": 1.74719800747198, "percentage": 58.17, "elapsed_time": "2 days, 0:51:29", "remaining_time": "1 day, 11:08:13", "throughput": 627.83, "total_tokens": 110428072} {"current_steps": 528, "total_steps": 906, "loss": 0.2654801607131958, "lr": 1.8655212878910805e-05, "epoch": 1.750518887505189, "percentage": 58.28, "elapsed_time": "2 days, 0:56:45", "remaining_time": "1 day, 11:02:26", "throughput": 627.88, "total_tokens": 110635672} {"current_steps": 529, "total_steps": 906, "loss": 0.27764183282852173, "lr": 1.8571400925793855e-05, "epoch": 1.7538397675383977, "percentage": 58.39, "elapsed_time": "2 days, 1:01:28", "remaining_time": "1 day, 10:56:17", "throughput": 628.02, "total_tokens": 110838664} {"current_steps": 530, "total_steps": 906, "loss": 0.2751466929912567, "lr": 1.84876662690749e-05, "epoch": 1.7571606475716064, "percentage": 58.5, "elapsed_time": "2 days, 1:06:44", "remaining_time": "1 day, 10:50:31", "throughput": 628.1, "total_tokens": 111051304} {"current_steps": 531, "total_steps": 906, "loss": 0.26104727387428284, "lr": 1.840400991556541e-05, "epoch": 1.7604815276048154, "percentage": 58.61, "elapsed_time": "2 days, 1:11:54", "remaining_time": "1 day, 10:44:40", "throughput": 628.19, "total_tokens": 111262512} {"current_steps": 532, "total_steps": 906, "loss": 0.26812130212783813, "lr": 1.8320432871135377e-05, "epoch": 1.763802407638024, "percentage": 58.72, "elapsed_time": "2 days, 1:16:34", "remaining_time": "1 day, 10:38:29", "throughput": 628.41, "total_tokens": 111476128} {"current_steps": 533, "total_steps": 906, "loss": 0.26285719871520996, "lr": 1.8236936140701165e-05, "epoch": 1.7671232876712328, "percentage": 58.83, "elapsed_time": "2 days, 1:21:13", "remaining_time": "1 day, 10:32:18", "throughput": 628.58, "total_tokens": 111681600} {"current_steps": 534, "total_steps": 906, "loss": 0.27905604243278503, "lr": 1.8153520728213472e-05, "epoch": 1.7704441677044418, "percentage": 58.94, "elapsed_time": "2 days, 1:26:29", "remaining_time": "1 day, 10:26:32", "throughput": 628.63, "total_tokens": 111889344} {"current_steps": 535, "total_steps": 906, "loss": 0.2693879306316376, "lr": 1.807018763664524e-05, "epoch": 1.7737650477376503, "percentage": 59.05, "elapsed_time": "2 days, 1:31:39", "remaining_time": "1 day, 10:20:43", "throughput": 628.7, "total_tokens": 112096032} {"current_steps": 536, "total_steps": 906, "loss": 0.28193628787994385, "lr": 1.7986937867979598e-05, "epoch": 1.7770859277708593, "percentage": 59.16, "elapsed_time": "2 days, 1:36:56", "remaining_time": "1 day, 10:14:58", "throughput": 628.79, "total_tokens": 112311232} {"current_steps": 537, "total_steps": 906, "loss": 0.27152201533317566, "lr": 1.7903772423197806e-05, "epoch": 1.7804068078040682, "percentage": 59.27, "elapsed_time": "2 days, 1:42:13", "remaining_time": "1 day, 10:09:14", "throughput": 628.88, "total_tokens": 112527000} {"current_steps": 538, "total_steps": 906, "loss": 0.27006030082702637, "lr": 1.782069230226725e-05, "epoch": 1.7837276878372768, "percentage": 59.38, "elapsed_time": "2 days, 1:47:20", "remaining_time": "1 day, 10:03:23", "throughput": 629.0, "total_tokens": 112742016} {"current_steps": 539, "total_steps": 906, "loss": 0.269748330116272, "lr": 1.773769850412937e-05, "epoch": 1.7870485678704857, "percentage": 59.49, "elapsed_time": "2 days, 1:52:21", "remaining_time": "1 day, 9:57:28", "throughput": 629.09, "total_tokens": 112946816} {"current_steps": 540, "total_steps": 906, "loss": 0.2661256790161133, "lr": 1.7654792026687695e-05, "epoch": 1.7903694479036945, "percentage": 59.6, "elapsed_time": "2 days, 1:57:48", "remaining_time": "1 day, 9:51:50", "throughput": 629.09, "total_tokens": 113152976} {"current_steps": 541, "total_steps": 906, "loss": 0.2615446150302887, "lr": 1.7571973866795815e-05, "epoch": 1.7936903279369032, "percentage": 59.71, "elapsed_time": "2 days, 2:02:46", "remaining_time": "1 day, 9:45:53", "throughput": 629.13, "total_tokens": 113347744} {"current_steps": 542, "total_steps": 906, "loss": 0.268423855304718, "lr": 1.74892450202454e-05, "epoch": 1.7970112079701122, "percentage": 59.82, "elapsed_time": "2 days, 2:08:08", "remaining_time": "1 day, 9:40:13", "throughput": 629.16, "total_tokens": 113556952} {"current_steps": 543, "total_steps": 906, "loss": 0.27438366413116455, "lr": 1.7406606481754258e-05, "epoch": 1.800332088003321, "percentage": 59.93, "elapsed_time": "2 days, 2:13:24", "remaining_time": "1 day, 9:34:29", "throughput": 629.21, "total_tokens": 113763736} {"current_steps": 544, "total_steps": 906, "loss": 0.267435759305954, "lr": 1.7324059244954295e-05, "epoch": 1.8036529680365296, "percentage": 60.04, "elapsed_time": "2 days, 2:19:18", "remaining_time": "1 day, 9:29:10", "throughput": 629.19, "total_tokens": 113983520} {"current_steps": 545, "total_steps": 906, "loss": 0.26886412501335144, "lr": 1.724160430237967e-05, "epoch": 1.8069738480697386, "percentage": 60.15, "elapsed_time": "2 days, 2:24:37", "remaining_time": "1 day, 9:23:28", "throughput": 629.23, "total_tokens": 114190608} {"current_steps": 546, "total_steps": 906, "loss": 0.26775413751602173, "lr": 1.71592426454548e-05, "epoch": 1.8102947281029471, "percentage": 60.26, "elapsed_time": "2 days, 2:29:57", "remaining_time": "1 day, 9:17:46", "throughput": 629.28, "total_tokens": 114402576} {"current_steps": 547, "total_steps": 906, "loss": 0.2695067524909973, "lr": 1.7076975264482434e-05, "epoch": 1.813615608136156, "percentage": 60.38, "elapsed_time": "2 days, 2:35:44", "remaining_time": "1 day, 9:12:23", "throughput": 629.25, "total_tokens": 114615352} {"current_steps": 548, "total_steps": 906, "loss": 0.2697087526321411, "lr": 1.699480314863179e-05, "epoch": 1.816936488169365, "percentage": 60.49, "elapsed_time": "2 days, 2:41:14", "remaining_time": "1 day, 9:06:47", "throughput": 629.28, "total_tokens": 114828080} {"current_steps": 549, "total_steps": 906, "loss": 0.26648998260498047, "lr": 1.6912727285926605e-05, "epoch": 1.8202573682025736, "percentage": 60.6, "elapsed_time": "2 days, 2:46:19", "remaining_time": "1 day, 9:00:56", "throughput": 629.39, "total_tokens": 115039744} {"current_steps": 550, "total_steps": 906, "loss": 0.26458990573883057, "lr": 1.6830748663233306e-05, "epoch": 1.8235782482357825, "percentage": 60.71, "elapsed_time": "2 days, 2:51:18", "remaining_time": "1 day, 8:55:01", "throughput": 629.49, "total_tokens": 115246976} {"current_steps": 551, "total_steps": 906, "loss": 0.26564475893974304, "lr": 1.6748868266249114e-05, "epoch": 1.8268991282689913, "percentage": 60.82, "elapsed_time": "2 days, 2:56:32", "remaining_time": "1 day, 8:49:16", "throughput": 629.57, "total_tokens": 115457976} {"current_steps": 552, "total_steps": 906, "loss": 0.27272582054138184, "lr": 1.66670870794902e-05, "epoch": 1.8302200083022, "percentage": 60.93, "elapsed_time": "2 days, 3:01:33", "remaining_time": "1 day, 8:43:23", "throughput": 629.67, "total_tokens": 115665928} {"current_steps": 553, "total_steps": 906, "loss": 0.2620367407798767, "lr": 1.658540608627985e-05, "epoch": 1.833540888335409, "percentage": 61.04, "elapsed_time": "2 days, 3:06:38", "remaining_time": "1 day, 8:37:33", "throughput": 629.75, "total_tokens": 115873504} {"current_steps": 554, "total_steps": 906, "loss": 0.26693207025527954, "lr": 1.6503826268736633e-05, "epoch": 1.8368617683686177, "percentage": 61.15, "elapsed_time": "2 days, 3:11:45", "remaining_time": "1 day, 8:31:43", "throughput": 629.83, "total_tokens": 116081680} {"current_steps": 555, "total_steps": 906, "loss": 0.27306675910949707, "lr": 1.642234860776261e-05, "epoch": 1.8401826484018264, "percentage": 61.26, "elapsed_time": "2 days, 3:16:55", "remaining_time": "1 day, 8:25:57", "throughput": 629.92, "total_tokens": 116293208} {"current_steps": 556, "total_steps": 906, "loss": 0.2827261686325073, "lr": 1.6340974083031523e-05, "epoch": 1.8435035284350354, "percentage": 61.37, "elapsed_time": "2 days, 3:22:05", "remaining_time": "1 day, 8:20:09", "throughput": 630.02, "total_tokens": 116505576} {"current_steps": 557, "total_steps": 906, "loss": 0.2710084617137909, "lr": 1.6259703672977022e-05, "epoch": 1.8468244084682441, "percentage": 61.48, "elapsed_time": "2 days, 3:27:04", "remaining_time": "1 day, 8:14:16", "throughput": 630.14, "total_tokens": 116717448} {"current_steps": 558, "total_steps": 906, "loss": 0.27030086517333984, "lr": 1.6178538354780893e-05, "epoch": 1.8501452885014529, "percentage": 61.59, "elapsed_time": "2 days, 3:32:21", "remaining_time": "1 day, 8:08:33", "throughput": 630.16, "total_tokens": 116920664} {"current_steps": 559, "total_steps": 906, "loss": 0.2695692479610443, "lr": 1.6097479104361326e-05, "epoch": 1.8534661685346618, "percentage": 61.7, "elapsed_time": "2 days, 3:37:28", "remaining_time": "1 day, 8:02:45", "throughput": 630.3, "total_tokens": 117140760} {"current_steps": 560, "total_steps": 906, "loss": 0.27516889572143555, "lr": 1.601652689636116e-05, "epoch": 1.8567870485678704, "percentage": 61.81, "elapsed_time": "2 days, 3:42:28", "remaining_time": "1 day, 7:56:53", "throughput": 630.42, "total_tokens": 117351832} {"current_steps": 561, "total_steps": 906, "loss": 0.28343820571899414, "lr": 1.5935682704136183e-05, "epoch": 1.8601079286010793, "percentage": 61.92, "elapsed_time": "2 days, 3:47:42", "remaining_time": "1 day, 7:51:09", "throughput": 630.51, "total_tokens": 117566432} {"current_steps": 562, "total_steps": 906, "loss": 0.2708832621574402, "lr": 1.5854947499743413e-05, "epoch": 1.863428808634288, "percentage": 62.03, "elapsed_time": "2 days, 3:53:14", "remaining_time": "1 day, 7:45:36", "throughput": 630.53, "total_tokens": 117779696} {"current_steps": 563, "total_steps": 906, "loss": 0.2764652669429779, "lr": 1.5774322253929425e-05, "epoch": 1.8667496886674968, "percentage": 62.14, "elapsed_time": "2 days, 3:59:02", "remaining_time": "1 day, 7:40:13", "throughput": 630.46, "total_tokens": 117986056} {"current_steps": 564, "total_steps": 906, "loss": 0.26546573638916016, "lr": 1.569380793611865e-05, "epoch": 1.8700705687007058, "percentage": 62.25, "elapsed_time": "2 days, 4:04:34", "remaining_time": "1 day, 7:34:41", "throughput": 630.46, "total_tokens": 118194176} {"current_steps": 565, "total_steps": 906, "loss": 0.26806896924972534, "lr": 1.561340551440176e-05, "epoch": 1.8733914487339145, "percentage": 62.36, "elapsed_time": "2 days, 4:09:42", "remaining_time": "1 day, 7:28:54", "throughput": 630.54, "total_tokens": 118404512} {"current_steps": 566, "total_steps": 906, "loss": 0.26904433965682983, "lr": 1.5533115955523997e-05, "epoch": 1.8767123287671232, "percentage": 62.47, "elapsed_time": "2 days, 4:15:13", "remaining_time": "1 day, 7:23:20", "throughput": 630.56, "total_tokens": 118616144} {"current_steps": 567, "total_steps": 906, "loss": 0.27207452058792114, "lr": 1.5452940224873568e-05, "epoch": 1.8800332088003322, "percentage": 62.58, "elapsed_time": "2 days, 4:20:25", "remaining_time": "1 day, 7:17:36", "throughput": 630.65, "total_tokens": 118829696} {"current_steps": 568, "total_steps": 906, "loss": 0.27362871170043945, "lr": 1.537287928647002e-05, "epoch": 1.883354088833541, "percentage": 62.69, "elapsed_time": "2 days, 4:25:29", "remaining_time": "1 day, 7:11:47", "throughput": 630.74, "total_tokens": 119040032} {"current_steps": 569, "total_steps": 906, "loss": 0.26967093348503113, "lr": 1.529293410295266e-05, "epoch": 1.8866749688667497, "percentage": 62.8, "elapsed_time": "2 days, 4:30:48", "remaining_time": "1 day, 7:06:07", "throughput": 630.75, "total_tokens": 119241752} {"current_steps": 570, "total_steps": 906, "loss": 0.2625196576118469, "lr": 1.521310563556898e-05, "epoch": 1.8899958488999586, "percentage": 62.91, "elapsed_time": "2 days, 4:36:09", "remaining_time": "1 day, 7:00:28", "throughput": 630.76, "total_tokens": 119447200} {"current_steps": 571, "total_steps": 906, "loss": 0.2724230885505676, "lr": 1.5133394844163093e-05, "epoch": 1.8933167289331672, "percentage": 63.02, "elapsed_time": "2 days, 4:41:49", "remaining_time": "1 day, 6:55:00", "throughput": 630.76, "total_tokens": 119661648} {"current_steps": 572, "total_steps": 906, "loss": 0.2689951956272125, "lr": 1.5053802687164195e-05, "epoch": 1.8966376089663761, "percentage": 63.13, "elapsed_time": "2 days, 4:46:45", "remaining_time": "1 day, 6:49:07", "throughput": 630.84, "total_tokens": 119862688} {"current_steps": 573, "total_steps": 906, "loss": 0.269534707069397, "lr": 1.4974330121575048e-05, "epoch": 1.8999584889995849, "percentage": 63.25, "elapsed_time": "2 days, 4:52:00", "remaining_time": "1 day, 6:43:24", "throughput": 630.92, "total_tokens": 120076592} {"current_steps": 574, "total_steps": 906, "loss": 0.2766106128692627, "lr": 1.489497810296046e-05, "epoch": 1.9032793690327936, "percentage": 63.36, "elapsed_time": "2 days, 4:57:00", "remaining_time": "1 day, 6:37:34", "throughput": 631.04, "total_tokens": 120289424} {"current_steps": 575, "total_steps": 906, "loss": 0.2619192600250244, "lr": 1.4815747585435801e-05, "epoch": 1.9066002490660026, "percentage": 63.47, "elapsed_time": "2 days, 5:02:22", "remaining_time": "1 day, 6:31:56", "throughput": 631.05, "total_tokens": 120493336} {"current_steps": 576, "total_steps": 906, "loss": 0.26499634981155396, "lr": 1.4736639521655548e-05, "epoch": 1.9099211290992113, "percentage": 63.58, "elapsed_time": "2 days, 5:08:00", "remaining_time": "1 day, 6:26:27", "throughput": 631.02, "total_tokens": 120701960} {"current_steps": 577, "total_steps": 906, "loss": 0.274825781583786, "lr": 1.4657654862801798e-05, "epoch": 1.91324200913242, "percentage": 63.69, "elapsed_time": "2 days, 5:13:15", "remaining_time": "1 day, 6:20:45", "throughput": 631.08, "total_tokens": 120911368} {"current_steps": 578, "total_steps": 906, "loss": 0.2685317397117615, "lr": 1.457879455857285e-05, "epoch": 1.916562889165629, "percentage": 63.8, "elapsed_time": "2 days, 5:18:34", "remaining_time": "1 day, 6:15:06", "throughput": 631.1, "total_tokens": 121117264} {"current_steps": 579, "total_steps": 906, "loss": 0.26968395709991455, "lr": 1.4500059557171791e-05, "epoch": 1.9198837691988377, "percentage": 63.91, "elapsed_time": "2 days, 5:23:59", "remaining_time": "1 day, 6:09:30", "throughput": 631.11, "total_tokens": 121323664} {"current_steps": 580, "total_steps": 906, "loss": 0.2712090015411377, "lr": 1.4421450805295084e-05, "epoch": 1.9232046492320465, "percentage": 64.02, "elapsed_time": "2 days, 5:29:27", "remaining_time": "1 day, 6:03:56", "throughput": 631.11, "total_tokens": 121530784} {"current_steps": 581, "total_steps": 906, "loss": 0.26714205741882324, "lr": 1.4342969248121185e-05, "epoch": 1.9265255292652554, "percentage": 64.13, "elapsed_time": "2 days, 5:34:35", "remaining_time": "1 day, 5:58:10", "throughput": 631.18, "total_tokens": 121738640} {"current_steps": 582, "total_steps": 906, "loss": 0.280328631401062, "lr": 1.4264615829299188e-05, "epoch": 1.929846409298464, "percentage": 64.24, "elapsed_time": "2 days, 5:40:17", "remaining_time": "1 day, 5:52:44", "throughput": 631.17, "total_tokens": 121953480} {"current_steps": 583, "total_steps": 906, "loss": 0.26496070623397827, "lr": 1.4186391490937481e-05, "epoch": 1.933167289331673, "percentage": 64.35, "elapsed_time": "2 days, 5:45:54", "remaining_time": "1 day, 5:47:15", "throughput": 631.15, "total_tokens": 122162464} {"current_steps": 584, "total_steps": 906, "loss": 0.2688587009906769, "lr": 1.4108297173592377e-05, "epoch": 1.9364881693648817, "percentage": 64.46, "elapsed_time": "2 days, 5:51:29", "remaining_time": "1 day, 5:41:44", "throughput": 631.14, "total_tokens": 122371184} {"current_steps": 585, "total_steps": 906, "loss": 0.2745931148529053, "lr": 1.403033381625688e-05, "epoch": 1.9398090493980904, "percentage": 64.57, "elapsed_time": "2 days, 5:57:47", "remaining_time": "1 day, 5:36:38", "throughput": 631.0, "total_tokens": 122583280} {"current_steps": 586, "total_steps": 906, "loss": 0.26626116037368774, "lr": 1.3952502356349323e-05, "epoch": 1.9431299294312994, "percentage": 64.68, "elapsed_time": "2 days, 6:03:22", "remaining_time": "1 day, 5:31:07", "throughput": 631.0, "total_tokens": 122794264} {"current_steps": 587, "total_steps": 906, "loss": 0.27492424845695496, "lr": 1.3874803729702141e-05, "epoch": 1.946450809464508, "percentage": 64.79, "elapsed_time": "2 days, 6:09:34", "remaining_time": "1 day, 5:25:57", "throughput": 630.9, "total_tokens": 123009488} {"current_steps": 588, "total_steps": 906, "loss": 0.26660919189453125, "lr": 1.37972388705506e-05, "epoch": 1.9497716894977168, "percentage": 64.9, "elapsed_time": "2 days, 6:15:22", "remaining_time": "1 day, 5:20:33", "throughput": 630.85, "total_tokens": 123220168} {"current_steps": 589, "total_steps": 906, "loss": 0.27515602111816406, "lr": 1.3719808711521573e-05, "epoch": 1.9530925695309258, "percentage": 65.01, "elapsed_time": "2 days, 6:21:06", "remaining_time": "1 day, 5:15:07", "throughput": 630.82, "total_tokens": 123430568} {"current_steps": 590, "total_steps": 906, "loss": 0.2688959240913391, "lr": 1.3642514183622313e-05, "epoch": 1.9564134495641345, "percentage": 65.12, "elapsed_time": "2 days, 6:26:20", "remaining_time": "1 day, 5:09:26", "throughput": 630.85, "total_tokens": 123634144} {"current_steps": 591, "total_steps": 906, "loss": 0.2695107161998749, "lr": 1.3565356216229268e-05, "epoch": 1.9597343295973433, "percentage": 65.23, "elapsed_time": "2 days, 6:31:32", "remaining_time": "1 day, 5:03:43", "throughput": 630.91, "total_tokens": 123843456} {"current_steps": 592, "total_steps": 906, "loss": 0.2678720951080322, "lr": 1.3488335737076912e-05, "epoch": 1.9630552096305522, "percentage": 65.34, "elapsed_time": "2 days, 6:36:52", "remaining_time": "1 day, 4:58:04", "throughput": 630.96, "total_tokens": 124054272} {"current_steps": 593, "total_steps": 906, "loss": 0.2621110677719116, "lr": 1.341145367224657e-05, "epoch": 1.9663760896637608, "percentage": 65.45, "elapsed_time": "2 days, 6:42:04", "remaining_time": "1 day, 4:52:21", "throughput": 631.02, "total_tokens": 124262952} {"current_steps": 594, "total_steps": 906, "loss": 0.2641463875770569, "lr": 1.3334710946155326e-05, "epoch": 1.9696969696969697, "percentage": 65.56, "elapsed_time": "2 days, 6:47:23", "remaining_time": "1 day, 4:46:42", "throughput": 631.07, "total_tokens": 124473792} {"current_steps": 595, "total_steps": 906, "loss": 0.26903510093688965, "lr": 1.3258108481544849e-05, "epoch": 1.9730178497301785, "percentage": 65.67, "elapsed_time": "2 days, 6:52:51", "remaining_time": "1 day, 4:41:08", "throughput": 631.07, "total_tokens": 124680848} {"current_steps": 596, "total_steps": 906, "loss": 0.2604109048843384, "lr": 1.3181647199470331e-05, "epoch": 1.9763387297633872, "percentage": 65.78, "elapsed_time": "2 days, 6:58:10", "remaining_time": "1 day, 4:35:29", "throughput": 631.09, "total_tokens": 124886640} {"current_steps": 597, "total_steps": 906, "loss": 0.270403116941452, "lr": 1.310532801928942e-05, "epoch": 1.9796596097965962, "percentage": 65.89, "elapsed_time": "2 days, 7:03:46", "remaining_time": "1 day, 4:29:59", "throughput": 631.05, "total_tokens": 125091376} {"current_steps": 598, "total_steps": 906, "loss": 0.264536589384079, "lr": 1.3029151858651146e-05, "epoch": 1.982980489829805, "percentage": 66.0, "elapsed_time": "2 days, 7:09:28", "remaining_time": "1 day, 4:24:32", "throughput": 631.03, "total_tokens": 125303336} {"current_steps": 599, "total_steps": 906, "loss": 0.2670980393886566, "lr": 1.2953119633484903e-05, "epoch": 1.9863013698630136, "percentage": 66.11, "elapsed_time": "2 days, 7:14:52", "remaining_time": "1 day, 4:18:56", "throughput": 631.09, "total_tokens": 125519280} {"current_steps": 600, "total_steps": 906, "loss": 0.2673285901546478, "lr": 1.2877232257989422e-05, "epoch": 1.9896222498962226, "percentage": 66.23, "elapsed_time": "2 days, 7:19:44", "remaining_time": "1 day, 4:13:03", "throughput": 631.23, "total_tokens": 125730432} {"current_steps": 601, "total_steps": 906, "loss": 0.26510292291641235, "lr": 1.2801490644621789e-05, "epoch": 1.9929431299294313, "percentage": 66.34, "elapsed_time": "2 days, 7:24:51", "remaining_time": "1 day, 4:07:19", "throughput": 631.31, "total_tokens": 125941760} {"current_steps": 602, "total_steps": 906, "loss": 0.27245032787323, "lr": 1.2725895704086486e-05, "epoch": 1.99626400996264, "percentage": 66.45, "elapsed_time": "2 days, 7:30:01", "remaining_time": "1 day, 4:01:36", "throughput": 631.39, "total_tokens": 126151928} {"current_steps": 603, "total_steps": 906, "loss": 0.2708059549331665, "lr": 1.2650448345324384e-05, "epoch": 1.999584889995849, "percentage": 66.56, "elapsed_time": "2 days, 7:35:46", "remaining_time": "1 day, 3:56:11", "throughput": 631.35, "total_tokens": 126362392} {"current_steps": 604, "total_steps": 906, "loss": 0.2280811071395874, "lr": 1.257514947550189e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2 days, 7:36:37", "remaining_time": "1 day, 3:48:18", "throughput": 631.32, "total_tokens": 126389368} {"current_steps": 605, "total_steps": 906, "loss": 0.14720846712589264, "lr": 1.2500000000000006e-05, "epoch": 2.003320880033209, "percentage": 66.78, "elapsed_time": "2 days, 7:41:46", "remaining_time": "1 day, 3:42:35", "throughput": 631.41, "total_tokens": 126602256} {"current_steps": 606, "total_steps": 906, "loss": 0.146211177110672, "lr": 1.2425000822403423e-05, "epoch": 2.0066417600664175, "percentage": 66.89, "elapsed_time": "2 days, 7:47:05", "remaining_time": "1 day, 3:36:58", "throughput": 631.49, "total_tokens": 126820280} {"current_steps": 607, "total_steps": 906, "loss": 0.1337592899799347, "lr": 1.235015284448969e-05, "epoch": 2.0099626400996264, "percentage": 67.0, "elapsed_time": "2 days, 7:52:42", "remaining_time": "1 day, 3:31:29", "throughput": 631.49, "total_tokens": 127031320} {"current_steps": 608, "total_steps": 906, "loss": 0.14277178049087524, "lr": 1.2275456966218346e-05, "epoch": 2.0132835201328354, "percentage": 67.11, "elapsed_time": "2 days, 7:58:02", "remaining_time": "1 day, 3:25:53", "throughput": 631.52, "total_tokens": 127240280} {"current_steps": 609, "total_steps": 906, "loss": 0.13723507523536682, "lr": 1.2200914085720119e-05, "epoch": 2.016604400166044, "percentage": 67.22, "elapsed_time": "2 days, 8:03:18", "remaining_time": "1 day, 3:20:14", "throughput": 631.58, "total_tokens": 127451832} {"current_steps": 610, "total_steps": 906, "loss": 0.13196174800395966, "lr": 1.212652509928611e-05, "epoch": 2.019925280199253, "percentage": 67.33, "elapsed_time": "2 days, 8:08:47", "remaining_time": "1 day, 3:14:41", "throughput": 631.57, "total_tokens": 127657568} {"current_steps": 611, "total_steps": 906, "loss": 0.13456305861473083, "lr": 1.2052290901357025e-05, "epoch": 2.0232461602324614, "percentage": 67.44, "elapsed_time": "2 days, 8:14:34", "remaining_time": "1 day, 3:09:17", "throughput": 631.52, "total_tokens": 127867344} {"current_steps": 612, "total_steps": 906, "loss": 0.1359504908323288, "lr": 1.1978212384512422e-05, "epoch": 2.0265670402656704, "percentage": 67.55, "elapsed_time": "2 days, 8:20:18", "remaining_time": "1 day, 3:03:52", "throughput": 631.5, "total_tokens": 128079744} {"current_steps": 613, "total_steps": 906, "loss": 0.13352707028388977, "lr": 1.1904290439459973e-05, "epoch": 2.0298879202988793, "percentage": 67.66, "elapsed_time": "2 days, 8:25:57", "remaining_time": "1 day, 2:58:24", "throughput": 631.48, "total_tokens": 128290560} {"current_steps": 614, "total_steps": 906, "loss": 0.13147719204425812, "lr": 1.183052595502476e-05, "epoch": 2.033208800332088, "percentage": 67.77, "elapsed_time": "2 days, 8:30:54", "remaining_time": "1 day, 2:52:36", "throughput": 631.6, "total_tokens": 128500784} {"current_steps": 615, "total_steps": 906, "loss": 0.13384553790092468, "lr": 1.175691981813858e-05, "epoch": 2.036529680365297, "percentage": 67.88, "elapsed_time": "2 days, 8:36:21", "remaining_time": "1 day, 2:47:03", "throughput": 631.64, "total_tokens": 128715488} {"current_steps": 616, "total_steps": 906, "loss": 0.13982361555099487, "lr": 1.1683472913829285e-05, "epoch": 2.0398505603985058, "percentage": 67.99, "elapsed_time": "2 days, 8:41:55", "remaining_time": "1 day, 2:41:33", "throughput": 631.68, "total_tokens": 128934936} {"current_steps": 617, "total_steps": 906, "loss": 0.13187921047210693, "lr": 1.1610186125210151e-05, "epoch": 2.0431714404317143, "percentage": 68.1, "elapsed_time": "2 days, 8:47:12", "remaining_time": "1 day, 2:35:55", "throughput": 631.72, "total_tokens": 129143952} {"current_steps": 618, "total_steps": 906, "loss": 0.12840893864631653, "lr": 1.1537060333469244e-05, "epoch": 2.0464923204649232, "percentage": 68.21, "elapsed_time": "2 days, 8:52:23", "remaining_time": "1 day, 2:30:14", "throughput": 631.8, "total_tokens": 129356664} {"current_steps": 619, "total_steps": 906, "loss": 0.1280813217163086, "lr": 1.1464096417858822e-05, "epoch": 2.049813200498132, "percentage": 68.32, "elapsed_time": "2 days, 8:57:33", "remaining_time": "1 day, 2:24:33", "throughput": 631.88, "total_tokens": 129569792} {"current_steps": 620, "total_steps": 906, "loss": 0.1295657753944397, "lr": 1.1391295255684774e-05, "epoch": 2.0531340805313407, "percentage": 68.43, "elapsed_time": "2 days, 9:02:26", "remaining_time": "1 day, 2:18:44", "throughput": 632.0, "total_tokens": 129779096} {"current_steps": 621, "total_steps": 906, "loss": 0.12441350519657135, "lr": 1.1318657722296097e-05, "epoch": 2.0564549605645497, "percentage": 68.54, "elapsed_time": "2 days, 9:07:15", "remaining_time": "1 day, 2:12:53", "throughput": 632.12, "total_tokens": 129986448} {"current_steps": 622, "total_steps": 906, "loss": 0.12921908497810364, "lr": 1.1246184691074316e-05, "epoch": 2.059775840597758, "percentage": 68.65, "elapsed_time": "2 days, 9:12:11", "remaining_time": "1 day, 2:07:06", "throughput": 632.19, "total_tokens": 130188480} {"current_steps": 623, "total_steps": 906, "loss": 0.1297408789396286, "lr": 1.1173877033422994e-05, "epoch": 2.063096720630967, "percentage": 68.76, "elapsed_time": "2 days, 9:17:21", "remaining_time": "1 day, 2:01:25", "throughput": 632.3, "total_tokens": 130405896} {"current_steps": 624, "total_steps": 906, "loss": 0.12841525673866272, "lr": 1.1101735618757304e-05, "epoch": 2.066417600664176, "percentage": 68.87, "elapsed_time": "2 days, 9:22:45", "remaining_time": "1 day, 1:55:51", "throughput": 632.29, "total_tokens": 130609104} {"current_steps": 625, "total_steps": 906, "loss": 0.13575738668441772, "lr": 1.102976131449352e-05, "epoch": 2.0697384806973846, "percentage": 68.98, "elapsed_time": "2 days, 9:27:54", "remaining_time": "1 day, 1:50:10", "throughput": 632.37, "total_tokens": 130821816} {"current_steps": 626, "total_steps": 906, "loss": 0.13225172460079193, "lr": 1.0957954986038621e-05, "epoch": 2.0730593607305936, "percentage": 69.09, "elapsed_time": "2 days, 9:33:15", "remaining_time": "1 day, 1:44:35", "throughput": 632.41, "total_tokens": 131031680} {"current_steps": 627, "total_steps": 906, "loss": 0.1296905130147934, "lr": 1.0886317496779863e-05, "epoch": 2.0763802407638026, "percentage": 69.21, "elapsed_time": "2 days, 9:38:16", "remaining_time": "1 day, 1:38:50", "throughput": 632.5, "total_tokens": 131242200} {"current_steps": 628, "total_steps": 906, "loss": 0.1264619529247284, "lr": 1.0814849708074415e-05, "epoch": 2.079701120797011, "percentage": 69.32, "elapsed_time": "2 days, 9:42:52", "remaining_time": "1 day, 1:32:55", "throughput": 632.67, "total_tokens": 131452008} {"current_steps": 629, "total_steps": 906, "loss": 0.12316682934761047, "lr": 1.0743552479238994e-05, "epoch": 2.08302200083022, "percentage": 69.43, "elapsed_time": "2 days, 9:47:48", "remaining_time": "1 day, 1:27:09", "throughput": 632.74, "total_tokens": 131653696} {"current_steps": 630, "total_steps": 906, "loss": 0.12878412008285522, "lr": 1.0672426667539526e-05, "epoch": 2.086342880863429, "percentage": 69.54, "elapsed_time": "2 days, 9:52:50", "remaining_time": "1 day, 1:21:25", "throughput": 632.83, "total_tokens": 131863576} {"current_steps": 631, "total_steps": 906, "loss": 0.12377721071243286, "lr": 1.0601473128180855e-05, "epoch": 2.0896637608966375, "percentage": 69.65, "elapsed_time": "2 days, 9:57:44", "remaining_time": "1 day, 1:15:39", "throughput": 632.93, "total_tokens": 132070736} {"current_steps": 632, "total_steps": 906, "loss": 0.13047188520431519, "lr": 1.053069271429645e-05, "epoch": 2.0929846409298465, "percentage": 69.76, "elapsed_time": "2 days, 10:02:30", "remaining_time": "1 day, 1:09:49", "throughput": 633.07, "total_tokens": 132279224} {"current_steps": 633, "total_steps": 906, "loss": 0.12644770741462708, "lr": 1.0460086276938144e-05, "epoch": 2.096305520963055, "percentage": 69.87, "elapsed_time": "2 days, 10:07:13", "remaining_time": "1 day, 1:03:58", "throughput": 633.2, "total_tokens": 132486664} {"current_steps": 634, "total_steps": 906, "loss": 0.12722255289554596, "lr": 1.038965466506591e-05, "epoch": 2.099626400996264, "percentage": 69.98, "elapsed_time": "2 days, 10:12:18", "remaining_time": "1 day, 0:58:16", "throughput": 633.27, "total_tokens": 132694584} {"current_steps": 635, "total_steps": 906, "loss": 0.12794266641139984, "lr": 1.0319398725537644e-05, "epoch": 2.102947281029473, "percentage": 70.09, "elapsed_time": "2 days, 10:16:48", "remaining_time": "1 day, 0:52:20", "throughput": 633.45, "total_tokens": 132902824} {"current_steps": 636, "total_steps": 906, "loss": 0.12236585468053818, "lr": 1.0249319303098992e-05, "epoch": 2.1062681610626814, "percentage": 70.2, "elapsed_time": "2 days, 10:21:58", "remaining_time": "1 day, 0:46:41", "throughput": 633.49, "total_tokens": 133107528} {"current_steps": 637, "total_steps": 906, "loss": 0.1218290850520134, "lr": 1.0179417240373183e-05, "epoch": 2.1095890410958904, "percentage": 70.31, "elapsed_time": "2 days, 10:27:08", "remaining_time": "1 day, 0:41:02", "throughput": 633.55, "total_tokens": 133317608} {"current_steps": 638, "total_steps": 906, "loss": 0.13139528036117554, "lr": 1.0109693377850906e-05, "epoch": 2.1129099211290994, "percentage": 70.42, "elapsed_time": "2 days, 10:32:40", "remaining_time": "1 day, 0:35:32", "throughput": 633.55, "total_tokens": 133527544} {"current_steps": 639, "total_steps": 906, "loss": 0.12472192198038101, "lr": 1.0040148553880205e-05, "epoch": 2.116230801162308, "percentage": 70.53, "elapsed_time": "2 days, 10:37:55", "remaining_time": "1 day, 0:29:55", "throughput": 633.6, "total_tokens": 133737328} {"current_steps": 640, "total_steps": 906, "loss": 0.11827680468559265, "lr": 9.970783604656383e-06, "epoch": 2.119551681195517, "percentage": 70.64, "elapsed_time": "2 days, 10:43:21", "remaining_time": "1 day, 0:24:23", "throughput": 633.59, "total_tokens": 133941736} {"current_steps": 641, "total_steps": 906, "loss": 0.1281852126121521, "lr": 9.90159936421197e-06, "epoch": 2.122872561228726, "percentage": 70.75, "elapsed_time": "2 days, 10:48:59", "remaining_time": "1 day, 0:18:56", "throughput": 633.57, "total_tokens": 134152784} {"current_steps": 642, "total_steps": 906, "loss": 0.13093870878219604, "lr": 9.832596664406674e-06, "epoch": 2.1261934412619343, "percentage": 70.86, "elapsed_time": "2 days, 10:54:34", "remaining_time": "1 day, 0:13:28", "throughput": 633.56, "total_tokens": 134363040} {"current_steps": 643, "total_steps": 906, "loss": 0.12560278177261353, "lr": 9.763776334917399e-06, "epoch": 2.1295143212951433, "percentage": 70.97, "elapsed_time": "2 days, 11:00:12", "remaining_time": "1 day, 0:08:01", "throughput": 633.53, "total_tokens": 134569288} {"current_steps": 644, "total_steps": 906, "loss": 0.11842095851898193, "lr": 9.695139203228254e-06, "epoch": 2.1328352013283522, "percentage": 71.08, "elapsed_time": "2 days, 11:05:35", "remaining_time": "1 day, 0:02:27", "throughput": 633.54, "total_tokens": 134775328} {"current_steps": 645, "total_steps": 906, "loss": 0.12078073620796204, "lr": 9.626686094620608e-06, "epoch": 2.1361560813615608, "percentage": 71.19, "elapsed_time": "2 days, 11:10:23", "remaining_time": "23:56:40", "throughput": 633.65, "total_tokens": 134981464} {"current_steps": 646, "total_steps": 906, "loss": 0.12525677680969238, "lr": 9.558417832163163e-06, "epoch": 2.1394769613947697, "percentage": 71.3, "elapsed_time": "2 days, 11:15:39", "remaining_time": "23:51:04", "throughput": 633.7, "total_tokens": 135192344} {"current_steps": 647, "total_steps": 906, "loss": 0.12024770677089691, "lr": 9.490335236702075e-06, "epoch": 2.1427978414279782, "percentage": 71.41, "elapsed_time": "2 days, 11:21:10", "remaining_time": "23:45:34", "throughput": 633.68, "total_tokens": 135399096} {"current_steps": 648, "total_steps": 906, "loss": 0.13157103955745697, "lr": 9.422439126851058e-06, "epoch": 2.146118721461187, "percentage": 71.52, "elapsed_time": "2 days, 11:26:26", "remaining_time": "23:39:58", "throughput": 633.75, "total_tokens": 135614416} {"current_steps": 649, "total_steps": 906, "loss": 0.12051853537559509, "lr": 9.354730318981562e-06, "epoch": 2.149439601494396, "percentage": 71.63, "elapsed_time": "2 days, 11:31:31", "remaining_time": "23:34:18", "throughput": 633.8, "total_tokens": 135817856} {"current_steps": 650, "total_steps": 906, "loss": 0.12102018296718597, "lr": 9.28720962721294e-06, "epoch": 2.1527604815276047, "percentage": 71.74, "elapsed_time": "2 days, 11:36:25", "remaining_time": "23:28:33", "throughput": 633.89, "total_tokens": 136023912} {"current_steps": 651, "total_steps": 906, "loss": 0.12422362715005875, "lr": 9.219877863402682e-06, "epoch": 2.1560813615608136, "percentage": 71.85, "elapsed_time": "2 days, 11:41:00", "remaining_time": "23:22:41", "throughput": 634.04, "total_tokens": 136229280} {"current_steps": 652, "total_steps": 906, "loss": 0.123842254281044, "lr": 9.152735837136631e-06, "epoch": 2.1594022415940226, "percentage": 71.96, "elapsed_time": "2 days, 11:46:07", "remaining_time": "23:17:03", "throughput": 634.11, "total_tokens": 136439960} {"current_steps": 653, "total_steps": 906, "loss": 0.13066406548023224, "lr": 9.085784355719257e-06, "epoch": 2.162723121627231, "percentage": 72.08, "elapsed_time": "2 days, 11:51:05", "remaining_time": "23:11:20", "throughput": 634.24, "total_tokens": 136655968} {"current_steps": 654, "total_steps": 906, "loss": 0.12675920128822327, "lr": 9.019024224163954e-06, "epoch": 2.16604400166044, "percentage": 72.19, "elapsed_time": "2 days, 11:56:08", "remaining_time": "23:05:40", "throughput": 634.33, "total_tokens": 136868616} {"current_steps": 655, "total_steps": 906, "loss": 0.11937602609395981, "lr": 8.95245624518336e-06, "epoch": 2.1693648816936486, "percentage": 72.3, "elapsed_time": "2 days, 12:01:03", "remaining_time": "22:59:56", "throughput": 634.44, "total_tokens": 137078416} {"current_steps": 656, "total_steps": 906, "loss": 0.13150331377983093, "lr": 8.886081219179695e-06, "epoch": 2.1726857617268576, "percentage": 72.41, "elapsed_time": "2 days, 12:05:51", "remaining_time": "22:54:11", "throughput": 634.55, "total_tokens": 137286352} {"current_steps": 657, "total_steps": 906, "loss": 0.11932653933763504, "lr": 8.819899944235152e-06, "epoch": 2.1760066417600665, "percentage": 72.52, "elapsed_time": "2 days, 12:10:57", "remaining_time": "22:48:32", "throughput": 634.58, "total_tokens": 137487016} {"current_steps": 658, "total_steps": 906, "loss": 0.13181953132152557, "lr": 8.753913216102286e-06, "epoch": 2.179327521793275, "percentage": 72.63, "elapsed_time": "2 days, 12:15:57", "remaining_time": "22:42:51", "throughput": 634.68, "total_tokens": 137697608} {"current_steps": 659, "total_steps": 906, "loss": 0.12009871006011963, "lr": 8.688121828194462e-06, "epoch": 2.182648401826484, "percentage": 72.74, "elapsed_time": "2 days, 12:21:40", "remaining_time": "22:37:26", "throughput": 634.63, "total_tokens": 137905256} {"current_steps": 660, "total_steps": 906, "loss": 0.12502983212471008, "lr": 8.622526571576303e-06, "epoch": 2.185969281859693, "percentage": 72.85, "elapsed_time": "2 days, 12:27:29", "remaining_time": "22:32:03", "throughput": 634.58, "total_tokens": 138115040} {"current_steps": 661, "total_steps": 906, "loss": 0.12703870236873627, "lr": 8.55712823495419e-06, "epoch": 2.1892901618929015, "percentage": 72.96, "elapsed_time": "2 days, 12:32:56", "remaining_time": "22:26:33", "throughput": 634.6, "total_tokens": 138329112} {"current_steps": 662, "total_steps": 906, "loss": 0.12845154106616974, "lr": 8.491927604666746e-06, "epoch": 2.1926110419261104, "percentage": 73.07, "elapsed_time": "2 days, 12:38:25", "remaining_time": "22:21:03", "throughput": 634.61, "total_tokens": 138539944} {"current_steps": 663, "total_steps": 906, "loss": 0.12254674732685089, "lr": 8.426925464675433e-06, "epoch": 2.1959319219593194, "percentage": 73.18, "elapsed_time": "2 days, 12:43:20", "remaining_time": "22:15:20", "throughput": 634.69, "total_tokens": 138743224} {"current_steps": 664, "total_steps": 906, "loss": 0.12825888395309448, "lr": 8.362122596555089e-06, "epoch": 2.199252801992528, "percentage": 73.29, "elapsed_time": "2 days, 12:48:41", "remaining_time": "22:09:47", "throughput": 634.72, "total_tokens": 138954016} {"current_steps": 665, "total_steps": 906, "loss": 0.12476789951324463, "lr": 8.297519779484541e-06, "epoch": 2.202573682025737, "percentage": 73.4, "elapsed_time": "2 days, 12:54:00", "remaining_time": "22:04:14", "throughput": 634.73, "total_tokens": 139159424} {"current_steps": 666, "total_steps": 906, "loss": 0.12099689245223999, "lr": 8.233117790237237e-06, "epoch": 2.205894562058946, "percentage": 73.51, "elapsed_time": "2 days, 12:59:41", "remaining_time": "21:58:48", "throughput": 634.69, "total_tokens": 139365496} {"current_steps": 667, "total_steps": 906, "loss": 0.1257515549659729, "lr": 8.168917403171891e-06, "epoch": 2.2092154420921544, "percentage": 73.62, "elapsed_time": "2 days, 13:05:44", "remaining_time": "21:53:30", "throughput": 634.61, "total_tokens": 139577896} {"current_steps": 668, "total_steps": 906, "loss": 0.13241630792617798, "lr": 8.10491939022322e-06, "epoch": 2.2125363221253633, "percentage": 73.73, "elapsed_time": "2 days, 13:11:59", "remaining_time": "21:48:17", "throughput": 634.5, "total_tokens": 139793112} {"current_steps": 669, "total_steps": 906, "loss": 0.12756380438804626, "lr": 8.041124520892598e-06, "epoch": 2.215857202158572, "percentage": 73.84, "elapsed_time": "2 days, 13:17:43", "remaining_time": "21:42:52", "throughput": 634.48, "total_tokens": 140007096} {"current_steps": 670, "total_steps": 906, "loss": 0.13113358616828918, "lr": 7.97753356223884e-06, "epoch": 2.219178082191781, "percentage": 73.95, "elapsed_time": "2 days, 13:23:46", "remaining_time": "21:37:34", "throughput": 634.4, "total_tokens": 140218888} {"current_steps": 671, "total_steps": 906, "loss": 0.12063190340995789, "lr": 7.91414727886898e-06, "epoch": 2.2224989622249898, "percentage": 74.06, "elapsed_time": "2 days, 13:29:30", "remaining_time": "21:32:09", "throughput": 634.36, "total_tokens": 140429592} {"current_steps": 672, "total_steps": 906, "loss": 0.13294678926467896, "lr": 7.850966432929066e-06, "epoch": 2.2258198422581983, "percentage": 74.17, "elapsed_time": "2 days, 13:35:04", "remaining_time": "21:26:40", "throughput": 634.4, "total_tokens": 140649288} {"current_steps": 673, "total_steps": 906, "loss": 0.11828938126564026, "lr": 7.787991784095e-06, "epoch": 2.2291407222914073, "percentage": 74.28, "elapsed_time": "2 days, 13:40:19", "remaining_time": "21:21:05", "throughput": 634.43, "total_tokens": 140856568} {"current_steps": 674, "total_steps": 906, "loss": 0.12606853246688843, "lr": 7.725224089563413e-06, "epoch": 2.232461602324616, "percentage": 74.39, "elapsed_time": "2 days, 13:45:27", "remaining_time": "21:15:28", "throughput": 634.5, "total_tokens": 141066592} {"current_steps": 675, "total_steps": 906, "loss": 0.12553736567497253, "lr": 7.662664104042538e-06, "epoch": 2.2357824823578247, "percentage": 74.5, "elapsed_time": "2 days, 13:50:41", "remaining_time": "21:09:52", "throughput": 634.54, "total_tokens": 141275784} {"current_steps": 676, "total_steps": 906, "loss": 0.12592512369155884, "lr": 7.60031257974316e-06, "epoch": 2.2391033623910337, "percentage": 74.61, "elapsed_time": "2 days, 13:55:55", "remaining_time": "21:04:17", "throughput": 634.58, "total_tokens": 141482088} {"current_steps": 677, "total_steps": 906, "loss": 0.12118929624557495, "lr": 7.538170266369563e-06, "epoch": 2.242424242424242, "percentage": 74.72, "elapsed_time": "2 days, 14:01:09", "remaining_time": "20:58:42", "throughput": 634.62, "total_tokens": 141691360} {"current_steps": 678, "total_steps": 906, "loss": 0.12104073166847229, "lr": 7.4762379111105036e-06, "epoch": 2.245745122457451, "percentage": 74.83, "elapsed_time": "2 days, 14:06:21", "remaining_time": "20:53:06", "throughput": 634.65, "total_tokens": 141895520} {"current_steps": 679, "total_steps": 906, "loss": 0.12766128778457642, "lr": 7.414516258630244e-06, "epoch": 2.24906600249066, "percentage": 74.94, "elapsed_time": "2 days, 14:11:36", "remaining_time": "20:47:31", "throughput": 634.69, "total_tokens": 142104912} {"current_steps": 680, "total_steps": 906, "loss": 0.12323226034641266, "lr": 7.353006051059594e-06, "epoch": 2.2523868825238686, "percentage": 75.06, "elapsed_time": "2 days, 14:17:05", "remaining_time": "20:42:02", "throughput": 634.68, "total_tokens": 142312352} {"current_steps": 681, "total_steps": 906, "loss": 0.12765762209892273, "lr": 7.291708027986988e-06, "epoch": 2.2557077625570776, "percentage": 75.17, "elapsed_time": "2 days, 14:22:40", "remaining_time": "20:36:33", "throughput": 634.69, "total_tokens": 142526896} {"current_steps": 682, "total_steps": 906, "loss": 0.13139531016349792, "lr": 7.230622926449565e-06, "epoch": 2.2590286425902866, "percentage": 75.28, "elapsed_time": "2 days, 14:27:46", "remaining_time": "20:30:56", "throughput": 634.76, "total_tokens": 142736840} {"current_steps": 683, "total_steps": 906, "loss": 0.13132360577583313, "lr": 7.169751480924361e-06, "epoch": 2.262349522623495, "percentage": 75.39, "elapsed_time": "2 days, 14:33:25", "remaining_time": "20:25:29", "throughput": 634.75, "total_tokens": 142948784} {"current_steps": 684, "total_steps": 906, "loss": 0.12250486016273499, "lr": 7.109094423319431e-06, "epoch": 2.265670402656704, "percentage": 75.5, "elapsed_time": "2 days, 14:38:56", "remaining_time": "20:20:00", "throughput": 634.75, "total_tokens": 143158976} {"current_steps": 685, "total_steps": 906, "loss": 0.12127131968736649, "lr": 7.048652482965079e-06, "epoch": 2.268991282689913, "percentage": 75.61, "elapsed_time": "2 days, 14:44:17", "remaining_time": "20:14:27", "throughput": 634.75, "total_tokens": 143363296} {"current_steps": 686, "total_steps": 906, "loss": 0.1265455186367035, "lr": 6.988426386605062e-06, "epoch": 2.2723121627231215, "percentage": 75.72, "elapsed_time": "2 days, 14:49:52", "remaining_time": "20:08:59", "throughput": 634.75, "total_tokens": 143574792} {"current_steps": 687, "total_steps": 906, "loss": 0.12172548472881317, "lr": 6.928416858387874e-06, "epoch": 2.2756330427563305, "percentage": 75.83, "elapsed_time": "2 days, 14:55:10", "remaining_time": "20:03:26", "throughput": 634.77, "total_tokens": 143781224} {"current_steps": 688, "total_steps": 906, "loss": 0.1293189823627472, "lr": 6.868624619858022e-06, "epoch": 2.2789539227895395, "percentage": 75.94, "elapsed_time": "2 days, 15:00:52", "remaining_time": "19:58:00", "throughput": 634.73, "total_tokens": 143989600} {"current_steps": 689, "total_steps": 906, "loss": 0.12729492783546448, "lr": 6.809050389947363e-06, "epoch": 2.282274802822748, "percentage": 76.05, "elapsed_time": "2 days, 15:06:03", "remaining_time": "19:52:24", "throughput": 634.79, "total_tokens": 144200256} {"current_steps": 690, "total_steps": 906, "loss": 0.12200905382633209, "lr": 6.749694884966454e-06, "epoch": 2.285595682855957, "percentage": 76.16, "elapsed_time": "2 days, 15:11:50", "remaining_time": "19:47:00", "throughput": 634.76, "total_tokens": 144413704} {"current_steps": 691, "total_steps": 906, "loss": 0.12561368942260742, "lr": 6.690558818595943e-06, "epoch": 2.2889165628891655, "percentage": 76.27, "elapsed_time": "2 days, 15:17:39", "remaining_time": "19:41:36", "throughput": 634.67, "total_tokens": 144616560} {"current_steps": 692, "total_steps": 906, "loss": 0.1299750804901123, "lr": 6.6316429018779825e-06, "epoch": 2.2922374429223744, "percentage": 76.38, "elapsed_time": "2 days, 15:22:52", "remaining_time": "19:36:01", "throughput": 634.72, "total_tokens": 144824744} {"current_steps": 693, "total_steps": 906, "loss": 0.12165538966655731, "lr": 6.5729478432076775e-06, "epoch": 2.2955583229555834, "percentage": 76.49, "elapsed_time": "2 days, 15:28:25", "remaining_time": "19:30:33", "throughput": 634.69, "total_tokens": 145030952} {"current_steps": 694, "total_steps": 906, "loss": 0.12155309319496155, "lr": 6.514474348324581e-06, "epoch": 2.298879202988792, "percentage": 76.6, "elapsed_time": "2 days, 15:34:05", "remaining_time": "19:25:06", "throughput": 634.67, "total_tokens": 145240848} {"current_steps": 695, "total_steps": 906, "loss": 0.12483226507902145, "lr": 6.456223120304192e-06, "epoch": 2.302200083022001, "percentage": 76.71, "elapsed_time": "2 days, 15:40:12", "remaining_time": "19:19:48", "throughput": 634.57, "total_tokens": 145450912} {"current_steps": 696, "total_steps": 906, "loss": 0.1289762258529663, "lr": 6.398194859549525e-06, "epoch": 2.30552096305521, "percentage": 76.82, "elapsed_time": "2 days, 15:45:37", "remaining_time": "19:14:17", "throughput": 634.6, "total_tokens": 145663512} {"current_steps": 697, "total_steps": 906, "loss": 0.12747865915298462, "lr": 6.340390263782655e-06, "epoch": 2.3088418430884183, "percentage": 76.93, "elapsed_time": "2 days, 15:51:03", "remaining_time": "19:08:46", "throughput": 634.63, "total_tokens": 145877688} {"current_steps": 698, "total_steps": 906, "loss": 0.12134255468845367, "lr": 6.2828100280363595e-06, "epoch": 2.3121627231216273, "percentage": 77.04, "elapsed_time": "2 days, 15:56:02", "remaining_time": "19:03:07", "throughput": 634.7, "total_tokens": 146083768} {"current_steps": 699, "total_steps": 906, "loss": 0.12224350869655609, "lr": 6.22545484464574e-06, "epoch": 2.315483603154836, "percentage": 77.15, "elapsed_time": "2 days, 16:01:02", "remaining_time": "18:57:28", "throughput": 634.79, "total_tokens": 146294792} {"current_steps": 700, "total_steps": 906, "loss": 0.12283925712108612, "lr": 6.168325403239913e-06, "epoch": 2.3188044831880448, "percentage": 77.26, "elapsed_time": "2 days, 16:06:27", "remaining_time": "18:51:57", "throughput": 634.79, "total_tokens": 146500808} {"current_steps": 701, "total_steps": 906, "loss": 0.12879249453544617, "lr": 6.111422390733715e-06, "epoch": 2.3221253632212537, "percentage": 77.37, "elapsed_time": "2 days, 16:12:06", "remaining_time": "18:46:30", "throughput": 634.79, "total_tokens": 146716448} {"current_steps": 702, "total_steps": 906, "loss": 0.12382742762565613, "lr": 6.054746491319419e-06, "epoch": 2.3254462432544623, "percentage": 77.48, "elapsed_time": "2 days, 16:17:38", "remaining_time": "18:41:01", "throughput": 634.78, "total_tokens": 146924192} {"current_steps": 703, "total_steps": 906, "loss": 0.12401469051837921, "lr": 5.998298386458545e-06, "epoch": 2.328767123287671, "percentage": 77.59, "elapsed_time": "2 days, 16:22:58", "remaining_time": "18:35:28", "throughput": 634.81, "total_tokens": 147135496} {"current_steps": 704, "total_steps": 906, "loss": 0.12756630778312683, "lr": 5.9420787548736535e-06, "epoch": 2.33208800332088, "percentage": 77.7, "elapsed_time": "2 days, 16:28:05", "remaining_time": "18:29:52", "throughput": 634.88, "total_tokens": 147347768} {"current_steps": 705, "total_steps": 906, "loss": 0.12014050781726837, "lr": 5.8860882725401665e-06, "epoch": 2.3354088833540887, "percentage": 77.81, "elapsed_time": "2 days, 16:33:10", "remaining_time": "18:24:15", "throughput": 634.94, "total_tokens": 147552896} {"current_steps": 706, "total_steps": 906, "loss": 0.11618681252002716, "lr": 5.8303276126782656e-06, "epoch": 2.3387297633872977, "percentage": 77.92, "elapsed_time": "2 days, 16:38:32", "remaining_time": "18:18:44", "throughput": 634.93, "total_tokens": 147755848} {"current_steps": 707, "total_steps": 906, "loss": 0.1188001036643982, "lr": 5.774797445744781e-06, "epoch": 2.3420506434205066, "percentage": 78.04, "elapsed_time": "2 days, 16:43:41", "remaining_time": "18:13:08", "throughput": 634.97, "total_tokens": 147960896} {"current_steps": 708, "total_steps": 906, "loss": 0.11904694885015488, "lr": 5.7194984394251335e-06, "epoch": 2.345371523453715, "percentage": 78.15, "elapsed_time": "2 days, 16:49:07", "remaining_time": "18:07:38", "throughput": 634.95, "total_tokens": 148164464} {"current_steps": 709, "total_steps": 906, "loss": 0.12943054735660553, "lr": 5.664431258625305e-06, "epoch": 2.348692403486924, "percentage": 78.26, "elapsed_time": "2 days, 16:54:33", "remaining_time": "18:02:07", "throughput": 635.0, "total_tokens": 148382640} {"current_steps": 710, "total_steps": 906, "loss": 0.12141716480255127, "lr": 5.609596565463854e-06, "epoch": 2.352013283520133, "percentage": 78.37, "elapsed_time": "2 days, 16:59:25", "remaining_time": "17:56:27", "throughput": 635.1, "total_tokens": 148590856} {"current_steps": 711, "total_steps": 906, "loss": 0.12018579244613647, "lr": 5.55499501926394e-06, "epoch": 2.3553341635533416, "percentage": 78.48, "elapsed_time": "2 days, 17:05:04", "remaining_time": "17:51:00", "throughput": 635.07, "total_tokens": 148799848} {"current_steps": 712, "total_steps": 906, "loss": 0.12448924034833908, "lr": 5.500627276545406e-06, "epoch": 2.3586550435865505, "percentage": 78.59, "elapsed_time": "2 days, 17:10:23", "remaining_time": "17:45:28", "throughput": 635.12, "total_tokens": 149013464} {"current_steps": 713, "total_steps": 906, "loss": 0.1262572705745697, "lr": 5.446493991016879e-06, "epoch": 2.361975923619759, "percentage": 78.7, "elapsed_time": "2 days, 17:15:37", "remaining_time": "17:39:54", "throughput": 635.16, "total_tokens": 149222856} {"current_steps": 714, "total_steps": 906, "loss": 0.12216039001941681, "lr": 5.392595813567911e-06, "epoch": 2.365296803652968, "percentage": 78.81, "elapsed_time": "2 days, 17:19:53", "remaining_time": "17:34:05", "throughput": 635.34, "total_tokens": 149428648} {"current_steps": 715, "total_steps": 906, "loss": 0.12278061360120773, "lr": 5.338933392261159e-06, "epoch": 2.368617683686177, "percentage": 78.92, "elapsed_time": "2 days, 17:24:30", "remaining_time": "17:28:21", "throughput": 635.5, "total_tokens": 149642104} {"current_steps": 716, "total_steps": 906, "loss": 0.12263549864292145, "lr": 5.28550737232458e-06, "epoch": 2.3719385637193855, "percentage": 79.03, "elapsed_time": "2 days, 17:28:57", "remaining_time": "17:22:36", "throughput": 635.67, "total_tokens": 149850928} {"current_steps": 717, "total_steps": 906, "loss": 0.1202726885676384, "lr": 5.23231839614369e-06, "epoch": 2.3752594437525945, "percentage": 79.14, "elapsed_time": "2 days, 17:33:52", "remaining_time": "17:16:57", "throughput": 635.77, "total_tokens": 150062656} {"current_steps": 718, "total_steps": 906, "loss": 0.12209299206733704, "lr": 5.179367103253821e-06, "epoch": 2.3785803237858034, "percentage": 79.25, "elapsed_time": "2 days, 17:38:22", "remaining_time": "17:11:13", "throughput": 635.93, "total_tokens": 150272216} {"current_steps": 719, "total_steps": 906, "loss": 0.1252414733171463, "lr": 5.126654130332451e-06, "epoch": 2.381901203819012, "percentage": 79.36, "elapsed_time": "2 days, 17:43:10", "remaining_time": "17:05:33", "throughput": 636.06, "total_tokens": 150486720} {"current_steps": 720, "total_steps": 906, "loss": 0.12755653262138367, "lr": 5.0741801111915235e-06, "epoch": 2.385222083852221, "percentage": 79.47, "elapsed_time": "2 days, 17:47:56", "remaining_time": "16:59:53", "throughput": 636.19, "total_tokens": 150698968} {"current_steps": 721, "total_steps": 906, "loss": 0.11924375593662262, "lr": 5.02194567676986e-06, "epoch": 2.3885429638854294, "percentage": 79.58, "elapsed_time": "2 days, 17:52:22", "remaining_time": "16:54:08", "throughput": 636.36, "total_tokens": 150907064} {"current_steps": 722, "total_steps": 906, "loss": 0.12659116089344025, "lr": 4.9699514551255435e-06, "epoch": 2.3918638439186384, "percentage": 79.69, "elapsed_time": "2 days, 17:56:43", "remaining_time": "16:48:21", "throughput": 636.55, "total_tokens": 151119776} {"current_steps": 723, "total_steps": 906, "loss": 0.11909331381320953, "lr": 4.918198071428382e-06, "epoch": 2.3951847239518473, "percentage": 79.8, "elapsed_time": "2 days, 18:01:18", "remaining_time": "16:42:39", "throughput": 636.71, "total_tokens": 151332480} {"current_steps": 724, "total_steps": 906, "loss": 0.12157981842756271, "lr": 4.866686147952387e-06, "epoch": 2.398505603985056, "percentage": 79.91, "elapsed_time": "2 days, 18:06:21", "remaining_time": "16:37:04", "throughput": 636.78, "total_tokens": 151542384} {"current_steps": 725, "total_steps": 906, "loss": 0.12464383989572525, "lr": 4.815416304068298e-06, "epoch": 2.401826484018265, "percentage": 80.02, "elapsed_time": "2 days, 18:10:58", "remaining_time": "16:31:22", "throughput": 636.94, "total_tokens": 151756640} {"current_steps": 726, "total_steps": 906, "loss": 0.1196499764919281, "lr": 4.764389156236126e-06, "epoch": 2.405147364051474, "percentage": 80.13, "elapsed_time": "2 days, 18:15:39", "remaining_time": "16:25:42", "throughput": 637.07, "total_tokens": 151966616} {"current_steps": 727, "total_steps": 906, "loss": 0.12495848536491394, "lr": 4.713605317997741e-06, "epoch": 2.4084682440846823, "percentage": 80.24, "elapsed_time": "2 days, 18:20:16", "remaining_time": "16:20:00", "throughput": 637.2, "total_tokens": 152174208} {"current_steps": 728, "total_steps": 906, "loss": 0.12677881121635437, "lr": 4.663065399969507e-06, "epoch": 2.4117891241178913, "percentage": 80.35, "elapsed_time": "2 days, 18:25:25", "remaining_time": "16:14:27", "throughput": 637.27, "total_tokens": 152387080} {"current_steps": 729, "total_steps": 906, "loss": 0.12012401223182678, "lr": 4.61277000983493e-06, "epoch": 2.4151100041511, "percentage": 80.46, "elapsed_time": "2 days, 18:30:42", "remaining_time": "16:08:56", "throughput": 637.29, "total_tokens": 152594736} {"current_steps": 730, "total_steps": 906, "loss": 0.1194409653544426, "lr": 4.5627197523373495e-06, "epoch": 2.4184308841843087, "percentage": 80.57, "elapsed_time": "2 days, 18:35:25", "remaining_time": "16:03:16", "throughput": 637.4, "total_tokens": 152799848} {"current_steps": 731, "total_steps": 906, "loss": 0.12269122153520584, "lr": 4.51291522927268e-06, "epoch": 2.4217517642175177, "percentage": 80.68, "elapsed_time": "2 days, 18:39:53", "remaining_time": "15:57:34", "throughput": 637.56, "total_tokens": 153009880} {"current_steps": 732, "total_steps": 906, "loss": 0.12360180914402008, "lr": 4.463357039482155e-06, "epoch": 2.4250726442507267, "percentage": 80.79, "elapsed_time": "2 days, 18:44:39", "remaining_time": "15:51:55", "throughput": 637.67, "total_tokens": 153220224} {"current_steps": 733, "total_steps": 906, "loss": 0.12754693627357483, "lr": 4.414045778845144e-06, "epoch": 2.428393524283935, "percentage": 80.91, "elapsed_time": "2 days, 18:49:02", "remaining_time": "15:46:11", "throughput": 637.86, "total_tokens": 153431992} {"current_steps": 734, "total_steps": 906, "loss": 0.11305053532123566, "lr": 4.364982040271986e-06, "epoch": 2.431714404317144, "percentage": 81.02, "elapsed_time": "2 days, 18:53:35", "remaining_time": "15:40:30", "throughput": 637.98, "total_tokens": 153635224} {"current_steps": 735, "total_steps": 906, "loss": 0.12115851789712906, "lr": 4.316166413696851e-06, "epoch": 2.4350352843503527, "percentage": 81.13, "elapsed_time": "2 days, 18:57:53", "remaining_time": "15:34:46", "throughput": 638.16, "total_tokens": 153842856} {"current_steps": 736, "total_steps": 906, "loss": 0.13038942217826843, "lr": 4.267599486070647e-06, "epoch": 2.4383561643835616, "percentage": 81.24, "elapsed_time": "2 days, 19:02:37", "remaining_time": "15:29:08", "throughput": 638.31, "total_tokens": 154060056} {"current_steps": 737, "total_steps": 906, "loss": 0.12545159459114075, "lr": 4.219281841353981e-06, "epoch": 2.4416770444167706, "percentage": 81.35, "elapsed_time": "2 days, 19:07:09", "remaining_time": "15:23:27", "throughput": 638.46, "total_tokens": 154271184} {"current_steps": 738, "total_steps": 906, "loss": 0.12204748392105103, "lr": 4.171214060510109e-06, "epoch": 2.444997924449979, "percentage": 81.46, "elapsed_time": "2 days, 19:11:44", "remaining_time": "15:17:47", "throughput": 638.6, "total_tokens": 154479520} {"current_steps": 739, "total_steps": 906, "loss": 0.12843818962574005, "lr": 4.123396721497977e-06, "epoch": 2.448318804483188, "percentage": 81.57, "elapsed_time": "2 days, 19:16:23", "remaining_time": "15:12:08", "throughput": 638.76, "total_tokens": 154697384} {"current_steps": 740, "total_steps": 906, "loss": 0.11923454701900482, "lr": 4.075830399265263e-06, "epoch": 2.451639684516397, "percentage": 81.68, "elapsed_time": "2 days, 19:20:58", "remaining_time": "15:06:29", "throughput": 638.89, "total_tokens": 154904408} {"current_steps": 741, "total_steps": 906, "loss": 0.11705135554075241, "lr": 4.028515665741439e-06, "epoch": 2.4549605645496055, "percentage": 81.79, "elapsed_time": "2 days, 19:25:20", "remaining_time": "15:00:47", "throughput": 639.06, "total_tokens": 155112432} {"current_steps": 742, "total_steps": 906, "loss": 0.1258704960346222, "lr": 3.981453089830936e-06, "epoch": 2.4582814445828145, "percentage": 81.9, "elapsed_time": "2 days, 19:30:04", "remaining_time": "14:55:09", "throughput": 639.2, "total_tokens": 155327680} {"current_steps": 743, "total_steps": 906, "loss": 0.12522853910923004, "lr": 3.934643237406291e-06, "epoch": 2.461602324616023, "percentage": 82.01, "elapsed_time": "2 days, 19:34:20", "remaining_time": "14:49:26", "throughput": 639.4, "total_tokens": 155541672} {"current_steps": 744, "total_steps": 906, "loss": 0.11793011426925659, "lr": 3.8880866713013164e-06, "epoch": 2.464923204649232, "percentage": 82.12, "elapsed_time": "2 days, 19:38:24", "remaining_time": "14:43:41", "throughput": 639.61, "total_tokens": 155748912} {"current_steps": 745, "total_steps": 906, "loss": 0.1318972110748291, "lr": 3.8417839513043645e-06, "epoch": 2.468244084682441, "percentage": 82.23, "elapsed_time": "2 days, 19:42:28", "remaining_time": "14:37:55", "throughput": 639.85, "total_tokens": 155962840} {"current_steps": 746, "total_steps": 906, "loss": 0.1243850439786911, "lr": 3.795735634151579e-06, "epoch": 2.4715649647156495, "percentage": 82.34, "elapsed_time": "2 days, 19:46:57", "remaining_time": "14:32:16", "throughput": 640.01, "total_tokens": 156173448} {"current_steps": 747, "total_steps": 906, "loss": 0.11858029663562775, "lr": 3.7499422735202127e-06, "epoch": 2.4748858447488584, "percentage": 82.45, "elapsed_time": "2 days, 19:51:11", "remaining_time": "14:26:33", "throughput": 640.18, "total_tokens": 156377712} {"current_steps": 748, "total_steps": 906, "loss": 0.12187186628580093, "lr": 3.7044044200219564e-06, "epoch": 2.4782067247820674, "percentage": 82.56, "elapsed_time": "2 days, 19:55:28", "remaining_time": "14:20:51", "throughput": 640.36, "total_tokens": 156586872} {"current_steps": 749, "total_steps": 906, "loss": 0.12624505162239075, "lr": 3.6591226211963287e-06, "epoch": 2.481527604815276, "percentage": 82.67, "elapsed_time": "2 days, 19:59:54", "remaining_time": "14:15:11", "throughput": 640.55, "total_tokens": 156803232} {"current_steps": 750, "total_steps": 906, "loss": 0.12942159175872803, "lr": 3.6140974215040953e-06, "epoch": 2.484848484848485, "percentage": 82.78, "elapsed_time": "2 days, 20:04:21", "remaining_time": "14:09:32", "throughput": 640.73, "total_tokens": 157018288} {"current_steps": 751, "total_steps": 906, "loss": 0.1220598816871643, "lr": 3.5693293623207086e-06, "epoch": 2.488169364881694, "percentage": 82.89, "elapsed_time": "2 days, 20:08:57", "remaining_time": "14:03:55", "throughput": 640.87, "total_tokens": 157228840} {"current_steps": 752, "total_steps": 906, "loss": 0.12424576282501221, "lr": 3.5248189819298086e-06, "epoch": 2.4914902449149023, "percentage": 83.0, "elapsed_time": "2 days, 20:13:33", "remaining_time": "13:58:18", "throughput": 641.02, "total_tokens": 157443528} {"current_steps": 753, "total_steps": 906, "loss": 0.12430645525455475, "lr": 3.480566815516756e-06, "epoch": 2.4948111249481113, "percentage": 83.11, "elapsed_time": "2 days, 20:17:54", "remaining_time": "13:52:38", "throughput": 641.2, "total_tokens": 157654584} {"current_steps": 754, "total_steps": 906, "loss": 0.12024077773094177, "lr": 3.4365733951621793e-06, "epoch": 2.4981320049813203, "percentage": 83.22, "elapsed_time": "2 days, 20:22:12", "remaining_time": "13:46:58", "throughput": 641.38, "total_tokens": 157865464} {"current_steps": 755, "total_steps": 906, "loss": 0.11887156218290329, "lr": 3.3928392498355916e-06, "epoch": 2.501452885014529, "percentage": 83.33, "elapsed_time": "2 days, 20:26:36", "remaining_time": "13:41:19", "throughput": 641.55, "total_tokens": 158074976} {"current_steps": 756, "total_steps": 906, "loss": 0.11605098843574524, "lr": 3.3493649053890326e-06, "epoch": 2.5047737650477377, "percentage": 83.44, "elapsed_time": "2 days, 20:31:30", "remaining_time": "13:35:46", "throughput": 641.63, "total_tokens": 158283656} {"current_steps": 757, "total_steps": 906, "loss": 0.12943193316459656, "lr": 3.3061508845507323e-06, "epoch": 2.5080946450809467, "percentage": 83.55, "elapsed_time": "2 days, 20:36:07", "remaining_time": "13:30:10", "throughput": 641.78, "total_tokens": 158499472} {"current_steps": 758, "total_steps": 906, "loss": 0.1205691397190094, "lr": 3.263197706918836e-06, "epoch": 2.5114155251141552, "percentage": 83.66, "elapsed_time": "2 days, 20:40:19", "remaining_time": "13:24:29", "throughput": 641.99, "total_tokens": 158712288} {"current_steps": 759, "total_steps": 906, "loss": 0.11933501064777374, "lr": 3.22050588895515e-06, "epoch": 2.514736405147364, "percentage": 83.77, "elapsed_time": "2 days, 20:44:20", "remaining_time": "13:18:47", "throughput": 642.22, "total_tokens": 158924464} {"current_steps": 760, "total_steps": 906, "loss": 0.12427882850170135, "lr": 3.1780759439789505e-06, "epoch": 2.5180572851805727, "percentage": 83.89, "elapsed_time": "2 days, 20:48:59", "remaining_time": "13:13:11", "throughput": 642.36, "total_tokens": 159138744} {"current_steps": 761, "total_steps": 906, "loss": 0.12325683981180191, "lr": 3.135908382160771e-06, "epoch": 2.5213781652137817, "percentage": 84.0, "elapsed_time": "2 days, 20:53:41", "remaining_time": "13:07:37", "throughput": 642.49, "total_tokens": 159350696} {"current_steps": 762, "total_steps": 906, "loss": 0.11813477426767349, "lr": 3.094003710516316e-06, "epoch": 2.52469904524699, "percentage": 84.11, "elapsed_time": "2 days, 20:58:39", "remaining_time": "13:02:06", "throughput": 642.54, "total_tokens": 159556232} {"current_steps": 763, "total_steps": 906, "loss": 0.12102234363555908, "lr": 3.0523624329003324e-06, "epoch": 2.528019925280199, "percentage": 84.22, "elapsed_time": "2 days, 21:03:42", "remaining_time": "12:56:36", "throughput": 642.61, "total_tokens": 159766984} {"current_steps": 764, "total_steps": 906, "loss": 0.12141455709934235, "lr": 3.010985050000567e-06, "epoch": 2.531340805313408, "percentage": 84.33, "elapsed_time": "2 days, 21:08:34", "remaining_time": "12:51:04", "throughput": 642.7, "total_tokens": 159976928} {"current_steps": 765, "total_steps": 906, "loss": 0.11940959841012955, "lr": 2.969872059331738e-06, "epoch": 2.5346616853466166, "percentage": 84.44, "elapsed_time": "2 days, 21:13:40", "remaining_time": "12:45:34", "throughput": 642.76, "total_tokens": 160188856} {"current_steps": 766, "total_steps": 906, "loss": 0.12051350623369217, "lr": 2.929023955229554e-06, "epoch": 2.5379825653798256, "percentage": 84.55, "elapsed_time": "2 days, 21:19:07", "remaining_time": "12:40:09", "throughput": 642.77, "total_tokens": 160402176} {"current_steps": 767, "total_steps": 906, "loss": 0.12026175111532211, "lr": 2.8884412288447737e-06, "epoch": 2.5413034454130345, "percentage": 84.66, "elapsed_time": "2 days, 21:24:12", "remaining_time": "12:34:39", "throughput": 642.81, "total_tokens": 160606848} {"current_steps": 768, "total_steps": 906, "loss": 0.11633945256471634, "lr": 2.8481243681373004e-06, "epoch": 2.544624325446243, "percentage": 84.77, "elapsed_time": "2 days, 21:29:06", "remaining_time": "12:29:08", "throughput": 642.88, "total_tokens": 160814128} {"current_steps": 769, "total_steps": 906, "loss": 0.12401984632015228, "lr": 2.8080738578703054e-06, "epoch": 2.547945205479452, "percentage": 84.88, "elapsed_time": "2 days, 21:34:05", "remaining_time": "12:23:37", "throughput": 642.96, "total_tokens": 161025112} {"current_steps": 770, "total_steps": 906, "loss": 0.1298520267009735, "lr": 2.7682901796044214e-06, "epoch": 2.551266085512661, "percentage": 84.99, "elapsed_time": "2 days, 21:39:35", "remaining_time": "12:18:12", "throughput": 642.94, "total_tokens": 161234864} {"current_steps": 771, "total_steps": 906, "loss": 0.12286140024662018, "lr": 2.728773811691923e-06, "epoch": 2.5545869655458695, "percentage": 85.1, "elapsed_time": "2 days, 21:45:02", "remaining_time": "12:12:47", "throughput": 642.95, "total_tokens": 161445032} {"current_steps": 772, "total_steps": 906, "loss": 0.12267804890871048, "lr": 2.689525229270998e-06, "epoch": 2.5579078455790785, "percentage": 85.21, "elapsed_time": "2 days, 21:50:17", "remaining_time": "12:07:19", "throughput": 642.97, "total_tokens": 161654816} {"current_steps": 773, "total_steps": 906, "loss": 0.11676201224327087, "lr": 2.6505449042600244e-06, "epoch": 2.5612287256122874, "percentage": 85.32, "elapsed_time": "2 days, 21:55:20", "remaining_time": "12:01:50", "throughput": 643.0, "total_tokens": 161856240} {"current_steps": 774, "total_steps": 906, "loss": 0.12199907749891281, "lr": 2.611833305351899e-06, "epoch": 2.564549605645496, "percentage": 85.43, "elapsed_time": "2 days, 22:00:37", "remaining_time": "11:56:23", "throughput": 643.03, "total_tokens": 162066904} {"current_steps": 775, "total_steps": 906, "loss": 0.12086299061775208, "lr": 2.5733908980083988e-06, "epoch": 2.567870485678705, "percentage": 85.54, "elapsed_time": "2 days, 22:05:47", "remaining_time": "11:50:54", "throughput": 643.07, "total_tokens": 162276928} {"current_steps": 776, "total_steps": 906, "loss": 0.1251925230026245, "lr": 2.535218144454585e-06, "epoch": 2.571191365711914, "percentage": 85.65, "elapsed_time": "2 days, 22:11:30", "remaining_time": "11:45:32", "throughput": 643.04, "total_tokens": 162490488} {"current_steps": 777, "total_steps": 906, "loss": 0.1298554539680481, "lr": 2.4973155036732534e-06, "epoch": 2.5745122457451224, "percentage": 85.76, "elapsed_time": "2 days, 22:16:36", "remaining_time": "11:40:03", "throughput": 643.1, "total_tokens": 162700640} {"current_steps": 778, "total_steps": 906, "loss": 0.11935385316610336, "lr": 2.4596834313994036e-06, "epoch": 2.5778331257783313, "percentage": 85.87, "elapsed_time": "2 days, 22:21:57", "remaining_time": "11:34:36", "throughput": 643.13, "total_tokens": 162915456} {"current_steps": 779, "total_steps": 906, "loss": 0.12721630930900574, "lr": 2.422322380114772e-06, "epoch": 2.5811540058115403, "percentage": 85.98, "elapsed_time": "2 days, 22:26:45", "remaining_time": "11:29:05", "throughput": 643.23, "total_tokens": 163125664} {"current_steps": 780, "total_steps": 906, "loss": 0.12535764276981354, "lr": 2.3852327990423666e-06, "epoch": 2.584474885844749, "percentage": 86.09, "elapsed_time": "2 days, 22:32:00", "remaining_time": "11:23:37", "throughput": 643.26, "total_tokens": 163337744} {"current_steps": 781, "total_steps": 906, "loss": 0.12309374660253525, "lr": 2.348415134141102e-06, "epoch": 2.587795765877958, "percentage": 86.2, "elapsed_time": "2 days, 22:37:23", "remaining_time": "11:18:12", "throughput": 643.29, "total_tokens": 163551400} {"current_steps": 782, "total_steps": 906, "loss": 0.11573754251003265, "lr": 2.3118698281004103e-06, "epoch": 2.5911166459111663, "percentage": 86.31, "elapsed_time": "2 days, 22:42:31", "remaining_time": "11:12:43", "throughput": 643.32, "total_tokens": 163759232} {"current_steps": 783, "total_steps": 906, "loss": 0.12840723991394043, "lr": 2.2755973203349294e-06, "epoch": 2.5944375259443753, "percentage": 86.42, "elapsed_time": "2 days, 22:47:42", "remaining_time": "11:07:15", "throughput": 643.38, "total_tokens": 163973024} {"current_steps": 784, "total_steps": 906, "loss": 0.12373904883861542, "lr": 2.2395980469792103e-06, "epoch": 2.597758405977584, "percentage": 86.53, "elapsed_time": "2 days, 22:52:32", "remaining_time": "11:01:44", "throughput": 643.47, "total_tokens": 164182328} {"current_steps": 785, "total_steps": 906, "loss": 0.1140456348657608, "lr": 2.2038724408824844e-06, "epoch": 2.6010792860107927, "percentage": 86.64, "elapsed_time": "2 days, 22:57:47", "remaining_time": "10:56:17", "throughput": 643.48, "total_tokens": 164388728} {"current_steps": 786, "total_steps": 906, "loss": 0.12779146432876587, "lr": 2.168420931603457e-06, "epoch": 2.6044001660440017, "percentage": 86.75, "elapsed_time": "2 days, 23:03:28", "remaining_time": "10:50:54", "throughput": 643.46, "total_tokens": 164602312} {"current_steps": 787, "total_steps": 906, "loss": 0.11502551287412643, "lr": 2.133243945405128e-06, "epoch": 2.6077210460772102, "percentage": 86.87, "elapsed_time": "2 days, 23:08:54", "remaining_time": "10:45:29", "throughput": 643.44, "total_tokens": 164808200} {"current_steps": 788, "total_steps": 906, "loss": 0.12242258340120316, "lr": 2.09834190524969e-06, "epoch": 2.611041926110419, "percentage": 86.98, "elapsed_time": "2 days, 23:14:13", "remaining_time": "10:40:02", "throughput": 643.47, "total_tokens": 165020992} {"current_steps": 789, "total_steps": 906, "loss": 0.12721297144889832, "lr": 2.0637152307934228e-06, "epoch": 2.614362806143628, "percentage": 87.09, "elapsed_time": "2 days, 23:19:22", "remaining_time": "10:34:35", "throughput": 643.54, "total_tokens": 165236832} {"current_steps": 790, "total_steps": 906, "loss": 0.11729756742715836, "lr": 2.029364338381656e-06, "epoch": 2.6176836861768367, "percentage": 87.2, "elapsed_time": "2 days, 23:24:52", "remaining_time": "10:29:10", "throughput": 643.52, "total_tokens": 165444256} {"current_steps": 791, "total_steps": 906, "loss": 0.12569686770439148, "lr": 1.995289641043768e-06, "epoch": 2.6210045662100456, "percentage": 87.31, "elapsed_time": "2 days, 23:30:16", "remaining_time": "10:23:44", "throughput": 643.51, "total_tokens": 165651408} {"current_steps": 792, "total_steps": 906, "loss": 0.12304438650608063, "lr": 1.961491548488206e-06, "epoch": 2.6243254462432546, "percentage": 87.42, "elapsed_time": "2 days, 23:35:30", "remaining_time": "10:18:17", "throughput": 643.53, "total_tokens": 165858696} {"current_steps": 793, "total_steps": 906, "loss": 0.11656749248504639, "lr": 1.927970467097573e-06, "epoch": 2.627646326276463, "percentage": 87.53, "elapsed_time": "2 days, 23:40:42", "remaining_time": "10:12:50", "throughput": 643.56, "total_tokens": 166067192} {"current_steps": 794, "total_steps": 906, "loss": 0.11832045018672943, "lr": 1.8947267999237322e-06, "epoch": 2.630967206309672, "percentage": 87.64, "elapsed_time": "2 days, 23:46:20", "remaining_time": "10:07:26", "throughput": 643.55, "total_tokens": 166279640} {"current_steps": 795, "total_steps": 906, "loss": 0.12332157790660858, "lr": 1.8617609466829666e-06, "epoch": 2.634288086342881, "percentage": 87.75, "elapsed_time": "2 days, 23:51:58", "remaining_time": "10:02:03", "throughput": 643.52, "total_tokens": 166490368} {"current_steps": 796, "total_steps": 906, "loss": 0.12114399671554565, "lr": 1.8290733037511721e-06, "epoch": 2.6376089663760895, "percentage": 87.86, "elapsed_time": "2 days, 23:57:52", "remaining_time": "9:56:41", "throughput": 643.46, "total_tokens": 166702400} {"current_steps": 797, "total_steps": 906, "loss": 0.12398452311754227, "lr": 1.7966642641590925e-06, "epoch": 2.6409298464092985, "percentage": 87.97, "elapsed_time": "3 days, 0:03:38", "remaining_time": "9:51:18", "throughput": 643.42, "total_tokens": 166915872} {"current_steps": 798, "total_steps": 906, "loss": 0.11987572908401489, "lr": 1.764534217587585e-06, "epoch": 2.6442507264425075, "percentage": 88.08, "elapsed_time": "3 days, 0:09:03", "remaining_time": "9:45:53", "throughput": 643.42, "total_tokens": 167125712} {"current_steps": 799, "total_steps": 906, "loss": 0.12342026829719543, "lr": 1.732683550362954e-06, "epoch": 2.647571606475716, "percentage": 88.19, "elapsed_time": "3 days, 0:14:32", "remaining_time": "9:40:28", "throughput": 643.42, "total_tokens": 167336384} {"current_steps": 800, "total_steps": 906, "loss": 0.12326280027627945, "lr": 1.7011126454522713e-06, "epoch": 2.650892486508925, "percentage": 88.3, "elapsed_time": "3 days, 0:20:34", "remaining_time": "9:35:07", "throughput": 643.33, "total_tokens": 167544792} {"current_steps": 801, "total_steps": 906, "loss": 0.12250946462154388, "lr": 1.6698218824588164e-06, "epoch": 2.654213366542134, "percentage": 88.41, "elapsed_time": "3 days, 0:26:08", "remaining_time": "9:29:43", "throughput": 643.32, "total_tokens": 167758024} {"current_steps": 802, "total_steps": 906, "loss": 0.1269228309392929, "lr": 1.6388116376174767e-06, "epoch": 2.6575342465753424, "percentage": 88.52, "elapsed_time": "3 days, 0:31:43", "remaining_time": "9:24:18", "throughput": 643.29, "total_tokens": 167964408} {"current_steps": 803, "total_steps": 906, "loss": 0.12384317815303802, "lr": 1.6080822837902382e-06, "epoch": 2.6608551266085514, "percentage": 88.63, "elapsed_time": "3 days, 0:37:18", "remaining_time": "9:18:54", "throughput": 643.28, "total_tokens": 168177256} {"current_steps": 804, "total_steps": 906, "loss": 0.12542122602462769, "lr": 1.5776341904617048e-06, "epoch": 2.66417600664176, "percentage": 88.74, "elapsed_time": "3 days, 0:43:00", "remaining_time": "9:13:30", "throughput": 643.26, "total_tokens": 168391888} {"current_steps": 805, "total_steps": 906, "loss": 0.11933274567127228, "lr": 1.5474677237346468e-06, "epoch": 2.667496886674969, "percentage": 88.85, "elapsed_time": "3 days, 0:48:05", "remaining_time": "9:08:02", "throughput": 643.29, "total_tokens": 168596424} {"current_steps": 806, "total_steps": 906, "loss": 0.11670228838920593, "lr": 1.5175832463256046e-06, "epoch": 2.670817766708178, "percentage": 88.96, "elapsed_time": "3 days, 0:53:31", "remaining_time": "9:02:37", "throughput": 643.26, "total_tokens": 168798304} {"current_steps": 807, "total_steps": 906, "loss": 0.11482670903205872, "lr": 1.4879811175605302e-06, "epoch": 2.6741386467413863, "percentage": 89.07, "elapsed_time": "3 days, 0:59:00", "remaining_time": "8:57:12", "throughput": 643.24, "total_tokens": 169005944} {"current_steps": 808, "total_steps": 906, "loss": 0.12115344405174255, "lr": 1.4586616933704528e-06, "epoch": 2.6774595267745953, "percentage": 89.18, "elapsed_time": "3 days, 1:04:15", "remaining_time": "8:51:45", "throughput": 643.27, "total_tokens": 169216600} {"current_steps": 809, "total_steps": 906, "loss": 0.11893177777528763, "lr": 1.4296253262872234e-06, "epoch": 2.680780406807804, "percentage": 89.29, "elapsed_time": "3 days, 1:09:27", "remaining_time": "8:46:18", "throughput": 643.31, "total_tokens": 169428032} {"current_steps": 810, "total_steps": 906, "loss": 0.13020320236682892, "lr": 1.400872365439246e-06, "epoch": 2.684101286841013, "percentage": 89.4, "elapsed_time": "3 days, 1:15:08", "remaining_time": "8:40:54", "throughput": 643.29, "total_tokens": 169641760} {"current_steps": 811, "total_steps": 906, "loss": 0.11801673471927643, "lr": 1.3724031565473112e-06, "epoch": 2.6874221668742218, "percentage": 89.51, "elapsed_time": "3 days, 1:20:11", "remaining_time": "8:35:26", "throughput": 643.33, "total_tokens": 169845856} {"current_steps": 812, "total_steps": 906, "loss": 0.11800455302000046, "lr": 1.3442180419204088e-06, "epoch": 2.6907430469074303, "percentage": 89.62, "elapsed_time": "3 days, 1:25:04", "remaining_time": "8:29:56", "throughput": 643.41, "total_tokens": 170055608} {"current_steps": 813, "total_steps": 906, "loss": 0.116279236972332, "lr": 1.316317360451641e-06, "epoch": 2.6940639269406392, "percentage": 89.74, "elapsed_time": "3 days, 1:30:26", "remaining_time": "8:24:30", "throughput": 643.39, "total_tokens": 170258376} {"current_steps": 814, "total_steps": 906, "loss": 0.12136112153530121, "lr": 1.2887014476141212e-06, "epoch": 2.697384806973848, "percentage": 89.85, "elapsed_time": "3 days, 1:35:47", "remaining_time": "8:19:04", "throughput": 643.41, "total_tokens": 170470528} {"current_steps": 815, "total_steps": 906, "loss": 0.1223984807729721, "lr": 1.2613706354569571e-06, "epoch": 2.7007056870070567, "percentage": 89.96, "elapsed_time": "3 days, 1:41:54", "remaining_time": "8:13:44", "throughput": 643.33, "total_tokens": 170684152} {"current_steps": 816, "total_steps": 906, "loss": 0.11964330077171326, "lr": 1.2343252526012595e-06, "epoch": 2.7040265670402657, "percentage": 90.07, "elapsed_time": "3 days, 1:47:37", "remaining_time": "8:08:20", "throughput": 643.31, "total_tokens": 170899184} {"current_steps": 817, "total_steps": 906, "loss": 0.12065157294273376, "lr": 1.2075656242361732e-06, "epoch": 2.7073474470734746, "percentage": 90.18, "elapsed_time": "3 days, 1:53:34", "remaining_time": "8:02:58", "throughput": 643.24, "total_tokens": 171112184} {"current_steps": 818, "total_steps": 906, "loss": 0.12584027647972107, "lr": 1.1810920721149892e-06, "epoch": 2.710668327106683, "percentage": 90.29, "elapsed_time": "3 days, 1:58:52", "remaining_time": "7:57:31", "throughput": 643.27, "total_tokens": 171323576} {"current_steps": 819, "total_steps": 906, "loss": 0.11420264095067978, "lr": 1.1549049145512636e-06, "epoch": 2.713989207139892, "percentage": 90.4, "elapsed_time": "3 days, 2:03:37", "remaining_time": "7:52:01", "throughput": 643.37, "total_tokens": 171533128} {"current_steps": 820, "total_steps": 906, "loss": 0.13194763660430908, "lr": 1.1290044664149873e-06, "epoch": 2.717310087173101, "percentage": 90.51, "elapsed_time": "3 days, 2:09:04", "remaining_time": "7:46:36", "throughput": 643.39, "total_tokens": 171750904} {"current_steps": 821, "total_steps": 906, "loss": 0.12018980830907822, "lr": 1.1033910391288065e-06, "epoch": 2.7206309672063096, "percentage": 90.62, "elapsed_time": "3 days, 2:14:22", "remaining_time": "7:41:10", "throughput": 643.43, "total_tokens": 171964648} {"current_steps": 822, "total_steps": 906, "loss": 0.12106224149465561, "lr": 1.0780649406642862e-06, "epoch": 2.7239518472395186, "percentage": 90.73, "elapsed_time": "3 days, 2:20:27", "remaining_time": "7:35:48", "throughput": 643.34, "total_tokens": 172174992} {"current_steps": 823, "total_steps": 906, "loss": 0.11653967201709747, "lr": 1.0530264755381824e-06, "epoch": 2.7272727272727275, "percentage": 90.84, "elapsed_time": "3 days, 2:25:44", "remaining_time": "7:30:22", "throughput": 643.36, "total_tokens": 172383840} {"current_steps": 824, "total_steps": 906, "loss": 0.1209145188331604, "lr": 1.028275944808807e-06, "epoch": 2.730593607305936, "percentage": 90.95, "elapsed_time": "3 days, 2:31:18", "remaining_time": "7:24:57", "throughput": 643.33, "total_tokens": 172590416} {"current_steps": 825, "total_steps": 906, "loss": 0.12629863619804382, "lr": 1.0038136460723963e-06, "epoch": 2.733914487339145, "percentage": 91.06, "elapsed_time": "3 days, 2:36:58", "remaining_time": "7:19:33", "throughput": 643.3, "total_tokens": 172802240} {"current_steps": 826, "total_steps": 906, "loss": 0.12389196455478668, "lr": 9.796398734595285e-07, "epoch": 2.7372353673723535, "percentage": 91.17, "elapsed_time": "3 days, 2:42:38", "remaining_time": "7:14:09", "throughput": 643.27, "total_tokens": 173013584} {"current_steps": 827, "total_steps": 906, "loss": 0.12121491134166718, "lr": 9.557549176315934e-07, "epoch": 2.7405562474055625, "percentage": 91.28, "elapsed_time": "3 days, 2:48:11", "remaining_time": "7:08:44", "throughput": 643.26, "total_tokens": 173223384} {"current_steps": 828, "total_steps": 906, "loss": 0.12518440186977386, "lr": 9.321590657772994e-07, "epoch": 2.7438771274387714, "percentage": 91.39, "elapsed_time": "3 days, 2:54:49", "remaining_time": "7:03:25", "throughput": 643.11, "total_tokens": 173439368} {"current_steps": 829, "total_steps": 906, "loss": 0.11913235485553741, "lr": 9.088526016092142e-07, "epoch": 2.74719800747198, "percentage": 91.5, "elapsed_time": "3 days, 3:00:39", "remaining_time": "6:58:02", "throughput": 643.05, "total_tokens": 173648176} {"current_steps": 830, "total_steps": 906, "loss": 0.12754884362220764, "lr": 8.858358053603577e-07, "epoch": 2.750518887505189, "percentage": 91.61, "elapsed_time": "3 days, 3:06:07", "remaining_time": "6:52:36", "throughput": 643.05, "total_tokens": 173859512} {"current_steps": 831, "total_steps": 906, "loss": 0.12187932431697845, "lr": 8.631089537808307e-07, "epoch": 2.7538397675383974, "percentage": 91.72, "elapsed_time": "3 days, 3:11:52", "remaining_time": "6:47:12", "throughput": 643.01, "total_tokens": 174070168} {"current_steps": 832, "total_steps": 906, "loss": 0.11619506031274796, "lr": 8.406723201344891e-07, "epoch": 2.7571606475716064, "percentage": 91.83, "elapsed_time": "3 days, 3:17:30", "remaining_time": "6:41:47", "throughput": 642.97, "total_tokens": 174277352} {"current_steps": 833, "total_steps": 906, "loss": 0.12683464586734772, "lr": 8.185261741956551e-07, "epoch": 2.7604815276048154, "percentage": 91.94, "elapsed_time": "3 days, 3:23:33", "remaining_time": "6:36:25", "throughput": 642.89, "total_tokens": 174490400} {"current_steps": 834, "total_steps": 906, "loss": 0.11898402124643326, "lr": 7.966707822458758e-07, "epoch": 2.763802407638024, "percentage": 92.05, "elapsed_time": "3 days, 3:28:57", "remaining_time": "6:30:59", "throughput": 642.9, "total_tokens": 174700432} {"current_steps": 835, "total_steps": 906, "loss": 0.11298386752605438, "lr": 7.751064070707248e-07, "epoch": 2.767123287671233, "percentage": 92.16, "elapsed_time": "3 days, 3:34:08", "remaining_time": "6:25:32", "throughput": 642.91, "total_tokens": 174903336} {"current_steps": 836, "total_steps": 906, "loss": 0.11921288073062897, "lr": 7.538333079566306e-07, "epoch": 2.770444167704442, "percentage": 92.27, "elapsed_time": "3 days, 3:40:10", "remaining_time": "6:20:09", "throughput": 642.84, "total_tokens": 175117688} {"current_steps": 837, "total_steps": 906, "loss": 0.12302444875240326, "lr": 7.328517406877761e-07, "epoch": 2.7737650477376503, "percentage": 92.38, "elapsed_time": "3 days, 3:45:58", "remaining_time": "6:14:45", "throughput": 642.8, "total_tokens": 175328400} {"current_steps": 838, "total_steps": 906, "loss": 0.11951660364866257, "lr": 7.12161957543006e-07, "epoch": 2.7770859277708593, "percentage": 92.49, "elapsed_time": "3 days, 3:51:38", "remaining_time": "6:09:20", "throughput": 642.76, "total_tokens": 175535848} {"current_steps": 839, "total_steps": 906, "loss": 0.12080246210098267, "lr": 6.917642072928137e-07, "epoch": 2.7804068078040682, "percentage": 92.6, "elapsed_time": "3 days, 3:57:35", "remaining_time": "6:03:57", "throughput": 642.68, "total_tokens": 175743512} {"current_steps": 840, "total_steps": 906, "loss": 0.12245343625545502, "lr": 6.716587351963205e-07, "epoch": 2.7837276878372768, "percentage": 92.72, "elapsed_time": "3 days, 4:02:48", "remaining_time": "5:58:30", "throughput": 642.71, "total_tokens": 175952928} {"current_steps": 841, "total_steps": 906, "loss": 0.11698979139328003, "lr": 6.51845782998356e-07, "epoch": 2.7870485678704857, "percentage": 92.83, "elapsed_time": "3 days, 4:08:35", "remaining_time": "5:53:06", "throughput": 642.66, "total_tokens": 176162864} {"current_steps": 842, "total_steps": 906, "loss": 0.12792760133743286, "lr": 6.323255889265411e-07, "epoch": 2.7903694479036947, "percentage": 92.94, "elapsed_time": "3 days, 4:14:23", "remaining_time": "5:47:41", "throughput": 642.64, "total_tokens": 176382440} {"current_steps": 843, "total_steps": 906, "loss": 0.11449296772480011, "lr": 6.130983876884155e-07, "epoch": 2.793690327936903, "percentage": 93.05, "elapsed_time": "3 days, 4:20:10", "remaining_time": "5:42:17", "throughput": 642.59, "total_tokens": 176590168} {"current_steps": 844, "total_steps": 906, "loss": 0.12309432774782181, "lr": 5.941644104686256e-07, "epoch": 2.797011207970112, "percentage": 93.16, "elapsed_time": "3 days, 4:25:46", "remaining_time": "5:36:52", "throughput": 642.56, "total_tokens": 176798448} {"current_steps": 845, "total_steps": 906, "loss": 0.11892662942409515, "lr": 5.755238849261407e-07, "epoch": 2.800332088003321, "percentage": 93.27, "elapsed_time": "3 days, 4:31:19", "remaining_time": "5:31:26", "throughput": 642.54, "total_tokens": 177008096} {"current_steps": 846, "total_steps": 906, "loss": 0.11739193648099899, "lr": 5.571770351915168e-07, "epoch": 2.8036529680365296, "percentage": 93.38, "elapsed_time": "3 days, 4:37:15", "remaining_time": "5:26:02", "throughput": 642.47, "total_tokens": 177215368} {"current_steps": 847, "total_steps": 906, "loss": 0.1246020719408989, "lr": 5.391240818642007e-07, "epoch": 2.8069738480697386, "percentage": 93.49, "elapsed_time": "3 days, 4:43:08", "remaining_time": "5:20:38", "throughput": 642.41, "total_tokens": 177425480} {"current_steps": 848, "total_steps": 906, "loss": 0.12035591900348663, "lr": 5.213652420098747e-07, "epoch": 2.810294728102947, "percentage": 93.6, "elapsed_time": "3 days, 4:48:51", "remaining_time": "5:15:13", "throughput": 642.38, "total_tokens": 177638424} {"current_steps": 849, "total_steps": 906, "loss": 0.1129733994603157, "lr": 5.039007291578579e-07, "epoch": 2.813615608136156, "percentage": 93.71, "elapsed_time": "3 days, 4:54:25", "remaining_time": "5:09:48", "throughput": 642.34, "total_tokens": 177841296} {"current_steps": 850, "total_steps": 906, "loss": 0.11389519274234772, "lr": 4.867307532985227e-07, "epoch": 2.816936488169365, "percentage": 93.82, "elapsed_time": "3 days, 5:00:02", "remaining_time": "5:04:22", "throughput": 642.28, "total_tokens": 178040808} {"current_steps": 851, "total_steps": 906, "loss": 0.12554343044757843, "lr": 4.698555208807853e-07, "epoch": 2.8202573682025736, "percentage": 93.93, "elapsed_time": "3 days, 5:05:13", "remaining_time": "4:58:55", "throughput": 642.31, "total_tokens": 178250240} {"current_steps": 852, "total_steps": 906, "loss": 0.12580470740795135, "lr": 4.532752348096081e-07, "epoch": 2.8235782482357825, "percentage": 94.04, "elapsed_time": "3 days, 5:11:15", "remaining_time": "4:53:31", "throughput": 642.25, "total_tokens": 178465496} {"current_steps": 853, "total_steps": 906, "loss": 0.1148395836353302, "lr": 4.3699009444357344e-07, "epoch": 2.826899128268991, "percentage": 94.15, "elapsed_time": "3 days, 5:16:50", "remaining_time": "4:48:06", "throughput": 642.23, "total_tokens": 178673616} {"current_steps": 854, "total_steps": 906, "loss": 0.12070584297180176, "lr": 4.21000295592483e-07, "epoch": 2.8302200083022, "percentage": 94.26, "elapsed_time": "3 days, 5:21:51", "remaining_time": "4:42:38", "throughput": 642.28, "total_tokens": 178882256} {"current_steps": 855, "total_steps": 906, "loss": 0.1180640459060669, "lr": 4.0530603051499584e-07, "epoch": 2.833540888335409, "percentage": 94.37, "elapsed_time": "3 days, 5:26:45", "remaining_time": "4:37:10", "throughput": 642.34, "total_tokens": 179086976} {"current_steps": 856, "total_steps": 906, "loss": 0.12119519710540771, "lr": 3.899074879163245e-07, "epoch": 2.8368617683686175, "percentage": 94.48, "elapsed_time": "3 days, 5:32:06", "remaining_time": "4:31:44", "throughput": 642.35, "total_tokens": 179295696} {"current_steps": 857, "total_steps": 906, "loss": 0.11769559979438782, "lr": 3.7480485294596747e-07, "epoch": 2.8401826484018264, "percentage": 94.59, "elapsed_time": "3 days, 5:37:54", "remaining_time": "4:26:19", "throughput": 642.29, "total_tokens": 179504888} {"current_steps": 858, "total_steps": 906, "loss": 0.11247526109218597, "lr": 3.599983071954777e-07, "epoch": 2.8435035284350354, "percentage": 94.7, "elapsed_time": "3 days, 5:43:14", "remaining_time": "4:20:52", "throughput": 642.3, "total_tokens": 179711696} {"current_steps": 859, "total_steps": 906, "loss": 0.12671740353107452, "lr": 3.454880286962781e-07, "epoch": 2.846824408468244, "percentage": 94.81, "elapsed_time": "3 days, 5:48:23", "remaining_time": "4:15:25", "throughput": 642.35, "total_tokens": 179923648} {"current_steps": 860, "total_steps": 906, "loss": 0.11756633222103119, "lr": 3.312741919175244e-07, "epoch": 2.850145288501453, "percentage": 94.92, "elapsed_time": "3 days, 5:53:32", "remaining_time": "4:09:58", "throughput": 642.39, "total_tokens": 180133392} {"current_steps": 861, "total_steps": 906, "loss": 0.11647183448076248, "lr": 3.1735696776400703e-07, "epoch": 2.853466168534662, "percentage": 95.03, "elapsed_time": "3 days, 5:58:46", "remaining_time": "4:04:32", "throughput": 642.41, "total_tokens": 180341328} {"current_steps": 862, "total_steps": 906, "loss": 0.11633309721946716, "lr": 3.0373652357410245e-07, "epoch": 2.8567870485678704, "percentage": 95.14, "elapsed_time": "3 days, 6:03:40", "remaining_time": "3:59:04", "throughput": 642.48, "total_tokens": 180550952} {"current_steps": 863, "total_steps": 906, "loss": 0.1253267228603363, "lr": 2.9041302311774433e-07, "epoch": 2.8601079286010793, "percentage": 95.25, "elapsed_time": "3 days, 6:08:52", "remaining_time": "3:53:37", "throughput": 642.53, "total_tokens": 180764624} {"current_steps": 864, "total_steps": 906, "loss": 0.12318548560142517, "lr": 2.7738662659447246e-07, "epoch": 2.8634288086342883, "percentage": 95.36, "elapsed_time": "3 days, 6:13:55", "remaining_time": "3:48:10", "throughput": 642.57, "total_tokens": 180971592} {"current_steps": 865, "total_steps": 906, "loss": 0.12904170155525208, "lr": 2.646574906314925e-07, "epoch": 2.866749688667497, "percentage": 95.47, "elapsed_time": "3 days, 6:19:09", "remaining_time": "3:42:44", "throughput": 642.61, "total_tokens": 181183608} {"current_steps": 866, "total_steps": 906, "loss": 0.11389099806547165, "lr": 2.52225768281808e-07, "epoch": 2.8700705687007058, "percentage": 95.58, "elapsed_time": "3 days, 6:24:39", "remaining_time": "3:37:18", "throughput": 642.6, "total_tokens": 181392224} {"current_steps": 867, "total_steps": 906, "loss": 0.11891908943653107, "lr": 2.4009160902235816e-07, "epoch": 2.8733914487339147, "percentage": 95.7, "elapsed_time": "3 days, 6:30:04", "remaining_time": "3:31:52", "throughput": 642.61, "total_tokens": 181604784} {"current_steps": 868, "total_steps": 906, "loss": 0.12021469324827194, "lr": 2.2825515875224413e-07, "epoch": 2.8767123287671232, "percentage": 95.81, "elapsed_time": "3 days, 6:35:41", "remaining_time": "3:26:26", "throughput": 642.57, "total_tokens": 181809728} {"current_steps": 869, "total_steps": 906, "loss": 0.12051525712013245, "lr": 2.1671655979096094e-07, "epoch": 2.880033208800332, "percentage": 95.92, "elapsed_time": "3 days, 6:41:03", "remaining_time": "3:21:00", "throughput": 642.58, "total_tokens": 182019896} {"current_steps": 870, "total_steps": 906, "loss": 0.11526565253734589, "lr": 2.0547595087668793e-07, "epoch": 2.883354088833541, "percentage": 96.03, "elapsed_time": "3 days, 6:45:51", "remaining_time": "3:15:33", "throughput": 642.66, "total_tokens": 182227944} {"current_steps": 871, "total_steps": 906, "loss": 0.1231502816081047, "lr": 1.9453346716462317e-07, "epoch": 2.8866749688667497, "percentage": 96.14, "elapsed_time": "3 days, 6:50:38", "remaining_time": "3:10:05", "throughput": 642.76, "total_tokens": 182438944} {"current_steps": 872, "total_steps": 906, "loss": 0.12128575146198273, "lr": 1.8388924022535725e-07, "epoch": 2.8899958488999586, "percentage": 96.25, "elapsed_time": "3 days, 6:55:53", "remaining_time": "3:04:39", "throughput": 642.78, "total_tokens": 182648344} {"current_steps": 873, "total_steps": 906, "loss": 0.1284339725971222, "lr": 1.73543398043291e-07, "epoch": 2.893316728933167, "percentage": 96.36, "elapsed_time": "3 days, 7:00:47", "remaining_time": "2:59:12", "throughput": 642.86, "total_tokens": 182861192} {"current_steps": 874, "total_steps": 906, "loss": 0.12369494140148163, "lr": 1.6349606501509796e-07, "epoch": 2.896637608966376, "percentage": 96.47, "elapsed_time": "3 days, 7:05:43", "remaining_time": "2:53:45", "throughput": 642.93, "total_tokens": 183070160} {"current_steps": 875, "total_steps": 906, "loss": 0.12231475114822388, "lr": 1.537473619482227e-07, "epoch": 2.8999584889995846, "percentage": 96.58, "elapsed_time": "3 days, 7:10:54", "remaining_time": "2:48:19", "throughput": 642.99, "total_tokens": 183285888} {"current_steps": 876, "total_steps": 906, "loss": 0.11586017906665802, "lr": 1.4429740605944319e-07, "epoch": 2.9032793690327936, "percentage": 96.69, "elapsed_time": "3 days, 7:16:27", "remaining_time": "2:42:53", "throughput": 642.99, "total_tokens": 183501752} {"current_steps": 877, "total_steps": 906, "loss": 0.12425873428583145, "lr": 1.351463109734441e-07, "epoch": 2.9066002490660026, "percentage": 96.8, "elapsed_time": "3 days, 7:21:31", "remaining_time": "2:37:27", "throughput": 643.05, "total_tokens": 183713168} {"current_steps": 878, "total_steps": 906, "loss": 0.11696077883243561, "lr": 1.2629418672145676e-07, "epoch": 2.909921129099211, "percentage": 96.91, "elapsed_time": "3 days, 7:26:05", "remaining_time": "2:31:59", "throughput": 643.16, "total_tokens": 183921672} {"current_steps": 879, "total_steps": 906, "loss": 0.11529619246721268, "lr": 1.1774113973994083e-07, "epoch": 2.91324200913242, "percentage": 97.02, "elapsed_time": "3 days, 7:31:25", "remaining_time": "2:26:33", "throughput": 643.15, "total_tokens": 184126072} {"current_steps": 880, "total_steps": 906, "loss": 0.1224733367562294, "lr": 1.0948727286930193e-07, "epoch": 2.916562889165629, "percentage": 97.13, "elapsed_time": "3 days, 7:36:55", "remaining_time": "2:21:08", "throughput": 643.14, "total_tokens": 184334184} {"current_steps": 881, "total_steps": 906, "loss": 0.12352342903614044, "lr": 1.0153268535264827e-07, "epoch": 2.9198837691988375, "percentage": 97.24, "elapsed_time": "3 days, 7:41:55", "remaining_time": "2:15:41", "throughput": 643.2, "total_tokens": 184543808} {"current_steps": 882, "total_steps": 906, "loss": 0.12213212251663208, "lr": 9.387747283460813e-08, "epoch": 2.9232046492320465, "percentage": 97.35, "elapsed_time": "3 days, 7:47:09", "remaining_time": "2:10:15", "throughput": 643.22, "total_tokens": 184752816} {"current_steps": 883, "total_steps": 906, "loss": 0.11964373290538788, "lr": 8.652172736017816e-08, "epoch": 2.9265255292652554, "percentage": 97.46, "elapsed_time": "3 days, 7:52:31", "remaining_time": "2:04:50", "throughput": 643.23, "total_tokens": 184962096} {"current_steps": 884, "total_steps": 906, "loss": 0.11658230423927307, "lr": 7.946553737360473e-08, "epoch": 2.929846409298464, "percentage": 97.57, "elapsed_time": "3 days, 7:57:47", "remaining_time": "1:59:24", "throughput": 643.27, "total_tokens": 185175696} {"current_steps": 885, "total_steps": 906, "loss": 0.11535081267356873, "lr": 7.270898771733481e-08, "epoch": 2.933167289331673, "percentage": 97.68, "elapsed_time": "3 days, 8:02:38", "remaining_time": "1:53:57", "throughput": 643.31, "total_tokens": 185374744} {"current_steps": 886, "total_steps": 906, "loss": 0.1184299886226654, "lr": 6.625215963098896e-08, "epoch": 2.936488169364882, "percentage": 97.79, "elapsed_time": "3 days, 8:07:25", "remaining_time": "1:48:31", "throughput": 643.39, "total_tokens": 185582624} {"current_steps": 887, "total_steps": 906, "loss": 0.11564740538597107, "lr": 6.00951307503872e-08, "epoch": 2.9398090493980904, "percentage": 97.9, "elapsed_time": "3 days, 8:12:39", "remaining_time": "1:43:05", "throughput": 643.4, "total_tokens": 185788368} {"current_steps": 888, "total_steps": 906, "loss": 0.11729012429714203, "lr": 5.423797510661355e-08, "epoch": 2.9431299294312994, "percentage": 98.01, "elapsed_time": "3 days, 8:18:08", "remaining_time": "1:37:39", "throughput": 643.39, "total_tokens": 185995472} {"current_steps": 889, "total_steps": 906, "loss": 0.11568398028612137, "lr": 4.868076312512515e-08, "epoch": 2.9464508094645083, "percentage": 98.12, "elapsed_time": "3 days, 8:22:55", "remaining_time": "1:32:13", "throughput": 643.45, "total_tokens": 186199944} {"current_steps": 890, "total_steps": 906, "loss": 0.12462468445301056, "lr": 4.3423561624905685e-08, "epoch": 2.949771689497717, "percentage": 98.23, "elapsed_time": "3 days, 8:28:07", "remaining_time": "1:26:47", "throughput": 643.5, "total_tokens": 186413312} {"current_steps": 891, "total_steps": 906, "loss": 0.13031190633773804, "lr": 3.846643381766879e-08, "epoch": 2.953092569530926, "percentage": 98.34, "elapsed_time": "3 days, 8:33:10", "remaining_time": "1:21:22", "throughput": 643.59, "total_tokens": 186635016} {"current_steps": 892, "total_steps": 906, "loss": 0.12338971346616745, "lr": 3.380943930708647e-08, "epoch": 2.9564134495641348, "percentage": 98.45, "elapsed_time": "3 days, 8:38:03", "remaining_time": "1:15:56", "throughput": 643.67, "total_tokens": 186845512} {"current_steps": 893, "total_steps": 906, "loss": 0.11317215859889984, "lr": 2.94526340880813e-08, "epoch": 2.9597343295973433, "percentage": 98.57, "elapsed_time": "3 days, 8:43:12", "remaining_time": "1:10:30", "throughput": 643.69, "total_tokens": 187051624} {"current_steps": 894, "total_steps": 906, "loss": 0.11464998126029968, "lr": 2.5396070546146456e-08, "epoch": 2.9630552096305522, "percentage": 98.68, "elapsed_time": "3 days, 8:48:22", "remaining_time": "1:05:04", "throughput": 643.71, "total_tokens": 187255784} {"current_steps": 895, "total_steps": 906, "loss": 0.12109000980854034, "lr": 2.1639797456723952e-08, "epoch": 2.9663760896637608, "percentage": 98.79, "elapsed_time": "3 days, 8:53:38", "remaining_time": "0:59:39", "throughput": 643.73, "total_tokens": 187466024} {"current_steps": 896, "total_steps": 906, "loss": 0.12020470201969147, "lr": 1.8183859984613472e-08, "epoch": 2.9696969696969697, "percentage": 98.9, "elapsed_time": "3 days, 8:59:07", "remaining_time": "0:54:13", "throughput": 643.73, "total_tokens": 187677224} {"current_steps": 897, "total_steps": 906, "loss": 0.11873486638069153, "lr": 1.5028299683425562e-08, "epoch": 2.9730178497301782, "percentage": 99.01, "elapsed_time": "3 days, 9:04:37", "remaining_time": "0:48:48", "throughput": 643.72, "total_tokens": 187886168} {"current_steps": 898, "total_steps": 906, "loss": 0.12158137559890747, "lr": 1.2173154495087601e-08, "epoch": 2.976338729763387, "percentage": 99.12, "elapsed_time": "3 days, 9:10:20", "remaining_time": "0:43:23", "throughput": 643.68, "total_tokens": 188096304} {"current_steps": 899, "total_steps": 906, "loss": 0.11632666736841202, "lr": 9.618458749391379e-09, "epoch": 2.979659609796596, "percentage": 99.23, "elapsed_time": "3 days, 9:15:56", "remaining_time": "0:37:57", "throughput": 643.65, "total_tokens": 188303944} {"current_steps": 900, "total_steps": 906, "loss": 0.11789841949939728, "lr": 7.364243163568429e-09, "epoch": 2.9829804898298047, "percentage": 99.34, "elapsed_time": "3 days, 9:21:27", "remaining_time": "0:32:32", "throughput": 643.64, "total_tokens": 188514200} {"current_steps": 901, "total_steps": 906, "loss": 0.12132750451564789, "lr": 5.41053484192644e-09, "epoch": 2.9863013698630136, "percentage": 99.45, "elapsed_time": "3 days, 9:26:40", "remaining_time": "0:27:07", "throughput": 643.67, "total_tokens": 188726056} {"current_steps": 902, "total_steps": 906, "loss": 0.12210451066493988, "lr": 3.75735727553006e-09, "epoch": 2.9896222498962226, "percentage": 99.56, "elapsed_time": "3 days, 9:32:08", "remaining_time": "0:21:41", "throughput": 643.67, "total_tokens": 188936616} {"current_steps": 903, "total_steps": 906, "loss": 0.11642736196517944, "lr": 2.4047303419094667e-09, "epoch": 2.992943129929431, "percentage": 99.67, "elapsed_time": "3 days, 9:37:58", "remaining_time": "0:16:16", "throughput": 643.6, "total_tokens": 189139152} {"current_steps": 904, "total_steps": 906, "loss": 0.11877848953008652, "lr": 1.3526703048216682e-09, "epoch": 2.99626400996264, "percentage": 99.78, "elapsed_time": "3 days, 9:43:44", "remaining_time": "0:10:50", "throughput": 643.56, "total_tokens": 189350544} {"current_steps": 905, "total_steps": 906, "loss": 0.12198566645383835, "lr": 6.011898140617645e-10, "epoch": 2.999584889995849, "percentage": 99.89, "elapsed_time": "3 days, 9:49:07", "remaining_time": "0:05:25", "throughput": 643.56, "total_tokens": 189559288} {"current_steps": 906, "total_steps": 906, "loss": 0.07718770951032639, "lr": 1.5029790530474152e-10, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3 days, 9:49:52", "remaining_time": "0:00:00", "throughput": 643.54, "total_tokens": 189583256} {"current_steps": 906, "total_steps": 906, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3 days, 9:50:25", "remaining_time": "0:00:00", "throughput": 643.47, "total_tokens": 189583256}