| {"current_steps": 5, "total_steps": 900, "loss": 0.5002, "lr": 2.2222222222222225e-06, "epoch": 0.05555555555555555, "percentage": 0.56, "elapsed_time": "0:00:01", "remaining_time": "0:03:31", "throughput": 1356.65, "total_tokens": 1600} |
| {"current_steps": 10, "total_steps": 900, "loss": 0.6939, "lr": 5e-06, "epoch": 0.1111111111111111, "percentage": 1.11, "elapsed_time": "0:00:01", "remaining_time": "0:02:45", "throughput": 1716.89, "total_tokens": 3200} |
| {"current_steps": 15, "total_steps": 900, "loss": 0.4727, "lr": 7.777777777777777e-06, "epoch": 0.16666666666666666, "percentage": 1.67, "elapsed_time": "0:00:02", "remaining_time": "0:02:30", "throughput": 1858.35, "total_tokens": 4736} |
| {"current_steps": 20, "total_steps": 900, "loss": 0.4553, "lr": 1.0555555555555555e-05, "epoch": 0.2222222222222222, "percentage": 2.22, "elapsed_time": "0:00:03", "remaining_time": "0:02:22", "throughput": 1970.63, "total_tokens": 6368} |
| {"current_steps": 25, "total_steps": 900, "loss": 0.536, "lr": 1.3333333333333333e-05, "epoch": 0.2777777777777778, "percentage": 2.78, "elapsed_time": "0:00:03", "remaining_time": "0:02:17", "throughput": 2010.41, "total_tokens": 7872} |
| {"current_steps": 30, "total_steps": 900, "loss": 0.3937, "lr": 1.6111111111111115e-05, "epoch": 0.3333333333333333, "percentage": 3.33, "elapsed_time": "0:00:04", "remaining_time": "0:02:13", "throughput": 2053.17, "total_tokens": 9440} |
| {"current_steps": 35, "total_steps": 900, "loss": 0.2638, "lr": 1.888888888888889e-05, "epoch": 0.3888888888888889, "percentage": 3.89, "elapsed_time": "0:00:05", "remaining_time": "0:02:10", "throughput": 2083.39, "total_tokens": 11008} |
| {"current_steps": 40, "total_steps": 900, "loss": 0.1663, "lr": 2.1666666666666667e-05, "epoch": 0.4444444444444444, "percentage": 4.44, "elapsed_time": "0:00:05", "remaining_time": "0:02:08", "throughput": 2112.23, "total_tokens": 12608} |
| {"current_steps": 45, "total_steps": 900, "loss": 0.1757, "lr": 2.4444444444444445e-05, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:06", "remaining_time": "0:02:06", "throughput": 2128.11, "total_tokens": 14144} |
| {"current_steps": 45, "total_steps": 900, "eval_loss": 0.08440126478672028, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:07", "remaining_time": "0:02:17", "throughput": 1959.22, "total_tokens": 14144} |
| {"current_steps": 50, "total_steps": 900, "loss": 0.3607, "lr": 2.7222222222222223e-05, "epoch": 0.5555555555555556, "percentage": 5.56, "elapsed_time": "0:00:08", "remaining_time": "0:02:28", "throughput": 1805.85, "total_tokens": 15744} |
| {"current_steps": 55, "total_steps": 900, "loss": 0.2197, "lr": 3e-05, "epoch": 0.6111111111111112, "percentage": 6.11, "elapsed_time": "0:00:09", "remaining_time": "0:02:24", "throughput": 1841.21, "total_tokens": 17312} |
| {"current_steps": 60, "total_steps": 900, "loss": 0.0129, "lr": 3.277777777777778e-05, "epoch": 0.6666666666666666, "percentage": 6.67, "elapsed_time": "0:00:10", "remaining_time": "0:02:22", "throughput": 1856.01, "total_tokens": 18880} |
| {"current_steps": 65, "total_steps": 900, "loss": 0.0469, "lr": 3.555555555555556e-05, "epoch": 0.7222222222222222, "percentage": 7.22, "elapsed_time": "0:00:10", "remaining_time": "0:02:19", "throughput": 1874.46, "total_tokens": 20416} |
| {"current_steps": 70, "total_steps": 900, "loss": 0.0526, "lr": 3.8333333333333334e-05, "epoch": 0.7777777777777778, "percentage": 7.78, "elapsed_time": "0:00:11", "remaining_time": "0:02:17", "throughput": 1885.32, "total_tokens": 21920} |
| {"current_steps": 75, "total_steps": 900, "loss": 0.0958, "lr": 4.111111111111111e-05, "epoch": 0.8333333333333334, "percentage": 8.33, "elapsed_time": "0:00:12", "remaining_time": "0:02:15", "throughput": 1907.77, "total_tokens": 23488} |
| {"current_steps": 80, "total_steps": 900, "loss": 0.1129, "lr": 4.388888888888889e-05, "epoch": 0.8888888888888888, "percentage": 8.89, "elapsed_time": "0:00:12", "remaining_time": "0:02:13", "throughput": 1928.27, "total_tokens": 25056} |
| {"current_steps": 85, "total_steps": 900, "loss": 0.2708, "lr": 4.666666666666667e-05, "epoch": 0.9444444444444444, "percentage": 9.44, "elapsed_time": "0:00:13", "remaining_time": "0:02:11", "throughput": 1945.59, "total_tokens": 26592} |
| {"current_steps": 90, "total_steps": 900, "loss": 0.3782, "lr": 4.9444444444444446e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:14", "remaining_time": "0:02:09", "throughput": 1959.51, "total_tokens": 28192} |
| {"current_steps": 90, "total_steps": 900, "eval_loss": 0.04465758427977562, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:14", "remaining_time": "0:02:14", "throughput": 1883.87, "total_tokens": 28192} |
| {"current_steps": 95, "total_steps": 900, "loss": 0.1593, "lr": 4.9996991493233693e-05, "epoch": 1.0555555555555556, "percentage": 10.56, "elapsed_time": "0:00:16", "remaining_time": "0:02:20", "throughput": 1801.59, "total_tokens": 29792} |
| {"current_steps": 100, "total_steps": 900, "loss": 0.0673, "lr": 4.99847706754774e-05, "epoch": 1.1111111111111112, "percentage": 11.11, "elapsed_time": "0:00:17", "remaining_time": "0:02:17", "throughput": 1820.87, "total_tokens": 31360} |
| {"current_steps": 105, "total_steps": 900, "loss": 0.003, "lr": 4.9963154107272295e-05, "epoch": 1.1666666666666667, "percentage": 11.67, "elapsed_time": "0:00:17", "remaining_time": "0:02:15", "throughput": 1833.19, "total_tokens": 32832} |
| {"current_steps": 110, "total_steps": 900, "loss": 0.0415, "lr": 4.993214991772563e-05, "epoch": 1.2222222222222223, "percentage": 12.22, "elapsed_time": "0:00:18", "remaining_time": "0:02:13", "throughput": 1846.64, "total_tokens": 34336} |
| {"current_steps": 115, "total_steps": 900, "loss": 0.1988, "lr": 4.989176976624511e-05, "epoch": 1.2777777777777777, "percentage": 12.78, "elapsed_time": "0:00:19", "remaining_time": "0:02:11", "throughput": 1864.01, "total_tokens": 35936} |
| {"current_steps": 120, "total_steps": 900, "loss": 0.0541, "lr": 4.9842028838154285e-05, "epoch": 1.3333333333333333, "percentage": 13.33, "elapsed_time": "0:00:19", "remaining_time": "0:02:09", "throughput": 1880.34, "total_tokens": 37536} |
| {"current_steps": 125, "total_steps": 900, "loss": 0.0173, "lr": 4.978294583898196e-05, "epoch": 1.3888888888888888, "percentage": 13.89, "elapsed_time": "0:00:20", "remaining_time": "0:02:08", "throughput": 1890.88, "total_tokens": 39040} |
| {"current_steps": 130, "total_steps": 900, "loss": 0.1875, "lr": 4.971454298742779e-05, "epoch": 1.4444444444444444, "percentage": 14.44, "elapsed_time": "0:00:21", "remaining_time": "0:02:06", "throughput": 1902.43, "total_tokens": 40576} |
| {"current_steps": 135, "total_steps": 900, "loss": 0.0451, "lr": 4.963684600700679e-05, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:00:22", "remaining_time": "0:02:04", "throughput": 1917.78, "total_tokens": 42208} |
| {"current_steps": 135, "total_steps": 900, "eval_loss": 0.03909554332494736, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:00:22", "remaining_time": "0:02:08", "throughput": 1868.53, "total_tokens": 42208} |
| {"current_steps": 140, "total_steps": 900, "loss": 0.1584, "lr": 4.9549884116375714e-05, "epoch": 1.5555555555555556, "percentage": 15.56, "elapsed_time": "0:00:24", "remaining_time": "0:02:10", "throughput": 1820.34, "total_tokens": 43776} |
| {"current_steps": 145, "total_steps": 900, "loss": 0.0471, "lr": 4.9453690018345144e-05, "epoch": 1.6111111111111112, "percentage": 16.11, "elapsed_time": "0:00:24", "remaining_time": "0:02:08", "throughput": 1834.51, "total_tokens": 45376} |
| {"current_steps": 150, "total_steps": 900, "loss": 0.0983, "lr": 4.934829988758131e-05, "epoch": 1.6666666666666665, "percentage": 16.67, "elapsed_time": "0:00:25", "remaining_time": "0:02:07", "throughput": 1846.69, "total_tokens": 46944} |
| {"current_steps": 155, "total_steps": 900, "loss": 0.038, "lr": 4.923375335700223e-05, "epoch": 1.7222222222222223, "percentage": 17.22, "elapsed_time": "0:00:26", "remaining_time": "0:02:05", "throughput": 1858.38, "total_tokens": 48512} |
| {"current_steps": 160, "total_steps": 900, "loss": 0.0347, "lr": 4.9110093502873476e-05, "epoch": 1.7777777777777777, "percentage": 17.78, "elapsed_time": "0:00:26", "remaining_time": "0:02:03", "throughput": 1870.69, "total_tokens": 50112} |
| {"current_steps": 165, "total_steps": 900, "loss": 0.2183, "lr": 4.897736682860885e-05, "epoch": 1.8333333333333335, "percentage": 18.33, "elapsed_time": "0:00:27", "remaining_time": "0:02:02", "throughput": 1881.32, "total_tokens": 51680} |
| {"current_steps": 170, "total_steps": 900, "loss": 0.0513, "lr": 4.883562324728241e-05, "epoch": 1.8888888888888888, "percentage": 18.89, "elapsed_time": "0:00:28", "remaining_time": "0:02:00", "throughput": 1890.32, "total_tokens": 53216} |
| {"current_steps": 175, "total_steps": 900, "loss": 0.2403, "lr": 4.868491606285823e-05, "epoch": 1.9444444444444444, "percentage": 19.44, "elapsed_time": "0:00:28", "remaining_time": "0:01:59", "throughput": 1898.15, "total_tokens": 54720} |
| {"current_steps": 180, "total_steps": 900, "loss": 0.0381, "lr": 4.8525301950144894e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:00:29", "remaining_time": "0:01:58", "throughput": 1902.52, "total_tokens": 56256} |
| {"current_steps": 180, "total_steps": 900, "eval_loss": 0.032618820667266846, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:00:30", "remaining_time": "0:02:00", "throughput": 1865.69, "total_tokens": 56256} |
| {"current_steps": 185, "total_steps": 900, "loss": 0.0241, "lr": 4.835684093348244e-05, "epoch": 2.0555555555555554, "percentage": 20.56, "elapsed_time": "0:00:31", "remaining_time": "0:02:02", "throughput": 1825.21, "total_tokens": 57856} |
| {"current_steps": 190, "total_steps": 900, "loss": 0.013, "lr": 4.817959636416969e-05, "epoch": 2.111111111111111, "percentage": 21.11, "elapsed_time": "0:00:32", "remaining_time": "0:02:01", "throughput": 1835.93, "total_tokens": 59456} |
| {"current_steps": 195, "total_steps": 900, "loss": 0.1312, "lr": 4.7993634896640394e-05, "epoch": 2.1666666666666665, "percentage": 21.67, "elapsed_time": "0:00:33", "remaining_time": "0:01:59", "throughput": 1845.22, "total_tokens": 61024} |
| {"current_steps": 200, "total_steps": 900, "loss": 0.0123, "lr": 4.779902646339722e-05, "epoch": 2.2222222222222223, "percentage": 22.22, "elapsed_time": "0:00:33", "remaining_time": "0:01:58", "throughput": 1854.29, "total_tokens": 62592} |
| {"current_steps": 205, "total_steps": 900, "loss": 0.0644, "lr": 4.759584424871302e-05, "epoch": 2.2777777777777777, "percentage": 22.78, "elapsed_time": "0:00:34", "remaining_time": "0:01:56", "throughput": 1862.09, "total_tokens": 64128} |
| {"current_steps": 210, "total_steps": 900, "loss": 0.131, "lr": 4.7384164661109176e-05, "epoch": 2.3333333333333335, "percentage": 23.33, "elapsed_time": "0:00:35", "remaining_time": "0:01:55", "throughput": 1870.39, "total_tokens": 65696} |
| {"current_steps": 215, "total_steps": 900, "loss": 0.1218, "lr": 4.7164067304621536e-05, "epoch": 2.388888888888889, "percentage": 23.89, "elapsed_time": "0:00:35", "remaining_time": "0:01:54", "throughput": 1876.72, "total_tokens": 67200} |
| {"current_steps": 220, "total_steps": 900, "loss": 0.1623, "lr": 4.693563494886455e-05, "epoch": 2.4444444444444446, "percentage": 24.44, "elapsed_time": "0:00:36", "remaining_time": "0:01:52", "throughput": 1885.61, "total_tokens": 68800} |
| {"current_steps": 225, "total_steps": 900, "loss": 0.1683, "lr": 4.669895349790502e-05, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:00:37", "remaining_time": "0:01:51", "throughput": 1893.3, "total_tokens": 70368} |
| {"current_steps": 225, "total_steps": 900, "eval_loss": 0.031709086149930954, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:00:37", "remaining_time": "0:01:53", "throughput": 1864.1, "total_tokens": 70368} |
| {"current_steps": 230, "total_steps": 900, "loss": 0.0607, "lr": 4.645411195795709e-05, "epoch": 2.5555555555555554, "percentage": 25.56, "elapsed_time": "0:00:39", "remaining_time": "0:01:54", "throughput": 1830.87, "total_tokens": 71872} |
| {"current_steps": 235, "total_steps": 900, "loss": 0.1372, "lr": 4.620120240391065e-05, "epoch": 2.611111111111111, "percentage": 26.11, "elapsed_time": "0:00:39", "remaining_time": "0:01:53", "throughput": 1839.75, "total_tokens": 73472} |
| {"current_steps": 240, "total_steps": 900, "loss": 0.02, "lr": 4.5940319944705736e-05, "epoch": 2.6666666666666665, "percentage": 26.67, "elapsed_time": "0:00:40", "remaining_time": "0:01:51", "throughput": 1847.18, "total_tokens": 75040} |
| {"current_steps": 245, "total_steps": 900, "loss": 0.0076, "lr": 4.567156268756594e-05, "epoch": 2.7222222222222223, "percentage": 27.22, "elapsed_time": "0:00:41", "remaining_time": "0:01:50", "throughput": 1852.86, "total_tokens": 76544} |
| {"current_steps": 250, "total_steps": 900, "loss": 0.0331, "lr": 4.539503170110431e-05, "epoch": 2.7777777777777777, "percentage": 27.78, "elapsed_time": "0:00:41", "remaining_time": "0:01:49", "throughput": 1858.54, "total_tokens": 78048} |
| {"current_steps": 255, "total_steps": 900, "loss": 0.009, "lr": 4.5110830977315556e-05, "epoch": 2.8333333333333335, "percentage": 28.33, "elapsed_time": "0:00:42", "remaining_time": "0:01:47", "throughput": 1867.08, "total_tokens": 79680} |
| {"current_steps": 260, "total_steps": 900, "loss": 0.0115, "lr": 4.4819067392468944e-05, "epoch": 2.888888888888889, "percentage": 28.89, "elapsed_time": "0:00:43", "remaining_time": "0:01:46", "throughput": 1872.35, "total_tokens": 81184} |
| {"current_steps": 265, "total_steps": 900, "loss": 0.0921, "lr": 4.4519850666916484e-05, "epoch": 2.9444444444444446, "percentage": 29.44, "elapsed_time": "0:00:44", "remaining_time": "0:01:45", "throughput": 1880.07, "total_tokens": 82784} |
| {"current_steps": 270, "total_steps": 900, "loss": 0.0061, "lr": 4.4213293323831585e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:00:44", "remaining_time": "0:01:44", "throughput": 1883.11, "total_tokens": 84320} |
| {"current_steps": 270, "total_steps": 900, "eval_loss": 0.029622137546539307, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:00:45", "remaining_time": "0:01:45", "throughput": 1859.1, "total_tokens": 84320} |
| {"current_steps": 275, "total_steps": 900, "loss": 0.1157, "lr": 4.38995106468937e-05, "epoch": 3.0555555555555554, "percentage": 30.56, "elapsed_time": "0:00:46", "remaining_time": "0:01:46", "throughput": 1830.36, "total_tokens": 85920} |
| {"current_steps": 280, "total_steps": 900, "loss": 0.0063, "lr": 4.357862063693486e-05, "epoch": 3.111111111111111, "percentage": 31.11, "elapsed_time": "0:00:47", "remaining_time": "0:01:45", "throughput": 1836.17, "total_tokens": 87456} |
| {"current_steps": 285, "total_steps": 900, "loss": 0.083, "lr": 4.325074396756437e-05, "epoch": 3.1666666666666665, "percentage": 31.67, "elapsed_time": "0:00:48", "remaining_time": "0:01:44", "throughput": 1843.02, "total_tokens": 89056} |
| {"current_steps": 290, "total_steps": 900, "loss": 0.0139, "lr": 4.2916003939788403e-05, "epoch": 3.2222222222222223, "percentage": 32.22, "elapsed_time": "0:00:49", "remaining_time": "0:01:43", "throughput": 1847.93, "total_tokens": 90560} |
| {"current_steps": 295, "total_steps": 900, "loss": 0.0744, "lr": 4.257452643564155e-05, "epoch": 3.2777777777777777, "percentage": 32.78, "elapsed_time": "0:00:49", "remaining_time": "0:01:41", "throughput": 1854.04, "total_tokens": 92128} |
| {"current_steps": 300, "total_steps": 900, "loss": 0.0363, "lr": 4.22264398708477e-05, "epoch": 3.3333333333333335, "percentage": 33.33, "elapsed_time": "0:00:50", "remaining_time": "0:01:40", "throughput": 1860.66, "total_tokens": 93728} |
| {"current_steps": 305, "total_steps": 900, "loss": 0.0177, "lr": 4.1871875146528195e-05, "epoch": 3.388888888888889, "percentage": 33.89, "elapsed_time": "0:00:51", "remaining_time": "0:01:39", "throughput": 1865.75, "total_tokens": 95264} |
| {"current_steps": 310, "total_steps": 900, "loss": 0.0447, "lr": 4.1510965599975196e-05, "epoch": 3.4444444444444446, "percentage": 34.44, "elapsed_time": "0:00:51", "remaining_time": "0:01:38", "throughput": 1870.17, "total_tokens": 96768} |
| {"current_steps": 315, "total_steps": 900, "loss": 0.0759, "lr": 4.114384695450906e-05, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:00:52", "remaining_time": "0:01:37", "throughput": 1876.97, "total_tokens": 98400} |
| {"current_steps": 315, "total_steps": 900, "eval_loss": 0.029490336775779724, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:00:53", "remaining_time": "0:01:38", "throughput": 1856.28, "total_tokens": 98400} |
| {"current_steps": 320, "total_steps": 900, "loss": 0.01, "lr": 4.077065726843828e-05, "epoch": 3.5555555555555554, "percentage": 35.56, "elapsed_time": "0:00:54", "remaining_time": "0:01:38", "throughput": 1834.63, "total_tokens": 99968} |
| {"current_steps": 325, "total_steps": 900, "loss": 0.0902, "lr": 4.039153688314145e-05, "epoch": 3.611111111111111, "percentage": 36.11, "elapsed_time": "0:00:55", "remaining_time": "0:01:37", "throughput": 1839.68, "total_tokens": 101504} |
| {"current_steps": 330, "total_steps": 900, "loss": 0.1016, "lr": 4.000662837029062e-05, "epoch": 3.6666666666666665, "percentage": 36.67, "elapsed_time": "0:00:55", "remaining_time": "0:01:36", "throughput": 1844.01, "total_tokens": 103008} |
| {"current_steps": 335, "total_steps": 900, "loss": 0.0392, "lr": 3.961607647823583e-05, "epoch": 3.7222222222222223, "percentage": 37.22, "elapsed_time": "0:00:56", "remaining_time": "0:01:35", "throughput": 1850.06, "total_tokens": 104608} |
| {"current_steps": 340, "total_steps": 900, "loss": 0.0477, "lr": 3.9220028077571295e-05, "epoch": 3.7777777777777777, "percentage": 37.78, "elapsed_time": "0:00:57", "remaining_time": "0:01:34", "throughput": 1854.71, "total_tokens": 106144} |
| {"current_steps": 345, "total_steps": 900, "loss": 0.0014, "lr": 3.881863210590332e-05, "epoch": 3.8333333333333335, "percentage": 38.33, "elapsed_time": "0:00:57", "remaining_time": "0:01:33", "throughput": 1860.46, "total_tokens": 107744} |
| {"current_steps": 350, "total_steps": 900, "loss": 0.0585, "lr": 3.841203951184095e-05, "epoch": 3.888888888888889, "percentage": 38.89, "elapsed_time": "0:00:58", "remaining_time": "0:01:32", "throughput": 1865.03, "total_tokens": 109280} |
| {"current_steps": 355, "total_steps": 900, "loss": 0.0802, "lr": 3.8000403198230387e-05, "epoch": 3.9444444444444446, "percentage": 39.44, "elapsed_time": "0:00:59", "remaining_time": "0:01:30", "throughput": 1870.32, "total_tokens": 110848} |
| {"current_steps": 360, "total_steps": 900, "loss": 0.0138, "lr": 3.75838779646545e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:01:00", "remaining_time": "0:01:30", "throughput": 1873.22, "total_tokens": 112416} |
| {"current_steps": 360, "total_steps": 900, "eval_loss": 0.02838282845914364, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:01:00", "remaining_time": "0:01:30", "throughput": 1855.39, "total_tokens": 112416} |
| {"current_steps": 365, "total_steps": 900, "loss": 0.0193, "lr": 3.7162620449219e-05, "epoch": 4.055555555555555, "percentage": 40.56, "elapsed_time": "0:01:02", "remaining_time": "0:01:31", "throughput": 1833.65, "total_tokens": 113984} |
| {"current_steps": 370, "total_steps": 900, "loss": 0.0681, "lr": 3.673678906964727e-05, "epoch": 4.111111111111111, "percentage": 41.11, "elapsed_time": "0:01:02", "remaining_time": "0:01:30", "throughput": 1838.41, "total_tokens": 115552} |
| {"current_steps": 375, "total_steps": 900, "loss": 0.0069, "lr": 3.630654396370594e-05, "epoch": 4.166666666666667, "percentage": 41.67, "elapsed_time": "0:01:03", "remaining_time": "0:01:28", "throughput": 1843.79, "total_tokens": 117152} |
| {"current_steps": 380, "total_steps": 900, "loss": 0.0966, "lr": 3.5872046928983626e-05, "epoch": 4.222222222222222, "percentage": 42.22, "elapsed_time": "0:01:04", "remaining_time": "0:01:27", "throughput": 1849.61, "total_tokens": 118784} |
| {"current_steps": 385, "total_steps": 900, "loss": 0.0624, "lr": 3.543346136204545e-05, "epoch": 4.277777777777778, "percentage": 42.78, "elapsed_time": "0:01:04", "remaining_time": "0:01:26", "throughput": 1852.76, "total_tokens": 120256} |
| {"current_steps": 390, "total_steps": 900, "loss": 0.0117, "lr": 3.499095219698631e-05, "epoch": 4.333333333333333, "percentage": 43.33, "elapsed_time": "0:01:05", "remaining_time": "0:01:25", "throughput": 1857.36, "total_tokens": 121824} |
| {"current_steps": 395, "total_steps": 900, "loss": 0.0314, "lr": 3.454468584340588e-05, "epoch": 4.388888888888889, "percentage": 43.89, "elapsed_time": "0:01:06", "remaining_time": "0:01:24", "throughput": 1861.85, "total_tokens": 123392} |
| {"current_steps": 400, "total_steps": 900, "loss": 0.0537, "lr": 3.409483012382879e-05, "epoch": 4.444444444444445, "percentage": 44.44, "elapsed_time": "0:01:06", "remaining_time": "0:01:23", "throughput": 1865.79, "total_tokens": 124928} |
| {"current_steps": 405, "total_steps": 900, "loss": 0.1811, "lr": 3.364155421059342e-05, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:01:07", "remaining_time": "0:01:22", "throughput": 1870.12, "total_tokens": 126496} |
| {"current_steps": 405, "total_steps": 900, "eval_loss": 0.02925872430205345, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:01:08", "remaining_time": "0:01:23", "throughput": 1854.35, "total_tokens": 126496} |
| {"current_steps": 410, "total_steps": 900, "loss": 0.0061, "lr": 3.318502856223311e-05, "epoch": 4.555555555555555, "percentage": 45.56, "elapsed_time": "0:01:09", "remaining_time": "0:01:23", "throughput": 1838.33, "total_tokens": 128064} |
| {"current_steps": 415, "total_steps": 900, "loss": 0.0036, "lr": 3.272542485937369e-05, "epoch": 4.611111111111111, "percentage": 46.11, "elapsed_time": "0:01:10", "remaining_time": "0:01:22", "throughput": 1842.72, "total_tokens": 129632} |
| {"current_steps": 420, "total_steps": 900, "loss": 0.0139, "lr": 3.2262915940171376e-05, "epoch": 4.666666666666667, "percentage": 46.67, "elapsed_time": "0:01:11", "remaining_time": "0:01:21", "throughput": 1846.76, "total_tokens": 131200} |
| {"current_steps": 425, "total_steps": 900, "loss": 0.0279, "lr": 3.1797675735315455e-05, "epoch": 4.722222222222222, "percentage": 47.22, "elapsed_time": "0:01:11", "remaining_time": "0:01:20", "throughput": 1851.22, "total_tokens": 132800} |
| {"current_steps": 430, "total_steps": 900, "loss": 0.0395, "lr": 3.132987920262005e-05, "epoch": 4.777777777777778, "percentage": 47.78, "elapsed_time": "0:01:12", "remaining_time": "0:01:19", "throughput": 1854.92, "total_tokens": 134336} |
| {"current_steps": 435, "total_steps": 900, "loss": 0.0727, "lr": 3.085970226122962e-05, "epoch": 4.833333333333333, "percentage": 48.33, "elapsed_time": "0:01:13", "remaining_time": "0:01:18", "throughput": 1859.07, "total_tokens": 135904} |
| {"current_steps": 440, "total_steps": 900, "loss": 0.0065, "lr": 3.0387321725463e-05, "epoch": 4.888888888888889, "percentage": 48.89, "elapsed_time": "0:01:13", "remaining_time": "0:01:17", "throughput": 1863.56, "total_tokens": 137504} |
| {"current_steps": 445, "total_steps": 900, "loss": 0.0197, "lr": 2.9912915238320754e-05, "epoch": 4.944444444444445, "percentage": 49.44, "elapsed_time": "0:01:14", "remaining_time": "0:01:16", "throughput": 1867.35, "total_tokens": 139040} |
| {"current_steps": 450, "total_steps": 900, "loss": 0.0018, "lr": 2.9436661204680882e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:15", "remaining_time": "0:01:15", "throughput": 1868.79, "total_tokens": 140544} |
| {"current_steps": 450, "total_steps": 900, "eval_loss": 0.029911955818533897, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:15", "remaining_time": "0:01:15", "throughput": 1854.47, "total_tokens": 140544} |
| {"current_steps": 455, "total_steps": 900, "loss": 0.1312, "lr": 2.8958738724208072e-05, "epoch": 5.055555555555555, "percentage": 50.56, "elapsed_time": "0:01:17", "remaining_time": "0:01:16", "throughput": 1826.8, "total_tokens": 142176} |
| {"current_steps": 460, "total_steps": 900, "loss": 0.0019, "lr": 2.8479327524001636e-05, "epoch": 5.111111111111111, "percentage": 51.11, "elapsed_time": "0:01:18", "remaining_time": "0:01:15", "throughput": 1831.23, "total_tokens": 143776} |
| {"current_steps": 465, "total_steps": 900, "loss": 0.0701, "lr": 2.7998607891007495e-05, "epoch": 5.166666666666667, "percentage": 51.67, "elapsed_time": "0:01:19", "remaining_time": "0:01:14", "throughput": 1834.69, "total_tokens": 145312} |
| {"current_steps": 470, "total_steps": 900, "loss": 0.0525, "lr": 2.7516760604219617e-05, "epoch": 5.222222222222222, "percentage": 52.22, "elapsed_time": "0:01:19", "remaining_time": "0:01:13", "throughput": 1838.64, "total_tokens": 146880} |
| {"current_steps": 475, "total_steps": 900, "loss": 0.0334, "lr": 2.7033966866696457e-05, "epoch": 5.277777777777778, "percentage": 52.78, "elapsed_time": "0:01:20", "remaining_time": "0:01:12", "throughput": 1842.14, "total_tokens": 148416} |
| {"current_steps": 480, "total_steps": 900, "loss": 0.0048, "lr": 2.6550408237417885e-05, "epoch": 5.333333333333333, "percentage": 53.33, "elapsed_time": "0:01:21", "remaining_time": "0:01:11", "throughput": 1845.48, "total_tokens": 149952} |
| {"current_steps": 485, "total_steps": 900, "loss": 0.005, "lr": 2.6066266563008267e-05, "epoch": 5.388888888888889, "percentage": 53.89, "elapsed_time": "0:01:21", "remaining_time": "0:01:10", "throughput": 1848.92, "total_tokens": 151488} |
| {"current_steps": 490, "total_steps": 900, "loss": 0.0093, "lr": 2.5581723909351406e-05, "epoch": 5.444444444444445, "percentage": 54.44, "elapsed_time": "0:01:22", "remaining_time": "0:01:09", "throughput": 1852.32, "total_tokens": 153024} |
| {"current_steps": 495, "total_steps": 900, "loss": 0.0038, "lr": 2.5096962493123012e-05, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:01:23", "remaining_time": "0:01:08", "throughput": 1855.93, "total_tokens": 154592} |
| {"current_steps": 495, "total_steps": 900, "eval_loss": 0.02898368611931801, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:01:23", "remaining_time": "0:01:08", "throughput": 1843.11, "total_tokens": 154592} |
| {"current_steps": 500, "total_steps": 900, "loss": 0.0182, "lr": 2.461216461326642e-05, "epoch": 5.555555555555555, "percentage": 55.56, "elapsed_time": "0:01:25", "remaining_time": "0:01:08", "throughput": 1829.17, "total_tokens": 156128} |
| {"current_steps": 505, "total_steps": 900, "loss": 0.0174, "lr": 2.4127512582437485e-05, "epoch": 5.611111111111111, "percentage": 56.11, "elapsed_time": "0:01:26", "remaining_time": "0:01:07", "throughput": 1833.14, "total_tokens": 157728} |
| {"current_steps": 510, "total_steps": 900, "loss": 0.052, "lr": 2.364318865844416e-05, "epoch": 5.666666666666667, "percentage": 56.67, "elapsed_time": "0:01:26", "remaining_time": "0:01:06", "throughput": 1836.7, "total_tokens": 159296} |
| {"current_steps": 515, "total_steps": 900, "loss": 0.0192, "lr": 2.3159374975706884e-05, "epoch": 5.722222222222222, "percentage": 57.22, "elapsed_time": "0:01:27", "remaining_time": "0:01:05", "throughput": 1840.65, "total_tokens": 160896} |
| {"current_steps": 520, "total_steps": 900, "loss": 0.0064, "lr": 2.2676253476765196e-05, "epoch": 5.777777777777778, "percentage": 57.78, "elapsed_time": "0:01:28", "remaining_time": "0:01:04", "throughput": 1843.37, "total_tokens": 162400} |
| {"current_steps": 525, "total_steps": 900, "loss": 0.0016, "lr": 2.2194005843856636e-05, "epoch": 5.833333333333333, "percentage": 58.33, "elapsed_time": "0:01:28", "remaining_time": "0:01:03", "throughput": 1846.85, "total_tokens": 163968} |
| {"current_steps": 530, "total_steps": 900, "loss": 0.0593, "lr": 2.1712813430593436e-05, "epoch": 5.888888888888889, "percentage": 58.89, "elapsed_time": "0:01:29", "remaining_time": "0:01:02", "throughput": 1850.28, "total_tokens": 165536} |
| {"current_steps": 535, "total_steps": 900, "loss": 0.1051, "lr": 2.1232857193762924e-05, "epoch": 5.944444444444445, "percentage": 59.44, "elapsed_time": "0:01:30", "remaining_time": "0:01:01", "throughput": 1854.6, "total_tokens": 167168} |
| {"current_steps": 540, "total_steps": 900, "loss": 0.0004, "lr": 2.0754317625276983e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:01:30", "remaining_time": "0:01:00", "throughput": 1857.06, "total_tokens": 168768} |
| {"current_steps": 540, "total_steps": 900, "eval_loss": 0.028095781803131104, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:01:31", "remaining_time": "0:01:00", "throughput": 1845.23, "total_tokens": 168768} |
| {"current_steps": 545, "total_steps": 900, "loss": 0.03, "lr": 2.02773746842965e-05, "epoch": 6.055555555555555, "percentage": 60.56, "elapsed_time": "0:01:33", "remaining_time": "0:01:00", "throughput": 1830.54, "total_tokens": 170336} |
| {"current_steps": 550, "total_steps": 900, "loss": 0.0013, "lr": 1.980220772955602e-05, "epoch": 6.111111111111111, "percentage": 61.11, "elapsed_time": "0:01:33", "remaining_time": "0:00:59", "throughput": 1833.79, "total_tokens": 171904} |
| {"current_steps": 555, "total_steps": 900, "loss": 0.0028, "lr": 1.932899545191433e-05, "epoch": 6.166666666666667, "percentage": 61.67, "elapsed_time": "0:01:34", "remaining_time": "0:00:58", "throughput": 1836.75, "total_tokens": 173440} |
| {"current_steps": 560, "total_steps": 900, "loss": 0.0017, "lr": 1.8857915807156092e-05, "epoch": 6.222222222222222, "percentage": 62.22, "elapsed_time": "0:01:35", "remaining_time": "0:00:57", "throughput": 1839.68, "total_tokens": 174976} |
| {"current_steps": 565, "total_steps": 900, "loss": 0.1433, "lr": 1.838914594906995e-05, "epoch": 6.277777777777778, "percentage": 62.78, "elapsed_time": "0:01:35", "remaining_time": "0:00:56", "throughput": 1843.58, "total_tokens": 176608} |
| {"current_steps": 570, "total_steps": 900, "loss": 0.0162, "lr": 1.792286216282824e-05, "epoch": 6.333333333333333, "percentage": 63.33, "elapsed_time": "0:01:36", "remaining_time": "0:00:55", "throughput": 1846.43, "total_tokens": 178144} |
| {"current_steps": 575, "total_steps": 900, "loss": 0.0043, "lr": 1.7459239798693364e-05, "epoch": 6.388888888888889, "percentage": 63.89, "elapsed_time": "0:01:37", "remaining_time": "0:00:54", "throughput": 1849.2, "total_tokens": 179680} |
| {"current_steps": 580, "total_steps": 900, "loss": 0.0163, "lr": 1.699845320607571e-05, "epoch": 6.444444444444445, "percentage": 64.44, "elapsed_time": "0:01:37", "remaining_time": "0:00:53", "throughput": 1852.15, "total_tokens": 181248} |
| {"current_steps": 585, "total_steps": 900, "loss": 0.0105, "lr": 1.6540675667967974e-05, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:01:38", "remaining_time": "0:00:53", "throughput": 1855.51, "total_tokens": 182848} |
| {"current_steps": 585, "total_steps": 900, "eval_loss": 0.027535680681467056, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:01:39", "remaining_time": "0:00:53", "throughput": 1844.57, "total_tokens": 182848} |
| {"current_steps": 590, "total_steps": 900, "loss": 0.0035, "lr": 1.60860793357805e-05, "epoch": 6.555555555555555, "percentage": 65.56, "elapsed_time": "0:01:40", "remaining_time": "0:00:52", "throughput": 1829.13, "total_tokens": 184352} |
| {"current_steps": 595, "total_steps": 900, "loss": 0.0055, "lr": 1.56348351646022e-05, "epoch": 6.611111111111111, "percentage": 66.11, "elapsed_time": "0:01:41", "remaining_time": "0:00:52", "throughput": 1832.53, "total_tokens": 185952} |
| {"current_steps": 600, "total_steps": 900, "loss": 0.0312, "lr": 1.5187112848911323e-05, "epoch": 6.666666666666667, "percentage": 66.67, "elapsed_time": "0:01:42", "remaining_time": "0:00:51", "throughput": 1835.26, "total_tokens": 187488} |
| {"current_steps": 605, "total_steps": 900, "loss": 0.0018, "lr": 1.47430807587603e-05, "epoch": 6.722222222222222, "percentage": 67.22, "elapsed_time": "0:01:42", "remaining_time": "0:00:50", "throughput": 1838.24, "total_tokens": 189056} |
| {"current_steps": 610, "total_steps": 900, "loss": 0.0615, "lr": 1.430290587645865e-05, "epoch": 6.777777777777778, "percentage": 67.78, "elapsed_time": "0:01:43", "remaining_time": "0:00:49", "throughput": 1840.95, "total_tokens": 190592} |
| {"current_steps": 615, "total_steps": 900, "loss": 0.0253, "lr": 1.3866753733777765e-05, "epoch": 6.833333333333333, "percentage": 68.33, "elapsed_time": "0:01:44", "remaining_time": "0:00:48", "throughput": 1844.24, "total_tokens": 192192} |
| {"current_steps": 620, "total_steps": 900, "loss": 0.1272, "lr": 1.343478834970121e-05, "epoch": 6.888888888888889, "percentage": 68.89, "elapsed_time": "0:01:44", "remaining_time": "0:00:47", "throughput": 1847.77, "total_tokens": 193824} |
| {"current_steps": 625, "total_steps": 900, "loss": 0.0013, "lr": 1.3007172168743854e-05, "epoch": 6.944444444444445, "percentage": 69.44, "elapsed_time": "0:01:45", "remaining_time": "0:00:46", "throughput": 1850.8, "total_tokens": 195392} |
| {"current_steps": 630, "total_steps": 900, "loss": 0.0076, "lr": 1.2584065999863102e-05, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:01:46", "remaining_time": "0:00:45", "throughput": 1852.03, "total_tokens": 196896} |
| {"current_steps": 630, "total_steps": 900, "eval_loss": 0.029028713703155518, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:01:46", "remaining_time": "0:00:45", "throughput": 1842.02, "total_tokens": 196896} |
| {"current_steps": 635, "total_steps": 900, "loss": 0.0959, "lr": 1.2165628955985314e-05, "epoch": 7.055555555555555, "percentage": 70.56, "elapsed_time": "0:01:48", "remaining_time": "0:00:45", "throughput": 1830.1, "total_tokens": 198496} |
| {"current_steps": 640, "total_steps": 900, "loss": 0.0011, "lr": 1.175201839416988e-05, "epoch": 7.111111111111111, "percentage": 71.11, "elapsed_time": "0:01:49", "remaining_time": "0:00:44", "throughput": 1832.87, "total_tokens": 200064} |
| {"current_steps": 645, "total_steps": 900, "loss": 0.0381, "lr": 1.1343389856433658e-05, "epoch": 7.166666666666667, "percentage": 71.67, "elapsed_time": "0:01:49", "remaining_time": "0:00:43", "throughput": 1835.43, "total_tokens": 201600} |
| {"current_steps": 650, "total_steps": 900, "loss": 0.0011, "lr": 1.0939897011258001e-05, "epoch": 7.222222222222222, "percentage": 72.22, "elapsed_time": "0:01:50", "remaining_time": "0:00:42", "throughput": 1838.24, "total_tokens": 203168} |
| {"current_steps": 655, "total_steps": 900, "loss": 0.0106, "lr": 1.0541691595800337e-05, "epoch": 7.277777777777778, "percentage": 72.78, "elapsed_time": "0:01:51", "remaining_time": "0:00:41", "throughput": 1840.75, "total_tokens": 204704} |
| {"current_steps": 660, "total_steps": 900, "loss": 0.0024, "lr": 1.0148923358832022e-05, "epoch": 7.333333333333333, "percentage": 73.33, "elapsed_time": "0:01:51", "remaining_time": "0:00:40", "throughput": 1843.52, "total_tokens": 206272} |
| {"current_steps": 665, "total_steps": 900, "loss": 0.0202, "lr": 9.761740004423927e-06, "epoch": 7.388888888888889, "percentage": 73.89, "elapsed_time": "0:01:52", "remaining_time": "0:00:39", "throughput": 1846.54, "total_tokens": 207872} |
| {"current_steps": 670, "total_steps": 900, "loss": 0.0163, "lr": 9.380287136401e-06, "epoch": 7.444444444444445, "percentage": 74.44, "elapsed_time": "0:01:53", "remaining_time": "0:00:38", "throughput": 1848.96, "total_tokens": 209408} |
| {"current_steps": 675, "total_steps": 900, "loss": 0.0572, "lr": 9.00470820358663e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:01:53", "remaining_time": "0:00:37", "throughput": 1851.06, "total_tokens": 210912} |
| {"current_steps": 675, "total_steps": 900, "eval_loss": 0.027888020500540733, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:01:54", "remaining_time": "0:00:38", "throughput": 1841.68, "total_tokens": 210912} |
| {"current_steps": 680, "total_steps": 900, "loss": 0.0223, "lr": 8.635144445857406e-06, "epoch": 7.555555555555555, "percentage": 75.56, "elapsed_time": "0:01:56", "remaining_time": "0:00:37", "throughput": 1831.63, "total_tokens": 212480} |
| {"current_steps": 685, "total_steps": 900, "loss": 0.0046, "lr": 8.271734841028553e-06, "epoch": 7.611111111111111, "percentage": 76.11, "elapsed_time": "0:01:56", "remaining_time": "0:00:36", "throughput": 1834.0, "total_tokens": 214016} |
| {"current_steps": 690, "total_steps": 900, "loss": 0.0081, "lr": 7.914616052590071e-06, "epoch": 7.666666666666667, "percentage": 76.67, "elapsed_time": "0:01:57", "remaining_time": "0:00:35", "throughput": 1836.65, "total_tokens": 215584} |
| {"current_steps": 695, "total_steps": 900, "loss": 0.0046, "lr": 7.563922378313218e-06, "epoch": 7.722222222222222, "percentage": 77.22, "elapsed_time": "0:01:58", "remaining_time": "0:00:34", "throughput": 1839.86, "total_tokens": 217216} |
| {"current_steps": 700, "total_steps": 900, "loss": 0.0443, "lr": 7.219785699746573e-06, "epoch": 7.777777777777778, "percentage": 77.78, "elapsed_time": "0:01:58", "remaining_time": "0:00:33", "throughput": 1842.22, "total_tokens": 218752} |
| {"current_steps": 705, "total_steps": 900, "loss": 0.0004, "lr": 6.882335432620779e-06, "epoch": 7.833333333333333, "percentage": 78.33, "elapsed_time": "0:01:59", "remaining_time": "0:00:33", "throughput": 1844.25, "total_tokens": 220256} |
| {"current_steps": 710, "total_steps": 900, "loss": 0.1015, "lr": 6.55169847818059e-06, "epoch": 7.888888888888889, "percentage": 78.89, "elapsed_time": "0:02:00", "remaining_time": "0:00:32", "throughput": 1846.51, "total_tokens": 221792} |
| {"current_steps": 715, "total_steps": 900, "loss": 0.0017, "lr": 6.22799917546252e-06, "epoch": 7.944444444444445, "percentage": 79.44, "elapsed_time": "0:02:00", "remaining_time": "0:00:31", "throughput": 1849.69, "total_tokens": 223424} |
| {"current_steps": 720, "total_steps": 900, "loss": 0.0018, "lr": 5.9113592545359945e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:02:01", "remaining_time": "0:00:30", "throughput": 1851.56, "total_tokens": 225024} |
| {"current_steps": 720, "total_steps": 900, "eval_loss": 0.030506333336234093, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:02:02", "remaining_time": "0:00:30", "throughput": 1842.79, "total_tokens": 225024} |
| {"current_steps": 725, "total_steps": 900, "loss": 0.0082, "lr": 5.601897790725643e-06, "epoch": 8.055555555555555, "percentage": 80.56, "elapsed_time": "0:02:03", "remaining_time": "0:00:29", "throughput": 1831.5, "total_tokens": 226560} |
| {"current_steps": 730, "total_steps": 900, "loss": 0.0047, "lr": 5.299731159831953e-06, "epoch": 8.11111111111111, "percentage": 81.11, "elapsed_time": "0:02:04", "remaining_time": "0:00:28", "throughput": 1833.98, "total_tokens": 228128} |
| {"current_steps": 735, "total_steps": 900, "loss": 0.0019, "lr": 5.004972994367102e-06, "epoch": 8.166666666666666, "percentage": 81.67, "elapsed_time": "0:02:05", "remaining_time": "0:00:28", "throughput": 1836.71, "total_tokens": 229728} |
| {"current_steps": 740, "total_steps": 900, "loss": 0.0031, "lr": 4.7177341408224e-06, "epoch": 8.222222222222221, "percentage": 82.22, "elapsed_time": "0:02:05", "remaining_time": "0:00:27", "throughput": 1839.38, "total_tokens": 231328} |
| {"current_steps": 745, "total_steps": 900, "loss": 0.0263, "lr": 4.438122617983443e-06, "epoch": 8.277777777777779, "percentage": 82.78, "elapsed_time": "0:02:06", "remaining_time": "0:00:26", "throughput": 1841.83, "total_tokens": 232896} |
| {"current_steps": 750, "total_steps": 900, "loss": 0.0936, "lr": 4.166243576308712e-06, "epoch": 8.333333333333334, "percentage": 83.33, "elapsed_time": "0:02:07", "remaining_time": "0:00:25", "throughput": 1844.49, "total_tokens": 234496} |
| {"current_steps": 755, "total_steps": 900, "loss": 0.033, "lr": 3.9021992583867325e-06, "epoch": 8.38888888888889, "percentage": 83.89, "elapsed_time": "0:02:07", "remaining_time": "0:00:24", "throughput": 1846.88, "total_tokens": 236064} |
| {"current_steps": 760, "total_steps": 900, "loss": 0.0046, "lr": 3.6460889604868626e-06, "epoch": 8.444444444444445, "percentage": 84.44, "elapsed_time": "0:02:08", "remaining_time": "0:00:23", "throughput": 1849.26, "total_tokens": 237632} |
| {"current_steps": 765, "total_steps": 900, "loss": 0.0037, "lr": 3.398008995217988e-06, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:02:09", "remaining_time": "0:00:22", "throughput": 1851.61, "total_tokens": 239200} |
| {"current_steps": 765, "total_steps": 900, "eval_loss": 0.029731493443250656, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:02:09", "remaining_time": "0:00:22", "throughput": 1843.2, "total_tokens": 239200} |
| {"current_steps": 770, "total_steps": 900, "loss": 0.0087, "lr": 3.158052655309332e-06, "epoch": 8.555555555555555, "percentage": 85.56, "elapsed_time": "0:02:11", "remaining_time": "0:00:22", "throughput": 1835.03, "total_tokens": 240832} |
| {"current_steps": 775, "total_steps": 900, "loss": 0.0585, "lr": 2.9263101785268254e-06, "epoch": 8.61111111111111, "percentage": 86.11, "elapsed_time": "0:02:11", "remaining_time": "0:00:21", "throughput": 1836.56, "total_tokens": 242304} |
| {"current_steps": 780, "total_steps": 900, "loss": 0.0041, "lr": 2.7028687137384267e-06, "epoch": 8.666666666666666, "percentage": 86.67, "elapsed_time": "0:02:12", "remaining_time": "0:00:20", "throughput": 1838.64, "total_tokens": 243840} |
| {"current_steps": 785, "total_steps": 900, "loss": 0.0021, "lr": 2.487812288140945e-06, "epoch": 8.722222222222221, "percentage": 87.22, "elapsed_time": "0:02:13", "remaining_time": "0:00:19", "throughput": 1840.72, "total_tokens": 245376} |
| {"current_steps": 790, "total_steps": 900, "loss": 0.0037, "lr": 2.281221775660894e-06, "epoch": 8.777777777777779, "percentage": 87.78, "elapsed_time": "0:02:13", "remaining_time": "0:00:18", "throughput": 1842.55, "total_tokens": 246880} |
| {"current_steps": 795, "total_steps": 900, "loss": 0.0538, "lr": 2.0831748665410765e-06, "epoch": 8.833333333333334, "percentage": 88.33, "elapsed_time": "0:02:14", "remaining_time": "0:00:17", "throughput": 1844.84, "total_tokens": 248448} |
| {"current_steps": 800, "total_steps": 900, "loss": 0.0024, "lr": 1.893746038124497e-06, "epoch": 8.88888888888889, "percentage": 88.89, "elapsed_time": "0:02:15", "remaining_time": "0:00:16", "throughput": 1847.06, "total_tokens": 250016} |
| {"current_steps": 805, "total_steps": 900, "loss": 0.0487, "lr": 1.713006526846439e-06, "epoch": 8.944444444444445, "percentage": 89.44, "elapsed_time": "0:02:16", "remaining_time": "0:00:16", "throughput": 1849.45, "total_tokens": 251584} |
| {"current_steps": 810, "total_steps": 900, "loss": 0.0221, "lr": 1.541024301445404e-06, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:02:16", "remaining_time": "0:00:15", "throughput": 1850.86, "total_tokens": 253152} |
| {"current_steps": 810, "total_steps": 900, "eval_loss": 0.027674119919538498, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:02:17", "remaining_time": "0:00:15", "throughput": 1843.13, "total_tokens": 253152} |
| {"current_steps": 815, "total_steps": 900, "loss": 0.0014, "lr": 1.3778640374027985e-06, "epoch": 9.055555555555555, "percentage": 90.56, "elapsed_time": "0:02:18", "remaining_time": "0:00:14", "throughput": 1833.81, "total_tokens": 254720} |
| {"current_steps": 820, "total_steps": 900, "loss": 0.0294, "lr": 1.2235870926211619e-06, "epoch": 9.11111111111111, "percentage": 91.11, "elapsed_time": "0:02:19", "remaining_time": "0:00:13", "throughput": 1835.95, "total_tokens": 256288} |
| {"current_steps": 825, "total_steps": 900, "loss": 0.0603, "lr": 1.0782514843499653e-06, "epoch": 9.166666666666666, "percentage": 91.67, "elapsed_time": "0:02:20", "remaining_time": "0:00:12", "throughput": 1837.92, "total_tokens": 257824} |
| {"current_steps": 830, "total_steps": 900, "loss": 0.002, "lr": 9.419118673676924e-07, "epoch": 9.222222222222221, "percentage": 92.22, "elapsed_time": "0:02:20", "remaining_time": "0:00:11", "throughput": 1840.16, "total_tokens": 259392} |
| {"current_steps": 835, "total_steps": 900, "loss": 0.0121, "lr": 8.146195134284052e-07, "epoch": 9.277777777777779, "percentage": 92.78, "elapsed_time": "0:02:21", "remaining_time": "0:00:11", "throughput": 1841.93, "total_tokens": 260896} |
| {"current_steps": 840, "total_steps": 900, "loss": 0.0013, "lr": 6.964222919805391e-07, "epoch": 9.333333333333334, "percentage": 93.33, "elapsed_time": "0:02:22", "remaining_time": "0:00:10", "throughput": 1844.14, "total_tokens": 262464} |
| {"current_steps": 845, "total_steps": 900, "loss": 0.001, "lr": 5.87364652165176e-07, "epoch": 9.38888888888889, "percentage": 93.89, "elapsed_time": "0:02:23", "remaining_time": "0:00:09", "throughput": 1845.96, "total_tokens": 264000} |
| {"current_steps": 850, "total_steps": 900, "loss": 0.0017, "lr": 4.874876061005173e-07, "epoch": 9.444444444444445, "percentage": 94.44, "elapsed_time": "0:02:23", "remaining_time": "0:00:08", "throughput": 1847.87, "total_tokens": 265536} |
| {"current_steps": 855, "total_steps": 900, "loss": 0.0106, "lr": 3.9682871345891883e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:24", "remaining_time": "0:00:07", "throughput": 1849.55, "total_tokens": 267040} |
| {"current_steps": 855, "total_steps": 900, "eval_loss": 0.02903667651116848, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:24", "remaining_time": "0:00:07", "throughput": 1842.14, "total_tokens": 267040} |
| {"current_steps": 860, "total_steps": 900, "loss": 0.0706, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:02:26", "remaining_time": "0:00:06", "throughput": 1833.61, "total_tokens": 268576} |
| {"current_steps": 865, "total_steps": 900, "loss": 0.0009, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 1835.68, "total_tokens": 270144} |
| {"current_steps": 870, "total_steps": 900, "loss": 0.0007, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 1837.34, "total_tokens": 271648} |
| {"current_steps": 875, "total_steps": 900, "loss": 0.0035, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:02:28", "remaining_time": "0:00:04", "throughput": 1839.87, "total_tokens": 273280} |
| {"current_steps": 880, "total_steps": 900, "loss": 0.0642, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:02:29", "remaining_time": "0:00:03", "throughput": 1842.09, "total_tokens": 274880} |
| {"current_steps": 885, "total_steps": 900, "loss": 0.0019, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:02:29", "remaining_time": "0:00:02", "throughput": 1844.34, "total_tokens": 276480} |
| {"current_steps": 890, "total_steps": 900, "loss": 0.0369, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:02:30", "remaining_time": "0:00:01", "throughput": 1846.55, "total_tokens": 278080} |
| {"current_steps": 895, "total_steps": 900, "loss": 0.0096, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:02:31", "remaining_time": "0:00:00", "throughput": 1848.92, "total_tokens": 279680} |
| {"current_steps": 900, "total_steps": 900, "loss": 0.0802, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 1850.65, "total_tokens": 281312} |
| {"current_steps": 900, "total_steps": 900, "eval_loss": 0.028846707195043564, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 1843.61, "total_tokens": 281312} |
| {"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:33", "remaining_time": "0:00:00", "throughput": 1834.51, "total_tokens": 281312} |
|
|