train_copa_1757340252 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 900
aba061a verified
raw
history blame
47.3 kB
{"current_steps": 5, "total_steps": 900, "loss": 0.4024, "lr": 2.2222222222222225e-06, "epoch": 0.05555555555555555, "percentage": 0.56, "elapsed_time": "0:00:01", "remaining_time": "0:03:41", "throughput": 1320.08, "total_tokens": 1632}
{"current_steps": 10, "total_steps": 900, "loss": 0.4231, "lr": 5e-06, "epoch": 0.1111111111111111, "percentage": 1.11, "elapsed_time": "0:00:02", "remaining_time": "0:03:00", "throughput": 1593.59, "total_tokens": 3232}
{"current_steps": 15, "total_steps": 900, "loss": 0.3863, "lr": 7.777777777777777e-06, "epoch": 0.16666666666666666, "percentage": 1.67, "elapsed_time": "0:00:02", "remaining_time": "0:02:45", "throughput": 1717.97, "total_tokens": 4832}
{"current_steps": 20, "total_steps": 900, "loss": 0.3997, "lr": 1.0555555555555555e-05, "epoch": 0.2222222222222222, "percentage": 2.22, "elapsed_time": "0:00:03", "remaining_time": "0:02:38", "throughput": 1788.31, "total_tokens": 6432}
{"current_steps": 25, "total_steps": 900, "loss": 0.4838, "lr": 1.3333333333333333e-05, "epoch": 0.2777777777777778, "percentage": 2.78, "elapsed_time": "0:00:04", "remaining_time": "0:02:33", "throughput": 1819.57, "total_tokens": 7968}
{"current_steps": 30, "total_steps": 900, "loss": 0.2237, "lr": 1.6111111111111115e-05, "epoch": 0.3333333333333333, "percentage": 3.33, "elapsed_time": "0:00:05", "remaining_time": "0:02:29", "throughput": 1841.51, "total_tokens": 9504}
{"current_steps": 35, "total_steps": 900, "loss": 0.3549, "lr": 1.888888888888889e-05, "epoch": 0.3888888888888889, "percentage": 3.89, "elapsed_time": "0:00:05", "remaining_time": "0:02:27", "throughput": 1866.82, "total_tokens": 11104}
{"current_steps": 40, "total_steps": 900, "loss": 0.3508, "lr": 2.1666666666666667e-05, "epoch": 0.4444444444444444, "percentage": 4.44, "elapsed_time": "0:00:06", "remaining_time": "0:02:24", "throughput": 1885.83, "total_tokens": 12704}
{"current_steps": 45, "total_steps": 900, "loss": 0.2013, "lr": 2.4444444444444445e-05, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:07", "remaining_time": "0:02:22", "throughput": 1893.97, "total_tokens": 14240}
{"current_steps": 45, "total_steps": 900, "eval_loss": 0.10952243953943253, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:08", "remaining_time": "0:02:39", "throughput": 1694.5, "total_tokens": 14240}
{"current_steps": 50, "total_steps": 900, "loss": 0.1169, "lr": 2.7222222222222223e-05, "epoch": 0.5555555555555556, "percentage": 5.56, "elapsed_time": "0:00:09", "remaining_time": "0:02:48", "throughput": 1594.88, "total_tokens": 15808}
{"current_steps": 55, "total_steps": 900, "loss": 0.1551, "lr": 3e-05, "epoch": 0.6111111111111112, "percentage": 6.11, "elapsed_time": "0:00:10", "remaining_time": "0:02:45", "throughput": 1613.61, "total_tokens": 17344}
{"current_steps": 60, "total_steps": 900, "loss": 0.1888, "lr": 3.277777777777778e-05, "epoch": 0.6666666666666666, "percentage": 6.67, "elapsed_time": "0:00:11", "remaining_time": "0:02:41", "throughput": 1639.73, "total_tokens": 18912}
{"current_steps": 65, "total_steps": 900, "loss": 0.0352, "lr": 3.555555555555556e-05, "epoch": 0.7222222222222222, "percentage": 7.22, "elapsed_time": "0:00:12", "remaining_time": "0:02:38", "throughput": 1660.31, "total_tokens": 20448}
{"current_steps": 70, "total_steps": 900, "loss": 0.0902, "lr": 3.8333333333333334e-05, "epoch": 0.7777777777777778, "percentage": 7.78, "elapsed_time": "0:00:13", "remaining_time": "0:02:35", "throughput": 1677.83, "total_tokens": 21984}
{"current_steps": 75, "total_steps": 900, "loss": 0.2458, "lr": 4.111111111111111e-05, "epoch": 0.8333333333333334, "percentage": 8.33, "elapsed_time": "0:00:13", "remaining_time": "0:02:32", "throughput": 1695.12, "total_tokens": 23552}
{"current_steps": 80, "total_steps": 900, "loss": 0.1474, "lr": 4.388888888888889e-05, "epoch": 0.8888888888888888, "percentage": 8.89, "elapsed_time": "0:00:14", "remaining_time": "0:02:30", "throughput": 1711.08, "total_tokens": 25120}
{"current_steps": 85, "total_steps": 900, "loss": 0.0076, "lr": 4.666666666666667e-05, "epoch": 0.9444444444444444, "percentage": 9.44, "elapsed_time": "0:00:15", "remaining_time": "0:02:28", "throughput": 1723.65, "total_tokens": 26656}
{"current_steps": 90, "total_steps": 900, "loss": 0.2033, "lr": 4.9444444444444446e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:16", "remaining_time": "0:02:26", "throughput": 1729.05, "total_tokens": 28192}
{"current_steps": 90, "total_steps": 900, "eval_loss": 0.0884777307510376, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:17", "remaining_time": "0:02:34", "throughput": 1639.99, "total_tokens": 28192}
{"current_steps": 95, "total_steps": 900, "loss": 0.0233, "lr": 4.9996991493233693e-05, "epoch": 1.0555555555555556, "percentage": 10.56, "elapsed_time": "0:00:18", "remaining_time": "0:02:39", "throughput": 1580.89, "total_tokens": 29792}
{"current_steps": 100, "total_steps": 900, "loss": 0.1269, "lr": 4.99847706754774e-05, "epoch": 1.1111111111111112, "percentage": 11.11, "elapsed_time": "0:00:19", "remaining_time": "0:02:37", "throughput": 1596.3, "total_tokens": 31328}
{"current_steps": 105, "total_steps": 900, "loss": 0.1503, "lr": 4.9963154107272295e-05, "epoch": 1.1666666666666667, "percentage": 11.67, "elapsed_time": "0:00:20", "remaining_time": "0:02:34", "throughput": 1608.88, "total_tokens": 32832}
{"current_steps": 110, "total_steps": 900, "loss": 0.1197, "lr": 4.993214991772563e-05, "epoch": 1.2222222222222223, "percentage": 12.22, "elapsed_time": "0:00:21", "remaining_time": "0:02:32", "throughput": 1618.9, "total_tokens": 34304}
{"current_steps": 115, "total_steps": 900, "loss": 0.1919, "lr": 4.989176976624511e-05, "epoch": 1.2777777777777777, "percentage": 12.78, "elapsed_time": "0:00:21", "remaining_time": "0:02:29", "throughput": 1631.24, "total_tokens": 35840}
{"current_steps": 120, "total_steps": 900, "loss": 0.2774, "lr": 4.9842028838154285e-05, "epoch": 1.3333333333333333, "percentage": 13.33, "elapsed_time": "0:00:22", "remaining_time": "0:02:27", "throughput": 1642.55, "total_tokens": 37376}
{"current_steps": 125, "total_steps": 900, "loss": 0.0903, "lr": 4.978294583898196e-05, "epoch": 1.3888888888888888, "percentage": 13.89, "elapsed_time": "0:00:23", "remaining_time": "0:02:25", "throughput": 1654.26, "total_tokens": 38944}
{"current_steps": 130, "total_steps": 900, "loss": 0.0628, "lr": 4.971454298742779e-05, "epoch": 1.4444444444444444, "percentage": 14.44, "elapsed_time": "0:00:24", "remaining_time": "0:02:24", "throughput": 1665.34, "total_tokens": 40512}
{"current_steps": 135, "total_steps": 900, "loss": 0.0778, "lr": 4.963684600700679e-05, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:00:25", "remaining_time": "0:02:22", "throughput": 1674.92, "total_tokens": 42080}
{"current_steps": 135, "total_steps": 900, "eval_loss": 0.08602945506572723, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:00:26", "remaining_time": "0:02:27", "throughput": 1616.77, "total_tokens": 42080}
{"current_steps": 140, "total_steps": 900, "loss": 0.1892, "lr": 4.9549884116375714e-05, "epoch": 1.5555555555555556, "percentage": 15.56, "elapsed_time": "0:00:27", "remaining_time": "0:02:29", "throughput": 1587.53, "total_tokens": 43680}
{"current_steps": 145, "total_steps": 900, "loss": 0.0656, "lr": 4.9453690018345144e-05, "epoch": 1.6111111111111112, "percentage": 16.11, "elapsed_time": "0:00:28", "remaining_time": "0:02:27", "throughput": 1597.7, "total_tokens": 45216}
{"current_steps": 150, "total_steps": 900, "loss": 0.2171, "lr": 4.934829988758131e-05, "epoch": 1.6666666666666665, "percentage": 16.67, "elapsed_time": "0:00:29", "remaining_time": "0:02:25", "throughput": 1606.54, "total_tokens": 46720}
{"current_steps": 155, "total_steps": 900, "loss": 0.0409, "lr": 4.923375335700223e-05, "epoch": 1.7222222222222223, "percentage": 17.22, "elapsed_time": "0:00:29", "remaining_time": "0:02:23", "throughput": 1616.76, "total_tokens": 48288}
{"current_steps": 160, "total_steps": 900, "loss": 0.0579, "lr": 4.9110093502873476e-05, "epoch": 1.7777777777777777, "percentage": 17.78, "elapsed_time": "0:00:30", "remaining_time": "0:02:21", "throughput": 1627.07, "total_tokens": 49888}
{"current_steps": 165, "total_steps": 900, "loss": 0.046, "lr": 4.897736682860885e-05, "epoch": 1.8333333333333335, "percentage": 18.33, "elapsed_time": "0:00:31", "remaining_time": "0:02:20", "throughput": 1635.11, "total_tokens": 51424}
{"current_steps": 170, "total_steps": 900, "loss": 0.3298, "lr": 4.883562324728241e-05, "epoch": 1.8888888888888888, "percentage": 18.89, "elapsed_time": "0:00:32", "remaining_time": "0:02:18", "throughput": 1643.69, "total_tokens": 52992}
{"current_steps": 175, "total_steps": 900, "loss": 0.1784, "lr": 4.868491606285823e-05, "epoch": 1.9444444444444444, "percentage": 19.44, "elapsed_time": "0:00:33", "remaining_time": "0:02:16", "throughput": 1652.88, "total_tokens": 54592}
{"current_steps": 180, "total_steps": 900, "loss": 0.1119, "lr": 4.8525301950144894e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:00:33", "remaining_time": "0:02:15", "throughput": 1658.02, "total_tokens": 56192}
{"current_steps": 180, "total_steps": 900, "eval_loss": 0.07766027748584747, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:00:34", "remaining_time": "0:02:19", "throughput": 1615.4, "total_tokens": 56192}
{"current_steps": 185, "total_steps": 900, "loss": 0.027, "lr": 4.835684093348244e-05, "epoch": 2.0555555555555554, "percentage": 20.56, "elapsed_time": "0:00:36", "remaining_time": "0:02:21", "throughput": 1581.92, "total_tokens": 57760}
{"current_steps": 190, "total_steps": 900, "loss": 0.0803, "lr": 4.817959636416969e-05, "epoch": 2.111111111111111, "percentage": 21.11, "elapsed_time": "0:00:37", "remaining_time": "0:02:19", "throughput": 1589.03, "total_tokens": 59264}
{"current_steps": 195, "total_steps": 900, "loss": 0.1008, "lr": 4.7993634896640394e-05, "epoch": 2.1666666666666665, "percentage": 21.67, "elapsed_time": "0:00:38", "remaining_time": "0:02:17", "throughput": 1595.9, "total_tokens": 60768}
{"current_steps": 200, "total_steps": 900, "loss": 0.0914, "lr": 4.779902646339722e-05, "epoch": 2.2222222222222223, "percentage": 22.22, "elapsed_time": "0:00:38", "remaining_time": "0:02:16", "throughput": 1602.22, "total_tokens": 62272}
{"current_steps": 205, "total_steps": 900, "loss": 0.0525, "lr": 4.759584424871302e-05, "epoch": 2.2777777777777777, "percentage": 22.78, "elapsed_time": "0:00:39", "remaining_time": "0:02:14", "throughput": 1608.89, "total_tokens": 63808}
{"current_steps": 210, "total_steps": 900, "loss": 0.0866, "lr": 4.7384164661109176e-05, "epoch": 2.3333333333333335, "percentage": 23.33, "elapsed_time": "0:00:40", "remaining_time": "0:02:12", "throughput": 1615.63, "total_tokens": 65344}
{"current_steps": 215, "total_steps": 900, "loss": 0.006, "lr": 4.7164067304621536e-05, "epoch": 2.388888888888889, "percentage": 23.89, "elapsed_time": "0:00:41", "remaining_time": "0:02:11", "throughput": 1622.71, "total_tokens": 66912}
{"current_steps": 220, "total_steps": 900, "loss": 0.2276, "lr": 4.693563494886455e-05, "epoch": 2.4444444444444446, "percentage": 24.44, "elapsed_time": "0:00:42", "remaining_time": "0:02:09", "throughput": 1629.51, "total_tokens": 68480}
{"current_steps": 225, "total_steps": 900, "loss": 0.0346, "lr": 4.669895349790502e-05, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:00:42", "remaining_time": "0:02:08", "throughput": 1636.16, "total_tokens": 70048}
{"current_steps": 225, "total_steps": 900, "eval_loss": 0.08226585388183594, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:00:43", "remaining_time": "0:02:11", "throughput": 1602.67, "total_tokens": 70048}
{"current_steps": 230, "total_steps": 900, "loss": 0.0039, "lr": 4.645411195795709e-05, "epoch": 2.5555555555555554, "percentage": 25.56, "elapsed_time": "0:00:45", "remaining_time": "0:02:11", "throughput": 1584.87, "total_tokens": 71680}
{"current_steps": 235, "total_steps": 900, "loss": 0.3201, "lr": 4.620120240391065e-05, "epoch": 2.611111111111111, "percentage": 26.11, "elapsed_time": "0:00:46", "remaining_time": "0:02:10", "throughput": 1592.34, "total_tokens": 73280}
{"current_steps": 240, "total_steps": 900, "loss": 0.005, "lr": 4.5940319944705736e-05, "epoch": 2.6666666666666665, "percentage": 26.67, "elapsed_time": "0:00:46", "remaining_time": "0:02:08", "throughput": 1597.04, "total_tokens": 74752}
{"current_steps": 245, "total_steps": 900, "loss": 0.1967, "lr": 4.567156268756594e-05, "epoch": 2.7222222222222223, "percentage": 27.22, "elapsed_time": "0:00:47", "remaining_time": "0:02:07", "throughput": 1602.81, "total_tokens": 76288}
{"current_steps": 250, "total_steps": 900, "loss": 0.0692, "lr": 4.539503170110431e-05, "epoch": 2.7777777777777777, "percentage": 27.78, "elapsed_time": "0:00:48", "remaining_time": "0:02:05", "throughput": 1609.63, "total_tokens": 77888}
{"current_steps": 255, "total_steps": 900, "loss": 0.003, "lr": 4.5110830977315556e-05, "epoch": 2.8333333333333335, "percentage": 28.33, "elapsed_time": "0:00:49", "remaining_time": "0:02:04", "throughput": 1615.56, "total_tokens": 79456}
{"current_steps": 260, "total_steps": 900, "loss": 0.1392, "lr": 4.4819067392468944e-05, "epoch": 2.888888888888889, "percentage": 28.89, "elapsed_time": "0:00:49", "remaining_time": "0:02:03", "throughput": 1622.67, "total_tokens": 81088}
{"current_steps": 265, "total_steps": 900, "loss": 0.0414, "lr": 4.4519850666916484e-05, "epoch": 2.9444444444444446, "percentage": 29.44, "elapsed_time": "0:00:50", "remaining_time": "0:02:01", "throughput": 1627.21, "total_tokens": 82592}
{"current_steps": 270, "total_steps": 900, "loss": 0.1199, "lr": 4.4213293323831585e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:00:51", "remaining_time": "0:02:00", "throughput": 1630.94, "total_tokens": 84192}
{"current_steps": 270, "total_steps": 900, "eval_loss": 0.07111923396587372, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:00:52", "remaining_time": "0:02:02", "throughput": 1602.99, "total_tokens": 84192}
{"current_steps": 275, "total_steps": 900, "loss": 0.0528, "lr": 4.38995106468937e-05, "epoch": 3.0555555555555554, "percentage": 30.56, "elapsed_time": "0:00:54", "remaining_time": "0:02:03", "throughput": 1581.99, "total_tokens": 85696}
{"current_steps": 280, "total_steps": 900, "loss": 0.0063, "lr": 4.357862063693486e-05, "epoch": 3.111111111111111, "percentage": 31.11, "elapsed_time": "0:00:54", "remaining_time": "0:02:01", "throughput": 1588.3, "total_tokens": 87296}
{"current_steps": 285, "total_steps": 900, "loss": 0.0745, "lr": 4.325074396756437e-05, "epoch": 3.1666666666666665, "percentage": 31.67, "elapsed_time": "0:00:55", "remaining_time": "0:02:00", "throughput": 1593.42, "total_tokens": 88832}
{"current_steps": 290, "total_steps": 900, "loss": 0.0024, "lr": 4.2916003939788403e-05, "epoch": 3.2222222222222223, "percentage": 32.22, "elapsed_time": "0:00:56", "remaining_time": "0:01:58", "throughput": 1598.21, "total_tokens": 90368}
{"current_steps": 295, "total_steps": 900, "loss": 0.0021, "lr": 4.257452643564155e-05, "epoch": 3.2777777777777777, "percentage": 32.78, "elapsed_time": "0:00:57", "remaining_time": "0:01:57", "throughput": 1604.16, "total_tokens": 91968}
{"current_steps": 300, "total_steps": 900, "loss": 0.052, "lr": 4.22264398708477e-05, "epoch": 3.3333333333333335, "percentage": 33.33, "elapsed_time": "0:00:58", "remaining_time": "0:01:56", "throughput": 1609.95, "total_tokens": 93568}
{"current_steps": 305, "total_steps": 900, "loss": 0.0381, "lr": 4.1871875146528195e-05, "epoch": 3.388888888888889, "percentage": 33.89, "elapsed_time": "0:00:58", "remaining_time": "0:01:54", "throughput": 1615.44, "total_tokens": 95168}
{"current_steps": 310, "total_steps": 900, "loss": 0.1334, "lr": 4.1510965599975196e-05, "epoch": 3.4444444444444446, "percentage": 34.44, "elapsed_time": "0:00:59", "remaining_time": "0:01:53", "throughput": 1619.77, "total_tokens": 96704}
{"current_steps": 315, "total_steps": 900, "loss": 0.0165, "lr": 4.114384695450906e-05, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:01:00", "remaining_time": "0:01:52", "throughput": 1625.11, "total_tokens": 98304}
{"current_steps": 315, "total_steps": 900, "eval_loss": 0.10467580705881119, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:01:01", "remaining_time": "0:01:54", "throughput": 1601.39, "total_tokens": 98304}
{"current_steps": 320, "total_steps": 900, "loss": 0.0007, "lr": 4.077065726843828e-05, "epoch": 3.5555555555555554, "percentage": 35.56, "elapsed_time": "0:01:02", "remaining_time": "0:01:54", "throughput": 1587.14, "total_tokens": 99840}
{"current_steps": 325, "total_steps": 900, "loss": 0.0356, "lr": 4.039153688314145e-05, "epoch": 3.611111111111111, "percentage": 36.11, "elapsed_time": "0:01:03", "remaining_time": "0:01:52", "throughput": 1591.69, "total_tokens": 101376}
{"current_steps": 330, "total_steps": 900, "loss": 0.0078, "lr": 4.000662837029062e-05, "epoch": 3.6666666666666665, "percentage": 36.67, "elapsed_time": "0:01:04", "remaining_time": "0:01:51", "throughput": 1596.9, "total_tokens": 102976}
{"current_steps": 335, "total_steps": 900, "loss": 0.1864, "lr": 3.961607647823583e-05, "epoch": 3.7222222222222223, "percentage": 37.22, "elapsed_time": "0:01:05", "remaining_time": "0:01:50", "throughput": 1602.16, "total_tokens": 104576}
{"current_steps": 340, "total_steps": 900, "loss": 0.1417, "lr": 3.9220028077571295e-05, "epoch": 3.7777777777777777, "percentage": 37.78, "elapsed_time": "0:01:06", "remaining_time": "0:01:48", "throughput": 1606.37, "total_tokens": 106112}
{"current_steps": 345, "total_steps": 900, "loss": 0.2733, "lr": 3.881863210590332e-05, "epoch": 3.8333333333333335, "percentage": 38.33, "elapsed_time": "0:01:06", "remaining_time": "0:01:47", "throughput": 1611.4, "total_tokens": 107712}
{"current_steps": 350, "total_steps": 900, "loss": 0.1161, "lr": 3.841203951184095e-05, "epoch": 3.888888888888889, "percentage": 38.89, "elapsed_time": "0:01:07", "remaining_time": "0:01:46", "throughput": 1616.55, "total_tokens": 109344}
{"current_steps": 355, "total_steps": 900, "loss": 0.1344, "lr": 3.8000403198230387e-05, "epoch": 3.9444444444444446, "percentage": 39.44, "elapsed_time": "0:01:08", "remaining_time": "0:01:45", "throughput": 1621.24, "total_tokens": 110944}
{"current_steps": 360, "total_steps": 900, "loss": 0.0248, "lr": 3.75838779646545e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:01:09", "remaining_time": "0:01:43", "throughput": 1623.82, "total_tokens": 112544}
{"current_steps": 360, "total_steps": 900, "eval_loss": 0.12180695682764053, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:01:10", "remaining_time": "0:01:45", "throughput": 1602.96, "total_tokens": 112544}
{"current_steps": 365, "total_steps": 900, "loss": 0.0435, "lr": 3.7162620449219e-05, "epoch": 4.055555555555555, "percentage": 40.56, "elapsed_time": "0:01:11", "remaining_time": "0:01:45", "throughput": 1587.57, "total_tokens": 114144}
{"current_steps": 370, "total_steps": 900, "loss": 0.0582, "lr": 3.673678906964727e-05, "epoch": 4.111111111111111, "percentage": 41.11, "elapsed_time": "0:01:12", "remaining_time": "0:01:44", "throughput": 1591.89, "total_tokens": 115712}
{"current_steps": 375, "total_steps": 900, "loss": 0.1575, "lr": 3.630654396370594e-05, "epoch": 4.166666666666667, "percentage": 41.67, "elapsed_time": "0:01:13", "remaining_time": "0:01:42", "throughput": 1596.61, "total_tokens": 117312}
{"current_steps": 380, "total_steps": 900, "loss": 0.0771, "lr": 3.5872046928983626e-05, "epoch": 4.222222222222222, "percentage": 42.22, "elapsed_time": "0:01:14", "remaining_time": "0:01:41", "throughput": 1600.52, "total_tokens": 118848}
{"current_steps": 385, "total_steps": 900, "loss": 0.0539, "lr": 3.543346136204545e-05, "epoch": 4.277777777777778, "percentage": 42.78, "elapsed_time": "0:01:15", "remaining_time": "0:01:40", "throughput": 1604.6, "total_tokens": 120416}
{"current_steps": 390, "total_steps": 900, "loss": 0.1802, "lr": 3.499095219698631e-05, "epoch": 4.333333333333333, "percentage": 43.33, "elapsed_time": "0:01:15", "remaining_time": "0:01:39", "throughput": 1608.82, "total_tokens": 122016}
{"current_steps": 395, "total_steps": 900, "loss": 0.0563, "lr": 3.454468584340588e-05, "epoch": 4.388888888888889, "percentage": 43.89, "elapsed_time": "0:01:16", "remaining_time": "0:01:37", "throughput": 1612.63, "total_tokens": 123584}
{"current_steps": 400, "total_steps": 900, "loss": 0.0031, "lr": 3.409483012382879e-05, "epoch": 4.444444444444445, "percentage": 44.44, "elapsed_time": "0:01:17", "remaining_time": "0:01:36", "throughput": 1617.11, "total_tokens": 125216}
{"current_steps": 405, "total_steps": 900, "loss": 0.003, "lr": 3.364155421059342e-05, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:01:18", "remaining_time": "0:01:35", "throughput": 1620.65, "total_tokens": 126784}
{"current_steps": 405, "total_steps": 900, "eval_loss": 0.1435653120279312, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:01:19", "remaining_time": "0:01:36", "throughput": 1602.1, "total_tokens": 126784}
{"current_steps": 410, "total_steps": 900, "loss": 0.0009, "lr": 3.318502856223311e-05, "epoch": 4.555555555555555, "percentage": 45.56, "elapsed_time": "0:01:20", "remaining_time": "0:01:36", "throughput": 1590.76, "total_tokens": 128352}
{"current_steps": 415, "total_steps": 900, "loss": 0.0078, "lr": 3.272542485937369e-05, "epoch": 4.611111111111111, "percentage": 46.11, "elapsed_time": "0:01:21", "remaining_time": "0:01:35", "throughput": 1594.58, "total_tokens": 129920}
{"current_steps": 420, "total_steps": 900, "loss": 0.0003, "lr": 3.2262915940171376e-05, "epoch": 4.666666666666667, "percentage": 46.67, "elapsed_time": "0:01:22", "remaining_time": "0:01:34", "throughput": 1598.26, "total_tokens": 131488}
{"current_steps": 425, "total_steps": 900, "loss": 0.0356, "lr": 3.1797675735315455e-05, "epoch": 4.722222222222222, "percentage": 47.22, "elapsed_time": "0:01:23", "remaining_time": "0:01:32", "throughput": 1601.95, "total_tokens": 133056}
{"current_steps": 430, "total_steps": 900, "loss": 0.118, "lr": 3.132987920262005e-05, "epoch": 4.777777777777778, "percentage": 47.78, "elapsed_time": "0:01:23", "remaining_time": "0:01:31", "throughput": 1605.48, "total_tokens": 134624}
{"current_steps": 435, "total_steps": 900, "loss": 0.0093, "lr": 3.085970226122962e-05, "epoch": 4.833333333333333, "percentage": 48.33, "elapsed_time": "0:01:24", "remaining_time": "0:01:30", "throughput": 1609.03, "total_tokens": 136192}
{"current_steps": 440, "total_steps": 900, "loss": 0.0005, "lr": 3.0387321725463e-05, "epoch": 4.888888888888889, "percentage": 48.89, "elapsed_time": "0:01:25", "remaining_time": "0:01:29", "throughput": 1613.15, "total_tokens": 137824}
{"current_steps": 445, "total_steps": 900, "loss": 0.0097, "lr": 2.9912915238320754e-05, "epoch": 4.944444444444445, "percentage": 49.44, "elapsed_time": "0:01:26", "remaining_time": "0:01:28", "throughput": 1616.56, "total_tokens": 139392}
{"current_steps": 450, "total_steps": 900, "loss": 0.0269, "lr": 2.9436661204680882e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:27", "remaining_time": "0:01:27", "throughput": 1618.32, "total_tokens": 140960}
{"current_steps": 450, "total_steps": 900, "eval_loss": 0.13498349487781525, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:28", "remaining_time": "0:01:28", "throughput": 1601.76, "total_tokens": 140960}
{"current_steps": 455, "total_steps": 900, "loss": 0.0038, "lr": 2.8958738724208072e-05, "epoch": 5.055555555555555, "percentage": 50.56, "elapsed_time": "0:01:29", "remaining_time": "0:01:27", "throughput": 1589.77, "total_tokens": 142560}
{"current_steps": 460, "total_steps": 900, "loss": 0.0003, "lr": 2.8479327524001636e-05, "epoch": 5.111111111111111, "percentage": 51.11, "elapsed_time": "0:01:30", "remaining_time": "0:01:26", "throughput": 1592.88, "total_tokens": 144096}
{"current_steps": 465, "total_steps": 900, "loss": 0.0002, "lr": 2.7998607891007495e-05, "epoch": 5.166666666666667, "percentage": 51.67, "elapsed_time": "0:01:31", "remaining_time": "0:01:25", "throughput": 1595.96, "total_tokens": 145632}
{"current_steps": 470, "total_steps": 900, "loss": 0.0242, "lr": 2.7516760604219617e-05, "epoch": 5.222222222222222, "percentage": 52.22, "elapsed_time": "0:01:32", "remaining_time": "0:01:24", "throughput": 1599.59, "total_tokens": 147232}
{"current_steps": 475, "total_steps": 900, "loss": 0.1703, "lr": 2.7033966866696457e-05, "epoch": 5.277777777777778, "percentage": 52.78, "elapsed_time": "0:01:32", "remaining_time": "0:01:23", "throughput": 1603.47, "total_tokens": 148864}
{"current_steps": 480, "total_steps": 900, "loss": 0.0039, "lr": 2.6550408237417885e-05, "epoch": 5.333333333333333, "percentage": 53.33, "elapsed_time": "0:01:33", "remaining_time": "0:01:21", "throughput": 1606.61, "total_tokens": 150432}
{"current_steps": 485, "total_steps": 900, "loss": 0.0603, "lr": 2.6066266563008267e-05, "epoch": 5.388888888888889, "percentage": 53.89, "elapsed_time": "0:01:34", "remaining_time": "0:01:20", "throughput": 1610.1, "total_tokens": 152032}
{"current_steps": 490, "total_steps": 900, "loss": 0.1105, "lr": 2.5581723909351406e-05, "epoch": 5.444444444444445, "percentage": 54.44, "elapsed_time": "0:01:35", "remaining_time": "0:01:19", "throughput": 1613.22, "total_tokens": 153600}
{"current_steps": 495, "total_steps": 900, "loss": 0.0008, "lr": 2.5096962493123012e-05, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:01:36", "remaining_time": "0:01:18", "throughput": 1616.6, "total_tokens": 155200}
{"current_steps": 495, "total_steps": 900, "eval_loss": 0.13894477486610413, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:01:36", "remaining_time": "0:01:19", "throughput": 1601.56, "total_tokens": 155200}
{"current_steps": 500, "total_steps": 900, "loss": 0.0067, "lr": 2.461216461326642e-05, "epoch": 5.555555555555555, "percentage": 55.56, "elapsed_time": "0:01:38", "remaining_time": "0:01:18", "throughput": 1593.03, "total_tokens": 156800}
{"current_steps": 505, "total_steps": 900, "loss": 0.0013, "lr": 2.4127512582437485e-05, "epoch": 5.611111111111111, "percentage": 56.11, "elapsed_time": "0:01:39", "remaining_time": "0:01:17", "throughput": 1595.85, "total_tokens": 158336}
{"current_steps": 510, "total_steps": 900, "loss": 0.001, "lr": 2.364318865844416e-05, "epoch": 5.666666666666667, "percentage": 56.67, "elapsed_time": "0:01:40", "remaining_time": "0:01:16", "throughput": 1599.01, "total_tokens": 159904}
{"current_steps": 515, "total_steps": 900, "loss": 0.1608, "lr": 2.3159374975706884e-05, "epoch": 5.722222222222222, "percentage": 57.22, "elapsed_time": "0:01:40", "remaining_time": "0:01:15", "throughput": 1602.41, "total_tokens": 161504}
{"current_steps": 520, "total_steps": 900, "loss": 0.0018, "lr": 2.2676253476765196e-05, "epoch": 5.777777777777778, "percentage": 57.78, "elapsed_time": "0:01:41", "remaining_time": "0:01:14", "throughput": 1604.93, "total_tokens": 163008}
{"current_steps": 525, "total_steps": 900, "loss": 0.0438, "lr": 2.2194005843856636e-05, "epoch": 5.833333333333333, "percentage": 58.33, "elapsed_time": "0:01:42", "remaining_time": "0:01:13", "throughput": 1607.32, "total_tokens": 164512}
{"current_steps": 530, "total_steps": 900, "loss": 0.0472, "lr": 2.1712813430593436e-05, "epoch": 5.888888888888889, "percentage": 58.89, "elapsed_time": "0:01:43", "remaining_time": "0:01:12", "throughput": 1610.31, "total_tokens": 166080}
{"current_steps": 535, "total_steps": 900, "loss": 0.0002, "lr": 2.1232857193762924e-05, "epoch": 5.944444444444445, "percentage": 59.44, "elapsed_time": "0:01:43", "remaining_time": "0:01:10", "throughput": 1613.56, "total_tokens": 167680}
{"current_steps": 540, "total_steps": 900, "loss": 0.027, "lr": 2.0754317625276983e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:01:44", "remaining_time": "0:01:09", "throughput": 1615.05, "total_tokens": 169216}
{"current_steps": 540, "total_steps": 900, "eval_loss": 0.15303298830986023, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:01:45", "remaining_time": "0:01:10", "throughput": 1601.54, "total_tokens": 169216}
{"current_steps": 545, "total_steps": 900, "loss": 0.0002, "lr": 2.02773746842965e-05, "epoch": 6.055555555555555, "percentage": 60.56, "elapsed_time": "0:01:47", "remaining_time": "0:01:10", "throughput": 1587.74, "total_tokens": 170784}
{"current_steps": 550, "total_steps": 900, "loss": 0.0738, "lr": 1.980220772955602e-05, "epoch": 6.111111111111111, "percentage": 61.11, "elapsed_time": "0:01:48", "remaining_time": "0:01:08", "throughput": 1590.67, "total_tokens": 172352}
{"current_steps": 555, "total_steps": 900, "loss": 0.0002, "lr": 1.932899545191433e-05, "epoch": 6.166666666666667, "percentage": 61.67, "elapsed_time": "0:01:49", "remaining_time": "0:01:07", "throughput": 1593.63, "total_tokens": 173920}
{"current_steps": 560, "total_steps": 900, "loss": 0.0017, "lr": 1.8857915807156092e-05, "epoch": 6.222222222222222, "percentage": 62.22, "elapsed_time": "0:01:49", "remaining_time": "0:01:06", "throughput": 1596.56, "total_tokens": 175488}
{"current_steps": 565, "total_steps": 900, "loss": 0.0062, "lr": 1.838914594906995e-05, "epoch": 6.277777777777778, "percentage": 62.78, "elapsed_time": "0:01:50", "remaining_time": "0:01:05", "throughput": 1599.14, "total_tokens": 177024}
{"current_steps": 570, "total_steps": 900, "loss": 0.0001, "lr": 1.792286216282824e-05, "epoch": 6.333333333333333, "percentage": 63.33, "elapsed_time": "0:01:51", "remaining_time": "0:01:04", "throughput": 1602.14, "total_tokens": 178624}
{"current_steps": 575, "total_steps": 900, "loss": 0.0542, "lr": 1.7459239798693364e-05, "epoch": 6.388888888888889, "percentage": 63.89, "elapsed_time": "0:01:52", "remaining_time": "0:01:03", "throughput": 1604.18, "total_tokens": 180096}
{"current_steps": 580, "total_steps": 900, "loss": 0.0349, "lr": 1.699845320607571e-05, "epoch": 6.444444444444445, "percentage": 64.44, "elapsed_time": "0:01:53", "remaining_time": "0:01:02", "throughput": 1606.42, "total_tokens": 181600}
{"current_steps": 585, "total_steps": 900, "loss": 0.0006, "lr": 1.6540675667967974e-05, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:01:53", "remaining_time": "0:01:01", "throughput": 1609.64, "total_tokens": 183232}
{"current_steps": 585, "total_steps": 900, "eval_loss": 0.1628120243549347, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:01:54", "remaining_time": "0:01:01", "throughput": 1597.12, "total_tokens": 183232}
{"current_steps": 590, "total_steps": 900, "loss": 0.0413, "lr": 1.60860793357805e-05, "epoch": 6.555555555555555, "percentage": 65.56, "elapsed_time": "0:01:56", "remaining_time": "0:01:01", "throughput": 1588.78, "total_tokens": 184768}
{"current_steps": 595, "total_steps": 900, "loss": 0.1563, "lr": 1.56348351646022e-05, "epoch": 6.611111111111111, "percentage": 66.11, "elapsed_time": "0:01:57", "remaining_time": "0:01:00", "throughput": 1590.53, "total_tokens": 186208}
{"current_steps": 600, "total_steps": 900, "loss": 0.0003, "lr": 1.5187112848911323e-05, "epoch": 6.666666666666667, "percentage": 66.67, "elapsed_time": "0:01:57", "remaining_time": "0:00:58", "throughput": 1593.26, "total_tokens": 187776}
{"current_steps": 605, "total_steps": 900, "loss": 0.0012, "lr": 1.47430807587603e-05, "epoch": 6.722222222222222, "percentage": 67.22, "elapsed_time": "0:01:58", "remaining_time": "0:00:57", "throughput": 1595.97, "total_tokens": 189344}
{"current_steps": 610, "total_steps": 900, "loss": 0.0003, "lr": 1.430290587645865e-05, "epoch": 6.777777777777778, "percentage": 67.78, "elapsed_time": "0:01:59", "remaining_time": "0:00:56", "throughput": 1598.64, "total_tokens": 190912}
{"current_steps": 615, "total_steps": 900, "loss": 0.0026, "lr": 1.3866753733777765e-05, "epoch": 6.833333333333333, "percentage": 68.33, "elapsed_time": "0:02:00", "remaining_time": "0:00:55", "throughput": 1601.46, "total_tokens": 192512}
{"current_steps": 620, "total_steps": 900, "loss": 0.0015, "lr": 1.343478834970121e-05, "epoch": 6.888888888888889, "percentage": 68.89, "elapsed_time": "0:02:00", "remaining_time": "0:00:54", "throughput": 1604.29, "total_tokens": 194112}
{"current_steps": 625, "total_steps": 900, "loss": 0.1629, "lr": 1.3007172168743854e-05, "epoch": 6.944444444444445, "percentage": 69.44, "elapsed_time": "0:02:01", "remaining_time": "0:00:53", "throughput": 1607.06, "total_tokens": 195712}
{"current_steps": 630, "total_steps": 900, "loss": 0.0002, "lr": 1.2584065999863102e-05, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:02:02", "remaining_time": "0:00:52", "throughput": 1608.33, "total_tokens": 197248}
{"current_steps": 630, "total_steps": 900, "eval_loss": 0.16838467121124268, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:02:03", "remaining_time": "0:00:52", "throughput": 1596.73, "total_tokens": 197248}
{"current_steps": 635, "total_steps": 900, "loss": 0.002, "lr": 1.2165628955985314e-05, "epoch": 7.055555555555555, "percentage": 70.56, "elapsed_time": "0:02:05", "remaining_time": "0:00:52", "throughput": 1588.42, "total_tokens": 198784}
{"current_steps": 640, "total_steps": 900, "loss": 0.0393, "lr": 1.175201839416988e-05, "epoch": 7.111111111111111, "percentage": 71.11, "elapsed_time": "0:02:05", "remaining_time": "0:00:51", "throughput": 1591.0, "total_tokens": 200352}
{"current_steps": 645, "total_steps": 900, "loss": 0.0002, "lr": 1.1343389856433658e-05, "epoch": 7.166666666666667, "percentage": 71.67, "elapsed_time": "0:02:06", "remaining_time": "0:00:50", "throughput": 1593.07, "total_tokens": 201856}
{"current_steps": 650, "total_steps": 900, "loss": 0.1564, "lr": 1.0939897011258001e-05, "epoch": 7.222222222222222, "percentage": 72.22, "elapsed_time": "0:02:07", "remaining_time": "0:00:49", "throughput": 1596.05, "total_tokens": 203488}
{"current_steps": 655, "total_steps": 900, "loss": 0.0003, "lr": 1.0541691595800337e-05, "epoch": 7.277777777777778, "percentage": 72.78, "elapsed_time": "0:02:08", "remaining_time": "0:00:47", "throughput": 1598.54, "total_tokens": 205056}
{"current_steps": 660, "total_steps": 900, "loss": 0.0001, "lr": 1.0148923358832022e-05, "epoch": 7.333333333333333, "percentage": 73.33, "elapsed_time": "0:02:09", "remaining_time": "0:00:46", "throughput": 1601.19, "total_tokens": 206656}
{"current_steps": 665, "total_steps": 900, "loss": 0.0001, "lr": 9.761740004423927e-06, "epoch": 7.388888888888889, "percentage": 73.89, "elapsed_time": "0:02:09", "remaining_time": "0:00:45", "throughput": 1604.0, "total_tokens": 208288}
{"current_steps": 670, "total_steps": 900, "loss": 0.0202, "lr": 9.380287136401e-06, "epoch": 7.444444444444445, "percentage": 74.44, "elapsed_time": "0:02:10", "remaining_time": "0:00:44", "throughput": 1606.41, "total_tokens": 209856}
{"current_steps": 675, "total_steps": 900, "loss": 0.0006, "lr": 9.00470820358663e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:02:11", "remaining_time": "0:00:43", "throughput": 1608.78, "total_tokens": 211424}
{"current_steps": 675, "total_steps": 900, "eval_loss": 0.16412463784217834, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:02:12", "remaining_time": "0:00:44", "throughput": 1597.96, "total_tokens": 211424}
{"current_steps": 680, "total_steps": 900, "loss": 0.0004, "lr": 8.635144445857406e-06, "epoch": 7.555555555555555, "percentage": 75.56, "elapsed_time": "0:02:13", "remaining_time": "0:00:43", "throughput": 1591.05, "total_tokens": 212928}
{"current_steps": 685, "total_steps": 900, "loss": 0.0007, "lr": 8.271734841028553e-06, "epoch": 7.611111111111111, "percentage": 76.11, "elapsed_time": "0:02:14", "remaining_time": "0:00:42", "throughput": 1593.45, "total_tokens": 214496}
{"current_steps": 690, "total_steps": 900, "loss": 0.003, "lr": 7.914616052590071e-06, "epoch": 7.666666666666667, "percentage": 76.67, "elapsed_time": "0:02:15", "remaining_time": "0:00:41", "throughput": 1595.81, "total_tokens": 216064}
{"current_steps": 695, "total_steps": 900, "loss": 0.0613, "lr": 7.563922378313218e-06, "epoch": 7.722222222222222, "percentage": 77.22, "elapsed_time": "0:02:16", "remaining_time": "0:00:40", "throughput": 1597.94, "total_tokens": 217600}
{"current_steps": 700, "total_steps": 900, "loss": 0.0003, "lr": 7.219785699746573e-06, "epoch": 7.777777777777778, "percentage": 77.78, "elapsed_time": "0:02:16", "remaining_time": "0:00:39", "throughput": 1599.96, "total_tokens": 219136}
{"current_steps": 705, "total_steps": 900, "loss": 0.0212, "lr": 6.882335432620779e-06, "epoch": 7.833333333333333, "percentage": 78.33, "elapsed_time": "0:02:17", "remaining_time": "0:00:38", "throughput": 1602.23, "total_tokens": 220704}
{"current_steps": 710, "total_steps": 900, "loss": 0.0009, "lr": 6.55169847818059e-06, "epoch": 7.888888888888889, "percentage": 78.89, "elapsed_time": "0:02:18", "remaining_time": "0:00:37", "throughput": 1604.46, "total_tokens": 222272}
{"current_steps": 715, "total_steps": 900, "loss": 0.0002, "lr": 6.22799917546252e-06, "epoch": 7.944444444444445, "percentage": 79.44, "elapsed_time": "0:02:19", "remaining_time": "0:00:36", "throughput": 1606.91, "total_tokens": 223872}
{"current_steps": 720, "total_steps": 900, "loss": 0.1687, "lr": 5.9113592545359945e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:02:20", "remaining_time": "0:00:35", "throughput": 1608.22, "total_tokens": 225440}
{"current_steps": 720, "total_steps": 900, "eval_loss": 0.17168062925338745, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:02:21", "remaining_time": "0:00:35", "throughput": 1598.14, "total_tokens": 225440}
{"current_steps": 725, "total_steps": 900, "loss": 0.0004, "lr": 5.601897790725643e-06, "epoch": 8.055555555555555, "percentage": 80.56, "elapsed_time": "0:02:22", "remaining_time": "0:00:34", "throughput": 1589.78, "total_tokens": 226912}
{"current_steps": 730, "total_steps": 900, "loss": 0.0004, "lr": 5.299731159831953e-06, "epoch": 8.11111111111111, "percentage": 81.11, "elapsed_time": "0:02:23", "remaining_time": "0:00:33", "throughput": 1592.21, "total_tokens": 228512}
{"current_steps": 735, "total_steps": 900, "loss": 0.0004, "lr": 5.004972994367102e-06, "epoch": 8.166666666666666, "percentage": 81.67, "elapsed_time": "0:02:24", "remaining_time": "0:00:32", "throughput": 1594.37, "total_tokens": 230080}
{"current_steps": 740, "total_steps": 900, "loss": 0.0001, "lr": 4.7177341408224e-06, "epoch": 8.222222222222221, "percentage": 82.22, "elapsed_time": "0:02:25", "remaining_time": "0:00:31", "throughput": 1596.33, "total_tokens": 231616}
{"current_steps": 745, "total_steps": 900, "loss": 0.0002, "lr": 4.438122617983443e-06, "epoch": 8.277777777777779, "percentage": 82.78, "elapsed_time": "0:02:25", "remaining_time": "0:00:30", "throughput": 1598.44, "total_tokens": 233184}
{"current_steps": 750, "total_steps": 900, "loss": 0.0002, "lr": 4.166243576308712e-06, "epoch": 8.333333333333334, "percentage": 83.33, "elapsed_time": "0:02:26", "remaining_time": "0:00:29", "throughput": 1600.21, "total_tokens": 234688}
{"current_steps": 755, "total_steps": 900, "loss": 0.1696, "lr": 3.9021992583867325e-06, "epoch": 8.38888888888889, "percentage": 83.89, "elapsed_time": "0:02:27", "remaining_time": "0:00:28", "throughput": 1602.3, "total_tokens": 236256}
{"current_steps": 760, "total_steps": 900, "loss": 0.0005, "lr": 3.6460889604868626e-06, "epoch": 8.444444444444445, "percentage": 84.44, "elapsed_time": "0:02:28", "remaining_time": "0:00:27", "throughput": 1604.6, "total_tokens": 237856}
{"current_steps": 765, "total_steps": 900, "loss": 0.0001, "lr": 3.398008995217988e-06, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:02:29", "remaining_time": "0:00:26", "throughput": 1606.5, "total_tokens": 239392}
{"current_steps": 765, "total_steps": 900, "eval_loss": 0.1705838143825531, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:02:29", "remaining_time": "0:00:26", "throughput": 1597.02, "total_tokens": 239392}
{"current_steps": 770, "total_steps": 900, "loss": 0.0009, "lr": 3.158052655309332e-06, "epoch": 8.555555555555555, "percentage": 85.56, "elapsed_time": "0:02:31", "remaining_time": "0:00:25", "throughput": 1591.8, "total_tokens": 240960}
{"current_steps": 775, "total_steps": 900, "loss": 0.0021, "lr": 2.9263101785268254e-06, "epoch": 8.61111111111111, "percentage": 86.11, "elapsed_time": "0:02:32", "remaining_time": "0:00:24", "throughput": 1593.69, "total_tokens": 242496}
{"current_steps": 780, "total_steps": 900, "loss": 0.0002, "lr": 2.7028687137384267e-06, "epoch": 8.666666666666666, "percentage": 86.67, "elapsed_time": "0:02:32", "remaining_time": "0:00:23", "throughput": 1595.77, "total_tokens": 244064}
{"current_steps": 785, "total_steps": 900, "loss": 0.0003, "lr": 2.487812288140945e-06, "epoch": 8.722222222222221, "percentage": 87.22, "elapsed_time": "0:02:33", "remaining_time": "0:00:22", "throughput": 1598.0, "total_tokens": 245664}
{"current_steps": 790, "total_steps": 900, "loss": 0.0006, "lr": 2.281221775660894e-06, "epoch": 8.777777777777779, "percentage": 87.78, "elapsed_time": "0:02:34", "remaining_time": "0:00:21", "throughput": 1600.22, "total_tokens": 247264}
{"current_steps": 795, "total_steps": 900, "loss": 0.1491, "lr": 2.0831748665410765e-06, "epoch": 8.833333333333334, "percentage": 88.33, "elapsed_time": "0:02:35", "remaining_time": "0:00:20", "throughput": 1602.25, "total_tokens": 248832}
{"current_steps": 800, "total_steps": 900, "loss": 0.0532, "lr": 1.893746038124497e-06, "epoch": 8.88888888888889, "percentage": 88.89, "elapsed_time": "0:02:36", "remaining_time": "0:00:19", "throughput": 1604.44, "total_tokens": 250432}
{"current_steps": 805, "total_steps": 900, "loss": 0.0792, "lr": 1.713006526846439e-06, "epoch": 8.944444444444445, "percentage": 89.44, "elapsed_time": "0:02:36", "remaining_time": "0:00:18", "throughput": 1606.8, "total_tokens": 252064}
{"current_steps": 810, "total_steps": 900, "loss": 0.0014, "lr": 1.541024301445404e-06, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:02:37", "remaining_time": "0:00:17", "throughput": 1607.93, "total_tokens": 253632}
{"current_steps": 810, "total_steps": 900, "eval_loss": 0.17227138578891754, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:02:38", "remaining_time": "0:00:17", "throughput": 1598.98, "total_tokens": 253632}
{"current_steps": 815, "total_steps": 900, "loss": 0.0009, "lr": 1.3778640374027985e-06, "epoch": 9.055555555555555, "percentage": 90.56, "elapsed_time": "0:02:40", "remaining_time": "0:00:16", "throughput": 1592.39, "total_tokens": 255232}
{"current_steps": 820, "total_steps": 900, "loss": 0.0006, "lr": 1.2235870926211619e-06, "epoch": 9.11111111111111, "percentage": 91.11, "elapsed_time": "0:02:41", "remaining_time": "0:00:15", "throughput": 1594.38, "total_tokens": 256800}
{"current_steps": 825, "total_steps": 900, "loss": 0.146, "lr": 1.0782514843499653e-06, "epoch": 9.166666666666666, "percentage": 91.67, "elapsed_time": "0:02:41", "remaining_time": "0:00:14", "throughput": 1596.34, "total_tokens": 258368}
{"current_steps": 830, "total_steps": 900, "loss": 0.0018, "lr": 9.419118673676924e-07, "epoch": 9.222222222222221, "percentage": 92.22, "elapsed_time": "0:02:42", "remaining_time": "0:00:13", "throughput": 1597.94, "total_tokens": 259872}
{"current_steps": 835, "total_steps": 900, "loss": 0.0002, "lr": 8.146195134284052e-07, "epoch": 9.277777777777779, "percentage": 92.78, "elapsed_time": "0:02:43", "remaining_time": "0:00:12", "throughput": 1599.52, "total_tokens": 261376}
{"current_steps": 840, "total_steps": 900, "loss": 0.0002, "lr": 6.964222919805391e-07, "epoch": 9.333333333333334, "percentage": 93.33, "elapsed_time": "0:02:44", "remaining_time": "0:00:11", "throughput": 1601.45, "total_tokens": 262944}
{"current_steps": 845, "total_steps": 900, "loss": 0.0164, "lr": 5.87364652165176e-07, "epoch": 9.38888888888889, "percentage": 93.89, "elapsed_time": "0:02:44", "remaining_time": "0:00:10", "throughput": 1603.54, "total_tokens": 264544}
{"current_steps": 850, "total_steps": 900, "loss": 0.0011, "lr": 4.874876061005173e-07, "epoch": 9.444444444444445, "percentage": 94.44, "elapsed_time": "0:02:45", "remaining_time": "0:00:09", "throughput": 1605.22, "total_tokens": 266080}
{"current_steps": 855, "total_steps": 900, "loss": 0.0004, "lr": 3.9682871345891883e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:46", "remaining_time": "0:00:08", "throughput": 1607.26, "total_tokens": 267680}
{"current_steps": 855, "total_steps": 900, "eval_loss": 0.1678561121225357, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:47", "remaining_time": "0:00:08", "throughput": 1598.74, "total_tokens": 267680}
{"current_steps": 860, "total_steps": 900, "loss": 0.2107, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:02:49", "remaining_time": "0:00:07", "throughput": 1591.62, "total_tokens": 269280}
{"current_steps": 865, "total_steps": 900, "loss": 0.0002, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:02:49", "remaining_time": "0:00:06", "throughput": 1593.86, "total_tokens": 270912}
{"current_steps": 870, "total_steps": 900, "loss": 0.0177, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:50", "remaining_time": "0:00:05", "throughput": 1595.84, "total_tokens": 272512}
{"current_steps": 875, "total_steps": 900, "loss": 0.061, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:02:51", "remaining_time": "0:00:04", "throughput": 1597.54, "total_tokens": 274048}
{"current_steps": 880, "total_steps": 900, "loss": 0.0004, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:02:52", "remaining_time": "0:00:03", "throughput": 1599.51, "total_tokens": 275648}
{"current_steps": 885, "total_steps": 900, "loss": 0.001, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:02:53", "remaining_time": "0:00:02", "throughput": 1601.51, "total_tokens": 277248}
{"current_steps": 890, "total_steps": 900, "loss": 0.0004, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:02:53", "remaining_time": "0:00:01", "throughput": 1603.29, "total_tokens": 278816}
{"current_steps": 895, "total_steps": 900, "loss": 0.0003, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:02:54", "remaining_time": "0:00:00", "throughput": 1605.24, "total_tokens": 280416}
{"current_steps": 900, "total_steps": 900, "loss": 0.0003, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:55", "remaining_time": "0:00:00", "throughput": 1606.32, "total_tokens": 281984}
{"current_steps": 900, "total_steps": 900, "eval_loss": 0.16516418755054474, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:56", "remaining_time": "0:00:00", "throughput": 1598.26, "total_tokens": 281984}
{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:57", "remaining_time": "0:00:00", "throughput": 1591.59, "total_tokens": 281984}