wisdom-llama3-70b / trainer_log.jsonl
Brown
Upload folder using huggingface_hub
ee7a6fb verified
raw
history blame
79.2 kB
{"current_steps": 10, "total_steps": 3093, "loss": 0.3895, "learning_rate": 1.0752688172043011e-06, "epoch": 0.009699321047526674, "percentage": 0.32, "elapsed_time": "0:09:45", "remaining_time": "2 days, 2:08:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 20, "total_steps": 3093, "loss": 0.3209, "learning_rate": 2.1505376344086023e-06, "epoch": 0.019398642095053348, "percentage": 0.65, "elapsed_time": "0:19:14", "remaining_time": "2 days, 1:15:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 30, "total_steps": 3093, "loss": 0.2648, "learning_rate": 3.225806451612903e-06, "epoch": 0.029097963142580018, "percentage": 0.97, "elapsed_time": "0:28:42", "remaining_time": "2 days, 0:51:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 40, "total_steps": 3093, "loss": 0.2353, "learning_rate": 4.3010752688172045e-06, "epoch": 0.038797284190106696, "percentage": 1.29, "elapsed_time": "0:38:11", "remaining_time": "2 days, 0:34:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 50, "total_steps": 3093, "loss": 0.2211, "learning_rate": 5.376344086021506e-06, "epoch": 0.04849660523763336, "percentage": 1.62, "elapsed_time": "0:47:40", "remaining_time": "2 days, 0:21:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 60, "total_steps": 3093, "loss": 0.2065, "learning_rate": 6.451612903225806e-06, "epoch": 0.058195926285160036, "percentage": 1.94, "elapsed_time": "0:57:08", "remaining_time": "2 days, 0:08:49", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 70, "total_steps": 3093, "loss": 0.2, "learning_rate": 7.526881720430108e-06, "epoch": 0.06789524733268672, "percentage": 2.26, "elapsed_time": "1:06:37", "remaining_time": "1 day, 23:57:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 80, "total_steps": 3093, "loss": 0.1932, "learning_rate": 8.602150537634409e-06, "epoch": 0.07759456838021339, "percentage": 2.59, "elapsed_time": "1:16:06", "remaining_time": "1 day, 23:46:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 90, "total_steps": 3093, "loss": 0.1888, "learning_rate": 9.67741935483871e-06, "epoch": 0.08729388942774007, "percentage": 2.91, "elapsed_time": "1:25:34", "remaining_time": "1 day, 23:35:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 100, "total_steps": 3093, "loss": 0.186, "learning_rate": 9.999865664319414e-06, "epoch": 0.09699321047526673, "percentage": 3.23, "elapsed_time": "1:35:04", "remaining_time": "1 day, 23:25:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 110, "total_steps": 3093, "loss": 0.182, "learning_rate": 9.999207711016081e-06, "epoch": 0.1066925315227934, "percentage": 3.56, "elapsed_time": "1:44:32", "remaining_time": "1 day, 23:15:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 120, "total_steps": 3093, "loss": 0.1779, "learning_rate": 9.998001538251283e-06, "epoch": 0.11639185257032007, "percentage": 3.88, "elapsed_time": "1:54:01", "remaining_time": "1 day, 23:04:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 130, "total_steps": 3093, "loss": 0.1743, "learning_rate": 9.99624727829546e-06, "epoch": 0.12609117361784675, "percentage": 4.2, "elapsed_time": "2:03:30", "remaining_time": "1 day, 22:54:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 140, "total_steps": 3093, "loss": 0.176, "learning_rate": 9.99394512352298e-06, "epoch": 0.13579049466537343, "percentage": 4.53, "elapsed_time": "2:12:59", "remaining_time": "1 day, 22:45:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 150, "total_steps": 3093, "loss": 0.1741, "learning_rate": 9.991095326391061e-06, "epoch": 0.1454898157129001, "percentage": 4.85, "elapsed_time": "2:22:27", "remaining_time": "1 day, 22:35:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 160, "total_steps": 3093, "loss": 0.1702, "learning_rate": 9.98769819941207e-06, "epoch": 0.15518913676042678, "percentage": 5.17, "elapsed_time": "2:31:56", "remaining_time": "1 day, 22:25:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 170, "total_steps": 3093, "loss": 0.1727, "learning_rate": 9.983754115119262e-06, "epoch": 0.16488845780795344, "percentage": 5.5, "elapsed_time": "2:41:24", "remaining_time": "1 day, 22:15:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 180, "total_steps": 3093, "loss": 0.1701, "learning_rate": 9.97926350602593e-06, "epoch": 0.17458777885548013, "percentage": 5.82, "elapsed_time": "2:50:53", "remaining_time": "1 day, 22:05:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 190, "total_steps": 3093, "loss": 0.1678, "learning_rate": 9.97422686457796e-06, "epoch": 0.1842870999030068, "percentage": 6.14, "elapsed_time": "3:00:21", "remaining_time": "1 day, 21:55:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 200, "total_steps": 3093, "loss": 0.1641, "learning_rate": 9.968644743099848e-06, "epoch": 0.19398642095053345, "percentage": 6.47, "elapsed_time": "3:09:50", "remaining_time": "1 day, 21:46:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 210, "total_steps": 3093, "loss": 0.167, "learning_rate": 9.96251775373412e-06, "epoch": 0.20368574199806014, "percentage": 6.79, "elapsed_time": "3:19:19", "remaining_time": "1 day, 21:36:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 220, "total_steps": 3093, "loss": 0.1655, "learning_rate": 9.955846568374201e-06, "epoch": 0.2133850630455868, "percentage": 7.11, "elapsed_time": "3:28:47", "remaining_time": "1 day, 21:26:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 230, "total_steps": 3093, "loss": 0.1617, "learning_rate": 9.948631918590746e-06, "epoch": 0.22308438409311349, "percentage": 7.44, "elapsed_time": "3:38:16", "remaining_time": "1 day, 21:17:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 240, "total_steps": 3093, "loss": 0.1626, "learning_rate": 9.940874595551403e-06, "epoch": 0.23278370514064015, "percentage": 7.76, "elapsed_time": "3:47:45", "remaining_time": "1 day, 21:07:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 250, "total_steps": 3093, "loss": 0.1644, "learning_rate": 9.932575449934063e-06, "epoch": 0.24248302618816683, "percentage": 8.08, "elapsed_time": "3:57:14", "remaining_time": "1 day, 20:57:49", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 260, "total_steps": 3093, "loss": 0.1618, "learning_rate": 9.923735391833564e-06, "epoch": 0.2521823472356935, "percentage": 8.41, "elapsed_time": "4:06:42", "remaining_time": "1 day, 20:48:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 270, "total_steps": 3093, "loss": 0.1588, "learning_rate": 9.914355390661897e-06, "epoch": 0.2618816682832202, "percentage": 8.73, "elapsed_time": "4:16:11", "remaining_time": "1 day, 20:38:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 280, "total_steps": 3093, "loss": 0.1599, "learning_rate": 9.904436475041892e-06, "epoch": 0.27158098933074687, "percentage": 9.05, "elapsed_time": "4:25:39", "remaining_time": "1 day, 20:28:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 290, "total_steps": 3093, "loss": 0.1608, "learning_rate": 9.893979732694422e-06, "epoch": 0.2812803103782735, "percentage": 9.38, "elapsed_time": "4:35:08", "remaining_time": "1 day, 20:19:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 300, "total_steps": 3093, "loss": 0.1571, "learning_rate": 9.882986310319124e-06, "epoch": 0.2909796314258002, "percentage": 9.7, "elapsed_time": "4:44:37", "remaining_time": "1 day, 20:09:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 310, "total_steps": 3093, "loss": 0.1602, "learning_rate": 9.871457413468645e-06, "epoch": 0.3006789524733269, "percentage": 10.02, "elapsed_time": "4:54:05", "remaining_time": "1 day, 20:00:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 320, "total_steps": 3093, "loss": 0.1587, "learning_rate": 9.859394306416443e-06, "epoch": 0.31037827352085356, "percentage": 10.35, "elapsed_time": "5:03:34", "remaining_time": "1 day, 19:50:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 330, "total_steps": 3093, "loss": 0.1593, "learning_rate": 9.846798312018147e-06, "epoch": 0.3200775945683802, "percentage": 10.67, "elapsed_time": "5:13:03", "remaining_time": "1 day, 19:41:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 340, "total_steps": 3093, "loss": 0.1555, "learning_rate": 9.833670811566485e-06, "epoch": 0.3297769156159069, "percentage": 10.99, "elapsed_time": "5:22:32", "remaining_time": "1 day, 19:31:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 350, "total_steps": 3093, "loss": 0.1575, "learning_rate": 9.820013244639817e-06, "epoch": 0.3394762366634336, "percentage": 11.32, "elapsed_time": "5:32:01", "remaining_time": "1 day, 19:22:03", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 360, "total_steps": 3093, "loss": 0.1573, "learning_rate": 9.80582710894426e-06, "epoch": 0.34917555771096026, "percentage": 11.64, "elapsed_time": "5:41:29", "remaining_time": "1 day, 19:12:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 370, "total_steps": 3093, "loss": 0.1549, "learning_rate": 9.791113960149458e-06, "epoch": 0.3588748787584869, "percentage": 11.96, "elapsed_time": "5:50:58", "remaining_time": "1 day, 19:02:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 380, "total_steps": 3093, "loss": 0.1559, "learning_rate": 9.775875411717981e-06, "epoch": 0.3685741998060136, "percentage": 12.29, "elapsed_time": "6:00:27", "remaining_time": "1 day, 18:53:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 390, "total_steps": 3093, "loss": 0.156, "learning_rate": 9.760113134728383e-06, "epoch": 0.37827352085354027, "percentage": 12.61, "elapsed_time": "6:09:56", "remaining_time": "1 day, 18:43:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 400, "total_steps": 3093, "loss": 0.1549, "learning_rate": 9.743828857691964e-06, "epoch": 0.3879728419010669, "percentage": 12.93, "elapsed_time": "6:19:24", "remaining_time": "1 day, 18:34:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 410, "total_steps": 3093, "loss": 0.1546, "learning_rate": 9.727024366363208e-06, "epoch": 0.3976721629485936, "percentage": 13.26, "elapsed_time": "6:28:53", "remaining_time": "1 day, 18:24:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 420, "total_steps": 3093, "loss": 0.1541, "learning_rate": 9.709701503543954e-06, "epoch": 0.4073714839961203, "percentage": 13.58, "elapsed_time": "6:38:22", "remaining_time": "1 day, 18:15:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 430, "total_steps": 3093, "loss": 0.153, "learning_rate": 9.691862168881325e-06, "epoch": 0.41707080504364696, "percentage": 13.9, "elapsed_time": "6:47:51", "remaining_time": "1 day, 18:05:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 440, "total_steps": 3093, "loss": 0.1514, "learning_rate": 9.673508318659399e-06, "epoch": 0.4267701260911736, "percentage": 14.23, "elapsed_time": "6:57:19", "remaining_time": "1 day, 17:56:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 450, "total_steps": 3093, "loss": 0.1507, "learning_rate": 9.65464196558468e-06, "epoch": 0.4364694471387003, "percentage": 14.55, "elapsed_time": "7:06:48", "remaining_time": "1 day, 17:46:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 460, "total_steps": 3093, "loss": 0.1529, "learning_rate": 9.635265178565386e-06, "epoch": 0.44616876818622697, "percentage": 14.87, "elapsed_time": "7:16:17", "remaining_time": "1 day, 17:37:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 470, "total_steps": 3093, "loss": 0.1524, "learning_rate": 9.615380082484573e-06, "epoch": 0.45586808923375366, "percentage": 15.2, "elapsed_time": "7:25:45", "remaining_time": "1 day, 17:27:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 480, "total_steps": 3093, "loss": 0.1519, "learning_rate": 9.594988857967107e-06, "epoch": 0.4655674102812803, "percentage": 15.52, "elapsed_time": "7:35:14", "remaining_time": "1 day, 17:18:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 490, "total_steps": 3093, "loss": 0.1503, "learning_rate": 9.574093741140549e-06, "epoch": 0.475266731328807, "percentage": 15.84, "elapsed_time": "7:44:43", "remaining_time": "1 day, 17:08:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 500, "total_steps": 3093, "loss": 0.15, "learning_rate": 9.552697023389923e-06, "epoch": 0.48496605237633367, "percentage": 16.17, "elapsed_time": "7:54:12", "remaining_time": "1 day, 16:59:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 510, "total_steps": 3093, "loss": 0.1505, "learning_rate": 9.530801051106449e-06, "epoch": 0.49466537342386036, "percentage": 16.49, "elapsed_time": "8:07:17", "remaining_time": "1 day, 17:07:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 520, "total_steps": 3093, "loss": 0.1512, "learning_rate": 9.508408225430237e-06, "epoch": 0.504364694471387, "percentage": 16.81, "elapsed_time": "8:16:45", "remaining_time": "1 day, 16:58:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 530, "total_steps": 3093, "loss": 0.1438, "learning_rate": 9.485521001986961e-06, "epoch": 0.5140640155189137, "percentage": 17.14, "elapsed_time": "8:26:14", "remaining_time": "1 day, 16:48:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 540, "total_steps": 3093, "loss": 0.1513, "learning_rate": 9.46214189061859e-06, "epoch": 0.5237633365664404, "percentage": 17.46, "elapsed_time": "8:35:42", "remaining_time": "1 day, 16:38:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 550, "total_steps": 3093, "loss": 0.1489, "learning_rate": 9.438273455108145e-06, "epoch": 0.533462657613967, "percentage": 17.78, "elapsed_time": "8:45:11", "remaining_time": "1 day, 16:28:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 560, "total_steps": 3093, "loss": 0.1496, "learning_rate": 9.41391831289855e-06, "epoch": 0.5431619786614937, "percentage": 18.11, "elapsed_time": "8:54:40", "remaining_time": "1 day, 16:18:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 570, "total_steps": 3093, "loss": 0.1457, "learning_rate": 9.38907913480561e-06, "epoch": 0.5528612997090203, "percentage": 18.43, "elapsed_time": "9:04:09", "remaining_time": "1 day, 16:08:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 580, "total_steps": 3093, "loss": 0.1443, "learning_rate": 9.36375864472511e-06, "epoch": 0.562560620756547, "percentage": 18.75, "elapsed_time": "9:13:37", "remaining_time": "1 day, 15:58:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 590, "total_steps": 3093, "loss": 0.1476, "learning_rate": 9.337959619334125e-06, "epoch": 0.5722599418040737, "percentage": 19.08, "elapsed_time": "9:23:06", "remaining_time": "1 day, 15:48:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 600, "total_steps": 3093, "loss": 0.1476, "learning_rate": 9.31168488778652e-06, "epoch": 0.5819592628516004, "percentage": 19.4, "elapsed_time": "9:32:35", "remaining_time": "1 day, 15:39:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 610, "total_steps": 3093, "loss": 0.1468, "learning_rate": 9.284937331402697e-06, "epoch": 0.5916585838991271, "percentage": 19.72, "elapsed_time": "9:42:03", "remaining_time": "1 day, 15:29:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 620, "total_steps": 3093, "loss": 0.1482, "learning_rate": 9.25771988335363e-06, "epoch": 0.6013579049466538, "percentage": 20.05, "elapsed_time": "9:51:32", "remaining_time": "1 day, 15:19:29", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 630, "total_steps": 3093, "loss": 0.1455, "learning_rate": 9.230035528339212e-06, "epoch": 0.6110572259941804, "percentage": 20.37, "elapsed_time": "10:01:01", "remaining_time": "1 day, 15:09:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 640, "total_steps": 3093, "loss": 0.1485, "learning_rate": 9.201887302260943e-06, "epoch": 0.6207565470417071, "percentage": 20.69, "elapsed_time": "10:10:29", "remaining_time": "1 day, 14:59:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 650, "total_steps": 3093, "loss": 0.1466, "learning_rate": 9.173278291889016e-06, "epoch": 0.6304558680892337, "percentage": 21.02, "elapsed_time": "10:19:58", "remaining_time": "1 day, 14:50:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 660, "total_steps": 3093, "loss": 0.1466, "learning_rate": 9.14421163452381e-06, "epoch": 0.6401551891367604, "percentage": 21.34, "elapsed_time": "10:29:27", "remaining_time": "1 day, 14:40:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 670, "total_steps": 3093, "loss": 0.1464, "learning_rate": 9.11469051765186e-06, "epoch": 0.6498545101842871, "percentage": 21.66, "elapsed_time": "10:38:56", "remaining_time": "1 day, 14:30:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 680, "total_steps": 3093, "loss": 0.1452, "learning_rate": 9.084718178596301e-06, "epoch": 0.6595538312318138, "percentage": 21.99, "elapsed_time": "10:48:25", "remaining_time": "1 day, 14:20:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 690, "total_steps": 3093, "loss": 0.1439, "learning_rate": 9.054297904161868e-06, "epoch": 0.6692531522793405, "percentage": 22.31, "elapsed_time": "10:57:54", "remaining_time": "1 day, 14:11:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 700, "total_steps": 3093, "loss": 0.1465, "learning_rate": 9.02343303027446e-06, "epoch": 0.6789524733268671, "percentage": 22.63, "elapsed_time": "11:07:23", "remaining_time": "1 day, 14:01:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 710, "total_steps": 3093, "loss": 0.1458, "learning_rate": 8.992126941615314e-06, "epoch": 0.6886517943743938, "percentage": 22.96, "elapsed_time": "11:16:52", "remaining_time": "1 day, 13:51:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 720, "total_steps": 3093, "loss": 0.1451, "learning_rate": 8.960383071249837e-06, "epoch": 0.6983511154219205, "percentage": 23.28, "elapsed_time": "11:26:21", "remaining_time": "1 day, 13:42:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 730, "total_steps": 3093, "loss": 0.1452, "learning_rate": 8.928204900251136e-06, "epoch": 0.7080504364694471, "percentage": 23.6, "elapsed_time": "11:35:49", "remaining_time": "1 day, 13:32:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 740, "total_steps": 3093, "loss": 0.146, "learning_rate": 8.895595957318277e-06, "epoch": 0.7177497575169738, "percentage": 23.92, "elapsed_time": "11:45:18", "remaining_time": "1 day, 13:22:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 750, "total_steps": 3093, "loss": 0.1418, "learning_rate": 8.862559818389322e-06, "epoch": 0.7274490785645005, "percentage": 24.25, "elapsed_time": "11:54:47", "remaining_time": "1 day, 13:12:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 760, "total_steps": 3093, "loss": 0.1429, "learning_rate": 8.829100106249189e-06, "epoch": 0.7371483996120272, "percentage": 24.57, "elapsed_time": "12:04:15", "remaining_time": "1 day, 13:03:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 770, "total_steps": 3093, "loss": 0.1461, "learning_rate": 8.795220490132369e-06, "epoch": 0.7468477206595538, "percentage": 24.89, "elapsed_time": "12:13:44", "remaining_time": "1 day, 12:53:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 780, "total_steps": 3093, "loss": 0.1426, "learning_rate": 8.760924685320558e-06, "epoch": 0.7565470417070805, "percentage": 25.22, "elapsed_time": "12:23:13", "remaining_time": "1 day, 12:43:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 790, "total_steps": 3093, "loss": 0.1427, "learning_rate": 8.726216452735233e-06, "epoch": 0.7662463627546072, "percentage": 25.54, "elapsed_time": "12:32:41", "remaining_time": "1 day, 12:34:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 800, "total_steps": 3093, "loss": 0.1425, "learning_rate": 8.691099598525222e-06, "epoch": 0.7759456838021338, "percentage": 25.86, "elapsed_time": "12:42:10", "remaining_time": "1 day, 12:24:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 810, "total_steps": 3093, "loss": 0.1447, "learning_rate": 8.655577973649322e-06, "epoch": 0.7856450048496605, "percentage": 26.19, "elapsed_time": "12:51:39", "remaining_time": "1 day, 12:14:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 820, "total_steps": 3093, "loss": 0.1431, "learning_rate": 8.61965547345399e-06, "epoch": 0.7953443258971872, "percentage": 26.51, "elapsed_time": "13:01:07", "remaining_time": "1 day, 12:05:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 830, "total_steps": 3093, "loss": 0.1436, "learning_rate": 8.583336037246187e-06, "epoch": 0.8050436469447139, "percentage": 26.83, "elapsed_time": "13:10:36", "remaining_time": "1 day, 11:55:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 840, "total_steps": 3093, "loss": 0.1447, "learning_rate": 8.54662364786137e-06, "epoch": 0.8147429679922406, "percentage": 27.16, "elapsed_time": "13:20:05", "remaining_time": "1 day, 11:45:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 850, "total_steps": 3093, "loss": 0.139, "learning_rate": 8.509522331226751e-06, "epoch": 0.8244422890397672, "percentage": 27.48, "elapsed_time": "13:29:33", "remaining_time": "1 day, 11:36:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 860, "total_steps": 3093, "loss": 0.1427, "learning_rate": 8.47203615591979e-06, "epoch": 0.8341416100872939, "percentage": 27.8, "elapsed_time": "13:39:02", "remaining_time": "1 day, 11:26:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 870, "total_steps": 3093, "loss": 0.1404, "learning_rate": 8.434169232722043e-06, "epoch": 0.8438409311348206, "percentage": 28.13, "elapsed_time": "13:48:31", "remaining_time": "1 day, 11:17:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 880, "total_steps": 3093, "loss": 0.1412, "learning_rate": 8.395925714168356e-06, "epoch": 0.8535402521823472, "percentage": 28.45, "elapsed_time": "13:58:00", "remaining_time": "1 day, 11:07:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 890, "total_steps": 3093, "loss": 0.1413, "learning_rate": 8.357309794091508e-06, "epoch": 0.8632395732298739, "percentage": 28.77, "elapsed_time": "14:07:28", "remaining_time": "1 day, 10:57:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 900, "total_steps": 3093, "loss": 0.1413, "learning_rate": 8.318325707162293e-06, "epoch": 0.8729388942774006, "percentage": 29.1, "elapsed_time": "14:16:57", "remaining_time": "1 day, 10:48:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 910, "total_steps": 3093, "loss": 0.1419, "learning_rate": 8.278977728425157e-06, "epoch": 0.8826382153249273, "percentage": 29.42, "elapsed_time": "14:26:26", "remaining_time": "1 day, 10:38:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 920, "total_steps": 3093, "loss": 0.1416, "learning_rate": 8.239270172829379e-06, "epoch": 0.8923375363724539, "percentage": 29.74, "elapsed_time": "14:35:55", "remaining_time": "1 day, 10:28:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 930, "total_steps": 3093, "loss": 0.1407, "learning_rate": 8.199207394755892e-06, "epoch": 0.9020368574199806, "percentage": 30.07, "elapsed_time": "14:45:24", "remaining_time": "1 day, 10:19:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 940, "total_steps": 3093, "loss": 0.1426, "learning_rate": 8.158793787539782e-06, "epoch": 0.9117361784675073, "percentage": 30.39, "elapsed_time": "14:54:52", "remaining_time": "1 day, 10:09:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 950, "total_steps": 3093, "loss": 0.1425, "learning_rate": 8.118033782988496e-06, "epoch": 0.9214354995150339, "percentage": 30.71, "elapsed_time": "15:04:21", "remaining_time": "1 day, 10:00:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 960, "total_steps": 3093, "loss": 0.1406, "learning_rate": 8.076931850895858e-06, "epoch": 0.9311348205625606, "percentage": 31.04, "elapsed_time": "15:13:50", "remaining_time": "1 day, 9:50:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 970, "total_steps": 3093, "loss": 0.1404, "learning_rate": 8.0354924985519e-06, "epoch": 0.9408341416100873, "percentage": 31.36, "elapsed_time": "15:23:19", "remaining_time": "1 day, 9:40:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 980, "total_steps": 3093, "loss": 0.1367, "learning_rate": 7.993720270248583e-06, "epoch": 0.950533462657614, "percentage": 31.68, "elapsed_time": "15:32:47", "remaining_time": "1 day, 9:31:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 990, "total_steps": 3093, "loss": 0.1404, "learning_rate": 7.951619746781474e-06, "epoch": 0.9602327837051406, "percentage": 32.01, "elapsed_time": "15:42:16", "remaining_time": "1 day, 9:21:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1000, "total_steps": 3093, "loss": 0.1379, "learning_rate": 7.909195544947398e-06, "epoch": 0.9699321047526673, "percentage": 32.33, "elapsed_time": "15:51:45", "remaining_time": "1 day, 9:12:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1010, "total_steps": 3093, "loss": 0.1407, "learning_rate": 7.866452317038164e-06, "epoch": 0.979631425800194, "percentage": 32.65, "elapsed_time": "16:04:58", "remaining_time": "1 day, 9:10:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1020, "total_steps": 3093, "loss": 0.1378, "learning_rate": 7.823394750330386e-06, "epoch": 0.9893307468477207, "percentage": 32.98, "elapsed_time": "16:14:26", "remaining_time": "1 day, 9:00:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1030, "total_steps": 3093, "loss": 0.1381, "learning_rate": 7.780027566571467e-06, "epoch": 0.9990300678952473, "percentage": 33.3, "elapsed_time": "16:23:55", "remaining_time": "1 day, 8:50:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1040, "total_steps": 3093, "loss": 0.1289, "learning_rate": 7.736355521461812e-06, "epoch": 1.008729388942774, "percentage": 33.62, "elapsed_time": "16:33:30", "remaining_time": "1 day, 8:41:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1050, "total_steps": 3093, "loss": 0.1251, "learning_rate": 7.692383404133302e-06, "epoch": 1.0184287099903007, "percentage": 33.95, "elapsed_time": "16:42:58", "remaining_time": "1 day, 8:31:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1060, "total_steps": 3093, "loss": 0.1256, "learning_rate": 7.648116036624125e-06, "epoch": 1.0281280310378274, "percentage": 34.27, "elapsed_time": "16:52:27", "remaining_time": "1 day, 8:21:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1070, "total_steps": 3093, "loss": 0.1255, "learning_rate": 7.6035582733499805e-06, "epoch": 1.037827352085354, "percentage": 34.59, "elapsed_time": "17:01:55", "remaining_time": "1 day, 8:12:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1080, "total_steps": 3093, "loss": 0.1241, "learning_rate": 7.5587150005717256e-06, "epoch": 1.0475266731328807, "percentage": 34.92, "elapsed_time": "17:11:24", "remaining_time": "1 day, 8:02:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1090, "total_steps": 3093, "loss": 0.1273, "learning_rate": 7.5135911358595615e-06, "epoch": 1.0572259941804074, "percentage": 35.24, "elapsed_time": "17:20:53", "remaining_time": "1 day, 7:52:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1100, "total_steps": 3093, "loss": 0.1264, "learning_rate": 7.468191627553752e-06, "epoch": 1.066925315227934, "percentage": 35.56, "elapsed_time": "17:30:21", "remaining_time": "1 day, 7:43:03", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1110, "total_steps": 3093, "loss": 0.1293, "learning_rate": 7.42252145422199e-06, "epoch": 1.0766246362754608, "percentage": 35.89, "elapsed_time": "17:39:50", "remaining_time": "1 day, 7:33:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1120, "total_steps": 3093, "loss": 0.1244, "learning_rate": 7.376585624113438e-06, "epoch": 1.0863239573229875, "percentage": 36.21, "elapsed_time": "17:49:19", "remaining_time": "1 day, 7:23:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1130, "total_steps": 3093, "loss": 0.1264, "learning_rate": 7.330389174609516e-06, "epoch": 1.0960232783705142, "percentage": 36.53, "elapsed_time": "17:58:47", "remaining_time": "1 day, 7:14:03", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1140, "total_steps": 3093, "loss": 0.128, "learning_rate": 7.283937171671498e-06, "epoch": 1.1057225994180406, "percentage": 36.86, "elapsed_time": "18:08:16", "remaining_time": "1 day, 7:04:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1150, "total_steps": 3093, "loss": 0.1268, "learning_rate": 7.2372347092849744e-06, "epoch": 1.1154219204655673, "percentage": 37.18, "elapsed_time": "18:17:45", "remaining_time": "1 day, 6:54:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1160, "total_steps": 3093, "loss": 0.127, "learning_rate": 7.190286908901234e-06, "epoch": 1.125121241513094, "percentage": 37.5, "elapsed_time": "18:27:14", "remaining_time": "1 day, 6:45:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1170, "total_steps": 3093, "loss": 0.1239, "learning_rate": 7.143098918875643e-06, "epoch": 1.1348205625606207, "percentage": 37.83, "elapsed_time": "18:36:42", "remaining_time": "1 day, 6:35:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1180, "total_steps": 3093, "loss": 0.1252, "learning_rate": 7.095675913903067e-06, "epoch": 1.1445198836081474, "percentage": 38.15, "elapsed_time": "18:46:11", "remaining_time": "1 day, 6:25:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1190, "total_steps": 3093, "loss": 0.1255, "learning_rate": 7.048023094450412e-06, "epoch": 1.154219204655674, "percentage": 38.47, "elapsed_time": "18:55:40", "remaining_time": "1 day, 6:16:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1200, "total_steps": 3093, "loss": 0.125, "learning_rate": 7.0001456861863236e-06, "epoch": 1.1639185257032008, "percentage": 38.8, "elapsed_time": "19:05:08", "remaining_time": "1 day, 6:06:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1210, "total_steps": 3093, "loss": 0.126, "learning_rate": 6.952048939408156e-06, "epoch": 1.1736178467507274, "percentage": 39.12, "elapsed_time": "19:14:37", "remaining_time": "1 day, 5:56:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1220, "total_steps": 3093, "loss": 0.1244, "learning_rate": 6.903738128466189e-06, "epoch": 1.1833171677982541, "percentage": 39.44, "elapsed_time": "19:24:07", "remaining_time": "1 day, 5:47:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1230, "total_steps": 3093, "loss": 0.1257, "learning_rate": 6.8552185511852555e-06, "epoch": 1.1930164888457808, "percentage": 39.77, "elapsed_time": "19:33:36", "remaining_time": "1 day, 5:37:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1240, "total_steps": 3093, "loss": 0.1247, "learning_rate": 6.806495528283772e-06, "epoch": 1.2027158098933075, "percentage": 40.09, "elapsed_time": "19:43:04", "remaining_time": "1 day, 5:27:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1250, "total_steps": 3093, "loss": 0.1266, "learning_rate": 6.75757440279026e-06, "epoch": 1.2124151309408342, "percentage": 40.41, "elapsed_time": "19:52:33", "remaining_time": "1 day, 5:18:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1260, "total_steps": 3093, "loss": 0.1259, "learning_rate": 6.708460539457418e-06, "epoch": 1.2221144519883609, "percentage": 40.74, "elapsed_time": "20:02:02", "remaining_time": "1 day, 5:08:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1270, "total_steps": 3093, "loss": 0.1264, "learning_rate": 6.659159324173823e-06, "epoch": 1.2318137730358876, "percentage": 41.06, "elapsed_time": "20:11:30", "remaining_time": "1 day, 4:59:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1280, "total_steps": 3093, "loss": 0.1212, "learning_rate": 6.6096761633733065e-06, "epoch": 1.2415130940834143, "percentage": 41.38, "elapsed_time": "20:20:59", "remaining_time": "1 day, 4:49:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1290, "total_steps": 3093, "loss": 0.1232, "learning_rate": 6.5600164834420754e-06, "epoch": 1.251212415130941, "percentage": 41.71, "elapsed_time": "20:30:27", "remaining_time": "1 day, 4:39:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1300, "total_steps": 3093, "loss": 0.1246, "learning_rate": 6.510185730123646e-06, "epoch": 1.2609117361784676, "percentage": 42.03, "elapsed_time": "20:39:56", "remaining_time": "1 day, 4:30:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1310, "total_steps": 3093, "loss": 0.1222, "learning_rate": 6.460189367921663e-06, "epoch": 1.270611057225994, "percentage": 42.35, "elapsed_time": "20:49:25", "remaining_time": "1 day, 4:20:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1320, "total_steps": 3093, "loss": 0.1237, "learning_rate": 6.410032879500647e-06, "epoch": 1.2803103782735208, "percentage": 42.68, "elapsed_time": "20:58:53", "remaining_time": "1 day, 4:10:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1330, "total_steps": 3093, "loss": 0.1246, "learning_rate": 6.35972176508477e-06, "epoch": 1.2900096993210475, "percentage": 43.0, "elapsed_time": "21:08:22", "remaining_time": "1 day, 4:01:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1340, "total_steps": 3093, "loss": 0.1246, "learning_rate": 6.309261541854679e-06, "epoch": 1.2997090203685742, "percentage": 43.32, "elapsed_time": "21:17:51", "remaining_time": "1 day, 3:51:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1350, "total_steps": 3093, "loss": 0.1214, "learning_rate": 6.258657743342486e-06, "epoch": 1.3094083414161009, "percentage": 43.65, "elapsed_time": "21:27:19", "remaining_time": "1 day, 3:42:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1360, "total_steps": 3093, "loss": 0.1261, "learning_rate": 6.207915918824952e-06, "epoch": 1.3191076624636275, "percentage": 43.97, "elapsed_time": "21:36:48", "remaining_time": "1 day, 3:32:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1370, "total_steps": 3093, "loss": 0.1255, "learning_rate": 6.157041632714945e-06, "epoch": 1.3288069835111542, "percentage": 44.29, "elapsed_time": "21:46:17", "remaining_time": "1 day, 3:22:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1380, "total_steps": 3093, "loss": 0.1236, "learning_rate": 6.106040463951237e-06, "epoch": 1.338506304558681, "percentage": 44.62, "elapsed_time": "21:55:45", "remaining_time": "1 day, 3:13:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1390, "total_steps": 3093, "loss": 0.1198, "learning_rate": 6.0549180053867114e-06, "epoch": 1.3482056256062076, "percentage": 44.94, "elapsed_time": "22:05:14", "remaining_time": "1 day, 3:03:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1400, "total_steps": 3093, "loss": 0.1241, "learning_rate": 6.003679863175052e-06, "epoch": 1.3579049466537343, "percentage": 45.26, "elapsed_time": "22:14:43", "remaining_time": "1 day, 2:54:03", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1410, "total_steps": 3093, "loss": 0.1263, "learning_rate": 5.952331656155951e-06, "epoch": 1.367604267701261, "percentage": 45.59, "elapsed_time": "22:24:11", "remaining_time": "1 day, 2:44:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1420, "total_steps": 3093, "loss": 0.126, "learning_rate": 5.900879015238948e-06, "epoch": 1.3773035887487877, "percentage": 45.91, "elapsed_time": "22:33:40", "remaining_time": "1 day, 2:34:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1430, "total_steps": 3093, "loss": 0.1269, "learning_rate": 5.849327582785943e-06, "epoch": 1.3870029097963141, "percentage": 46.23, "elapsed_time": "22:43:09", "remaining_time": "1 day, 2:25:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1440, "total_steps": 3093, "loss": 0.1203, "learning_rate": 5.797683011992432e-06, "epoch": 1.3967022308438408, "percentage": 46.56, "elapsed_time": "22:52:38", "remaining_time": "1 day, 2:15:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1450, "total_steps": 3093, "loss": 0.1248, "learning_rate": 5.745950966267586e-06, "epoch": 1.4064015518913675, "percentage": 46.88, "elapsed_time": "23:02:07", "remaining_time": "1 day, 2:06:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1460, "total_steps": 3093, "loss": 0.1208, "learning_rate": 5.694137118613185e-06, "epoch": 1.4161008729388942, "percentage": 47.2, "elapsed_time": "23:11:36", "remaining_time": "1 day, 1:56:29", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1470, "total_steps": 3093, "loss": 0.1219, "learning_rate": 5.642247151001515e-06, "epoch": 1.4258001939864209, "percentage": 47.53, "elapsed_time": "23:21:05", "remaining_time": "1 day, 1:46:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1480, "total_steps": 3093, "loss": 0.1246, "learning_rate": 5.590286753752269e-06, "epoch": 1.4354995150339476, "percentage": 47.85, "elapsed_time": "23:30:33", "remaining_time": "1 day, 1:37:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1490, "total_steps": 3093, "loss": 0.1238, "learning_rate": 5.5382616249085476e-06, "epoch": 1.4451988360814743, "percentage": 48.17, "elapsed_time": "23:40:02", "remaining_time": "1 day, 1:27:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1500, "total_steps": 3093, "loss": 0.1218, "learning_rate": 5.486177469611999e-06, "epoch": 1.454898157129001, "percentage": 48.5, "elapsed_time": "23:49:31", "remaining_time": "1 day, 1:18:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1510, "total_steps": 3093, "loss": 0.1217, "learning_rate": 5.434039999477182e-06, "epoch": 1.4645974781765276, "percentage": 48.82, "elapsed_time": "1 day, 0:03:06", "remaining_time": "1 day, 1:12:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1520, "total_steps": 3093, "loss": 0.1212, "learning_rate": 5.381854931965238e-06, "epoch": 1.4742967992240543, "percentage": 49.14, "elapsed_time": "1 day, 0:12:35", "remaining_time": "1 day, 1:03:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1530, "total_steps": 3093, "loss": 0.1221, "learning_rate": 5.32962798975689e-06, "epoch": 1.483996120271581, "percentage": 49.47, "elapsed_time": "1 day, 0:22:03", "remaining_time": "1 day, 0:53:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1540, "total_steps": 3093, "loss": 0.1201, "learning_rate": 5.2773649001248965e-06, "epoch": 1.4936954413191077, "percentage": 49.79, "elapsed_time": "1 day, 0:31:32", "remaining_time": "1 day, 0:43:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1550, "total_steps": 3093, "loss": 0.1222, "learning_rate": 5.2250713943059826e-06, "epoch": 1.5033947623666344, "percentage": 50.11, "elapsed_time": "1 day, 0:41:01", "remaining_time": "1 day, 0:34:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1560, "total_steps": 3093, "loss": 0.1209, "learning_rate": 5.172753206872363e-06, "epoch": 1.513094083414161, "percentage": 50.44, "elapsed_time": "1 day, 0:50:30", "remaining_time": "1 day, 0:24:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1570, "total_steps": 3093, "loss": 0.1257, "learning_rate": 5.120416075102855e-06, "epoch": 1.5227934044616878, "percentage": 50.76, "elapsed_time": "1 day, 0:59:58", "remaining_time": "1 day, 0:15:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1580, "total_steps": 3093, "loss": 0.124, "learning_rate": 5.068065738353748e-06, "epoch": 1.5324927255092144, "percentage": 51.08, "elapsed_time": "1 day, 1:09:27", "remaining_time": "1 day, 0:05:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1590, "total_steps": 3093, "loss": 0.1192, "learning_rate": 5.015707937429398e-06, "epoch": 1.5421920465567411, "percentage": 51.41, "elapsed_time": "1 day, 1:18:56", "remaining_time": "23:55:49", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1600, "total_steps": 3093, "loss": 0.1225, "learning_rate": 4.9633484139526975e-06, "epoch": 1.5518913676042678, "percentage": 51.73, "elapsed_time": "1 day, 1:28:24", "remaining_time": "23:46:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1610, "total_steps": 3093, "loss": 0.1201, "learning_rate": 4.910992909735432e-06, "epoch": 1.5615906886517945, "percentage": 52.05, "elapsed_time": "1 day, 1:37:53", "remaining_time": "23:36:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1620, "total_steps": 3093, "loss": 0.1227, "learning_rate": 4.8586471661486345e-06, "epoch": 1.5712900096993212, "percentage": 52.38, "elapsed_time": "1 day, 1:47:22", "remaining_time": "23:26:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1630, "total_steps": 3093, "loss": 0.1232, "learning_rate": 4.80631692349297e-06, "epoch": 1.5809893307468477, "percentage": 52.7, "elapsed_time": "1 day, 1:56:51", "remaining_time": "23:17:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1640, "total_steps": 3093, "loss": 0.1213, "learning_rate": 4.754007920369252e-06, "epoch": 1.5906886517943744, "percentage": 53.02, "elapsed_time": "1 day, 2:06:19", "remaining_time": "23:07:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1650, "total_steps": 3093, "loss": 0.1194, "learning_rate": 4.7017258930491474e-06, "epoch": 1.600387972841901, "percentage": 53.35, "elapsed_time": "1 day, 2:15:48", "remaining_time": "22:58:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1660, "total_steps": 3093, "loss": 0.1206, "learning_rate": 4.649476574846113e-06, "epoch": 1.6100872938894277, "percentage": 53.67, "elapsed_time": "1 day, 2:25:17", "remaining_time": "22:48:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1670, "total_steps": 3093, "loss": 0.122, "learning_rate": 4.597265695486685e-06, "epoch": 1.6197866149369544, "percentage": 53.99, "elapsed_time": "1 day, 2:34:45", "remaining_time": "22:38:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1680, "total_steps": 3093, "loss": 0.1217, "learning_rate": 4.545098980482151e-06, "epoch": 1.629485935984481, "percentage": 54.32, "elapsed_time": "1 day, 2:44:14", "remaining_time": "22:29:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1690, "total_steps": 3093, "loss": 0.1222, "learning_rate": 4.492982150500677e-06, "epoch": 1.6391852570320078, "percentage": 54.64, "elapsed_time": "1 day, 2:53:43", "remaining_time": "22:19:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1700, "total_steps": 3093, "loss": 0.1203, "learning_rate": 4.44092092073997e-06, "epoch": 1.6488845780795345, "percentage": 54.96, "elapsed_time": "1 day, 3:03:12", "remaining_time": "22:10:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1710, "total_steps": 3093, "loss": 0.1195, "learning_rate": 4.388921000300553e-06, "epoch": 1.658583899127061, "percentage": 55.29, "elapsed_time": "1 day, 3:12:40", "remaining_time": "22:00:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1720, "total_steps": 3093, "loss": 0.1179, "learning_rate": 4.336988091559688e-06, "epoch": 1.6682832201745876, "percentage": 55.61, "elapsed_time": "1 day, 3:22:09", "remaining_time": "21:50:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1730, "total_steps": 3093, "loss": 0.1214, "learning_rate": 4.285127889546049e-06, "epoch": 1.6779825412221143, "percentage": 55.93, "elapsed_time": "1 day, 3:31:38", "remaining_time": "21:41:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1740, "total_steps": 3093, "loss": 0.1197, "learning_rate": 4.233346081315197e-06, "epoch": 1.687681862269641, "percentage": 56.26, "elapsed_time": "1 day, 3:41:07", "remaining_time": "21:31:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1750, "total_steps": 3093, "loss": 0.1173, "learning_rate": 4.181648345325934e-06, "epoch": 1.6973811833171677, "percentage": 56.58, "elapsed_time": "1 day, 3:50:36", "remaining_time": "21:22:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1760, "total_steps": 3093, "loss": 0.1177, "learning_rate": 4.13004035081759e-06, "epoch": 1.7070805043646944, "percentage": 56.9, "elapsed_time": "1 day, 4:00:04", "remaining_time": "21:12:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1770, "total_steps": 3093, "loss": 0.1193, "learning_rate": 4.078527757188333e-06, "epoch": 1.716779825412221, "percentage": 57.23, "elapsed_time": "1 day, 4:09:33", "remaining_time": "21:02:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1780, "total_steps": 3093, "loss": 0.1237, "learning_rate": 4.02711621337455e-06, "epoch": 1.7264791464597478, "percentage": 57.55, "elapsed_time": "1 day, 4:19:03", "remaining_time": "20:53:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1790, "total_steps": 3093, "loss": 0.1189, "learning_rate": 3.9758113572313735e-06, "epoch": 1.7361784675072744, "percentage": 57.87, "elapsed_time": "1 day, 4:28:32", "remaining_time": "20:43:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1800, "total_steps": 3093, "loss": 0.119, "learning_rate": 3.924618814914435e-06, "epoch": 1.7458777885548011, "percentage": 58.2, "elapsed_time": "1 day, 4:38:00", "remaining_time": "20:34:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1810, "total_steps": 3093, "loss": 0.1202, "learning_rate": 3.873544200262882e-06, "epoch": 1.7555771096023278, "percentage": 58.52, "elapsed_time": "1 day, 4:47:29", "remaining_time": "20:24:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1820, "total_steps": 3093, "loss": 0.1203, "learning_rate": 3.822593114183777e-06, "epoch": 1.7652764306498545, "percentage": 58.84, "elapsed_time": "1 day, 4:56:58", "remaining_time": "20:14:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1830, "total_steps": 3093, "loss": 0.1197, "learning_rate": 3.7717711440378695e-06, "epoch": 1.7749757516973812, "percentage": 59.17, "elapsed_time": "1 day, 5:06:27", "remaining_time": "20:05:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1840, "total_steps": 3093, "loss": 0.1185, "learning_rate": 3.7210838630268986e-06, "epoch": 1.7846750727449079, "percentage": 59.49, "elapsed_time": "1 day, 5:15:55", "remaining_time": "19:55:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1850, "total_steps": 3093, "loss": 0.1191, "learning_rate": 3.670536829582424e-06, "epoch": 1.7943743937924346, "percentage": 59.81, "elapsed_time": "1 day, 5:25:24", "remaining_time": "19:46:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1860, "total_steps": 3093, "loss": 0.1191, "learning_rate": 3.6201355867562725e-06, "epoch": 1.8040737148399613, "percentage": 60.14, "elapsed_time": "1 day, 5:34:53", "remaining_time": "19:36:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1870, "total_steps": 3093, "loss": 0.1195, "learning_rate": 3.569885661612691e-06, "epoch": 1.813773035887488, "percentage": 60.46, "elapsed_time": "1 day, 5:44:22", "remaining_time": "19:26:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1880, "total_steps": 3093, "loss": 0.1204, "learning_rate": 3.5197925646222387e-06, "epoch": 1.8234723569350146, "percentage": 60.78, "elapsed_time": "1 day, 5:53:51", "remaining_time": "19:17:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1890, "total_steps": 3093, "loss": 0.1187, "learning_rate": 3.4698617890574972e-06, "epoch": 1.8331716779825413, "percentage": 61.11, "elapsed_time": "1 day, 6:03:19", "remaining_time": "19:07:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1900, "total_steps": 3093, "loss": 0.1181, "learning_rate": 3.4200988103906747e-06, "epoch": 1.842870999030068, "percentage": 61.43, "elapsed_time": "1 day, 6:12:48", "remaining_time": "18:58:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1910, "total_steps": 3093, "loss": 0.1189, "learning_rate": 3.3705090856931626e-06, "epoch": 1.8525703200775947, "percentage": 61.75, "elapsed_time": "1 day, 6:22:17", "remaining_time": "18:48:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1920, "total_steps": 3093, "loss": 0.1163, "learning_rate": 3.3210980530370974e-06, "epoch": 1.8622696411251214, "percentage": 62.08, "elapsed_time": "1 day, 6:31:46", "remaining_time": "18:39:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1930, "total_steps": 3093, "loss": 0.1173, "learning_rate": 3.2718711308990226e-06, "epoch": 1.871968962172648, "percentage": 62.4, "elapsed_time": "1 day, 6:41:15", "remaining_time": "18:29:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1940, "total_steps": 3093, "loss": 0.1175, "learning_rate": 3.2228337175656856e-06, "epoch": 1.8816682832201745, "percentage": 62.72, "elapsed_time": "1 day, 6:50:43", "remaining_time": "18:19:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1950, "total_steps": 3093, "loss": 0.1157, "learning_rate": 3.1739911905420617e-06, "epoch": 1.8913676042677012, "percentage": 63.05, "elapsed_time": "1 day, 7:00:12", "remaining_time": "18:10:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1960, "total_steps": 3093, "loss": 0.1206, "learning_rate": 3.1253489059616448e-06, "epoch": 1.901066925315228, "percentage": 63.37, "elapsed_time": "1 day, 7:09:41", "remaining_time": "18:00:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1970, "total_steps": 3093, "loss": 0.1176, "learning_rate": 3.0769121979990845e-06, "epoch": 1.9107662463627546, "percentage": 63.69, "elapsed_time": "1 day, 7:19:09", "remaining_time": "17:51:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1980, "total_steps": 3093, "loss": 0.1188, "learning_rate": 3.028686378285245e-06, "epoch": 1.9204655674102813, "percentage": 64.02, "elapsed_time": "1 day, 7:28:38", "remaining_time": "17:41:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 1990, "total_steps": 3093, "loss": 0.1199, "learning_rate": 2.9806767353247127e-06, "epoch": 1.930164888457808, "percentage": 64.34, "elapsed_time": "1 day, 7:38:07", "remaining_time": "17:32:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2000, "total_steps": 3093, "loss": 0.118, "learning_rate": 2.9328885339158554e-06, "epoch": 1.9398642095053347, "percentage": 64.66, "elapsed_time": "1 day, 7:47:36", "remaining_time": "17:22:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2010, "total_steps": 3093, "loss": 0.1185, "learning_rate": 2.8853270145734846e-06, "epoch": 1.9495635305528611, "percentage": 64.99, "elapsed_time": "1 day, 8:01:25", "remaining_time": "17:15:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2020, "total_steps": 3093, "loss": 0.116, "learning_rate": 2.837997392954165e-06, "epoch": 1.9592628516003878, "percentage": 65.31, "elapsed_time": "1 day, 8:10:54", "remaining_time": "17:05:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2030, "total_steps": 3093, "loss": 0.1152, "learning_rate": 2.7909048592842602e-06, "epoch": 1.9689621726479145, "percentage": 65.63, "elapsed_time": "1 day, 8:20:23", "remaining_time": "16:56:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2040, "total_steps": 3093, "loss": 0.1159, "learning_rate": 2.7440545777907747e-06, "epoch": 1.9786614936954412, "percentage": 65.96, "elapsed_time": "1 day, 8:29:51", "remaining_time": "16:46:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2050, "total_steps": 3093, "loss": 0.1186, "learning_rate": 2.697451686135031e-06, "epoch": 1.9883608147429679, "percentage": 66.28, "elapsed_time": "1 day, 8:39:21", "remaining_time": "16:36:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2060, "total_steps": 3093, "loss": 0.1172, "learning_rate": 2.6511012948492625e-06, "epoch": 1.9980601357904946, "percentage": 66.6, "elapsed_time": "1 day, 8:48:49", "remaining_time": "16:27:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2070, "total_steps": 3093, "loss": 0.1045, "learning_rate": 2.6050084867761953e-06, "epoch": 2.0077594568380213, "percentage": 66.93, "elapsed_time": "1 day, 8:58:25", "remaining_time": "16:17:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2080, "total_steps": 3093, "loss": 0.105, "learning_rate": 2.5591783165116563e-06, "epoch": 2.017458777885548, "percentage": 67.25, "elapsed_time": "1 day, 9:07:54", "remaining_time": "16:08:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2090, "total_steps": 3093, "loss": 0.1038, "learning_rate": 2.51361580985027e-06, "epoch": 2.0271580989330746, "percentage": 67.57, "elapsed_time": "1 day, 9:17:23", "remaining_time": "15:58:33", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2100, "total_steps": 3093, "loss": 0.101, "learning_rate": 2.4683259632343363e-06, "epoch": 2.0368574199806013, "percentage": 67.9, "elapsed_time": "1 day, 9:26:52", "remaining_time": "15:48:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2110, "total_steps": 3093, "loss": 0.1023, "learning_rate": 2.42331374320591e-06, "epoch": 2.046556741028128, "percentage": 68.22, "elapsed_time": "1 day, 9:36:20", "remaining_time": "15:39:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2120, "total_steps": 3093, "loss": 0.1038, "learning_rate": 2.3785840858621556e-06, "epoch": 2.0562560620756547, "percentage": 68.54, "elapsed_time": "1 day, 9:45:49", "remaining_time": "15:29:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2130, "total_steps": 3093, "loss": 0.1015, "learning_rate": 2.334141896314057e-06, "epoch": 2.0659553831231814, "percentage": 68.87, "elapsed_time": "1 day, 9:55:18", "remaining_time": "15:20:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2140, "total_steps": 3093, "loss": 0.1006, "learning_rate": 2.2899920481485192e-06, "epoch": 2.075654704170708, "percentage": 69.19, "elapsed_time": "1 day, 10:04:47", "remaining_time": "15:10:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2150, "total_steps": 3093, "loss": 0.103, "learning_rate": 2.246139382893915e-06, "epoch": 2.0853540252182348, "percentage": 69.51, "elapsed_time": "1 day, 10:14:15", "remaining_time": "15:01:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2160, "total_steps": 3093, "loss": 0.1021, "learning_rate": 2.2025887094891657e-06, "epoch": 2.0950533462657615, "percentage": 69.84, "elapsed_time": "1 day, 10:23:44", "remaining_time": "14:51:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2170, "total_steps": 3093, "loss": 0.1012, "learning_rate": 2.1593448037563795e-06, "epoch": 2.104752667313288, "percentage": 70.16, "elapsed_time": "1 day, 10:33:13", "remaining_time": "14:41:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2180, "total_steps": 3093, "loss": 0.0989, "learning_rate": 2.116412407877138e-06, "epoch": 2.114451988360815, "percentage": 70.48, "elapsed_time": "1 day, 10:42:42", "remaining_time": "14:32:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2190, "total_steps": 3093, "loss": 0.1028, "learning_rate": 2.0737962298724513e-06, "epoch": 2.1241513094083415, "percentage": 70.81, "elapsed_time": "1 day, 10:52:11", "remaining_time": "14:22:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2200, "total_steps": 3093, "loss": 0.0981, "learning_rate": 2.0315009430864762e-06, "epoch": 2.133850630455868, "percentage": 71.13, "elapsed_time": "1 day, 11:01:39", "remaining_time": "14:13:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2210, "total_steps": 3093, "loss": 0.1006, "learning_rate": 1.989531185674037e-06, "epoch": 2.143549951503395, "percentage": 71.45, "elapsed_time": "1 day, 11:11:08", "remaining_time": "14:03:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2220, "total_steps": 3093, "loss": 0.0994, "learning_rate": 1.9478915600919877e-06, "epoch": 2.1532492725509216, "percentage": 71.77, "elapsed_time": "1 day, 11:20:37", "remaining_time": "13:53:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2230, "total_steps": 3093, "loss": 0.1006, "learning_rate": 1.9065866325945099e-06, "epoch": 2.1629485935984483, "percentage": 72.1, "elapsed_time": "1 day, 11:30:05", "remaining_time": "13:44:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2240, "total_steps": 3093, "loss": 0.1032, "learning_rate": 1.8656209327323704e-06, "epoch": 2.172647914645975, "percentage": 72.42, "elapsed_time": "1 day, 11:39:34", "remaining_time": "13:34:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2250, "total_steps": 3093, "loss": 0.0995, "learning_rate": 1.824998952856198e-06, "epoch": 2.1823472356935016, "percentage": 72.74, "elapsed_time": "1 day, 11:49:03", "remaining_time": "13:25:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2260, "total_steps": 3093, "loss": 0.1014, "learning_rate": 1.784725147623853e-06, "epoch": 2.1920465567410283, "percentage": 73.07, "elapsed_time": "1 day, 11:58:32", "remaining_time": "13:15:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2270, "total_steps": 3093, "loss": 0.1002, "learning_rate": 1.7448039335119272e-06, "epoch": 2.2017458777885546, "percentage": 73.39, "elapsed_time": "1 day, 12:08:01", "remaining_time": "13:06:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2280, "total_steps": 3093, "loss": 0.1007, "learning_rate": 1.7052396883314154e-06, "epoch": 2.2114451988360813, "percentage": 73.71, "elapsed_time": "1 day, 12:17:29", "remaining_time": "12:56:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2290, "total_steps": 3093, "loss": 0.1032, "learning_rate": 1.6660367507476539e-06, "epoch": 2.221144519883608, "percentage": 74.04, "elapsed_time": "1 day, 12:26:58", "remaining_time": "12:46:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2300, "total_steps": 3093, "loss": 0.0974, "learning_rate": 1.627199419804522e-06, "epoch": 2.2308438409311346, "percentage": 74.36, "elapsed_time": "1 day, 12:36:27", "remaining_time": "12:37:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2310, "total_steps": 3093, "loss": 0.0993, "learning_rate": 1.5887319544530182e-06, "epoch": 2.2405431619786613, "percentage": 74.68, "elapsed_time": "1 day, 12:45:56", "remaining_time": "12:27:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2320, "total_steps": 3093, "loss": 0.0994, "learning_rate": 1.5506385730842062e-06, "epoch": 2.250242483026188, "percentage": 75.01, "elapsed_time": "1 day, 12:55:25", "remaining_time": "12:18:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2330, "total_steps": 3093, "loss": 0.0996, "learning_rate": 1.5129234530666232e-06, "epoch": 2.2599418040737147, "percentage": 75.33, "elapsed_time": "1 day, 13:04:54", "remaining_time": "12:08:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2340, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.4755907302881927e-06, "epoch": 2.2696411251212414, "percentage": 75.65, "elapsed_time": "1 day, 13:14:23", "remaining_time": "11:59:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2350, "total_steps": 3093, "loss": 0.1008, "learning_rate": 1.4386444987026705e-06, "epoch": 2.279340446168768, "percentage": 75.98, "elapsed_time": "1 day, 13:23:52", "remaining_time": "11:49:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2360, "total_steps": 3093, "loss": 0.1012, "learning_rate": 1.4020888098806924e-06, "epoch": 2.2890397672162948, "percentage": 76.3, "elapsed_time": "1 day, 13:33:21", "remaining_time": "11:39:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2370, "total_steps": 3093, "loss": 0.0994, "learning_rate": 1.3659276725654863e-06, "epoch": 2.2987390882638215, "percentage": 76.62, "elapsed_time": "1 day, 13:42:51", "remaining_time": "11:30:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2380, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.3301650522332566e-06, "epoch": 2.308438409311348, "percentage": 76.95, "elapsed_time": "1 day, 13:52:20", "remaining_time": "11:20:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2390, "total_steps": 3093, "loss": 0.1011, "learning_rate": 1.2948048706583284e-06, "epoch": 2.318137730358875, "percentage": 77.27, "elapsed_time": "1 day, 14:01:49", "remaining_time": "11:11:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2400, "total_steps": 3093, "loss": 0.1026, "learning_rate": 1.2598510054830888e-06, "epoch": 2.3278370514064015, "percentage": 77.59, "elapsed_time": "1 day, 14:11:17", "remaining_time": "11:01:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2410, "total_steps": 3093, "loss": 0.1004, "learning_rate": 1.2253072897927437e-06, "epoch": 2.337536372453928, "percentage": 77.92, "elapsed_time": "1 day, 14:20:46", "remaining_time": "10:52:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2420, "total_steps": 3093, "loss": 0.1026, "learning_rate": 1.1911775116949958e-06, "epoch": 2.347235693501455, "percentage": 78.24, "elapsed_time": "1 day, 14:30:15", "remaining_time": "10:42:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2430, "total_steps": 3093, "loss": 0.1004, "learning_rate": 1.1574654139046171e-06, "epoch": 2.3569350145489816, "percentage": 78.56, "elapsed_time": "1 day, 14:39:44", "remaining_time": "10:32:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2440, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.1241746933330338e-06, "epoch": 2.3666343355965083, "percentage": 78.89, "elapsed_time": "1 day, 14:49:12", "remaining_time": "10:23:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2450, "total_steps": 3093, "loss": 0.1004, "learning_rate": 1.0913090006829085e-06, "epoch": 2.376333656644035, "percentage": 79.21, "elapsed_time": "1 day, 14:58:41", "remaining_time": "10:13:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2460, "total_steps": 3093, "loss": 0.0977, "learning_rate": 1.0588719400478004e-06, "epoch": 2.3860329776915616, "percentage": 79.53, "elapsed_time": "1 day, 15:08:10", "remaining_time": "10:04:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2470, "total_steps": 3093, "loss": 0.1021, "learning_rate": 1.026867068516943e-06, "epoch": 2.3957322987390883, "percentage": 79.86, "elapsed_time": "1 day, 15:17:39", "remaining_time": "9:54:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2480, "total_steps": 3093, "loss": 0.098, "learning_rate": 9.952978957851622e-07, "epoch": 2.405431619786615, "percentage": 80.18, "elapsed_time": "1 day, 15:27:08", "remaining_time": "9:45:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2490, "total_steps": 3093, "loss": 0.1, "learning_rate": 9.641678837679985e-07, "epoch": 2.4151309408341417, "percentage": 80.5, "elapsed_time": "1 day, 15:36:36", "remaining_time": "9:35:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2500, "total_steps": 3093, "loss": 0.0968, "learning_rate": 9.334804462220748e-07, "epoch": 2.4248302618816684, "percentage": 80.83, "elapsed_time": "1 day, 15:46:05", "remaining_time": "9:25:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2510, "total_steps": 3093, "loss": 0.0985, "learning_rate": 9.032389483707332e-07, "epoch": 2.434529582929195, "percentage": 81.15, "elapsed_time": "1 day, 15:59:28", "remaining_time": "9:17:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2520, "total_steps": 3093, "loss": 0.1011, "learning_rate": 8.734467065350022e-07, "epoch": 2.4442289039767218, "percentage": 81.47, "elapsed_time": "1 day, 16:08:57", "remaining_time": "9:07:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2530, "total_steps": 3093, "loss": 0.0988, "learning_rate": 8.441069877699287e-07, "epoch": 2.4539282250242485, "percentage": 81.8, "elapsed_time": "1 day, 16:18:25", "remaining_time": "8:58:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2540, "total_steps": 3093, "loss": 0.1002, "learning_rate": 8.152230095063051e-07, "epoch": 2.463627546071775, "percentage": 82.12, "elapsed_time": "1 day, 16:27:54", "remaining_time": "8:48:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2550, "total_steps": 3093, "loss": 0.1007, "learning_rate": 7.867979391978398e-07, "epoch": 2.473326867119302, "percentage": 82.44, "elapsed_time": "1 day, 16:37:23", "remaining_time": "8:39:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2560, "total_steps": 3093, "loss": 0.0986, "learning_rate": 7.588348939738116e-07, "epoch": 2.4830261881668285, "percentage": 82.77, "elapsed_time": "1 day, 16:46:51", "remaining_time": "8:29:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2570, "total_steps": 3093, "loss": 0.0992, "learning_rate": 7.31336940297247e-07, "epoch": 2.492725509214355, "percentage": 83.09, "elapsed_time": "1 day, 16:56:21", "remaining_time": "8:19:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2580, "total_steps": 3093, "loss": 0.0978, "learning_rate": 7.043070936286395e-07, "epoch": 2.502424830261882, "percentage": 83.41, "elapsed_time": "1 day, 17:05:49", "remaining_time": "8:10:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2590, "total_steps": 3093, "loss": 0.1012, "learning_rate": 6.777483180952732e-07, "epoch": 2.5121241513094086, "percentage": 83.74, "elapsed_time": "1 day, 17:15:18", "remaining_time": "8:00:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2600, "total_steps": 3093, "loss": 0.0974, "learning_rate": 6.516635261661775e-07, "epoch": 2.5218234723569353, "percentage": 84.06, "elapsed_time": "1 day, 17:24:47", "remaining_time": "7:51:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2610, "total_steps": 3093, "loss": 0.0966, "learning_rate": 6.260555783327366e-07, "epoch": 2.531522793404462, "percentage": 84.38, "elapsed_time": "1 day, 17:34:16", "remaining_time": "7:41:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2620, "total_steps": 3093, "loss": 0.0999, "learning_rate": 6.009272827950042e-07, "epoch": 2.541222114451988, "percentage": 84.71, "elapsed_time": "1 day, 17:43:45", "remaining_time": "7:32:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2630, "total_steps": 3093, "loss": 0.101, "learning_rate": 5.762813951537582e-07, "epoch": 2.550921435499515, "percentage": 85.03, "elapsed_time": "1 day, 17:53:15", "remaining_time": "7:22:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2640, "total_steps": 3093, "loss": 0.0978, "learning_rate": 5.521206181083111e-07, "epoch": 2.5606207565470416, "percentage": 85.35, "elapsed_time": "1 day, 18:02:44", "remaining_time": "7:12:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2650, "total_steps": 3093, "loss": 0.0965, "learning_rate": 5.28447601160132e-07, "epoch": 2.5703200775945683, "percentage": 85.68, "elapsed_time": "1 day, 18:12:13", "remaining_time": "7:03:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2660, "total_steps": 3093, "loss": 0.0976, "learning_rate": 5.052649403223015e-07, "epoch": 2.580019398642095, "percentage": 86.0, "elapsed_time": "1 day, 18:21:42", "remaining_time": "6:53:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2670, "total_steps": 3093, "loss": 0.0981, "learning_rate": 4.825751778348259e-07, "epoch": 2.5897187196896216, "percentage": 86.32, "elapsed_time": "1 day, 18:31:11", "remaining_time": "6:44:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2680, "total_steps": 3093, "loss": 0.0992, "learning_rate": 4.6038080188585135e-07, "epoch": 2.5994180407371483, "percentage": 86.65, "elapsed_time": "1 day, 18:40:40", "remaining_time": "6:34:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2690, "total_steps": 3093, "loss": 0.0987, "learning_rate": 4.38684246338808e-07, "epoch": 2.609117361784675, "percentage": 86.97, "elapsed_time": "1 day, 18:50:09", "remaining_time": "6:25:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2700, "total_steps": 3093, "loss": 0.0978, "learning_rate": 4.1748789046551055e-07, "epoch": 2.6188166828322017, "percentage": 87.29, "elapsed_time": "1 day, 18:59:38", "remaining_time": "6:15:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2710, "total_steps": 3093, "loss": 0.0976, "learning_rate": 3.967940586852409e-07, "epoch": 2.6285160038797284, "percentage": 87.62, "elapsed_time": "1 day, 19:09:07", "remaining_time": "6:05:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2720, "total_steps": 3093, "loss": 0.0988, "learning_rate": 3.7660502030985203e-07, "epoch": 2.638215324927255, "percentage": 87.94, "elapsed_time": "1 day, 19:18:35", "remaining_time": "5:56:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2730, "total_steps": 3093, "loss": 0.0999, "learning_rate": 3.569229892949133e-07, "epoch": 2.6479146459747818, "percentage": 88.26, "elapsed_time": "1 day, 19:28:04", "remaining_time": "5:46:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2740, "total_steps": 3093, "loss": 0.0989, "learning_rate": 3.3775012399692055e-07, "epoch": 2.6576139670223085, "percentage": 88.59, "elapsed_time": "1 day, 19:37:33", "remaining_time": "5:37:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2750, "total_steps": 3093, "loss": 0.0994, "learning_rate": 3.1908852693661116e-07, "epoch": 2.667313288069835, "percentage": 88.91, "elapsed_time": "1 day, 19:47:02", "remaining_time": "5:27:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2760, "total_steps": 3093, "loss": 0.0987, "learning_rate": 3.0094024456840176e-07, "epoch": 2.677012609117362, "percentage": 89.23, "elapsed_time": "1 day, 19:56:31", "remaining_time": "5:18:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2770, "total_steps": 3093, "loss": 0.0981, "learning_rate": 2.833072670559661e-07, "epoch": 2.6867119301648885, "percentage": 89.56, "elapsed_time": "1 day, 20:06:00", "remaining_time": "5:08:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2780, "total_steps": 3093, "loss": 0.098, "learning_rate": 2.6619152805399286e-07, "epoch": 2.696411251212415, "percentage": 89.88, "elapsed_time": "1 day, 20:15:28", "remaining_time": "4:58:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2790, "total_steps": 3093, "loss": 0.0972, "learning_rate": 2.49594904496141e-07, "epoch": 2.706110572259942, "percentage": 90.2, "elapsed_time": "1 day, 20:24:57", "remaining_time": "4:49:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2800, "total_steps": 3093, "loss": 0.0986, "learning_rate": 2.3351921638921193e-07, "epoch": 2.7158098933074686, "percentage": 90.53, "elapsed_time": "1 day, 20:34:26", "remaining_time": "4:39:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2810, "total_steps": 3093, "loss": 0.1005, "learning_rate": 2.1796622661356238e-07, "epoch": 2.7255092143549953, "percentage": 90.85, "elapsed_time": "1 day, 20:43:54", "remaining_time": "4:30:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2820, "total_steps": 3093, "loss": 0.1017, "learning_rate": 2.0293764072978618e-07, "epoch": 2.735208535402522, "percentage": 91.17, "elapsed_time": "1 day, 20:53:23", "remaining_time": "4:20:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2830, "total_steps": 3093, "loss": 0.0969, "learning_rate": 1.8843510679168341e-07, "epoch": 2.7449078564500486, "percentage": 91.5, "elapsed_time": "1 day, 21:02:52", "remaining_time": "4:11:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2840, "total_steps": 3093, "loss": 0.0967, "learning_rate": 1.744602151655289e-07, "epoch": 2.7546071774975753, "percentage": 91.82, "elapsed_time": "1 day, 21:12:21", "remaining_time": "4:01:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2850, "total_steps": 3093, "loss": 0.097, "learning_rate": 1.6101449835567273e-07, "epoch": 2.7643064985451016, "percentage": 92.14, "elapsed_time": "1 day, 21:21:50", "remaining_time": "3:52:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2860, "total_steps": 3093, "loss": 0.0966, "learning_rate": 1.4809943083648194e-07, "epoch": 2.7740058195926283, "percentage": 92.47, "elapsed_time": "1 day, 21:31:19", "remaining_time": "3:42:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2870, "total_steps": 3093, "loss": 0.0965, "learning_rate": 1.3571642889064984e-07, "epoch": 2.783705140640155, "percentage": 92.79, "elapsed_time": "1 day, 21:40:48", "remaining_time": "3:32:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2880, "total_steps": 3093, "loss": 0.0934, "learning_rate": 1.2386685045388313e-07, "epoch": 2.7934044616876816, "percentage": 93.11, "elapsed_time": "1 day, 21:50:17", "remaining_time": "3:23:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2890, "total_steps": 3093, "loss": 0.1002, "learning_rate": 1.1255199496599034e-07, "epoch": 2.8031037827352083, "percentage": 93.44, "elapsed_time": "1 day, 21:59:46", "remaining_time": "3:13:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2900, "total_steps": 3093, "loss": 0.0984, "learning_rate": 1.0177310322838251e-07, "epoch": 2.812803103782735, "percentage": 93.76, "elapsed_time": "1 day, 22:09:14", "remaining_time": "3:04:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2910, "total_steps": 3093, "loss": 0.0991, "learning_rate": 9.153135726800599e-08, "epoch": 2.8225024248302617, "percentage": 94.08, "elapsed_time": "1 day, 22:18:44", "remaining_time": "2:54:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2920, "total_steps": 3093, "loss": 0.0995, "learning_rate": 8.182788020771826e-08, "epoch": 2.8322017458777884, "percentage": 94.41, "elapsed_time": "1 day, 22:28:14", "remaining_time": "2:45:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2930, "total_steps": 3093, "loss": 0.0997, "learning_rate": 7.266373614312927e-08, "epoch": 2.841901066925315, "percentage": 94.73, "elapsed_time": "1 day, 22:37:43", "remaining_time": "2:35:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2940, "total_steps": 3093, "loss": 0.099, "learning_rate": 6.403993002590425e-08, "epoch": 2.8516003879728418, "percentage": 95.05, "elapsed_time": "1 day, 22:47:13", "remaining_time": "2:26:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2950, "total_steps": 3093, "loss": 0.0961, "learning_rate": 5.595740755356627e-08, "epoch": 2.8612997090203685, "percentage": 95.38, "elapsed_time": "1 day, 22:56:42", "remaining_time": "2:16:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2960, "total_steps": 3093, "loss": 0.0984, "learning_rate": 4.841705506578587e-08, "epoch": 2.870999030067895, "percentage": 95.7, "elapsed_time": "1 day, 23:06:11", "remaining_time": "2:06:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2970, "total_steps": 3093, "loss": 0.0995, "learning_rate": 4.1419699447186045e-08, "epoch": 2.880698351115422, "percentage": 96.02, "elapsed_time": "1 day, 23:15:40", "remaining_time": "1:57:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2980, "total_steps": 3093, "loss": 0.0987, "learning_rate": 3.4966108036662006e-08, "epoch": 2.8903976721629485, "percentage": 96.35, "elapsed_time": "1 day, 23:25:09", "remaining_time": "1:47:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2990, "total_steps": 3093, "loss": 0.1002, "learning_rate": 2.9056988543239018e-08, "epoch": 2.900096993210475, "percentage": 96.67, "elapsed_time": "1 day, 23:34:38", "remaining_time": "1:38:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3000, "total_steps": 3093, "loss": 0.0966, "learning_rate": 2.3692988968458398e-08, "epoch": 2.909796314258002, "percentage": 96.99, "elapsed_time": "1 day, 23:44:06", "remaining_time": "1:28:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3010, "total_steps": 3093, "loss": 0.0965, "learning_rate": 1.8874697535319897e-08, "epoch": 2.9194956353055286, "percentage": 97.32, "elapsed_time": "1 day, 23:57:20", "remaining_time": "1:19:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3020, "total_steps": 3093, "loss": 0.0992, "learning_rate": 1.4602642623777752e-08, "epoch": 2.9291949563530553, "percentage": 97.64, "elapsed_time": "2 days, 0:06:49", "remaining_time": "1:09:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3030, "total_steps": 3093, "loss": 0.0954, "learning_rate": 1.0877292712792586e-08, "epoch": 2.938894277400582, "percentage": 97.96, "elapsed_time": "2 days, 0:16:18", "remaining_time": "1:00:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3040, "total_steps": 3093, "loss": 0.0985, "learning_rate": 7.699056328964726e-09, "epoch": 2.9485935984481086, "percentage": 98.29, "elapsed_time": "2 days, 0:25:47", "remaining_time": "0:50:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3050, "total_steps": 3093, "loss": 0.1001, "learning_rate": 5.06828200172893e-09, "epoch": 2.9582929194956353, "percentage": 98.61, "elapsed_time": "2 days, 0:35:15", "remaining_time": "0:41:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3060, "total_steps": 3093, "loss": 0.0979, "learning_rate": 2.9852582251355124e-09, "epoch": 2.967992240543162, "percentage": 98.93, "elapsed_time": "2 days, 0:44:44", "remaining_time": "0:31:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3070, "total_steps": 3093, "loss": 0.0973, "learning_rate": 1.4502134262156519e-09, "epoch": 2.9776915615906887, "percentage": 99.26, "elapsed_time": "2 days, 0:54:13", "remaining_time": "0:21:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3080, "total_steps": 3093, "loss": 0.0973, "learning_rate": 4.6331593993032e-10, "epoch": 2.9873908826382154, "percentage": 99.58, "elapsed_time": "2 days, 1:03:41", "remaining_time": "0:12:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3090, "total_steps": 3093, "loss": 0.0964, "learning_rate": 2.467399070893439e-11, "epoch": 2.997090203685742, "percentage": 99.9, "elapsed_time": "2 days, 1:13:10", "remaining_time": "0:02:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3093, "total_steps": 3093, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2 days, 1:19:53", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}