train_copa_1755694501 / trainer_log.jsonl
rbelanec's picture
Model save
4e1b9b0 verified
{"current_steps": 5, "total_steps": 1800, "loss": 8.7394, "lr": 1.1111111111111112e-06, "epoch": 0.027777777777777776, "percentage": 0.28, "elapsed_time": "0:00:01", "remaining_time": "0:06:08", "throughput": 733.31, "total_tokens": 752}
{"current_steps": 10, "total_steps": 1800, "loss": 7.4195, "lr": 2.5e-06, "epoch": 0.05555555555555555, "percentage": 0.56, "elapsed_time": "0:00:01", "remaining_time": "0:04:17", "throughput": 1054.72, "total_tokens": 1520}
{"current_steps": 15, "total_steps": 1800, "loss": 5.4249, "lr": 3.888888888888889e-06, "epoch": 0.08333333333333333, "percentage": 0.83, "elapsed_time": "0:00:01", "remaining_time": "0:03:40", "throughput": 1250.41, "total_tokens": 2320}
{"current_steps": 20, "total_steps": 1800, "loss": 3.7254, "lr": 5.277777777777778e-06, "epoch": 0.1111111111111111, "percentage": 1.11, "elapsed_time": "0:00:02", "remaining_time": "0:03:22", "throughput": 1352.64, "total_tokens": 3072}
{"current_steps": 25, "total_steps": 1800, "loss": 2.1759, "lr": 6.666666666666667e-06, "epoch": 0.1388888888888889, "percentage": 1.39, "elapsed_time": "0:00:02", "remaining_time": "0:03:11", "throughput": 1426.12, "total_tokens": 3840}
{"current_steps": 30, "total_steps": 1800, "loss": 1.1654, "lr": 8.055555555555557e-06, "epoch": 0.16666666666666666, "percentage": 1.67, "elapsed_time": "0:00:03", "remaining_time": "0:03:03", "throughput": 1473.61, "total_tokens": 4576}
{"current_steps": 35, "total_steps": 1800, "loss": 0.5527, "lr": 9.444444444444445e-06, "epoch": 0.19444444444444445, "percentage": 1.94, "elapsed_time": "0:00:03", "remaining_time": "0:02:57", "throughput": 1514.58, "total_tokens": 5328}
{"current_steps": 40, "total_steps": 1800, "loss": 0.257, "lr": 1.0833333333333334e-05, "epoch": 0.2222222222222222, "percentage": 2.22, "elapsed_time": "0:00:03", "remaining_time": "0:02:53", "throughput": 1554.21, "total_tokens": 6112}
{"current_steps": 45, "total_steps": 1800, "loss": 0.3216, "lr": 1.2222222222222222e-05, "epoch": 0.25, "percentage": 2.5, "elapsed_time": "0:00:04", "remaining_time": "0:02:49", "throughput": 1574.98, "total_tokens": 6848}
{"current_steps": 50, "total_steps": 1800, "loss": 0.3313, "lr": 1.3611111111111111e-05, "epoch": 0.2777777777777778, "percentage": 2.78, "elapsed_time": "0:00:04", "remaining_time": "0:02:46", "throughput": 1594.4, "total_tokens": 7600}
{"current_steps": 55, "total_steps": 1800, "loss": 0.2349, "lr": 1.5e-05, "epoch": 0.3055555555555556, "percentage": 3.06, "elapsed_time": "0:00:05", "remaining_time": "0:02:44", "throughput": 1614.93, "total_tokens": 8368}
{"current_steps": 60, "total_steps": 1800, "loss": 0.175, "lr": 1.638888888888889e-05, "epoch": 0.3333333333333333, "percentage": 3.33, "elapsed_time": "0:00:05", "remaining_time": "0:02:42", "throughput": 1635.59, "total_tokens": 9152}
{"current_steps": 65, "total_steps": 1800, "loss": 0.4744, "lr": 1.777777777777778e-05, "epoch": 0.3611111111111111, "percentage": 3.61, "elapsed_time": "0:00:06", "remaining_time": "0:02:40", "throughput": 1644.29, "total_tokens": 9888}
{"current_steps": 70, "total_steps": 1800, "loss": 0.5353, "lr": 1.9166666666666667e-05, "epoch": 0.3888888888888889, "percentage": 3.89, "elapsed_time": "0:00:06", "remaining_time": "0:02:39", "throughput": 1656.08, "total_tokens": 10656}
{"current_steps": 75, "total_steps": 1800, "loss": 0.2667, "lr": 2.0555555555555555e-05, "epoch": 0.4166666666666667, "percentage": 4.17, "elapsed_time": "0:00:06", "remaining_time": "0:02:37", "throughput": 1665.79, "total_tokens": 11408}
{"current_steps": 80, "total_steps": 1800, "loss": 0.2415, "lr": 2.1944444444444445e-05, "epoch": 0.4444444444444444, "percentage": 4.44, "elapsed_time": "0:00:07", "remaining_time": "0:02:36", "throughput": 1671.67, "total_tokens": 12144}
{"current_steps": 85, "total_steps": 1800, "loss": 0.229, "lr": 2.3333333333333336e-05, "epoch": 0.4722222222222222, "percentage": 4.72, "elapsed_time": "0:00:07", "remaining_time": "0:02:35", "throughput": 1676.59, "total_tokens": 12880}
{"current_steps": 90, "total_steps": 1800, "loss": 0.2146, "lr": 2.4722222222222223e-05, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:08", "remaining_time": "0:02:33", "throughput": 1688.02, "total_tokens": 13664}
{"current_steps": 90, "total_steps": 1800, "eval_loss": 0.25626200437545776, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:00:08", "remaining_time": "0:02:50", "throughput": 1525.44, "total_tokens": 13664}
{"current_steps": 95, "total_steps": 1800, "loss": 0.2801, "lr": 2.6111111111111114e-05, "epoch": 0.5277777777777778, "percentage": 5.28, "elapsed_time": "0:00:10", "remaining_time": "0:03:12", "throughput": 1346.57, "total_tokens": 14464}
{"current_steps": 100, "total_steps": 1800, "loss": 0.2593, "lr": 2.7500000000000004e-05, "epoch": 0.5555555555555556, "percentage": 5.56, "elapsed_time": "0:00:11", "remaining_time": "0:03:09", "throughput": 1363.15, "total_tokens": 15216}
{"current_steps": 105, "total_steps": 1800, "loss": 0.2524, "lr": 2.8888888888888888e-05, "epoch": 0.5833333333333334, "percentage": 5.83, "elapsed_time": "0:00:11", "remaining_time": "0:03:06", "throughput": 1380.96, "total_tokens": 15984}
{"current_steps": 110, "total_steps": 1800, "loss": 0.2935, "lr": 3.0277777777777776e-05, "epoch": 0.6111111111111112, "percentage": 6.11, "elapsed_time": "0:00:11", "remaining_time": "0:03:04", "throughput": 1398.66, "total_tokens": 16768}
{"current_steps": 115, "total_steps": 1800, "loss": 0.6453, "lr": 3.1666666666666666e-05, "epoch": 0.6388888888888888, "percentage": 6.39, "elapsed_time": "0:00:12", "remaining_time": "0:03:01", "throughput": 1414.06, "total_tokens": 17552}
{"current_steps": 120, "total_steps": 1800, "loss": 0.6614, "lr": 3.3055555555555553e-05, "epoch": 0.6666666666666666, "percentage": 6.67, "elapsed_time": "0:00:12", "remaining_time": "0:02:59", "throughput": 1427.12, "total_tokens": 18304}
{"current_steps": 125, "total_steps": 1800, "loss": 0.216, "lr": 3.444444444444445e-05, "epoch": 0.6944444444444444, "percentage": 6.94, "elapsed_time": "0:00:13", "remaining_time": "0:02:57", "throughput": 1440.3, "total_tokens": 19072}
{"current_steps": 130, "total_steps": 1800, "loss": 0.2517, "lr": 3.5833333333333335e-05, "epoch": 0.7222222222222222, "percentage": 7.22, "elapsed_time": "0:00:13", "remaining_time": "0:02:55", "throughput": 1451.86, "total_tokens": 19840}
{"current_steps": 135, "total_steps": 1800, "loss": 0.3197, "lr": 3.722222222222222e-05, "epoch": 0.75, "percentage": 7.5, "elapsed_time": "0:00:14", "remaining_time": "0:02:54", "throughput": 1461.75, "total_tokens": 20640}
{"current_steps": 140, "total_steps": 1800, "loss": 0.2696, "lr": 3.8611111111111116e-05, "epoch": 0.7777777777777778, "percentage": 7.78, "elapsed_time": "0:00:14", "remaining_time": "0:02:52", "throughput": 1469.24, "total_tokens": 21408}
{"current_steps": 145, "total_steps": 1800, "loss": 0.3404, "lr": 4e-05, "epoch": 0.8055555555555556, "percentage": 8.06, "elapsed_time": "0:00:15", "remaining_time": "0:02:51", "throughput": 1473.71, "total_tokens": 22128}
{"current_steps": 150, "total_steps": 1800, "loss": 0.2222, "lr": 4.138888888888889e-05, "epoch": 0.8333333333333334, "percentage": 8.33, "elapsed_time": "0:00:15", "remaining_time": "0:02:49", "throughput": 1480.97, "total_tokens": 22880}
{"current_steps": 155, "total_steps": 1800, "loss": 0.2368, "lr": 4.277777777777778e-05, "epoch": 0.8611111111111112, "percentage": 8.61, "elapsed_time": "0:00:15", "remaining_time": "0:02:48", "throughput": 1490.85, "total_tokens": 23664}
{"current_steps": 160, "total_steps": 1800, "loss": 0.3835, "lr": 4.4166666666666665e-05, "epoch": 0.8888888888888888, "percentage": 8.89, "elapsed_time": "0:00:16", "remaining_time": "0:02:47", "throughput": 1499.2, "total_tokens": 24432}
{"current_steps": 165, "total_steps": 1800, "loss": 0.2734, "lr": 4.555555555555556e-05, "epoch": 0.9166666666666666, "percentage": 9.17, "elapsed_time": "0:00:16", "remaining_time": "0:02:45", "throughput": 1506.8, "total_tokens": 25184}
{"current_steps": 170, "total_steps": 1800, "loss": 0.2508, "lr": 4.6944444444444446e-05, "epoch": 0.9444444444444444, "percentage": 9.44, "elapsed_time": "0:00:17", "remaining_time": "0:02:44", "throughput": 1512.4, "total_tokens": 25920}
{"current_steps": 175, "total_steps": 1800, "loss": 0.2465, "lr": 4.8333333333333334e-05, "epoch": 0.9722222222222222, "percentage": 9.72, "elapsed_time": "0:00:17", "remaining_time": "0:02:42", "throughput": 1519.78, "total_tokens": 26672}
{"current_steps": 180, "total_steps": 1800, "loss": 0.2358, "lr": 4.972222222222223e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:18", "remaining_time": "0:02:42", "throughput": 1521.94, "total_tokens": 27408}
{"current_steps": 180, "total_steps": 1800, "eval_loss": 0.25230473279953003, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:18", "remaining_time": "0:02:49", "throughput": 1452.39, "total_tokens": 27408}
{"current_steps": 185, "total_steps": 1800, "loss": 0.2369, "lr": 4.9999247861994194e-05, "epoch": 1.0277777777777777, "percentage": 10.28, "elapsed_time": "0:00:20", "remaining_time": "0:02:58", "throughput": 1377.29, "total_tokens": 28176}
{"current_steps": 190, "total_steps": 1800, "loss": 0.2493, "lr": 4.9996192378909786e-05, "epoch": 1.0555555555555556, "percentage": 10.56, "elapsed_time": "0:00:20", "remaining_time": "0:02:56", "throughput": 1385.92, "total_tokens": 28928}
{"current_steps": 195, "total_steps": 1800, "loss": 0.2294, "lr": 4.999078682916774e-05, "epoch": 1.0833333333333333, "percentage": 10.83, "elapsed_time": "0:00:21", "remaining_time": "0:02:55", "throughput": 1395.28, "total_tokens": 29696}
{"current_steps": 200, "total_steps": 1800, "loss": 0.2446, "lr": 4.998303172098155e-05, "epoch": 1.1111111111111112, "percentage": 11.11, "elapsed_time": "0:00:21", "remaining_time": "0:02:53", "throughput": 1402.96, "total_tokens": 30448}
{"current_steps": 205, "total_steps": 1800, "loss": 0.2748, "lr": 4.997292778346312e-05, "epoch": 1.1388888888888888, "percentage": 11.39, "elapsed_time": "0:00:22", "remaining_time": "0:02:52", "throughput": 1410.62, "total_tokens": 31200}
{"current_steps": 210, "total_steps": 1800, "loss": 0.2413, "lr": 4.996047596655418e-05, "epoch": 1.1666666666666667, "percentage": 11.67, "elapsed_time": "0:00:22", "remaining_time": "0:02:50", "throughput": 1417.2, "total_tokens": 31936}
{"current_steps": 215, "total_steps": 1800, "loss": 0.2306, "lr": 4.994567744093703e-05, "epoch": 1.1944444444444444, "percentage": 11.94, "elapsed_time": "0:00:22", "remaining_time": "0:02:49", "throughput": 1425.27, "total_tokens": 32704}
{"current_steps": 220, "total_steps": 1800, "loss": 0.2347, "lr": 4.992853359792444e-05, "epoch": 1.2222222222222223, "percentage": 12.22, "elapsed_time": "0:00:23", "remaining_time": "0:02:47", "throughput": 1431.4, "total_tokens": 33440}
{"current_steps": 225, "total_steps": 1800, "loss": 0.2522, "lr": 4.9909046049328846e-05, "epoch": 1.25, "percentage": 12.5, "elapsed_time": "0:00:23", "remaining_time": "0:02:46", "throughput": 1438.15, "total_tokens": 34192}
{"current_steps": 230, "total_steps": 1800, "loss": 0.2392, "lr": 4.988721662731083e-05, "epoch": 1.2777777777777777, "percentage": 12.78, "elapsed_time": "0:00:24", "remaining_time": "0:02:45", "throughput": 1445.3, "total_tokens": 34960}
{"current_steps": 235, "total_steps": 1800, "loss": 0.2476, "lr": 4.9863047384206835e-05, "epoch": 1.3055555555555556, "percentage": 13.06, "elapsed_time": "0:00:24", "remaining_time": "0:02:43", "throughput": 1452.02, "total_tokens": 35728}
{"current_steps": 240, "total_steps": 1800, "loss": 0.2353, "lr": 4.983654059233626e-05, "epoch": 1.3333333333333333, "percentage": 13.33, "elapsed_time": "0:00:25", "remaining_time": "0:02:42", "throughput": 1457.4, "total_tokens": 36464}
{"current_steps": 245, "total_steps": 1800, "loss": 0.2421, "lr": 4.9807698743787744e-05, "epoch": 1.3611111111111112, "percentage": 13.61, "elapsed_time": "0:00:25", "remaining_time": "0:02:41", "throughput": 1463.19, "total_tokens": 37216}
{"current_steps": 250, "total_steps": 1800, "loss": 0.2127, "lr": 4.9776524550184965e-05, "epoch": 1.3888888888888888, "percentage": 13.89, "elapsed_time": "0:00:25", "remaining_time": "0:02:40", "throughput": 1470.14, "total_tokens": 38000}
{"current_steps": 255, "total_steps": 1800, "loss": 0.294, "lr": 4.974302094243164e-05, "epoch": 1.4166666666666667, "percentage": 14.17, "elapsed_time": "0:00:26", "remaining_time": "0:02:39", "throughput": 1477.56, "total_tokens": 38800}
{"current_steps": 260, "total_steps": 1800, "loss": 0.294, "lr": 4.970719107043595e-05, "epoch": 1.4444444444444444, "percentage": 14.44, "elapsed_time": "0:00:26", "remaining_time": "0:02:38", "throughput": 1483.62, "total_tokens": 39584}
{"current_steps": 265, "total_steps": 1800, "loss": 0.2288, "lr": 4.966903830281449e-05, "epoch": 1.4722222222222223, "percentage": 14.72, "elapsed_time": "0:00:27", "remaining_time": "0:02:36", "throughput": 1489.27, "total_tokens": 40352}
{"current_steps": 270, "total_steps": 1800, "loss": 0.2177, "lr": 4.962856622657541e-05, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:00:27", "remaining_time": "0:02:35", "throughput": 1494.88, "total_tokens": 41120}
{"current_steps": 270, "total_steps": 1800, "eval_loss": 0.24368472397327423, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:00:28", "remaining_time": "0:02:40", "throughput": 1449.49, "total_tokens": 41120}
{"current_steps": 275, "total_steps": 1800, "loss": 0.1989, "lr": 4.9585778646781364e-05, "epoch": 1.5277777777777777, "percentage": 15.28, "elapsed_time": "0:00:30", "remaining_time": "0:02:46", "throughput": 1393.84, "total_tokens": 41856}
{"current_steps": 280, "total_steps": 1800, "loss": 0.3601, "lr": 4.9540679586191605e-05, "epoch": 1.5555555555555556, "percentage": 15.56, "elapsed_time": "0:00:30", "remaining_time": "0:02:45", "throughput": 1400.52, "total_tokens": 42640}
{"current_steps": 285, "total_steps": 1800, "loss": 0.2522, "lr": 4.9493273284883854e-05, "epoch": 1.5833333333333335, "percentage": 15.83, "elapsed_time": "0:00:30", "remaining_time": "0:02:44", "throughput": 1406.16, "total_tokens": 43392}
{"current_steps": 290, "total_steps": 1800, "loss": 0.2265, "lr": 4.9443564199855666e-05, "epoch": 1.6111111111111112, "percentage": 16.11, "elapsed_time": "0:00:31", "remaining_time": "0:02:42", "throughput": 1412.67, "total_tokens": 44176}
{"current_steps": 295, "total_steps": 1800, "loss": 0.3362, "lr": 4.939155700460536e-05, "epoch": 1.6388888888888888, "percentage": 16.39, "elapsed_time": "0:00:31", "remaining_time": "0:02:41", "throughput": 1417.47, "total_tokens": 44928}
{"current_steps": 300, "total_steps": 1800, "loss": 0.2511, "lr": 4.933725658869267e-05, "epoch": 1.6666666666666665, "percentage": 16.67, "elapsed_time": "0:00:32", "remaining_time": "0:02:40", "throughput": 1422.85, "total_tokens": 45696}
{"current_steps": 305, "total_steps": 1800, "loss": 0.2678, "lr": 4.9280668057279014e-05, "epoch": 1.6944444444444444, "percentage": 16.94, "elapsed_time": "0:00:32", "remaining_time": "0:02:39", "throughput": 1427.69, "total_tokens": 46464}
{"current_steps": 310, "total_steps": 1800, "loss": 0.2901, "lr": 4.9221796730647516e-05, "epoch": 1.7222222222222223, "percentage": 17.22, "elapsed_time": "0:00:32", "remaining_time": "0:02:38", "throughput": 1432.32, "total_tokens": 47216}
{"current_steps": 315, "total_steps": 1800, "loss": 0.2388, "lr": 4.916064814370287e-05, "epoch": 1.75, "percentage": 17.5, "elapsed_time": "0:00:33", "remaining_time": "0:02:37", "throughput": 1437.37, "total_tokens": 47984}
{"current_steps": 320, "total_steps": 1800, "loss": 0.2227, "lr": 4.9097228045450864e-05, "epoch": 1.7777777777777777, "percentage": 17.78, "elapsed_time": "0:00:33", "remaining_time": "0:02:36", "throughput": 1441.4, "total_tokens": 48720}
{"current_steps": 325, "total_steps": 1800, "loss": 0.2635, "lr": 4.9031542398457974e-05, "epoch": 1.8055555555555556, "percentage": 18.06, "elapsed_time": "0:00:34", "remaining_time": "0:02:35", "throughput": 1445.69, "total_tokens": 49472}
{"current_steps": 330, "total_steps": 1800, "loss": 0.2325, "lr": 4.896359737829071e-05, "epoch": 1.8333333333333335, "percentage": 18.33, "elapsed_time": "0:00:34", "remaining_time": "0:02:34", "throughput": 1450.0, "total_tokens": 50224}
{"current_steps": 335, "total_steps": 1800, "loss": 0.2295, "lr": 4.889339937293508e-05, "epoch": 1.8611111111111112, "percentage": 18.61, "elapsed_time": "0:00:35", "remaining_time": "0:02:33", "throughput": 1453.34, "total_tokens": 50944}
{"current_steps": 340, "total_steps": 1800, "loss": 0.2262, "lr": 4.8820954982195905e-05, "epoch": 1.8888888888888888, "percentage": 18.89, "elapsed_time": "0:00:35", "remaining_time": "0:02:32", "throughput": 1457.53, "total_tokens": 51696}
{"current_steps": 345, "total_steps": 1800, "loss": 0.2475, "lr": 4.874627101707644e-05, "epoch": 1.9166666666666665, "percentage": 19.17, "elapsed_time": "0:00:35", "remaining_time": "0:02:31", "throughput": 1462.48, "total_tokens": 52480}
{"current_steps": 350, "total_steps": 1800, "loss": 0.2275, "lr": 4.8669354499137955e-05, "epoch": 1.9444444444444444, "percentage": 19.44, "elapsed_time": "0:00:36", "remaining_time": "0:02:30", "throughput": 1466.17, "total_tokens": 53232}
{"current_steps": 355, "total_steps": 1800, "loss": 0.2316, "lr": 4.859021265983959e-05, "epoch": 1.9722222222222223, "percentage": 19.72, "elapsed_time": "0:00:36", "remaining_time": "0:02:29", "throughput": 1471.24, "total_tokens": 54016}
{"current_steps": 360, "total_steps": 1800, "loss": 0.2349, "lr": 4.850885293985853e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:00:37", "remaining_time": "0:02:28", "throughput": 1472.39, "total_tokens": 54752}
{"current_steps": 360, "total_steps": 1800, "eval_loss": 0.23472540080547333, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:00:38", "remaining_time": "0:02:32", "throughput": 1438.88, "total_tokens": 54752}
{"current_steps": 365, "total_steps": 1800, "loss": 0.2274, "lr": 4.8425282988390376e-05, "epoch": 2.0277777777777777, "percentage": 20.28, "elapsed_time": "0:00:39", "remaining_time": "0:02:35", "throughput": 1400.07, "total_tokens": 55520}
{"current_steps": 370, "total_steps": 1800, "loss": 0.2281, "lr": 4.8339510662430046e-05, "epoch": 2.0555555555555554, "percentage": 20.56, "elapsed_time": "0:00:40", "remaining_time": "0:02:34", "throughput": 1404.65, "total_tokens": 56288}
{"current_steps": 375, "total_steps": 1800, "loss": 0.2279, "lr": 4.825154402603308e-05, "epoch": 2.0833333333333335, "percentage": 20.83, "elapsed_time": "0:00:40", "remaining_time": "0:02:33", "throughput": 1408.82, "total_tokens": 57040}
{"current_steps": 380, "total_steps": 1800, "loss": 0.2326, "lr": 4.816139134955746e-05, "epoch": 2.111111111111111, "percentage": 21.11, "elapsed_time": "0:00:40", "remaining_time": "0:02:32", "throughput": 1412.91, "total_tokens": 57792}
{"current_steps": 385, "total_steps": 1800, "loss": 0.256, "lr": 4.806906110888606e-05, "epoch": 2.138888888888889, "percentage": 21.39, "elapsed_time": "0:00:41", "remaining_time": "0:02:31", "throughput": 1417.54, "total_tokens": 58576}
{"current_steps": 390, "total_steps": 1800, "loss": 0.2249, "lr": 4.797456198462979e-05, "epoch": 2.1666666666666665, "percentage": 21.67, "elapsed_time": "0:00:41", "remaining_time": "0:02:30", "throughput": 1421.89, "total_tokens": 59344}
{"current_steps": 395, "total_steps": 1800, "loss": 0.2427, "lr": 4.7877902861311446e-05, "epoch": 2.1944444444444446, "percentage": 21.94, "elapsed_time": "0:00:42", "remaining_time": "0:02:29", "throughput": 1426.04, "total_tokens": 60112}
{"current_steps": 400, "total_steps": 1800, "loss": 0.2081, "lr": 4.777909282653042e-05, "epoch": 2.2222222222222223, "percentage": 22.22, "elapsed_time": "0:00:42", "remaining_time": "0:02:28", "throughput": 1430.54, "total_tokens": 60896}
{"current_steps": 405, "total_steps": 1800, "loss": 0.2586, "lr": 4.7678141170108345e-05, "epoch": 2.25, "percentage": 22.5, "elapsed_time": "0:00:42", "remaining_time": "0:02:28", "throughput": 1434.22, "total_tokens": 61648}
{"current_steps": 410, "total_steps": 1800, "loss": 0.2304, "lr": 4.757505738321563e-05, "epoch": 2.2777777777777777, "percentage": 22.78, "elapsed_time": "0:00:43", "remaining_time": "0:02:27", "throughput": 1437.83, "total_tokens": 62400}
{"current_steps": 415, "total_steps": 1800, "loss": 0.2372, "lr": 4.7469851157479177e-05, "epoch": 2.3055555555555554, "percentage": 23.06, "elapsed_time": "0:00:43", "remaining_time": "0:02:26", "throughput": 1440.96, "total_tokens": 63136}
{"current_steps": 420, "total_steps": 1800, "loss": 0.2341, "lr": 4.736253238407119e-05, "epoch": 2.3333333333333335, "percentage": 23.33, "elapsed_time": "0:00:44", "remaining_time": "0:02:25", "throughput": 1444.31, "total_tokens": 63888}
{"current_steps": 425, "total_steps": 1800, "loss": 0.2189, "lr": 4.725311115277924e-05, "epoch": 2.361111111111111, "percentage": 23.61, "elapsed_time": "0:00:44", "remaining_time": "0:02:24", "throughput": 1447.26, "total_tokens": 64624}
{"current_steps": 430, "total_steps": 1800, "loss": 0.2431, "lr": 4.714159775105765e-05, "epoch": 2.388888888888889, "percentage": 23.89, "elapsed_time": "0:00:45", "remaining_time": "0:02:23", "throughput": 1450.58, "total_tokens": 65376}
{"current_steps": 435, "total_steps": 1800, "loss": 0.2989, "lr": 4.70280026630603e-05, "epoch": 2.4166666666666665, "percentage": 24.17, "elapsed_time": "0:00:45", "remaining_time": "0:02:22", "throughput": 1453.43, "total_tokens": 66112}
{"current_steps": 440, "total_steps": 1800, "loss": 0.2382, "lr": 4.6912336568654925e-05, "epoch": 2.4444444444444446, "percentage": 24.44, "elapsed_time": "0:00:45", "remaining_time": "0:02:21", "throughput": 1456.97, "total_tokens": 66896}
{"current_steps": 445, "total_steps": 1800, "loss": 0.2219, "lr": 4.679461034241906e-05, "epoch": 2.4722222222222223, "percentage": 24.72, "elapsed_time": "0:00:46", "remaining_time": "0:02:21", "throughput": 1460.45, "total_tokens": 67664}
{"current_steps": 450, "total_steps": 1800, "loss": 0.2026, "lr": 4.667483505261762e-05, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:00:46", "remaining_time": "0:02:20", "throughput": 1463.93, "total_tokens": 68432}
{"current_steps": 450, "total_steps": 1800, "eval_loss": 0.24386009573936462, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:00:47", "remaining_time": "0:02:22", "throughput": 1437.28, "total_tokens": 68432}
{"current_steps": 455, "total_steps": 1800, "loss": 0.2422, "lr": 4.655302196016228e-05, "epoch": 2.5277777777777777, "percentage": 25.28, "elapsed_time": "0:00:49", "remaining_time": "0:02:26", "throughput": 1399.64, "total_tokens": 69152}
{"current_steps": 460, "total_steps": 1800, "loss": 0.2645, "lr": 4.642918251755281e-05, "epoch": 2.5555555555555554, "percentage": 25.56, "elapsed_time": "0:00:49", "remaining_time": "0:02:25", "throughput": 1403.81, "total_tokens": 69936}
{"current_steps": 465, "total_steps": 1800, "loss": 0.2151, "lr": 4.6303328367800284e-05, "epoch": 2.5833333333333335, "percentage": 25.83, "elapsed_time": "0:00:50", "remaining_time": "0:02:24", "throughput": 1407.39, "total_tokens": 70704}
{"current_steps": 470, "total_steps": 1800, "loss": 0.22, "lr": 4.6175471343332485e-05, "epoch": 2.611111111111111, "percentage": 26.11, "elapsed_time": "0:00:50", "remaining_time": "0:02:23", "throughput": 1411.0, "total_tokens": 71488}
{"current_steps": 475, "total_steps": 1800, "loss": 0.2466, "lr": 4.604562346488144e-05, "epoch": 2.638888888888889, "percentage": 26.39, "elapsed_time": "0:00:51", "remaining_time": "0:02:22", "throughput": 1413.9, "total_tokens": 72224}
{"current_steps": 480, "total_steps": 1800, "loss": 0.2571, "lr": 4.591379694035325e-05, "epoch": 2.6666666666666665, "percentage": 26.67, "elapsed_time": "0:00:51", "remaining_time": "0:02:21", "throughput": 1417.01, "total_tokens": 72976}
{"current_steps": 485, "total_steps": 1800, "loss": 0.2415, "lr": 4.5780004163680365e-05, "epoch": 2.6944444444444446, "percentage": 26.94, "elapsed_time": "0:00:51", "remaining_time": "0:02:20", "throughput": 1421.5, "total_tokens": 73792}
{"current_steps": 490, "total_steps": 1800, "loss": 0.2342, "lr": 4.5644257713656356e-05, "epoch": 2.7222222222222223, "percentage": 27.22, "elapsed_time": "0:00:52", "remaining_time": "0:02:19", "throughput": 1424.82, "total_tokens": 74560}
{"current_steps": 495, "total_steps": 1800, "loss": 0.2381, "lr": 4.550657035275323e-05, "epoch": 2.75, "percentage": 27.5, "elapsed_time": "0:00:52", "remaining_time": "0:02:19", "throughput": 1428.17, "total_tokens": 75328}
{"current_steps": 500, "total_steps": 1800, "loss": 0.2511, "lr": 4.536695502592162e-05, "epoch": 2.7777777777777777, "percentage": 27.78, "elapsed_time": "0:00:53", "remaining_time": "0:02:18", "throughput": 1431.14, "total_tokens": 76080}
{"current_steps": 505, "total_steps": 1800, "loss": 0.2262, "lr": 4.522542485937369e-05, "epoch": 2.8055555555555554, "percentage": 28.06, "elapsed_time": "0:00:53", "remaining_time": "0:02:17", "throughput": 1434.45, "total_tokens": 76848}
{"current_steps": 510, "total_steps": 1800, "loss": 0.2282, "lr": 4.5081993159349056e-05, "epoch": 2.8333333333333335, "percentage": 28.33, "elapsed_time": "0:00:53", "remaining_time": "0:02:16", "throughput": 1437.46, "total_tokens": 77616}
{"current_steps": 515, "total_steps": 1800, "loss": 0.2145, "lr": 4.493667341086379e-05, "epoch": 2.861111111111111, "percentage": 28.61, "elapsed_time": "0:00:54", "remaining_time": "0:02:15", "throughput": 1440.35, "total_tokens": 78384}
{"current_steps": 520, "total_steps": 1800, "loss": 0.2395, "lr": 4.478947927644258e-05, "epoch": 2.888888888888889, "percentage": 28.89, "elapsed_time": "0:00:54", "remaining_time": "0:02:14", "throughput": 1442.96, "total_tokens": 79136}
{"current_steps": 525, "total_steps": 1800, "loss": 0.2285, "lr": 4.464042459483425e-05, "epoch": 2.9166666666666665, "percentage": 29.17, "elapsed_time": "0:00:55", "remaining_time": "0:02:14", "throughput": 1446.26, "total_tokens": 79920}
{"current_steps": 530, "total_steps": 1800, "loss": 0.2108, "lr": 4.448952337971064e-05, "epoch": 2.9444444444444446, "percentage": 29.44, "elapsed_time": "0:00:55", "remaining_time": "0:02:13", "throughput": 1448.86, "total_tokens": 80672}
{"current_steps": 535, "total_steps": 1800, "loss": 0.2696, "lr": 4.43367898183491e-05, "epoch": 2.9722222222222223, "percentage": 29.72, "elapsed_time": "0:00:56", "remaining_time": "0:02:12", "throughput": 1451.93, "total_tokens": 81440}
{"current_steps": 540, "total_steps": 1800, "loss": 0.2456, "lr": 4.418223827029867e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:00:56", "remaining_time": "0:02:11", "throughput": 1452.78, "total_tokens": 82176}
{"current_steps": 540, "total_steps": 1800, "eval_loss": 0.23222021758556366, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:00:57", "remaining_time": "0:02:13", "throughput": 1431.08, "total_tokens": 82176}
{"current_steps": 545, "total_steps": 1800, "loss": 0.2362, "lr": 4.402588326603002e-05, "epoch": 3.0277777777777777, "percentage": 30.28, "elapsed_time": "0:00:59", "remaining_time": "0:02:15", "throughput": 1405.81, "total_tokens": 82944}
{"current_steps": 550, "total_steps": 1800, "loss": 0.2492, "lr": 4.386773950556931e-05, "epoch": 3.0555555555555554, "percentage": 30.56, "elapsed_time": "0:00:59", "remaining_time": "0:02:15", "throughput": 1408.91, "total_tokens": 83712}
{"current_steps": 555, "total_steps": 1800, "loss": 0.228, "lr": 4.3707821857116176e-05, "epoch": 3.0833333333333335, "percentage": 30.83, "elapsed_time": "0:00:59", "remaining_time": "0:02:14", "throughput": 1412.15, "total_tokens": 84496}
{"current_steps": 560, "total_steps": 1800, "loss": 0.239, "lr": 4.354614535564588e-05, "epoch": 3.111111111111111, "percentage": 31.11, "elapsed_time": "0:01:00", "remaining_time": "0:02:13", "throughput": 1415.39, "total_tokens": 85280}
{"current_steps": 565, "total_steps": 1800, "loss": 0.2388, "lr": 4.3382725201495723e-05, "epoch": 3.138888888888889, "percentage": 31.39, "elapsed_time": "0:01:00", "remaining_time": "0:02:12", "throughput": 1417.59, "total_tokens": 86016}
{"current_steps": 570, "total_steps": 1800, "loss": 0.2244, "lr": 4.321757675893596e-05, "epoch": 3.1666666666666665, "percentage": 31.67, "elapsed_time": "0:01:01", "remaining_time": "0:02:11", "throughput": 1420.88, "total_tokens": 86800}
{"current_steps": 575, "total_steps": 1800, "loss": 0.2363, "lr": 4.305071555472534e-05, "epoch": 3.1944444444444446, "percentage": 31.94, "elapsed_time": "0:01:01", "remaining_time": "0:02:11", "throughput": 1423.75, "total_tokens": 87568}
{"current_steps": 580, "total_steps": 1800, "loss": 0.2317, "lr": 4.288215727665129e-05, "epoch": 3.2222222222222223, "percentage": 32.22, "elapsed_time": "0:01:01", "remaining_time": "0:02:10", "throughput": 1426.33, "total_tokens": 88320}
{"current_steps": 585, "total_steps": 1800, "loss": 0.2324, "lr": 4.2711917772055e-05, "epoch": 3.25, "percentage": 32.5, "elapsed_time": "0:01:02", "remaining_time": "0:02:09", "throughput": 1428.84, "total_tokens": 89072}
{"current_steps": 590, "total_steps": 1800, "loss": 0.215, "lr": 4.254001304634151e-05, "epoch": 3.2777777777777777, "percentage": 32.78, "elapsed_time": "0:01:02", "remaining_time": "0:02:08", "throughput": 1430.91, "total_tokens": 89792}
{"current_steps": 595, "total_steps": 1800, "loss": 0.2409, "lr": 4.2366459261474933e-05, "epoch": 3.3055555555555554, "percentage": 33.06, "elapsed_time": "0:01:03", "remaining_time": "0:02:07", "throughput": 1433.94, "total_tokens": 90576}
{"current_steps": 600, "total_steps": 1800, "loss": 0.2328, "lr": 4.2191272734458955e-05, "epoch": 3.3333333333333335, "percentage": 33.33, "elapsed_time": "0:01:03", "remaining_time": "0:02:07", "throughput": 1436.92, "total_tokens": 91360}
{"current_steps": 605, "total_steps": 1800, "loss": 0.1925, "lr": 4.201446993580276e-05, "epoch": 3.361111111111111, "percentage": 33.61, "elapsed_time": "0:01:03", "remaining_time": "0:02:06", "throughput": 1439.54, "total_tokens": 92128}
{"current_steps": 610, "total_steps": 1800, "loss": 0.2581, "lr": 4.183606748797251e-05, "epoch": 3.388888888888889, "percentage": 33.89, "elapsed_time": "0:01:04", "remaining_time": "0:02:05", "throughput": 1442.44, "total_tokens": 92912}
{"current_steps": 615, "total_steps": 1800, "loss": 0.224, "lr": 4.1656082163828566e-05, "epoch": 3.4166666666666665, "percentage": 34.17, "elapsed_time": "0:01:04", "remaining_time": "0:02:04", "throughput": 1444.62, "total_tokens": 93648}
{"current_steps": 620, "total_steps": 1800, "loss": 0.2514, "lr": 4.147453088504854e-05, "epoch": 3.4444444444444446, "percentage": 34.44, "elapsed_time": "0:01:05", "remaining_time": "0:02:04", "throughput": 1447.09, "total_tokens": 94416}
{"current_steps": 625, "total_steps": 1800, "loss": 0.226, "lr": 4.129143072053638e-05, "epoch": 3.4722222222222223, "percentage": 34.72, "elapsed_time": "0:01:05", "remaining_time": "0:02:03", "throughput": 1449.45, "total_tokens": 95168}
{"current_steps": 630, "total_steps": 1800, "loss": 0.2229, "lr": 4.110679888481763e-05, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:01:06", "remaining_time": "0:02:02", "throughput": 1451.98, "total_tokens": 95936}
{"current_steps": 630, "total_steps": 1800, "eval_loss": 0.24021664261817932, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:01:06", "remaining_time": "0:02:04", "throughput": 1433.24, "total_tokens": 95936}
{"current_steps": 635, "total_steps": 1800, "loss": 0.2186, "lr": 4.09206527364209e-05, "epoch": 3.5277777777777777, "percentage": 35.28, "elapsed_time": "0:01:08", "remaining_time": "0:02:05", "throughput": 1408.09, "total_tokens": 96688}
{"current_steps": 640, "total_steps": 1800, "loss": 0.2406, "lr": 4.073300977624594e-05, "epoch": 3.5555555555555554, "percentage": 35.56, "elapsed_time": "0:01:09", "remaining_time": "0:02:05", "throughput": 1410.74, "total_tokens": 97456}
{"current_steps": 645, "total_steps": 1800, "loss": 0.2401, "lr": 4.054388764591822e-05, "epoch": 3.5833333333333335, "percentage": 35.83, "elapsed_time": "0:01:09", "remaining_time": "0:02:04", "throughput": 1413.16, "total_tokens": 98208}
{"current_steps": 650, "total_steps": 1800, "loss": 0.242, "lr": 4.035330412613035e-05, "epoch": 3.611111111111111, "percentage": 36.11, "elapsed_time": "0:01:09", "remaining_time": "0:02:03", "throughput": 1415.19, "total_tokens": 98944}
{"current_steps": 655, "total_steps": 1800, "loss": 0.2361, "lr": 4.0161277134970345e-05, "epoch": 3.638888888888889, "percentage": 36.39, "elapsed_time": "0:01:10", "remaining_time": "0:02:02", "throughput": 1417.98, "total_tokens": 99728}
{"current_steps": 660, "total_steps": 1800, "loss": 0.2442, "lr": 3.996782472623705e-05, "epoch": 3.6666666666666665, "percentage": 36.67, "elapsed_time": "0:01:10", "remaining_time": "0:02:02", "throughput": 1420.55, "total_tokens": 100496}
{"current_steps": 665, "total_steps": 1800, "loss": 0.2306, "lr": 3.977296508774278e-05, "epoch": 3.6944444444444446, "percentage": 36.94, "elapsed_time": "0:01:11", "remaining_time": "0:02:01", "throughput": 1423.09, "total_tokens": 101264}
{"current_steps": 670, "total_steps": 1800, "loss": 0.2411, "lr": 3.957671653960337e-05, "epoch": 3.7222222222222223, "percentage": 37.22, "elapsed_time": "0:01:11", "remaining_time": "0:02:00", "throughput": 1425.35, "total_tokens": 102016}
{"current_steps": 675, "total_steps": 1800, "loss": 0.2454, "lr": 3.9379097532515725e-05, "epoch": 3.75, "percentage": 37.5, "elapsed_time": "0:01:11", "remaining_time": "0:01:59", "throughput": 1427.63, "total_tokens": 102768}
{"current_steps": 680, "total_steps": 1800, "loss": 0.2297, "lr": 3.918012664602317e-05, "epoch": 3.7777777777777777, "percentage": 37.78, "elapsed_time": "0:01:12", "remaining_time": "0:01:59", "throughput": 1429.85, "total_tokens": 103520}
{"current_steps": 685, "total_steps": 1800, "loss": 0.2359, "lr": 3.897982258676867e-05, "epoch": 3.8055555555555554, "percentage": 38.06, "elapsed_time": "0:01:12", "remaining_time": "0:01:58", "throughput": 1432.25, "total_tokens": 104288}
{"current_steps": 690, "total_steps": 1800, "loss": 0.2408, "lr": 3.8778204186736076e-05, "epoch": 3.8333333333333335, "percentage": 38.33, "elapsed_time": "0:01:13", "remaining_time": "0:01:57", "throughput": 1434.65, "total_tokens": 105056}
{"current_steps": 695, "total_steps": 1800, "loss": 0.2279, "lr": 3.8575290401479586e-05, "epoch": 3.861111111111111, "percentage": 38.61, "elapsed_time": "0:01:13", "remaining_time": "0:01:57", "throughput": 1436.46, "total_tokens": 105792}
{"current_steps": 700, "total_steps": 1800, "loss": 0.2282, "lr": 3.837110030834161e-05, "epoch": 3.888888888888889, "percentage": 38.89, "elapsed_time": "0:01:14", "remaining_time": "0:01:56", "throughput": 1438.53, "total_tokens": 106544}
{"current_steps": 705, "total_steps": 1800, "loss": 0.2322, "lr": 3.8165653104659185e-05, "epoch": 3.9166666666666665, "percentage": 39.17, "elapsed_time": "0:01:14", "remaining_time": "0:01:55", "throughput": 1440.83, "total_tokens": 107312}
{"current_steps": 710, "total_steps": 1800, "loss": 0.2198, "lr": 3.79589681059591e-05, "epoch": 3.9444444444444446, "percentage": 39.44, "elapsed_time": "0:01:14", "remaining_time": "0:01:55", "throughput": 1442.6, "total_tokens": 108064}
{"current_steps": 715, "total_steps": 1800, "loss": 0.2491, "lr": 3.775106474414188e-05, "epoch": 3.9722222222222223, "percentage": 39.72, "elapsed_time": "0:01:15", "remaining_time": "0:01:54", "throughput": 1444.94, "total_tokens": 108848}
{"current_steps": 720, "total_steps": 1800, "loss": 0.2258, "lr": 3.75419625656549e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:01:15", "remaining_time": "0:01:53", "throughput": 1445.52, "total_tokens": 109584}
{"current_steps": 720, "total_steps": 1800, "eval_loss": 0.23475679755210876, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:01:16", "remaining_time": "0:01:54", "throughput": 1429.4, "total_tokens": 109584}
{"current_steps": 725, "total_steps": 1800, "loss": 0.2315, "lr": 3.7331681229654635e-05, "epoch": 4.027777777777778, "percentage": 40.28, "elapsed_time": "0:01:18", "remaining_time": "0:01:55", "throughput": 1410.52, "total_tokens": 110336}
{"current_steps": 730, "total_steps": 1800, "loss": 0.2273, "lr": 3.712024050615843e-05, "epoch": 4.055555555555555, "percentage": 40.56, "elapsed_time": "0:01:18", "remaining_time": "0:01:55", "throughput": 1412.86, "total_tokens": 111104}
{"current_steps": 735, "total_steps": 1800, "loss": 0.2337, "lr": 3.690766027418573e-05, "epoch": 4.083333333333333, "percentage": 40.83, "elapsed_time": "0:01:19", "remaining_time": "0:01:54", "throughput": 1414.98, "total_tokens": 111856}
{"current_steps": 740, "total_steps": 1800, "loss": 0.2421, "lr": 3.6693960519889106e-05, "epoch": 4.111111111111111, "percentage": 41.11, "elapsed_time": "0:01:19", "remaining_time": "0:01:53", "throughput": 1417.29, "total_tokens": 112624}
{"current_steps": 745, "total_steps": 1800, "loss": 0.2294, "lr": 3.6479161334675296e-05, "epoch": 4.138888888888889, "percentage": 41.39, "elapsed_time": "0:01:19", "remaining_time": "0:01:53", "throughput": 1419.25, "total_tokens": 113376}
{"current_steps": 750, "total_steps": 1800, "loss": 0.2318, "lr": 3.626328291331618e-05, "epoch": 4.166666666666667, "percentage": 41.67, "elapsed_time": "0:01:20", "remaining_time": "0:01:52", "throughput": 1420.86, "total_tokens": 114096}
{"current_steps": 755, "total_steps": 1800, "loss": 0.2405, "lr": 3.60463455520502e-05, "epoch": 4.194444444444445, "percentage": 41.94, "elapsed_time": "0:01:20", "remaining_time": "0:01:51", "throughput": 1422.72, "total_tokens": 114832}
{"current_steps": 760, "total_steps": 1800, "loss": 0.2252, "lr": 3.582836964667408e-05, "epoch": 4.222222222222222, "percentage": 42.22, "elapsed_time": "0:01:21", "remaining_time": "0:01:51", "throughput": 1425.35, "total_tokens": 115632}
{"current_steps": 765, "total_steps": 1800, "loss": 0.2274, "lr": 3.560937569062538e-05, "epoch": 4.25, "percentage": 42.5, "elapsed_time": "0:01:21", "remaining_time": "0:01:50", "throughput": 1426.92, "total_tokens": 116352}
{"current_steps": 770, "total_steps": 1800, "loss": 0.2275, "lr": 3.538938427305573e-05, "epoch": 4.277777777777778, "percentage": 42.78, "elapsed_time": "0:01:21", "remaining_time": "0:01:49", "throughput": 1429.51, "total_tokens": 117152}
{"current_steps": 775, "total_steps": 1800, "loss": 0.2315, "lr": 3.516841607689501e-05, "epoch": 4.305555555555555, "percentage": 43.06, "elapsed_time": "0:01:22", "remaining_time": "0:01:48", "throughput": 1431.49, "total_tokens": 117904}
{"current_steps": 780, "total_steps": 1800, "loss": 0.2477, "lr": 3.494649187690695e-05, "epoch": 4.333333333333333, "percentage": 43.33, "elapsed_time": "0:01:22", "remaining_time": "0:01:48", "throughput": 1433.63, "total_tokens": 118672}
{"current_steps": 785, "total_steps": 1800, "loss": 0.2364, "lr": 3.4723632537735846e-05, "epoch": 4.361111111111111, "percentage": 43.61, "elapsed_time": "0:01:23", "remaining_time": "0:01:47", "throughput": 1435.55, "total_tokens": 119424}
{"current_steps": 790, "total_steps": 1800, "loss": 0.2215, "lr": 3.449985901194498e-05, "epoch": 4.388888888888889, "percentage": 43.89, "elapsed_time": "0:01:23", "remaining_time": "0:01:46", "throughput": 1437.42, "total_tokens": 120176}
{"current_steps": 795, "total_steps": 1800, "loss": 0.2236, "lr": 3.427519233804667e-05, "epoch": 4.416666666666667, "percentage": 44.17, "elapsed_time": "0:01:24", "remaining_time": "0:01:46", "throughput": 1439.62, "total_tokens": 120960}
{"current_steps": 800, "total_steps": 1800, "loss": 0.2236, "lr": 3.404965363852437e-05, "epoch": 4.444444444444445, "percentage": 44.44, "elapsed_time": "0:01:24", "remaining_time": "0:01:45", "throughput": 1441.37, "total_tokens": 121712}
{"current_steps": 805, "total_steps": 1800, "loss": 0.2255, "lr": 3.382326411784672e-05, "epoch": 4.472222222222222, "percentage": 44.72, "elapsed_time": "0:01:24", "remaining_time": "0:01:44", "throughput": 1443.08, "total_tokens": 122464}
{"current_steps": 810, "total_steps": 1800, "loss": 0.2307, "lr": 3.359604506047403e-05, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:01:25", "remaining_time": "0:01:44", "throughput": 1445.08, "total_tokens": 123232}
{"current_steps": 810, "total_steps": 1800, "eval_loss": 0.24546261131763458, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:01:26", "remaining_time": "0:01:45", "throughput": 1430.5, "total_tokens": 123232}
{"current_steps": 815, "total_steps": 1800, "loss": 0.2561, "lr": 3.336801782885712e-05, "epoch": 4.527777777777778, "percentage": 45.28, "elapsed_time": "0:01:27", "remaining_time": "0:01:46", "throughput": 1412.22, "total_tokens": 124000}
{"current_steps": 820, "total_steps": 1800, "loss": 0.2566, "lr": 3.313920386142892e-05, "epoch": 4.555555555555555, "percentage": 45.56, "elapsed_time": "0:01:28", "remaining_time": "0:01:45", "throughput": 1414.21, "total_tokens": 124768}
{"current_steps": 825, "total_steps": 1800, "loss": 0.2327, "lr": 3.290962467058891e-05, "epoch": 4.583333333333333, "percentage": 45.83, "elapsed_time": "0:01:28", "remaining_time": "0:01:44", "throughput": 1415.96, "total_tokens": 125520}
{"current_steps": 830, "total_steps": 1800, "loss": 0.2206, "lr": 3.267930184068057e-05, "epoch": 4.611111111111111, "percentage": 46.11, "elapsed_time": "0:01:29", "remaining_time": "0:01:44", "throughput": 1417.65, "total_tokens": 126256}
{"current_steps": 835, "total_steps": 1800, "loss": 0.2357, "lr": 3.244825702596205e-05, "epoch": 4.638888888888889, "percentage": 46.39, "elapsed_time": "0:01:29", "remaining_time": "0:01:43", "throughput": 1419.46, "total_tokens": 127024}
{"current_steps": 840, "total_steps": 1800, "loss": 0.2289, "lr": 3.2216511948570374e-05, "epoch": 4.666666666666667, "percentage": 46.67, "elapsed_time": "0:01:29", "remaining_time": "0:01:42", "throughput": 1421.4, "total_tokens": 127792}
{"current_steps": 845, "total_steps": 1800, "loss": 0.2391, "lr": 3.198408839647911e-05, "epoch": 4.694444444444445, "percentage": 46.94, "elapsed_time": "0:01:30", "remaining_time": "0:01:42", "throughput": 1423.11, "total_tokens": 128544}
{"current_steps": 850, "total_steps": 1800, "loss": 0.2343, "lr": 3.1751008221450025e-05, "epoch": 4.722222222222222, "percentage": 47.22, "elapsed_time": "0:01:30", "remaining_time": "0:01:41", "throughput": 1424.99, "total_tokens": 129312}
{"current_steps": 855, "total_steps": 1800, "loss": 0.2278, "lr": 3.151729333697854e-05, "epoch": 4.75, "percentage": 47.5, "elapsed_time": "0:01:31", "remaining_time": "0:01:40", "throughput": 1427.29, "total_tokens": 130112}
{"current_steps": 860, "total_steps": 1800, "loss": 0.2338, "lr": 3.1282965716233594e-05, "epoch": 4.777777777777778, "percentage": 47.78, "elapsed_time": "0:01:31", "remaining_time": "0:01:40", "throughput": 1428.95, "total_tokens": 130864}
{"current_steps": 865, "total_steps": 1800, "loss": 0.2258, "lr": 3.104804738999169e-05, "epoch": 4.805555555555555, "percentage": 48.06, "elapsed_time": "0:01:31", "remaining_time": "0:01:39", "throughput": 1430.86, "total_tokens": 131632}
{"current_steps": 870, "total_steps": 1800, "loss": 0.2376, "lr": 3.0812560444565745e-05, "epoch": 4.833333333333333, "percentage": 48.33, "elapsed_time": "0:01:32", "remaining_time": "0:01:38", "throughput": 1432.68, "total_tokens": 132400}
{"current_steps": 875, "total_steps": 1800, "loss": 0.2318, "lr": 3.057652701972848e-05, "epoch": 4.861111111111111, "percentage": 48.61, "elapsed_time": "0:01:32", "remaining_time": "0:01:38", "throughput": 1434.38, "total_tokens": 133152}
{"current_steps": 880, "total_steps": 1800, "loss": 0.2514, "lr": 3.0339969306631005e-05, "epoch": 4.888888888888889, "percentage": 48.89, "elapsed_time": "0:01:33", "remaining_time": "0:01:37", "throughput": 1436.15, "total_tokens": 133920}
{"current_steps": 885, "total_steps": 1800, "loss": 0.2193, "lr": 3.0102909545716396e-05, "epoch": 4.916666666666667, "percentage": 49.17, "elapsed_time": "0:01:33", "remaining_time": "0:01:36", "throughput": 1437.98, "total_tokens": 134688}
{"current_steps": 890, "total_steps": 1800, "loss": 0.2272, "lr": 2.9865370024628775e-05, "epoch": 4.944444444444445, "percentage": 49.44, "elapsed_time": "0:01:34", "remaining_time": "0:01:36", "throughput": 1439.74, "total_tokens": 135456}
{"current_steps": 895, "total_steps": 1800, "loss": 0.2476, "lr": 2.9627373076117863e-05, "epoch": 4.972222222222222, "percentage": 49.72, "elapsed_time": "0:01:34", "remaining_time": "0:01:35", "throughput": 1441.72, "total_tokens": 136240}
{"current_steps": 900, "total_steps": 1800, "loss": 0.2319, "lr": 2.9388941075939334e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:34", "remaining_time": "0:01:34", "throughput": 1442.63, "total_tokens": 137008}
{"current_steps": 900, "total_steps": 1800, "eval_loss": 0.23156842589378357, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:35", "remaining_time": "0:01:35", "throughput": 1429.62, "total_tokens": 137008}
{"current_steps": 905, "total_steps": 1800, "loss": 0.2233, "lr": 2.9150096440751107e-05, "epoch": 5.027777777777778, "percentage": 50.28, "elapsed_time": "0:01:37", "remaining_time": "0:01:36", "throughput": 1410.39, "total_tokens": 137776}
{"current_steps": 910, "total_steps": 1800, "loss": 0.2314, "lr": 2.8910861626005776e-05, "epoch": 5.055555555555555, "percentage": 50.56, "elapsed_time": "0:01:38", "remaining_time": "0:01:35", "throughput": 1411.74, "total_tokens": 138496}
{"current_steps": 915, "total_steps": 1800, "loss": 0.2235, "lr": 2.8671259123839472e-05, "epoch": 5.083333333333333, "percentage": 50.83, "elapsed_time": "0:01:38", "remaining_time": "0:01:35", "throughput": 1413.75, "total_tokens": 139280}
{"current_steps": 920, "total_steps": 1800, "loss": 0.2359, "lr": 2.843131146095719e-05, "epoch": 5.111111111111111, "percentage": 51.11, "elapsed_time": "0:01:38", "remaining_time": "0:01:34", "throughput": 1415.86, "total_tokens": 140080}
{"current_steps": 925, "total_steps": 1800, "loss": 0.2401, "lr": 2.8191041196514873e-05, "epoch": 5.138888888888889, "percentage": 51.39, "elapsed_time": "0:01:39", "remaining_time": "0:01:33", "throughput": 1417.57, "total_tokens": 140848}
{"current_steps": 930, "total_steps": 1800, "loss": 0.2341, "lr": 2.795047091999849e-05, "epoch": 5.166666666666667, "percentage": 51.67, "elapsed_time": "0:01:39", "remaining_time": "0:01:33", "throughput": 1419.54, "total_tokens": 141632}
{"current_steps": 935, "total_steps": 1800, "loss": 0.2295, "lr": 2.770962324910027e-05, "epoch": 5.194444444444445, "percentage": 51.94, "elapsed_time": "0:01:40", "remaining_time": "0:01:32", "throughput": 1421.02, "total_tokens": 142368}
{"current_steps": 940, "total_steps": 1800, "loss": 0.2338, "lr": 2.7468520827592197e-05, "epoch": 5.222222222222222, "percentage": 52.22, "elapsed_time": "0:01:40", "remaining_time": "0:01:32", "throughput": 1422.64, "total_tokens": 143120}
{"current_steps": 945, "total_steps": 1800, "loss": 0.2255, "lr": 2.7227186323197162e-05, "epoch": 5.25, "percentage": 52.5, "elapsed_time": "0:01:41", "remaining_time": "0:01:31", "throughput": 1424.5, "total_tokens": 143904}
{"current_steps": 950, "total_steps": 1800, "loss": 0.2298, "lr": 2.6985642425457757e-05, "epoch": 5.277777777777778, "percentage": 52.78, "elapsed_time": "0:01:41", "remaining_time": "0:01:30", "throughput": 1425.77, "total_tokens": 144640}
{"current_steps": 955, "total_steps": 1800, "loss": 0.2315, "lr": 2.674391184360313e-05, "epoch": 5.305555555555555, "percentage": 53.06, "elapsed_time": "0:01:41", "remaining_time": "0:01:30", "throughput": 1427.08, "total_tokens": 145376}
{"current_steps": 960, "total_steps": 1800, "loss": 0.2237, "lr": 2.650201730441392e-05, "epoch": 5.333333333333333, "percentage": 53.33, "elapsed_time": "0:01:42", "remaining_time": "0:01:29", "throughput": 1428.79, "total_tokens": 146144}
{"current_steps": 965, "total_steps": 1800, "loss": 0.2343, "lr": 2.6259981550085504e-05, "epoch": 5.361111111111111, "percentage": 53.61, "elapsed_time": "0:01:42", "remaining_time": "0:01:28", "throughput": 1430.47, "total_tokens": 146912}
{"current_steps": 970, "total_steps": 1800, "loss": 0.2436, "lr": 2.60178273360899e-05, "epoch": 5.388888888888889, "percentage": 53.89, "elapsed_time": "0:01:43", "remaining_time": "0:01:28", "throughput": 1431.95, "total_tokens": 147664}
{"current_steps": 975, "total_steps": 1800, "loss": 0.2284, "lr": 2.5775577429036345e-05, "epoch": 5.416666666666667, "percentage": 54.17, "elapsed_time": "0:01:43", "remaining_time": "0:01:27", "throughput": 1433.79, "total_tokens": 148448}
{"current_steps": 980, "total_steps": 1800, "loss": 0.2464, "lr": 2.553325460453086e-05, "epoch": 5.444444444444445, "percentage": 54.44, "elapsed_time": "0:01:43", "remaining_time": "0:01:26", "throughput": 1435.33, "total_tokens": 149200}
{"current_steps": 985, "total_steps": 1800, "loss": 0.21, "lr": 2.5290881645034932e-05, "epoch": 5.472222222222222, "percentage": 54.72, "elapsed_time": "0:01:44", "remaining_time": "0:01:26", "throughput": 1436.55, "total_tokens": 149936}
{"current_steps": 990, "total_steps": 1800, "loss": 0.2225, "lr": 2.504848133772358e-05, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:01:44", "remaining_time": "0:01:25", "throughput": 1437.85, "total_tokens": 150672}
{"current_steps": 990, "total_steps": 1800, "eval_loss": 0.237586110830307, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:01:45", "remaining_time": "0:01:26", "throughput": 1426.07, "total_tokens": 150672}
{"current_steps": 995, "total_steps": 1800, "loss": 0.2193, "lr": 2.4806076472342997e-05, "epoch": 5.527777777777778, "percentage": 55.28, "elapsed_time": "0:01:47", "remaining_time": "0:01:26", "throughput": 1409.58, "total_tokens": 151440}
{"current_steps": 1000, "total_steps": 1800, "loss": 0.2278, "lr": 2.4563689839067913e-05, "epoch": 5.555555555555555, "percentage": 55.56, "elapsed_time": "0:01:47", "remaining_time": "0:01:26", "throughput": 1411.46, "total_tokens": 152224}
{"current_steps": 1005, "total_steps": 1800, "loss": 0.2352, "lr": 2.432134422635893e-05, "epoch": 5.583333333333333, "percentage": 55.83, "elapsed_time": "0:01:48", "remaining_time": "0:01:25", "throughput": 1413.06, "total_tokens": 152976}
{"current_steps": 1010, "total_steps": 1800, "loss": 0.2326, "lr": 2.4079062418820002e-05, "epoch": 5.611111111111111, "percentage": 56.11, "elapsed_time": "0:01:48", "remaining_time": "0:01:24", "throughput": 1414.81, "total_tokens": 153744}
{"current_steps": 1015, "total_steps": 1800, "loss": 0.2318, "lr": 2.3836867195056335e-05, "epoch": 5.638888888888889, "percentage": 56.39, "elapsed_time": "0:01:49", "remaining_time": "0:01:24", "throughput": 1416.44, "total_tokens": 154512}
{"current_steps": 1020, "total_steps": 1800, "loss": 0.2367, "lr": 2.3594781325532784e-05, "epoch": 5.666666666666667, "percentage": 56.67, "elapsed_time": "0:01:49", "remaining_time": "0:01:23", "throughput": 1418.14, "total_tokens": 155280}
{"current_steps": 1025, "total_steps": 1800, "loss": 0.2425, "lr": 2.3352827570433036e-05, "epoch": 5.694444444444445, "percentage": 56.94, "elapsed_time": "0:01:49", "remaining_time": "0:01:23", "throughput": 1419.7, "total_tokens": 156032}
{"current_steps": 1030, "total_steps": 1800, "loss": 0.2254, "lr": 2.3111028677519804e-05, "epoch": 5.722222222222222, "percentage": 57.22, "elapsed_time": "0:01:50", "remaining_time": "0:01:22", "throughput": 1421.78, "total_tokens": 156848}
{"current_steps": 1035, "total_steps": 1800, "loss": 0.2325, "lr": 2.2869407379996088e-05, "epoch": 5.75, "percentage": 57.5, "elapsed_time": "0:01:50", "remaining_time": "0:01:21", "throughput": 1423.3, "total_tokens": 157600}
{"current_steps": 1040, "total_steps": 1800, "loss": 0.2271, "lr": 2.2627986394367938e-05, "epoch": 5.777777777777778, "percentage": 57.78, "elapsed_time": "0:01:51", "remaining_time": "0:01:21", "throughput": 1424.79, "total_tokens": 158352}
{"current_steps": 1045, "total_steps": 1800, "loss": 0.2416, "lr": 2.238678841830867e-05, "epoch": 5.805555555555555, "percentage": 58.06, "elapsed_time": "0:01:51", "remaining_time": "0:01:20", "throughput": 1426.23, "total_tokens": 159104}
{"current_steps": 1050, "total_steps": 1800, "loss": 0.2402, "lr": 2.2145836128524902e-05, "epoch": 5.833333333333333, "percentage": 58.33, "elapsed_time": "0:01:51", "remaining_time": "0:01:19", "throughput": 1427.48, "total_tokens": 159856}
{"current_steps": 1055, "total_steps": 1800, "loss": 0.2359, "lr": 2.1905152178624595e-05, "epoch": 5.861111111111111, "percentage": 58.61, "elapsed_time": "0:01:52", "remaining_time": "0:01:19", "throughput": 1429.0, "total_tokens": 160624}
{"current_steps": 1060, "total_steps": 1800, "loss": 0.2378, "lr": 2.1664759196987182e-05, "epoch": 5.888888888888889, "percentage": 58.89, "elapsed_time": "0:01:52", "remaining_time": "0:01:18", "throughput": 1430.29, "total_tokens": 161360}
{"current_steps": 1065, "total_steps": 1800, "loss": 0.2323, "lr": 2.1424679784636144e-05, "epoch": 5.916666666666667, "percentage": 59.17, "elapsed_time": "0:01:53", "remaining_time": "0:01:18", "throughput": 1431.3, "total_tokens": 162080}
{"current_steps": 1070, "total_steps": 1800, "loss": 0.238, "lr": 2.118493651311413e-05, "epoch": 5.944444444444445, "percentage": 59.44, "elapsed_time": "0:01:53", "remaining_time": "0:01:17", "throughput": 1432.73, "total_tokens": 162832}
{"current_steps": 1075, "total_steps": 1800, "loss": 0.2338, "lr": 2.0945551922360818e-05, "epoch": 5.972222222222222, "percentage": 59.72, "elapsed_time": "0:01:54", "remaining_time": "0:01:16", "throughput": 1434.0, "total_tokens": 163568}
{"current_steps": 1080, "total_steps": 1800, "loss": 0.2297, "lr": 2.070654851859383e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:01:54", "remaining_time": "0:01:16", "throughput": 1434.8, "total_tokens": 164336}
{"current_steps": 1080, "total_steps": 1800, "eval_loss": 0.2332942932844162, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:01:55", "remaining_time": "0:01:16", "throughput": 1424.02, "total_tokens": 164336}
{"current_steps": 1085, "total_steps": 1800, "loss": 0.2255, "lr": 2.0467948772192713e-05, "epoch": 6.027777777777778, "percentage": 60.28, "elapsed_time": "0:01:57", "remaining_time": "0:01:17", "throughput": 1410.1, "total_tokens": 165072}
{"current_steps": 1090, "total_steps": 1800, "loss": 0.2316, "lr": 2.022977511558638e-05, "epoch": 6.055555555555555, "percentage": 60.56, "elapsed_time": "0:01:57", "remaining_time": "0:01:16", "throughput": 1411.5, "total_tokens": 165824}
{"current_steps": 1095, "total_steps": 1800, "loss": 0.2283, "lr": 1.9992049941144066e-05, "epoch": 6.083333333333333, "percentage": 60.83, "elapsed_time": "0:01:57", "remaining_time": "0:01:15", "throughput": 1413.17, "total_tokens": 166608}
{"current_steps": 1100, "total_steps": 1800, "loss": 0.2385, "lr": 1.9754795599070068e-05, "epoch": 6.111111111111111, "percentage": 61.11, "elapsed_time": "0:01:58", "remaining_time": "0:01:15", "throughput": 1414.56, "total_tokens": 167360}
{"current_steps": 1105, "total_steps": 1800, "loss": 0.2361, "lr": 1.9518034395302414e-05, "epoch": 6.138888888888889, "percentage": 61.39, "elapsed_time": "0:01:58", "remaining_time": "0:01:14", "throughput": 1415.98, "total_tokens": 168128}
{"current_steps": 1110, "total_steps": 1800, "loss": 0.2304, "lr": 1.9281788589415804e-05, "epoch": 6.166666666666667, "percentage": 61.67, "elapsed_time": "0:01:59", "remaining_time": "0:01:14", "throughput": 1417.49, "total_tokens": 168896}
{"current_steps": 1115, "total_steps": 1800, "loss": 0.2316, "lr": 1.9046080392528735e-05, "epoch": 6.194444444444445, "percentage": 61.94, "elapsed_time": "0:01:59", "remaining_time": "0:01:13", "throughput": 1418.86, "total_tokens": 169648}
{"current_steps": 1120, "total_steps": 1800, "loss": 0.2237, "lr": 1.8810931965215356e-05, "epoch": 6.222222222222222, "percentage": 62.22, "elapsed_time": "0:01:59", "remaining_time": "0:01:12", "throughput": 1420.29, "total_tokens": 170416}
{"current_steps": 1125, "total_steps": 1800, "loss": 0.2381, "lr": 1.857636541542195e-05, "epoch": 6.25, "percentage": 62.5, "elapsed_time": "0:02:00", "remaining_time": "0:01:12", "throughput": 1421.69, "total_tokens": 171184}
{"current_steps": 1130, "total_steps": 1800, "loss": 0.2279, "lr": 1.8342402796388445e-05, "epoch": 6.277777777777778, "percentage": 62.78, "elapsed_time": "0:02:00", "remaining_time": "0:01:11", "throughput": 1423.44, "total_tokens": 171984}
{"current_steps": 1135, "total_steps": 1800, "loss": 0.2197, "lr": 1.8109066104575023e-05, "epoch": 6.305555555555555, "percentage": 63.06, "elapsed_time": "0:02:01", "remaining_time": "0:01:11", "throughput": 1425.02, "total_tokens": 172768}
{"current_steps": 1140, "total_steps": 1800, "loss": 0.2378, "lr": 1.7876377277594053e-05, "epoch": 6.333333333333333, "percentage": 63.33, "elapsed_time": "0:02:01", "remaining_time": "0:01:10", "throughput": 1426.23, "total_tokens": 173520}
{"current_steps": 1145, "total_steps": 1800, "loss": 0.2275, "lr": 1.764435819214762e-05, "epoch": 6.361111111111111, "percentage": 63.61, "elapsed_time": "0:02:02", "remaining_time": "0:01:09", "throughput": 1427.75, "total_tokens": 174304}
{"current_steps": 1150, "total_steps": 1800, "loss": 0.2423, "lr": 1.7413030661970742e-05, "epoch": 6.388888888888889, "percentage": 63.89, "elapsed_time": "0:02:02", "remaining_time": "0:01:09", "throughput": 1428.83, "total_tokens": 175040}
{"current_steps": 1155, "total_steps": 1800, "loss": 0.2275, "lr": 1.7182416435780454e-05, "epoch": 6.416666666666667, "percentage": 64.17, "elapsed_time": "0:02:02", "remaining_time": "0:01:08", "throughput": 1429.88, "total_tokens": 175776}
{"current_steps": 1160, "total_steps": 1800, "loss": 0.2242, "lr": 1.695253719523115e-05, "epoch": 6.444444444444445, "percentage": 64.44, "elapsed_time": "0:02:03", "remaining_time": "0:01:08", "throughput": 1430.96, "total_tokens": 176512}
{"current_steps": 1165, "total_steps": 1800, "loss": 0.2388, "lr": 1.672341455287605e-05, "epoch": 6.472222222222222, "percentage": 64.72, "elapsed_time": "0:02:03", "remaining_time": "0:01:07", "throughput": 1432.25, "total_tokens": 177280}
{"current_steps": 1170, "total_steps": 1800, "loss": 0.2299, "lr": 1.649507005013532e-05, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:02:04", "remaining_time": "0:01:06", "throughput": 1433.46, "total_tokens": 178032}
{"current_steps": 1170, "total_steps": 1800, "eval_loss": 0.23246487975120544, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:02:05", "remaining_time": "0:01:07", "throughput": 1423.45, "total_tokens": 178032}
{"current_steps": 1175, "total_steps": 1800, "loss": 0.2214, "lr": 1.6267525155270773e-05, "epoch": 6.527777777777778, "percentage": 65.28, "elapsed_time": "0:02:06", "remaining_time": "0:01:07", "throughput": 1408.98, "total_tokens": 178784}
{"current_steps": 1180, "total_steps": 1800, "loss": 0.2287, "lr": 1.6040801261367493e-05, "epoch": 6.555555555555555, "percentage": 65.56, "elapsed_time": "0:02:07", "remaining_time": "0:01:06", "throughput": 1410.52, "total_tokens": 179568}
{"current_steps": 1185, "total_steps": 1800, "loss": 0.2405, "lr": 1.5814919684322545e-05, "epoch": 6.583333333333333, "percentage": 65.83, "elapsed_time": "0:02:07", "remaining_time": "0:01:06", "throughput": 1411.92, "total_tokens": 180336}
{"current_steps": 1190, "total_steps": 1800, "loss": 0.2293, "lr": 1.5589901660840896e-05, "epoch": 6.611111111111111, "percentage": 66.11, "elapsed_time": "0:02:08", "remaining_time": "0:01:05", "throughput": 1412.92, "total_tokens": 181056}
{"current_steps": 1195, "total_steps": 1800, "loss": 0.2238, "lr": 1.5365768346438797e-05, "epoch": 6.638888888888889, "percentage": 66.39, "elapsed_time": "0:02:08", "remaining_time": "0:01:05", "throughput": 1414.42, "total_tokens": 181840}
{"current_steps": 1200, "total_steps": 1800, "loss": 0.2256, "lr": 1.5142540813454836e-05, "epoch": 6.666666666666667, "percentage": 66.67, "elapsed_time": "0:02:08", "remaining_time": "0:01:04", "throughput": 1415.6, "total_tokens": 182592}
{"current_steps": 1205, "total_steps": 1800, "loss": 0.2518, "lr": 1.4920240049068748e-05, "epoch": 6.694444444444445, "percentage": 66.94, "elapsed_time": "0:02:09", "remaining_time": "0:01:03", "throughput": 1416.86, "total_tokens": 183344}
{"current_steps": 1210, "total_steps": 1800, "loss": 0.2219, "lr": 1.4698886953328292e-05, "epoch": 6.722222222222222, "percentage": 67.22, "elapsed_time": "0:02:09", "remaining_time": "0:01:03", "throughput": 1418.21, "total_tokens": 184112}
{"current_steps": 1215, "total_steps": 1800, "loss": 0.23, "lr": 1.4478502337184274e-05, "epoch": 6.75, "percentage": 67.5, "elapsed_time": "0:02:10", "remaining_time": "0:01:02", "throughput": 1419.46, "total_tokens": 184864}
{"current_steps": 1220, "total_steps": 1800, "loss": 0.2432, "lr": 1.4259106920533955e-05, "epoch": 6.777777777777778, "percentage": 67.78, "elapsed_time": "0:02:10", "remaining_time": "0:01:02", "throughput": 1420.78, "total_tokens": 185632}
{"current_steps": 1225, "total_steps": 1800, "loss": 0.2304, "lr": 1.4040721330273062e-05, "epoch": 6.805555555555555, "percentage": 68.06, "elapsed_time": "0:02:11", "remaining_time": "0:01:01", "throughput": 1421.89, "total_tokens": 186368}
{"current_steps": 1230, "total_steps": 1800, "loss": 0.2318, "lr": 1.3823366098356487e-05, "epoch": 6.833333333333333, "percentage": 68.33, "elapsed_time": "0:02:11", "remaining_time": "0:01:00", "throughput": 1423.08, "total_tokens": 187120}
{"current_steps": 1235, "total_steps": 1800, "loss": 0.238, "lr": 1.3607061659867892e-05, "epoch": 6.861111111111111, "percentage": 68.61, "elapsed_time": "0:02:11", "remaining_time": "0:01:00", "throughput": 1424.37, "total_tokens": 187888}
{"current_steps": 1240, "total_steps": 1800, "loss": 0.2317, "lr": 1.3391828351098578e-05, "epoch": 6.888888888888889, "percentage": 68.89, "elapsed_time": "0:02:12", "remaining_time": "0:00:59", "throughput": 1425.8, "total_tokens": 188672}
{"current_steps": 1245, "total_steps": 1800, "loss": 0.2238, "lr": 1.3177686407635417e-05, "epoch": 6.916666666666667, "percentage": 69.17, "elapsed_time": "0:02:12", "remaining_time": "0:00:59", "throughput": 1426.96, "total_tokens": 189424}
{"current_steps": 1250, "total_steps": 1800, "loss": 0.224, "lr": 1.29646559624584e-05, "epoch": 6.944444444444445, "percentage": 69.44, "elapsed_time": "0:02:13", "remaining_time": "0:00:58", "throughput": 1428.14, "total_tokens": 190176}
{"current_steps": 1255, "total_steps": 1800, "loss": 0.2277, "lr": 1.2752757044047827e-05, "epoch": 6.972222222222222, "percentage": 69.72, "elapsed_time": "0:02:13", "remaining_time": "0:00:58", "throughput": 1429.16, "total_tokens": 190928}
{"current_steps": 1260, "total_steps": 1800, "loss": 0.2122, "lr": 1.2542009574501246e-05, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:02:14", "remaining_time": "0:00:57", "throughput": 1429.98, "total_tokens": 191712}
{"current_steps": 1260, "total_steps": 1800, "eval_loss": 0.23317117989063263, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:02:14", "remaining_time": "0:00:57", "throughput": 1420.74, "total_tokens": 191712}
{"current_steps": 1265, "total_steps": 1800, "loss": 0.2311, "lr": 1.2332433367660442e-05, "epoch": 7.027777777777778, "percentage": 70.28, "elapsed_time": "0:02:16", "remaining_time": "0:00:57", "throughput": 1410.11, "total_tokens": 192480}
{"current_steps": 1270, "total_steps": 1800, "loss": 0.2233, "lr": 1.2124048127248644e-05, "epoch": 7.055555555555555, "percentage": 70.56, "elapsed_time": "0:02:16", "remaining_time": "0:00:57", "throughput": 1411.43, "total_tokens": 193248}
{"current_steps": 1275, "total_steps": 1800, "loss": 0.228, "lr": 1.1916873445017982e-05, "epoch": 7.083333333333333, "percentage": 70.83, "elapsed_time": "0:02:17", "remaining_time": "0:00:56", "throughput": 1412.62, "total_tokens": 194000}
{"current_steps": 1280, "total_steps": 1800, "loss": 0.2322, "lr": 1.1710928798907556e-05, "epoch": 7.111111111111111, "percentage": 71.11, "elapsed_time": "0:02:17", "remaining_time": "0:00:55", "throughput": 1413.82, "total_tokens": 194752}
{"current_steps": 1285, "total_steps": 1800, "loss": 0.2488, "lr": 1.1506233551212186e-05, "epoch": 7.138888888888889, "percentage": 71.39, "elapsed_time": "0:02:18", "remaining_time": "0:00:55", "throughput": 1415.03, "total_tokens": 195504}
{"current_steps": 1290, "total_steps": 1800, "loss": 0.2513, "lr": 1.1302806946762004e-05, "epoch": 7.166666666666667, "percentage": 71.67, "elapsed_time": "0:02:18", "remaining_time": "0:00:54", "throughput": 1415.9, "total_tokens": 196224}
{"current_steps": 1295, "total_steps": 1800, "loss": 0.2143, "lr": 1.1100668111113166e-05, "epoch": 7.194444444444445, "percentage": 71.94, "elapsed_time": "0:02:18", "remaining_time": "0:00:54", "throughput": 1417.1, "total_tokens": 196976}
{"current_steps": 1300, "total_steps": 1800, "loss": 0.2304, "lr": 1.0899836048749645e-05, "epoch": 7.222222222222222, "percentage": 72.22, "elapsed_time": "0:02:19", "remaining_time": "0:00:53", "throughput": 1418.58, "total_tokens": 197776}
{"current_steps": 1305, "total_steps": 1800, "loss": 0.2479, "lr": 1.0700329641296541e-05, "epoch": 7.25, "percentage": 72.5, "elapsed_time": "0:02:19", "remaining_time": "0:00:53", "throughput": 1419.63, "total_tokens": 198512}
{"current_steps": 1310, "total_steps": 1800, "loss": 0.2447, "lr": 1.0502167645744895e-05, "epoch": 7.277777777777778, "percentage": 72.78, "elapsed_time": "0:02:20", "remaining_time": "0:00:52", "throughput": 1420.89, "total_tokens": 199280}
{"current_steps": 1315, "total_steps": 1800, "loss": 0.2298, "lr": 1.0305368692688174e-05, "epoch": 7.305555555555555, "percentage": 73.06, "elapsed_time": "0:02:20", "remaining_time": "0:00:51", "throughput": 1422.03, "total_tokens": 200032}
{"current_steps": 1320, "total_steps": 1800, "loss": 0.2318, "lr": 1.01099512845707e-05, "epoch": 7.333333333333333, "percentage": 73.33, "elapsed_time": "0:02:21", "remaining_time": "0:00:51", "throughput": 1423.06, "total_tokens": 200768}
{"current_steps": 1325, "total_steps": 1800, "loss": 0.2318, "lr": 9.91593379394811e-06, "epoch": 7.361111111111111, "percentage": 73.61, "elapsed_time": "0:02:21", "remaining_time": "0:00:50", "throughput": 1424.41, "total_tokens": 201552}
{"current_steps": 1330, "total_steps": 1800, "loss": 0.2298, "lr": 9.723334461760006e-06, "epoch": 7.388888888888889, "percentage": 73.89, "elapsed_time": "0:02:21", "remaining_time": "0:00:50", "throughput": 1425.67, "total_tokens": 202320}
{"current_steps": 1335, "total_steps": 1800, "loss": 0.2276, "lr": 9.532171395615036e-06, "epoch": 7.416666666666667, "percentage": 74.17, "elapsed_time": "0:02:22", "remaining_time": "0:00:49", "throughput": 1426.93, "total_tokens": 203088}
{"current_steps": 1340, "total_steps": 1800, "loss": 0.2335, "lr": 9.342462568088416e-06, "epoch": 7.444444444444445, "percentage": 74.44, "elapsed_time": "0:02:22", "remaining_time": "0:00:48", "throughput": 1427.95, "total_tokens": 203824}
{"current_steps": 1345, "total_steps": 1800, "loss": 0.2282, "lr": 9.154225815032242e-06, "epoch": 7.472222222222222, "percentage": 74.72, "elapsed_time": "0:02:23", "remaining_time": "0:00:48", "throughput": 1429.09, "total_tokens": 204576}
{"current_steps": 1350, "total_steps": 1800, "loss": 0.2274, "lr": 8.967478833898612e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:02:23", "remaining_time": "0:00:47", "throughput": 1430.0, "total_tokens": 205312}
{"current_steps": 1350, "total_steps": 1800, "eval_loss": 0.2340662032365799, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:02:24", "remaining_time": "0:00:48", "throughput": 1421.29, "total_tokens": 205312}
{"current_steps": 1355, "total_steps": 1800, "loss": 0.2278, "lr": 8.78223918207575e-06, "epoch": 7.527777777777778, "percentage": 75.28, "elapsed_time": "0:02:26", "remaining_time": "0:00:48", "throughput": 1408.47, "total_tokens": 206080}
{"current_steps": 1360, "total_steps": 1800, "loss": 0.2257, "lr": 8.598524275237322e-06, "epoch": 7.555555555555555, "percentage": 75.56, "elapsed_time": "0:02:26", "remaining_time": "0:00:47", "throughput": 1409.72, "total_tokens": 206848}
{"current_steps": 1365, "total_steps": 1800, "loss": 0.2215, "lr": 8.41635138570507e-06, "epoch": 7.583333333333333, "percentage": 75.83, "elapsed_time": "0:02:27", "remaining_time": "0:00:46", "throughput": 1410.96, "total_tokens": 207616}
{"current_steps": 1370, "total_steps": 1800, "loss": 0.2318, "lr": 8.235737640824908e-06, "epoch": 7.611111111111111, "percentage": 76.11, "elapsed_time": "0:02:27", "remaining_time": "0:00:46", "throughput": 1411.99, "total_tokens": 208352}
{"current_steps": 1375, "total_steps": 1800, "loss": 0.2318, "lr": 8.056700021356694e-06, "epoch": 7.638888888888889, "percentage": 76.39, "elapsed_time": "0:02:27", "remaining_time": "0:00:45", "throughput": 1413.11, "total_tokens": 209104}
{"current_steps": 1380, "total_steps": 1800, "loss": 0.2214, "lr": 7.879255359877705e-06, "epoch": 7.666666666666667, "percentage": 76.67, "elapsed_time": "0:02:28", "remaining_time": "0:00:45", "throughput": 1413.94, "total_tokens": 209824}
{"current_steps": 1385, "total_steps": 1800, "loss": 0.2277, "lr": 7.703420339200101e-06, "epoch": 7.694444444444445, "percentage": 76.94, "elapsed_time": "0:02:28", "remaining_time": "0:00:44", "throughput": 1415.04, "total_tokens": 210576}
{"current_steps": 1390, "total_steps": 1800, "loss": 0.2321, "lr": 7.529211490802498e-06, "epoch": 7.722222222222222, "percentage": 77.22, "elapsed_time": "0:02:29", "remaining_time": "0:00:44", "throughput": 1416.47, "total_tokens": 211376}
{"current_steps": 1395, "total_steps": 1800, "loss": 0.2219, "lr": 7.3566451932756744e-06, "epoch": 7.75, "percentage": 77.5, "elapsed_time": "0:02:29", "remaining_time": "0:00:43", "throughput": 1417.55, "total_tokens": 212128}
{"current_steps": 1400, "total_steps": 1800, "loss": 0.2341, "lr": 7.185737670782727e-06, "epoch": 7.777777777777778, "percentage": 77.78, "elapsed_time": "0:02:30", "remaining_time": "0:00:42", "throughput": 1418.96, "total_tokens": 212928}
{"current_steps": 1405, "total_steps": 1800, "loss": 0.2281, "lr": 7.016504991533726e-06, "epoch": 7.805555555555555, "percentage": 78.06, "elapsed_time": "0:02:30", "remaining_time": "0:00:42", "throughput": 1420.15, "total_tokens": 213696}
{"current_steps": 1410, "total_steps": 1800, "loss": 0.2235, "lr": 6.848963066275027e-06, "epoch": 7.833333333333333, "percentage": 78.33, "elapsed_time": "0:02:30", "remaining_time": "0:00:41", "throughput": 1421.31, "total_tokens": 214464}
{"current_steps": 1415, "total_steps": 1800, "loss": 0.2256, "lr": 6.683127646793411e-06, "epoch": 7.861111111111111, "percentage": 78.61, "elapsed_time": "0:02:31", "remaining_time": "0:00:41", "throughput": 1422.59, "total_tokens": 215248}
{"current_steps": 1420, "total_steps": 1800, "loss": 0.23, "lr": 6.519014324435102e-06, "epoch": 7.888888888888889, "percentage": 78.89, "elapsed_time": "0:02:31", "remaining_time": "0:00:40", "throughput": 1423.73, "total_tokens": 216016}
{"current_steps": 1425, "total_steps": 1800, "loss": 0.2161, "lr": 6.356638528639955e-06, "epoch": 7.916666666666667, "percentage": 79.17, "elapsed_time": "0:02:32", "remaining_time": "0:00:40", "throughput": 1424.86, "total_tokens": 216784}
{"current_steps": 1430, "total_steps": 1800, "loss": 0.2378, "lr": 6.196015525490825e-06, "epoch": 7.944444444444445, "percentage": 79.44, "elapsed_time": "0:02:32", "remaining_time": "0:00:39", "throughput": 1425.91, "total_tokens": 217552}
{"current_steps": 1435, "total_steps": 1800, "loss": 0.2106, "lr": 6.037160416278278e-06, "epoch": 7.972222222222222, "percentage": 79.72, "elapsed_time": "0:02:32", "remaining_time": "0:00:38", "throughput": 1427.09, "total_tokens": 218320}
{"current_steps": 1440, "total_steps": 1800, "loss": 0.2397, "lr": 5.880088136080814e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:02:33", "remaining_time": "0:00:38", "throughput": 1427.5, "total_tokens": 219072}
{"current_steps": 1440, "total_steps": 1800, "eval_loss": 0.23981384932994843, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:02:34", "remaining_time": "0:00:38", "throughput": 1419.51, "total_tokens": 219072}
{"current_steps": 1445, "total_steps": 1800, "loss": 0.2387, "lr": 5.724813452360736e-06, "epoch": 8.027777777777779, "percentage": 80.28, "elapsed_time": "0:02:35", "remaining_time": "0:00:38", "throughput": 1409.78, "total_tokens": 219824}
{"current_steps": 1450, "total_steps": 1800, "loss": 0.225, "lr": 5.571350963575728e-06, "epoch": 8.055555555555555, "percentage": 80.56, "elapsed_time": "0:02:36", "remaining_time": "0:00:37", "throughput": 1411.04, "total_tokens": 220608}
{"current_steps": 1455, "total_steps": 1800, "loss": 0.2226, "lr": 5.4197150978063965e-06, "epoch": 8.083333333333334, "percentage": 80.83, "elapsed_time": "0:02:36", "remaining_time": "0:00:37", "throughput": 1411.98, "total_tokens": 221344}
{"current_steps": 1460, "total_steps": 1800, "loss": 0.2099, "lr": 5.269920111399732e-06, "epoch": 8.11111111111111, "percentage": 81.11, "elapsed_time": "0:02:37", "remaining_time": "0:00:36", "throughput": 1412.97, "total_tokens": 222096}
{"current_steps": 1465, "total_steps": 1800, "loss": 0.22, "lr": 5.121980087628803e-06, "epoch": 8.13888888888889, "percentage": 81.39, "elapsed_time": "0:02:37", "remaining_time": "0:00:36", "throughput": 1414.05, "total_tokens": 222864}
{"current_steps": 1470, "total_steps": 1800, "loss": 0.2085, "lr": 4.975908935368701e-06, "epoch": 8.166666666666666, "percentage": 81.67, "elapsed_time": "0:02:38", "remaining_time": "0:00:35", "throughput": 1415.21, "total_tokens": 223648}
{"current_steps": 1475, "total_steps": 1800, "loss": 0.2232, "lr": 4.831720387788827e-06, "epoch": 8.194444444444445, "percentage": 81.94, "elapsed_time": "0:02:38", "remaining_time": "0:00:34", "throughput": 1416.54, "total_tokens": 224448}
{"current_steps": 1480, "total_steps": 1800, "loss": 0.2372, "lr": 4.689428001061774e-06, "epoch": 8.222222222222221, "percentage": 82.22, "elapsed_time": "0:02:38", "remaining_time": "0:00:34", "throughput": 1417.44, "total_tokens": 225184}
{"current_steps": 1485, "total_steps": 1800, "loss": 0.2445, "lr": 4.549045153088813e-06, "epoch": 8.25, "percentage": 82.5, "elapsed_time": "0:02:39", "remaining_time": "0:00:33", "throughput": 1418.46, "total_tokens": 225936}
{"current_steps": 1490, "total_steps": 1800, "loss": 0.2127, "lr": 4.410585042242124e-06, "epoch": 8.277777777777779, "percentage": 82.78, "elapsed_time": "0:02:39", "remaining_time": "0:00:33", "throughput": 1419.33, "total_tokens": 226672}
{"current_steps": 1495, "total_steps": 1800, "loss": 0.2291, "lr": 4.274060686123959e-06, "epoch": 8.305555555555555, "percentage": 83.06, "elapsed_time": "0:02:40", "remaining_time": "0:00:32", "throughput": 1420.34, "total_tokens": 227424}
{"current_steps": 1500, "total_steps": 1800, "loss": 0.2215, "lr": 4.1394849203427284e-06, "epoch": 8.333333333333334, "percentage": 83.33, "elapsed_time": "0:02:40", "remaining_time": "0:00:32", "throughput": 1421.49, "total_tokens": 228208}
{"current_steps": 1505, "total_steps": 1800, "loss": 0.2285, "lr": 4.006870397306256e-06, "epoch": 8.36111111111111, "percentage": 83.61, "elapsed_time": "0:02:40", "remaining_time": "0:00:31", "throughput": 1422.69, "total_tokens": 228992}
{"current_steps": 1510, "total_steps": 1800, "loss": 0.2346, "lr": 3.876229585032245e-06, "epoch": 8.38888888888889, "percentage": 83.89, "elapsed_time": "0:02:41", "remaining_time": "0:00:30", "throughput": 1423.65, "total_tokens": 229744}
{"current_steps": 1515, "total_steps": 1800, "loss": 0.2227, "lr": 3.7475747659760502e-06, "epoch": 8.416666666666666, "percentage": 84.17, "elapsed_time": "0:02:41", "remaining_time": "0:00:30", "throughput": 1424.59, "total_tokens": 230496}
{"current_steps": 1520, "total_steps": 1800, "loss": 0.2451, "lr": 3.6209180358759394e-06, "epoch": 8.444444444444445, "percentage": 84.44, "elapsed_time": "0:02:42", "remaining_time": "0:00:29", "throughput": 1425.51, "total_tokens": 231248}
{"current_steps": 1525, "total_steps": 1800, "loss": 0.2349, "lr": 3.4962713026158694e-06, "epoch": 8.472222222222221, "percentage": 84.72, "elapsed_time": "0:02:42", "remaining_time": "0:00:29", "throughput": 1426.48, "total_tokens": 232000}
{"current_steps": 1530, "total_steps": 1800, "loss": 0.2326, "lr": 3.373646285105958e-06, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:02:43", "remaining_time": "0:00:28", "throughput": 1427.47, "total_tokens": 232768}
{"current_steps": 1530, "total_steps": 1800, "eval_loss": 0.23918041586875916, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:02:43", "remaining_time": "0:00:28", "throughput": 1419.88, "total_tokens": 232768}
{"current_steps": 1535, "total_steps": 1800, "loss": 0.2182, "lr": 3.2530545121807145e-06, "epoch": 8.527777777777779, "percentage": 85.28, "elapsed_time": "0:02:45", "remaining_time": "0:00:28", "throughput": 1410.19, "total_tokens": 233568}
{"current_steps": 1540, "total_steps": 1800, "loss": 0.2303, "lr": 3.1345073215151066e-06, "epoch": 8.555555555555555, "percentage": 85.56, "elapsed_time": "0:02:46", "remaining_time": "0:00:28", "throughput": 1411.11, "total_tokens": 234320}
{"current_steps": 1545, "total_steps": 1800, "loss": 0.2351, "lr": 3.0180158585586397e-06, "epoch": 8.583333333333334, "percentage": 85.83, "elapsed_time": "0:02:46", "remaining_time": "0:00:27", "throughput": 1411.91, "total_tokens": 235040}
{"current_steps": 1550, "total_steps": 1800, "loss": 0.2208, "lr": 2.9035910754875136e-06, "epoch": 8.61111111111111, "percentage": 86.11, "elapsed_time": "0:02:46", "remaining_time": "0:00:26", "throughput": 1413.01, "total_tokens": 235824}
{"current_steps": 1555, "total_steps": 1800, "loss": 0.2515, "lr": 2.7912437301749026e-06, "epoch": 8.63888888888889, "percentage": 86.39, "elapsed_time": "0:02:47", "remaining_time": "0:00:26", "throughput": 1414.09, "total_tokens": 236592}
{"current_steps": 1560, "total_steps": 1800, "loss": 0.2304, "lr": 2.6809843851795357e-06, "epoch": 8.666666666666666, "percentage": 86.67, "elapsed_time": "0:02:47", "remaining_time": "0:00:25", "throughput": 1415.01, "total_tokens": 237344}
{"current_steps": 1565, "total_steps": 1800, "loss": 0.2283, "lr": 2.57282340675267e-06, "epoch": 8.694444444444445, "percentage": 86.94, "elapsed_time": "0:02:48", "remaining_time": "0:00:25", "throughput": 1415.87, "total_tokens": 238080}
{"current_steps": 1570, "total_steps": 1800, "loss": 0.218, "lr": 2.4667709638634434e-06, "epoch": 8.722222222222221, "percentage": 87.22, "elapsed_time": "0:02:48", "remaining_time": "0:00:24", "throughput": 1416.74, "total_tokens": 238816}
{"current_steps": 1575, "total_steps": 1800, "loss": 0.2227, "lr": 2.3628370272428564e-06, "epoch": 8.75, "percentage": 87.5, "elapsed_time": "0:02:48", "remaining_time": "0:00:24", "throughput": 1417.67, "total_tokens": 239568}
{"current_steps": 1580, "total_steps": 1800, "loss": 0.2221, "lr": 2.2610313684463177e-06, "epoch": 8.777777777777779, "percentage": 87.78, "elapsed_time": "0:02:49", "remaining_time": "0:00:23", "throughput": 1418.8, "total_tokens": 240352}
{"current_steps": 1585, "total_steps": 1800, "loss": 0.2258, "lr": 2.1613635589349756e-06, "epoch": 8.805555555555555, "percentage": 88.06, "elapsed_time": "0:02:49", "remaining_time": "0:00:23", "throughput": 1419.82, "total_tokens": 241120}
{"current_steps": 1590, "total_steps": 1800, "loss": 0.2072, "lr": 2.063842969175847e-06, "epoch": 8.833333333333334, "percentage": 88.33, "elapsed_time": "0:02:50", "remaining_time": "0:00:22", "throughput": 1420.66, "total_tokens": 241856}
{"current_steps": 1595, "total_steps": 1800, "loss": 0.227, "lr": 1.968478767760812e-06, "epoch": 8.86111111111111, "percentage": 88.61, "elapsed_time": "0:02:50", "remaining_time": "0:00:21", "throughput": 1421.47, "total_tokens": 242608}
{"current_steps": 1600, "total_steps": 1800, "loss": 0.2292, "lr": 1.8752799205445982e-06, "epoch": 8.88888888888889, "percentage": 88.89, "elapsed_time": "0:02:51", "remaining_time": "0:00:21", "throughput": 1422.35, "total_tokens": 243360}
{"current_steps": 1605, "total_steps": 1800, "loss": 0.2272, "lr": 1.784255189801895e-06, "epoch": 8.916666666666666, "percentage": 89.17, "elapsed_time": "0:02:51", "remaining_time": "0:00:20", "throughput": 1423.33, "total_tokens": 244128}
{"current_steps": 1610, "total_steps": 1800, "loss": 0.2165, "lr": 1.6954131334034922e-06, "epoch": 8.944444444444445, "percentage": 89.44, "elapsed_time": "0:02:51", "remaining_time": "0:00:20", "throughput": 1424.36, "total_tokens": 244896}
{"current_steps": 1615, "total_steps": 1800, "loss": 0.2252, "lr": 1.6087621040117157e-06, "epoch": 8.972222222222221, "percentage": 89.72, "elapsed_time": "0:02:52", "remaining_time": "0:00:19", "throughput": 1425.47, "total_tokens": 245664}
{"current_steps": 1620, "total_steps": 1800, "loss": 0.2314, "lr": 1.524310248295152e-06, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:02:52", "remaining_time": "0:00:19", "throughput": 1425.85, "total_tokens": 246416}
{"current_steps": 1620, "total_steps": 1800, "eval_loss": 0.23724833130836487, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:02:53", "remaining_time": "0:00:19", "throughput": 1418.82, "total_tokens": 246416}
{"current_steps": 1625, "total_steps": 1800, "loss": 0.224, "lr": 1.4420655061626932e-06, "epoch": 9.027777777777779, "percentage": 90.28, "elapsed_time": "0:02:55", "remaining_time": "0:00:18", "throughput": 1410.33, "total_tokens": 247184}
{"current_steps": 1630, "total_steps": 1800, "loss": 0.2113, "lr": 1.362035610017079e-06, "epoch": 9.055555555555555, "percentage": 90.56, "elapsed_time": "0:02:55", "remaining_time": "0:00:18", "throughput": 1411.27, "total_tokens": 247936}
{"current_steps": 1635, "total_steps": 1800, "loss": 0.2259, "lr": 1.2842280840278997e-06, "epoch": 9.083333333333334, "percentage": 90.83, "elapsed_time": "0:02:56", "remaining_time": "0:00:17", "throughput": 1412.2, "total_tokens": 248688}
{"current_steps": 1640, "total_steps": 1800, "loss": 0.2334, "lr": 1.2086502434241865e-06, "epoch": 9.11111111111111, "percentage": 91.11, "elapsed_time": "0:02:56", "remaining_time": "0:00:17", "throughput": 1413.32, "total_tokens": 249472}
{"current_steps": 1645, "total_steps": 1800, "loss": 0.2343, "lr": 1.1353091938067023e-06, "epoch": 9.13888888888889, "percentage": 91.39, "elapsed_time": "0:02:56", "remaining_time": "0:00:16", "throughput": 1414.25, "total_tokens": 250224}
{"current_steps": 1650, "total_steps": 1800, "loss": 0.2204, "lr": 1.0642118304798442e-06, "epoch": 9.166666666666666, "percentage": 91.67, "elapsed_time": "0:02:57", "remaining_time": "0:00:16", "throughput": 1415.06, "total_tokens": 250960}
{"current_steps": 1655, "total_steps": 1800, "loss": 0.2128, "lr": 9.95364837803392e-07, "epoch": 9.194444444444445, "percentage": 91.94, "elapsed_time": "0:02:57", "remaining_time": "0:00:15", "throughput": 1416.03, "total_tokens": 251728}
{"current_steps": 1660, "total_steps": 1800, "loss": 0.2267, "lr": 9.287746885640603e-07, "epoch": 9.222222222222221, "percentage": 92.22, "elapsed_time": "0:02:58", "remaining_time": "0:00:15", "throughput": 1417.14, "total_tokens": 252512}
{"current_steps": 1665, "total_steps": 1800, "loss": 0.2159, "lr": 8.64447643366953e-07, "epoch": 9.25, "percentage": 92.5, "elapsed_time": "0:02:58", "remaining_time": "0:00:14", "throughput": 1418.14, "total_tokens": 253280}
{"current_steps": 1670, "total_steps": 1800, "loss": 0.2129, "lr": 8.023897500469391e-07, "epoch": 9.277777777777779, "percentage": 92.78, "elapsed_time": "0:02:59", "remaining_time": "0:00:13", "throughput": 1419.06, "total_tokens": 254032}
{"current_steps": 1675, "total_steps": 1800, "loss": 0.1987, "lr": 7.426068431000882e-07, "epoch": 9.305555555555555, "percentage": 93.06, "elapsed_time": "0:02:59", "remaining_time": "0:00:13", "throughput": 1420.01, "total_tokens": 254800}
{"current_steps": 1680, "total_steps": 1800, "loss": 0.2243, "lr": 6.851045431350927e-07, "epoch": 9.333333333333334, "percentage": 93.33, "elapsed_time": "0:02:59", "remaining_time": "0:00:12", "throughput": 1421.08, "total_tokens": 255584}
{"current_steps": 1685, "total_steps": 1800, "loss": 0.2209, "lr": 6.298882563448599e-07, "epoch": 9.36111111111111, "percentage": 93.61, "elapsed_time": "0:03:00", "remaining_time": "0:00:12", "throughput": 1422.14, "total_tokens": 256368}
{"current_steps": 1690, "total_steps": 1800, "loss": 0.2311, "lr": 5.769631739982267e-07, "epoch": 9.38888888888889, "percentage": 93.89, "elapsed_time": "0:03:00", "remaining_time": "0:00:11", "throughput": 1422.91, "total_tokens": 257104}
{"current_steps": 1695, "total_steps": 1800, "loss": 0.2182, "lr": 5.263342719518921e-07, "epoch": 9.416666666666666, "percentage": 94.17, "elapsed_time": "0:03:01", "remaining_time": "0:00:11", "throughput": 1423.78, "total_tokens": 257856}
{"current_steps": 1700, "total_steps": 1800, "loss": 0.2338, "lr": 4.780063101826132e-07, "epoch": 9.444444444444445, "percentage": 94.44, "elapsed_time": "0:03:01", "remaining_time": "0:00:10", "throughput": 1424.66, "total_tokens": 258608}
{"current_steps": 1705, "total_steps": 1800, "loss": 0.2313, "lr": 4.319838323396691e-07, "epoch": 9.472222222222221, "percentage": 94.72, "elapsed_time": "0:03:01", "remaining_time": "0:00:10", "throughput": 1425.43, "total_tokens": 259344}
{"current_steps": 1710, "total_steps": 1800, "loss": 0.2125, "lr": 3.88271165317694e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:03:02", "remaining_time": "0:00:09", "throughput": 1426.33, "total_tokens": 260112}
{"current_steps": 1710, "total_steps": 1800, "eval_loss": 0.23740486800670624, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:03:03", "remaining_time": "0:00:09", "throughput": 1419.57, "total_tokens": 260112}
{"current_steps": 1715, "total_steps": 1800, "loss": 0.2365, "lr": 3.468724188498751e-07, "epoch": 9.527777777777779, "percentage": 95.28, "elapsed_time": "0:03:04", "remaining_time": "0:00:09", "throughput": 1410.49, "total_tokens": 260864}
{"current_steps": 1720, "total_steps": 1800, "loss": 0.21, "lr": 3.077914851215585e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:03:05", "remaining_time": "0:00:08", "throughput": 1411.47, "total_tokens": 261632}
{"current_steps": 1725, "total_steps": 1800, "loss": 0.2185, "lr": 2.71032038404323e-07, "epoch": 9.583333333333334, "percentage": 95.83, "elapsed_time": "0:03:05", "remaining_time": "0:00:08", "throughput": 1412.28, "total_tokens": 262368}
{"current_steps": 1730, "total_steps": 1800, "loss": 0.2031, "lr": 2.365975347105448e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:03:06", "remaining_time": "0:00:07", "throughput": 1413.24, "total_tokens": 263136}
{"current_steps": 1735, "total_steps": 1800, "loss": 0.2374, "lr": 2.0449121146845774e-07, "epoch": 9.63888888888889, "percentage": 96.39, "elapsed_time": "0:03:06", "remaining_time": "0:00:06", "throughput": 1414.02, "total_tokens": 263872}
{"current_steps": 1740, "total_steps": 1800, "loss": 0.2216, "lr": 1.747160872177883e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:03:07", "remaining_time": "0:00:06", "throughput": 1414.82, "total_tokens": 264608}
{"current_steps": 1745, "total_steps": 1800, "loss": 0.2279, "lr": 1.472749613259661e-07, "epoch": 9.694444444444445, "percentage": 96.94, "elapsed_time": "0:03:07", "remaining_time": "0:00:05", "throughput": 1415.48, "total_tokens": 265328}
{"current_steps": 1750, "total_steps": 1800, "loss": 0.224, "lr": 1.22170413724923e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:03:07", "remaining_time": "0:00:05", "throughput": 1416.53, "total_tokens": 266112}
{"current_steps": 1755, "total_steps": 1800, "loss": 0.2377, "lr": 9.940480466855417e-08, "epoch": 9.75, "percentage": 97.5, "elapsed_time": "0:03:08", "remaining_time": "0:00:04", "throughput": 1417.41, "total_tokens": 266864}
{"current_steps": 1760, "total_steps": 1800, "loss": 0.2261, "lr": 7.898027451078982e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:03:08", "remaining_time": "0:00:04", "throughput": 1418.18, "total_tokens": 267600}
{"current_steps": 1765, "total_steps": 1800, "loss": 0.2265, "lr": 6.089874350439506e-08, "epoch": 9.805555555555555, "percentage": 98.06, "elapsed_time": "0:03:09", "remaining_time": "0:00:03", "throughput": 1419.22, "total_tokens": 268384}
{"current_steps": 1770, "total_steps": 1800, "loss": 0.2262, "lr": 4.516191162040051e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:03:09", "remaining_time": "0:00:03", "throughput": 1420.25, "total_tokens": 269168}
{"current_steps": 1775, "total_steps": 1800, "loss": 0.2183, "lr": 3.177125838830786e-08, "epoch": 9.86111111111111, "percentage": 98.61, "elapsed_time": "0:03:09", "remaining_time": "0:00:02", "throughput": 1421.02, "total_tokens": 269904}
{"current_steps": 1780, "total_steps": 1800, "loss": 0.2199, "lr": 2.0728042756967824e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:03:10", "remaining_time": "0:00:02", "throughput": 1421.83, "total_tokens": 270656}
{"current_steps": 1785, "total_steps": 1800, "loss": 0.2163, "lr": 1.2033302976222071e-08, "epoch": 9.916666666666666, "percentage": 99.17, "elapsed_time": "0:03:10", "remaining_time": "0:00:01", "throughput": 1422.63, "total_tokens": 271408}
{"current_steps": 1790, "total_steps": 1800, "loss": 0.2302, "lr": 5.687856499297928e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:03:11", "remaining_time": "0:00:01", "throughput": 1423.54, "total_tokens": 272192}
{"current_steps": 1795, "total_steps": 1800, "loss": 0.2309, "lr": 1.692299905944883e-09, "epoch": 9.972222222222221, "percentage": 99.72, "elapsed_time": "0:03:11", "remaining_time": "0:00:00", "throughput": 1424.52, "total_tokens": 272960}
{"current_steps": 1800, "total_steps": 1800, "loss": 0.2223, "lr": 4.700884634611935e-11, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:12", "remaining_time": "0:00:00", "throughput": 1424.77, "total_tokens": 273712}
{"current_steps": 1800, "total_steps": 1800, "eval_loss": 0.23892374336719513, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:12", "remaining_time": "0:00:00", "throughput": 1418.38, "total_tokens": 273712}
{"current_steps": 1800, "total_steps": 1800, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:14", "remaining_time": "0:00:00", "throughput": 1410.26, "total_tokens": 273712}