diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" --- "a/trainer_log.jsonl" +++ "b/trainer_log.jsonl" @@ -1,386 +1,32 @@ -{"current_steps": 1, "total_steps": 385, "loss": 8.1083, "learning_rate": 8.333333333333335e-09, "epoch": 0.012861736334405145, "percentage": 0.26, "elapsed_time": "0:00:11", "remaining_time": "1:15:00", "throughput": "1411.72", "total_tokens": 16544} -{"current_steps": 2, "total_steps": 385, "loss": 8.1052, "learning_rate": 1.666666666666667e-08, "epoch": 0.02572347266881029, "percentage": 0.52, "elapsed_time": "0:00:22", "remaining_time": "1:12:54", "throughput": "1455.41", "total_tokens": 33248} -{"current_steps": 3, "total_steps": 385, "loss": 8.1366, "learning_rate": 2.5000000000000002e-08, "epoch": 0.03858520900321544, "percentage": 0.78, "elapsed_time": "0:00:33", "remaining_time": "1:11:59", "throughput": "1466.88", "total_tokens": 49760} -{"current_steps": 4, "total_steps": 385, "loss": 8.0413, "learning_rate": 3.333333333333334e-08, "epoch": 0.05144694533762058, "percentage": 1.04, "elapsed_time": "0:00:45", "remaining_time": "1:11:27", "throughput": "1462.41", "total_tokens": 65824} -{"current_steps": 5, "total_steps": 385, "loss": 8.1055, "learning_rate": 4.166666666666667e-08, "epoch": 0.06430868167202572, "percentage": 1.3, "elapsed_time": "0:00:56", "remaining_time": "1:11:04", "throughput": "1471.37", "total_tokens": 82560} -{"current_steps": 6, "total_steps": 385, "loss": 7.9666, "learning_rate": 5.0000000000000004e-08, "epoch": 0.07717041800643087, "percentage": 1.56, "elapsed_time": "0:01:07", "remaining_time": "1:10:47", "throughput": "1484.19", "total_tokens": 99808} -{"current_steps": 7, "total_steps": 385, "loss": 8.0182, "learning_rate": 5.833333333333334e-08, "epoch": 0.09003215434083602, "percentage": 1.82, "elapsed_time": "0:01:18", "remaining_time": "1:10:31", "throughput": "1477.83", "total_tokens": 115808} -{"current_steps": 8, "total_steps": 385, "loss": 8.0363, "learning_rate": 6.666666666666668e-08, "epoch": 0.10289389067524116, "percentage": 2.08, "elapsed_time": "0:01:29", "remaining_time": "1:10:17", "throughput": "1468.21", "total_tokens": 131392} -{"current_steps": 9, "total_steps": 385, "loss": 8.0918, "learning_rate": 7.500000000000001e-08, "epoch": 0.1157556270096463, "percentage": 2.34, "elapsed_time": "0:01:40", "remaining_time": "1:10:04", "throughput": "1469.05", "total_tokens": 147840} -{"current_steps": 10, "total_steps": 385, "loss": 8.0197, "learning_rate": 8.333333333333334e-08, "epoch": 0.12861736334405144, "percentage": 2.6, "elapsed_time": "0:01:51", "remaining_time": "1:09:51", "throughput": "1467.95", "total_tokens": 164064} -{"current_steps": 11, "total_steps": 385, "loss": 7.9714, "learning_rate": 9.166666666666668e-08, "epoch": 0.1414790996784566, "percentage": 2.86, "elapsed_time": "0:02:02", "remaining_time": "1:09:38", "throughput": "1470.48", "total_tokens": 180704} -{"current_steps": 12, "total_steps": 385, "loss": 8.0131, "learning_rate": 1.0000000000000001e-07, "epoch": 0.15434083601286175, "percentage": 3.12, "elapsed_time": "0:02:13", "remaining_time": "1:09:23", "throughput": "1463.77", "total_tokens": 196064} -{"current_steps": 13, "total_steps": 385, "loss": 7.9796, "learning_rate": 1.0833333333333335e-07, "epoch": 0.16720257234726688, "percentage": 3.38, "elapsed_time": "0:02:25", "remaining_time": "1:09:09", "throughput": "1457.86", "total_tokens": 211424} -{"current_steps": 14, "total_steps": 385, "loss": 7.9999, "learning_rate": 1.1666666666666668e-07, "epoch": 0.18006430868167203, "percentage": 3.64, "elapsed_time": "0:02:36", "remaining_time": "1:08:57", "throughput": "1460.84", "total_tokens": 228096} -{"current_steps": 15, "total_steps": 385, "loss": 8.0168, "learning_rate": 1.2500000000000002e-07, "epoch": 0.19292604501607716, "percentage": 3.9, "elapsed_time": "0:02:47", "remaining_time": "1:08:46", "throughput": "1461.12", "total_tokens": 244416} -{"current_steps": 16, "total_steps": 385, "loss": 7.8423, "learning_rate": 1.3333333333333336e-07, "epoch": 0.2057877813504823, "percentage": 4.16, "elapsed_time": "0:02:58", "remaining_time": "1:08:34", "throughput": "1463.26", "total_tokens": 261056} -{"current_steps": 17, "total_steps": 385, "loss": 7.9208, "learning_rate": 1.4166666666666668e-07, "epoch": 0.21864951768488747, "percentage": 4.42, "elapsed_time": "0:03:09", "remaining_time": "1:08:23", "throughput": "1461.36", "total_tokens": 276992} -{"current_steps": 18, "total_steps": 385, "loss": 7.6898, "learning_rate": 1.5000000000000002e-07, "epoch": 0.2315112540192926, "percentage": 4.68, "elapsed_time": "0:03:20", "remaining_time": "1:08:11", "throughput": "1462.71", "total_tokens": 293536} -{"current_steps": 19, "total_steps": 385, "loss": 7.9285, "learning_rate": 1.5833333333333336e-07, "epoch": 0.24437299035369775, "percentage": 4.94, "elapsed_time": "0:03:31", "remaining_time": "1:07:59", "throughput": "1459.08", "total_tokens": 309024} -{"current_steps": 20, "total_steps": 385, "loss": 7.8924, "learning_rate": 1.6666666666666668e-07, "epoch": 0.2572347266881029, "percentage": 5.19, "elapsed_time": "0:03:42", "remaining_time": "1:07:47", "throughput": "1458.15", "total_tokens": 325024} -{"current_steps": 21, "total_steps": 385, "loss": 7.6173, "learning_rate": 1.7500000000000002e-07, "epoch": 0.27009646302250806, "percentage": 5.45, "elapsed_time": "0:03:54", "remaining_time": "1:07:36", "throughput": "1460.88", "total_tokens": 341856} -{"current_steps": 22, "total_steps": 385, "loss": 7.7661, "learning_rate": 1.8333333333333336e-07, "epoch": 0.2829581993569132, "percentage": 5.71, "elapsed_time": "0:04:05", "remaining_time": "1:07:24", "throughput": "1463.97", "total_tokens": 358848} -{"current_steps": 23, "total_steps": 385, "loss": 7.2936, "learning_rate": 1.9166666666666668e-07, "epoch": 0.2958199356913183, "percentage": 5.97, "elapsed_time": "0:04:16", "remaining_time": "1:07:12", "throughput": "1464.98", "total_tokens": 375360} -{"current_steps": 24, "total_steps": 385, "loss": 7.3044, "learning_rate": 2.0000000000000002e-07, "epoch": 0.3086816720257235, "percentage": 6.23, "elapsed_time": "0:04:27", "remaining_time": "1:07:01", "throughput": "1468.54", "total_tokens": 392608} -{"current_steps": 25, "total_steps": 385, "loss": 7.35, "learning_rate": 2.0833333333333333e-07, "epoch": 0.3215434083601286, "percentage": 6.49, "elapsed_time": "0:04:38", "remaining_time": "1:06:49", "throughput": "1468.11", "total_tokens": 408800} -{"current_steps": 26, "total_steps": 385, "loss": 7.1213, "learning_rate": 2.166666666666667e-07, "epoch": 0.33440514469453375, "percentage": 6.75, "elapsed_time": "0:04:49", "remaining_time": "1:06:38", "throughput": "1469.84", "total_tokens": 425632} -{"current_steps": 27, "total_steps": 385, "loss": 7.1363, "learning_rate": 2.2500000000000002e-07, "epoch": 0.34726688102893893, "percentage": 7.01, "elapsed_time": "0:05:00", "remaining_time": "1:06:26", "throughput": "1469.80", "total_tokens": 441952} -{"current_steps": 28, "total_steps": 385, "loss": 6.9016, "learning_rate": 2.3333333333333336e-07, "epoch": 0.36012861736334406, "percentage": 7.27, "elapsed_time": "0:05:11", "remaining_time": "1:06:16", "throughput": "1468.87", "total_tokens": 458080} -{"current_steps": 29, "total_steps": 385, "loss": 6.9764, "learning_rate": 2.416666666666667e-07, "epoch": 0.3729903536977492, "percentage": 7.53, "elapsed_time": "0:05:22", "remaining_time": "1:06:04", "throughput": "1467.16", "total_tokens": 473824} -{"current_steps": 30, "total_steps": 385, "loss": 6.9005, "learning_rate": 2.5000000000000004e-07, "epoch": 0.3858520900321543, "percentage": 7.79, "elapsed_time": "0:05:34", "remaining_time": "1:05:53", "throughput": "1467.82", "total_tokens": 490336} -{"current_steps": 31, "total_steps": 385, "loss": 6.9852, "learning_rate": 2.5833333333333333e-07, "epoch": 0.3987138263665595, "percentage": 8.05, "elapsed_time": "0:05:45", "remaining_time": "1:05:41", "throughput": "1468.73", "total_tokens": 506976} -{"current_steps": 32, "total_steps": 385, "loss": 5.834, "learning_rate": 2.666666666666667e-07, "epoch": 0.4115755627009646, "percentage": 8.31, "elapsed_time": "0:05:56", "remaining_time": "1:05:30", "throughput": "1469.26", "total_tokens": 523520} -{"current_steps": 33, "total_steps": 385, "loss": 5.5452, "learning_rate": 2.75e-07, "epoch": 0.42443729903536975, "percentage": 8.57, "elapsed_time": "0:06:07", "remaining_time": "1:05:19", "throughput": "1471.43", "total_tokens": 540672} -{"current_steps": 34, "total_steps": 385, "loss": 5.5189, "learning_rate": 2.8333333333333336e-07, "epoch": 0.43729903536977494, "percentage": 8.83, "elapsed_time": "0:06:18", "remaining_time": "1:05:08", "throughput": "1473.12", "total_tokens": 557696} -{"current_steps": 35, "total_steps": 385, "loss": 5.4654, "learning_rate": 2.916666666666667e-07, "epoch": 0.45016077170418006, "percentage": 9.09, "elapsed_time": "0:06:29", "remaining_time": "1:04:57", "throughput": "1473.94", "total_tokens": 574400} -{"current_steps": 36, "total_steps": 385, "loss": 5.3117, "learning_rate": 3.0000000000000004e-07, "epoch": 0.4630225080385852, "percentage": 9.35, "elapsed_time": "0:06:40", "remaining_time": "1:04:45", "throughput": "1472.23", "total_tokens": 590112} -{"current_steps": 37, "total_steps": 385, "loss": 5.2744, "learning_rate": 3.083333333333334e-07, "epoch": 0.4758842443729904, "percentage": 9.61, "elapsed_time": "0:06:51", "remaining_time": "1:04:34", "throughput": "1470.87", "total_tokens": 605920} -{"current_steps": 38, "total_steps": 385, "loss": 5.2821, "learning_rate": 3.166666666666667e-07, "epoch": 0.4887459807073955, "percentage": 9.87, "elapsed_time": "0:07:03", "remaining_time": "1:04:23", "throughput": "1470.77", "total_tokens": 622208} -{"current_steps": 39, "total_steps": 385, "loss": 5.0967, "learning_rate": 3.25e-07, "epoch": 0.5016077170418006, "percentage": 10.13, "elapsed_time": "0:07:14", "remaining_time": "1:04:11", "throughput": "1470.64", "total_tokens": 638464} -{"current_steps": 40, "total_steps": 385, "loss": 5.2167, "learning_rate": 3.3333333333333335e-07, "epoch": 0.5144694533762058, "percentage": 10.39, "elapsed_time": "0:07:25", "remaining_time": "1:04:00", "throughput": "1470.41", "total_tokens": 654656} -{"current_steps": 41, "total_steps": 385, "loss": 5.1517, "learning_rate": 3.416666666666667e-07, "epoch": 0.5273311897106109, "percentage": 10.65, "elapsed_time": "0:07:36", "remaining_time": "1:03:49", "throughput": "1471.24", "total_tokens": 671424} -{"current_steps": 42, "total_steps": 385, "loss": 4.6959, "learning_rate": 3.5000000000000004e-07, "epoch": 0.5401929260450161, "percentage": 10.91, "elapsed_time": "0:07:47", "remaining_time": "1:03:37", "throughput": "1471.59", "total_tokens": 687968} -{"current_steps": 43, "total_steps": 385, "loss": 4.1458, "learning_rate": 3.583333333333334e-07, "epoch": 0.5530546623794212, "percentage": 11.17, "elapsed_time": "0:07:58", "remaining_time": "1:03:26", "throughput": "1471.34", "total_tokens": 704224} -{"current_steps": 44, "total_steps": 385, "loss": 3.6692, "learning_rate": 3.666666666666667e-07, "epoch": 0.5659163987138264, "percentage": 11.43, "elapsed_time": "0:08:09", "remaining_time": "1:03:15", "throughput": "1471.55", "total_tokens": 720704} -{"current_steps": 45, "total_steps": 385, "loss": 3.3322, "learning_rate": 3.75e-07, "epoch": 0.5787781350482315, "percentage": 11.69, "elapsed_time": "0:08:20", "remaining_time": "1:03:04", "throughput": "1472.18", "total_tokens": 737408} -{"current_steps": 46, "total_steps": 385, "loss": 3.2857, "learning_rate": 3.8333333333333335e-07, "epoch": 0.5916398713826366, "percentage": 11.95, "elapsed_time": "0:08:32", "remaining_time": "1:02:53", "throughput": "1472.04", "total_tokens": 753728} -{"current_steps": 47, "total_steps": 385, "loss": 3.0806, "learning_rate": 3.9166666666666675e-07, "epoch": 0.6045016077170418, "percentage": 12.21, "elapsed_time": "0:08:43", "remaining_time": "1:02:42", "throughput": "1472.06", "total_tokens": 770080} -{"current_steps": 48, "total_steps": 385, "loss": 2.8239, "learning_rate": 4.0000000000000003e-07, "epoch": 0.617363344051447, "percentage": 12.47, "elapsed_time": "0:08:54", "remaining_time": "1:02:30", "throughput": "1472.90", "total_tokens": 786912} -{"current_steps": 49, "total_steps": 385, "loss": 2.8695, "learning_rate": 4.083333333333334e-07, "epoch": 0.6302250803858521, "percentage": 12.73, "elapsed_time": "0:09:05", "remaining_time": "1:02:19", "throughput": "1474.53", "total_tokens": 804192} -{"current_steps": 50, "total_steps": 385, "loss": 2.6218, "learning_rate": 4.1666666666666667e-07, "epoch": 0.6430868167202572, "percentage": 12.99, "elapsed_time": "0:09:16", "remaining_time": "1:02:08", "throughput": "1475.14", "total_tokens": 820928} -{"current_steps": 51, "total_steps": 385, "loss": 2.3993, "learning_rate": 4.2500000000000006e-07, "epoch": 0.6559485530546624, "percentage": 13.25, "elapsed_time": "0:09:27", "remaining_time": "1:01:57", "throughput": "1474.86", "total_tokens": 837152} -{"current_steps": 52, "total_steps": 385, "loss": 2.2828, "learning_rate": 4.333333333333334e-07, "epoch": 0.6688102893890675, "percentage": 13.51, "elapsed_time": "0:09:38", "remaining_time": "1:01:46", "throughput": "1474.81", "total_tokens": 853568} -{"current_steps": 53, "total_steps": 385, "loss": 2.2063, "learning_rate": 4.416666666666667e-07, "epoch": 0.6816720257234726, "percentage": 13.77, "elapsed_time": "0:09:49", "remaining_time": "1:01:35", "throughput": "1475.84", "total_tokens": 870592} -{"current_steps": 54, "total_steps": 385, "loss": 1.8878, "learning_rate": 4.5000000000000003e-07, "epoch": 0.6945337620578779, "percentage": 14.03, "elapsed_time": "0:10:01", "remaining_time": "1:01:24", "throughput": "1474.30", "total_tokens": 886080} -{"current_steps": 55, "total_steps": 385, "loss": 1.5971, "learning_rate": 4.583333333333333e-07, "epoch": 0.707395498392283, "percentage": 14.29, "elapsed_time": "0:10:12", "remaining_time": "1:01:12", "throughput": "1475.65", "total_tokens": 903296} -{"current_steps": 56, "total_steps": 385, "loss": 0.9604, "learning_rate": 4.666666666666667e-07, "epoch": 0.7202572347266881, "percentage": 14.55, "elapsed_time": "0:10:23", "remaining_time": "1:01:01", "throughput": "1475.05", "total_tokens": 919296} -{"current_steps": 57, "total_steps": 385, "loss": 0.6287, "learning_rate": 4.7500000000000006e-07, "epoch": 0.7331189710610932, "percentage": 14.81, "elapsed_time": "0:10:34", "remaining_time": "1:00:50", "throughput": "1475.70", "total_tokens": 936096} -{"current_steps": 58, "total_steps": 385, "loss": 0.4844, "learning_rate": 4.833333333333334e-07, "epoch": 0.7459807073954984, "percentage": 15.06, "elapsed_time": "0:10:45", "remaining_time": "1:00:39", "throughput": "1476.45", "total_tokens": 953024} -{"current_steps": 59, "total_steps": 385, "loss": 0.3891, "learning_rate": 4.916666666666667e-07, "epoch": 0.7588424437299035, "percentage": 15.32, "elapsed_time": "0:10:56", "remaining_time": "1:00:27", "throughput": "1475.83", "total_tokens": 969024} -{"current_steps": 60, "total_steps": 385, "loss": 0.357, "learning_rate": 5.000000000000001e-07, "epoch": 0.7717041800643086, "percentage": 15.58, "elapsed_time": "0:11:07", "remaining_time": "1:00:16", "throughput": "1476.05", "total_tokens": 985600} -{"current_steps": 61, "total_steps": 385, "loss": 0.2854, "learning_rate": 5.083333333333334e-07, "epoch": 0.7845659163987139, "percentage": 15.84, "elapsed_time": "0:11:18", "remaining_time": "1:00:05", "throughput": "1476.53", "total_tokens": 1002336} -{"current_steps": 62, "total_steps": 385, "loss": 0.2403, "learning_rate": 5.166666666666667e-07, "epoch": 0.797427652733119, "percentage": 16.1, "elapsed_time": "0:11:29", "remaining_time": "0:59:54", "throughput": "1476.18", "total_tokens": 1018496} -{"current_steps": 63, "total_steps": 385, "loss": 0.2522, "learning_rate": 5.250000000000001e-07, "epoch": 0.8102893890675241, "percentage": 16.36, "elapsed_time": "0:11:41", "remaining_time": "0:59:43", "throughput": "1477.05", "total_tokens": 1035552} -{"current_steps": 64, "total_steps": 385, "loss": 0.2339, "learning_rate": 5.333333333333335e-07, "epoch": 0.8231511254019293, "percentage": 16.62, "elapsed_time": "0:11:52", "remaining_time": "0:59:32", "throughput": "1476.51", "total_tokens": 1051584} -{"current_steps": 65, "total_steps": 385, "loss": 0.2214, "learning_rate": 5.416666666666667e-07, "epoch": 0.8360128617363344, "percentage": 16.88, "elapsed_time": "0:12:03", "remaining_time": "0:59:20", "throughput": "1477.43", "total_tokens": 1068640} -{"current_steps": 66, "total_steps": 385, "loss": 0.1912, "learning_rate": 5.5e-07, "epoch": 0.8488745980707395, "percentage": 17.14, "elapsed_time": "0:12:14", "remaining_time": "0:59:09", "throughput": "1478.13", "total_tokens": 1085568} -{"current_steps": 67, "total_steps": 385, "loss": 0.2157, "learning_rate": 5.583333333333333e-07, "epoch": 0.8617363344051447, "percentage": 17.4, "elapsed_time": "0:12:25", "remaining_time": "0:58:58", "throughput": "1479.16", "total_tokens": 1102784} -{"current_steps": 68, "total_steps": 385, "loss": 0.2045, "learning_rate": 5.666666666666667e-07, "epoch": 0.8745980707395499, "percentage": 17.66, "elapsed_time": "0:12:36", "remaining_time": "0:58:47", "throughput": "1478.13", "total_tokens": 1118432} -{"current_steps": 69, "total_steps": 385, "loss": 0.1964, "learning_rate": 5.750000000000001e-07, "epoch": 0.887459807073955, "percentage": 17.92, "elapsed_time": "0:12:47", "remaining_time": "0:58:36", "throughput": "1478.54", "total_tokens": 1135232} -{"current_steps": 70, "total_steps": 385, "loss": 0.1901, "learning_rate": 5.833333333333334e-07, "epoch": 0.9003215434083601, "percentage": 18.18, "elapsed_time": "0:12:58", "remaining_time": "0:58:25", "throughput": "1477.07", "total_tokens": 1150496} -{"current_steps": 71, "total_steps": 385, "loss": 0.1891, "learning_rate": 5.916666666666667e-07, "epoch": 0.9131832797427653, "percentage": 18.44, "elapsed_time": "0:13:10", "remaining_time": "0:58:13", "throughput": "1477.00", "total_tokens": 1166848} -{"current_steps": 72, "total_steps": 385, "loss": 0.1841, "learning_rate": 6.000000000000001e-07, "epoch": 0.9260450160771704, "percentage": 18.7, "elapsed_time": "0:13:21", "remaining_time": "0:58:02", "throughput": "1477.26", "total_tokens": 1183552} -{"current_steps": 73, "total_steps": 385, "loss": 0.1803, "learning_rate": 6.083333333333334e-07, "epoch": 0.9389067524115756, "percentage": 18.96, "elapsed_time": "0:13:32", "remaining_time": "0:57:51", "throughput": "1477.28", "total_tokens": 1199968} -{"current_steps": 74, "total_steps": 385, "loss": 0.1657, "learning_rate": 6.166666666666668e-07, "epoch": 0.9517684887459807, "percentage": 19.22, "elapsed_time": "0:13:43", "remaining_time": "0:57:40", "throughput": "1477.17", "total_tokens": 1216256} -{"current_steps": 75, "total_steps": 385, "loss": 0.2157, "learning_rate": 6.25e-07, "epoch": 0.9646302250803859, "percentage": 19.48, "elapsed_time": "0:13:54", "remaining_time": "0:57:29", "throughput": "1477.26", "total_tokens": 1232736} -{"current_steps": 76, "total_steps": 385, "loss": 0.2, "learning_rate": 6.333333333333334e-07, "epoch": 0.977491961414791, "percentage": 19.74, "elapsed_time": "0:14:05", "remaining_time": "0:57:17", "throughput": "1477.40", "total_tokens": 1249248} -{"current_steps": 77, "total_steps": 385, "loss": 0.1519, "learning_rate": 6.416666666666667e-07, "epoch": 0.9903536977491961, "percentage": 20.0, "elapsed_time": "0:14:16", "remaining_time": "0:57:06", "throughput": "1476.86", "total_tokens": 1265152} -{"current_steps": 78, "total_steps": 385, "loss": 0.1765, "learning_rate": 6.5e-07, "epoch": 1.0032154340836013, "percentage": 20.26, "elapsed_time": "0:14:27", "remaining_time": "0:56:55", "throughput": "1477.71", "total_tokens": 1282336} -{"current_steps": 79, "total_steps": 385, "loss": 0.1907, "learning_rate": 6.583333333333333e-07, "epoch": 1.0160771704180065, "percentage": 20.52, "elapsed_time": "0:14:38", "remaining_time": "0:56:44", "throughput": "1478.10", "total_tokens": 1299168} -{"current_steps": 80, "total_steps": 385, "loss": 0.1593, "learning_rate": 6.666666666666667e-07, "epoch": 1.0289389067524115, "percentage": 20.78, "elapsed_time": "0:14:50", "remaining_time": "0:56:33", "throughput": "1477.21", "total_tokens": 1314816} -{"current_steps": 81, "total_steps": 385, "loss": 0.1659, "learning_rate": 6.750000000000001e-07, "epoch": 1.0418006430868167, "percentage": 21.04, "elapsed_time": "0:15:01", "remaining_time": "0:56:22", "throughput": "1477.14", "total_tokens": 1331168} -{"current_steps": 82, "total_steps": 385, "loss": 0.1619, "learning_rate": 6.833333333333334e-07, "epoch": 1.0546623794212218, "percentage": 21.3, "elapsed_time": "0:15:12", "remaining_time": "0:56:10", "throughput": "1477.58", "total_tokens": 1347968} -{"current_steps": 83, "total_steps": 385, "loss": 0.168, "learning_rate": 6.916666666666668e-07, "epoch": 1.067524115755627, "percentage": 21.56, "elapsed_time": "0:15:23", "remaining_time": "0:55:59", "throughput": "1477.08", "total_tokens": 1363872} -{"current_steps": 84, "total_steps": 385, "loss": 0.1627, "learning_rate": 7.000000000000001e-07, "epoch": 1.0803858520900322, "percentage": 21.82, "elapsed_time": "0:15:34", "remaining_time": "0:55:48", "throughput": "1477.67", "total_tokens": 1380896} -{"current_steps": 85, "total_steps": 385, "loss": 0.1421, "learning_rate": 7.083333333333334e-07, "epoch": 1.0932475884244373, "percentage": 22.08, "elapsed_time": "0:15:45", "remaining_time": "0:55:37", "throughput": "1478.13", "total_tokens": 1397792} -{"current_steps": 86, "total_steps": 385, "loss": 0.1517, "learning_rate": 7.166666666666668e-07, "epoch": 1.1061093247588425, "percentage": 22.34, "elapsed_time": "0:15:56", "remaining_time": "0:55:26", "throughput": "1478.20", "total_tokens": 1414272} -{"current_steps": 87, "total_steps": 385, "loss": 0.1519, "learning_rate": 7.25e-07, "epoch": 1.1189710610932475, "percentage": 22.6, "elapsed_time": "0:16:07", "remaining_time": "0:55:15", "throughput": "1477.17", "total_tokens": 1429696} -{"current_steps": 88, "total_steps": 385, "loss": 0.128, "learning_rate": 7.333333333333334e-07, "epoch": 1.1318327974276527, "percentage": 22.86, "elapsed_time": "0:16:19", "remaining_time": "0:55:04", "throughput": "1477.75", "total_tokens": 1446720} -{"current_steps": 89, "total_steps": 385, "loss": 0.1481, "learning_rate": 7.416666666666668e-07, "epoch": 1.144694533762058, "percentage": 23.12, "elapsed_time": "0:16:30", "remaining_time": "0:54:53", "throughput": "1477.59", "total_tokens": 1463008} -{"current_steps": 90, "total_steps": 385, "loss": 0.1636, "learning_rate": 7.5e-07, "epoch": 1.157556270096463, "percentage": 23.38, "elapsed_time": "0:16:41", "remaining_time": "0:54:41", "throughput": "1478.21", "total_tokens": 1480096} -{"current_steps": 91, "total_steps": 385, "loss": 0.1443, "learning_rate": 7.583333333333334e-07, "epoch": 1.1704180064308682, "percentage": 23.64, "elapsed_time": "0:16:52", "remaining_time": "0:54:30", "throughput": "1478.70", "total_tokens": 1497024} -{"current_steps": 92, "total_steps": 385, "loss": 0.1592, "learning_rate": 7.666666666666667e-07, "epoch": 1.1832797427652733, "percentage": 23.9, "elapsed_time": "0:17:03", "remaining_time": "0:54:19", "throughput": "1479.03", "total_tokens": 1513792} -{"current_steps": 93, "total_steps": 385, "loss": 0.1744, "learning_rate": 7.750000000000001e-07, "epoch": 1.1961414790996785, "percentage": 24.16, "elapsed_time": "0:17:14", "remaining_time": "0:54:08", "throughput": "1478.61", "total_tokens": 1529696} -{"current_steps": 94, "total_steps": 385, "loss": 0.1615, "learning_rate": 7.833333333333335e-07, "epoch": 1.2090032154340835, "percentage": 24.42, "elapsed_time": "0:17:25", "remaining_time": "0:53:57", "throughput": "1478.86", "total_tokens": 1546400} -{"current_steps": 95, "total_steps": 385, "loss": 0.1466, "learning_rate": 7.916666666666667e-07, "epoch": 1.2218649517684887, "percentage": 24.68, "elapsed_time": "0:17:36", "remaining_time": "0:53:46", "throughput": "1480.34", "total_tokens": 1564448} -{"current_steps": 96, "total_steps": 385, "loss": 0.1333, "learning_rate": 8.000000000000001e-07, "epoch": 1.234726688102894, "percentage": 24.94, "elapsed_time": "0:17:47", "remaining_time": "0:53:34", "throughput": "1480.18", "total_tokens": 1580736} -{"current_steps": 97, "total_steps": 385, "loss": 0.1475, "learning_rate": 8.083333333333334e-07, "epoch": 1.247588424437299, "percentage": 25.19, "elapsed_time": "0:17:59", "remaining_time": "0:53:23", "throughput": "1479.91", "total_tokens": 1596928} -{"current_steps": 98, "total_steps": 385, "loss": 0.142, "learning_rate": 8.166666666666668e-07, "epoch": 1.2604501607717042, "percentage": 25.45, "elapsed_time": "0:18:10", "remaining_time": "0:53:12", "throughput": "1480.14", "total_tokens": 1613728} -{"current_steps": 99, "total_steps": 385, "loss": 0.148, "learning_rate": 8.250000000000001e-07, "epoch": 1.2733118971061093, "percentage": 25.71, "elapsed_time": "0:18:21", "remaining_time": "0:53:01", "throughput": "1480.08", "total_tokens": 1630112} -{"current_steps": 100, "total_steps": 385, "loss": 0.1539, "learning_rate": 8.333333333333333e-07, "epoch": 1.2861736334405145, "percentage": 25.97, "elapsed_time": "0:18:32", "remaining_time": "0:52:50", "throughput": "1478.98", "total_tokens": 1645248} -{"current_steps": 101, "total_steps": 385, "loss": 0.1496, "learning_rate": 8.416666666666667e-07, "epoch": 1.2990353697749195, "percentage": 26.23, "elapsed_time": "0:18:43", "remaining_time": "0:52:39", "throughput": "1479.63", "total_tokens": 1662400} -{"current_steps": 102, "total_steps": 385, "loss": 0.1563, "learning_rate": 8.500000000000001e-07, "epoch": 1.3118971061093248, "percentage": 26.49, "elapsed_time": "0:18:54", "remaining_time": "0:52:28", "throughput": "1479.38", "total_tokens": 1678528} -{"current_steps": 103, "total_steps": 385, "loss": 0.1295, "learning_rate": 8.583333333333334e-07, "epoch": 1.32475884244373, "percentage": 26.75, "elapsed_time": "0:19:05", "remaining_time": "0:52:16", "throughput": "1478.95", "total_tokens": 1694432} -{"current_steps": 104, "total_steps": 385, "loss": 0.1353, "learning_rate": 8.666666666666668e-07, "epoch": 1.337620578778135, "percentage": 27.01, "elapsed_time": "0:19:16", "remaining_time": "0:52:05", "throughput": "1478.71", "total_tokens": 1710624} -{"current_steps": 105, "total_steps": 385, "loss": 0.1376, "learning_rate": 8.75e-07, "epoch": 1.3504823151125402, "percentage": 27.27, "elapsed_time": "0:19:27", "remaining_time": "0:51:54", "throughput": "1478.25", "total_tokens": 1726560} -{"current_steps": 106, "total_steps": 385, "loss": 0.1313, "learning_rate": 8.833333333333334e-07, "epoch": 1.3633440514469453, "percentage": 27.53, "elapsed_time": "0:19:39", "remaining_time": "0:51:43", "throughput": "1478.13", "total_tokens": 1742912} -{"current_steps": 107, "total_steps": 385, "loss": 0.1367, "learning_rate": 8.916666666666668e-07, "epoch": 1.3762057877813505, "percentage": 27.79, "elapsed_time": "0:19:50", "remaining_time": "0:51:32", "throughput": "1477.58", "total_tokens": 1758688} -{"current_steps": 108, "total_steps": 385, "loss": 0.135, "learning_rate": 9.000000000000001e-07, "epoch": 1.3890675241157555, "percentage": 28.05, "elapsed_time": "0:20:01", "remaining_time": "0:51:21", "throughput": "1477.67", "total_tokens": 1775264} -{"current_steps": 109, "total_steps": 385, "loss": 0.1212, "learning_rate": 9.083333333333335e-07, "epoch": 1.4019292604501608, "percentage": 28.31, "elapsed_time": "0:20:12", "remaining_time": "0:51:10", "throughput": "1477.90", "total_tokens": 1791904} -{"current_steps": 110, "total_steps": 385, "loss": 0.1355, "learning_rate": 9.166666666666666e-07, "epoch": 1.414790996784566, "percentage": 28.57, "elapsed_time": "0:20:23", "remaining_time": "0:50:58", "throughput": "1478.26", "total_tokens": 1808736} -{"current_steps": 111, "total_steps": 385, "loss": 0.1439, "learning_rate": 9.25e-07, "epoch": 1.427652733118971, "percentage": 28.83, "elapsed_time": "0:20:34", "remaining_time": "0:50:47", "throughput": "1478.53", "total_tokens": 1825504} -{"current_steps": 112, "total_steps": 385, "loss": 0.1323, "learning_rate": 9.333333333333334e-07, "epoch": 1.4405144694533762, "percentage": 29.09, "elapsed_time": "0:20:45", "remaining_time": "0:50:36", "throughput": "1478.60", "total_tokens": 1842080} -{"current_steps": 113, "total_steps": 385, "loss": 0.1376, "learning_rate": 9.416666666666667e-07, "epoch": 1.4533762057877815, "percentage": 29.35, "elapsed_time": "0:20:56", "remaining_time": "0:50:25", "throughput": "1478.52", "total_tokens": 1858432} -{"current_steps": 114, "total_steps": 385, "loss": 0.1191, "learning_rate": 9.500000000000001e-07, "epoch": 1.4662379421221865, "percentage": 29.61, "elapsed_time": "0:21:08", "remaining_time": "0:50:14", "throughput": "1478.08", "total_tokens": 1874304} -{"current_steps": 115, "total_steps": 385, "loss": 0.1045, "learning_rate": 9.583333333333334e-07, "epoch": 1.4790996784565915, "percentage": 29.87, "elapsed_time": "0:21:19", "remaining_time": "0:50:03", "throughput": "1477.61", "total_tokens": 1890144} -{"current_steps": 116, "total_steps": 385, "loss": 0.1467, "learning_rate": 9.666666666666668e-07, "epoch": 1.4919614147909968, "percentage": 30.13, "elapsed_time": "0:21:30", "remaining_time": "0:49:52", "throughput": "1476.92", "total_tokens": 1905664} -{"current_steps": 117, "total_steps": 385, "loss": 0.1142, "learning_rate": 9.750000000000002e-07, "epoch": 1.504823151125402, "percentage": 30.39, "elapsed_time": "0:21:41", "remaining_time": "0:49:41", "throughput": "1477.03", "total_tokens": 1922240} -{"current_steps": 118, "total_steps": 385, "loss": 0.1107, "learning_rate": 9.833333333333334e-07, "epoch": 1.517684887459807, "percentage": 30.65, "elapsed_time": "0:21:52", "remaining_time": "0:49:29", "throughput": "1476.73", "total_tokens": 1938240} -{"current_steps": 119, "total_steps": 385, "loss": 0.146, "learning_rate": 9.916666666666668e-07, "epoch": 1.5305466237942122, "percentage": 30.91, "elapsed_time": "0:22:03", "remaining_time": "0:49:18", "throughput": "1477.00", "total_tokens": 1955008} -{"current_steps": 120, "total_steps": 385, "loss": 0.1533, "learning_rate": 1.0000000000000002e-06, "epoch": 1.5434083601286175, "percentage": 31.17, "elapsed_time": "0:22:14", "remaining_time": "0:49:07", "throughput": "1477.02", "total_tokens": 1971456} -{"current_steps": 121, "total_steps": 385, "loss": 0.1315, "learning_rate": 1.0083333333333333e-06, "epoch": 1.5562700964630225, "percentage": 31.43, "elapsed_time": "0:22:25", "remaining_time": "0:48:56", "throughput": "1476.81", "total_tokens": 1987552} -{"current_steps": 122, "total_steps": 385, "loss": 0.1197, "learning_rate": 1.0166666666666667e-06, "epoch": 1.5691318327974275, "percentage": 31.69, "elapsed_time": "0:22:37", "remaining_time": "0:48:45", "throughput": "1476.92", "total_tokens": 2004192} -{"current_steps": 123, "total_steps": 385, "loss": 0.1228, "learning_rate": 1.025e-06, "epoch": 1.5819935691318328, "percentage": 31.95, "elapsed_time": "0:22:48", "remaining_time": "0:48:34", "throughput": "1477.06", "total_tokens": 2020832} -{"current_steps": 124, "total_steps": 385, "loss": 0.1273, "learning_rate": 1.0333333333333333e-06, "epoch": 1.594855305466238, "percentage": 32.21, "elapsed_time": "0:22:59", "remaining_time": "0:48:23", "throughput": "1477.06", "total_tokens": 2037312} -{"current_steps": 125, "total_steps": 385, "loss": 0.141, "learning_rate": 1.0416666666666667e-06, "epoch": 1.607717041800643, "percentage": 32.47, "elapsed_time": "0:23:10", "remaining_time": "0:48:12", "throughput": "1477.45", "total_tokens": 2054304} -{"current_steps": 126, "total_steps": 385, "loss": 0.1315, "learning_rate": 1.0500000000000001e-06, "epoch": 1.6205787781350482, "percentage": 32.73, "elapsed_time": "0:23:21", "remaining_time": "0:48:00", "throughput": "1477.73", "total_tokens": 2071136} -{"current_steps": 127, "total_steps": 385, "loss": 0.1136, "learning_rate": 1.0583333333333335e-06, "epoch": 1.6334405144694535, "percentage": 32.99, "elapsed_time": "0:23:32", "remaining_time": "0:47:49", "throughput": "1478.09", "total_tokens": 2088064} -{"current_steps": 128, "total_steps": 385, "loss": 0.1013, "learning_rate": 1.066666666666667e-06, "epoch": 1.6463022508038585, "percentage": 33.25, "elapsed_time": "0:23:43", "remaining_time": "0:47:38", "throughput": "1478.54", "total_tokens": 2105120} -{"current_steps": 129, "total_steps": 385, "loss": 0.1056, "learning_rate": 1.075e-06, "epoch": 1.6591639871382635, "percentage": 33.51, "elapsed_time": "0:23:54", "remaining_time": "0:47:27", "throughput": "1478.14", "total_tokens": 2120992} -{"current_steps": 130, "total_steps": 385, "loss": 0.1071, "learning_rate": 1.0833333333333335e-06, "epoch": 1.6720257234726688, "percentage": 33.77, "elapsed_time": "0:24:06", "remaining_time": "0:47:16", "throughput": "1478.54", "total_tokens": 2137984} -{"current_steps": 131, "total_steps": 385, "loss": 0.1357, "learning_rate": 1.0916666666666667e-06, "epoch": 1.684887459807074, "percentage": 34.03, "elapsed_time": "0:24:17", "remaining_time": "0:47:05", "throughput": "1478.41", "total_tokens": 2154240} -{"current_steps": 132, "total_steps": 385, "loss": 0.1181, "learning_rate": 1.1e-06, "epoch": 1.697749196141479, "percentage": 34.29, "elapsed_time": "0:24:28", "remaining_time": "0:46:54", "throughput": "1478.26", "total_tokens": 2170464} -{"current_steps": 133, "total_steps": 385, "loss": 0.0826, "learning_rate": 1.1083333333333335e-06, "epoch": 1.7106109324758842, "percentage": 34.55, "elapsed_time": "0:24:39", "remaining_time": "0:46:43", "throughput": "1478.30", "total_tokens": 2187008} -{"current_steps": 134, "total_steps": 385, "loss": 0.1221, "learning_rate": 1.1166666666666666e-06, "epoch": 1.7234726688102895, "percentage": 34.81, "elapsed_time": "0:24:50", "remaining_time": "0:46:31", "throughput": "1477.92", "total_tokens": 2202880} -{"current_steps": 135, "total_steps": 385, "loss": 0.1021, "learning_rate": 1.125e-06, "epoch": 1.7363344051446945, "percentage": 35.06, "elapsed_time": "0:25:01", "remaining_time": "0:46:20", "throughput": "1478.20", "total_tokens": 2219744} -{"current_steps": 136, "total_steps": 385, "loss": 0.098, "learning_rate": 1.1333333333333334e-06, "epoch": 1.7491961414790995, "percentage": 35.32, "elapsed_time": "0:25:12", "remaining_time": "0:46:09", "throughput": "1478.17", "total_tokens": 2236064} -{"current_steps": 137, "total_steps": 385, "loss": 0.1085, "learning_rate": 1.1416666666666668e-06, "epoch": 1.762057877813505, "percentage": 35.58, "elapsed_time": "0:25:23", "remaining_time": "0:45:58", "throughput": "1478.40", "total_tokens": 2252832} -{"current_steps": 138, "total_steps": 385, "loss": 0.1038, "learning_rate": 1.1500000000000002e-06, "epoch": 1.77491961414791, "percentage": 35.84, "elapsed_time": "0:25:34", "remaining_time": "0:45:47", "throughput": "1478.07", "total_tokens": 2268704} -{"current_steps": 139, "total_steps": 385, "loss": 0.1081, "learning_rate": 1.1583333333333334e-06, "epoch": 1.787781350482315, "percentage": 36.1, "elapsed_time": "0:25:46", "remaining_time": "0:45:36", "throughput": "1478.19", "total_tokens": 2285280} -{"current_steps": 140, "total_steps": 385, "loss": 0.1287, "learning_rate": 1.1666666666666668e-06, "epoch": 1.8006430868167203, "percentage": 36.36, "elapsed_time": "0:25:57", "remaining_time": "0:45:24", "throughput": "1478.10", "total_tokens": 2301600} -{"current_steps": 141, "total_steps": 385, "loss": 0.1068, "learning_rate": 1.175e-06, "epoch": 1.8135048231511255, "percentage": 36.62, "elapsed_time": "0:26:08", "remaining_time": "0:45:13", "throughput": "1478.11", "total_tokens": 2318048} -{"current_steps": 142, "total_steps": 385, "loss": 0.1202, "learning_rate": 1.1833333333333334e-06, "epoch": 1.8263665594855305, "percentage": 36.88, "elapsed_time": "0:26:19", "remaining_time": "0:45:02", "throughput": "1477.67", "total_tokens": 2333728} -{"current_steps": 143, "total_steps": 385, "loss": 0.119, "learning_rate": 1.1916666666666668e-06, "epoch": 1.8392282958199357, "percentage": 37.14, "elapsed_time": "0:26:30", "remaining_time": "0:44:51", "throughput": "1477.42", "total_tokens": 2349760} -{"current_steps": 144, "total_steps": 385, "loss": 0.1273, "learning_rate": 1.2000000000000002e-06, "epoch": 1.852090032154341, "percentage": 37.4, "elapsed_time": "0:26:41", "remaining_time": "0:44:40", "throughput": "1477.51", "total_tokens": 2366336} -{"current_steps": 145, "total_steps": 385, "loss": 0.1024, "learning_rate": 1.2083333333333333e-06, "epoch": 1.864951768488746, "percentage": 37.66, "elapsed_time": "0:26:52", "remaining_time": "0:44:29", "throughput": "1477.11", "total_tokens": 2382016} -{"current_steps": 146, "total_steps": 385, "loss": 0.1143, "learning_rate": 1.2166666666666667e-06, "epoch": 1.877813504823151, "percentage": 37.92, "elapsed_time": "0:27:03", "remaining_time": "0:44:17", "throughput": "1476.97", "total_tokens": 2398176} -{"current_steps": 147, "total_steps": 385, "loss": 0.1229, "learning_rate": 1.2250000000000001e-06, "epoch": 1.8906752411575563, "percentage": 38.18, "elapsed_time": "0:27:14", "remaining_time": "0:44:06", "throughput": "1477.01", "total_tokens": 2414656} -{"current_steps": 148, "total_steps": 385, "loss": 0.0964, "learning_rate": 1.2333333333333335e-06, "epoch": 1.9035369774919615, "percentage": 38.44, "elapsed_time": "0:27:25", "remaining_time": "0:43:55", "throughput": "1476.61", "total_tokens": 2430400} -{"current_steps": 149, "total_steps": 385, "loss": 0.1132, "learning_rate": 1.2416666666666667e-06, "epoch": 1.9163987138263665, "percentage": 38.7, "elapsed_time": "0:27:37", "remaining_time": "0:43:44", "throughput": "1477.03", "total_tokens": 2447520} -{"current_steps": 150, "total_steps": 385, "loss": 0.0734, "learning_rate": 1.25e-06, "epoch": 1.9292604501607717, "percentage": 38.96, "elapsed_time": "0:27:48", "remaining_time": "0:43:33", "throughput": "1476.98", "total_tokens": 2463872} -{"current_steps": 151, "total_steps": 385, "loss": 0.0939, "learning_rate": 1.2583333333333333e-06, "epoch": 1.942122186495177, "percentage": 39.22, "elapsed_time": "0:27:59", "remaining_time": "0:43:22", "throughput": "1477.57", "total_tokens": 2481344} -{"current_steps": 152, "total_steps": 385, "loss": 0.1143, "learning_rate": 1.2666666666666669e-06, "epoch": 1.954983922829582, "percentage": 39.48, "elapsed_time": "0:28:10", "remaining_time": "0:43:11", "throughput": "1477.48", "total_tokens": 2497632} -{"current_steps": 153, "total_steps": 385, "loss": 0.1114, "learning_rate": 1.275e-06, "epoch": 1.967845659163987, "percentage": 39.74, "elapsed_time": "0:28:21", "remaining_time": "0:43:00", "throughput": "1476.92", "total_tokens": 2513024} -{"current_steps": 154, "total_steps": 385, "loss": 0.0948, "learning_rate": 1.2833333333333335e-06, "epoch": 1.9807073954983923, "percentage": 40.0, "elapsed_time": "0:28:32", "remaining_time": "0:42:48", "throughput": "1476.58", "total_tokens": 2528800} -{"current_steps": 155, "total_steps": 385, "loss": 0.0805, "learning_rate": 1.2916666666666669e-06, "epoch": 1.9935691318327975, "percentage": 40.26, "elapsed_time": "0:28:43", "remaining_time": "0:42:37", "throughput": "1476.85", "total_tokens": 2545696} -{"current_steps": 156, "total_steps": 385, "loss": 0.1001, "learning_rate": 1.3e-06, "epoch": 2.0064308681672025, "percentage": 40.52, "elapsed_time": "0:28:54", "remaining_time": "0:42:26", "throughput": "1476.62", "total_tokens": 2561728} -{"current_steps": 157, "total_steps": 385, "loss": 0.1002, "learning_rate": 1.3083333333333334e-06, "epoch": 2.0192926045016075, "percentage": 40.78, "elapsed_time": "0:29:05", "remaining_time": "0:42:15", "throughput": "1476.44", "total_tokens": 2577856} -{"current_steps": 158, "total_steps": 385, "loss": 0.0847, "learning_rate": 1.3166666666666666e-06, "epoch": 2.032154340836013, "percentage": 41.04, "elapsed_time": "0:29:17", "remaining_time": "0:42:04", "throughput": "1476.26", "total_tokens": 2593984} -{"current_steps": 159, "total_steps": 385, "loss": 0.071, "learning_rate": 1.3250000000000002e-06, "epoch": 2.045016077170418, "percentage": 41.3, "elapsed_time": "0:29:28", "remaining_time": "0:41:53", "throughput": "1476.41", "total_tokens": 2610720} -{"current_steps": 160, "total_steps": 385, "loss": 0.0791, "learning_rate": 1.3333333333333334e-06, "epoch": 2.057877813504823, "percentage": 41.56, "elapsed_time": "0:29:39", "remaining_time": "0:41:42", "throughput": "1476.00", "total_tokens": 2626400} -{"current_steps": 161, "total_steps": 385, "loss": 0.0769, "learning_rate": 1.3416666666666666e-06, "epoch": 2.0707395498392285, "percentage": 41.82, "elapsed_time": "0:29:50", "remaining_time": "0:41:31", "throughput": "1475.83", "total_tokens": 2642496} -{"current_steps": 162, "total_steps": 385, "loss": 0.0916, "learning_rate": 1.3500000000000002e-06, "epoch": 2.0836012861736335, "percentage": 42.08, "elapsed_time": "0:30:01", "remaining_time": "0:41:19", "throughput": "1475.46", "total_tokens": 2658144} -{"current_steps": 163, "total_steps": 385, "loss": 0.0584, "learning_rate": 1.3583333333333334e-06, "epoch": 2.0964630225080385, "percentage": 42.34, "elapsed_time": "0:30:12", "remaining_time": "0:41:08", "throughput": "1475.48", "total_tokens": 2674560} -{"current_steps": 164, "total_steps": 385, "loss": 0.0811, "learning_rate": 1.3666666666666668e-06, "epoch": 2.1093247588424435, "percentage": 42.6, "elapsed_time": "0:30:23", "remaining_time": "0:40:57", "throughput": "1475.35", "total_tokens": 2690688} -{"current_steps": 165, "total_steps": 385, "loss": 0.0663, "learning_rate": 1.3750000000000002e-06, "epoch": 2.122186495176849, "percentage": 42.86, "elapsed_time": "0:30:34", "remaining_time": "0:40:46", "throughput": "1475.17", "total_tokens": 2706720} -{"current_steps": 166, "total_steps": 385, "loss": 0.0802, "learning_rate": 1.3833333333333336e-06, "epoch": 2.135048231511254, "percentage": 43.12, "elapsed_time": "0:30:45", "remaining_time": "0:40:35", "throughput": "1475.13", "total_tokens": 2723008} -{"current_steps": 167, "total_steps": 385, "loss": 0.0587, "learning_rate": 1.3916666666666668e-06, "epoch": 2.147909967845659, "percentage": 43.38, "elapsed_time": "0:30:57", "remaining_time": "0:40:24", "throughput": "1474.82", "total_tokens": 2738784} -{"current_steps": 168, "total_steps": 385, "loss": 0.0953, "learning_rate": 1.4000000000000001e-06, "epoch": 2.1607717041800645, "percentage": 43.64, "elapsed_time": "0:31:08", "remaining_time": "0:40:13", "throughput": "1474.73", "total_tokens": 2755072} -{"current_steps": 169, "total_steps": 385, "loss": 0.0795, "learning_rate": 1.4083333333333335e-06, "epoch": 2.1736334405144695, "percentage": 43.9, "elapsed_time": "0:31:19", "remaining_time": "0:40:01", "throughput": "1474.63", "total_tokens": 2771296} -{"current_steps": 170, "total_steps": 385, "loss": 0.1015, "learning_rate": 1.4166666666666667e-06, "epoch": 2.1864951768488745, "percentage": 44.16, "elapsed_time": "0:31:30", "remaining_time": "0:39:50", "throughput": "1474.63", "total_tokens": 2787712} -{"current_steps": 171, "total_steps": 385, "loss": 0.0614, "learning_rate": 1.425e-06, "epoch": 2.19935691318328, "percentage": 44.42, "elapsed_time": "0:31:41", "remaining_time": "0:39:39", "throughput": "1474.37", "total_tokens": 2803552} -{"current_steps": 172, "total_steps": 385, "loss": 0.0753, "learning_rate": 1.4333333333333335e-06, "epoch": 2.212218649517685, "percentage": 44.68, "elapsed_time": "0:31:52", "remaining_time": "0:39:28", "throughput": "1474.59", "total_tokens": 2820352} -{"current_steps": 173, "total_steps": 385, "loss": 0.08, "learning_rate": 1.4416666666666667e-06, "epoch": 2.22508038585209, "percentage": 44.94, "elapsed_time": "0:32:03", "remaining_time": "0:39:17", "throughput": "1475.05", "total_tokens": 2837696} -{"current_steps": 174, "total_steps": 385, "loss": 0.0603, "learning_rate": 1.45e-06, "epoch": 2.237942122186495, "percentage": 45.19, "elapsed_time": "0:32:14", "remaining_time": "0:39:06", "throughput": "1475.13", "total_tokens": 2854272} -{"current_steps": 175, "total_steps": 385, "loss": 0.0874, "learning_rate": 1.4583333333333335e-06, "epoch": 2.2508038585209005, "percentage": 45.45, "elapsed_time": "0:32:26", "remaining_time": "0:38:55", "throughput": "1475.01", "total_tokens": 2870464} -{"current_steps": 176, "total_steps": 385, "loss": 0.0833, "learning_rate": 1.4666666666666669e-06, "epoch": 2.2636655948553055, "percentage": 45.71, "elapsed_time": "0:32:37", "remaining_time": "0:38:44", "throughput": "1475.02", "total_tokens": 2886880} -{"current_steps": 177, "total_steps": 385, "loss": 0.0676, "learning_rate": 1.475e-06, "epoch": 2.2765273311897105, "percentage": 45.97, "elapsed_time": "0:32:48", "remaining_time": "0:38:33", "throughput": "1474.80", "total_tokens": 2902880} -{"current_steps": 178, "total_steps": 385, "loss": 0.086, "learning_rate": 1.4833333333333337e-06, "epoch": 2.289389067524116, "percentage": 46.23, "elapsed_time": "0:32:59", "remaining_time": "0:38:21", "throughput": "1474.96", "total_tokens": 2919584} -{"current_steps": 179, "total_steps": 385, "loss": 0.0662, "learning_rate": 1.4916666666666669e-06, "epoch": 2.302250803858521, "percentage": 46.49, "elapsed_time": "0:33:10", "remaining_time": "0:38:10", "throughput": "1474.55", "total_tokens": 2935136} -{"current_steps": 180, "total_steps": 385, "loss": 0.1028, "learning_rate": 1.5e-06, "epoch": 2.315112540192926, "percentage": 46.75, "elapsed_time": "0:33:21", "remaining_time": "0:37:59", "throughput": "1474.63", "total_tokens": 2951680} -{"current_steps": 181, "total_steps": 385, "loss": 0.0882, "learning_rate": 1.5083333333333336e-06, "epoch": 2.327974276527331, "percentage": 47.01, "elapsed_time": "0:33:32", "remaining_time": "0:37:48", "throughput": "1474.45", "total_tokens": 2967712} -{"current_steps": 182, "total_steps": 385, "loss": 0.0806, "learning_rate": 1.5166666666666668e-06, "epoch": 2.3408360128617365, "percentage": 47.27, "elapsed_time": "0:33:43", "remaining_time": "0:37:37", "throughput": "1474.52", "total_tokens": 2984224} -{"current_steps": 183, "total_steps": 385, "loss": 0.1108, "learning_rate": 1.525e-06, "epoch": 2.3536977491961415, "percentage": 47.53, "elapsed_time": "0:33:54", "remaining_time": "0:37:26", "throughput": "1474.19", "total_tokens": 2999904} -{"current_steps": 184, "total_steps": 385, "loss": 0.0687, "learning_rate": 1.5333333333333334e-06, "epoch": 2.3665594855305465, "percentage": 47.79, "elapsed_time": "0:34:06", "remaining_time": "0:37:15", "throughput": "1474.68", "total_tokens": 3017376} -{"current_steps": 185, "total_steps": 385, "loss": 0.0736, "learning_rate": 1.5416666666666668e-06, "epoch": 2.379421221864952, "percentage": 48.05, "elapsed_time": "0:34:17", "remaining_time": "0:37:04", "throughput": "1474.67", "total_tokens": 3033728} -{"current_steps": 186, "total_steps": 385, "loss": 0.0779, "learning_rate": 1.5500000000000002e-06, "epoch": 2.392282958199357, "percentage": 48.31, "elapsed_time": "0:34:28", "remaining_time": "0:36:52", "throughput": "1474.70", "total_tokens": 3050176} -{"current_steps": 187, "total_steps": 385, "loss": 0.0709, "learning_rate": 1.5583333333333334e-06, "epoch": 2.405144694533762, "percentage": 48.57, "elapsed_time": "0:34:39", "remaining_time": "0:36:41", "throughput": "1474.61", "total_tokens": 3066400} -{"current_steps": 188, "total_steps": 385, "loss": 0.0652, "learning_rate": 1.566666666666667e-06, "epoch": 2.418006430868167, "percentage": 48.83, "elapsed_time": "0:34:50", "remaining_time": "0:36:30", "throughput": "1474.76", "total_tokens": 3083104} -{"current_steps": 189, "total_steps": 385, "loss": 0.1095, "learning_rate": 1.5750000000000002e-06, "epoch": 2.4308681672025725, "percentage": 49.09, "elapsed_time": "0:35:01", "remaining_time": "0:36:19", "throughput": "1475.00", "total_tokens": 3100000} -{"current_steps": 190, "total_steps": 385, "loss": 0.0618, "learning_rate": 1.5833333333333333e-06, "epoch": 2.4437299035369775, "percentage": 49.35, "elapsed_time": "0:35:12", "remaining_time": "0:36:08", "throughput": "1475.18", "total_tokens": 3116800} -{"current_steps": 191, "total_steps": 385, "loss": 0.0666, "learning_rate": 1.591666666666667e-06, "epoch": 2.4565916398713825, "percentage": 49.61, "elapsed_time": "0:35:23", "remaining_time": "0:35:57", "throughput": "1475.36", "total_tokens": 3133568} -{"current_steps": 192, "total_steps": 385, "loss": 0.0573, "learning_rate": 1.6000000000000001e-06, "epoch": 2.469453376205788, "percentage": 49.87, "elapsed_time": "0:35:35", "remaining_time": "0:35:46", "throughput": "1475.40", "total_tokens": 3150048} -{"current_steps": 193, "total_steps": 385, "loss": 0.0577, "learning_rate": 1.6083333333333333e-06, "epoch": 2.482315112540193, "percentage": 50.13, "elapsed_time": "0:35:46", "remaining_time": "0:35:35", "throughput": "1475.50", "total_tokens": 3166688} -{"current_steps": 194, "total_steps": 385, "loss": 0.0813, "learning_rate": 1.6166666666666667e-06, "epoch": 2.495176848874598, "percentage": 50.39, "elapsed_time": "0:35:57", "remaining_time": "0:35:23", "throughput": "1475.34", "total_tokens": 3182752} -{"current_steps": 195, "total_steps": 385, "loss": 0.066, "learning_rate": 1.6250000000000001e-06, "epoch": 2.508038585209003, "percentage": 50.65, "elapsed_time": "0:36:08", "remaining_time": "0:35:12", "throughput": "1475.24", "total_tokens": 3198944} -{"current_steps": 196, "total_steps": 385, "loss": 0.0622, "learning_rate": 1.6333333333333335e-06, "epoch": 2.5209003215434085, "percentage": 50.91, "elapsed_time": "0:36:19", "remaining_time": "0:35:01", "throughput": "1475.32", "total_tokens": 3215552} -{"current_steps": 197, "total_steps": 385, "loss": 0.0616, "learning_rate": 1.6416666666666667e-06, "epoch": 2.5337620578778135, "percentage": 51.17, "elapsed_time": "0:36:30", "remaining_time": "0:34:50", "throughput": "1475.12", "total_tokens": 3231488} -{"current_steps": 198, "total_steps": 385, "loss": 0.0993, "learning_rate": 1.6500000000000003e-06, "epoch": 2.5466237942122185, "percentage": 51.43, "elapsed_time": "0:36:41", "remaining_time": "0:34:39", "throughput": "1475.12", "total_tokens": 3247840} -{"current_steps": 199, "total_steps": 385, "loss": 0.0702, "learning_rate": 1.6583333333333335e-06, "epoch": 2.559485530546624, "percentage": 51.69, "elapsed_time": "0:36:52", "remaining_time": "0:34:28", "throughput": "1475.10", "total_tokens": 3264128} -{"current_steps": 200, "total_steps": 385, "loss": 0.0743, "learning_rate": 1.6666666666666667e-06, "epoch": 2.572347266881029, "percentage": 51.95, "elapsed_time": "0:37:03", "remaining_time": "0:34:17", "throughput": "1474.97", "total_tokens": 3280192} -{"current_steps": 201, "total_steps": 385, "loss": 0.0647, "learning_rate": 1.6750000000000003e-06, "epoch": 2.585209003215434, "percentage": 52.21, "elapsed_time": "0:37:15", "remaining_time": "0:34:05", "throughput": "1474.93", "total_tokens": 3296480} -{"current_steps": 202, "total_steps": 385, "loss": 0.0814, "learning_rate": 1.6833333333333335e-06, "epoch": 2.598070739549839, "percentage": 52.47, "elapsed_time": "0:37:26", "remaining_time": "0:33:54", "throughput": "1475.03", "total_tokens": 3313120} -{"current_steps": 203, "total_steps": 385, "loss": 0.0861, "learning_rate": 1.6916666666666666e-06, "epoch": 2.6109324758842445, "percentage": 52.73, "elapsed_time": "0:37:37", "remaining_time": "0:33:43", "throughput": "1474.89", "total_tokens": 3329184} -{"current_steps": 204, "total_steps": 385, "loss": 0.0769, "learning_rate": 1.7000000000000002e-06, "epoch": 2.6237942122186495, "percentage": 52.99, "elapsed_time": "0:37:48", "remaining_time": "0:33:32", "throughput": "1475.15", "total_tokens": 3346208} -{"current_steps": 205, "total_steps": 385, "loss": 0.0888, "learning_rate": 1.7083333333333334e-06, "epoch": 2.6366559485530545, "percentage": 53.25, "elapsed_time": "0:37:59", "remaining_time": "0:33:21", "throughput": "1475.31", "total_tokens": 3363008} -{"current_steps": 206, "total_steps": 385, "loss": 0.1017, "learning_rate": 1.7166666666666668e-06, "epoch": 2.64951768488746, "percentage": 53.51, "elapsed_time": "0:38:10", "remaining_time": "0:33:10", "throughput": "1475.34", "total_tokens": 3379488} -{"current_steps": 207, "total_steps": 385, "loss": 0.0677, "learning_rate": 1.725e-06, "epoch": 2.662379421221865, "percentage": 53.77, "elapsed_time": "0:38:21", "remaining_time": "0:32:59", "throughput": "1475.25", "total_tokens": 3395648} -{"current_steps": 208, "total_steps": 385, "loss": 0.0861, "learning_rate": 1.7333333333333336e-06, "epoch": 2.67524115755627, "percentage": 54.03, "elapsed_time": "0:38:32", "remaining_time": "0:32:48", "throughput": "1475.55", "total_tokens": 3412736} -{"current_steps": 209, "total_steps": 385, "loss": 0.0562, "learning_rate": 1.7416666666666668e-06, "epoch": 2.688102893890675, "percentage": 54.29, "elapsed_time": "0:38:43", "remaining_time": "0:32:37", "throughput": "1475.69", "total_tokens": 3429472} -{"current_steps": 210, "total_steps": 385, "loss": 0.0641, "learning_rate": 1.75e-06, "epoch": 2.7009646302250805, "percentage": 54.55, "elapsed_time": "0:38:55", "remaining_time": "0:32:25", "throughput": "1475.59", "total_tokens": 3445632} -{"current_steps": 211, "total_steps": 385, "loss": 0.0829, "learning_rate": 1.7583333333333336e-06, "epoch": 2.7138263665594855, "percentage": 54.81, "elapsed_time": "0:39:06", "remaining_time": "0:32:14", "throughput": "1475.88", "total_tokens": 3462720} -{"current_steps": 212, "total_steps": 385, "loss": 0.0632, "learning_rate": 1.7666666666666668e-06, "epoch": 2.7266881028938905, "percentage": 55.06, "elapsed_time": "0:39:17", "remaining_time": "0:32:03", "throughput": "1475.70", "total_tokens": 3478720} -{"current_steps": 213, "total_steps": 385, "loss": 0.062, "learning_rate": 1.7750000000000002e-06, "epoch": 2.739549839228296, "percentage": 55.32, "elapsed_time": "0:39:28", "remaining_time": "0:31:52", "throughput": "1475.36", "total_tokens": 3494304} -{"current_steps": 214, "total_steps": 385, "loss": 0.0816, "learning_rate": 1.7833333333333336e-06, "epoch": 2.752411575562701, "percentage": 55.58, "elapsed_time": "0:39:39", "remaining_time": "0:31:41", "throughput": "1475.14", "total_tokens": 3510176} -{"current_steps": 215, "total_steps": 385, "loss": 0.096, "learning_rate": 1.7916666666666667e-06, "epoch": 2.765273311897106, "percentage": 55.84, "elapsed_time": "0:39:50", "remaining_time": "0:31:30", "throughput": "1475.26", "total_tokens": 3526848} -{"current_steps": 216, "total_steps": 385, "loss": 0.0639, "learning_rate": 1.8000000000000001e-06, "epoch": 2.778135048231511, "percentage": 56.1, "elapsed_time": "0:40:01", "remaining_time": "0:31:19", "throughput": "1475.21", "total_tokens": 3543136} -{"current_steps": 217, "total_steps": 385, "loss": 0.0915, "learning_rate": 1.8083333333333335e-06, "epoch": 2.7909967845659165, "percentage": 56.36, "elapsed_time": "0:40:12", "remaining_time": "0:31:08", "throughput": "1474.69", "total_tokens": 3558240} -{"current_steps": 218, "total_steps": 385, "loss": 0.061, "learning_rate": 1.816666666666667e-06, "epoch": 2.8038585209003215, "percentage": 56.62, "elapsed_time": "0:40:23", "remaining_time": "0:30:56", "throughput": "1474.53", "total_tokens": 3574240} -{"current_steps": 219, "total_steps": 385, "loss": 0.0572, "learning_rate": 1.825e-06, "epoch": 2.816720257234727, "percentage": 56.88, "elapsed_time": "0:40:35", "remaining_time": "0:30:45", "throughput": "1474.35", "total_tokens": 3590240} -{"current_steps": 220, "total_steps": 385, "loss": 0.0497, "learning_rate": 1.8333333333333333e-06, "epoch": 2.829581993569132, "percentage": 57.14, "elapsed_time": "0:40:46", "remaining_time": "0:30:34", "throughput": "1474.44", "total_tokens": 3606912} -{"current_steps": 221, "total_steps": 385, "loss": 0.0672, "learning_rate": 1.8416666666666669e-06, "epoch": 2.842443729903537, "percentage": 57.4, "elapsed_time": "0:40:57", "remaining_time": "0:30:23", "throughput": "1474.31", "total_tokens": 3623008} -{"current_steps": 222, "total_steps": 385, "loss": 0.0563, "learning_rate": 1.85e-06, "epoch": 2.855305466237942, "percentage": 57.66, "elapsed_time": "0:41:08", "remaining_time": "0:30:12", "throughput": "1474.33", "total_tokens": 3639456} -{"current_steps": 223, "total_steps": 385, "loss": 0.069, "learning_rate": 1.8583333333333335e-06, "epoch": 2.868167202572347, "percentage": 57.92, "elapsed_time": "0:41:19", "remaining_time": "0:30:01", "throughput": "1474.50", "total_tokens": 3656288} -{"current_steps": 224, "total_steps": 385, "loss": 0.0824, "learning_rate": 1.8666666666666669e-06, "epoch": 2.8810289389067525, "percentage": 58.18, "elapsed_time": "0:41:30", "remaining_time": "0:29:50", "throughput": "1474.59", "total_tokens": 3672896} -{"current_steps": 225, "total_steps": 385, "loss": 0.057, "learning_rate": 1.8750000000000003e-06, "epoch": 2.8938906752411575, "percentage": 58.44, "elapsed_time": "0:41:41", "remaining_time": "0:29:39", "throughput": "1474.72", "total_tokens": 3689632} -{"current_steps": 226, "total_steps": 385, "loss": 0.0549, "learning_rate": 1.8833333333333334e-06, "epoch": 2.906752411575563, "percentage": 58.7, "elapsed_time": "0:41:53", "remaining_time": "0:29:28", "throughput": "1475.08", "total_tokens": 3706944} -{"current_steps": 227, "total_steps": 385, "loss": 0.0652, "learning_rate": 1.8916666666666668e-06, "epoch": 2.919614147909968, "percentage": 58.96, "elapsed_time": "0:42:04", "remaining_time": "0:29:16", "throughput": "1474.98", "total_tokens": 3723072} -{"current_steps": 228, "total_steps": 385, "loss": 0.0743, "learning_rate": 1.9000000000000002e-06, "epoch": 2.932475884244373, "percentage": 59.22, "elapsed_time": "0:42:15", "remaining_time": "0:29:05", "throughput": "1475.20", "total_tokens": 3740064} -{"current_steps": 229, "total_steps": 385, "loss": 0.0416, "learning_rate": 1.9083333333333334e-06, "epoch": 2.945337620578778, "percentage": 59.48, "elapsed_time": "0:42:26", "remaining_time": "0:28:54", "throughput": "1475.35", "total_tokens": 3756864} -{"current_steps": 230, "total_steps": 385, "loss": 0.0668, "learning_rate": 1.916666666666667e-06, "epoch": 2.958199356913183, "percentage": 59.74, "elapsed_time": "0:42:37", "remaining_time": "0:28:43", "throughput": "1475.75", "total_tokens": 3774336} -{"current_steps": 231, "total_steps": 385, "loss": 0.0603, "learning_rate": 1.925e-06, "epoch": 2.9710610932475885, "percentage": 60.0, "elapsed_time": "0:42:48", "remaining_time": "0:28:32", "throughput": "1475.60", "total_tokens": 3790336} -{"current_steps": 232, "total_steps": 385, "loss": 0.066, "learning_rate": 1.9333333333333336e-06, "epoch": 2.9839228295819935, "percentage": 60.26, "elapsed_time": "0:42:59", "remaining_time": "0:28:21", "throughput": "1475.88", "total_tokens": 3807520} -{"current_steps": 233, "total_steps": 385, "loss": 0.0692, "learning_rate": 1.9416666666666666e-06, "epoch": 2.996784565916399, "percentage": 60.52, "elapsed_time": "0:43:10", "remaining_time": "0:28:10", "throughput": "1475.87", "total_tokens": 3823872} -{"current_steps": 234, "total_steps": 385, "loss": 0.0323, "learning_rate": 1.9500000000000004e-06, "epoch": 3.009646302250804, "percentage": 60.78, "elapsed_time": "0:43:22", "remaining_time": "0:27:59", "throughput": "1475.89", "total_tokens": 3840320} -{"current_steps": 235, "total_steps": 385, "loss": 0.0403, "learning_rate": 1.9583333333333334e-06, "epoch": 3.022508038585209, "percentage": 61.04, "elapsed_time": "0:43:33", "remaining_time": "0:27:47", "throughput": "1475.72", "total_tokens": 3856256} -{"current_steps": 236, "total_steps": 385, "loss": 0.0477, "learning_rate": 1.9666666666666668e-06, "epoch": 3.035369774919614, "percentage": 61.3, "elapsed_time": "0:43:44", "remaining_time": "0:27:36", "throughput": "1475.66", "total_tokens": 3872512} -{"current_steps": 237, "total_steps": 385, "loss": 0.0356, "learning_rate": 1.975e-06, "epoch": 3.0482315112540195, "percentage": 61.56, "elapsed_time": "0:43:55", "remaining_time": "0:27:25", "throughput": "1475.41", "total_tokens": 3888256} -{"current_steps": 238, "total_steps": 385, "loss": 0.0324, "learning_rate": 1.9833333333333335e-06, "epoch": 3.0610932475884245, "percentage": 61.82, "elapsed_time": "0:44:06", "remaining_time": "0:27:14", "throughput": "1475.56", "total_tokens": 3905024} -{"current_steps": 239, "total_steps": 385, "loss": 0.0428, "learning_rate": 1.991666666666667e-06, "epoch": 3.0739549839228295, "percentage": 62.08, "elapsed_time": "0:44:17", "remaining_time": "0:27:03", "throughput": "1475.76", "total_tokens": 3922016} -{"current_steps": 240, "total_steps": 385, "loss": 0.0315, "learning_rate": 2.0000000000000003e-06, "epoch": 3.0868167202572345, "percentage": 62.34, "elapsed_time": "0:44:28", "remaining_time": "0:26:52", "throughput": "1475.75", "total_tokens": 3938400} -{"current_steps": 241, "total_steps": 385, "loss": 0.0366, "learning_rate": 2.0083333333333337e-06, "epoch": 3.09967845659164, "percentage": 62.6, "elapsed_time": "0:44:39", "remaining_time": "0:26:41", "throughput": "1475.78", "total_tokens": 3954912} -{"current_steps": 242, "total_steps": 385, "loss": 0.0307, "learning_rate": 2.0166666666666667e-06, "epoch": 3.112540192926045, "percentage": 62.86, "elapsed_time": "0:44:50", "remaining_time": "0:26:30", "throughput": "1475.47", "total_tokens": 3970400} -{"current_steps": 243, "total_steps": 385, "loss": 0.0338, "learning_rate": 2.025e-06, "epoch": 3.12540192926045, "percentage": 63.12, "elapsed_time": "0:45:02", "remaining_time": "0:26:18", "throughput": "1475.52", "total_tokens": 3986944} -{"current_steps": 244, "total_steps": 385, "loss": 0.0348, "learning_rate": 2.0333333333333335e-06, "epoch": 3.1382636655948555, "percentage": 63.38, "elapsed_time": "0:45:13", "remaining_time": "0:26:07", "throughput": "1475.62", "total_tokens": 4003648} -{"current_steps": 245, "total_steps": 385, "loss": 0.0355, "learning_rate": 2.041666666666667e-06, "epoch": 3.1511254019292605, "percentage": 63.64, "elapsed_time": "0:45:24", "remaining_time": "0:25:56", "throughput": "1475.75", "total_tokens": 4020384} -{"current_steps": 246, "total_steps": 385, "loss": 0.0272, "learning_rate": 2.05e-06, "epoch": 3.1639871382636655, "percentage": 63.9, "elapsed_time": "0:45:35", "remaining_time": "0:25:45", "throughput": "1475.84", "total_tokens": 4037088} -{"current_steps": 247, "total_steps": 385, "loss": 0.0464, "learning_rate": 2.0583333333333337e-06, "epoch": 3.176848874598071, "percentage": 64.16, "elapsed_time": "0:45:46", "remaining_time": "0:25:34", "throughput": "1475.83", "total_tokens": 4053472} -{"current_steps": 248, "total_steps": 385, "loss": 0.0268, "learning_rate": 2.0666666666666666e-06, "epoch": 3.189710610932476, "percentage": 64.42, "elapsed_time": "0:45:57", "remaining_time": "0:25:23", "throughput": "1475.60", "total_tokens": 4069248} -{"current_steps": 249, "total_steps": 385, "loss": 0.0229, "learning_rate": 2.075e-06, "epoch": 3.202572347266881, "percentage": 64.68, "elapsed_time": "0:46:08", "remaining_time": "0:25:12", "throughput": "1475.38", "total_tokens": 4085024} -{"current_steps": 250, "total_steps": 385, "loss": 0.0373, "learning_rate": 2.0833333333333334e-06, "epoch": 3.215434083601286, "percentage": 64.94, "elapsed_time": "0:46:19", "remaining_time": "0:25:01", "throughput": "1475.74", "total_tokens": 4102432} -{"current_steps": 251, "total_steps": 385, "loss": 0.0361, "learning_rate": 2.091666666666667e-06, "epoch": 3.2282958199356915, "percentage": 65.19, "elapsed_time": "0:46:31", "remaining_time": "0:24:50", "throughput": "1475.59", "total_tokens": 4118368} -{"current_steps": 252, "total_steps": 385, "loss": 0.0401, "learning_rate": 2.1000000000000002e-06, "epoch": 3.2411575562700965, "percentage": 65.45, "elapsed_time": "0:46:42", "remaining_time": "0:24:38", "throughput": "1475.60", "total_tokens": 4134784} -{"current_steps": 253, "total_steps": 385, "loss": 0.0262, "learning_rate": 2.1083333333333336e-06, "epoch": 3.2540192926045015, "percentage": 65.71, "elapsed_time": "0:46:53", "remaining_time": "0:24:27", "throughput": "1475.38", "total_tokens": 4150528} -{"current_steps": 254, "total_steps": 385, "loss": 0.0481, "learning_rate": 2.116666666666667e-06, "epoch": 3.266881028938907, "percentage": 65.97, "elapsed_time": "0:47:04", "remaining_time": "0:24:16", "throughput": "1475.34", "total_tokens": 4166816} -{"current_steps": 255, "total_steps": 385, "loss": 0.0417, "learning_rate": 2.125e-06, "epoch": 3.279742765273312, "percentage": 66.23, "elapsed_time": "0:47:15", "remaining_time": "0:24:05", "throughput": "1475.21", "total_tokens": 4182880} -{"current_steps": 256, "total_steps": 385, "loss": 0.0457, "learning_rate": 2.133333333333334e-06, "epoch": 3.292604501607717, "percentage": 66.49, "elapsed_time": "0:47:26", "remaining_time": "0:23:54", "throughput": "1475.48", "total_tokens": 4200128} -{"current_steps": 257, "total_steps": 385, "loss": 0.0175, "learning_rate": 2.1416666666666668e-06, "epoch": 3.305466237942122, "percentage": 66.75, "elapsed_time": "0:47:37", "remaining_time": "0:23:43", "throughput": "1475.19", "total_tokens": 4215680} -{"current_steps": 258, "total_steps": 385, "loss": 0.0371, "learning_rate": 2.15e-06, "epoch": 3.3183279742765275, "percentage": 67.01, "elapsed_time": "0:47:48", "remaining_time": "0:23:32", "throughput": "1475.40", "total_tokens": 4232736} -{"current_steps": 259, "total_steps": 385, "loss": 0.0268, "learning_rate": 2.1583333333333336e-06, "epoch": 3.3311897106109325, "percentage": 67.27, "elapsed_time": "0:47:59", "remaining_time": "0:23:21", "throughput": "1475.58", "total_tokens": 4249664} -{"current_steps": 260, "total_steps": 385, "loss": 0.0417, "learning_rate": 2.166666666666667e-06, "epoch": 3.3440514469453375, "percentage": 67.53, "elapsed_time": "0:48:11", "remaining_time": "0:23:09", "throughput": "1475.58", "total_tokens": 4266016} -{"current_steps": 261, "total_steps": 385, "loss": 0.0264, "learning_rate": 2.1750000000000004e-06, "epoch": 3.356913183279743, "percentage": 67.79, "elapsed_time": "0:48:22", "remaining_time": "0:22:58", "throughput": "1475.32", "total_tokens": 4281664} -{"current_steps": 262, "total_steps": 385, "loss": 0.0336, "learning_rate": 2.1833333333333333e-06, "epoch": 3.369774919614148, "percentage": 68.05, "elapsed_time": "0:48:33", "remaining_time": "0:22:47", "throughput": "1475.42", "total_tokens": 4298368} -{"current_steps": 263, "total_steps": 385, "loss": 0.0434, "learning_rate": 2.191666666666667e-06, "epoch": 3.382636655948553, "percentage": 68.31, "elapsed_time": "0:48:44", "remaining_time": "0:22:36", "throughput": "1475.28", "total_tokens": 4314336} -{"current_steps": 264, "total_steps": 385, "loss": 0.0389, "learning_rate": 2.2e-06, "epoch": 3.395498392282958, "percentage": 68.57, "elapsed_time": "0:48:55", "remaining_time": "0:22:25", "throughput": "1475.08", "total_tokens": 4330144} -{"current_steps": 265, "total_steps": 385, "loss": 0.045, "learning_rate": 2.2083333333333335e-06, "epoch": 3.4083601286173635, "percentage": 68.83, "elapsed_time": "0:49:06", "remaining_time": "0:22:14", "throughput": "1474.84", "total_tokens": 4345856} -{"current_steps": 266, "total_steps": 385, "loss": 0.0331, "learning_rate": 2.216666666666667e-06, "epoch": 3.4212218649517685, "percentage": 69.09, "elapsed_time": "0:49:17", "remaining_time": "0:22:03", "throughput": "1474.66", "total_tokens": 4361696} -{"current_steps": 267, "total_steps": 385, "loss": 0.0228, "learning_rate": 2.2250000000000003e-06, "epoch": 3.4340836012861735, "percentage": 69.35, "elapsed_time": "0:49:28", "remaining_time": "0:21:52", "throughput": "1474.73", "total_tokens": 4378304} -{"current_steps": 268, "total_steps": 385, "loss": 0.0307, "learning_rate": 2.2333333333333333e-06, "epoch": 3.446945337620579, "percentage": 69.61, "elapsed_time": "0:49:39", "remaining_time": "0:21:40", "throughput": "1474.93", "total_tokens": 4395232} -{"current_steps": 269, "total_steps": 385, "loss": 0.0332, "learning_rate": 2.2416666666666667e-06, "epoch": 3.459807073954984, "percentage": 69.87, "elapsed_time": "0:49:51", "remaining_time": "0:21:29", "throughput": "1474.79", "total_tokens": 4411232} -{"current_steps": 270, "total_steps": 385, "loss": 0.0662, "learning_rate": 2.25e-06, "epoch": 3.472668810289389, "percentage": 70.13, "elapsed_time": "0:50:02", "remaining_time": "0:21:18", "throughput": "1474.75", "total_tokens": 4427520} -{"current_steps": 271, "total_steps": 385, "loss": 0.0431, "learning_rate": 2.2583333333333335e-06, "epoch": 3.485530546623794, "percentage": 70.39, "elapsed_time": "0:50:13", "remaining_time": "0:21:07", "throughput": "1474.76", "total_tokens": 4443904} -{"current_steps": 272, "total_steps": 385, "loss": 0.0423, "learning_rate": 2.266666666666667e-06, "epoch": 3.4983922829581995, "percentage": 70.65, "elapsed_time": "0:50:24", "remaining_time": "0:20:56", "throughput": "1474.84", "total_tokens": 4460608} -{"current_steps": 273, "total_steps": 385, "loss": 0.0447, "learning_rate": 2.2750000000000002e-06, "epoch": 3.5112540192926045, "percentage": 70.91, "elapsed_time": "0:50:35", "remaining_time": "0:20:45", "throughput": "1474.86", "total_tokens": 4477120} -{"current_steps": 274, "total_steps": 385, "loss": 0.0337, "learning_rate": 2.2833333333333336e-06, "epoch": 3.5241157556270095, "percentage": 71.17, "elapsed_time": "0:50:46", "remaining_time": "0:20:34", "throughput": "1474.75", "total_tokens": 4493152} -{"current_steps": 275, "total_steps": 385, "loss": 0.0319, "learning_rate": 2.2916666666666666e-06, "epoch": 3.536977491961415, "percentage": 71.43, "elapsed_time": "0:50:57", "remaining_time": "0:20:23", "throughput": "1474.61", "total_tokens": 4509120} -{"current_steps": 276, "total_steps": 385, "loss": 0.027, "learning_rate": 2.3000000000000004e-06, "epoch": 3.54983922829582, "percentage": 71.69, "elapsed_time": "0:51:08", "remaining_time": "0:20:12", "throughput": "1474.75", "total_tokens": 4525984} -{"current_steps": 277, "total_steps": 385, "loss": 0.0244, "learning_rate": 2.3083333333333334e-06, "epoch": 3.562700964630225, "percentage": 71.95, "elapsed_time": "0:51:20", "remaining_time": "0:20:00", "throughput": "1474.91", "total_tokens": 4542816} -{"current_steps": 278, "total_steps": 385, "loss": 0.0377, "learning_rate": 2.316666666666667e-06, "epoch": 3.57556270096463, "percentage": 72.21, "elapsed_time": "0:51:31", "remaining_time": "0:19:49", "throughput": "1475.12", "total_tokens": 4559872} -{"current_steps": 279, "total_steps": 385, "loss": 0.0477, "learning_rate": 2.325e-06, "epoch": 3.5884244372990355, "percentage": 72.47, "elapsed_time": "0:51:42", "remaining_time": "0:19:38", "throughput": "1475.12", "total_tokens": 4576288} -{"current_steps": 280, "total_steps": 385, "loss": 0.0332, "learning_rate": 2.3333333333333336e-06, "epoch": 3.6012861736334405, "percentage": 72.73, "elapsed_time": "0:51:53", "remaining_time": "0:19:27", "throughput": "1474.74", "total_tokens": 4591456} -{"current_steps": 281, "total_steps": 385, "loss": 0.0285, "learning_rate": 2.341666666666667e-06, "epoch": 3.6141479099678455, "percentage": 72.99, "elapsed_time": "0:52:04", "remaining_time": "0:19:16", "throughput": "1474.97", "total_tokens": 4608608} -{"current_steps": 282, "total_steps": 385, "loss": 0.0468, "learning_rate": 2.35e-06, "epoch": 3.627009646302251, "percentage": 73.25, "elapsed_time": "0:52:15", "remaining_time": "0:19:05", "throughput": "1475.00", "total_tokens": 4625120} -{"current_steps": 283, "total_steps": 385, "loss": 0.037, "learning_rate": 2.3583333333333338e-06, "epoch": 3.639871382636656, "percentage": 73.51, "elapsed_time": "0:52:26", "remaining_time": "0:18:54", "throughput": "1475.13", "total_tokens": 4641952} -{"current_steps": 284, "total_steps": 385, "loss": 0.041, "learning_rate": 2.3666666666666667e-06, "epoch": 3.652733118971061, "percentage": 73.77, "elapsed_time": "0:52:37", "remaining_time": "0:18:43", "throughput": "1474.98", "total_tokens": 4657920} -{"current_steps": 285, "total_steps": 385, "loss": 0.0461, "learning_rate": 2.375e-06, "epoch": 3.665594855305466, "percentage": 74.03, "elapsed_time": "0:52:49", "remaining_time": "0:18:31", "throughput": "1475.10", "total_tokens": 4674688} -{"current_steps": 286, "total_steps": 385, "loss": 0.0594, "learning_rate": 2.3833333333333335e-06, "epoch": 3.6784565916398715, "percentage": 74.29, "elapsed_time": "0:53:00", "remaining_time": "0:18:20", "throughput": "1474.95", "total_tokens": 4690592} -{"current_steps": 287, "total_steps": 385, "loss": 0.0728, "learning_rate": 2.391666666666667e-06, "epoch": 3.6913183279742765, "percentage": 74.55, "elapsed_time": "0:53:11", "remaining_time": "0:18:09", "throughput": "1475.07", "total_tokens": 4707360} -{"current_steps": 288, "total_steps": 385, "loss": 0.029, "learning_rate": 2.4000000000000003e-06, "epoch": 3.7041800643086815, "percentage": 74.81, "elapsed_time": "0:53:22", "remaining_time": "0:17:58", "throughput": "1475.20", "total_tokens": 4724192} -{"current_steps": 289, "total_steps": 385, "loss": 0.0412, "learning_rate": 2.4083333333333337e-06, "epoch": 3.717041800643087, "percentage": 75.06, "elapsed_time": "0:53:33", "remaining_time": "0:17:47", "throughput": "1475.44", "total_tokens": 4741344} -{"current_steps": 290, "total_steps": 385, "loss": 0.0262, "learning_rate": 2.4166666666666667e-06, "epoch": 3.729903536977492, "percentage": 75.32, "elapsed_time": "0:53:44", "remaining_time": "0:17:36", "throughput": "1475.13", "total_tokens": 4756768} -{"current_steps": 291, "total_steps": 385, "loss": 0.0796, "learning_rate": 2.425e-06, "epoch": 3.742765273311897, "percentage": 75.58, "elapsed_time": "0:53:55", "remaining_time": "0:17:25", "throughput": "1474.96", "total_tokens": 4772608} -{"current_steps": 292, "total_steps": 385, "loss": 0.0447, "learning_rate": 2.4333333333333335e-06, "epoch": 3.755627009646302, "percentage": 75.84, "elapsed_time": "0:54:06", "remaining_time": "0:17:14", "throughput": "1474.93", "total_tokens": 4788928} -{"current_steps": 293, "total_steps": 385, "loss": 0.0252, "learning_rate": 2.441666666666667e-06, "epoch": 3.7684887459807075, "percentage": 76.1, "elapsed_time": "0:54:18", "remaining_time": "0:17:02", "throughput": "1474.95", "total_tokens": 4805408} -{"current_steps": 294, "total_steps": 385, "loss": 0.0458, "learning_rate": 2.4500000000000003e-06, "epoch": 3.7813504823151125, "percentage": 76.36, "elapsed_time": "0:54:29", "remaining_time": "0:16:51", "throughput": "1474.79", "total_tokens": 4821248} -{"current_steps": 295, "total_steps": 385, "loss": 0.0431, "learning_rate": 2.4583333333333332e-06, "epoch": 3.7942122186495175, "percentage": 76.62, "elapsed_time": "0:54:40", "remaining_time": "0:16:40", "throughput": "1474.62", "total_tokens": 4837024} -{"current_steps": 296, "total_steps": 385, "loss": 0.0422, "learning_rate": 2.466666666666667e-06, "epoch": 3.807073954983923, "percentage": 76.88, "elapsed_time": "0:54:51", "remaining_time": "0:16:29", "throughput": "1474.72", "total_tokens": 4853760} -{"current_steps": 297, "total_steps": 385, "loss": 0.0428, "learning_rate": 2.475e-06, "epoch": 3.819935691318328, "percentage": 77.14, "elapsed_time": "0:55:02", "remaining_time": "0:16:18", "throughput": "1474.85", "total_tokens": 4870560} -{"current_steps": 298, "total_steps": 385, "loss": 0.0473, "learning_rate": 2.4833333333333334e-06, "epoch": 3.832797427652733, "percentage": 77.4, "elapsed_time": "0:55:13", "remaining_time": "0:16:07", "throughput": "1474.88", "total_tokens": 4887040} -{"current_steps": 299, "total_steps": 385, "loss": 0.0223, "learning_rate": 2.491666666666667e-06, "epoch": 3.845659163987138, "percentage": 77.66, "elapsed_time": "0:55:24", "remaining_time": "0:15:56", "throughput": "1474.81", "total_tokens": 4903232} -{"current_steps": 300, "total_steps": 385, "loss": 0.0274, "learning_rate": 2.5e-06, "epoch": 3.8585209003215435, "percentage": 77.92, "elapsed_time": "0:55:35", "remaining_time": "0:15:45", "throughput": "1474.73", "total_tokens": 4919392} -{"current_steps": 301, "total_steps": 385, "loss": 0.0454, "learning_rate": 2.5083333333333336e-06, "epoch": 3.8713826366559485, "percentage": 78.18, "elapsed_time": "0:55:46", "remaining_time": "0:15:34", "throughput": "1474.68", "total_tokens": 4935648} -{"current_steps": 302, "total_steps": 385, "loss": 0.022, "learning_rate": 2.5166666666666666e-06, "epoch": 3.884244372990354, "percentage": 78.44, "elapsed_time": "0:55:58", "remaining_time": "0:15:22", "throughput": "1474.90", "total_tokens": 4952768} -{"current_steps": 303, "total_steps": 385, "loss": 0.0357, "learning_rate": 2.5250000000000004e-06, "epoch": 3.897106109324759, "percentage": 78.7, "elapsed_time": "0:56:09", "remaining_time": "0:15:11", "throughput": "1474.97", "total_tokens": 4969408} -{"current_steps": 304, "total_steps": 385, "loss": 0.0458, "learning_rate": 2.5333333333333338e-06, "epoch": 3.909967845659164, "percentage": 78.96, "elapsed_time": "0:56:20", "remaining_time": "0:15:00", "throughput": "1475.20", "total_tokens": 4986592} -{"current_steps": 305, "total_steps": 385, "loss": 0.0454, "learning_rate": 2.5416666666666668e-06, "epoch": 3.922829581993569, "percentage": 79.22, "elapsed_time": "0:56:31", "remaining_time": "0:14:49", "throughput": "1475.13", "total_tokens": 5002720} -{"current_steps": 306, "total_steps": 385, "loss": 0.0262, "learning_rate": 2.55e-06, "epoch": 3.935691318327974, "percentage": 79.48, "elapsed_time": "0:56:42", "remaining_time": "0:14:38", "throughput": "1475.05", "total_tokens": 5018848} -{"current_steps": 307, "total_steps": 385, "loss": 0.0234, "learning_rate": 2.558333333333334e-06, "epoch": 3.9485530546623795, "percentage": 79.74, "elapsed_time": "0:56:53", "remaining_time": "0:14:27", "throughput": "1474.86", "total_tokens": 5034528} -{"current_steps": 308, "total_steps": 385, "loss": 0.0366, "learning_rate": 2.566666666666667e-06, "epoch": 3.9614147909967845, "percentage": 80.0, "elapsed_time": "0:57:04", "remaining_time": "0:14:16", "throughput": "1474.97", "total_tokens": 5051328} -{"current_steps": 309, "total_steps": 385, "loss": 0.0236, "learning_rate": 2.5750000000000003e-06, "epoch": 3.97427652733119, "percentage": 80.26, "elapsed_time": "0:57:15", "remaining_time": "0:14:05", "throughput": "1474.97", "total_tokens": 5067712} -{"current_steps": 310, "total_steps": 385, "loss": 0.0403, "learning_rate": 2.5833333333333337e-06, "epoch": 3.987138263665595, "percentage": 80.52, "elapsed_time": "0:57:26", "remaining_time": "0:13:53", "throughput": "1475.24", "total_tokens": 5085088} -{"current_steps": 311, "total_steps": 385, "loss": 0.0395, "learning_rate": 2.5916666666666667e-06, "epoch": 4.0, "percentage": 80.78, "elapsed_time": "0:57:38", "remaining_time": "0:13:42", "throughput": "1475.24", "total_tokens": 5101536} -{"current_steps": 312, "total_steps": 385, "loss": 0.0163, "learning_rate": 2.6e-06, "epoch": 4.012861736334405, "percentage": 81.04, "elapsed_time": "0:57:49", "remaining_time": "0:13:31", "throughput": "1475.19", "total_tokens": 5117696} -{"current_steps": 313, "total_steps": 385, "loss": 0.0181, "learning_rate": 2.608333333333333e-06, "epoch": 4.02572347266881, "percentage": 81.3, "elapsed_time": "0:58:00", "remaining_time": "0:13:20", "throughput": "1475.00", "total_tokens": 5133408} -{"current_steps": 314, "total_steps": 385, "loss": 0.013, "learning_rate": 2.616666666666667e-06, "epoch": 4.038585209003215, "percentage": 81.56, "elapsed_time": "0:58:11", "remaining_time": "0:13:09", "throughput": "1474.96", "total_tokens": 5149664} -{"current_steps": 315, "total_steps": 385, "loss": 0.0178, "learning_rate": 2.6250000000000003e-06, "epoch": 4.051446945337621, "percentage": 81.82, "elapsed_time": "0:58:22", "remaining_time": "0:12:58", "throughput": "1474.78", "total_tokens": 5165344} -{"current_steps": 316, "total_steps": 385, "loss": 0.0153, "learning_rate": 2.6333333333333332e-06, "epoch": 4.064308681672026, "percentage": 82.08, "elapsed_time": "0:58:33", "remaining_time": "0:12:47", "throughput": "1475.20", "total_tokens": 5183264} -{"current_steps": 317, "total_steps": 385, "loss": 0.0205, "learning_rate": 2.6416666666666666e-06, "epoch": 4.077170418006431, "percentage": 82.34, "elapsed_time": "0:58:44", "remaining_time": "0:12:36", "throughput": "1475.09", "total_tokens": 5199296} -{"current_steps": 318, "total_steps": 385, "loss": 0.0021, "learning_rate": 2.6500000000000005e-06, "epoch": 4.090032154340836, "percentage": 82.6, "elapsed_time": "0:58:55", "remaining_time": "0:12:24", "throughput": "1475.17", "total_tokens": 5216032} -{"current_steps": 319, "total_steps": 385, "loss": 0.022, "learning_rate": 2.6583333333333334e-06, "epoch": 4.102893890675241, "percentage": 82.86, "elapsed_time": "0:59:07", "remaining_time": "0:12:13", "throughput": "1475.20", "total_tokens": 5232544} -{"current_steps": 320, "total_steps": 385, "loss": 0.0134, "learning_rate": 2.666666666666667e-06, "epoch": 4.115755627009646, "percentage": 83.12, "elapsed_time": "0:59:18", "remaining_time": "0:12:02", "throughput": "1475.14", "total_tokens": 5248704} -{"current_steps": 321, "total_steps": 385, "loss": 0.0175, "learning_rate": 2.6750000000000002e-06, "epoch": 4.128617363344051, "percentage": 83.38, "elapsed_time": "0:59:29", "remaining_time": "0:11:51", "throughput": "1474.95", "total_tokens": 5264384} -{"current_steps": 322, "total_steps": 385, "loss": 0.023, "learning_rate": 2.683333333333333e-06, "epoch": 4.141479099678457, "percentage": 83.64, "elapsed_time": "0:59:40", "remaining_time": "0:11:40", "throughput": "1474.98", "total_tokens": 5280928} -{"current_steps": 323, "total_steps": 385, "loss": 0.0303, "learning_rate": 2.691666666666667e-06, "epoch": 4.154340836012862, "percentage": 83.9, "elapsed_time": "0:59:51", "remaining_time": "0:11:29", "throughput": "1474.77", "total_tokens": 5296512} -{"current_steps": 324, "total_steps": 385, "loss": 0.0187, "learning_rate": 2.7000000000000004e-06, "epoch": 4.167202572347267, "percentage": 84.16, "elapsed_time": "1:00:02", "remaining_time": "0:11:18", "throughput": "1474.91", "total_tokens": 5313440} -{"current_steps": 325, "total_steps": 385, "loss": 0.0126, "learning_rate": 2.7083333333333334e-06, "epoch": 4.180064308681672, "percentage": 84.42, "elapsed_time": "1:00:13", "remaining_time": "0:11:07", "throughput": "1474.71", "total_tokens": 5329088} -{"current_steps": 326, "total_steps": 385, "loss": 0.0203, "learning_rate": 2.7166666666666668e-06, "epoch": 4.192926045016077, "percentage": 84.68, "elapsed_time": "1:00:24", "remaining_time": "0:10:56", "throughput": "1474.67", "total_tokens": 5345376} -{"current_steps": 327, "total_steps": 385, "loss": 0.0078, "learning_rate": 2.7250000000000006e-06, "epoch": 4.205787781350482, "percentage": 84.94, "elapsed_time": "1:00:35", "remaining_time": "0:10:44", "throughput": "1474.62", "total_tokens": 5361568} -{"current_steps": 328, "total_steps": 385, "loss": 0.0165, "learning_rate": 2.7333333333333336e-06, "epoch": 4.218649517684887, "percentage": 85.19, "elapsed_time": "1:00:47", "remaining_time": "0:10:33", "throughput": "1474.50", "total_tokens": 5377536} -{"current_steps": 329, "total_steps": 385, "loss": 0.0113, "learning_rate": 2.741666666666667e-06, "epoch": 4.231511254019293, "percentage": 85.45, "elapsed_time": "1:00:58", "remaining_time": "0:10:22", "throughput": "1474.78", "total_tokens": 5395040} -{"current_steps": 330, "total_steps": 385, "loss": 0.0058, "learning_rate": 2.7500000000000004e-06, "epoch": 4.244372990353698, "percentage": 85.71, "elapsed_time": "1:01:09", "remaining_time": "0:10:11", "throughput": "1474.81", "total_tokens": 5411488} -{"current_steps": 331, "total_steps": 385, "loss": 0.007, "learning_rate": 2.7583333333333333e-06, "epoch": 4.257234726688103, "percentage": 85.97, "elapsed_time": "1:01:20", "remaining_time": "0:10:00", "throughput": "1474.67", "total_tokens": 5427328} -{"current_steps": 332, "total_steps": 385, "loss": 0.027, "learning_rate": 2.766666666666667e-06, "epoch": 4.270096463022508, "percentage": 86.23, "elapsed_time": "1:01:31", "remaining_time": "0:09:49", "throughput": "1474.84", "total_tokens": 5444352} -{"current_steps": 333, "total_steps": 385, "loss": 0.0276, "learning_rate": 2.7750000000000005e-06, "epoch": 4.282958199356913, "percentage": 86.49, "elapsed_time": "1:01:42", "remaining_time": "0:09:38", "throughput": "1474.61", "total_tokens": 5459840} -{"current_steps": 334, "total_steps": 385, "loss": 0.0367, "learning_rate": 2.7833333333333335e-06, "epoch": 4.295819935691318, "percentage": 86.75, "elapsed_time": "1:01:53", "remaining_time": "0:09:27", "throughput": "1474.55", "total_tokens": 5476000} -{"current_steps": 335, "total_steps": 385, "loss": 0.0161, "learning_rate": 2.791666666666667e-06, "epoch": 4.308681672025724, "percentage": 87.01, "elapsed_time": "1:02:04", "remaining_time": "0:09:15", "throughput": "1474.44", "total_tokens": 5491968} -{"current_steps": 336, "total_steps": 385, "loss": 0.018, "learning_rate": 2.8000000000000003e-06, "epoch": 4.321543408360129, "percentage": 87.27, "elapsed_time": "1:02:15", "remaining_time": "0:09:04", "throughput": "1474.57", "total_tokens": 5508864} -{"current_steps": 337, "total_steps": 385, "loss": 0.0044, "learning_rate": 2.8083333333333333e-06, "epoch": 4.334405144694534, "percentage": 87.53, "elapsed_time": "1:02:27", "remaining_time": "0:08:53", "throughput": "1474.64", "total_tokens": 5525536} -{"current_steps": 338, "total_steps": 385, "loss": 0.0109, "learning_rate": 2.816666666666667e-06, "epoch": 4.347266881028939, "percentage": 87.79, "elapsed_time": "1:02:38", "remaining_time": "0:08:42", "throughput": "1474.75", "total_tokens": 5542368} -{"current_steps": 339, "total_steps": 385, "loss": 0.0173, "learning_rate": 2.825e-06, "epoch": 4.360128617363344, "percentage": 88.05, "elapsed_time": "1:02:49", "remaining_time": "0:08:31", "throughput": "1474.67", "total_tokens": 5558400} -{"current_steps": 340, "total_steps": 385, "loss": 0.0107, "learning_rate": 2.8333333333333335e-06, "epoch": 4.372990353697749, "percentage": 88.31, "elapsed_time": "1:03:00", "remaining_time": "0:08:20", "throughput": "1474.70", "total_tokens": 5575008} -{"current_steps": 341, "total_steps": 385, "loss": 0.0116, "learning_rate": 2.841666666666667e-06, "epoch": 4.385852090032154, "percentage": 88.57, "elapsed_time": "1:03:11", "remaining_time": "0:08:09", "throughput": "1474.55", "total_tokens": 5590784} -{"current_steps": 342, "total_steps": 385, "loss": 0.0281, "learning_rate": 2.85e-06, "epoch": 4.39871382636656, "percentage": 88.83, "elapsed_time": "1:03:22", "remaining_time": "0:07:58", "throughput": "1474.78", "total_tokens": 5608032} -{"current_steps": 343, "total_steps": 385, "loss": 0.0246, "learning_rate": 2.8583333333333336e-06, "epoch": 4.411575562700965, "percentage": 89.09, "elapsed_time": "1:03:33", "remaining_time": "0:07:46", "throughput": "1474.86", "total_tokens": 5624704} -{"current_steps": 344, "total_steps": 385, "loss": 0.0146, "learning_rate": 2.866666666666667e-06, "epoch": 4.42443729903537, "percentage": 89.35, "elapsed_time": "1:03:44", "remaining_time": "0:07:35", "throughput": "1474.84", "total_tokens": 5641056} -{"current_steps": 345, "total_steps": 385, "loss": 0.0439, "learning_rate": 2.875e-06, "epoch": 4.437299035369775, "percentage": 89.61, "elapsed_time": "1:03:55", "remaining_time": "0:07:24", "throughput": "1474.62", "total_tokens": 5656608} -{"current_steps": 346, "total_steps": 385, "loss": 0.0279, "learning_rate": 2.8833333333333334e-06, "epoch": 4.45016077170418, "percentage": 89.87, "elapsed_time": "1:04:07", "remaining_time": "0:07:13", "throughput": "1474.60", "total_tokens": 5672928} -{"current_steps": 347, "total_steps": 385, "loss": 0.0276, "learning_rate": 2.8916666666666672e-06, "epoch": 4.463022508038585, "percentage": 90.13, "elapsed_time": "1:04:18", "remaining_time": "0:07:02", "throughput": "1474.70", "total_tokens": 5689728} -{"current_steps": 348, "total_steps": 385, "loss": 0.0167, "learning_rate": 2.9e-06, "epoch": 4.47588424437299, "percentage": 90.39, "elapsed_time": "1:04:29", "remaining_time": "0:06:51", "throughput": "1474.63", "total_tokens": 5705824} -{"current_steps": 349, "total_steps": 385, "loss": 0.0258, "learning_rate": 2.9083333333333336e-06, "epoch": 4.488745980707396, "percentage": 90.65, "elapsed_time": "1:04:40", "remaining_time": "0:06:40", "throughput": "1474.83", "total_tokens": 5723008} -{"current_steps": 350, "total_steps": 385, "loss": 0.0306, "learning_rate": 2.916666666666667e-06, "epoch": 4.501607717041801, "percentage": 90.91, "elapsed_time": "1:04:51", "remaining_time": "0:06:29", "throughput": "1474.91", "total_tokens": 5739680} -{"current_steps": 351, "total_steps": 385, "loss": 0.0395, "learning_rate": 2.925e-06, "epoch": 4.514469453376206, "percentage": 91.17, "elapsed_time": "1:05:02", "remaining_time": "0:06:18", "throughput": "1475.01", "total_tokens": 5756480} -{"current_steps": 352, "total_steps": 385, "loss": 0.0203, "learning_rate": 2.9333333333333338e-06, "epoch": 4.527331189710611, "percentage": 91.43, "elapsed_time": "1:05:13", "remaining_time": "0:06:06", "throughput": "1475.06", "total_tokens": 5773088} -{"current_steps": 353, "total_steps": 385, "loss": 0.0241, "learning_rate": 2.941666666666667e-06, "epoch": 4.540192926045016, "percentage": 91.69, "elapsed_time": "1:05:24", "remaining_time": "0:05:55", "throughput": "1475.01", "total_tokens": 5789312} -{"current_steps": 354, "total_steps": 385, "loss": 0.0151, "learning_rate": 2.95e-06, "epoch": 4.553054662379421, "percentage": 91.95, "elapsed_time": "1:05:36", "remaining_time": "0:05:44", "throughput": "1474.68", "total_tokens": 5804352} -{"current_steps": 355, "total_steps": 385, "loss": 0.0355, "learning_rate": 2.9583333333333335e-06, "epoch": 4.565916398713826, "percentage": 92.21, "elapsed_time": "1:05:47", "remaining_time": "0:05:33", "throughput": "1474.59", "total_tokens": 5820384} -{"current_steps": 356, "total_steps": 385, "loss": 0.0093, "learning_rate": 2.9666666666666673e-06, "epoch": 4.578778135048232, "percentage": 92.47, "elapsed_time": "1:05:58", "remaining_time": "0:05:22", "throughput": "1474.72", "total_tokens": 5837280} -{"current_steps": 357, "total_steps": 385, "loss": 0.0314, "learning_rate": 2.9750000000000003e-06, "epoch": 4.591639871382637, "percentage": 92.73, "elapsed_time": "1:06:09", "remaining_time": "0:05:11", "throughput": "1474.75", "total_tokens": 5853760} -{"current_steps": 358, "total_steps": 385, "loss": 0.0155, "learning_rate": 2.9833333333333337e-06, "epoch": 4.604501607717042, "percentage": 92.99, "elapsed_time": "1:06:20", "remaining_time": "0:05:00", "throughput": "1474.77", "total_tokens": 5870240} -{"current_steps": 359, "total_steps": 385, "loss": 0.0138, "learning_rate": 2.991666666666667e-06, "epoch": 4.617363344051447, "percentage": 93.25, "elapsed_time": "1:06:31", "remaining_time": "0:04:49", "throughput": "1474.94", "total_tokens": 5887296} -{"current_steps": 360, "total_steps": 385, "loss": 0.0212, "learning_rate": 3e-06, "epoch": 4.630225080385852, "percentage": 93.51, "elapsed_time": "1:06:42", "remaining_time": "0:04:37", "throughput": "1475.10", "total_tokens": 5904384} -{"current_steps": 361, "total_steps": 385, "loss": 0.0255, "learning_rate": 3.0083333333333335e-06, "epoch": 4.643086816720257, "percentage": 93.77, "elapsed_time": "1:06:53", "remaining_time": "0:04:26", "throughput": "1475.11", "total_tokens": 5920832} -{"current_steps": 362, "total_steps": 385, "loss": 0.0231, "learning_rate": 3.0166666666666673e-06, "epoch": 4.655948553054662, "percentage": 94.03, "elapsed_time": "1:07:04", "remaining_time": "0:04:15", "throughput": "1474.99", "total_tokens": 5936736} -{"current_steps": 363, "total_steps": 385, "loss": 0.0083, "learning_rate": 3.0250000000000003e-06, "epoch": 4.668810289389068, "percentage": 94.29, "elapsed_time": "1:07:16", "remaining_time": "0:04:04", "throughput": "1474.99", "total_tokens": 5953120} -{"current_steps": 364, "total_steps": 385, "loss": 0.0122, "learning_rate": 3.0333333333333337e-06, "epoch": 4.681672025723473, "percentage": 94.55, "elapsed_time": "1:07:27", "remaining_time": "0:03:53", "throughput": "1475.18", "total_tokens": 5970336} -{"current_steps": 365, "total_steps": 385, "loss": 0.0142, "learning_rate": 3.0416666666666666e-06, "epoch": 4.694533762057878, "percentage": 94.81, "elapsed_time": "1:07:38", "remaining_time": "0:03:42", "throughput": "1475.37", "total_tokens": 5987488} -{"current_steps": 366, "total_steps": 385, "loss": 0.0293, "learning_rate": 3.05e-06, "epoch": 4.707395498392283, "percentage": 95.06, "elapsed_time": "1:07:49", "remaining_time": "0:03:31", "throughput": "1475.24", "total_tokens": 6003296} -{"current_steps": 367, "total_steps": 385, "loss": 0.0292, "learning_rate": 3.058333333333334e-06, "epoch": 4.720257234726688, "percentage": 95.32, "elapsed_time": "1:08:00", "remaining_time": "0:03:20", "throughput": "1475.50", "total_tokens": 6020768} -{"current_steps": 368, "total_steps": 385, "loss": 0.032, "learning_rate": 3.066666666666667e-06, "epoch": 4.733118971061093, "percentage": 95.58, "elapsed_time": "1:08:11", "remaining_time": "0:03:09", "throughput": "1475.46", "total_tokens": 6036992} -{"current_steps": 369, "total_steps": 385, "loss": 0.0189, "learning_rate": 3.075e-06, "epoch": 4.745980707395498, "percentage": 95.84, "elapsed_time": "1:08:22", "remaining_time": "0:02:57", "throughput": "1475.50", "total_tokens": 6053568} -{"current_steps": 370, "total_steps": 385, "loss": 0.022, "learning_rate": 3.0833333333333336e-06, "epoch": 4.758842443729904, "percentage": 96.1, "elapsed_time": "1:08:33", "remaining_time": "0:02:46", "throughput": "1475.57", "total_tokens": 6070336} -{"current_steps": 371, "total_steps": 385, "loss": 0.0242, "learning_rate": 3.0916666666666666e-06, "epoch": 4.771704180064309, "percentage": 96.36, "elapsed_time": "1:08:45", "remaining_time": "0:02:35", "throughput": "1475.68", "total_tokens": 6087200} -{"current_steps": 372, "total_steps": 385, "loss": 0.015, "learning_rate": 3.1000000000000004e-06, "epoch": 4.784565916398714, "percentage": 96.62, "elapsed_time": "1:08:56", "remaining_time": "0:02:24", "throughput": "1475.82", "total_tokens": 6104224} -{"current_steps": 373, "total_steps": 385, "loss": 0.0154, "learning_rate": 3.1083333333333338e-06, "epoch": 4.797427652733119, "percentage": 96.88, "elapsed_time": "1:09:07", "remaining_time": "0:02:13", "throughput": "1475.81", "total_tokens": 6120576} -{"current_steps": 374, "total_steps": 385, "loss": 0.0195, "learning_rate": 3.1166666666666668e-06, "epoch": 4.810289389067524, "percentage": 97.14, "elapsed_time": "1:09:18", "remaining_time": "0:02:02", "throughput": "1475.92", "total_tokens": 6137440} -{"current_steps": 375, "total_steps": 385, "loss": 0.031, "learning_rate": 3.125e-06, "epoch": 4.823151125401929, "percentage": 97.4, "elapsed_time": "1:09:29", "remaining_time": "0:01:51", "throughput": "1476.19", "total_tokens": 6154976} -{"current_steps": 376, "total_steps": 385, "loss": 0.0376, "learning_rate": 3.133333333333334e-06, "epoch": 4.836012861736334, "percentage": 97.66, "elapsed_time": "1:09:40", "remaining_time": "0:01:40", "throughput": "1476.09", "total_tokens": 6170912} -{"current_steps": 377, "total_steps": 385, "loss": 0.0093, "learning_rate": 3.141666666666667e-06, "epoch": 4.84887459807074, "percentage": 97.92, "elapsed_time": "1:09:51", "remaining_time": "0:01:28", "throughput": "1476.24", "total_tokens": 6187968} -{"current_steps": 378, "total_steps": 385, "loss": 0.027, "learning_rate": 3.1500000000000003e-06, "epoch": 4.861736334405145, "percentage": 98.18, "elapsed_time": "1:10:02", "remaining_time": "0:01:17", "throughput": "1476.22", "total_tokens": 6204320} -{"current_steps": 379, "total_steps": 385, "loss": 0.0191, "learning_rate": 3.1583333333333337e-06, "epoch": 4.87459807073955, "percentage": 98.44, "elapsed_time": "1:10:13", "remaining_time": "0:01:06", "throughput": "1476.16", "total_tokens": 6220512} -{"current_steps": 380, "total_steps": 385, "loss": 0.0132, "learning_rate": 3.1666666666666667e-06, "epoch": 4.887459807073955, "percentage": 98.7, "elapsed_time": "1:10:25", "remaining_time": "0:00:55", "throughput": "1476.06", "total_tokens": 6236512} -{"current_steps": 381, "total_steps": 385, "loss": 0.0111, "learning_rate": 3.175e-06, "epoch": 4.90032154340836, "percentage": 98.96, "elapsed_time": "1:10:36", "remaining_time": "0:00:44", "throughput": "1475.94", "total_tokens": 6252416} -{"current_steps": 382, "total_steps": 385, "loss": 0.0145, "learning_rate": 3.183333333333334e-06, "epoch": 4.913183279742765, "percentage": 99.22, "elapsed_time": "1:10:47", "remaining_time": "0:00:33", "throughput": "1475.98", "total_tokens": 6268992} -{"current_steps": 383, "total_steps": 385, "loss": 0.0082, "learning_rate": 3.191666666666667e-06, "epoch": 4.92604501607717, "percentage": 99.48, "elapsed_time": "1:10:58", "remaining_time": "0:00:22", "throughput": "1475.97", "total_tokens": 6285312} -{"current_steps": 384, "total_steps": 385, "loss": 0.0165, "learning_rate": 3.2000000000000003e-06, "epoch": 4.938906752411576, "percentage": 99.74, "elapsed_time": "1:11:09", "remaining_time": "0:00:11", "throughput": "1475.81", "total_tokens": 6300992} -{"current_steps": 385, "total_steps": 385, "loss": 0.0243, "learning_rate": 3.2083333333333337e-06, "epoch": 4.951768488745981, "percentage": 100.0, "elapsed_time": "1:11:20", "remaining_time": "0:00:00", "throughput": "1476.08", "total_tokens": 6318560} -{"current_steps": 385, "total_steps": 385, "epoch": 4.951768488745981, "percentage": 100.0, "elapsed_time": "1:12:11", "remaining_time": "0:00:00", "throughput": "1458.88", "total_tokens": 6318560} +{"current_steps": 5, "total_steps": 160, "percentage": 3.12, "elapsed_time": "0:00:00", "remaining_time": "0:00:12"} +{"current_steps": 10, "total_steps": 160, "percentage": 6.25, "elapsed_time": "0:00:00", "remaining_time": "0:00:13"} +{"current_steps": 15, "total_steps": 160, "percentage": 9.38, "elapsed_time": "0:00:01", "remaining_time": "0:00:13"} +{"current_steps": 20, "total_steps": 160, "percentage": 12.5, "elapsed_time": "0:00:01", "remaining_time": "0:00:12"} +{"current_steps": 25, "total_steps": 160, "percentage": 15.62, "elapsed_time": "0:00:02", "remaining_time": "0:00:12"} +{"current_steps": 30, "total_steps": 160, "percentage": 18.75, "elapsed_time": "0:00:02", "remaining_time": "0:00:12"} +{"current_steps": 35, "total_steps": 160, "percentage": 21.88, "elapsed_time": "0:00:03", "remaining_time": "0:00:11"} +{"current_steps": 40, "total_steps": 160, "percentage": 25.0, "elapsed_time": "0:00:03", "remaining_time": "0:00:11"} +{"current_steps": 45, "total_steps": 160, "percentage": 28.12, "elapsed_time": "0:00:04", "remaining_time": "0:00:10"} +{"current_steps": 50, "total_steps": 160, "percentage": 31.25, "elapsed_time": "0:00:04", "remaining_time": "0:00:10"} +{"current_steps": 55, "total_steps": 160, "percentage": 34.38, "elapsed_time": "0:00:05", "remaining_time": "0:00:09"} +{"current_steps": 60, "total_steps": 160, "percentage": 37.5, "elapsed_time": "0:00:05", "remaining_time": "0:00:09"} +{"current_steps": 65, "total_steps": 160, "percentage": 40.62, "elapsed_time": "0:00:06", "remaining_time": "0:00:08"} +{"current_steps": 70, "total_steps": 160, "percentage": 43.75, "elapsed_time": "0:00:06", "remaining_time": "0:00:08"} +{"current_steps": 75, "total_steps": 160, "percentage": 46.88, "elapsed_time": "0:00:07", "remaining_time": "0:00:07"} +{"current_steps": 80, "total_steps": 160, "percentage": 50.0, "elapsed_time": "0:00:07", "remaining_time": "0:00:07"} +{"current_steps": 85, "total_steps": 160, "percentage": 53.12, "elapsed_time": "0:00:08", "remaining_time": "0:00:07"} +{"current_steps": 90, "total_steps": 160, "percentage": 56.25, "elapsed_time": "0:00:08", "remaining_time": "0:00:06"} +{"current_steps": 95, "total_steps": 160, "percentage": 59.38, "elapsed_time": "0:00:08", "remaining_time": "0:00:06"} +{"current_steps": 100, "total_steps": 160, "percentage": 62.5, "elapsed_time": "0:00:09", "remaining_time": "0:00:05"} +{"current_steps": 105, "total_steps": 160, "percentage": 65.62, "elapsed_time": "0:00:09", "remaining_time": "0:00:05"} +{"current_steps": 110, "total_steps": 160, "percentage": 68.75, "elapsed_time": "0:00:10", "remaining_time": "0:00:04"} +{"current_steps": 115, "total_steps": 160, "percentage": 71.88, "elapsed_time": "0:00:10", "remaining_time": "0:00:04"} +{"current_steps": 120, "total_steps": 160, "percentage": 75.0, "elapsed_time": "0:00:11", "remaining_time": "0:00:03"} +{"current_steps": 125, "total_steps": 160, "percentage": 78.12, "elapsed_time": "0:00:11", "remaining_time": "0:00:03"} +{"current_steps": 130, "total_steps": 160, "percentage": 81.25, "elapsed_time": "0:00:12", "remaining_time": "0:00:02"} +{"current_steps": 135, "total_steps": 160, "percentage": 84.38, "elapsed_time": "0:00:12", "remaining_time": "0:00:02"} +{"current_steps": 140, "total_steps": 160, "percentage": 87.5, "elapsed_time": "0:00:13", "remaining_time": "0:00:01"} +{"current_steps": 145, "total_steps": 160, "percentage": 90.62, "elapsed_time": "0:00:13", "remaining_time": "0:00:01"} +{"current_steps": 150, "total_steps": 160, "percentage": 93.75, "elapsed_time": "0:00:14", "remaining_time": "0:00:00"} +{"current_steps": 155, "total_steps": 160, "percentage": 96.88, "elapsed_time": "0:00:14", "remaining_time": "0:00:00"} +{"current_steps": 160, "total_steps": 160, "percentage": 100.0, "elapsed_time": "0:00:15", "remaining_time": "0:00:00"}