| {"current_steps": 1, "total_steps": 295, "loss": 1.9672, "lr": 1.9999432949662483e-05, "epoch": 0.016736401673640166, "percentage": 0.34, "elapsed_time": "0:00:55", "remaining_time": "4:30:17", "throughput": 9504.47, "total_tokens": 524288} | |
| {"current_steps": 2, "total_steps": 295, "loss": 1.7966, "lr": 1.9997731862959143e-05, "epoch": 0.03347280334728033, "percentage": 0.68, "elapsed_time": "0:01:47", "remaining_time": "4:23:41", "throughput": 9709.29, "total_tokens": 1048576} | |
| {"current_steps": 3, "total_steps": 295, "loss": 1.7334, "lr": 1.999489693281034e-05, "epoch": 0.0502092050209205, "percentage": 1.02, "elapsed_time": "0:02:40", "remaining_time": "4:19:46", "throughput": 9822.06, "total_tokens": 1572864} | |
| {"current_steps": 4, "total_steps": 295, "loss": 1.3503, "lr": 1.9990928480725694e-05, "epoch": 0.06694560669456066, "percentage": 1.36, "elapsed_time": "0:03:32", "remaining_time": "4:17:33", "throughput": 9872.49, "total_tokens": 2097152} | |
| {"current_steps": 5, "total_steps": 295, "loss": 1.3152, "lr": 1.998582695676762e-05, "epoch": 0.08368200836820083, "percentage": 1.69, "elapsed_time": "0:04:24", "remaining_time": "4:15:48", "throughput": 9906.17, "total_tokens": 2621440} | |
| {"current_steps": 6, "total_steps": 295, "loss": 1.2668, "lr": 1.99795929395003e-05, "epoch": 0.100418410041841, "percentage": 2.03, "elapsed_time": "0:05:16", "remaining_time": "4:14:17", "throughput": 9930.97, "total_tokens": 3145728} | |
| {"current_steps": 7, "total_steps": 295, "loss": 1.1997, "lr": 1.997222713592405e-05, "epoch": 0.11715481171548117, "percentage": 2.37, "elapsed_time": "0:06:09", "remaining_time": "4:13:06", "throughput": 9943.02, "total_tokens": 3670016} | |
| {"current_steps": 8, "total_steps": 295, "loss": 1.1487, "lr": 1.9963730381395154e-05, "epoch": 0.13389121338912133, "percentage": 2.71, "elapsed_time": "0:07:01", "remaining_time": "4:11:56", "throughput": 9953.84, "total_tokens": 4194304} | |
| {"current_steps": 9, "total_steps": 295, "loss": 1.133, "lr": 1.9954103639531116e-05, "epoch": 0.1506276150627615, "percentage": 3.05, "elapsed_time": "0:07:53", "remaining_time": "4:10:49", "throughput": 9963.37, "total_tokens": 4718592} | |
| {"current_steps": 10, "total_steps": 295, "loss": 1.0892, "lr": 1.9943348002101374e-05, "epoch": 0.16736401673640167, "percentage": 3.39, "elapsed_time": "0:08:45", "remaining_time": "4:09:44", "throughput": 9971.51, "total_tokens": 5242880} | |
| {"current_steps": 11, "total_steps": 295, "loss": 1.1456, "lr": 1.9931464688903502e-05, "epoch": 0.18410041841004185, "percentage": 3.73, "elapsed_time": "0:09:37", "remaining_time": "4:08:42", "throughput": 9977.97, "total_tokens": 5767168} | |
| {"current_steps": 12, "total_steps": 295, "loss": 1.0797, "lr": 1.9918455047624847e-05, "epoch": 0.200836820083682, "percentage": 4.07, "elapsed_time": "0:10:30", "remaining_time": "4:07:42", "throughput": 9982.94, "total_tokens": 6291456} | |
| {"current_steps": 1, "total_steps": 295, "loss": 1.9261, "lr": 1.9999432949662483e-05, "epoch": 0.016736401673640166, "percentage": 0.34, "elapsed_time": "0:00:54", "remaining_time": "4:28:43", "throughput": 9559.74, "total_tokens": 524288} | |
| {"current_steps": 2, "total_steps": 295, "loss": 2.1533, "lr": 1.9997731862959143e-05, "epoch": 0.03347280334728033, "percentage": 0.68, "elapsed_time": "0:01:47", "remaining_time": "4:22:18", "throughput": 9760.83, "total_tokens": 1048576} | |
| {"current_steps": 3, "total_steps": 295, "loss": 1.8457, "lr": 1.999489693281034e-05, "epoch": 0.0502092050209205, "percentage": 1.02, "elapsed_time": "0:02:39", "remaining_time": "4:18:56", "throughput": 9853.54, "total_tokens": 1572864} | |
| {"current_steps": 4, "total_steps": 295, "loss": 1.6327, "lr": 1.9990928480725694e-05, "epoch": 0.06694560669456066, "percentage": 1.36, "elapsed_time": "0:03:31", "remaining_time": "4:16:49", "throughput": 9900.64, "total_tokens": 2097152} | |
| {"current_steps": 5, "total_steps": 295, "loss": 1.5825, "lr": 1.998582695676762e-05, "epoch": 0.08368200836820083, "percentage": 1.69, "elapsed_time": "0:04:23", "remaining_time": "4:15:09", "throughput": 9931.51, "total_tokens": 2621440} | |
| {"current_steps": 6, "total_steps": 295, "loss": 1.5141, "lr": 1.99795929395003e-05, "epoch": 0.100418410041841, "percentage": 2.03, "elapsed_time": "0:05:15", "remaining_time": "4:13:38", "throughput": 9956.13, "total_tokens": 3145728} | |
| {"current_steps": 7, "total_steps": 295, "loss": 1.457, "lr": 1.997222713592405e-05, "epoch": 0.11715481171548117, "percentage": 2.37, "elapsed_time": "0:06:08", "remaining_time": "4:12:23", "throughput": 9971.18, "total_tokens": 3670016} | |
| {"current_steps": 8, "total_steps": 295, "loss": 1.424, "lr": 1.9963730381395154e-05, "epoch": 0.13389121338912133, "percentage": 2.71, "elapsed_time": "0:07:00", "remaining_time": "4:11:17", "throughput": 9979.57, "total_tokens": 4194304} | |
| {"current_steps": 9, "total_steps": 295, "loss": 1.3584, "lr": 1.9954103639531116e-05, "epoch": 0.1506276150627615, "percentage": 3.05, "elapsed_time": "0:07:52", "remaining_time": "4:10:10", "throughput": 9989.22, "total_tokens": 4718592} | |
| {"current_steps": 10, "total_steps": 295, "loss": 1.314, "lr": 1.9943348002101374e-05, "epoch": 0.16736401673640167, "percentage": 3.39, "elapsed_time": "0:08:44", "remaining_time": "4:09:09", "throughput": 9995.22, "total_tokens": 5242880} | |
| {"current_steps": 11, "total_steps": 295, "loss": 1.3626, "lr": 1.9931464688903502e-05, "epoch": 0.18410041841004185, "percentage": 3.73, "elapsed_time": "0:09:36", "remaining_time": "4:08:07", "throughput": 10001.43, "total_tokens": 5767168} | |
| {"current_steps": 12, "total_steps": 295, "loss": 1.3027, "lr": 1.9918455047624847e-05, "epoch": 0.200836820083682, "percentage": 4.07, "elapsed_time": "0:10:28", "remaining_time": "4:07:06", "throughput": 10007.37, "total_tokens": 6291456} | |
| {"current_steps": 13, "total_steps": 295, "loss": 1.2689, "lr": 1.990432055368971e-05, "epoch": 0.2175732217573222, "percentage": 4.41, "elapsed_time": "0:11:20", "remaining_time": "4:06:05", "throughput": 10013.06, "total_tokens": 6815744} | |
| {"current_steps": 14, "total_steps": 295, "loss": 1.2622, "lr": 1.9889062810092002e-05, "epoch": 0.23430962343096234, "percentage": 4.75, "elapsed_time": "0:12:12", "remaining_time": "4:05:07", "throughput": 10016.76, "total_tokens": 7340032} | |
| {"current_steps": 15, "total_steps": 295, "loss": 1.2636, "lr": 1.9872683547213446e-05, "epoch": 0.2510460251046025, "percentage": 5.08, "elapsed_time": "0:13:04", "remaining_time": "4:04:11", "throughput": 10019.58, "total_tokens": 7864320} | |
| {"current_steps": 16, "total_steps": 295, "loss": 1.2279, "lr": 1.9855184622627362e-05, "epoch": 0.26778242677824265, "percentage": 5.42, "elapsed_time": "0:13:57", "remaining_time": "4:03:15", "throughput": 10021.85, "total_tokens": 8388608} | |
| {"current_steps": 17, "total_steps": 295, "loss": 1.2161, "lr": 1.9836568020887963e-05, "epoch": 0.28451882845188287, "percentage": 5.76, "elapsed_time": "0:14:49", "remaining_time": "4:02:18", "throughput": 10025.52, "total_tokens": 8912896} | |
| {"current_steps": 18, "total_steps": 295, "loss": 1.2292, "lr": 1.9816835853305306e-05, "epoch": 0.301255230125523, "percentage": 6.1, "elapsed_time": "0:15:41", "remaining_time": "4:01:25", "throughput": 10025.87, "total_tokens": 9437184} | |
| {"current_steps": 19, "total_steps": 295, "loss": 1.1968, "lr": 1.9795990357705853e-05, "epoch": 0.3179916317991632, "percentage": 6.44, "elapsed_time": "0:16:33", "remaining_time": "4:00:31", "throughput": 10026.57, "total_tokens": 9961472} | |
| {"current_steps": 20, "total_steps": 295, "loss": 1.2131, "lr": 1.9774033898178668e-05, "epoch": 0.33472803347280333, "percentage": 6.78, "elapsed_time": "0:17:25", "remaining_time": "3:59:36", "throughput": 10028.68, "total_tokens": 10485760} | |
| {"current_steps": 21, "total_steps": 295, "loss": 1.1885, "lr": 1.9750968964807305e-05, "epoch": 0.3514644351464435, "percentage": 7.12, "elapsed_time": "0:18:17", "remaining_time": "3:58:43", "throughput": 10029.65, "total_tokens": 11010048} | |
| {"current_steps": 22, "total_steps": 295, "loss": 1.1421, "lr": 1.9726798173387417e-05, "epoch": 0.3682008368200837, "percentage": 7.46, "elapsed_time": "0:19:09", "remaining_time": "3:57:50", "throughput": 10029.96, "total_tokens": 11534336} | |
| {"current_steps": 23, "total_steps": 295, "loss": 1.1817, "lr": 1.9701524265130088e-05, "epoch": 0.38493723849372385, "percentage": 7.8, "elapsed_time": "0:20:02", "remaining_time": "3:56:56", "throughput": 10031.28, "total_tokens": 12058624} | |
| {"current_steps": 24, "total_steps": 295, "loss": 1.1543, "lr": 1.9675150106350957e-05, "epoch": 0.401673640167364, "percentage": 8.14, "elapsed_time": "0:20:54", "remaining_time": "3:56:02", "throughput": 10032.46, "total_tokens": 12582912} | |
| {"current_steps": 25, "total_steps": 295, "loss": 1.1435, "lr": 1.9647678688145163e-05, "epoch": 0.41841004184100417, "percentage": 8.47, "elapsed_time": "0:21:46", "remaining_time": "3:55:08", "throughput": 10033.21, "total_tokens": 13107200} | |
| {"current_steps": 26, "total_steps": 295, "loss": 1.1397, "lr": 1.9619113126048086e-05, "epoch": 0.4351464435146444, "percentage": 8.81, "elapsed_time": "0:22:38", "remaining_time": "3:54:15", "throughput": 10033.72, "total_tokens": 13631488} | |
| {"current_steps": 27, "total_steps": 295, "loss": 1.1226, "lr": 1.958945665968206e-05, "epoch": 0.45188284518828453, "percentage": 9.15, "elapsed_time": "0:23:30", "remaining_time": "3:53:22", "throughput": 10034.4, "total_tokens": 14155776} | |
| {"current_steps": 28, "total_steps": 295, "loss": 1.119, "lr": 1.9558712652388932e-05, "epoch": 0.4686192468619247, "percentage": 9.49, "elapsed_time": "0:24:22", "remaining_time": "3:52:29", "throughput": 10035.04, "total_tokens": 14680064} | |
| {"current_steps": 29, "total_steps": 295, "loss": 1.1163, "lr": 1.9526884590848646e-05, "epoch": 0.48535564853556484, "percentage": 9.83, "elapsed_time": "0:25:15", "remaining_time": "3:51:36", "throughput": 10035.54, "total_tokens": 15204352} | |
| {"current_steps": 30, "total_steps": 295, "loss": 1.1229, "lr": 1.9493976084683814e-05, "epoch": 0.502092050209205, "percentage": 10.17, "elapsed_time": "0:26:07", "remaining_time": "3:50:44", "throughput": 10035.52, "total_tokens": 15728640} | |
| {"current_steps": 31, "total_steps": 295, "loss": 1.1161, "lr": 1.9459990866050337e-05, "epoch": 0.5188284518828452, "percentage": 10.51, "elapsed_time": "0:26:59", "remaining_time": "3:49:51", "throughput": 10035.71, "total_tokens": 16252928} | |
| {"current_steps": 32, "total_steps": 295, "loss": 1.0928, "lr": 1.9424932789214158e-05, "epoch": 0.5355648535564853, "percentage": 10.85, "elapsed_time": "0:27:51", "remaining_time": "3:48:59", "throughput": 10035.62, "total_tokens": 16777216} | |
| {"current_steps": 33, "total_steps": 295, "loss": 1.0888, "lr": 1.9388805830114132e-05, "epoch": 0.5523012552301255, "percentage": 11.19, "elapsed_time": "0:28:43", "remaining_time": "3:48:07", "throughput": 10035.88, "total_tokens": 17301504} | |
| {"current_steps": 34, "total_steps": 295, "loss": 1.119, "lr": 1.9351614085911134e-05, "epoch": 0.5690376569037657, "percentage": 11.53, "elapsed_time": "0:29:36", "remaining_time": "3:47:14", "throughput": 10035.97, "total_tokens": 17825792} | |
| {"current_steps": 35, "total_steps": 295, "loss": 1.0641, "lr": 1.9313361774523387e-05, "epoch": 0.5857740585774058, "percentage": 11.86, "elapsed_time": "0:30:28", "remaining_time": "3:46:21", "throughput": 10036.72, "total_tokens": 18350080} | |
| {"current_steps": 36, "total_steps": 295, "loss": 1.0788, "lr": 1.92740532341481e-05, "epoch": 0.602510460251046, "percentage": 12.2, "elapsed_time": "0:31:20", "remaining_time": "3:45:28", "throughput": 10037.25, "total_tokens": 18874368} | |
| {"current_steps": 37, "total_steps": 295, "loss": 1.0845, "lr": 1.9233692922769497e-05, "epoch": 0.6192468619246861, "percentage": 12.54, "elapsed_time": "0:32:12", "remaining_time": "3:44:35", "throughput": 10037.59, "total_tokens": 19398656} | |
| {"current_steps": 38, "total_steps": 295, "loss": 1.0601, "lr": 1.9192285417653208e-05, "epoch": 0.6359832635983264, "percentage": 12.88, "elapsed_time": "0:33:04", "remaining_time": "3:43:42", "throughput": 10038.23, "total_tokens": 19922944} | |
| {"current_steps": 39, "total_steps": 295, "loss": 1.0343, "lr": 1.9149835414827193e-05, "epoch": 0.6527196652719666, "percentage": 13.22, "elapsed_time": "0:33:56", "remaining_time": "3:42:49", "throughput": 10039.05, "total_tokens": 20447232} | |
| {"current_steps": 40, "total_steps": 295, "loss": 1.0453, "lr": 1.9106347728549134e-05, "epoch": 0.6694560669456067, "percentage": 13.56, "elapsed_time": "0:34:48", "remaining_time": "3:41:57", "throughput": 10039.22, "total_tokens": 20971520} | |
| {"current_steps": 41, "total_steps": 295, "loss": 1.0442, "lr": 1.9061827290760466e-05, "epoch": 0.6861924686192469, "percentage": 13.9, "elapsed_time": "0:35:41", "remaining_time": "3:41:04", "throughput": 10039.6, "total_tokens": 21495808} | |
| {"current_steps": 42, "total_steps": 295, "loss": 1.0157, "lr": 1.9016279150527044e-05, "epoch": 0.702928870292887, "percentage": 14.24, "elapsed_time": "0:36:33", "remaining_time": "3:40:11", "throughput": 10040.28, "total_tokens": 22020096} | |
| {"current_steps": 1, "total_steps": 635, "loss": 1.9576, "lr": 1.999987761691029e-05, "epoch": 0.007858546168958742, "percentage": 0.16, "elapsed_time": "0:00:26", "remaining_time": "4:35:31", "throughput": 10053.44, "total_tokens": 262144} | |
| {"current_steps": 2, "total_steps": 635, "loss": 2.1663, "lr": 1.9999510470636677e-05, "epoch": 0.015717092337917484, "percentage": 0.31, "elapsed_time": "0:00:50", "remaining_time": "4:26:28", "throughput": 10378.5, "total_tokens": 524288} | |
| {"current_steps": 3, "total_steps": 635, "loss": 1.827, "lr": 1.9998898570165663e-05, "epoch": 0.023575638506876228, "percentage": 0.47, "elapsed_time": "0:01:14", "remaining_time": "4:22:01", "throughput": 10537.84, "total_tokens": 786432} | |
| {"current_steps": 4, "total_steps": 635, "loss": 1.6313, "lr": 1.9998041930474498e-05, "epoch": 0.03143418467583497, "percentage": 0.63, "elapsed_time": "0:01:38", "remaining_time": "4:19:27", "throughput": 10625.79, "total_tokens": 1048576} | |
| {"current_steps": 5, "total_steps": 635, "loss": 1.538, "lr": 1.999694057253083e-05, "epoch": 0.03929273084479371, "percentage": 0.79, "elapsed_time": "0:02:02", "remaining_time": "4:17:46", "throughput": 10677.7, "total_tokens": 1310720} | |
| {"current_steps": 6, "total_steps": 635, "loss": 1.5278, "lr": 1.999559452329218e-05, "epoch": 0.047151277013752456, "percentage": 0.94, "elapsed_time": "0:02:26", "remaining_time": "4:16:28", "throughput": 10715.37, "total_tokens": 1572864} | |
| {"current_steps": 7, "total_steps": 635, "loss": 1.5173, "lr": 1.999400381570527e-05, "epoch": 0.0550098231827112, "percentage": 1.1, "elapsed_time": "0:02:50", "remaining_time": "4:15:27", "throughput": 10740.57, "total_tokens": 1835008} | |
| {"current_steps": 8, "total_steps": 635, "loss": 1.4766, "lr": 1.9992168488705248e-05, "epoch": 0.06286836935166994, "percentage": 1.26, "elapsed_time": "0:03:14", "remaining_time": "4:14:33", "throughput": 10761.75, "total_tokens": 2097152} | |
| {"current_steps": 9, "total_steps": 635, "loss": 1.4497, "lr": 1.9990088587214712e-05, "epoch": 0.07072691552062868, "percentage": 1.42, "elapsed_time": "0:03:38", "remaining_time": "4:13:47", "throughput": 10776.73, "total_tokens": 2359296} | |
| {"current_steps": 10, "total_steps": 635, "loss": 1.3948, "lr": 1.9987764162142615e-05, "epoch": 0.07858546168958742, "percentage": 1.57, "elapsed_time": "0:04:02", "remaining_time": "4:13:04", "throughput": 10789.78, "total_tokens": 2621440} | |
| {"current_steps": 11, "total_steps": 635, "loss": 1.3356, "lr": 1.998519527038302e-05, "epoch": 0.08644400785854617, "percentage": 1.73, "elapsed_time": "0:04:27", "remaining_time": "4:12:27", "throughput": 10798.93, "total_tokens": 2883584} | |
| {"current_steps": 12, "total_steps": 635, "loss": 1.3478, "lr": 1.9982381974813714e-05, "epoch": 0.09430255402750491, "percentage": 1.89, "elapsed_time": "0:04:51", "remaining_time": "4:11:53", "throughput": 10806.04, "total_tokens": 3145728} | |
| {"current_steps": 13, "total_steps": 635, "loss": 1.3409, "lr": 1.9979324344294654e-05, "epoch": 0.10216110019646366, "percentage": 2.05, "elapsed_time": "0:05:15", "remaining_time": "4:11:17", "throughput": 10814.47, "total_tokens": 3407872} | |
| {"current_steps": 14, "total_steps": 635, "loss": 1.3193, "lr": 1.9976022453666293e-05, "epoch": 0.1100196463654224, "percentage": 2.2, "elapsed_time": "0:05:39", "remaining_time": "4:10:46", "throughput": 10819.51, "total_tokens": 3670016} | |
| {"current_steps": 15, "total_steps": 635, "loss": 1.2988, "lr": 1.9972476383747748e-05, "epoch": 0.11787819253438114, "percentage": 2.36, "elapsed_time": "0:06:03", "remaining_time": "4:10:12", "throughput": 10826.51, "total_tokens": 3932160} | |
| {"current_steps": 16, "total_steps": 635, "loss": 1.3077, "lr": 1.9968686221334818e-05, "epoch": 0.12573673870333987, "percentage": 2.52, "elapsed_time": "0:06:27", "remaining_time": "4:09:42", "throughput": 10830.65, "total_tokens": 4194304} | |
| {"current_steps": 17, "total_steps": 635, "loss": 1.2826, "lr": 1.9964652059197863e-05, "epoch": 0.13359528487229863, "percentage": 2.68, "elapsed_time": "0:06:51", "remaining_time": "4:09:12", "throughput": 10834.54, "total_tokens": 4456448} | |
| {"current_steps": 18, "total_steps": 635, "loss": 1.2984, "lr": 1.996037399607952e-05, "epoch": 0.14145383104125736, "percentage": 2.83, "elapsed_time": "0:07:15", "remaining_time": "4:08:43", "throughput": 10838.45, "total_tokens": 4718592} | |
| {"current_steps": 19, "total_steps": 635, "loss": 1.2384, "lr": 1.9955852136692315e-05, "epoch": 0.14931237721021612, "percentage": 2.99, "elapsed_time": "0:07:39", "remaining_time": "4:08:15", "throughput": 10841.26, "total_tokens": 4980736} | |
| {"current_steps": 20, "total_steps": 635, "loss": 1.2592, "lr": 1.995108659171607e-05, "epoch": 0.15717092337917485, "percentage": 3.15, "elapsed_time": "0:08:03", "remaining_time": "4:07:46", "throughput": 10844.54, "total_tokens": 5242880} | |
| {"current_steps": 21, "total_steps": 635, "loss": 1.2345, "lr": 1.99460774777952e-05, "epoch": 0.1650294695481336, "percentage": 3.31, "elapsed_time": "0:08:27", "remaining_time": "4:07:19", "throughput": 10846.22, "total_tokens": 5505024} | |
| {"current_steps": 22, "total_steps": 635, "loss": 1.2459, "lr": 1.9940824917535887e-05, "epoch": 0.17288801571709234, "percentage": 3.46, "elapsed_time": "0:08:51", "remaining_time": "4:06:53", "throughput": 10848.16, "total_tokens": 5767168} | |
| {"current_steps": 23, "total_steps": 635, "loss": 1.2296, "lr": 1.993532903950303e-05, "epoch": 0.1807465618860511, "percentage": 3.62, "elapsed_time": "0:09:15", "remaining_time": "4:06:26", "throughput": 10849.64, "total_tokens": 6029312} | |
| {"current_steps": 24, "total_steps": 635, "loss": 1.2143, "lr": 1.992958997821714e-05, "epoch": 0.18860510805500982, "percentage": 3.78, "elapsed_time": "0:09:39", "remaining_time": "4:06:00", "throughput": 10851.34, "total_tokens": 6291456} | |
| {"current_steps": 25, "total_steps": 635, "loss": 1.2137, "lr": 1.992360787415103e-05, "epoch": 0.19646365422396855, "percentage": 3.94, "elapsed_time": "0:10:03", "remaining_time": "4:05:34", "throughput": 10852.72, "total_tokens": 6553600} | |
| {"current_steps": 26, "total_steps": 635, "loss": 1.2058, "lr": 1.9917382873726375e-05, "epoch": 0.2043222003929273, "percentage": 4.09, "elapsed_time": "0:10:27", "remaining_time": "4:05:08", "throughput": 10853.76, "total_tokens": 6815744} | |
| {"current_steps": 27, "total_steps": 635, "loss": 1.1692, "lr": 1.991091512931013e-05, "epoch": 0.21218074656188604, "percentage": 4.25, "elapsed_time": "0:10:51", "remaining_time": "4:04:41", "throughput": 10855.76, "total_tokens": 7077888} | |
| {"current_steps": 28, "total_steps": 635, "loss": 1.1788, "lr": 1.99042047992108e-05, "epoch": 0.2200392927308448, "percentage": 4.41, "elapsed_time": "0:11:15", "remaining_time": "4:04:14", "throughput": 10858.04, "total_tokens": 7340032} | |
| {"current_steps": 29, "total_steps": 635, "loss": 1.1924, "lr": 1.989725204767458e-05, "epoch": 0.22789783889980353, "percentage": 4.57, "elapsed_time": "0:11:40", "remaining_time": "4:03:48", "throughput": 10859.47, "total_tokens": 7602176} | |
| {"current_steps": 30, "total_steps": 635, "loss": 1.1869, "lr": 1.9890057044881308e-05, "epoch": 0.2357563850687623, "percentage": 4.72, "elapsed_time": "0:12:04", "remaining_time": "4:03:21", "throughput": 10861.33, "total_tokens": 7864320} | |
| {"current_steps": 31, "total_steps": 635, "loss": 1.1845, "lr": 1.988261996694032e-05, "epoch": 0.24361493123772102, "percentage": 4.88, "elapsed_time": "0:12:28", "remaining_time": "4:02:55", "throughput": 10862.81, "total_tokens": 8126464} | |
| {"current_steps": 32, "total_steps": 635, "loss": 1.1248, "lr": 1.987494099588613e-05, "epoch": 0.25147347740667975, "percentage": 5.04, "elapsed_time": "0:12:52", "remaining_time": "4:02:29", "throughput": 10864.45, "total_tokens": 8388608} | |
| {"current_steps": 33, "total_steps": 635, "loss": 1.1716, "lr": 1.986702031967398e-05, "epoch": 0.2593320235756385, "percentage": 5.2, "elapsed_time": "0:13:16", "remaining_time": "4:02:03", "throughput": 10865.6, "total_tokens": 8650752} | |
| {"current_steps": 34, "total_steps": 635, "loss": 1.159, "lr": 1.985885813217523e-05, "epoch": 0.26719056974459726, "percentage": 5.35, "elapsed_time": "0:13:40", "remaining_time": "4:01:38", "throughput": 10866.7, "total_tokens": 8912896} | |
| {"current_steps": 35, "total_steps": 635, "loss": 1.152, "lr": 1.9850454633172632e-05, "epoch": 0.275049115913556, "percentage": 5.51, "elapsed_time": "0:14:04", "remaining_time": "4:01:12", "throughput": 10867.65, "total_tokens": 9175040} | |
| {"current_steps": 36, "total_steps": 635, "loss": 1.1214, "lr": 1.984181002835542e-05, "epoch": 0.2829076620825147, "percentage": 5.67, "elapsed_time": "0:14:28", "remaining_time": "4:00:47", "throughput": 10868.77, "total_tokens": 9437184} | |
| {"current_steps": 37, "total_steps": 635, "loss": 1.1326, "lr": 1.9832924529314284e-05, "epoch": 0.2907662082514735, "percentage": 5.83, "elapsed_time": "0:14:52", "remaining_time": "4:00:22", "throughput": 10869.64, "total_tokens": 9699328} | |
| {"current_steps": 38, "total_steps": 635, "loss": 1.1491, "lr": 1.9823798353536183e-05, "epoch": 0.29862475442043224, "percentage": 5.98, "elapsed_time": "0:15:16", "remaining_time": "3:59:57", "throughput": 10870.29, "total_tokens": 9961472} | |
| {"current_steps": 39, "total_steps": 635, "loss": 1.1309, "lr": 1.981443172439904e-05, "epoch": 0.30648330058939094, "percentage": 6.14, "elapsed_time": "0:15:40", "remaining_time": "3:59:31", "throughput": 10871.07, "total_tokens": 10223616} | |
| {"current_steps": 40, "total_steps": 635, "loss": 1.1071, "lr": 1.9804824871166254e-05, "epoch": 0.3143418467583497, "percentage": 6.3, "elapsed_time": "0:16:04", "remaining_time": "3:59:07", "throughput": 10871.27, "total_tokens": 10485760} | |
| {"current_steps": 41, "total_steps": 635, "loss": 1.1271, "lr": 1.9794978028981106e-05, "epoch": 0.32220039292730845, "percentage": 6.46, "elapsed_time": "0:16:28", "remaining_time": "3:58:42", "throughput": 10872.0, "total_tokens": 10747904} | |
| {"current_steps": 42, "total_steps": 635, "loss": 1.1159, "lr": 1.9784891438860987e-05, "epoch": 0.3300589390962672, "percentage": 6.61, "elapsed_time": "0:16:52", "remaining_time": "3:58:17", "throughput": 10872.61, "total_tokens": 11010048} | |
| {"current_steps": 43, "total_steps": 635, "loss": 1.121, "lr": 1.977456534769151e-05, "epoch": 0.3379174852652259, "percentage": 6.77, "elapsed_time": "0:17:16", "remaining_time": "3:57:52", "throughput": 10873.63, "total_tokens": 11272192} | |
| {"current_steps": 44, "total_steps": 635, "loss": 1.1528, "lr": 1.9764000008220464e-05, "epoch": 0.34577603143418467, "percentage": 6.93, "elapsed_time": "0:17:40", "remaining_time": "3:57:26", "throughput": 10874.47, "total_tokens": 11534336} | |
| {"current_steps": 45, "total_steps": 635, "loss": 1.1184, "lr": 1.975319567905163e-05, "epoch": 0.35363457760314343, "percentage": 7.09, "elapsed_time": "0:18:04", "remaining_time": "3:57:02", "throughput": 10874.85, "total_tokens": 11796480} | |
| {"current_steps": 46, "total_steps": 635, "loss": 1.0754, "lr": 1.9742152624638437e-05, "epoch": 0.3614931237721022, "percentage": 7.24, "elapsed_time": "0:18:28", "remaining_time": "3:56:37", "throughput": 10875.54, "total_tokens": 12058624} | |
| {"current_steps": 47, "total_steps": 635, "loss": 1.1187, "lr": 1.9730871115277513e-05, "epoch": 0.3693516699410609, "percentage": 7.4, "elapsed_time": "0:18:52", "remaining_time": "3:56:12", "throughput": 10875.73, "total_tokens": 12320768} | |
| {"current_steps": 48, "total_steps": 635, "loss": 1.0941, "lr": 1.9719351427102054e-05, "epoch": 0.37721021611001965, "percentage": 7.56, "elapsed_time": "0:19:16", "remaining_time": "3:55:48", "throughput": 10876.23, "total_tokens": 12582912} | |
| {"current_steps": 49, "total_steps": 635, "loss": 1.1153, "lr": 1.970759384207507e-05, "epoch": 0.3850687622789784, "percentage": 7.72, "elapsed_time": "0:19:40", "remaining_time": "3:55:23", "throughput": 10876.49, "total_tokens": 12845056} | |
| {"current_steps": 50, "total_steps": 635, "loss": 1.1251, "lr": 1.9695598647982467e-05, "epoch": 0.3929273084479371, "percentage": 7.87, "elapsed_time": "0:20:05", "remaining_time": "3:54:59", "throughput": 10876.64, "total_tokens": 13107200} | |
| {"current_steps": 51, "total_steps": 635, "loss": 1.1247, "lr": 1.9683366138426033e-05, "epoch": 0.40078585461689586, "percentage": 8.03, "elapsed_time": "0:20:29", "remaining_time": "3:54:35", "throughput": 10876.76, "total_tokens": 13369344} | |
| {"current_steps": 52, "total_steps": 635, "loss": 1.0657, "lr": 1.9670896612816236e-05, "epoch": 0.4086444007858546, "percentage": 8.19, "elapsed_time": "0:20:53", "remaining_time": "3:54:10", "throughput": 10876.88, "total_tokens": 13631488} | |
| {"current_steps": 53, "total_steps": 635, "loss": 1.0712, "lr": 1.9658190376364884e-05, "epoch": 0.4165029469548134, "percentage": 8.35, "elapsed_time": "0:21:17", "remaining_time": "3:53:47", "throughput": 10876.56, "total_tokens": 13893632} | |
| {"current_steps": 54, "total_steps": 635, "loss": 1.0743, "lr": 1.964524774007768e-05, "epoch": 0.4243614931237721, "percentage": 8.5, "elapsed_time": "0:21:41", "remaining_time": "3:53:22", "throughput": 10876.98, "total_tokens": 14155776} | |
| {"current_steps": 55, "total_steps": 635, "loss": 1.0666, "lr": 1.9632069020746574e-05, "epoch": 0.43222003929273084, "percentage": 8.66, "elapsed_time": "0:22:05", "remaining_time": "3:52:58", "throughput": 10876.98, "total_tokens": 14417920} | |
| {"current_steps": 56, "total_steps": 635, "loss": 1.061, "lr": 1.961865454094205e-05, "epoch": 0.4400785854616896, "percentage": 8.82, "elapsed_time": "0:22:29", "remaining_time": "3:52:34", "throughput": 10877.26, "total_tokens": 14680064} | |
| {"current_steps": 57, "total_steps": 635, "loss": 1.1252, "lr": 1.9605004629005214e-05, "epoch": 0.44793713163064836, "percentage": 8.98, "elapsed_time": "0:22:53", "remaining_time": "3:52:09", "throughput": 10877.46, "total_tokens": 14942208} | |
| {"current_steps": 58, "total_steps": 635, "loss": 1.0443, "lr": 1.959111961903973e-05, "epoch": 0.45579567779960706, "percentage": 9.13, "elapsed_time": "0:23:17", "remaining_time": "3:51:45", "throughput": 10877.8, "total_tokens": 15204352} | |
| {"current_steps": 59, "total_steps": 635, "loss": 1.0814, "lr": 1.9576999850903698e-05, "epoch": 0.4636542239685658, "percentage": 9.29, "elapsed_time": "0:23:41", "remaining_time": "3:51:20", "throughput": 10878.07, "total_tokens": 15466496} | |
| {"current_steps": 60, "total_steps": 635, "loss": 1.0637, "lr": 1.9562645670201278e-05, "epoch": 0.4715127701375246, "percentage": 9.45, "elapsed_time": "0:24:05", "remaining_time": "3:50:56", "throughput": 10878.14, "total_tokens": 15728640} | |
| {"current_steps": 61, "total_steps": 635, "loss": 1.0697, "lr": 1.9548057428274267e-05, "epoch": 0.4793713163064833, "percentage": 9.61, "elapsed_time": "0:24:29", "remaining_time": "3:50:31", "throughput": 10878.46, "total_tokens": 15990784} | |
| {"current_steps": 62, "total_steps": 635, "loss": 1.0893, "lr": 1.9533235482193492e-05, "epoch": 0.48722986247544203, "percentage": 9.76, "elapsed_time": "0:24:54", "remaining_time": "3:50:07", "throughput": 10878.49, "total_tokens": 16252928} | |
| {"current_steps": 63, "total_steps": 635, "loss": 1.0391, "lr": 1.9518180194750063e-05, "epoch": 0.4950884086444008, "percentage": 9.92, "elapsed_time": "0:25:18", "remaining_time": "3:49:43", "throughput": 10878.77, "total_tokens": 16515072} | |
| {"current_steps": 64, "total_steps": 635, "loss": 1.0457, "lr": 1.9502891934446505e-05, "epoch": 0.5029469548133595, "percentage": 10.08, "elapsed_time": "0:25:42", "remaining_time": "3:49:18", "throughput": 10879.03, "total_tokens": 16777216} | |
| {"current_steps": 65, "total_steps": 635, "loss": 1.0535, "lr": 1.948737107548771e-05, "epoch": 0.5108055009823183, "percentage": 10.24, "elapsed_time": "0:26:06", "remaining_time": "3:48:55", "throughput": 10878.88, "total_tokens": 17039360} | |
| {"current_steps": 66, "total_steps": 635, "loss": 1.0672, "lr": 1.947161799777183e-05, "epoch": 0.518664047151277, "percentage": 10.39, "elapsed_time": "0:26:30", "remaining_time": "3:48:30", "throughput": 10879.01, "total_tokens": 17301504} | |
| {"current_steps": 67, "total_steps": 635, "loss": 1.0715, "lr": 1.9455633086880916e-05, "epoch": 0.5265225933202358, "percentage": 10.55, "elapsed_time": "0:26:54", "remaining_time": "3:48:06", "throughput": 10879.45, "total_tokens": 17563648} | |
| {"current_steps": 68, "total_steps": 635, "loss": 1.0406, "lr": 1.9439416734071535e-05, "epoch": 0.5343811394891945, "percentage": 10.71, "elapsed_time": "0:27:18", "remaining_time": "3:47:41", "throughput": 10879.54, "total_tokens": 17825792} | |
| {"current_steps": 69, "total_steps": 635, "loss": 1.047, "lr": 1.942296933626515e-05, "epoch": 0.5422396856581533, "percentage": 10.87, "elapsed_time": "0:27:42", "remaining_time": "3:47:17", "throughput": 10879.9, "total_tokens": 18087936} | |
| {"current_steps": 70, "total_steps": 635, "loss": 1.0231, "lr": 1.940629129603844e-05, "epoch": 0.550098231827112, "percentage": 11.02, "elapsed_time": "0:28:06", "remaining_time": "3:46:53", "throughput": 10879.92, "total_tokens": 18350080} | |
| {"current_steps": 71, "total_steps": 635, "loss": 1.0116, "lr": 1.9389383021613422e-05, "epoch": 0.5579567779960707, "percentage": 11.18, "elapsed_time": "0:28:30", "remaining_time": "3:46:28", "throughput": 10880.4, "total_tokens": 18612224} | |
| {"current_steps": 72, "total_steps": 635, "loss": 1.0266, "lr": 1.9372244926847467e-05, "epoch": 0.5658153241650294, "percentage": 11.34, "elapsed_time": "0:28:54", "remaining_time": "3:46:04", "throughput": 10880.61, "total_tokens": 18874368} | |
| {"current_steps": 73, "total_steps": 635, "loss": 1.0676, "lr": 1.9354877431223173e-05, "epoch": 0.5736738703339882, "percentage": 11.5, "elapsed_time": "0:29:18", "remaining_time": "3:45:39", "throughput": 10880.89, "total_tokens": 19136512} | |
| {"current_steps": 74, "total_steps": 635, "loss": 1.0185, "lr": 1.93372809598381e-05, "epoch": 0.581532416502947, "percentage": 11.65, "elapsed_time": "0:29:42", "remaining_time": "3:45:15", "throughput": 10881.17, "total_tokens": 19398656} | |
| {"current_steps": 75, "total_steps": 635, "loss": 1.0257, "lr": 1.9319455943394347e-05, "epoch": 0.5893909626719057, "percentage": 11.81, "elapsed_time": "0:30:06", "remaining_time": "3:44:51", "throughput": 10881.19, "total_tokens": 19660800} | |
| {"current_steps": 76, "total_steps": 635, "loss": 1.0569, "lr": 1.9301402818188036e-05, "epoch": 0.5972495088408645, "percentage": 11.97, "elapsed_time": "0:30:31", "remaining_time": "3:44:27", "throughput": 10880.67, "total_tokens": 19922944} | |
| {"current_steps": 77, "total_steps": 635, "loss": 1.0525, "lr": 1.928312202609862e-05, "epoch": 0.6051080550098232, "percentage": 12.13, "elapsed_time": "0:30:55", "remaining_time": "3:44:03", "throughput": 10880.93, "total_tokens": 20185088} | |
| {"current_steps": 78, "total_steps": 635, "loss": 1.0357, "lr": 1.9264614014578057e-05, "epoch": 0.6129666011787819, "percentage": 12.28, "elapsed_time": "0:31:19", "remaining_time": "3:43:39", "throughput": 10881.01, "total_tokens": 20447232} | |
| {"current_steps": 79, "total_steps": 635, "loss": 1.0234, "lr": 1.924587923663987e-05, "epoch": 0.6208251473477406, "percentage": 12.44, "elapsed_time": "0:31:43", "remaining_time": "3:43:15", "throughput": 10881.01, "total_tokens": 20709376} | |
| {"current_steps": 80, "total_steps": 635, "loss": 1.0061, "lr": 1.9226918150848067e-05, "epoch": 0.6286836935166994, "percentage": 12.6, "elapsed_time": "0:32:07", "remaining_time": "3:42:50", "throughput": 10881.35, "total_tokens": 20971520} | |
| {"current_steps": 81, "total_steps": 635, "loss": 0.9951, "lr": 1.9207731221305905e-05, "epoch": 0.6365422396856582, "percentage": 12.76, "elapsed_time": "0:32:31", "remaining_time": "3:42:26", "throughput": 10881.53, "total_tokens": 21233664} | |
| {"current_steps": 82, "total_steps": 635, "loss": 1.0264, "lr": 1.9188318917644514e-05, "epoch": 0.6444007858546169, "percentage": 12.91, "elapsed_time": "0:32:55", "remaining_time": "3:42:01", "throughput": 10881.78, "total_tokens": 21495808} | |
| {"current_steps": 83, "total_steps": 635, "loss": 0.9915, "lr": 1.9168681715011444e-05, "epoch": 0.6522593320235757, "percentage": 13.07, "elapsed_time": "0:33:19", "remaining_time": "3:41:37", "throughput": 10882.18, "total_tokens": 21757952} | |
| {"current_steps": 84, "total_steps": 635, "loss": 1.0232, "lr": 1.9148820094059004e-05, "epoch": 0.6601178781925344, "percentage": 13.23, "elapsed_time": "0:33:43", "remaining_time": "3:41:12", "throughput": 10882.39, "total_tokens": 22020096} | |
| {"current_steps": 85, "total_steps": 635, "loss": 1.0041, "lr": 1.9128734540932494e-05, "epoch": 0.6679764243614931, "percentage": 13.39, "elapsed_time": "0:34:07", "remaining_time": "3:40:48", "throughput": 10882.6, "total_tokens": 22282240} | |
| {"current_steps": 86, "total_steps": 635, "loss": 0.998, "lr": 1.9108425547258328e-05, "epoch": 0.6758349705304518, "percentage": 13.54, "elapsed_time": "0:34:31", "remaining_time": "3:40:24", "throughput": 10882.71, "total_tokens": 22544384} | |
| {"current_steps": 87, "total_steps": 635, "loss": 1.0002, "lr": 1.9087893610131986e-05, "epoch": 0.6836935166994106, "percentage": 13.7, "elapsed_time": "0:34:55", "remaining_time": "3:39:59", "throughput": 10883.04, "total_tokens": 22806528} | |
| {"current_steps": 88, "total_steps": 635, "loss": 1.0017, "lr": 1.9067139232105844e-05, "epoch": 0.6915520628683693, "percentage": 13.86, "elapsed_time": "0:35:19", "remaining_time": "3:39:35", "throughput": 10883.27, "total_tokens": 23068672} | |
| {"current_steps": 89, "total_steps": 635, "loss": 1.0316, "lr": 1.904616292117689e-05, "epoch": 0.6994106090373281, "percentage": 14.02, "elapsed_time": "0:35:43", "remaining_time": "3:39:11", "throughput": 10883.6, "total_tokens": 23330816} | |
| {"current_steps": 90, "total_steps": 635, "loss": 1.0109, "lr": 1.9024965190774262e-05, "epoch": 0.7072691552062869, "percentage": 14.17, "elapsed_time": "0:36:07", "remaining_time": "3:38:46", "throughput": 10883.73, "total_tokens": 23592960} | |
| {"current_steps": 91, "total_steps": 635, "loss": 1.0034, "lr": 1.900354655974672e-05, "epoch": 0.7151277013752456, "percentage": 14.33, "elapsed_time": "0:36:31", "remaining_time": "3:38:22", "throughput": 10883.94, "total_tokens": 23855104} | |
| {"current_steps": 92, "total_steps": 635, "loss": 1.0092, "lr": 1.898190755234991e-05, "epoch": 0.7229862475442044, "percentage": 14.49, "elapsed_time": "0:36:55", "remaining_time": "3:37:58", "throughput": 10884.11, "total_tokens": 24117248} | |
| {"current_steps": 93, "total_steps": 635, "loss": 1.0067, "lr": 1.8960048698233544e-05, "epoch": 0.730844793713163, "percentage": 14.65, "elapsed_time": "0:37:19", "remaining_time": "3:37:33", "throughput": 10884.36, "total_tokens": 24379392} | |
| {"current_steps": 94, "total_steps": 635, "loss": 0.9972, "lr": 1.8937970532428446e-05, "epoch": 0.7387033398821218, "percentage": 14.8, "elapsed_time": "0:37:43", "remaining_time": "3:37:09", "throughput": 10884.47, "total_tokens": 24641536} | |
| {"current_steps": 95, "total_steps": 635, "loss": 1.007, "lr": 1.8915673595333443e-05, "epoch": 0.7465618860510805, "percentage": 14.96, "elapsed_time": "0:38:07", "remaining_time": "3:36:45", "throughput": 10884.54, "total_tokens": 24903680} | |
| {"current_steps": 96, "total_steps": 635, "loss": 0.9833, "lr": 1.889315843270215e-05, "epoch": 0.7544204322200393, "percentage": 15.12, "elapsed_time": "0:38:32", "remaining_time": "3:36:21", "throughput": 10884.67, "total_tokens": 25165824} | |
| {"current_steps": 97, "total_steps": 635, "loss": 0.9835, "lr": 1.8870425595629597e-05, "epoch": 0.762278978388998, "percentage": 15.28, "elapsed_time": "0:38:56", "remaining_time": "3:35:56", "throughput": 10884.96, "total_tokens": 25427968} | |
| {"current_steps": 98, "total_steps": 635, "loss": 0.9512, "lr": 1.8847475640538753e-05, "epoch": 0.7701375245579568, "percentage": 15.43, "elapsed_time": "0:39:20", "remaining_time": "3:35:32", "throughput": 10885.09, "total_tokens": 25690112} | |
| {"current_steps": 99, "total_steps": 635, "loss": 0.9992, "lr": 1.8824309129166897e-05, "epoch": 0.7779960707269156, "percentage": 15.59, "elapsed_time": "0:39:44", "remaining_time": "3:35:08", "throughput": 10885.2, "total_tokens": 25952256} | |
| {"current_steps": 100, "total_steps": 635, "loss": 1.0016, "lr": 1.8800926628551884e-05, "epoch": 0.7858546168958742, "percentage": 15.75, "elapsed_time": "0:40:08", "remaining_time": "3:34:44", "throughput": 10885.31, "total_tokens": 26214400} | |
| {"current_steps": 101, "total_steps": 635, "loss": 0.9576, "lr": 1.8777328711018244e-05, "epoch": 0.793713163064833, "percentage": 15.91, "elapsed_time": "0:40:32", "remaining_time": "3:34:19", "throughput": 10885.51, "total_tokens": 26476544} | |
| {"current_steps": 102, "total_steps": 635, "loss": 0.9713, "lr": 1.8753515954163188e-05, "epoch": 0.8015717092337917, "percentage": 16.06, "elapsed_time": "0:40:56", "remaining_time": "3:33:55", "throughput": 10885.78, "total_tokens": 26738688} | |
| {"current_steps": 103, "total_steps": 635, "loss": 0.9747, "lr": 1.8729488940842468e-05, "epoch": 0.8094302554027505, "percentage": 16.22, "elapsed_time": "0:41:20", "remaining_time": "3:33:30", "throughput": 10886.03, "total_tokens": 27000832} | |
| {"current_steps": 104, "total_steps": 635, "loss": 0.9845, "lr": 1.870524825915611e-05, "epoch": 0.8172888015717092, "percentage": 16.38, "elapsed_time": "0:41:44", "remaining_time": "3:33:06", "throughput": 10886.07, "total_tokens": 27262976} | |
| {"current_steps": 105, "total_steps": 635, "loss": 0.9594, "lr": 1.8680794502434018e-05, "epoch": 0.825147347740668, "percentage": 16.54, "elapsed_time": "0:42:08", "remaining_time": "3:32:42", "throughput": 10886.28, "total_tokens": 27525120} | |
| {"current_steps": 106, "total_steps": 635, "loss": 0.954, "lr": 1.8656128269221452e-05, "epoch": 0.8330058939096268, "percentage": 16.69, "elapsed_time": "0:42:32", "remaining_time": "3:32:18", "throughput": 10886.55, "total_tokens": 27787264} | |
| {"current_steps": 107, "total_steps": 635, "loss": 0.9442, "lr": 1.8631250163264383e-05, "epoch": 0.8408644400785854, "percentage": 16.85, "elapsed_time": "0:42:56", "remaining_time": "3:31:53", "throughput": 10886.72, "total_tokens": 28049408} | |
| {"current_steps": 108, "total_steps": 635, "loss": 0.9881, "lr": 1.8606160793494697e-05, "epoch": 0.8487229862475442, "percentage": 17.01, "elapsed_time": "0:43:20", "remaining_time": "3:31:29", "throughput": 10886.81, "total_tokens": 28311552} | |
| {"current_steps": 109, "total_steps": 635, "loss": 0.9657, "lr": 1.858086077401532e-05, "epoch": 0.8565815324165029, "percentage": 17.17, "elapsed_time": "0:43:44", "remaining_time": "3:31:05", "throughput": 10886.73, "total_tokens": 28573696} | |
| {"current_steps": 110, "total_steps": 635, "loss": 0.9683, "lr": 1.855535072408516e-05, "epoch": 0.8644400785854617, "percentage": 17.32, "elapsed_time": "0:44:08", "remaining_time": "3:30:41", "throughput": 10886.76, "total_tokens": 28835840} | |
| {"current_steps": 111, "total_steps": 635, "loss": 0.959, "lr": 1.8529631268103964e-05, "epoch": 0.8722986247544204, "percentage": 17.48, "elapsed_time": "0:44:32", "remaining_time": "3:30:17", "throughput": 10886.86, "total_tokens": 29097984} | |
| {"current_steps": 112, "total_steps": 635, "loss": 0.9917, "lr": 1.8503703035597026e-05, "epoch": 0.8801571709233792, "percentage": 17.64, "elapsed_time": "0:44:56", "remaining_time": "3:29:53", "throughput": 10886.77, "total_tokens": 29360128} | |
| {"current_steps": 113, "total_steps": 635, "loss": 0.9514, "lr": 1.8477566661199788e-05, "epoch": 0.888015717092338, "percentage": 17.8, "elapsed_time": "0:45:20", "remaining_time": "3:29:29", "throughput": 10886.91, "total_tokens": 29622272} | |
| {"current_steps": 114, "total_steps": 635, "loss": 0.9848, "lr": 1.8451222784642307e-05, "epoch": 0.8958742632612967, "percentage": 17.95, "elapsed_time": "0:45:44", "remaining_time": "3:29:04", "throughput": 10887.2, "total_tokens": 29884416} | |
| {"current_steps": 115, "total_steps": 635, "loss": 0.9904, "lr": 1.8424672050733577e-05, "epoch": 0.9037328094302554, "percentage": 18.11, "elapsed_time": "0:46:09", "remaining_time": "3:28:40", "throughput": 10887.1, "total_tokens": 30146560} | |
| {"current_steps": 116, "total_steps": 635, "loss": 0.9803, "lr": 1.839791510934577e-05, "epoch": 0.9115913555992141, "percentage": 18.27, "elapsed_time": "0:46:33", "remaining_time": "3:28:16", "throughput": 10887.21, "total_tokens": 30408704} | |
| {"current_steps": 117, "total_steps": 635, "loss": 0.9435, "lr": 1.837095261539832e-05, "epoch": 0.9194499017681729, "percentage": 18.43, "elapsed_time": "0:46:57", "remaining_time": "3:27:52", "throughput": 10887.53, "total_tokens": 30670848} | |
| {"current_steps": 118, "total_steps": 635, "loss": 0.9832, "lr": 1.8343785228841886e-05, "epoch": 0.9273084479371316, "percentage": 18.58, "elapsed_time": "0:47:21", "remaining_time": "3:27:27", "throughput": 10887.65, "total_tokens": 30932992} | |
| {"current_steps": 119, "total_steps": 635, "loss": 0.9564, "lr": 1.8316413614642213e-05, "epoch": 0.9351669941060904, "percentage": 18.74, "elapsed_time": "0:47:45", "remaining_time": "3:27:03", "throughput": 10887.74, "total_tokens": 31195136} | |
| {"current_steps": 120, "total_steps": 635, "loss": 0.9679, "lr": 1.8288838442763838e-05, "epoch": 0.9430255402750491, "percentage": 18.9, "elapsed_time": "0:48:09", "remaining_time": "3:26:39", "throughput": 10887.66, "total_tokens": 31457280} | |
| {"current_steps": 121, "total_steps": 635, "loss": 0.9453, "lr": 1.8261060388153716e-05, "epoch": 0.9508840864440079, "percentage": 19.06, "elapsed_time": "0:48:33", "remaining_time": "3:26:15", "throughput": 10887.81, "total_tokens": 31719424} | |
| {"current_steps": 122, "total_steps": 635, "loss": 0.9705, "lr": 1.8233080130724677e-05, "epoch": 0.9587426326129665, "percentage": 19.21, "elapsed_time": "0:48:57", "remaining_time": "3:25:51", "throughput": 10887.87, "total_tokens": 31981568} | |
| {"current_steps": 123, "total_steps": 635, "loss": 0.9276, "lr": 1.8204898355338785e-05, "epoch": 0.9666011787819253, "percentage": 19.37, "elapsed_time": "0:49:21", "remaining_time": "3:25:27", "throughput": 10887.86, "total_tokens": 32243712} | |
| {"current_steps": 124, "total_steps": 635, "loss": 0.9797, "lr": 1.8176515751790593e-05, "epoch": 0.9744597249508841, "percentage": 19.53, "elapsed_time": "0:49:45", "remaining_time": "3:25:03", "throughput": 10887.86, "total_tokens": 32505856} | |
| {"current_steps": 125, "total_steps": 635, "loss": 0.9861, "lr": 1.8147933014790245e-05, "epoch": 0.9823182711198428, "percentage": 19.69, "elapsed_time": "0:50:09", "remaining_time": "3:24:38", "throughput": 10888.16, "total_tokens": 32768000} | |
| {"current_steps": 126, "total_steps": 635, "loss": 0.969, "lr": 1.8119150843946475e-05, "epoch": 0.9901768172888016, "percentage": 19.84, "elapsed_time": "0:50:33", "remaining_time": "3:24:14", "throughput": 10888.11, "total_tokens": 33030144} | |
| {"current_steps": 127, "total_steps": 635, "loss": 0.9681, "lr": 1.8090169943749477e-05, "epoch": 0.9980353634577603, "percentage": 20.0, "elapsed_time": "0:50:57", "remaining_time": "3:23:50", "throughput": 10888.09, "total_tokens": 33292288} | |
| {"current_steps": 128, "total_steps": 635, "loss": 0.8889, "lr": 1.8060991023553676e-05, "epoch": 1.0, "percentage": 20.16, "elapsed_time": "0:51:03", "remaining_time": "3:22:14", "throughput": 10888.43, "total_tokens": 33357824} | |
| {"current_steps": 129, "total_steps": 635, "loss": 0.7536, "lr": 1.8031614797560352e-05, "epoch": 1.0078585461689586, "percentage": 20.31, "elapsed_time": "0:51:27", "remaining_time": "3:21:51", "throughput": 10888.38, "total_tokens": 33619968} | |
| {"current_steps": 130, "total_steps": 635, "loss": 0.7183, "lr": 1.8002041984800173e-05, "epoch": 1.0157170923379175, "percentage": 20.47, "elapsed_time": "0:51:51", "remaining_time": "3:21:28", "throughput": 10888.28, "total_tokens": 33882112} | |
| {"current_steps": 131, "total_steps": 635, "loss": 0.7336, "lr": 1.797227330911557e-05, "epoch": 1.0235756385068762, "percentage": 20.63, "elapsed_time": "0:52:15", "remaining_time": "3:21:04", "throughput": 10888.33, "total_tokens": 34144256} | |
| {"current_steps": 132, "total_steps": 635, "loss": 0.7242, "lr": 1.7942309499143045e-05, "epoch": 1.031434184675835, "percentage": 20.79, "elapsed_time": "0:52:39", "remaining_time": "3:20:41", "throughput": 10888.35, "total_tokens": 34406400} | |
| {"current_steps": 133, "total_steps": 635, "loss": 0.7392, "lr": 1.7912151288295328e-05, "epoch": 1.0392927308447937, "percentage": 20.94, "elapsed_time": "0:53:03", "remaining_time": "3:20:17", "throughput": 10888.39, "total_tokens": 34668544} | |
| {"current_steps": 134, "total_steps": 635, "loss": 0.6998, "lr": 1.7881799414743428e-05, "epoch": 1.0471512770137525, "percentage": 21.1, "elapsed_time": "0:53:28", "remaining_time": "3:19:54", "throughput": 10888.45, "total_tokens": 34930688} | |
| {"current_steps": 135, "total_steps": 635, "loss": 0.6813, "lr": 1.785125462139855e-05, "epoch": 1.0550098231827112, "percentage": 21.26, "elapsed_time": "0:53:52", "remaining_time": "3:19:30", "throughput": 10888.44, "total_tokens": 35192832} | |
| {"current_steps": 136, "total_steps": 635, "loss": 0.6913, "lr": 1.782051765589394e-05, "epoch": 1.0628683693516698, "percentage": 21.42, "elapsed_time": "0:54:16", "remaining_time": "3:19:07", "throughput": 10888.47, "total_tokens": 35454976} | |
| {"current_steps": 137, "total_steps": 635, "loss": 0.7459, "lr": 1.7789589270566548e-05, "epoch": 1.0707269155206287, "percentage": 21.57, "elapsed_time": "0:54:40", "remaining_time": "3:18:43", "throughput": 10888.7, "total_tokens": 35717120} | |
| {"current_steps": 138, "total_steps": 635, "loss": 0.6882, "lr": 1.7758470222438656e-05, "epoch": 1.0785854616895874, "percentage": 21.73, "elapsed_time": "0:55:04", "remaining_time": "3:18:20", "throughput": 10888.65, "total_tokens": 35979264} | |
| {"current_steps": 139, "total_steps": 635, "loss": 0.7069, "lr": 1.772716127319931e-05, "epoch": 1.0864440078585462, "percentage": 21.89, "elapsed_time": "0:55:28", "remaining_time": "3:17:56", "throughput": 10888.75, "total_tokens": 36241408} | |
| {"current_steps": 140, "total_steps": 635, "loss": 0.688, "lr": 1.7695663189185703e-05, "epoch": 1.0943025540275049, "percentage": 22.05, "elapsed_time": "0:55:52", "remaining_time": "3:17:33", "throughput": 10888.63, "total_tokens": 36503552} | |
| {"current_steps": 141, "total_steps": 635, "loss": 0.6843, "lr": 1.7663976741364394e-05, "epoch": 1.1021611001964637, "percentage": 22.2, "elapsed_time": "0:56:16", "remaining_time": "3:17:09", "throughput": 10888.64, "total_tokens": 36765696} | |
| {"current_steps": 142, "total_steps": 635, "loss": 0.6768, "lr": 1.7632102705312472e-05, "epoch": 1.1100196463654224, "percentage": 22.36, "elapsed_time": "0:56:40", "remaining_time": "3:16:46", "throughput": 10888.68, "total_tokens": 37027840} | |
| {"current_steps": 143, "total_steps": 635, "loss": 0.6901, "lr": 1.7600041861198533e-05, "epoch": 1.117878192534381, "percentage": 22.52, "elapsed_time": "0:57:04", "remaining_time": "3:16:22", "throughput": 10888.76, "total_tokens": 37289984} | |
| {"current_steps": 144, "total_steps": 635, "loss": 0.6924, "lr": 1.7567794993763606e-05, "epoch": 1.12573673870334, "percentage": 22.68, "elapsed_time": "0:57:28", "remaining_time": "3:15:59", "throughput": 10888.7, "total_tokens": 37552128} | |
| {"current_steps": 145, "total_steps": 635, "loss": 0.7159, "lr": 1.7535362892301953e-05, "epoch": 1.1335952848722985, "percentage": 22.83, "elapsed_time": "0:57:52", "remaining_time": "3:15:35", "throughput": 10888.77, "total_tokens": 37814272} | |
| {"current_steps": 146, "total_steps": 635, "loss": 0.6726, "lr": 1.750274635064173e-05, "epoch": 1.1414538310412574, "percentage": 22.99, "elapsed_time": "0:58:16", "remaining_time": "3:15:12", "throughput": 10888.81, "total_tokens": 38076416} | |
| {"current_steps": 147, "total_steps": 635, "loss": 0.7028, "lr": 1.7469946167125563e-05, "epoch": 1.149312377210216, "percentage": 23.15, "elapsed_time": "0:58:40", "remaining_time": "3:14:48", "throughput": 10888.9, "total_tokens": 38338560} | |
| {"current_steps": 148, "total_steps": 635, "loss": 0.68, "lr": 1.743696314459101e-05, "epoch": 1.157170923379175, "percentage": 23.31, "elapsed_time": "0:59:05", "remaining_time": "3:14:25", "throughput": 10887.87, "total_tokens": 38600704} | |
| {"current_steps": 149, "total_steps": 635, "loss": 0.688, "lr": 1.7403798090350913e-05, "epoch": 1.1650294695481336, "percentage": 23.46, "elapsed_time": "0:59:29", "remaining_time": "3:14:02", "throughput": 10888.01, "total_tokens": 38862848} | |
| {"current_steps": 150, "total_steps": 635, "loss": 0.6955, "lr": 1.737045181617364e-05, "epoch": 1.1728880157170924, "percentage": 23.62, "elapsed_time": "0:59:53", "remaining_time": "3:13:38", "throughput": 10888.13, "total_tokens": 39124992} | |
| {"current_steps": 151, "total_steps": 635, "loss": 0.6909, "lr": 1.7336925138263195e-05, "epoch": 1.180746561886051, "percentage": 23.78, "elapsed_time": "1:00:17", "remaining_time": "3:13:14", "throughput": 10888.11, "total_tokens": 39387136} | |
| {"current_steps": 152, "total_steps": 635, "loss": 0.696, "lr": 1.730321887723927e-05, "epoch": 1.1886051080550097, "percentage": 23.94, "elapsed_time": "1:00:41", "remaining_time": "3:12:51", "throughput": 10888.21, "total_tokens": 39649280} | |
| {"current_steps": 153, "total_steps": 635, "loss": 0.6792, "lr": 1.7269333858117137e-05, "epoch": 1.1964636542239686, "percentage": 24.09, "elapsed_time": "1:01:05", "remaining_time": "3:12:27", "throughput": 10888.36, "total_tokens": 39911424} | |
| {"current_steps": 154, "total_steps": 635, "loss": 0.6945, "lr": 1.7235270910287462e-05, "epoch": 1.2043222003929273, "percentage": 24.25, "elapsed_time": "1:01:29", "remaining_time": "3:12:03", "throughput": 10888.58, "total_tokens": 40173568} | |
| {"current_steps": 155, "total_steps": 635, "loss": 0.6924, "lr": 1.7201030867496005e-05, "epoch": 1.2121807465618861, "percentage": 24.41, "elapsed_time": "1:01:53", "remaining_time": "3:11:40", "throughput": 10888.69, "total_tokens": 40435712} | |
| {"current_steps": 156, "total_steps": 635, "loss": 0.7122, "lr": 1.7166614567823214e-05, "epoch": 1.2200392927308448, "percentage": 24.57, "elapsed_time": "1:02:17", "remaining_time": "3:11:16", "throughput": 10888.79, "total_tokens": 40697856} | |
| {"current_steps": 157, "total_steps": 635, "loss": 0.705, "lr": 1.7132022853663706e-05, "epoch": 1.2278978388998034, "percentage": 24.72, "elapsed_time": "1:02:41", "remaining_time": "3:10:52", "throughput": 10888.91, "total_tokens": 40960000} | |
| {"current_steps": 158, "total_steps": 635, "loss": 0.6741, "lr": 1.709725657170565e-05, "epoch": 1.2357563850687623, "percentage": 24.88, "elapsed_time": "1:03:05", "remaining_time": "3:10:28", "throughput": 10889.03, "total_tokens": 41222144} | |
| {"current_steps": 159, "total_steps": 635, "loss": 0.7103, "lr": 1.7062316572910048e-05, "epoch": 1.243614931237721, "percentage": 25.04, "elapsed_time": "1:03:29", "remaining_time": "3:10:05", "throughput": 10889.1, "total_tokens": 41484288} | |
| {"current_steps": 160, "total_steps": 635, "loss": 0.6716, "lr": 1.7027203712489902e-05, "epoch": 1.2514734774066798, "percentage": 25.2, "elapsed_time": "1:03:53", "remaining_time": "3:09:41", "throughput": 10889.17, "total_tokens": 41746432} | |
| {"current_steps": 161, "total_steps": 635, "loss": 0.6992, "lr": 1.6991918849889283e-05, "epoch": 1.2593320235756384, "percentage": 25.35, "elapsed_time": "1:04:17", "remaining_time": "3:09:17", "throughput": 10889.27, "total_tokens": 42008576} | |
| {"current_steps": 162, "total_steps": 635, "loss": 0.6984, "lr": 1.695646284876229e-05, "epoch": 1.2671905697445973, "percentage": 25.51, "elapsed_time": "1:04:41", "remaining_time": "3:08:54", "throughput": 10889.32, "total_tokens": 42270720} | |
| {"current_steps": 163, "total_steps": 635, "loss": 0.6852, "lr": 1.692083657695192e-05, "epoch": 1.275049115913556, "percentage": 25.67, "elapsed_time": "1:05:05", "remaining_time": "3:08:30", "throughput": 10889.34, "total_tokens": 42532864} | |
| {"current_steps": 164, "total_steps": 635, "loss": 0.7004, "lr": 1.6885040906468807e-05, "epoch": 1.2829076620825148, "percentage": 25.83, "elapsed_time": "1:05:30", "remaining_time": "3:08:06", "throughput": 10889.3, "total_tokens": 42795008} | |
| {"current_steps": 165, "total_steps": 635, "loss": 0.6708, "lr": 1.6849076713469914e-05, "epoch": 1.2907662082514735, "percentage": 25.98, "elapsed_time": "1:05:54", "remaining_time": "3:07:43", "throughput": 10889.39, "total_tokens": 43057152} | |
| {"current_steps": 166, "total_steps": 635, "loss": 0.704, "lr": 1.681294487823704e-05, "epoch": 1.2986247544204321, "percentage": 26.14, "elapsed_time": "1:06:18", "remaining_time": "3:07:19", "throughput": 10889.44, "total_tokens": 43319296} | |
| {"current_steps": 167, "total_steps": 635, "loss": 0.6805, "lr": 1.6776646285155326e-05, "epoch": 1.306483300589391, "percentage": 26.3, "elapsed_time": "1:06:42", "remaining_time": "3:06:55", "throughput": 10889.54, "total_tokens": 43581440} | |
| {"current_steps": 168, "total_steps": 635, "loss": 0.6943, "lr": 1.6740181822691556e-05, "epoch": 1.3143418467583496, "percentage": 26.46, "elapsed_time": "1:07:06", "remaining_time": "3:06:31", "throughput": 10889.52, "total_tokens": 43843584} | |
| {"current_steps": 169, "total_steps": 635, "loss": 0.7084, "lr": 1.6703552383372447e-05, "epoch": 1.3222003929273085, "percentage": 26.61, "elapsed_time": "1:07:30", "remaining_time": "3:06:08", "throughput": 10889.57, "total_tokens": 44105728} | |
| {"current_steps": 170, "total_steps": 635, "loss": 0.6963, "lr": 1.6666758863762796e-05, "epoch": 1.3300589390962672, "percentage": 26.77, "elapsed_time": "1:07:54", "remaining_time": "3:05:44", "throughput": 10889.69, "total_tokens": 44367872} | |
| {"current_steps": 171, "total_steps": 635, "loss": 0.6912, "lr": 1.6629802164443522e-05, "epoch": 1.3379174852652258, "percentage": 26.93, "elapsed_time": "1:08:18", "remaining_time": "3:05:20", "throughput": 10889.68, "total_tokens": 44630016} | |
| {"current_steps": 172, "total_steps": 635, "loss": 0.7055, "lr": 1.659268318998963e-05, "epoch": 1.3457760314341847, "percentage": 27.09, "elapsed_time": "1:08:42", "remaining_time": "3:04:57", "throughput": 10889.68, "total_tokens": 44892160} | |
| {"current_steps": 173, "total_steps": 635, "loss": 0.6976, "lr": 1.6555402848948085e-05, "epoch": 1.3536345776031435, "percentage": 27.24, "elapsed_time": "1:09:06", "remaining_time": "3:04:33", "throughput": 10889.73, "total_tokens": 45154304} | |
| {"current_steps": 174, "total_steps": 635, "loss": 0.6808, "lr": 1.6517962053815547e-05, "epoch": 1.3614931237721022, "percentage": 27.4, "elapsed_time": "1:09:30", "remaining_time": "3:04:09", "throughput": 10889.89, "total_tokens": 45416448} | |
| {"current_steps": 175, "total_steps": 635, "loss": 0.685, "lr": 1.6480361721016053e-05, "epoch": 1.3693516699410608, "percentage": 27.56, "elapsed_time": "1:09:54", "remaining_time": "3:03:45", "throughput": 10889.97, "total_tokens": 45678592} | |
| {"current_steps": 176, "total_steps": 635, "loss": 0.6977, "lr": 1.6442602770878586e-05, "epoch": 1.3772102161100197, "percentage": 27.72, "elapsed_time": "1:10:18", "remaining_time": "3:03:21", "throughput": 10890.09, "total_tokens": 45940736} | |
| {"current_steps": 177, "total_steps": 635, "loss": 0.6951, "lr": 1.640468612761454e-05, "epoch": 1.3850687622789783, "percentage": 27.87, "elapsed_time": "1:10:42", "remaining_time": "3:02:58", "throughput": 10890.11, "total_tokens": 46202880} | |
| {"current_steps": 178, "total_steps": 635, "loss": 0.6949, "lr": 1.6366612719295106e-05, "epoch": 1.3929273084479372, "percentage": 28.03, "elapsed_time": "1:11:06", "remaining_time": "3:02:34", "throughput": 10890.11, "total_tokens": 46465024} | |
| {"current_steps": 179, "total_steps": 635, "loss": 0.735, "lr": 1.6328383477828556e-05, "epoch": 1.4007858546168959, "percentage": 28.19, "elapsed_time": "1:11:31", "remaining_time": "3:02:13", "throughput": 10887.39, "total_tokens": 46727168} | |
| {"current_steps": 180, "total_steps": 635, "loss": 0.6719, "lr": 1.6289999338937427e-05, "epoch": 1.4086444007858545, "percentage": 28.35, "elapsed_time": "1:11:55", "remaining_time": "3:01:49", "throughput": 10887.54, "total_tokens": 46989312} | |
| {"current_steps": 181, "total_steps": 635, "loss": 0.7112, "lr": 1.625146124213562e-05, "epoch": 1.4165029469548134, "percentage": 28.5, "elapsed_time": "1:12:19", "remaining_time": "3:01:25", "throughput": 10887.63, "total_tokens": 47251456} | |
| {"current_steps": 182, "total_steps": 635, "loss": 0.7147, "lr": 1.6212770130705403e-05, "epoch": 1.424361493123772, "percentage": 28.66, "elapsed_time": "1:12:43", "remaining_time": "3:01:01", "throughput": 10887.69, "total_tokens": 47513600} | |
| {"current_steps": 183, "total_steps": 635, "loss": 0.7026, "lr": 1.6173926951674336e-05, "epoch": 1.432220039292731, "percentage": 28.82, "elapsed_time": "1:13:08", "remaining_time": "3:00:38", "throughput": 10887.71, "total_tokens": 47775744} | |
| {"current_steps": 184, "total_steps": 635, "loss": 0.683, "lr": 1.613493265579207e-05, "epoch": 1.4400785854616895, "percentage": 28.98, "elapsed_time": "1:13:32", "remaining_time": "3:00:14", "throughput": 10887.68, "total_tokens": 48037888} | |
| {"current_steps": 185, "total_steps": 635, "loss": 0.7084, "lr": 1.609578819750708e-05, "epoch": 1.4479371316306484, "percentage": 29.13, "elapsed_time": "1:13:56", "remaining_time": "2:59:50", "throughput": 10887.62, "total_tokens": 48300032} | |
| {"current_steps": 186, "total_steps": 635, "loss": 0.6933, "lr": 1.6056494534943324e-05, "epoch": 1.455795677799607, "percentage": 29.29, "elapsed_time": "1:14:20", "remaining_time": "2:59:26", "throughput": 10887.74, "total_tokens": 48562176} | |
| {"current_steps": 187, "total_steps": 635, "loss": 0.7242, "lr": 1.6017052629876768e-05, "epoch": 1.463654223968566, "percentage": 29.45, "elapsed_time": "1:14:44", "remaining_time": "2:59:03", "throughput": 10887.82, "total_tokens": 48824320} | |
| {"current_steps": 188, "total_steps": 635, "loss": 0.6881, "lr": 1.5977463447711844e-05, "epoch": 1.4715127701375246, "percentage": 29.61, "elapsed_time": "1:15:08", "remaining_time": "2:58:39", "throughput": 10887.88, "total_tokens": 49086464} | |
| {"current_steps": 189, "total_steps": 635, "loss": 0.7024, "lr": 1.5937727957457853e-05, "epoch": 1.4793713163064832, "percentage": 29.76, "elapsed_time": "1:15:32", "remaining_time": "2:58:15", "throughput": 10887.98, "total_tokens": 49348608} | |
| {"current_steps": 190, "total_steps": 635, "loss": 0.701, "lr": 1.5897847131705194e-05, "epoch": 1.487229862475442, "percentage": 29.92, "elapsed_time": "1:15:56", "remaining_time": "2:57:51", "throughput": 10888.01, "total_tokens": 49610752} | |
| {"current_steps": 191, "total_steps": 635, "loss": 0.6461, "lr": 1.5857821946601616e-05, "epoch": 1.4950884086444007, "percentage": 30.08, "elapsed_time": "1:16:20", "remaining_time": "2:57:27", "throughput": 10888.09, "total_tokens": 49872896} | |
| {"current_steps": 192, "total_steps": 635, "loss": 0.6754, "lr": 1.581765338182827e-05, "epoch": 1.5029469548133596, "percentage": 30.24, "elapsed_time": "1:16:44", "remaining_time": "2:57:04", "throughput": 10888.18, "total_tokens": 50135040} | |
| {"current_steps": 193, "total_steps": 635, "loss": 0.6974, "lr": 1.5777342420575782e-05, "epoch": 1.5108055009823183, "percentage": 30.39, "elapsed_time": "1:17:08", "remaining_time": "2:56:40", "throughput": 10888.15, "total_tokens": 50397184} | |
| {"current_steps": 194, "total_steps": 635, "loss": 0.6937, "lr": 1.5736890049520136e-05, "epoch": 1.518664047151277, "percentage": 30.55, "elapsed_time": "1:17:32", "remaining_time": "2:56:16", "throughput": 10888.1, "total_tokens": 50659328} | |
| {"current_steps": 195, "total_steps": 635, "loss": 0.7051, "lr": 1.5696297258798573e-05, "epoch": 1.5265225933202358, "percentage": 30.71, "elapsed_time": "1:17:56", "remaining_time": "2:55:52", "throughput": 10888.15, "total_tokens": 50921472} | |
| {"current_steps": 196, "total_steps": 635, "loss": 0.6858, "lr": 1.565556504198532e-05, "epoch": 1.5343811394891946, "percentage": 30.87, "elapsed_time": "1:18:20", "remaining_time": "2:55:29", "throughput": 10888.04, "total_tokens": 51183616} | |
| {"current_steps": 197, "total_steps": 635, "loss": 0.6954, "lr": 1.5614694396067285e-05, "epoch": 1.5422396856581533, "percentage": 31.02, "elapsed_time": "1:18:44", "remaining_time": "2:55:05", "throughput": 10888.07, "total_tokens": 51445760} | |
| {"current_steps": 198, "total_steps": 635, "loss": 0.6842, "lr": 1.5573686321419653e-05, "epoch": 1.550098231827112, "percentage": 31.18, "elapsed_time": "1:19:08", "remaining_time": "2:54:41", "throughput": 10888.17, "total_tokens": 51707904} | |
| {"current_steps": 199, "total_steps": 635, "loss": 0.7147, "lr": 1.55325418217814e-05, "epoch": 1.5579567779960706, "percentage": 31.34, "elapsed_time": "1:19:33", "remaining_time": "2:54:17", "throughput": 10888.24, "total_tokens": 51970048} | |
| {"current_steps": 200, "total_steps": 635, "loss": 0.6668, "lr": 1.549126190423073e-05, "epoch": 1.5658153241650294, "percentage": 31.5, "elapsed_time": "1:19:57", "remaining_time": "2:53:53", "throughput": 10888.29, "total_tokens": 52232192} | |
| {"current_steps": 201, "total_steps": 635, "loss": 0.6935, "lr": 1.5449847579160398e-05, "epoch": 1.5736738703339883, "percentage": 31.65, "elapsed_time": "1:20:21", "remaining_time": "2:53:29", "throughput": 10888.38, "total_tokens": 52494336} | |
| {"current_steps": 202, "total_steps": 635, "loss": 0.7003, "lr": 1.5408299860253034e-05, "epoch": 1.581532416502947, "percentage": 31.81, "elapsed_time": "1:20:45", "remaining_time": "2:53:06", "throughput": 10888.31, "total_tokens": 52756480} | |
| {"current_steps": 203, "total_steps": 635, "loss": 0.698, "lr": 1.536661976445627e-05, "epoch": 1.5893909626719056, "percentage": 31.97, "elapsed_time": "1:21:09", "remaining_time": "2:52:42", "throughput": 10888.25, "total_tokens": 53018624} | |
| {"current_steps": 204, "total_steps": 635, "loss": 0.7137, "lr": 1.532480831195789e-05, "epoch": 1.5972495088408645, "percentage": 32.13, "elapsed_time": "1:21:33", "remaining_time": "2:52:18", "throughput": 10888.18, "total_tokens": 53280768} | |
| {"current_steps": 205, "total_steps": 635, "loss": 0.6855, "lr": 1.5282866526160837e-05, "epoch": 1.6051080550098233, "percentage": 32.28, "elapsed_time": "1:21:57", "remaining_time": "2:51:54", "throughput": 10888.2, "total_tokens": 53542912} | |
| {"current_steps": 206, "total_steps": 635, "loss": 0.7022, "lr": 1.5240795433658187e-05, "epoch": 1.612966601178782, "percentage": 32.44, "elapsed_time": "1:22:21", "remaining_time": "2:51:30", "throughput": 10888.24, "total_tokens": 53805056} | |
| {"current_steps": 207, "total_steps": 635, "loss": 0.6933, "lr": 1.5198596064207989e-05, "epoch": 1.6208251473477406, "percentage": 32.6, "elapsed_time": "1:22:45", "remaining_time": "2:51:07", "throughput": 10888.2, "total_tokens": 54067200} | |
| {"current_steps": 208, "total_steps": 635, "loss": 0.69, "lr": 1.5156269450708094e-05, "epoch": 1.6286836935166993, "percentage": 32.76, "elapsed_time": "1:23:09", "remaining_time": "2:50:43", "throughput": 10888.27, "total_tokens": 54329344} | |
| {"current_steps": 209, "total_steps": 635, "loss": 0.6883, "lr": 1.5113816629170843e-05, "epoch": 1.6365422396856582, "percentage": 32.91, "elapsed_time": "1:23:33", "remaining_time": "2:50:19", "throughput": 10888.28, "total_tokens": 54591488} | |
| {"current_steps": 210, "total_steps": 635, "loss": 0.721, "lr": 1.5071238638697731e-05, "epoch": 1.644400785854617, "percentage": 33.07, "elapsed_time": "1:23:57", "remaining_time": "2:49:55", "throughput": 10888.3, "total_tokens": 54853632} | |
| {"current_steps": 211, "total_steps": 635, "loss": 0.6737, "lr": 1.5028536521453969e-05, "epoch": 1.6522593320235757, "percentage": 33.23, "elapsed_time": "1:24:21", "remaining_time": "2:49:31", "throughput": 10888.28, "total_tokens": 55115776} | |
| {"current_steps": 212, "total_steps": 635, "loss": 0.7177, "lr": 1.4985711322642957e-05, "epoch": 1.6601178781925343, "percentage": 33.39, "elapsed_time": "1:24:45", "remaining_time": "2:49:08", "throughput": 10888.31, "total_tokens": 55377920} | |
| {"current_steps": 213, "total_steps": 635, "loss": 0.6943, "lr": 1.494276409048073e-05, "epoch": 1.667976424361493, "percentage": 33.54, "elapsed_time": "1:25:10", "remaining_time": "2:48:44", "throughput": 10888.36, "total_tokens": 55640064} | |
| {"current_steps": 214, "total_steps": 635, "loss": 0.709, "lr": 1.4899695876170283e-05, "epoch": 1.6758349705304518, "percentage": 33.7, "elapsed_time": "1:25:34", "remaining_time": "2:48:20", "throughput": 10888.32, "total_tokens": 55902208} | |
| {"current_steps": 215, "total_steps": 635, "loss": 0.6733, "lr": 1.4856507733875837e-05, "epoch": 1.6836935166994107, "percentage": 33.86, "elapsed_time": "1:25:58", "remaining_time": "2:47:56", "throughput": 10888.45, "total_tokens": 56164352} | |
| {"current_steps": 216, "total_steps": 635, "loss": 0.6872, "lr": 1.4813200720697056e-05, "epoch": 1.6915520628683693, "percentage": 34.02, "elapsed_time": "1:26:22", "remaining_time": "2:47:32", "throughput": 10888.53, "total_tokens": 56426496} | |
| {"current_steps": 217, "total_steps": 635, "loss": 0.6826, "lr": 1.4769775896643157e-05, "epoch": 1.699410609037328, "percentage": 34.17, "elapsed_time": "1:26:46", "remaining_time": "2:47:08", "throughput": 10888.47, "total_tokens": 56688640} | |
| {"current_steps": 218, "total_steps": 635, "loss": 0.6784, "lr": 1.472623432460696e-05, "epoch": 1.7072691552062869, "percentage": 34.33, "elapsed_time": "1:27:10", "remaining_time": "2:46:44", "throughput": 10888.42, "total_tokens": 56950784} | |
| {"current_steps": 219, "total_steps": 635, "loss": 0.6666, "lr": 1.4682577070338898e-05, "epoch": 1.7151277013752457, "percentage": 34.49, "elapsed_time": "1:27:34", "remaining_time": "2:46:21", "throughput": 10888.46, "total_tokens": 57212928} | |
| {"current_steps": 220, "total_steps": 635, "loss": 0.6743, "lr": 1.4638805202420896e-05, "epoch": 1.7229862475442044, "percentage": 34.65, "elapsed_time": "1:27:58", "remaining_time": "2:45:57", "throughput": 10888.53, "total_tokens": 57475072} | |
| {"current_steps": 221, "total_steps": 635, "loss": 0.7019, "lr": 1.4594919792240244e-05, "epoch": 1.730844793713163, "percentage": 34.8, "elapsed_time": "1:28:22", "remaining_time": "2:45:33", "throughput": 10888.55, "total_tokens": 57737216} | |
| {"current_steps": 222, "total_steps": 635, "loss": 0.6782, "lr": 1.4550921913963364e-05, "epoch": 1.7387033398821217, "percentage": 34.96, "elapsed_time": "1:28:46", "remaining_time": "2:45:09", "throughput": 10888.61, "total_tokens": 57999360} | |
| {"current_steps": 223, "total_steps": 635, "loss": 0.6734, "lr": 1.4506812644509505e-05, "epoch": 1.7465618860510805, "percentage": 35.12, "elapsed_time": "1:29:10", "remaining_time": "2:44:45", "throughput": 10888.62, "total_tokens": 58261504} | |
| {"current_steps": 224, "total_steps": 635, "loss": 0.701, "lr": 1.446259306352441e-05, "epoch": 1.7544204322200394, "percentage": 35.28, "elapsed_time": "1:29:34", "remaining_time": "2:44:21", "throughput": 10888.59, "total_tokens": 58523648} | |
| {"current_steps": 225, "total_steps": 635, "loss": 0.6662, "lr": 1.4418264253353869e-05, "epoch": 1.762278978388998, "percentage": 35.43, "elapsed_time": "1:29:58", "remaining_time": "2:43:57", "throughput": 10888.56, "total_tokens": 58785792} | |
| {"current_steps": 226, "total_steps": 635, "loss": 0.6775, "lr": 1.4373827299017226e-05, "epoch": 1.7701375245579567, "percentage": 35.59, "elapsed_time": "1:30:22", "remaining_time": "2:43:34", "throughput": 10888.48, "total_tokens": 59047936} | |
| {"current_steps": 227, "total_steps": 635, "loss": 0.7021, "lr": 1.4329283288180841e-05, "epoch": 1.7779960707269156, "percentage": 35.75, "elapsed_time": "1:30:47", "remaining_time": "2:43:10", "throughput": 10888.47, "total_tokens": 59310080} | |
| {"current_steps": 228, "total_steps": 635, "loss": 0.7081, "lr": 1.4284633311131448e-05, "epoch": 1.7858546168958742, "percentage": 35.91, "elapsed_time": "1:31:11", "remaining_time": "2:42:46", "throughput": 10888.47, "total_tokens": 59572224} | |
| {"current_steps": 229, "total_steps": 635, "loss": 0.7012, "lr": 1.4239878460749474e-05, "epoch": 1.793713163064833, "percentage": 36.06, "elapsed_time": "1:31:35", "remaining_time": "2:42:22", "throughput": 10888.44, "total_tokens": 59834368} | |
| {"current_steps": 230, "total_steps": 635, "loss": 0.6972, "lr": 1.419501983248229e-05, "epoch": 1.8015717092337917, "percentage": 36.22, "elapsed_time": "1:31:59", "remaining_time": "2:41:58", "throughput": 10888.47, "total_tokens": 60096512} | |
| {"current_steps": 231, "total_steps": 635, "loss": 0.6791, "lr": 1.415005852431741e-05, "epoch": 1.8094302554027504, "percentage": 36.38, "elapsed_time": "1:32:23", "remaining_time": "2:41:34", "throughput": 10888.47, "total_tokens": 60358656} | |
| {"current_steps": 232, "total_steps": 635, "loss": 0.6915, "lr": 1.410499563675559e-05, "epoch": 1.8172888015717092, "percentage": 36.54, "elapsed_time": "1:32:47", "remaining_time": "2:41:11", "throughput": 10888.47, "total_tokens": 60620800} | |
| {"current_steps": 233, "total_steps": 635, "loss": 0.6901, "lr": 1.4059832272783913e-05, "epoch": 1.8251473477406681, "percentage": 36.69, "elapsed_time": "1:33:11", "remaining_time": "2:40:47", "throughput": 10888.43, "total_tokens": 60882944} | |
| {"current_steps": 234, "total_steps": 635, "loss": 0.703, "lr": 1.4014569537848784e-05, "epoch": 1.8330058939096268, "percentage": 36.85, "elapsed_time": "1:33:35", "remaining_time": "2:40:23", "throughput": 10888.37, "total_tokens": 61145088} | |
| {"current_steps": 235, "total_steps": 635, "loss": 0.658, "lr": 1.3969208539828873e-05, "epoch": 1.8408644400785854, "percentage": 37.01, "elapsed_time": "1:33:59", "remaining_time": "2:39:59", "throughput": 10888.39, "total_tokens": 61407232} | |
| {"current_steps": 236, "total_steps": 635, "loss": 0.6876, "lr": 1.3923750389008e-05, "epoch": 1.848722986247544, "percentage": 37.17, "elapsed_time": "1:34:23", "remaining_time": "2:39:35", "throughput": 10888.39, "total_tokens": 61669376} | |
| {"current_steps": 237, "total_steps": 635, "loss": 0.6826, "lr": 1.3878196198047956e-05, "epoch": 1.856581532416503, "percentage": 37.32, "elapsed_time": "1:34:47", "remaining_time": "2:39:11", "throughput": 10888.46, "total_tokens": 61931520} | |
| {"current_steps": 238, "total_steps": 635, "loss": 0.6808, "lr": 1.3832547081961261e-05, "epoch": 1.8644400785854618, "percentage": 37.48, "elapsed_time": "1:35:11", "remaining_time": "2:38:47", "throughput": 10888.38, "total_tokens": 62193664} | |
| {"current_steps": 239, "total_steps": 635, "loss": 0.6961, "lr": 1.3786804158083898e-05, "epoch": 1.8722986247544204, "percentage": 37.64, "elapsed_time": "1:35:36", "remaining_time": "2:38:24", "throughput": 10888.28, "total_tokens": 62455808} | |
| {"current_steps": 240, "total_steps": 635, "loss": 0.6869, "lr": 1.3740968546047935e-05, "epoch": 1.880157170923379, "percentage": 37.8, "elapsed_time": "1:36:00", "remaining_time": "2:38:00", "throughput": 10888.38, "total_tokens": 62717952} | |
| {"current_steps": 241, "total_steps": 635, "loss": 0.6725, "lr": 1.3695041367754134e-05, "epoch": 1.888015717092338, "percentage": 37.95, "elapsed_time": "1:36:24", "remaining_time": "2:37:36", "throughput": 10888.33, "total_tokens": 62980096} | |
| {"current_steps": 242, "total_steps": 635, "loss": 0.694, "lr": 1.3649023747344492e-05, "epoch": 1.8958742632612968, "percentage": 38.11, "elapsed_time": "1:36:48", "remaining_time": "2:37:12", "throughput": 10888.32, "total_tokens": 63242240} | |
| {"current_steps": 243, "total_steps": 635, "loss": 0.6783, "lr": 1.3602916811174724e-05, "epoch": 1.9037328094302555, "percentage": 38.27, "elapsed_time": "1:37:12", "remaining_time": "2:36:48", "throughput": 10888.39, "total_tokens": 63504384} | |
| {"current_steps": 244, "total_steps": 635, "loss": 0.6716, "lr": 1.3556721687786692e-05, "epoch": 1.9115913555992141, "percentage": 38.43, "elapsed_time": "1:37:36", "remaining_time": "2:36:24", "throughput": 10888.39, "total_tokens": 63766528} | |
| {"current_steps": 245, "total_steps": 635, "loss": 0.7154, "lr": 1.3510439507880778e-05, "epoch": 1.9194499017681728, "percentage": 38.58, "elapsed_time": "1:38:00", "remaining_time": "2:36:00", "throughput": 10888.36, "total_tokens": 64028672} | |
| {"current_steps": 246, "total_steps": 635, "loss": 0.6622, "lr": 1.3464071404288219e-05, "epoch": 1.9273084479371316, "percentage": 38.74, "elapsed_time": "1:38:24", "remaining_time": "2:35:36", "throughput": 10888.35, "total_tokens": 64290816} | |
| {"current_steps": 247, "total_steps": 635, "loss": 0.6815, "lr": 1.3417618511943374e-05, "epoch": 1.9351669941060905, "percentage": 38.9, "elapsed_time": "1:38:48", "remaining_time": "2:35:12", "throughput": 10888.44, "total_tokens": 64552960} | |
| {"current_steps": 248, "total_steps": 635, "loss": 0.682, "lr": 1.3371081967855939e-05, "epoch": 1.9430255402750491, "percentage": 39.06, "elapsed_time": "1:39:12", "remaining_time": "2:34:48", "throughput": 10888.51, "total_tokens": 64815104} | |
| {"current_steps": 249, "total_steps": 635, "loss": 0.703, "lr": 1.3324462911083123e-05, "epoch": 1.9508840864440078, "percentage": 39.21, "elapsed_time": "1:39:36", "remaining_time": "2:34:25", "throughput": 10888.52, "total_tokens": 65077248} | |
| {"current_steps": 250, "total_steps": 635, "loss": 0.7144, "lr": 1.3277762482701769e-05, "epoch": 1.9587426326129664, "percentage": 39.37, "elapsed_time": "1:40:00", "remaining_time": "2:34:01", "throughput": 10888.55, "total_tokens": 65339392} | |
| {"current_steps": 251, "total_steps": 635, "loss": 0.7023, "lr": 1.323098182578042e-05, "epoch": 1.9666011787819253, "percentage": 39.53, "elapsed_time": "1:40:24", "remaining_time": "2:33:37", "throughput": 10888.62, "total_tokens": 65601536} | |
| {"current_steps": 252, "total_steps": 635, "loss": 0.7108, "lr": 1.3184122085351343e-05, "epoch": 1.9744597249508842, "percentage": 39.69, "elapsed_time": "1:40:48", "remaining_time": "2:33:13", "throughput": 10888.69, "total_tokens": 65863680} | |
| {"current_steps": 253, "total_steps": 635, "loss": 0.6767, "lr": 1.31371844083825e-05, "epoch": 1.9823182711198428, "percentage": 39.84, "elapsed_time": "1:41:12", "remaining_time": "2:32:49", "throughput": 10888.73, "total_tokens": 66125824} | |
| {"current_steps": 254, "total_steps": 635, "loss": 0.6731, "lr": 1.3090169943749475e-05, "epoch": 1.9901768172888015, "percentage": 40.0, "elapsed_time": "1:41:36", "remaining_time": "2:32:25", "throughput": 10888.69, "total_tokens": 66387968} | |
| {"current_steps": 255, "total_steps": 635, "loss": 0.663, "lr": 1.3043079842207363e-05, "epoch": 1.9980353634577603, "percentage": 40.16, "elapsed_time": "1:42:01", "remaining_time": "2:32:01", "throughput": 10888.66, "total_tokens": 66650112} | |
| {"current_steps": 256, "total_steps": 635, "loss": 0.6595, "lr": 1.2995915256362583e-05, "epoch": 2.0, "percentage": 40.31, "elapsed_time": "1:42:07", "remaining_time": "2:31:10", "throughput": 10888.77, "total_tokens": 66715648} | |
| {"current_steps": 257, "total_steps": 635, "loss": 0.4632, "lr": 1.2948677340644687e-05, "epoch": 2.0078585461689586, "percentage": 40.47, "elapsed_time": "1:42:31", "remaining_time": "2:30:47", "throughput": 10888.76, "total_tokens": 66977792} | |
| {"current_steps": 258, "total_steps": 635, "loss": 0.4437, "lr": 1.2901367251278085e-05, "epoch": 2.0157170923379173, "percentage": 40.63, "elapsed_time": "1:42:55", "remaining_time": "2:30:23", "throughput": 10888.8, "total_tokens": 67239936} | |
| {"current_steps": 259, "total_steps": 635, "loss": 0.4571, "lr": 1.2853986146253768e-05, "epoch": 2.0235756385068764, "percentage": 40.79, "elapsed_time": "1:43:19", "remaining_time": "2:29:59", "throughput": 10888.82, "total_tokens": 67502080} | |
| {"current_steps": 260, "total_steps": 635, "loss": 0.4139, "lr": 1.2806535185300931e-05, "epoch": 2.031434184675835, "percentage": 40.94, "elapsed_time": "1:43:43", "remaining_time": "2:29:35", "throughput": 10888.91, "total_tokens": 67764224} | |
| {"current_steps": 261, "total_steps": 635, "loss": 0.4268, "lr": 1.2759015529858625e-05, "epoch": 2.0392927308447937, "percentage": 41.1, "elapsed_time": "1:44:07", "remaining_time": "2:29:12", "throughput": 10889.0, "total_tokens": 68026368} | |
| {"current_steps": 262, "total_steps": 635, "loss": 0.4061, "lr": 1.2711428343047293e-05, "epoch": 2.0471512770137523, "percentage": 41.26, "elapsed_time": "1:44:31", "remaining_time": "2:28:48", "throughput": 10889.07, "total_tokens": 68288512} | |
| {"current_steps": 263, "total_steps": 635, "loss": 0.4066, "lr": 1.2663774789640335e-05, "epoch": 2.0550098231827114, "percentage": 41.42, "elapsed_time": "1:44:55", "remaining_time": "2:28:24", "throughput": 10889.12, "total_tokens": 68550656} | |
| {"current_steps": 264, "total_steps": 635, "loss": 0.4078, "lr": 1.2616056036035564e-05, "epoch": 2.06286836935167, "percentage": 41.57, "elapsed_time": "1:45:19", "remaining_time": "2:28:00", "throughput": 10889.1, "total_tokens": 68812800} | |
| {"current_steps": 265, "total_steps": 635, "loss": 0.4108, "lr": 1.2568273250226681e-05, "epoch": 2.0707269155206287, "percentage": 41.73, "elapsed_time": "1:45:43", "remaining_time": "2:27:36", "throughput": 10889.11, "total_tokens": 69074944} | |
| {"current_steps": 266, "total_steps": 635, "loss": 0.4036, "lr": 1.2520427601774683e-05, "epoch": 2.0785854616895874, "percentage": 41.89, "elapsed_time": "1:46:07", "remaining_time": "2:27:13", "throughput": 10889.05, "total_tokens": 69337088} | |
| {"current_steps": 267, "total_steps": 635, "loss": 0.3954, "lr": 1.2472520261779221e-05, "epoch": 2.086444007858546, "percentage": 42.05, "elapsed_time": "1:46:31", "remaining_time": "2:26:49", "throughput": 10889.12, "total_tokens": 69599232} | |
| {"current_steps": 268, "total_steps": 635, "loss": 0.4108, "lr": 1.242455240284996e-05, "epoch": 2.094302554027505, "percentage": 42.2, "elapsed_time": "1:46:55", "remaining_time": "2:26:25", "throughput": 10889.18, "total_tokens": 69861376} | |
| {"current_steps": 269, "total_steps": 635, "loss": 0.3969, "lr": 1.2376525199077853e-05, "epoch": 2.1021611001964637, "percentage": 42.36, "elapsed_time": "1:47:19", "remaining_time": "2:26:01", "throughput": 10889.22, "total_tokens": 70123520} | |
| {"current_steps": 270, "total_steps": 635, "loss": 0.3813, "lr": 1.2328439826006415e-05, "epoch": 2.1100196463654224, "percentage": 42.52, "elapsed_time": "1:47:43", "remaining_time": "2:25:38", "throughput": 10889.26, "total_tokens": 70385664} | |
| {"current_steps": 271, "total_steps": 635, "loss": 0.416, "lr": 1.2280297460602958e-05, "epoch": 2.117878192534381, "percentage": 42.68, "elapsed_time": "1:48:07", "remaining_time": "2:25:14", "throughput": 10889.26, "total_tokens": 70647808} | |
| {"current_steps": 272, "total_steps": 635, "loss": 0.4097, "lr": 1.223209928122976e-05, "epoch": 2.1257367387033397, "percentage": 42.83, "elapsed_time": "1:48:31", "remaining_time": "2:24:50", "throughput": 10889.3, "total_tokens": 70909952} | |
| {"current_steps": 273, "total_steps": 635, "loss": 0.4083, "lr": 1.2183846467615244e-05, "epoch": 2.1335952848722988, "percentage": 42.99, "elapsed_time": "1:48:55", "remaining_time": "2:24:26", "throughput": 10889.3, "total_tokens": 71172096} | |
| {"current_steps": 274, "total_steps": 635, "loss": 0.3817, "lr": 1.2135540200825095e-05, "epoch": 2.1414538310412574, "percentage": 43.15, "elapsed_time": "1:49:20", "remaining_time": "2:24:02", "throughput": 10889.28, "total_tokens": 71434240} | |
| {"current_steps": 275, "total_steps": 635, "loss": 0.4005, "lr": 1.2087181663233354e-05, "epoch": 2.149312377210216, "percentage": 43.31, "elapsed_time": "1:49:44", "remaining_time": "2:23:39", "throughput": 10889.25, "total_tokens": 71696384} | |
| {"current_steps": 276, "total_steps": 635, "loss": 0.4011, "lr": 1.203877203849346e-05, "epoch": 2.1571709233791747, "percentage": 43.46, "elapsed_time": "1:50:08", "remaining_time": "2:23:15", "throughput": 10889.26, "total_tokens": 71958528} | |
| {"current_steps": 277, "total_steps": 635, "loss": 0.4158, "lr": 1.1990312511509313e-05, "epoch": 2.165029469548134, "percentage": 43.62, "elapsed_time": "1:50:32", "remaining_time": "2:22:51", "throughput": 10889.32, "total_tokens": 72220672} | |
| {"current_steps": 278, "total_steps": 635, "loss": 0.3963, "lr": 1.1941804268406232e-05, "epoch": 2.1728880157170924, "percentage": 43.78, "elapsed_time": "1:50:56", "remaining_time": "2:22:27", "throughput": 10889.36, "total_tokens": 72482816} | |
| {"current_steps": 279, "total_steps": 635, "loss": 0.3979, "lr": 1.1893248496501955e-05, "epoch": 2.180746561886051, "percentage": 43.94, "elapsed_time": "1:51:20", "remaining_time": "2:22:04", "throughput": 10889.39, "total_tokens": 72744960} | |
| {"current_steps": 280, "total_steps": 635, "loss": 0.4028, "lr": 1.184464638427756e-05, "epoch": 2.1886051080550097, "percentage": 44.09, "elapsed_time": "1:51:44", "remaining_time": "2:21:40", "throughput": 10889.49, "total_tokens": 73007104} | |
| {"current_steps": 281, "total_steps": 635, "loss": 0.4007, "lr": 1.1795999121348379e-05, "epoch": 2.1964636542239684, "percentage": 44.25, "elapsed_time": "1:52:08", "remaining_time": "2:21:16", "throughput": 10889.58, "total_tokens": 73269248} | |
| {"current_steps": 282, "total_steps": 635, "loss": 0.4041, "lr": 1.1747307898434877e-05, "epoch": 2.2043222003929275, "percentage": 44.41, "elapsed_time": "1:52:32", "remaining_time": "2:20:52", "throughput": 10889.66, "total_tokens": 73531392} | |
| {"current_steps": 283, "total_steps": 635, "loss": 0.4192, "lr": 1.1698573907333519e-05, "epoch": 2.212180746561886, "percentage": 44.57, "elapsed_time": "1:52:56", "remaining_time": "2:20:28", "throughput": 10889.76, "total_tokens": 73793536} | |
| {"current_steps": 284, "total_steps": 635, "loss": 0.4126, "lr": 1.1649798340887584e-05, "epoch": 2.2200392927308448, "percentage": 44.72, "elapsed_time": "1:53:20", "remaining_time": "2:20:04", "throughput": 10889.84, "total_tokens": 74055680} | |
| {"current_steps": 285, "total_steps": 635, "loss": 0.3962, "lr": 1.1600982392957978e-05, "epoch": 2.2278978388998034, "percentage": 44.88, "elapsed_time": "1:53:44", "remaining_time": "2:19:40", "throughput": 10889.83, "total_tokens": 74317824} | |
| {"current_steps": 286, "total_steps": 635, "loss": 0.3763, "lr": 1.1552127258394004e-05, "epoch": 2.235756385068762, "percentage": 45.04, "elapsed_time": "1:54:08", "remaining_time": "2:19:17", "throughput": 10889.92, "total_tokens": 74579968} | |
| {"current_steps": 287, "total_steps": 635, "loss": 0.4106, "lr": 1.1503234133004129e-05, "epoch": 2.243614931237721, "percentage": 45.2, "elapsed_time": "1:54:32", "remaining_time": "2:18:53", "throughput": 10890.0, "total_tokens": 74842112} | |
| {"current_steps": 288, "total_steps": 635, "loss": 0.4059, "lr": 1.1454304213526703e-05, "epoch": 2.25147347740668, "percentage": 45.35, "elapsed_time": "1:54:56", "remaining_time": "2:18:29", "throughput": 10890.05, "total_tokens": 75104256} | |
| {"current_steps": 289, "total_steps": 635, "loss": 0.3942, "lr": 1.1405338697600672e-05, "epoch": 2.2593320235756384, "percentage": 45.51, "elapsed_time": "1:55:20", "remaining_time": "2:18:05", "throughput": 10890.07, "total_tokens": 75366400} | |
| {"current_steps": 290, "total_steps": 635, "loss": 0.4047, "lr": 1.1356338783736256e-05, "epoch": 2.267190569744597, "percentage": 45.67, "elapsed_time": "1:55:44", "remaining_time": "2:17:41", "throughput": 10890.13, "total_tokens": 75628544} | |
| {"current_steps": 291, "total_steps": 635, "loss": 0.4023, "lr": 1.1307305671285633e-05, "epoch": 2.275049115913556, "percentage": 45.83, "elapsed_time": "1:56:08", "remaining_time": "2:17:18", "throughput": 10890.1, "total_tokens": 75890688} | |
| {"current_steps": 292, "total_steps": 635, "loss": 0.3718, "lr": 1.125824056041356e-05, "epoch": 2.282907662082515, "percentage": 45.98, "elapsed_time": "1:56:32", "remaining_time": "2:16:54", "throughput": 10890.16, "total_tokens": 76152832} | |
| {"current_steps": 293, "total_steps": 635, "loss": 0.412, "lr": 1.120914465206801e-05, "epoch": 2.2907662082514735, "percentage": 46.14, "elapsed_time": "1:56:56", "remaining_time": "2:16:30", "throughput": 10890.24, "total_tokens": 76414976} | |
| {"current_steps": 294, "total_steps": 635, "loss": 0.4119, "lr": 1.1160019147950774e-05, "epoch": 2.298624754420432, "percentage": 46.3, "elapsed_time": "1:57:20", "remaining_time": "2:16:06", "throughput": 10890.2, "total_tokens": 76677120} | |
| {"current_steps": 295, "total_steps": 635, "loss": 0.4099, "lr": 1.1110865250488047e-05, "epoch": 2.3064833005893908, "percentage": 46.46, "elapsed_time": "1:57:44", "remaining_time": "2:15:42", "throughput": 10890.25, "total_tokens": 76939264} | |
| {"current_steps": 296, "total_steps": 635, "loss": 0.4084, "lr": 1.1061684162801e-05, "epoch": 2.31434184675835, "percentage": 46.61, "elapsed_time": "1:58:09", "remaining_time": "2:15:18", "throughput": 10890.28, "total_tokens": 77201408} | |
| {"current_steps": 297, "total_steps": 635, "loss": 0.3941, "lr": 1.1012477088676322e-05, "epoch": 2.3222003929273085, "percentage": 46.77, "elapsed_time": "1:58:33", "remaining_time": "2:14:54", "throughput": 10890.35, "total_tokens": 77463552} | |
| {"current_steps": 298, "total_steps": 635, "loss": 0.3922, "lr": 1.0963245232536768e-05, "epoch": 2.330058939096267, "percentage": 46.93, "elapsed_time": "1:58:57", "remaining_time": "2:14:31", "throughput": 10890.44, "total_tokens": 77725696} | |
| {"current_steps": 299, "total_steps": 635, "loss": 0.3683, "lr": 1.0913989799411675e-05, "epoch": 2.337917485265226, "percentage": 47.09, "elapsed_time": "1:59:21", "remaining_time": "2:14:07", "throughput": 10890.5, "total_tokens": 77987840} | |
| {"current_steps": 300, "total_steps": 635, "loss": 0.3917, "lr": 1.0864711994907457e-05, "epoch": 2.345776031434185, "percentage": 47.24, "elapsed_time": "1:59:45", "remaining_time": "2:13:43", "throughput": 10890.56, "total_tokens": 78249984} | |
| {"current_steps": 301, "total_steps": 635, "loss": 0.3877, "lr": 1.0815413025178112e-05, "epoch": 2.3536345776031435, "percentage": 47.4, "elapsed_time": "2:00:09", "remaining_time": "2:13:19", "throughput": 10890.61, "total_tokens": 78512128} | |
| {"current_steps": 302, "total_steps": 635, "loss": 0.381, "lr": 1.076609409689568e-05, "epoch": 2.361493123772102, "percentage": 47.56, "elapsed_time": "2:00:33", "remaining_time": "2:12:55", "throughput": 10890.73, "total_tokens": 78774272} | |
| {"current_steps": 303, "total_steps": 635, "loss": 0.3864, "lr": 1.0716756417220735e-05, "epoch": 2.369351669941061, "percentage": 47.72, "elapsed_time": "2:00:57", "remaining_time": "2:12:31", "throughput": 10890.76, "total_tokens": 79036416} | |
| {"current_steps": 304, "total_steps": 635, "loss": 0.3911, "lr": 1.0667401193772807e-05, "epoch": 2.3772102161100195, "percentage": 47.87, "elapsed_time": "2:01:21", "remaining_time": "2:12:07", "throughput": 10890.76, "total_tokens": 79298560} | |
| {"current_steps": 305, "total_steps": 635, "loss": 0.4172, "lr": 1.0618029634600843e-05, "epoch": 2.3850687622789786, "percentage": 48.03, "elapsed_time": "2:01:45", "remaining_time": "2:11:44", "throughput": 10890.85, "total_tokens": 79560704} | |
| {"current_steps": 306, "total_steps": 635, "loss": 0.4036, "lr": 1.0568642948153635e-05, "epoch": 2.392927308447937, "percentage": 48.19, "elapsed_time": "2:02:09", "remaining_time": "2:11:20", "throughput": 10890.89, "total_tokens": 79822848} | |
| {"current_steps": 307, "total_steps": 635, "loss": 0.397, "lr": 1.0519242343250241e-05, "epoch": 2.400785854616896, "percentage": 48.35, "elapsed_time": "2:02:33", "remaining_time": "2:10:56", "throughput": 10890.93, "total_tokens": 80084992} | |
| {"current_steps": 308, "total_steps": 635, "loss": 0.4211, "lr": 1.0469829029050391e-05, "epoch": 2.4086444007858545, "percentage": 48.5, "elapsed_time": "2:02:57", "remaining_time": "2:10:32", "throughput": 10890.94, "total_tokens": 80347136} | |
| {"current_steps": 309, "total_steps": 635, "loss": 0.4088, "lr": 1.04204042150249e-05, "epoch": 2.4165029469548136, "percentage": 48.66, "elapsed_time": "2:03:21", "remaining_time": "2:10:08", "throughput": 10890.94, "total_tokens": 80609280} | |
| {"current_steps": 310, "total_steps": 635, "loss": 0.4126, "lr": 1.0370969110926052e-05, "epoch": 2.4243614931237722, "percentage": 48.82, "elapsed_time": "2:03:45", "remaining_time": "2:09:44", "throughput": 10890.92, "total_tokens": 80871424} | |
| {"current_steps": 311, "total_steps": 635, "loss": 0.4069, "lr": 1.0321524926758013e-05, "epoch": 2.432220039292731, "percentage": 48.98, "elapsed_time": "2:04:09", "remaining_time": "2:09:20", "throughput": 10891.0, "total_tokens": 81133568} | |
| {"current_steps": 312, "total_steps": 635, "loss": 0.4, "lr": 1.0272072872747181e-05, "epoch": 2.4400785854616895, "percentage": 49.13, "elapsed_time": "2:04:33", "remaining_time": "2:08:57", "throughput": 10891.01, "total_tokens": 81395712} | |
| {"current_steps": 313, "total_steps": 635, "loss": 0.4007, "lr": 1.0222614159312589e-05, "epoch": 2.447937131630648, "percentage": 49.29, "elapsed_time": "2:04:57", "remaining_time": "2:08:33", "throughput": 10891.11, "total_tokens": 81657856} | |
| {"current_steps": 314, "total_steps": 635, "loss": 0.4157, "lr": 1.0173149997036272e-05, "epoch": 2.455795677799607, "percentage": 49.45, "elapsed_time": "2:05:21", "remaining_time": "2:08:09", "throughput": 10891.23, "total_tokens": 81920000} | |
| {"current_steps": 315, "total_steps": 635, "loss": 0.4294, "lr": 1.012368159663363e-05, "epoch": 2.463654223968566, "percentage": 49.61, "elapsed_time": "2:05:45", "remaining_time": "2:07:45", "throughput": 10891.29, "total_tokens": 82182144} | |
| {"current_steps": 316, "total_steps": 635, "loss": 0.3813, "lr": 1.0074210168923804e-05, "epoch": 2.4715127701375246, "percentage": 49.76, "elapsed_time": "2:06:09", "remaining_time": "2:07:21", "throughput": 10891.38, "total_tokens": 82444288} | |
| {"current_steps": 317, "total_steps": 635, "loss": 0.3915, "lr": 1.002473692480002e-05, "epoch": 2.479371316306483, "percentage": 49.92, "elapsed_time": "2:06:33", "remaining_time": "2:06:57", "throughput": 10891.47, "total_tokens": 82706432} | |
| {"current_steps": 318, "total_steps": 635, "loss": 0.4095, "lr": 9.975263075199983e-06, "epoch": 2.487229862475442, "percentage": 50.08, "elapsed_time": "2:06:57", "remaining_time": "2:06:33", "throughput": 10891.49, "total_tokens": 82968576} | |
| {"current_steps": 319, "total_steps": 635, "loss": 0.4172, "lr": 9.925789831076202e-06, "epoch": 2.495088408644401, "percentage": 50.24, "elapsed_time": "2:07:21", "remaining_time": "2:06:09", "throughput": 10891.59, "total_tokens": 83230720} | |
| {"current_steps": 320, "total_steps": 635, "loss": 0.3937, "lr": 9.876318403366371e-06, "epoch": 2.5029469548133596, "percentage": 50.39, "elapsed_time": "2:07:45", "remaining_time": "2:05:45", "throughput": 10891.66, "total_tokens": 83492864} | |
| {"current_steps": 321, "total_steps": 635, "loss": 0.4091, "lr": 9.82685000296373e-06, "epoch": 2.5108055009823183, "percentage": 50.55, "elapsed_time": "2:08:09", "remaining_time": "2:05:22", "throughput": 10891.67, "total_tokens": 83755008} | |
| {"current_steps": 322, "total_steps": 635, "loss": 0.4102, "lr": 9.777385840687415e-06, "epoch": 2.518664047151277, "percentage": 50.71, "elapsed_time": "2:08:33", "remaining_time": "2:04:58", "throughput": 10891.79, "total_tokens": 84017152} | |
| {"current_steps": 323, "total_steps": 635, "loss": 0.3752, "lr": 9.727927127252822e-06, "epoch": 2.5265225933202355, "percentage": 50.87, "elapsed_time": "2:08:57", "remaining_time": "2:04:34", "throughput": 10891.87, "total_tokens": 84279296} | |
| {"current_steps": 324, "total_steps": 635, "loss": 0.4105, "lr": 9.678475073241987e-06, "epoch": 2.5343811394891946, "percentage": 51.02, "elapsed_time": "2:09:21", "remaining_time": "2:04:10", "throughput": 10891.91, "total_tokens": 84541440} | |
| {"current_steps": 325, "total_steps": 635, "loss": 0.4022, "lr": 9.62903088907395e-06, "epoch": 2.5422396856581533, "percentage": 51.18, "elapsed_time": "2:09:45", "remaining_time": "2:03:46", "throughput": 10891.97, "total_tokens": 84803584} | |
| {"current_steps": 326, "total_steps": 635, "loss": 0.4219, "lr": 9.579595784975102e-06, "epoch": 2.550098231827112, "percentage": 51.34, "elapsed_time": "2:10:09", "remaining_time": "2:03:22", "throughput": 10892.04, "total_tokens": 85065728} | |
| {"current_steps": 327, "total_steps": 635, "loss": 0.3942, "lr": 9.530170970949612e-06, "epoch": 2.5579567779960706, "percentage": 51.5, "elapsed_time": "2:10:33", "remaining_time": "2:02:58", "throughput": 10892.11, "total_tokens": 85327872} | |
| {"current_steps": 328, "total_steps": 635, "loss": 0.4117, "lr": 9.48075765674976e-06, "epoch": 2.5658153241650297, "percentage": 51.65, "elapsed_time": "2:10:57", "remaining_time": "2:02:34", "throughput": 10892.13, "total_tokens": 85590016} | |
| {"current_steps": 329, "total_steps": 635, "loss": 0.4101, "lr": 9.431357051846367e-06, "epoch": 2.5736738703339883, "percentage": 51.81, "elapsed_time": "2:11:22", "remaining_time": "2:02:11", "throughput": 10892.1, "total_tokens": 85852160} | |
| {"current_steps": 330, "total_steps": 635, "loss": 0.423, "lr": 9.381970365399162e-06, "epoch": 2.581532416502947, "percentage": 51.97, "elapsed_time": "2:11:46", "remaining_time": "2:01:47", "throughput": 10892.17, "total_tokens": 86114304} | |
| {"current_steps": 331, "total_steps": 635, "loss": 0.3918, "lr": 9.332598806227195e-06, "epoch": 2.5893909626719056, "percentage": 52.13, "elapsed_time": "2:12:10", "remaining_time": "2:01:23", "throughput": 10892.19, "total_tokens": 86376448} | |
| {"current_steps": 332, "total_steps": 635, "loss": 0.3953, "lr": 9.283243582779266e-06, "epoch": 2.5972495088408643, "percentage": 52.28, "elapsed_time": "2:12:34", "remaining_time": "2:00:59", "throughput": 10892.21, "total_tokens": 86638592} | |
| {"current_steps": 333, "total_steps": 635, "loss": 0.4169, "lr": 9.233905903104321e-06, "epoch": 2.6051080550098233, "percentage": 52.44, "elapsed_time": "2:12:58", "remaining_time": "2:00:35", "throughput": 10892.23, "total_tokens": 86900736} | |
| {"current_steps": 334, "total_steps": 635, "loss": 0.4146, "lr": 9.184586974821891e-06, "epoch": 2.612966601178782, "percentage": 52.6, "elapsed_time": "2:13:22", "remaining_time": "2:00:11", "throughput": 10892.22, "total_tokens": 87162880} | |
| {"current_steps": 335, "total_steps": 635, "loss": 0.4287, "lr": 9.135288005092546e-06, "epoch": 2.6208251473477406, "percentage": 52.76, "elapsed_time": "2:13:46", "remaining_time": "1:59:47", "throughput": 10892.24, "total_tokens": 87425024} | |
| {"current_steps": 336, "total_steps": 635, "loss": 0.4105, "lr": 9.086010200588328e-06, "epoch": 2.6286836935166993, "percentage": 52.91, "elapsed_time": "2:14:10", "remaining_time": "1:59:23", "throughput": 10892.32, "total_tokens": 87687168} | |
| {"current_steps": 337, "total_steps": 635, "loss": 0.3887, "lr": 9.036754767463233e-06, "epoch": 2.6365422396856584, "percentage": 53.07, "elapsed_time": "2:14:34", "remaining_time": "1:58:59", "throughput": 10892.35, "total_tokens": 87949312} | |
| {"current_steps": 338, "total_steps": 635, "loss": 0.4234, "lr": 8.987522911323681e-06, "epoch": 2.644400785854617, "percentage": 53.23, "elapsed_time": "2:14:58", "remaining_time": "1:58:36", "throughput": 10892.44, "total_tokens": 88211456} | |
| {"current_steps": 339, "total_steps": 635, "loss": 0.3682, "lr": 8.938315837199003e-06, "epoch": 2.6522593320235757, "percentage": 53.39, "elapsed_time": "2:15:22", "remaining_time": "1:58:12", "throughput": 10892.47, "total_tokens": 88473600} | |
| {"current_steps": 340, "total_steps": 635, "loss": 0.406, "lr": 8.889134749511956e-06, "epoch": 2.6601178781925343, "percentage": 53.54, "elapsed_time": "2:15:46", "remaining_time": "1:57:48", "throughput": 10892.58, "total_tokens": 88735744} | |
| {"current_steps": 341, "total_steps": 635, "loss": 0.4277, "lr": 8.83998085204923e-06, "epoch": 2.667976424361493, "percentage": 53.7, "elapsed_time": "2:16:10", "remaining_time": "1:57:24", "throughput": 10892.54, "total_tokens": 88997888} | |
| {"current_steps": 342, "total_steps": 635, "loss": 0.3848, "lr": 8.790855347931991e-06, "epoch": 2.6758349705304516, "percentage": 53.86, "elapsed_time": "2:16:34", "remaining_time": "1:57:00", "throughput": 10892.5, "total_tokens": 89260032} | |
| {"current_steps": 343, "total_steps": 635, "loss": 0.3892, "lr": 8.741759439586443e-06, "epoch": 2.6836935166994107, "percentage": 54.02, "elapsed_time": "2:16:58", "remaining_time": "1:56:36", "throughput": 10892.54, "total_tokens": 89522176} | |
| {"current_steps": 344, "total_steps": 635, "loss": 0.3988, "lr": 8.692694328714369e-06, "epoch": 2.6915520628683693, "percentage": 54.17, "elapsed_time": "2:17:22", "remaining_time": "1:56:12", "throughput": 10892.56, "total_tokens": 89784320} | |
| {"current_steps": 345, "total_steps": 635, "loss": 0.4293, "lr": 8.643661216263744e-06, "epoch": 2.699410609037328, "percentage": 54.33, "elapsed_time": "2:17:46", "remaining_time": "1:55:48", "throughput": 10892.6, "total_tokens": 90046464} | |
| {"current_steps": 346, "total_steps": 635, "loss": 0.4374, "lr": 8.594661302399333e-06, "epoch": 2.707269155206287, "percentage": 54.49, "elapsed_time": "2:18:11", "remaining_time": "1:55:25", "throughput": 10892.19, "total_tokens": 90308608} | |
| {"current_steps": 347, "total_steps": 635, "loss": 0.3974, "lr": 8.5456957864733e-06, "epoch": 2.7151277013752457, "percentage": 54.65, "elapsed_time": "2:18:35", "remaining_time": "1:55:01", "throughput": 10892.24, "total_tokens": 90570752} | |
| {"current_steps": 348, "total_steps": 635, "loss": 0.4161, "lr": 8.496765866995871e-06, "epoch": 2.7229862475442044, "percentage": 54.8, "elapsed_time": "2:18:59", "remaining_time": "1:54:37", "throughput": 10892.26, "total_tokens": 90832896} | |
| {"current_steps": 349, "total_steps": 635, "loss": 0.4083, "lr": 8.447872741606e-06, "epoch": 2.730844793713163, "percentage": 54.96, "elapsed_time": "2:19:23", "remaining_time": "1:54:13", "throughput": 10892.32, "total_tokens": 91095040} | |
| {"current_steps": 350, "total_steps": 635, "loss": 0.4209, "lr": 8.399017607042025e-06, "epoch": 2.7387033398821217, "percentage": 55.12, "elapsed_time": "2:19:47", "remaining_time": "1:53:49", "throughput": 10892.35, "total_tokens": 91357184} | |
| {"current_steps": 351, "total_steps": 635, "loss": 0.3989, "lr": 8.35020165911242e-06, "epoch": 2.7465618860510803, "percentage": 55.28, "elapsed_time": "2:20:11", "remaining_time": "1:53:25", "throughput": 10892.31, "total_tokens": 91619328} | |
| {"current_steps": 352, "total_steps": 635, "loss": 0.4138, "lr": 8.301426092666483e-06, "epoch": 2.7544204322200394, "percentage": 55.43, "elapsed_time": "2:20:35", "remaining_time": "1:53:01", "throughput": 10892.32, "total_tokens": 91881472} | |
| {"current_steps": 353, "total_steps": 635, "loss": 0.4197, "lr": 8.252692101565123e-06, "epoch": 2.762278978388998, "percentage": 55.59, "elapsed_time": "2:20:59", "remaining_time": "1:52:38", "throughput": 10892.24, "total_tokens": 92143616} | |
| {"current_steps": 354, "total_steps": 635, "loss": 0.3969, "lr": 8.204000878651626e-06, "epoch": 2.7701375245579567, "percentage": 55.75, "elapsed_time": "2:21:23", "remaining_time": "1:52:14", "throughput": 10892.25, "total_tokens": 92405760} | |
| {"current_steps": 355, "total_steps": 635, "loss": 0.3994, "lr": 8.155353615722442e-06, "epoch": 2.777996070726916, "percentage": 55.91, "elapsed_time": "2:21:47", "remaining_time": "1:51:50", "throughput": 10892.22, "total_tokens": 92667904} | |
| {"current_steps": 356, "total_steps": 635, "loss": 0.3916, "lr": 8.106751503498045e-06, "epoch": 2.7858546168958744, "percentage": 56.06, "elapsed_time": "2:22:11", "remaining_time": "1:51:26", "throughput": 10892.19, "total_tokens": 92930048} | |
| {"current_steps": 357, "total_steps": 635, "loss": 0.4028, "lr": 8.058195731593773e-06, "epoch": 2.793713163064833, "percentage": 56.22, "elapsed_time": "2:22:35", "remaining_time": "1:51:02", "throughput": 10892.29, "total_tokens": 93192192} | |
| {"current_steps": 358, "total_steps": 635, "loss": 0.4092, "lr": 8.009687488490692e-06, "epoch": 2.8015717092337917, "percentage": 56.38, "elapsed_time": "2:22:59", "remaining_time": "1:50:38", "throughput": 10892.3, "total_tokens": 93454336} | |
| {"current_steps": 359, "total_steps": 635, "loss": 0.4191, "lr": 7.961227961506543e-06, "epoch": 2.8094302554027504, "percentage": 56.54, "elapsed_time": "2:23:23", "remaining_time": "1:50:14", "throughput": 10892.34, "total_tokens": 93716480} | |
| {"current_steps": 360, "total_steps": 635, "loss": 0.4011, "lr": 7.91281833676665e-06, "epoch": 2.817288801571709, "percentage": 56.69, "elapsed_time": "2:23:47", "remaining_time": "1:49:50", "throughput": 10892.33, "total_tokens": 93978624} | |
| {"current_steps": 361, "total_steps": 635, "loss": 0.4132, "lr": 7.864459799174905e-06, "epoch": 2.825147347740668, "percentage": 56.85, "elapsed_time": "2:24:12", "remaining_time": "1:49:26", "throughput": 10892.36, "total_tokens": 94240768} | |
| {"current_steps": 362, "total_steps": 635, "loss": 0.4152, "lr": 7.81615353238476e-06, "epoch": 2.8330058939096268, "percentage": 57.01, "elapsed_time": "2:24:35", "remaining_time": "1:49:02", "throughput": 10892.45, "total_tokens": 94502912} | |
| {"current_steps": 363, "total_steps": 635, "loss": 0.411, "lr": 7.767900718770245e-06, "epoch": 2.8408644400785854, "percentage": 57.17, "elapsed_time": "2:25:00", "remaining_time": "1:48:39", "throughput": 10892.51, "total_tokens": 94765056} | |
| {"current_steps": 364, "total_steps": 635, "loss": 0.3992, "lr": 7.719702539397044e-06, "epoch": 2.848722986247544, "percentage": 57.32, "elapsed_time": "2:25:24", "remaining_time": "1:48:15", "throughput": 10892.52, "total_tokens": 95027200} | |
| {"current_steps": 365, "total_steps": 635, "loss": 0.3975, "lr": 7.671560173993588e-06, "epoch": 2.856581532416503, "percentage": 57.48, "elapsed_time": "2:25:48", "remaining_time": "1:47:51", "throughput": 10892.63, "total_tokens": 95289344} | |
| {"current_steps": 366, "total_steps": 635, "loss": 0.392, "lr": 7.62347480092215e-06, "epoch": 2.864440078585462, "percentage": 57.64, "elapsed_time": "2:26:12", "remaining_time": "1:47:27", "throughput": 10892.67, "total_tokens": 95551488} | |
| {"current_steps": 367, "total_steps": 635, "loss": 0.4133, "lr": 7.575447597150045e-06, "epoch": 2.8722986247544204, "percentage": 57.8, "elapsed_time": "2:26:36", "remaining_time": "1:47:03", "throughput": 10892.7, "total_tokens": 95813632} | |
| {"current_steps": 368, "total_steps": 635, "loss": 0.4037, "lr": 7.527479738220781e-06, "epoch": 2.880157170923379, "percentage": 57.95, "elapsed_time": "2:27:00", "remaining_time": "1:46:39", "throughput": 10892.74, "total_tokens": 96075776} | |
| {"current_steps": 369, "total_steps": 635, "loss": 0.4068, "lr": 7.479572398225321e-06, "epoch": 2.8880157170923377, "percentage": 58.11, "elapsed_time": "2:27:24", "remaining_time": "1:46:15", "throughput": 10892.82, "total_tokens": 96337920} | |
| {"current_steps": 370, "total_steps": 635, "loss": 0.4022, "lr": 7.431726749773322e-06, "epoch": 2.895874263261297, "percentage": 58.27, "elapsed_time": "2:27:48", "remaining_time": "1:45:51", "throughput": 10892.83, "total_tokens": 96600064} | |
| {"current_steps": 371, "total_steps": 635, "loss": 0.4168, "lr": 7.383943963964439e-06, "epoch": 2.9037328094302555, "percentage": 58.43, "elapsed_time": "2:28:12", "remaining_time": "1:45:27", "throughput": 10892.82, "total_tokens": 96862208} | |
| {"current_steps": 372, "total_steps": 635, "loss": 0.4123, "lr": 7.336225210359666e-06, "epoch": 2.911591355599214, "percentage": 58.58, "elapsed_time": "2:28:36", "remaining_time": "1:45:03", "throughput": 10892.88, "total_tokens": 97124352} | |
| {"current_steps": 373, "total_steps": 635, "loss": 0.4046, "lr": 7.288571656952708e-06, "epoch": 2.9194499017681728, "percentage": 58.74, "elapsed_time": "2:29:00", "remaining_time": "1:44:39", "throughput": 10892.88, "total_tokens": 97386496} | |
| {"current_steps": 374, "total_steps": 635, "loss": 0.3987, "lr": 7.240984470141378e-06, "epoch": 2.927308447937132, "percentage": 58.9, "elapsed_time": "2:29:24", "remaining_time": "1:44:15", "throughput": 10892.88, "total_tokens": 97648640} | |
| {"current_steps": 375, "total_steps": 635, "loss": 0.3882, "lr": 7.193464814699073e-06, "epoch": 2.9351669941060905, "percentage": 59.06, "elapsed_time": "2:29:48", "remaining_time": "1:43:52", "throughput": 10892.9, "total_tokens": 97910784} | |
| {"current_steps": 376, "total_steps": 635, "loss": 0.4016, "lr": 7.146013853746236e-06, "epoch": 2.943025540275049, "percentage": 59.21, "elapsed_time": "2:30:12", "remaining_time": "1:43:28", "throughput": 10892.81, "total_tokens": 98172928} | |
| {"current_steps": 377, "total_steps": 635, "loss": 0.4026, "lr": 7.098632748721914e-06, "epoch": 2.950884086444008, "percentage": 59.37, "elapsed_time": "2:30:36", "remaining_time": "1:43:04", "throughput": 10892.86, "total_tokens": 98435072} | |
| {"current_steps": 378, "total_steps": 635, "loss": 0.4059, "lr": 7.0513226593553175e-06, "epoch": 2.9587426326129664, "percentage": 59.53, "elapsed_time": "2:31:00", "remaining_time": "1:42:40", "throughput": 10892.88, "total_tokens": 98697216} | |
| {"current_steps": 379, "total_steps": 635, "loss": 0.4226, "lr": 7.00408474363742e-06, "epoch": 2.966601178781925, "percentage": 59.69, "elapsed_time": "2:31:24", "remaining_time": "1:42:16", "throughput": 10892.92, "total_tokens": 98959360} | |
| {"current_steps": 380, "total_steps": 635, "loss": 0.3966, "lr": 6.9569201577926395e-06, "epoch": 2.974459724950884, "percentage": 59.84, "elapsed_time": "2:31:48", "remaining_time": "1:41:52", "throughput": 10892.95, "total_tokens": 99221504} | |
| {"current_steps": 381, "total_steps": 635, "loss": 0.4071, "lr": 6.909830056250527e-06, "epoch": 2.982318271119843, "percentage": 60.0, "elapsed_time": "2:32:12", "remaining_time": "1:41:28", "throughput": 10892.99, "total_tokens": 99483648} | |
| {"current_steps": 382, "total_steps": 635, "loss": 0.3819, "lr": 6.862815591617503e-06, "epoch": 2.9901768172888015, "percentage": 60.16, "elapsed_time": "2:32:36", "remaining_time": "1:41:04", "throughput": 10893.01, "total_tokens": 99745792} | |
| {"current_steps": 383, "total_steps": 635, "loss": 0.3989, "lr": 6.815877914648663e-06, "epoch": 2.9980353634577606, "percentage": 60.31, "elapsed_time": "2:33:00", "remaining_time": "1:40:40", "throughput": 10893.02, "total_tokens": 100007936} | |
| {"current_steps": 384, "total_steps": 635, "loss": 0.3563, "lr": 6.769018174219584e-06, "epoch": 3.0, "percentage": 60.47, "elapsed_time": "2:33:06", "remaining_time": "1:40:04", "throughput": 10893.09, "total_tokens": 100073472} | |
| {"current_steps": 385, "total_steps": 635, "loss": 0.217, "lr": 6.722237517298232e-06, "epoch": 3.0078585461689586, "percentage": 60.63, "elapsed_time": "2:33:30", "remaining_time": "1:39:41", "throughput": 10893.07, "total_tokens": 100335616} | |
| {"current_steps": 386, "total_steps": 635, "loss": 0.2392, "lr": 6.6755370889168816e-06, "epoch": 3.0157170923379173, "percentage": 60.79, "elapsed_time": "2:33:55", "remaining_time": "1:39:17", "throughput": 10893.06, "total_tokens": 100597760} | |
| {"current_steps": 387, "total_steps": 635, "loss": 0.2208, "lr": 6.628918032144064e-06, "epoch": 3.0235756385068764, "percentage": 60.94, "elapsed_time": "2:34:19", "remaining_time": "1:38:53", "throughput": 10893.04, "total_tokens": 100859904} | |
| {"current_steps": 388, "total_steps": 635, "loss": 0.2105, "lr": 6.582381488056627e-06, "epoch": 3.031434184675835, "percentage": 61.1, "elapsed_time": "2:34:43", "remaining_time": "1:38:29", "throughput": 10893.06, "total_tokens": 101122048} | |
| {"current_steps": 389, "total_steps": 635, "loss": 0.2035, "lr": 6.535928595711785e-06, "epoch": 3.0392927308447937, "percentage": 61.26, "elapsed_time": "2:35:07", "remaining_time": "1:38:05", "throughput": 10893.01, "total_tokens": 101384192} | |
| {"current_steps": 390, "total_steps": 635, "loss": 0.1981, "lr": 6.489560492119225e-06, "epoch": 3.0471512770137523, "percentage": 61.42, "elapsed_time": "2:35:31", "remaining_time": "1:37:41", "throughput": 10893.01, "total_tokens": 101646336} | |
| {"current_steps": 391, "total_steps": 635, "loss": 0.2132, "lr": 6.4432783122133124e-06, "epoch": 3.0550098231827114, "percentage": 61.57, "elapsed_time": "2:35:55", "remaining_time": "1:37:18", "throughput": 10892.92, "total_tokens": 101908480} | |
| {"current_steps": 392, "total_steps": 635, "loss": 0.2075, "lr": 6.397083188825278e-06, "epoch": 3.06286836935167, "percentage": 61.73, "elapsed_time": "2:36:19", "remaining_time": "1:36:54", "throughput": 10892.95, "total_tokens": 102170624} | |
| {"current_steps": 393, "total_steps": 635, "loss": 0.2179, "lr": 6.35097625265551e-06, "epoch": 3.0707269155206287, "percentage": 61.89, "elapsed_time": "2:36:43", "remaining_time": "1:36:30", "throughput": 10893.02, "total_tokens": 102432768} | |
| {"current_steps": 394, "total_steps": 635, "loss": 0.2171, "lr": 6.304958632245871e-06, "epoch": 3.0785854616895874, "percentage": 62.05, "elapsed_time": "2:37:07", "remaining_time": "1:36:06", "throughput": 10893.01, "total_tokens": 102694912} | |
| {"current_steps": 395, "total_steps": 635, "loss": 0.2088, "lr": 6.2590314539520695e-06, "epoch": 3.086444007858546, "percentage": 62.2, "elapsed_time": "2:37:31", "remaining_time": "1:35:42", "throughput": 10893.05, "total_tokens": 102957056} | |
| {"current_steps": 396, "total_steps": 635, "loss": 0.2077, "lr": 6.213195841916104e-06, "epoch": 3.094302554027505, "percentage": 62.36, "elapsed_time": "2:37:55", "remaining_time": "1:35:18", "throughput": 10893.12, "total_tokens": 103219200} | |
| {"current_steps": 397, "total_steps": 635, "loss": 0.1957, "lr": 6.167452918038744e-06, "epoch": 3.1021611001964637, "percentage": 62.52, "elapsed_time": "2:38:19", "remaining_time": "1:34:55", "throughput": 10893.16, "total_tokens": 103481344} | |
| {"current_steps": 398, "total_steps": 635, "loss": 0.2255, "lr": 6.121803801952049e-06, "epoch": 3.1100196463654224, "percentage": 62.68, "elapsed_time": "2:38:44", "remaining_time": "1:34:31", "throughput": 10892.52, "total_tokens": 103743488} | |
| {"current_steps": 399, "total_steps": 635, "loss": 0.2002, "lr": 6.076249610992002e-06, "epoch": 3.117878192534381, "percentage": 62.83, "elapsed_time": "2:39:08", "remaining_time": "1:34:07", "throughput": 10892.17, "total_tokens": 104005632} | |
| {"current_steps": 400, "total_steps": 635, "loss": 0.2069, "lr": 6.03079146017113e-06, "epoch": 3.1257367387033397, "percentage": 62.99, "elapsed_time": "2:39:32", "remaining_time": "1:33:43", "throughput": 10892.21, "total_tokens": 104267776} | |
| {"current_steps": 401, "total_steps": 635, "loss": 0.2208, "lr": 5.985430462151219e-06, "epoch": 3.1335952848722988, "percentage": 63.15, "elapsed_time": "2:39:56", "remaining_time": "1:33:20", "throughput": 10892.29, "total_tokens": 104529920} | |
| {"current_steps": 402, "total_steps": 635, "loss": 0.1957, "lr": 5.940167727216091e-06, "epoch": 3.1414538310412574, "percentage": 63.31, "elapsed_time": "2:40:20", "remaining_time": "1:32:56", "throughput": 10892.34, "total_tokens": 104792064} | |
| {"current_steps": 403, "total_steps": 635, "loss": 0.1992, "lr": 5.895004363244413e-06, "epoch": 3.149312377210216, "percentage": 63.46, "elapsed_time": "2:40:44", "remaining_time": "1:32:32", "throughput": 10892.41, "total_tokens": 105054208} | |
| {"current_steps": 404, "total_steps": 635, "loss": 0.2005, "lr": 5.849941475682591e-06, "epoch": 3.1571709233791747, "percentage": 63.62, "elapsed_time": "2:41:08", "remaining_time": "1:32:08", "throughput": 10892.4, "total_tokens": 105316352} | |
| {"current_steps": 405, "total_steps": 635, "loss": 0.2056, "lr": 5.804980167517712e-06, "epoch": 3.165029469548134, "percentage": 63.78, "elapsed_time": "2:41:32", "remaining_time": "1:31:44", "throughput": 10892.42, "total_tokens": 105578496} | |
| {"current_steps": 406, "total_steps": 635, "loss": 0.2113, "lr": 5.760121539250532e-06, "epoch": 3.1728880157170924, "percentage": 63.94, "elapsed_time": "2:41:56", "remaining_time": "1:31:20", "throughput": 10892.47, "total_tokens": 105840640} | |
| {"current_steps": 407, "total_steps": 635, "loss": 0.2079, "lr": 5.7153666888685576e-06, "epoch": 3.180746561886051, "percentage": 64.09, "elapsed_time": "2:42:20", "remaining_time": "1:30:56", "throughput": 10892.49, "total_tokens": 106102784} | |
| {"current_steps": 408, "total_steps": 635, "loss": 0.1997, "lr": 5.670716711819159e-06, "epoch": 3.1886051080550097, "percentage": 64.25, "elapsed_time": "2:42:44", "remaining_time": "1:30:32", "throughput": 10892.56, "total_tokens": 106364928} | |
| {"current_steps": 409, "total_steps": 635, "loss": 0.2298, "lr": 5.626172700982775e-06, "epoch": 3.1964636542239684, "percentage": 64.41, "elapsed_time": "2:43:08", "remaining_time": "1:30:09", "throughput": 10892.58, "total_tokens": 106627072} | |
| {"current_steps": 410, "total_steps": 635, "loss": 0.1887, "lr": 5.581735746646134e-06, "epoch": 3.2043222003929275, "percentage": 64.57, "elapsed_time": "2:43:33", "remaining_time": "1:29:45", "throughput": 10892.61, "total_tokens": 106889216} | |
| {"current_steps": 411, "total_steps": 635, "loss": 0.1845, "lr": 5.537406936475592e-06, "epoch": 3.212180746561886, "percentage": 64.72, "elapsed_time": "2:43:56", "remaining_time": "1:29:21", "throughput": 10892.69, "total_tokens": 107151360} | |
| {"current_steps": 412, "total_steps": 635, "loss": 0.1956, "lr": 5.493187355490495e-06, "epoch": 3.2200392927308448, "percentage": 64.88, "elapsed_time": "2:44:21", "remaining_time": "1:28:57", "throughput": 10892.73, "total_tokens": 107413504} | |
| {"current_steps": 413, "total_steps": 635, "loss": 0.1893, "lr": 5.449078086036643e-06, "epoch": 3.2278978388998034, "percentage": 65.04, "elapsed_time": "2:44:45", "remaining_time": "1:28:33", "throughput": 10892.8, "total_tokens": 107675648} | |
| {"current_steps": 414, "total_steps": 635, "loss": 0.1863, "lr": 5.405080207759759e-06, "epoch": 3.235756385068762, "percentage": 65.2, "elapsed_time": "2:45:09", "remaining_time": "1:28:09", "throughput": 10892.82, "total_tokens": 107937792} | |
| {"current_steps": 415, "total_steps": 635, "loss": 0.2129, "lr": 5.361194797579108e-06, "epoch": 3.243614931237721, "percentage": 65.35, "elapsed_time": "2:45:33", "remaining_time": "1:27:45", "throughput": 10892.87, "total_tokens": 108199936} | |
| {"current_steps": 416, "total_steps": 635, "loss": 0.2094, "lr": 5.3174229296611064e-06, "epoch": 3.25147347740668, "percentage": 65.51, "elapsed_time": "2:45:57", "remaining_time": "1:27:21", "throughput": 10892.77, "total_tokens": 108462080} | |
| {"current_steps": 417, "total_steps": 635, "loss": 0.2076, "lr": 5.273765675393042e-06, "epoch": 3.2593320235756384, "percentage": 65.67, "elapsed_time": "2:46:21", "remaining_time": "1:26:58", "throughput": 10892.72, "total_tokens": 108724224} | |
| {"current_steps": 418, "total_steps": 635, "loss": 0.2075, "lr": 5.2302241033568476e-06, "epoch": 3.267190569744597, "percentage": 65.83, "elapsed_time": "2:46:45", "remaining_time": "1:26:34", "throughput": 10892.74, "total_tokens": 108986368} | |
| {"current_steps": 419, "total_steps": 635, "loss": 0.2007, "lr": 5.1867992793029435e-06, "epoch": 3.275049115913556, "percentage": 65.98, "elapsed_time": "2:47:09", "remaining_time": "1:26:10", "throughput": 10892.78, "total_tokens": 109248512} | |
| {"current_steps": 420, "total_steps": 635, "loss": 0.2058, "lr": 5.143492266124164e-06, "epoch": 3.282907662082515, "percentage": 66.14, "elapsed_time": "2:47:33", "remaining_time": "1:25:46", "throughput": 10892.72, "total_tokens": 109510656} | |
| {"current_steps": 421, "total_steps": 635, "loss": 0.1832, "lr": 5.10030412382972e-06, "epoch": 3.2907662082514735, "percentage": 66.3, "elapsed_time": "2:47:57", "remaining_time": "1:25:22", "throughput": 10892.82, "total_tokens": 109772800} | |
| {"current_steps": 422, "total_steps": 635, "loss": 0.2025, "lr": 5.057235909519271e-06, "epoch": 3.298624754420432, "percentage": 66.46, "elapsed_time": "2:48:21", "remaining_time": "1:24:58", "throughput": 10892.87, "total_tokens": 110034944} | |
| {"current_steps": 423, "total_steps": 635, "loss": 0.1908, "lr": 5.014288677357046e-06, "epoch": 3.3064833005893908, "percentage": 66.61, "elapsed_time": "2:48:45", "remaining_time": "1:24:34", "throughput": 10892.9, "total_tokens": 110297088} | |
| {"current_steps": 424, "total_steps": 635, "loss": 0.2067, "lr": 4.971463478546037e-06, "epoch": 3.31434184675835, "percentage": 66.77, "elapsed_time": "2:49:09", "remaining_time": "1:24:10", "throughput": 10892.91, "total_tokens": 110559232} | |
| {"current_steps": 425, "total_steps": 635, "loss": 0.1923, "lr": 4.928761361302269e-06, "epoch": 3.3222003929273085, "percentage": 66.93, "elapsed_time": "2:49:33", "remaining_time": "1:23:47", "throughput": 10892.9, "total_tokens": 110821376} | |
| {"current_steps": 426, "total_steps": 635, "loss": 0.2089, "lr": 4.886183370829159e-06, "epoch": 3.330058939096267, "percentage": 67.09, "elapsed_time": "2:49:57", "remaining_time": "1:23:23", "throughput": 10892.87, "total_tokens": 111083520} | |
| {"current_steps": 427, "total_steps": 635, "loss": 0.223, "lr": 4.843730549291909e-06, "epoch": 3.337917485265226, "percentage": 67.24, "elapsed_time": "2:50:21", "remaining_time": "1:22:59", "throughput": 10892.87, "total_tokens": 111345664} | |
| {"current_steps": 428, "total_steps": 635, "loss": 0.2036, "lr": 4.801403935792013e-06, "epoch": 3.345776031434185, "percentage": 67.4, "elapsed_time": "2:50:45", "remaining_time": "1:22:35", "throughput": 10892.89, "total_tokens": 111607808} | |
| {"current_steps": 429, "total_steps": 635, "loss": 0.2096, "lr": 4.7592045663418175e-06, "epoch": 3.3536345776031435, "percentage": 67.56, "elapsed_time": "2:51:09", "remaining_time": "1:22:11", "throughput": 10892.93, "total_tokens": 111869952} | |
| {"current_steps": 430, "total_steps": 635, "loss": 0.2028, "lr": 4.717133473839163e-06, "epoch": 3.361493123772102, "percentage": 67.72, "elapsed_time": "2:51:33", "remaining_time": "1:21:47", "throughput": 10893.0, "total_tokens": 112132096} | |
| {"current_steps": 431, "total_steps": 635, "loss": 0.1908, "lr": 4.675191688042118e-06, "epoch": 3.369351669941061, "percentage": 67.87, "elapsed_time": "2:51:58", "remaining_time": "1:21:23", "throughput": 10892.99, "total_tokens": 112394240} | |
| {"current_steps": 432, "total_steps": 635, "loss": 0.2045, "lr": 4.633380235543733e-06, "epoch": 3.3772102161100195, "percentage": 68.03, "elapsed_time": "2:52:22", "remaining_time": "1:20:59", "throughput": 10892.98, "total_tokens": 112656384} | |
| {"current_steps": 433, "total_steps": 635, "loss": 0.2034, "lr": 4.59170013974697e-06, "epoch": 3.3850687622789786, "percentage": 68.19, "elapsed_time": "2:52:46", "remaining_time": "1:20:35", "throughput": 10893.02, "total_tokens": 112918528} | |
| {"current_steps": 434, "total_steps": 635, "loss": 0.1912, "lr": 4.550152420839604e-06, "epoch": 3.392927308447937, "percentage": 68.35, "elapsed_time": "2:53:10", "remaining_time": "1:20:12", "throughput": 10893.09, "total_tokens": 113180672} | |
| {"current_steps": 435, "total_steps": 635, "loss": 0.2045, "lr": 4.508738095769278e-06, "epoch": 3.400785854616896, "percentage": 68.5, "elapsed_time": "2:53:34", "remaining_time": "1:19:48", "throughput": 10893.11, "total_tokens": 113442816} | |
| {"current_steps": 436, "total_steps": 635, "loss": 0.2065, "lr": 4.4674581782186e-06, "epoch": 3.4086444007858545, "percentage": 68.66, "elapsed_time": "2:53:58", "remaining_time": "1:19:24", "throughput": 10893.16, "total_tokens": 113704960} | |
| {"current_steps": 437, "total_steps": 635, "loss": 0.1832, "lr": 4.42631367858035e-06, "epoch": 3.4165029469548136, "percentage": 68.82, "elapsed_time": "2:54:22", "remaining_time": "1:19:00", "throughput": 10893.19, "total_tokens": 113967104} | |
| {"current_steps": 438, "total_steps": 635, "loss": 0.2016, "lr": 4.385305603932718e-06, "epoch": 3.4243614931237722, "percentage": 68.98, "elapsed_time": "2:54:46", "remaining_time": "1:18:36", "throughput": 10893.25, "total_tokens": 114229248} | |
| {"current_steps": 439, "total_steps": 635, "loss": 0.2129, "lr": 4.3444349580146836e-06, "epoch": 3.432220039292731, "percentage": 69.13, "elapsed_time": "2:55:10", "remaining_time": "1:18:12", "throughput": 10893.29, "total_tokens": 114491392} | |
| {"current_steps": 440, "total_steps": 635, "loss": 0.1916, "lr": 4.303702741201431e-06, "epoch": 3.4400785854616895, "percentage": 69.29, "elapsed_time": "2:55:34", "remaining_time": "1:17:48", "throughput": 10893.33, "total_tokens": 114753536} | |
| {"current_steps": 441, "total_steps": 635, "loss": 0.1836, "lr": 4.263109950479864e-06, "epoch": 3.447937131630648, "percentage": 69.45, "elapsed_time": "2:55:58", "remaining_time": "1:17:24", "throughput": 10893.3, "total_tokens": 115015680} | |
| {"current_steps": 442, "total_steps": 635, "loss": 0.1977, "lr": 4.222657579424225e-06, "epoch": 3.455795677799607, "percentage": 69.61, "elapsed_time": "2:56:22", "remaining_time": "1:17:00", "throughput": 10893.31, "total_tokens": 115277824} | |
| {"current_steps": 443, "total_steps": 635, "loss": 0.2249, "lr": 4.18234661817173e-06, "epoch": 3.463654223968566, "percentage": 69.76, "elapsed_time": "2:56:46", "remaining_time": "1:16:36", "throughput": 10893.32, "total_tokens": 115539968} | |
| {"current_steps": 444, "total_steps": 635, "loss": 0.19, "lr": 4.1421780533983865e-06, "epoch": 3.4715127701375246, "percentage": 69.92, "elapsed_time": "2:57:10", "remaining_time": "1:16:13", "throughput": 10893.32, "total_tokens": 115802112} | |
| {"current_steps": 445, "total_steps": 635, "loss": 0.2043, "lr": 4.1021528682948064e-06, "epoch": 3.479371316306483, "percentage": 70.08, "elapsed_time": "2:57:34", "remaining_time": "1:15:49", "throughput": 10893.33, "total_tokens": 116064256} | |
| {"current_steps": 446, "total_steps": 635, "loss": 0.2009, "lr": 4.062272042542151e-06, "epoch": 3.487229862475442, "percentage": 70.24, "elapsed_time": "2:57:58", "remaining_time": "1:15:25", "throughput": 10893.36, "total_tokens": 116326400} | |
| {"current_steps": 447, "total_steps": 635, "loss": 0.1952, "lr": 4.022536552288158e-06, "epoch": 3.495088408644401, "percentage": 70.39, "elapsed_time": "2:58:22", "remaining_time": "1:15:01", "throughput": 10893.37, "total_tokens": 116588544} | |
| {"current_steps": 448, "total_steps": 635, "loss": 0.1927, "lr": 3.982947370123236e-06, "epoch": 3.5029469548133596, "percentage": 70.55, "elapsed_time": "2:58:46", "remaining_time": "1:14:37", "throughput": 10893.39, "total_tokens": 116850688} | |
| {"current_steps": 449, "total_steps": 635, "loss": 0.2022, "lr": 3.943505465056677e-06, "epoch": 3.5108055009823183, "percentage": 70.71, "elapsed_time": "2:59:10", "remaining_time": "1:14:13", "throughput": 10893.4, "total_tokens": 117112832} | |
| {"current_steps": 450, "total_steps": 635, "loss": 0.2075, "lr": 3.904211802492922e-06, "epoch": 3.518664047151277, "percentage": 70.87, "elapsed_time": "2:59:34", "remaining_time": "1:13:49", "throughput": 10893.41, "total_tokens": 117374976} | |
| {"current_steps": 451, "total_steps": 635, "loss": 0.2012, "lr": 3.865067344207935e-06, "epoch": 3.5265225933202355, "percentage": 71.02, "elapsed_time": "2:59:58", "remaining_time": "1:13:25", "throughput": 10893.43, "total_tokens": 117637120} | |
| {"current_steps": 452, "total_steps": 635, "loss": 0.1738, "lr": 3.826073048325664e-06, "epoch": 3.5343811394891946, "percentage": 71.18, "elapsed_time": "3:00:22", "remaining_time": "1:13:01", "throughput": 10893.5, "total_tokens": 117899264} | |
| {"current_steps": 453, "total_steps": 635, "loss": 0.2193, "lr": 3.7872298692945995e-06, "epoch": 3.5422396856581533, "percentage": 71.34, "elapsed_time": "3:00:46", "remaining_time": "1:12:37", "throughput": 10893.54, "total_tokens": 118161408} | |
| {"current_steps": 454, "total_steps": 635, "loss": 0.2003, "lr": 3.748538757864383e-06, "epoch": 3.550098231827112, "percentage": 71.5, "elapsed_time": "3:01:10", "remaining_time": "1:12:14", "throughput": 10893.57, "total_tokens": 118423552} | |
| {"current_steps": 455, "total_steps": 635, "loss": 0.2098, "lr": 3.710000661062578e-06, "epoch": 3.5579567779960706, "percentage": 71.65, "elapsed_time": "3:01:35", "remaining_time": "1:11:50", "throughput": 10893.59, "total_tokens": 118685696} | |
| {"current_steps": 456, "total_steps": 635, "loss": 0.1836, "lr": 3.671616522171445e-06, "epoch": 3.5658153241650297, "percentage": 71.81, "elapsed_time": "3:01:59", "remaining_time": "1:11:26", "throughput": 10893.62, "total_tokens": 118947840} | |
| {"current_steps": 457, "total_steps": 635, "loss": 0.1831, "lr": 3.633387280704895e-06, "epoch": 3.5736738703339883, "percentage": 71.97, "elapsed_time": "3:02:23", "remaining_time": "1:11:02", "throughput": 10893.68, "total_tokens": 119209984} | |
| {"current_steps": 458, "total_steps": 635, "loss": 0.2039, "lr": 3.595313872385463e-06, "epoch": 3.581532416502947, "percentage": 72.13, "elapsed_time": "3:02:47", "remaining_time": "1:10:38", "throughput": 10893.69, "total_tokens": 119472128} | |
| {"current_steps": 459, "total_steps": 635, "loss": 0.1971, "lr": 3.5573972291214154e-06, "epoch": 3.5893909626719056, "percentage": 72.28, "elapsed_time": "3:03:11", "remaining_time": "1:10:14", "throughput": 10893.67, "total_tokens": 119734272} | |
| {"current_steps": 460, "total_steps": 635, "loss": 0.2267, "lr": 3.5196382789839477e-06, "epoch": 3.5972495088408643, "percentage": 72.44, "elapsed_time": "3:03:35", "remaining_time": "1:09:50", "throughput": 10893.66, "total_tokens": 119996416} | |
| {"current_steps": 461, "total_steps": 635, "loss": 0.2159, "lr": 3.4820379461844555e-06, "epoch": 3.6051080550098233, "percentage": 72.6, "elapsed_time": "3:03:59", "remaining_time": "1:09:26", "throughput": 10893.65, "total_tokens": 120258560} | |
| {"current_steps": 462, "total_steps": 635, "loss": 0.2097, "lr": 3.444597151051917e-06, "epoch": 3.612966601178782, "percentage": 72.76, "elapsed_time": "3:04:23", "remaining_time": "1:09:02", "throughput": 10893.63, "total_tokens": 120520704} | |
| {"current_steps": 463, "total_steps": 635, "loss": 0.2045, "lr": 3.4073168100103725e-06, "epoch": 3.6208251473477406, "percentage": 72.91, "elapsed_time": "3:04:47", "remaining_time": "1:08:38", "throughput": 10893.64, "total_tokens": 120782848} | |
| {"current_steps": 464, "total_steps": 635, "loss": 0.2094, "lr": 3.370197835556485e-06, "epoch": 3.6286836935166993, "percentage": 73.07, "elapsed_time": "3:05:11", "remaining_time": "1:08:14", "throughput": 10893.65, "total_tokens": 121044992} | |
| {"current_steps": 465, "total_steps": 635, "loss": 0.1824, "lr": 3.3332411362372063e-06, "epoch": 3.6365422396856584, "percentage": 73.23, "elapsed_time": "3:05:35", "remaining_time": "1:07:51", "throughput": 10893.58, "total_tokens": 121307136} | |
| {"current_steps": 466, "total_steps": 635, "loss": 0.1914, "lr": 3.2964476166275572e-06, "epoch": 3.644400785854617, "percentage": 73.39, "elapsed_time": "3:05:59", "remaining_time": "1:07:27", "throughput": 10893.58, "total_tokens": 121569280} | |
| {"current_steps": 467, "total_steps": 635, "loss": 0.1985, "lr": 3.259818177308447e-06, "epoch": 3.6522593320235757, "percentage": 73.54, "elapsed_time": "3:06:23", "remaining_time": "1:07:03", "throughput": 10893.58, "total_tokens": 121831424} | |
| {"current_steps": 468, "total_steps": 635, "loss": 0.2007, "lr": 3.223353714844678e-06, "epoch": 3.6601178781925343, "percentage": 73.7, "elapsed_time": "3:06:47", "remaining_time": "1:06:39", "throughput": 10893.55, "total_tokens": 122093568} | |
| {"current_steps": 469, "total_steps": 635, "loss": 0.1807, "lr": 3.1870551217629608e-06, "epoch": 3.667976424361493, "percentage": 73.86, "elapsed_time": "3:07:11", "remaining_time": "1:06:15", "throughput": 10893.57, "total_tokens": 122355712} | |
| {"current_steps": 470, "total_steps": 635, "loss": 0.2121, "lr": 3.1509232865300886e-06, "epoch": 3.6758349705304516, "percentage": 74.02, "elapsed_time": "3:07:35", "remaining_time": "1:05:51", "throughput": 10893.58, "total_tokens": 122617856} | |
| {"current_steps": 471, "total_steps": 635, "loss": 0.2084, "lr": 3.1149590935311968e-06, "epoch": 3.6836935166994107, "percentage": 74.17, "elapsed_time": "3:08:00", "remaining_time": "1:05:27", "throughput": 10893.59, "total_tokens": 122880000} | |
| {"current_steps": 472, "total_steps": 635, "loss": 0.2026, "lr": 3.079163423048085e-06, "epoch": 3.6915520628683693, "percentage": 74.33, "elapsed_time": "3:08:24", "remaining_time": "1:05:03", "throughput": 10893.54, "total_tokens": 123142144} | |
| {"current_steps": 473, "total_steps": 635, "loss": 0.1761, "lr": 3.043537151237712e-06, "epoch": 3.699410609037328, "percentage": 74.49, "elapsed_time": "3:08:48", "remaining_time": "1:04:39", "throughput": 10893.59, "total_tokens": 123404288} | |
| {"current_steps": 474, "total_steps": 635, "loss": 0.1898, "lr": 3.0080811501107187e-06, "epoch": 3.707269155206287, "percentage": 74.65, "elapsed_time": "3:09:12", "remaining_time": "1:04:15", "throughput": 10893.57, "total_tokens": 123666432} | |
| {"current_steps": 475, "total_steps": 635, "loss": 0.1898, "lr": 2.9727962875101e-06, "epoch": 3.7151277013752457, "percentage": 74.8, "elapsed_time": "3:09:36", "remaining_time": "1:03:52", "throughput": 10893.58, "total_tokens": 123928576} | |
| {"current_steps": 476, "total_steps": 635, "loss": 0.1983, "lr": 2.9376834270899523e-06, "epoch": 3.7229862475442044, "percentage": 74.96, "elapsed_time": "3:10:00", "remaining_time": "1:03:28", "throughput": 10893.55, "total_tokens": 124190720} | |
| {"current_steps": 477, "total_steps": 635, "loss": 0.2023, "lr": 2.9027434282943555e-06, "epoch": 3.730844793713163, "percentage": 75.12, "elapsed_time": "3:10:24", "remaining_time": "1:03:04", "throughput": 10893.59, "total_tokens": 124452864} | |
| {"current_steps": 478, "total_steps": 635, "loss": 0.1949, "lr": 2.8679771463362973e-06, "epoch": 3.7387033398821217, "percentage": 75.28, "elapsed_time": "3:10:48", "remaining_time": "1:02:40", "throughput": 10893.58, "total_tokens": 124715008} | |
| {"current_steps": 479, "total_steps": 635, "loss": 0.2069, "lr": 2.8333854321767884e-06, "epoch": 3.7465618860510803, "percentage": 75.43, "elapsed_time": "3:11:12", "remaining_time": "1:02:16", "throughput": 10893.55, "total_tokens": 124977152} | |
| {"current_steps": 480, "total_steps": 635, "loss": 0.2032, "lr": 2.798969132503997e-06, "epoch": 3.7544204322200394, "percentage": 75.59, "elapsed_time": "3:11:36", "remaining_time": "1:01:52", "throughput": 10893.52, "total_tokens": 125239296} | |
| {"current_steps": 481, "total_steps": 635, "loss": 0.2037, "lr": 2.764729089712538e-06, "epoch": 3.762278978388998, "percentage": 75.75, "elapsed_time": "3:12:00", "remaining_time": "1:01:28", "throughput": 10893.51, "total_tokens": 125501440} | |
| {"current_steps": 482, "total_steps": 635, "loss": 0.2019, "lr": 2.730666141882866e-06, "epoch": 3.7701375245579567, "percentage": 75.91, "elapsed_time": "3:12:24", "remaining_time": "1:01:04", "throughput": 10893.54, "total_tokens": 125763584} | |
| {"current_steps": 483, "total_steps": 635, "loss": 0.1954, "lr": 2.6967811227607297e-06, "epoch": 3.777996070726916, "percentage": 76.06, "elapsed_time": "3:12:48", "remaining_time": "1:00:40", "throughput": 10893.6, "total_tokens": 126025728} | |
| {"current_steps": 484, "total_steps": 635, "loss": 0.1925, "lr": 2.6630748617368053e-06, "epoch": 3.7858546168958744, "percentage": 76.22, "elapsed_time": "3:13:12", "remaining_time": "1:00:16", "throughput": 10893.6, "total_tokens": 126287872} | |
| {"current_steps": 485, "total_steps": 635, "loss": 0.2002, "lr": 2.6295481838263628e-06, "epoch": 3.793713163064833, "percentage": 76.38, "elapsed_time": "3:13:36", "remaining_time": "0:59:52", "throughput": 10893.62, "total_tokens": 126550016} | |
| {"current_steps": 486, "total_steps": 635, "loss": 0.2004, "lr": 2.5962019096490876e-06, "epoch": 3.8015717092337917, "percentage": 76.54, "elapsed_time": "3:14:00", "remaining_time": "0:59:28", "throughput": 10893.65, "total_tokens": 126812160} | |
| {"current_steps": 487, "total_steps": 635, "loss": 0.2099, "lr": 2.5630368554089935e-06, "epoch": 3.8094302554027504, "percentage": 76.69, "elapsed_time": "3:14:24", "remaining_time": "0:59:05", "throughput": 10893.65, "total_tokens": 127074304} | |
| {"current_steps": 488, "total_steps": 635, "loss": 0.1908, "lr": 2.5300538328744416e-06, "epoch": 3.817288801571709, "percentage": 76.85, "elapsed_time": "3:14:49", "remaining_time": "0:58:41", "throughput": 10893.68, "total_tokens": 127336448} | |
| {"current_steps": 489, "total_steps": 635, "loss": 0.2044, "lr": 2.49725364935827e-06, "epoch": 3.825147347740668, "percentage": 77.01, "elapsed_time": "3:15:13", "remaining_time": "0:58:17", "throughput": 10893.68, "total_tokens": 127598592} | |
| {"current_steps": 490, "total_steps": 635, "loss": 0.2041, "lr": 2.464637107698046e-06, "epoch": 3.8330058939096268, "percentage": 77.17, "elapsed_time": "3:15:37", "remaining_time": "0:57:53", "throughput": 10893.67, "total_tokens": 127860736} | |
| {"current_steps": 491, "total_steps": 635, "loss": 0.2105, "lr": 2.4322050062363945e-06, "epoch": 3.8408644400785854, "percentage": 77.32, "elapsed_time": "3:16:01", "remaining_time": "0:57:29", "throughput": 10893.65, "total_tokens": 128122880} | |
| {"current_steps": 492, "total_steps": 635, "loss": 0.1803, "lr": 2.3999581388014692e-06, "epoch": 3.848722986247544, "percentage": 77.48, "elapsed_time": "3:16:25", "remaining_time": "0:57:05", "throughput": 10893.7, "total_tokens": 128385024} | |
| {"current_steps": 493, "total_steps": 635, "loss": 0.203, "lr": 2.3678972946875324e-06, "epoch": 3.856581532416503, "percentage": 77.64, "elapsed_time": "3:16:49", "remaining_time": "0:56:41", "throughput": 10893.71, "total_tokens": 128647168} | |
| {"current_steps": 494, "total_steps": 635, "loss": 0.2001, "lr": 2.336023258635607e-06, "epoch": 3.864440078585462, "percentage": 77.8, "elapsed_time": "3:17:13", "remaining_time": "0:56:17", "throughput": 10893.77, "total_tokens": 128909312} | |
| {"current_steps": 495, "total_steps": 635, "loss": 0.2057, "lr": 2.304336810814305e-06, "epoch": 3.8722986247544204, "percentage": 77.95, "elapsed_time": "3:17:37", "remaining_time": "0:55:53", "throughput": 10893.78, "total_tokens": 129171456} | |
| {"current_steps": 496, "total_steps": 635, "loss": 0.2, "lr": 2.2728387268006924e-06, "epoch": 3.880157170923379, "percentage": 78.11, "elapsed_time": "3:18:01", "remaining_time": "0:55:29", "throughput": 10893.8, "total_tokens": 129433600} | |
| {"current_steps": 497, "total_steps": 635, "loss": 0.1914, "lr": 2.2415297775613465e-06, "epoch": 3.8880157170923377, "percentage": 78.27, "elapsed_time": "3:18:25", "remaining_time": "0:55:05", "throughput": 10893.86, "total_tokens": 129695744} | |
| {"current_steps": 498, "total_steps": 635, "loss": 0.2032, "lr": 2.210410729433454e-06, "epoch": 3.895874263261297, "percentage": 78.43, "elapsed_time": "3:18:49", "remaining_time": "0:54:41", "throughput": 10893.89, "total_tokens": 129957888} | |
| {"current_steps": 499, "total_steps": 635, "loss": 0.1935, "lr": 2.1794823441060663e-06, "epoch": 3.9037328094302555, "percentage": 78.58, "elapsed_time": "3:19:13", "remaining_time": "0:54:17", "throughput": 10893.87, "total_tokens": 130220032} | |
| {"current_steps": 500, "total_steps": 635, "loss": 0.1904, "lr": 2.1487453786014513e-06, "epoch": 3.911591355599214, "percentage": 78.74, "elapsed_time": "3:19:37", "remaining_time": "0:53:53", "throughput": 10893.9, "total_tokens": 130482176} | |
| {"current_steps": 501, "total_steps": 635, "loss": 0.1895, "lr": 2.118200585256576e-06, "epoch": 3.9194499017681728, "percentage": 78.9, "elapsed_time": "3:20:01", "remaining_time": "0:53:30", "throughput": 10893.92, "total_tokens": 130744320} | |
| {"current_steps": 502, "total_steps": 635, "loss": 0.2158, "lr": 2.087848711704673e-06, "epoch": 3.927308447937132, "percentage": 79.06, "elapsed_time": "3:20:25", "remaining_time": "0:53:06", "throughput": 10893.93, "total_tokens": 131006464} | |
| {"current_steps": 503, "total_steps": 635, "loss": 0.2131, "lr": 2.057690500856958e-06, "epoch": 3.9351669941060905, "percentage": 79.21, "elapsed_time": "3:20:49", "remaining_time": "0:52:42", "throughput": 10893.91, "total_tokens": 131268608} | |
| {"current_steps": 504, "total_steps": 635, "loss": 0.1967, "lr": 2.027726690884435e-06, "epoch": 3.943025540275049, "percentage": 79.37, "elapsed_time": "3:21:13", "remaining_time": "0:52:18", "throughput": 10893.94, "total_tokens": 131530752} | |
| {"current_steps": 505, "total_steps": 635, "loss": 0.2182, "lr": 1.997958015199829e-06, "epoch": 3.950884086444008, "percentage": 79.53, "elapsed_time": "3:21:37", "remaining_time": "0:51:54", "throughput": 10893.98, "total_tokens": 131792896} | |
| {"current_steps": 506, "total_steps": 635, "loss": 0.1923, "lr": 1.96838520243965e-06, "epoch": 3.9587426326129664, "percentage": 79.69, "elapsed_time": "3:22:01", "remaining_time": "0:51:30", "throughput": 10894.0, "total_tokens": 132055040} | |
| {"current_steps": 507, "total_steps": 635, "loss": 0.1959, "lr": 1.939008976446326e-06, "epoch": 3.966601178781925, "percentage": 79.84, "elapsed_time": "3:22:25", "remaining_time": "0:51:06", "throughput": 10894.02, "total_tokens": 132317184} | |
| {"current_steps": 508, "total_steps": 635, "loss": 0.1854, "lr": 1.9098300562505266e-06, "epoch": 3.974459724950884, "percentage": 80.0, "elapsed_time": "3:22:49", "remaining_time": "0:50:42", "throughput": 10894.04, "total_tokens": 132579328} | |
| {"current_steps": 509, "total_steps": 635, "loss": 0.1955, "lr": 1.8808491560535292e-06, "epoch": 3.982318271119843, "percentage": 80.16, "elapsed_time": "3:23:13", "remaining_time": "0:50:18", "throughput": 10894.03, "total_tokens": 132841472} | |
| {"current_steps": 510, "total_steps": 635, "loss": 0.1951, "lr": 1.8520669852097573e-06, "epoch": 3.9901768172888015, "percentage": 80.31, "elapsed_time": "3:23:37", "remaining_time": "0:49:54", "throughput": 10894.06, "total_tokens": 133103616} | |
| {"current_steps": 511, "total_steps": 635, "loss": 0.1961, "lr": 1.8234842482094094e-06, "epoch": 3.9980353634577606, "percentage": 80.47, "elapsed_time": "3:24:02", "remaining_time": "0:49:30", "throughput": 10894.06, "total_tokens": 133365760} | |
| {"current_steps": 512, "total_steps": 635, "loss": 0.1957, "lr": 1.7951016446612157e-06, "epoch": 4.0, "percentage": 80.63, "elapsed_time": "3:24:08", "remaining_time": "0:49:02", "throughput": 10893.96, "total_tokens": 133431296} | |
| {"current_steps": 513, "total_steps": 635, "loss": 0.1129, "lr": 1.7669198692753242e-06, "epoch": 4.007858546168959, "percentage": 80.79, "elapsed_time": "3:24:32", "remaining_time": "0:48:38", "throughput": 10893.93, "total_tokens": 133693440} | |
| {"current_steps": 514, "total_steps": 635, "loss": 0.1176, "lr": 1.7389396118462831e-06, "epoch": 4.015717092337917, "percentage": 80.94, "elapsed_time": "3:24:56", "remaining_time": "0:48:14", "throughput": 10893.93, "total_tokens": 133955584} | |
| {"current_steps": 515, "total_steps": 635, "loss": 0.105, "lr": 1.7111615572361628e-06, "epoch": 4.023575638506876, "percentage": 81.1, "elapsed_time": "3:25:20", "remaining_time": "0:47:50", "throughput": 10893.94, "total_tokens": 134217728} | |
| {"current_steps": 516, "total_steps": 635, "loss": 0.1286, "lr": 1.6835863853577894e-06, "epoch": 4.031434184675835, "percentage": 81.26, "elapsed_time": "3:25:44", "remaining_time": "0:47:26", "throughput": 10893.92, "total_tokens": 134479872} | |
| {"current_steps": 517, "total_steps": 635, "loss": 0.1072, "lr": 1.6562147711581188e-06, "epoch": 4.039292730844794, "percentage": 81.42, "elapsed_time": "3:26:08", "remaining_time": "0:47:02", "throughput": 10893.96, "total_tokens": 134742016} | |
| {"current_steps": 518, "total_steps": 635, "loss": 0.0865, "lr": 1.629047384601684e-06, "epoch": 4.047151277013753, "percentage": 81.57, "elapsed_time": "3:26:32", "remaining_time": "0:46:39", "throughput": 10893.95, "total_tokens": 135004160} | |
| {"current_steps": 519, "total_steps": 635, "loss": 0.1109, "lr": 1.602084890654233e-06, "epoch": 4.055009823182711, "percentage": 81.73, "elapsed_time": "3:26:56", "remaining_time": "0:46:15", "throughput": 10893.97, "total_tokens": 135266304} | |
| {"current_steps": 520, "total_steps": 635, "loss": 0.0974, "lr": 1.5753279492664264e-06, "epoch": 4.06286836935167, "percentage": 81.89, "elapsed_time": "3:27:20", "remaining_time": "0:45:51", "throughput": 10893.99, "total_tokens": 135528448} | |
| {"current_steps": 521, "total_steps": 635, "loss": 0.1128, "lr": 1.5487772153576962e-06, "epoch": 4.070726915520629, "percentage": 82.05, "elapsed_time": "3:27:44", "remaining_time": "0:45:27", "throughput": 10894.04, "total_tokens": 135790592} | |
| {"current_steps": 522, "total_steps": 635, "loss": 0.0987, "lr": 1.5224333388002132e-06, "epoch": 4.078585461689587, "percentage": 82.2, "elapsed_time": "3:28:08", "remaining_time": "0:45:03", "throughput": 10894.04, "total_tokens": 136052736} | |
| {"current_steps": 523, "total_steps": 635, "loss": 0.0943, "lr": 1.4962969644029757e-06, "epoch": 4.086444007858546, "percentage": 82.36, "elapsed_time": "3:28:32", "remaining_time": "0:44:39", "throughput": 10894.04, "total_tokens": 136314880} | |
| {"current_steps": 524, "total_steps": 635, "loss": 0.0899, "lr": 1.470368731896038e-06, "epoch": 4.094302554027505, "percentage": 82.52, "elapsed_time": "3:28:56", "remaining_time": "0:44:15", "throughput": 10894.08, "total_tokens": 136577024} | |
| {"current_steps": 525, "total_steps": 635, "loss": 0.0949, "lr": 1.4446492759148411e-06, "epoch": 4.102161100196463, "percentage": 82.68, "elapsed_time": "3:29:20", "remaining_time": "0:43:51", "throughput": 10894.03, "total_tokens": 136839168} | |
| {"current_steps": 526, "total_steps": 635, "loss": 0.1146, "lr": 1.4191392259846804e-06, "epoch": 4.110019646365423, "percentage": 82.83, "elapsed_time": "3:29:45", "remaining_time": "0:43:27", "throughput": 10893.99, "total_tokens": 137101312} | |
| {"current_steps": 527, "total_steps": 635, "loss": 0.1049, "lr": 1.393839206505304e-06, "epoch": 4.1178781925343815, "percentage": 82.99, "elapsed_time": "3:30:09", "remaining_time": "0:43:04", "throughput": 10893.98, "total_tokens": 137363456} | |
| {"current_steps": 528, "total_steps": 635, "loss": 0.1078, "lr": 1.368749836735621e-06, "epoch": 4.12573673870334, "percentage": 83.15, "elapsed_time": "3:30:33", "remaining_time": "0:42:40", "throughput": 10893.91, "total_tokens": 137625600} | |
| {"current_steps": 529, "total_steps": 635, "loss": 0.1137, "lr": 1.3438717307785477e-06, "epoch": 4.133595284872299, "percentage": 83.31, "elapsed_time": "3:30:57", "remaining_time": "0:42:16", "throughput": 10893.94, "total_tokens": 137887744} | |
| {"current_steps": 530, "total_steps": 635, "loss": 0.099, "lr": 1.319205497565983e-06, "epoch": 4.141453831041257, "percentage": 83.46, "elapsed_time": "3:31:21", "remaining_time": "0:41:52", "throughput": 10893.97, "total_tokens": 138149888} | |
| {"current_steps": 531, "total_steps": 635, "loss": 0.1119, "lr": 1.2947517408438925e-06, "epoch": 4.149312377210216, "percentage": 83.62, "elapsed_time": "3:31:45", "remaining_time": "0:41:28", "throughput": 10893.97, "total_tokens": 138412032} | |
| {"current_steps": 532, "total_steps": 635, "loss": 0.1113, "lr": 1.2705110591575343e-06, "epoch": 4.157170923379175, "percentage": 83.78, "elapsed_time": "3:32:09", "remaining_time": "0:41:04", "throughput": 10893.96, "total_tokens": 138674176} | |
| {"current_steps": 533, "total_steps": 635, "loss": 0.1007, "lr": 1.2464840458368155e-06, "epoch": 4.165029469548133, "percentage": 83.94, "elapsed_time": "3:32:33", "remaining_time": "0:40:40", "throughput": 10893.96, "total_tokens": 138936320} | |
| {"current_steps": 534, "total_steps": 635, "loss": 0.0917, "lr": 1.2226712889817571e-06, "epoch": 4.172888015717092, "percentage": 84.09, "elapsed_time": "3:32:57", "remaining_time": "0:40:16", "throughput": 10894.0, "total_tokens": 139198464} | |
| {"current_steps": 535, "total_steps": 635, "loss": 0.1098, "lr": 1.1990733714481185e-06, "epoch": 4.1807465618860515, "percentage": 84.25, "elapsed_time": "3:33:21", "remaining_time": "0:39:52", "throughput": 10894.0, "total_tokens": 139460608} | |
| {"current_steps": 536, "total_steps": 635, "loss": 0.0987, "lr": 1.1756908708331028e-06, "epoch": 4.18860510805501, "percentage": 84.41, "elapsed_time": "3:33:45", "remaining_time": "0:39:28", "throughput": 10894.03, "total_tokens": 139722752} | |
| {"current_steps": 537, "total_steps": 635, "loss": 0.0925, "lr": 1.152524359461249e-06, "epoch": 4.196463654223969, "percentage": 84.57, "elapsed_time": "3:34:09", "remaining_time": "0:39:04", "throughput": 10894.11, "total_tokens": 139984896} | |
| {"current_steps": 538, "total_steps": 635, "loss": 0.0841, "lr": 1.1295744043704048e-06, "epoch": 4.2043222003929275, "percentage": 84.72, "elapsed_time": "3:34:33", "remaining_time": "0:38:41", "throughput": 10894.08, "total_tokens": 140247040} | |
| {"current_steps": 539, "total_steps": 635, "loss": 0.1001, "lr": 1.1068415672978516e-06, "epoch": 4.212180746561886, "percentage": 84.88, "elapsed_time": "3:34:57", "remaining_time": "0:38:17", "throughput": 10894.08, "total_tokens": 140509184} | |
| {"current_steps": 540, "total_steps": 635, "loss": 0.0956, "lr": 1.0843264046665558e-06, "epoch": 4.220039292730845, "percentage": 85.04, "elapsed_time": "3:35:21", "remaining_time": "0:37:53", "throughput": 10894.1, "total_tokens": 140771328} | |
| {"current_steps": 541, "total_steps": 635, "loss": 0.1042, "lr": 1.0620294675715548e-06, "epoch": 4.227897838899803, "percentage": 85.2, "elapsed_time": "3:35:45", "remaining_time": "0:37:29", "throughput": 10894.13, "total_tokens": 141033472} | |
| {"current_steps": 542, "total_steps": 635, "loss": 0.1094, "lr": 1.0399513017664575e-06, "epoch": 4.235756385068762, "percentage": 85.35, "elapsed_time": "3:36:09", "remaining_time": "0:37:05", "throughput": 10894.15, "total_tokens": 141295616} | |
| {"current_steps": 543, "total_steps": 635, "loss": 0.1015, "lr": 1.018092447650092e-06, "epoch": 4.243614931237721, "percentage": 85.51, "elapsed_time": "3:36:33", "remaining_time": "0:36:41", "throughput": 10894.2, "total_tokens": 141557760} | |
| {"current_steps": 544, "total_steps": 635, "loss": 0.0934, "lr": 9.9645344025328e-07, "epoch": 4.251473477406679, "percentage": 85.67, "elapsed_time": "3:36:57", "remaining_time": "0:36:17", "throughput": 10894.18, "total_tokens": 141819904} | |
| {"current_steps": 545, "total_steps": 635, "loss": 0.0991, "lr": 9.750348092257368e-07, "epoch": 4.259332023575639, "percentage": 85.83, "elapsed_time": "3:37:21", "remaining_time": "0:35:53", "throughput": 10894.25, "total_tokens": 142082048} | |
| {"current_steps": 546, "total_steps": 635, "loss": 0.0881, "lr": 9.538370788231154e-07, "epoch": 4.2671905697445975, "percentage": 85.98, "elapsed_time": "3:37:45", "remaining_time": "0:35:29", "throughput": 10894.31, "total_tokens": 142344192} | |
| {"current_steps": 547, "total_steps": 635, "loss": 0.1077, "lr": 9.328607678941581e-07, "epoch": 4.275049115913556, "percentage": 86.14, "elapsed_time": "3:38:09", "remaining_time": "0:35:05", "throughput": 10894.32, "total_tokens": 142606336} | |
| {"current_steps": 548, "total_steps": 635, "loss": 0.1116, "lr": 9.121063898680171e-07, "epoch": 4.282907662082515, "percentage": 86.3, "elapsed_time": "3:38:34", "remaining_time": "0:34:41", "throughput": 10894.2, "total_tokens": 142868480} | |
| {"current_steps": 549, "total_steps": 635, "loss": 0.1059, "lr": 8.915744527416736e-07, "epoch": 4.2907662082514735, "percentage": 86.46, "elapsed_time": "3:38:58", "remaining_time": "0:34:18", "throughput": 10894.25, "total_tokens": 143130624} | |
| {"current_steps": 550, "total_steps": 635, "loss": 0.0922, "lr": 8.712654590675085e-07, "epoch": 4.298624754420432, "percentage": 86.61, "elapsed_time": "3:39:22", "remaining_time": "0:33:54", "throughput": 10894.29, "total_tokens": 143392768} | |
| {"current_steps": 551, "total_steps": 635, "loss": 0.112, "lr": 8.511799059409998e-07, "epoch": 4.306483300589391, "percentage": 86.77, "elapsed_time": "3:39:46", "remaining_time": "0:33:30", "throughput": 10894.31, "total_tokens": 143654912} | |
| {"current_steps": 552, "total_steps": 635, "loss": 0.1044, "lr": 8.313182849885548e-07, "epoch": 4.314341846758349, "percentage": 86.93, "elapsed_time": "3:40:10", "remaining_time": "0:33:06", "throughput": 10894.34, "total_tokens": 143917056} | |
| {"current_steps": 553, "total_steps": 635, "loss": 0.1108, "lr": 8.116810823554877e-07, "epoch": 4.322200392927308, "percentage": 87.09, "elapsed_time": "3:40:34", "remaining_time": "0:32:42", "throughput": 10894.38, "total_tokens": 144179200} | |
| {"current_steps": 554, "total_steps": 635, "loss": 0.0977, "lr": 7.922687786940997e-07, "epoch": 4.330058939096268, "percentage": 87.24, "elapsed_time": "3:40:58", "remaining_time": "0:32:18", "throughput": 10894.39, "total_tokens": 144441344} | |
| {"current_steps": 555, "total_steps": 635, "loss": 0.0882, "lr": 7.730818491519343e-07, "epoch": 4.337917485265226, "percentage": 87.4, "elapsed_time": "3:41:22", "remaining_time": "0:31:54", "throughput": 10894.4, "total_tokens": 144703488} | |
| {"current_steps": 556, "total_steps": 635, "loss": 0.0915, "lr": 7.54120763360131e-07, "epoch": 4.345776031434185, "percentage": 87.56, "elapsed_time": "3:41:46", "remaining_time": "0:31:30", "throughput": 10894.45, "total_tokens": 144965632} | |
| {"current_steps": 557, "total_steps": 635, "loss": 0.1002, "lr": 7.35385985421948e-07, "epoch": 4.3536345776031435, "percentage": 87.72, "elapsed_time": "3:42:10", "remaining_time": "0:31:06", "throughput": 10894.53, "total_tokens": 145227776} | |
| {"current_steps": 558, "total_steps": 635, "loss": 0.0999, "lr": 7.168779739013821e-07, "epoch": 4.361493123772102, "percentage": 87.87, "elapsed_time": "3:42:34", "remaining_time": "0:30:42", "throughput": 10894.53, "total_tokens": 145489920} | |
| {"current_steps": 559, "total_steps": 635, "loss": 0.1033, "lr": 6.985971818119653e-07, "epoch": 4.369351669941061, "percentage": 88.03, "elapsed_time": "3:42:58", "remaining_time": "0:30:18", "throughput": 10894.53, "total_tokens": 145752064} | |
| {"current_steps": 560, "total_steps": 635, "loss": 0.0957, "lr": 6.805440566056554e-07, "epoch": 4.3772102161100195, "percentage": 88.19, "elapsed_time": "3:43:22", "remaining_time": "0:29:54", "throughput": 10894.49, "total_tokens": 146014208} | |
| {"current_steps": 561, "total_steps": 635, "loss": 0.1025, "lr": 6.627190401619044e-07, "epoch": 4.385068762278978, "percentage": 88.35, "elapsed_time": "3:43:46", "remaining_time": "0:29:31", "throughput": 10894.5, "total_tokens": 146276352} | |
| {"current_steps": 562, "total_steps": 635, "loss": 0.0955, "lr": 6.451225687768293e-07, "epoch": 4.392927308447937, "percentage": 88.5, "elapsed_time": "3:44:10", "remaining_time": "0:29:07", "throughput": 10894.49, "total_tokens": 146538496} | |
| {"current_steps": 563, "total_steps": 635, "loss": 0.0975, "lr": 6.27755073152535e-07, "epoch": 4.400785854616895, "percentage": 88.66, "elapsed_time": "3:44:34", "remaining_time": "0:28:43", "throughput": 10894.51, "total_tokens": 146800640} | |
| {"current_steps": 564, "total_steps": 635, "loss": 0.1064, "lr": 6.106169783865801e-07, "epoch": 4.408644400785855, "percentage": 88.82, "elapsed_time": "3:44:58", "remaining_time": "0:28:19", "throughput": 10894.54, "total_tokens": 147062784} | |
| {"current_steps": 565, "total_steps": 635, "loss": 0.104, "lr": 5.937087039615619e-07, "epoch": 4.416502946954814, "percentage": 88.98, "elapsed_time": "3:45:22", "remaining_time": "0:27:55", "throughput": 10894.59, "total_tokens": 147324928} | |
| {"current_steps": 566, "total_steps": 635, "loss": 0.0993, "lr": 5.77030663734851e-07, "epoch": 4.424361493123772, "percentage": 89.13, "elapsed_time": "3:45:46", "remaining_time": "0:27:31", "throughput": 10894.58, "total_tokens": 147587072} | |
| {"current_steps": 567, "total_steps": 635, "loss": 0.099, "lr": 5.605832659284682e-07, "epoch": 4.432220039292731, "percentage": 89.29, "elapsed_time": "3:46:10", "remaining_time": "0:27:07", "throughput": 10894.59, "total_tokens": 147849216} | |
| {"current_steps": 568, "total_steps": 635, "loss": 0.1064, "lr": 5.443669131190843e-07, "epoch": 4.4400785854616895, "percentage": 89.45, "elapsed_time": "3:46:34", "remaining_time": "0:26:43", "throughput": 10894.62, "total_tokens": 148111360} | |
| {"current_steps": 569, "total_steps": 635, "loss": 0.099, "lr": 5.283820022281715e-07, "epoch": 4.447937131630648, "percentage": 89.61, "elapsed_time": "3:46:58", "remaining_time": "0:26:19", "throughput": 10894.66, "total_tokens": 148373504} | |
| {"current_steps": 570, "total_steps": 635, "loss": 0.0972, "lr": 5.126289245122906e-07, "epoch": 4.455795677799607, "percentage": 89.76, "elapsed_time": "3:47:22", "remaining_time": "0:25:55", "throughput": 10894.66, "total_tokens": 148635648} | |
| {"current_steps": 571, "total_steps": 635, "loss": 0.1019, "lr": 4.971080655534988e-07, "epoch": 4.4636542239685655, "percentage": 89.92, "elapsed_time": "3:47:47", "remaining_time": "0:25:31", "throughput": 10894.62, "total_tokens": 148897792} | |
| {"current_steps": 572, "total_steps": 635, "loss": 0.1016, "lr": 4.818198052499368e-07, "epoch": 4.471512770137524, "percentage": 90.08, "elapsed_time": "3:48:11", "remaining_time": "0:25:07", "throughput": 10894.65, "total_tokens": 149159936} | |
| {"current_steps": 573, "total_steps": 635, "loss": 0.1021, "lr": 4.6676451780650947e-07, "epoch": 4.479371316306484, "percentage": 90.24, "elapsed_time": "3:48:35", "remaining_time": "0:24:44", "throughput": 10894.68, "total_tokens": 149422080} | |
| {"current_steps": 574, "total_steps": 635, "loss": 0.0993, "lr": 4.519425717257342e-07, "epoch": 4.487229862475442, "percentage": 90.39, "elapsed_time": "3:48:59", "remaining_time": "0:24:20", "throughput": 10894.7, "total_tokens": 149684224} | |
| {"current_steps": 575, "total_steps": 635, "loss": 0.104, "lr": 4.3735432979872593e-07, "epoch": 4.495088408644401, "percentage": 90.55, "elapsed_time": "3:49:23", "remaining_time": "0:23:56", "throughput": 10894.71, "total_tokens": 149946368} | |
| {"current_steps": 576, "total_steps": 635, "loss": 0.093, "lr": 4.230001490963043e-07, "epoch": 4.50294695481336, "percentage": 90.71, "elapsed_time": "3:49:47", "remaining_time": "0:23:32", "throughput": 10894.74, "total_tokens": 150208512} | |
| {"current_steps": 577, "total_steps": 635, "loss": 0.1069, "lr": 4.088803809602693e-07, "epoch": 4.510805500982318, "percentage": 90.87, "elapsed_time": "3:50:11", "remaining_time": "0:23:08", "throughput": 10894.74, "total_tokens": 150470656} | |
| {"current_steps": 578, "total_steps": 635, "loss": 0.1102, "lr": 3.9499537099478955e-07, "epoch": 4.518664047151277, "percentage": 91.02, "elapsed_time": "3:50:35", "remaining_time": "0:22:44", "throughput": 10894.72, "total_tokens": 150732800} | |
| {"current_steps": 579, "total_steps": 635, "loss": 0.0933, "lr": 3.813454590579502e-07, "epoch": 4.5265225933202355, "percentage": 91.18, "elapsed_time": "3:50:59", "remaining_time": "0:22:20", "throughput": 10894.73, "total_tokens": 150994944} | |
| {"current_steps": 580, "total_steps": 635, "loss": 0.1082, "lr": 3.679309792534291e-07, "epoch": 4.534381139489194, "percentage": 91.34, "elapsed_time": "3:51:23", "remaining_time": "0:21:56", "throughput": 10894.76, "total_tokens": 151257088} | |
| {"current_steps": 581, "total_steps": 635, "loss": 0.1007, "lr": 3.547522599223263e-07, "epoch": 4.542239685658153, "percentage": 91.5, "elapsed_time": "3:51:47", "remaining_time": "0:21:32", "throughput": 10894.77, "total_tokens": 151519232} | |
| {"current_steps": 582, "total_steps": 635, "loss": 0.0903, "lr": 3.418096236351165e-07, "epoch": 4.550098231827112, "percentage": 91.65, "elapsed_time": "3:52:11", "remaining_time": "0:21:08", "throughput": 10894.75, "total_tokens": 151781376} | |
| {"current_steps": 583, "total_steps": 635, "loss": 0.108, "lr": 3.2910338718376455e-07, "epoch": 4.557956777996071, "percentage": 91.81, "elapsed_time": "3:52:35", "remaining_time": "0:20:44", "throughput": 10894.77, "total_tokens": 152043520} | |
| {"current_steps": 584, "total_steps": 635, "loss": 0.1045, "lr": 3.166338615739661e-07, "epoch": 4.56581532416503, "percentage": 91.97, "elapsed_time": "3:52:59", "remaining_time": "0:20:20", "throughput": 10894.78, "total_tokens": 152305664} | |
| {"current_steps": 585, "total_steps": 635, "loss": 0.1056, "lr": 3.044013520175337e-07, "epoch": 4.573673870333988, "percentage": 92.13, "elapsed_time": "3:53:23", "remaining_time": "0:19:56", "throughput": 10894.8, "total_tokens": 152567808} | |
| {"current_steps": 586, "total_steps": 635, "loss": 0.1091, "lr": 2.9240615792493377e-07, "epoch": 4.581532416502947, "percentage": 92.28, "elapsed_time": "3:53:47", "remaining_time": "0:19:32", "throughput": 10894.82, "total_tokens": 152829952} | |
| {"current_steps": 587, "total_steps": 635, "loss": 0.0985, "lr": 2.806485728979458e-07, "epoch": 4.589390962671906, "percentage": 92.44, "elapsed_time": "3:54:11", "remaining_time": "0:19:09", "throughput": 10894.85, "total_tokens": 153092096} | |
| {"current_steps": 588, "total_steps": 635, "loss": 0.1003, "lr": 2.691288847224871e-07, "epoch": 4.597249508840864, "percentage": 92.6, "elapsed_time": "3:54:35", "remaining_time": "0:18:45", "throughput": 10894.81, "total_tokens": 153354240} | |
| {"current_steps": 589, "total_steps": 635, "loss": 0.1095, "lr": 2.578473753615651e-07, "epoch": 4.605108055009823, "percentage": 92.76, "elapsed_time": "3:54:59", "remaining_time": "0:18:21", "throughput": 10894.81, "total_tokens": 153616384} | |
| {"current_steps": 590, "total_steps": 635, "loss": 0.1136, "lr": 2.4680432094837394e-07, "epoch": 4.6129666011787815, "percentage": 92.91, "elapsed_time": "3:55:24", "remaining_time": "0:17:57", "throughput": 10894.82, "total_tokens": 153878528} | |
| {"current_steps": 591, "total_steps": 635, "loss": 0.1009, "lr": 2.359999917795375e-07, "epoch": 4.620825147347741, "percentage": 93.07, "elapsed_time": "3:55:48", "remaining_time": "0:17:33", "throughput": 10894.83, "total_tokens": 154140672} | |
| {"current_steps": 592, "total_steps": 635, "loss": 0.1073, "lr": 2.2543465230849158e-07, "epoch": 4.6286836935167, "percentage": 93.23, "elapsed_time": "3:56:12", "remaining_time": "0:17:09", "throughput": 10894.84, "total_tokens": 154402816} | |
| {"current_steps": 593, "total_steps": 635, "loss": 0.0904, "lr": 2.1510856113901467e-07, "epoch": 4.636542239685658, "percentage": 93.39, "elapsed_time": "3:56:36", "remaining_time": "0:16:45", "throughput": 10894.9, "total_tokens": 154664960} | |
| {"current_steps": 594, "total_steps": 635, "loss": 0.1022, "lr": 2.0502197101889608e-07, "epoch": 4.644400785854617, "percentage": 93.54, "elapsed_time": "3:57:00", "remaining_time": "0:16:21", "throughput": 10894.92, "total_tokens": 154927104} | |
| {"current_steps": 595, "total_steps": 635, "loss": 0.1065, "lr": 1.9517512883374667e-07, "epoch": 4.652259332023576, "percentage": 93.7, "elapsed_time": "3:57:24", "remaining_time": "0:15:57", "throughput": 10894.96, "total_tokens": 155189248} | |
| {"current_steps": 596, "total_steps": 635, "loss": 0.0991, "lr": 1.8556827560096247e-07, "epoch": 4.660117878192534, "percentage": 93.86, "elapsed_time": "3:57:48", "remaining_time": "0:15:33", "throughput": 10894.98, "total_tokens": 155451392} | |
| {"current_steps": 597, "total_steps": 635, "loss": 0.1019, "lr": 1.7620164646381943e-07, "epoch": 4.667976424361493, "percentage": 94.02, "elapsed_time": "3:58:12", "remaining_time": "0:15:09", "throughput": 10894.75, "total_tokens": 155713536} | |
| {"current_steps": 598, "total_steps": 635, "loss": 0.0959, "lr": 1.6707547068571805e-07, "epoch": 4.675834970530452, "percentage": 94.17, "elapsed_time": "3:58:36", "remaining_time": "0:14:45", "throughput": 10894.49, "total_tokens": 155975680} | |
| {"current_steps": 599, "total_steps": 635, "loss": 0.1037, "lr": 1.5818997164458005e-07, "epoch": 4.68369351669941, "percentage": 94.33, "elapsed_time": "3:59:00", "remaining_time": "0:14:21", "throughput": 10894.5, "total_tokens": 156237824} | |
| {"current_steps": 600, "total_steps": 635, "loss": 0.1022, "lr": 1.495453668273672e-07, "epoch": 4.69155206286837, "percentage": 94.49, "elapsed_time": "3:59:25", "remaining_time": "0:13:57", "throughput": 10894.5, "total_tokens": 156499968} | |
| {"current_steps": 601, "total_steps": 635, "loss": 0.1031, "lr": 1.4114186782477e-07, "epoch": 4.699410609037328, "percentage": 94.65, "elapsed_time": "3:59:49", "remaining_time": "0:13:34", "throughput": 10894.52, "total_tokens": 156762112} | |
| {"current_steps": 602, "total_steps": 635, "loss": 0.0923, "lr": 1.3297968032602414e-07, "epoch": 4.707269155206287, "percentage": 94.8, "elapsed_time": "4:00:13", "remaining_time": "0:13:10", "throughput": 10894.52, "total_tokens": 157024256} | |
| {"current_steps": 603, "total_steps": 635, "loss": 0.0934, "lr": 1.2505900411387328e-07, "epoch": 4.715127701375246, "percentage": 94.96, "elapsed_time": "4:00:37", "remaining_time": "0:12:46", "throughput": 10894.53, "total_tokens": 157286400} | |
| {"current_steps": 604, "total_steps": 635, "loss": 0.0975, "lr": 1.1738003305968193e-07, "epoch": 4.722986247544204, "percentage": 95.12, "elapsed_time": "4:01:01", "remaining_time": "0:12:22", "throughput": 10894.56, "total_tokens": 157548544} | |
| {"current_steps": 605, "total_steps": 635, "loss": 0.1017, "lr": 1.0994295511869257e-07, "epoch": 4.730844793713163, "percentage": 95.28, "elapsed_time": "4:01:25", "remaining_time": "0:11:58", "throughput": 10894.55, "total_tokens": 157810688} | |
| {"current_steps": 606, "total_steps": 635, "loss": 0.1026, "lr": 1.0274795232542045e-07, "epoch": 4.738703339882122, "percentage": 95.43, "elapsed_time": "4:01:49", "remaining_time": "0:11:34", "throughput": 10894.56, "total_tokens": 158072832} | |
| {"current_steps": 607, "total_steps": 635, "loss": 0.103, "lr": 9.579520078919935e-08, "epoch": 4.74656188605108, "percentage": 95.59, "elapsed_time": "4:02:13", "remaining_time": "0:11:10", "throughput": 10894.58, "total_tokens": 158334976} | |
| {"current_steps": 608, "total_steps": 635, "loss": 0.0973, "lr": 8.908487068987281e-08, "epoch": 4.754420432220039, "percentage": 95.75, "elapsed_time": "4:02:37", "remaining_time": "0:10:46", "throughput": 10894.61, "total_tokens": 158597120} | |
| {"current_steps": 609, "total_steps": 635, "loss": 0.1098, "lr": 8.26171262736264e-08, "epoch": 4.7622789783889985, "percentage": 95.91, "elapsed_time": "4:03:01", "remaining_time": "0:10:22", "throughput": 10894.63, "total_tokens": 158859264} | |
| {"current_steps": 610, "total_steps": 635, "loss": 0.1107, "lr": 7.639212584897082e-08, "epoch": 4.770137524557957, "percentage": 96.06, "elapsed_time": "4:03:25", "remaining_time": "0:09:58", "throughput": 10894.65, "total_tokens": 159121408} | |
| {"current_steps": 611, "total_steps": 635, "loss": 0.1141, "lr": 7.04100217828596e-08, "epoch": 4.777996070726916, "percentage": 96.22, "elapsed_time": "4:03:49", "remaining_time": "0:09:34", "throughput": 10894.66, "total_tokens": 159383552} | |
| {"current_steps": 612, "total_steps": 635, "loss": 0.1, "lr": 6.467096049697196e-08, "epoch": 4.785854616895874, "percentage": 96.38, "elapsed_time": "4:04:13", "remaining_time": "0:09:10", "throughput": 10894.69, "total_tokens": 159645696} | |
| {"current_steps": 613, "total_steps": 635, "loss": 0.0914, "lr": 5.917508246411574e-08, "epoch": 4.793713163064833, "percentage": 96.54, "elapsed_time": "4:04:37", "remaining_time": "0:08:46", "throughput": 10894.74, "total_tokens": 159907840} | |
| {"current_steps": 614, "total_steps": 635, "loss": 0.0939, "lr": 5.39225222048001e-08, "epoch": 4.801571709233792, "percentage": 96.69, "elapsed_time": "4:05:01", "remaining_time": "0:08:22", "throughput": 10894.79, "total_tokens": 160169984} | |
| {"current_steps": 615, "total_steps": 635, "loss": 0.0976, "lr": 4.8913408283934874e-08, "epoch": 4.80943025540275, "percentage": 96.85, "elapsed_time": "4:05:25", "remaining_time": "0:07:58", "throughput": 10894.83, "total_tokens": 160432128} | |
| {"current_steps": 616, "total_steps": 635, "loss": 0.1002, "lr": 4.414786330768639e-08, "epoch": 4.817288801571709, "percentage": 97.01, "elapsed_time": "4:05:49", "remaining_time": "0:07:34", "throughput": 10894.9, "total_tokens": 160694272} | |
| {"current_steps": 617, "total_steps": 635, "loss": 0.0805, "lr": 3.962600392047988e-08, "epoch": 4.825147347740668, "percentage": 97.17, "elapsed_time": "4:06:13", "remaining_time": "0:07:10", "throughput": 10894.95, "total_tokens": 160956416} | |
| {"current_steps": 618, "total_steps": 635, "loss": 0.1038, "lr": 3.534794080214066e-08, "epoch": 4.833005893909627, "percentage": 97.32, "elapsed_time": "4:06:37", "remaining_time": "0:06:47", "throughput": 10894.96, "total_tokens": 161218560} | |
| {"current_steps": 619, "total_steps": 635, "loss": 0.0976, "lr": 3.131377866518293e-08, "epoch": 4.840864440078585, "percentage": 97.48, "elapsed_time": "4:07:01", "remaining_time": "0:06:23", "throughput": 10894.99, "total_tokens": 161480704} | |
| {"current_steps": 620, "total_steps": 635, "loss": 0.1146, "lr": 2.7523616252252972e-08, "epoch": 4.8487229862475445, "percentage": 97.64, "elapsed_time": "4:07:25", "remaining_time": "0:05:59", "throughput": 10895.0, "total_tokens": 161742848} | |
| {"current_steps": 621, "total_steps": 635, "loss": 0.11, "lr": 2.3977546333709966e-08, "epoch": 4.856581532416503, "percentage": 97.8, "elapsed_time": "4:07:49", "remaining_time": "0:05:35", "throughput": 10895.04, "total_tokens": 162004992} | |
| {"current_steps": 622, "total_steps": 635, "loss": 0.1006, "lr": 2.0675655705348908e-08, "epoch": 4.864440078585462, "percentage": 97.95, "elapsed_time": "4:08:13", "remaining_time": "0:05:11", "throughput": 10895.08, "total_tokens": 162267136} | |
| {"current_steps": 623, "total_steps": 635, "loss": 0.0888, "lr": 1.7618025186287858e-08, "epoch": 4.87229862475442, "percentage": 98.11, "elapsed_time": "4:08:37", "remaining_time": "0:04:47", "throughput": 10895.12, "total_tokens": 162529280} | |
| {"current_steps": 624, "total_steps": 635, "loss": 0.1089, "lr": 1.480472961698065e-08, "epoch": 4.880157170923379, "percentage": 98.27, "elapsed_time": "4:09:01", "remaining_time": "0:04:23", "throughput": 10895.13, "total_tokens": 162791424} | |
| {"current_steps": 625, "total_steps": 635, "loss": 0.0981, "lr": 1.2235837857387246e-08, "epoch": 4.888015717092338, "percentage": 98.43, "elapsed_time": "4:09:25", "remaining_time": "0:03:59", "throughput": 10895.14, "total_tokens": 163053568} | |
| {"current_steps": 626, "total_steps": 635, "loss": 0.0905, "lr": 9.911412785290619e-09, "epoch": 4.895874263261296, "percentage": 98.58, "elapsed_time": "4:09:49", "remaining_time": "0:03:35", "throughput": 10895.18, "total_tokens": 163315712} | |
| {"current_steps": 627, "total_steps": 635, "loss": 0.1057, "lr": 7.831511294753569e-09, "epoch": 4.903732809430255, "percentage": 98.74, "elapsed_time": "4:10:13", "remaining_time": "0:03:11", "throughput": 10895.21, "total_tokens": 163577856} | |
| {"current_steps": 628, "total_steps": 635, "loss": 0.0931, "lr": 5.996184294732033e-09, "epoch": 4.911591355599214, "percentage": 98.9, "elapsed_time": "4:10:37", "remaining_time": "0:02:47", "throughput": 10895.26, "total_tokens": 163840000} | |
| {"current_steps": 629, "total_steps": 635, "loss": 0.1011, "lr": 4.405476707822765e-09, "epoch": 4.919449901768173, "percentage": 99.06, "elapsed_time": "4:11:01", "remaining_time": "0:02:23", "throughput": 10895.25, "total_tokens": 164102144} | |
| {"current_steps": 630, "total_steps": 635, "loss": 0.0978, "lr": 3.0594274691686522e-09, "epoch": 4.927308447937132, "percentage": 99.21, "elapsed_time": "4:11:25", "remaining_time": "0:01:59", "throughput": 10895.24, "total_tokens": 164364288} | |
| {"current_steps": 631, "total_steps": 635, "loss": 0.1015, "lr": 1.9580695255017048e-09, "epoch": 4.9351669941060905, "percentage": 99.37, "elapsed_time": "4:11:50", "remaining_time": "0:01:35", "throughput": 10894.92, "total_tokens": 164626432} | |
| {"current_steps": 632, "total_steps": 635, "loss": 0.1064, "lr": 1.1014298343403617e-09, "epoch": 4.943025540275049, "percentage": 99.53, "elapsed_time": "4:12:14", "remaining_time": "0:01:11", "throughput": 10894.94, "total_tokens": 164888576} | |
| {"current_steps": 633, "total_steps": 635, "loss": 0.0914, "lr": 4.895293633255804e-10, "epoch": 4.950884086444008, "percentage": 99.69, "elapsed_time": "4:12:38", "remaining_time": "0:00:47", "throughput": 10894.93, "total_tokens": 165150720} | |
| {"current_steps": 634, "total_steps": 635, "loss": 0.1009, "lr": 1.2238308971235234e-10, "epoch": 4.958742632612966, "percentage": 99.84, "elapsed_time": "4:13:02", "remaining_time": "0:00:23", "throughput": 10894.97, "total_tokens": 165412864} | |
| {"current_steps": 635, "total_steps": 635, "loss": 0.094, "lr": 0.0, "epoch": 4.966601178781925, "percentage": 100.0, "elapsed_time": "4:13:26", "remaining_time": "0:00:00", "throughput": 10894.97, "total_tokens": 165675008} | |