Sauron0019's picture
Upload 20 files
869aea1 verified
{"current_steps": 25, "total_steps": 880, "loss": 6.768, "lr": 3.2000000000000003e-06, "epoch": 0.11332728921124206, "percentage": 2.84, "elapsed_time": "0:04:01", "remaining_time": "2:17:49", "throughput": 1323.46, "total_tokens": 320000}
{"current_steps": 50, "total_steps": 880, "loss": 2.2714, "lr": 6.533333333333334e-06, "epoch": 0.22665457842248413, "percentage": 5.68, "elapsed_time": "0:08:03", "remaining_time": "2:13:39", "throughput": 1324.71, "total_tokens": 640000}
{"current_steps": 75, "total_steps": 880, "loss": 1.6663, "lr": 9.866666666666668e-06, "epoch": 0.3399818676337262, "percentage": 8.52, "elapsed_time": "0:12:04", "remaining_time": "2:09:36", "throughput": 1324.97, "total_tokens": 960000}
{"current_steps": 100, "total_steps": 880, "loss": 1.5351, "lr": 1.3200000000000002e-05, "epoch": 0.45330915684496825, "percentage": 11.36, "elapsed_time": "0:16:05", "remaining_time": "2:05:33", "throughput": 1325.22, "total_tokens": 1280000}
{"current_steps": 125, "total_steps": 880, "loss": 1.4698, "lr": 1.6533333333333333e-05, "epoch": 0.5666364460562103, "percentage": 14.2, "elapsed_time": "0:20:07", "remaining_time": "2:01:31", "throughput": 1325.37, "total_tokens": 1600000}
{"current_steps": 150, "total_steps": 880, "loss": 1.4164, "lr": 1.9866666666666667e-05, "epoch": 0.6799637352674524, "percentage": 17.05, "elapsed_time": "0:24:08", "remaining_time": "1:57:29", "throughput": 1325.44, "total_tokens": 1920000}
{"current_steps": 175, "total_steps": 880, "loss": 1.3952, "lr": 1.994670819911521e-05, "epoch": 0.7932910244786945, "percentage": 19.89, "elapsed_time": "0:28:09", "remaining_time": "1:53:27", "throughput": 1325.53, "total_tokens": 2239840}
{"current_steps": 200, "total_steps": 880, "loss": 1.3792, "lr": 1.977848341505657e-05, "epoch": 0.9066183136899365, "percentage": 22.73, "elapsed_time": "0:32:11", "remaining_time": "1:49:25", "throughput": 1325.63, "total_tokens": 2559800}
{"current_steps": 225, "total_steps": 880, "loss": 1.3537, "lr": 1.949717842791432e-05, "epoch": 1.0226654578422485, "percentage": 25.57, "elapsed_time": "0:36:16", "remaining_time": "1:45:34", "throughput": 1325.71, "total_tokens": 2884920}
{"current_steps": 250, "total_steps": 880, "loss": 1.2956, "lr": 1.9106046300942165e-05, "epoch": 1.1359927470534905, "percentage": 28.41, "elapsed_time": "0:40:17", "remaining_time": "1:41:31", "throughput": 1325.77, "total_tokens": 3204920}
{"current_steps": 275, "total_steps": 880, "loss": 1.2642, "lr": 1.8609610158889943e-05, "epoch": 1.2493200362647325, "percentage": 31.25, "elapsed_time": "0:44:31", "remaining_time": "1:37:57", "throughput": 1319.47, "total_tokens": 3524920}
{"current_steps": 300, "total_steps": 880, "loss": 1.2527, "lr": 1.8013610881746767e-05, "epoch": 1.3626473254759746, "percentage": 34.09, "elapsed_time": "0:48:32", "remaining_time": "1:33:51", "throughput": 1320.02, "total_tokens": 3844920}
{"current_steps": 325, "total_steps": 880, "loss": 1.2602, "lr": 1.732494071613579e-05, "epoch": 1.4759746146872166, "percentage": 36.93, "elapsed_time": "0:52:34", "remaining_time": "1:29:46", "throughput": 1320.49, "total_tokens": 4164920}
{"current_steps": 350, "total_steps": 880, "loss": 1.2551, "lr": 1.6551563572090855e-05, "epoch": 1.5893019038984586, "percentage": 39.77, "elapsed_time": "0:56:35", "remaining_time": "1:25:41", "throughput": 1320.88, "total_tokens": 4484840}
{"current_steps": 375, "total_steps": 880, "loss": 1.2325, "lr": 1.5702422926917872e-05, "epoch": 1.7026291931097008, "percentage": 42.61, "elapsed_time": "1:00:36", "remaining_time": "1:21:37", "throughput": 1321.22, "total_tokens": 4804840}
{"current_steps": 400, "total_steps": 880, "loss": 1.2436, "lr": 1.4787338401157888e-05, "epoch": 1.8159564823209429, "percentage": 45.45, "elapsed_time": "1:04:37", "remaining_time": "1:17:33", "throughput": 1321.53, "total_tokens": 5124840}
{"current_steps": 425, "total_steps": 880, "loss": 1.2319, "lr": 1.3816892202666591e-05, "epoch": 1.929283771532185, "percentage": 48.3, "elapsed_time": "1:08:39", "remaining_time": "1:13:30", "throughput": 1321.8, "total_tokens": 5444840}
{"current_steps": 450, "total_steps": 880, "loss": 1.2132, "lr": 1.2802306751992163e-05, "epoch": 2.045330915684497, "percentage": 51.14, "elapsed_time": "1:12:44", "remaining_time": "1:09:30", "throughput": 1322.03, "total_tokens": 5769800}
{"current_steps": 475, "total_steps": 880, "loss": 1.0794, "lr": 1.1755314904214284e-05, "epoch": 2.158658204895739, "percentage": 53.98, "elapsed_time": "1:16:45", "remaining_time": "1:05:26", "throughput": 1322.25, "total_tokens": 6089800}
{"current_steps": 500, "total_steps": 880, "loss": 1.0779, "lr": 1.06880242680232e-05, "epoch": 2.271985494106981, "percentage": 56.82, "elapsed_time": "1:20:46", "remaining_time": "1:01:23", "throughput": 1322.44, "total_tokens": 6409680}
{"current_steps": 525, "total_steps": 880, "loss": 1.0722, "lr": 9.612777191078257e-06, "epoch": 2.385312783318223, "percentage": 59.66, "elapsed_time": "1:24:58", "remaining_time": "0:57:27", "throughput": 1320.03, "total_tokens": 6729680}
{"current_steps": 550, "total_steps": 880, "loss": 1.0663, "lr": 8.542008030801254e-06, "epoch": 2.498640072529465, "percentage": 62.5, "elapsed_time": "1:28:59", "remaining_time": "0:53:23", "throughput": 1320.33, "total_tokens": 7049680}
{"current_steps": 575, "total_steps": 880, "loss": 1.056, "lr": 7.4880993611518095e-06, "epoch": 2.611967361740707, "percentage": 65.34, "elapsed_time": "1:33:00", "remaining_time": "0:49:20", "throughput": 1320.6, "total_tokens": 7369680}
{"current_steps": 600, "total_steps": 880, "loss": 1.0578, "lr": 6.463238778236287e-06, "epoch": 2.725294650951949, "percentage": 68.18, "elapsed_time": "1:37:02", "remaining_time": "0:45:17", "throughput": 1320.75, "total_tokens": 7689680}
{"current_steps": 625, "total_steps": 880, "loss": 1.0531, "lr": 5.479277960676959e-06, "epoch": 2.838621940163191, "percentage": 71.02, "elapsed_time": "1:41:03", "remaining_time": "0:41:13", "throughput": 1320.96, "total_tokens": 8009600}
{"current_steps": 650, "total_steps": 880, "loss": 1.0523, "lr": 4.547595614593489e-06, "epoch": 2.951949229374433, "percentage": 73.86, "elapsed_time": "1:45:04", "remaining_time": "0:37:10", "throughput": 1321.16, "total_tokens": 8329600}
{"current_steps": 675, "total_steps": 880, "loss": 1.0127, "lr": 3.6789658881265135e-06, "epoch": 3.067996373526745, "percentage": 76.7, "elapsed_time": "1:49:09", "remaining_time": "0:33:09", "throughput": 1321.35, "total_tokens": 8654720}
{"current_steps": 700, "total_steps": 880, "loss": 0.9245, "lr": 2.883433777182255e-06, "epoch": 3.1813236627379875, "percentage": 79.55, "elapsed_time": "1:53:11", "remaining_time": "0:29:06", "throughput": 1321.51, "total_tokens": 8974520}
{"current_steps": 725, "total_steps": 880, "loss": 0.918, "lr": 2.170198963229372e-06, "epoch": 3.2946509519492295, "percentage": 82.39, "elapsed_time": "1:57:12", "remaining_time": "0:25:03", "throughput": 1321.69, "total_tokens": 9294520}
{"current_steps": 750, "total_steps": 880, "loss": 0.9192, "lr": 1.547509426469368e-06, "epoch": 3.4079782411604715, "percentage": 85.23, "elapsed_time": "2:01:13", "remaining_time": "0:21:00", "throughput": 1321.84, "total_tokens": 9614520}
{"current_steps": 775, "total_steps": 880, "loss": 0.9177, "lr": 1.022566064657663e-06, "epoch": 3.5213055303717136, "percentage": 88.07, "elapsed_time": "2:05:26", "remaining_time": "0:16:59", "throughput": 1319.93, "total_tokens": 9934520}
{"current_steps": 800, "total_steps": 880, "loss": 0.9152, "lr": 6.01439420581047e-07, "epoch": 3.6346328195829556, "percentage": 90.91, "elapsed_time": "2:09:27", "remaining_time": "0:12:56", "throughput": 1320.12, "total_tokens": 10254520}
{"current_steps": 825, "total_steps": 880, "loss": 0.917, "lr": 2.889994811704966e-07, "epoch": 3.7479601087941976, "percentage": 93.75, "elapsed_time": "2:13:29", "remaining_time": "0:08:53", "throughput": 1320.3, "total_tokens": 10574520}
{"current_steps": 850, "total_steps": 880, "loss": 0.912, "lr": 8.885936006545304e-08, "epoch": 3.8612873980054396, "percentage": 96.59, "elapsed_time": "2:17:30", "remaining_time": "0:04:51", "throughput": 1320.48, "total_tokens": 10894520}
{"current_steps": 875, "total_steps": 880, "loss": 0.9239, "lr": 3.333514894887646e-09, "epoch": 3.9746146872166817, "percentage": 99.43, "elapsed_time": "2:21:31", "remaining_time": "0:00:48", "throughput": 1320.65, "total_tokens": 11214520}
{"current_steps": 880, "total_steps": 880, "epoch": 3.99728014505893, "percentage": 100.0, "elapsed_time": "2:22:32", "remaining_time": "0:00:00", "throughput": 1318.79, "total_tokens": 11278520}