| {"current_steps": 5, "total_steps": 168, "loss": 0.9542, "learning_rate": 4.989080197352834e-05, "epoch": 0.08888888888888889, "percentage": 2.98, "elapsed_time": "0:00:33", "remaining_time": "0:18:26", "throughput": 1389.23, "total_tokens": 47168} | |
| {"current_steps": 10, "total_steps": 168, "loss": 0.7834, "learning_rate": 4.956416183083221e-05, "epoch": 0.17777777777777778, "percentage": 5.95, "elapsed_time": "0:01:07", "remaining_time": "0:17:48", "throughput": 1487.79, "total_tokens": 100640} | |
| {"current_steps": 15, "total_steps": 168, "loss": 0.7296, "learning_rate": 4.9022933048627496e-05, "epoch": 0.26666666666666666, "percentage": 8.93, "elapsed_time": "0:01:40", "remaining_time": "0:17:06", "throughput": 1490.51, "total_tokens": 150048} | |
| {"current_steps": 20, "total_steps": 168, "loss": 0.6653, "learning_rate": 4.827184371610511e-05, "epoch": 0.35555555555555557, "percentage": 11.9, "elapsed_time": "0:02:11", "remaining_time": "0:16:15", "throughput": 1493.24, "total_tokens": 196928} | |
| {"current_steps": 25, "total_steps": 168, "loss": 0.683, "learning_rate": 4.731745523109029e-05, "epoch": 0.4444444444444444, "percentage": 14.88, "elapsed_time": "0:02:41", "remaining_time": "0:15:24", "throughput": 1513.54, "total_tokens": 244592} | |
| {"current_steps": 30, "total_steps": 168, "loss": 0.5651, "learning_rate": 4.6168104980707107e-05, "epoch": 0.5333333333333333, "percentage": 17.86, "elapsed_time": "0:03:11", "remaining_time": "0:14:40", "throughput": 1533.3, "total_tokens": 293488} | |
| {"current_steps": 35, "total_steps": 168, "loss": 0.5411, "learning_rate": 4.4833833507280884e-05, "epoch": 0.6222222222222222, "percentage": 20.83, "elapsed_time": "0:03:42", "remaining_time": "0:14:05", "throughput": 1520.29, "total_tokens": 338160} | |
| {"current_steps": 40, "total_steps": 168, "loss": 0.572, "learning_rate": 4.332629679574566e-05, "epoch": 0.7111111111111111, "percentage": 23.81, "elapsed_time": "0:04:11", "remaining_time": "0:13:24", "throughput": 1523.32, "total_tokens": 382768} | |
| {"current_steps": 45, "total_steps": 168, "loss": 0.6106, "learning_rate": 4.16586644488001e-05, "epoch": 0.8, "percentage": 26.79, "elapsed_time": "0:04:41", "remaining_time": "0:12:50", "throughput": 1528.21, "total_tokens": 430928} | |
| {"current_steps": 50, "total_steps": 168, "loss": 0.5552, "learning_rate": 3.9845504639337535e-05, "epoch": 0.8888888888888888, "percentage": 29.76, "elapsed_time": "0:05:12", "remaining_time": "0:12:16", "throughput": 1529.26, "total_tokens": 477520} | |
| {"current_steps": 55, "total_steps": 168, "loss": 0.5659, "learning_rate": 3.790265684518767e-05, "epoch": 0.9777777777777777, "percentage": 32.74, "elapsed_time": "0:05:44", "remaining_time": "0:11:47", "throughput": 1528.57, "total_tokens": 526640} | |
| {"current_steps": 60, "total_steps": 168, "loss": 0.58, "learning_rate": 3.5847093477938956e-05, "epoch": 1.0666666666666667, "percentage": 35.71, "elapsed_time": "0:06:17", "remaining_time": "0:11:20", "throughput": 1527.01, "total_tokens": 577184} | |
| {"current_steps": 65, "total_steps": 168, "loss": 0.5429, "learning_rate": 3.369677161463068e-05, "epoch": 1.1555555555555554, "percentage": 38.69, "elapsed_time": "0:06:48", "remaining_time": "0:10:47", "throughput": 1529.65, "total_tokens": 625344} | |
| {"current_steps": 70, "total_steps": 168, "loss": 0.4384, "learning_rate": 3.147047612756302e-05, "epoch": 1.2444444444444445, "percentage": 41.67, "elapsed_time": "0:07:17", "remaining_time": "0:10:12", "throughput": 1532.32, "total_tokens": 670224} | |
| {"current_steps": 75, "total_steps": 168, "loss": 0.5749, "learning_rate": 2.918765558261841e-05, "epoch": 1.3333333333333333, "percentage": 44.64, "elapsed_time": "0:07:48", "remaining_time": "0:09:41", "throughput": 1525.37, "total_tokens": 714880} | |
| {"current_steps": 80, "total_steps": 168, "loss": 0.4222, "learning_rate": 2.686825233966061e-05, "epoch": 1.4222222222222223, "percentage": 47.62, "elapsed_time": "0:08:17", "remaining_time": "0:09:06", "throughput": 1514.93, "total_tokens": 752944} | |
| {"current_steps": 85, "total_steps": 168, "loss": 0.556, "learning_rate": 2.4532528339227452e-05, "epoch": 1.511111111111111, "percentage": 50.6, "elapsed_time": "0:08:48", "remaining_time": "0:08:35", "throughput": 1519.0, "total_tokens": 802064} | |
| {"current_steps": 90, "total_steps": 168, "loss": 0.4963, "learning_rate": 2.2200888097417307e-05, "epoch": 1.6, "percentage": 53.57, "elapsed_time": "0:09:19", "remaining_time": "0:08:05", "throughput": 1522.01, "total_tokens": 852112} | |
| {"current_steps": 95, "total_steps": 168, "loss": 0.5085, "learning_rate": 1.9893700455257996e-05, "epoch": 1.6888888888888889, "percentage": 56.55, "elapsed_time": "0:09:54", "remaining_time": "0:07:36", "throughput": 1522.94, "total_tokens": 905184} | |
| {"current_steps": 100, "total_steps": 168, "loss": 0.4726, "learning_rate": 1.7631120639727393e-05, "epoch": 1.7777777777777777, "percentage": 59.52, "elapsed_time": "0:10:23", "remaining_time": "0:07:04", "throughput": 1522.11, "total_tokens": 949424} | |
| {"current_steps": 100, "total_steps": 168, "eval_loss": 0.39410004019737244, "epoch": 1.7777777777777777, "percentage": 59.52, "elapsed_time": "0:10:35", "remaining_time": "0:07:11", "throughput": 1494.69, "total_tokens": 949424} | |
| {"current_steps": 105, "total_steps": 168, "loss": 0.4874, "learning_rate": 1.5432914190872757e-05, "epoch": 1.8666666666666667, "percentage": 62.5, "elapsed_time": "0:11:08", "remaining_time": "0:06:40", "throughput": 1490.45, "total_tokens": 996112} | |
| {"current_steps": 110, "total_steps": 168, "loss": 0.5235, "learning_rate": 1.331828429317345e-05, "epoch": 1.9555555555555557, "percentage": 65.48, "elapsed_time": "0:11:42", "remaining_time": "0:06:10", "throughput": 1491.79, "total_tokens": 1047520} | |
| {"current_steps": 115, "total_steps": 168, "loss": 0.4984, "learning_rate": 1.130570401955322e-05, "epoch": 2.0444444444444443, "percentage": 68.45, "elapsed_time": "0:12:14", "remaining_time": "0:05:38", "throughput": 1493.02, "total_tokens": 1096832} | |
| {"current_steps": 120, "total_steps": 168, "loss": 0.4777, "learning_rate": 9.412754953531663e-06, "epoch": 2.1333333333333333, "percentage": 71.43, "elapsed_time": "0:12:48", "remaining_time": "0:05:07", "throughput": 1498.71, "total_tokens": 1151104} | |
| {"current_steps": 125, "total_steps": 168, "loss": 0.4918, "learning_rate": 7.65597359928646e-06, "epoch": 2.2222222222222223, "percentage": 74.4, "elapsed_time": "0:13:17", "remaining_time": "0:04:34", "throughput": 1498.79, "total_tokens": 1194592} | |
| {"current_steps": 130, "total_steps": 168, "loss": 0.4573, "learning_rate": 6.050706921363672e-06, "epoch": 2.311111111111111, "percentage": 77.38, "elapsed_time": "0:13:46", "remaining_time": "0:04:01", "throughput": 1494.08, "total_tokens": 1235104} | |
| {"current_steps": 135, "total_steps": 168, "loss": 0.4549, "learning_rate": 4.610978276018496e-06, "epoch": 2.4, "percentage": 80.36, "elapsed_time": "0:14:16", "remaining_time": "0:03:29", "throughput": 1494.64, "total_tokens": 1280560} | |
| {"current_steps": 140, "total_steps": 168, "loss": 0.5422, "learning_rate": 3.3493649053890326e-06, "epoch": 2.488888888888889, "percentage": 83.33, "elapsed_time": "0:14:48", "remaining_time": "0:02:57", "throughput": 1497.43, "total_tokens": 1329792} | |
| {"current_steps": 145, "total_steps": 168, "loss": 0.4968, "learning_rate": 2.2768880646947268e-06, "epoch": 2.5777777777777775, "percentage": 86.31, "elapsed_time": "0:15:20", "remaining_time": "0:02:26", "throughput": 1500.22, "total_tokens": 1380976} | |
| {"current_steps": 150, "total_steps": 168, "loss": 0.4361, "learning_rate": 1.4029167422908107e-06, "epoch": 2.6666666666666665, "percentage": 89.29, "elapsed_time": "0:15:50", "remaining_time": "0:01:54", "throughput": 1497.23, "total_tokens": 1423712} | |
| {"current_steps": 155, "total_steps": 168, "loss": 0.4517, "learning_rate": 7.350858136652261e-07, "epoch": 2.7555555555555555, "percentage": 92.26, "elapsed_time": "0:16:21", "remaining_time": "0:01:22", "throughput": 1498.31, "total_tokens": 1470000} | |
| {"current_steps": 160, "total_steps": 168, "loss": 0.4099, "learning_rate": 2.7922934437178695e-07, "epoch": 2.8444444444444446, "percentage": 95.24, "elapsed_time": "0:16:51", "remaining_time": "0:00:50", "throughput": 1498.38, "total_tokens": 1515168} | |
| {"current_steps": 165, "total_steps": 168, "loss": 0.4861, "learning_rate": 3.9329624554584884e-08, "epoch": 2.9333333333333336, "percentage": 98.21, "elapsed_time": "0:17:21", "remaining_time": "0:00:18", "throughput": 1504.61, "total_tokens": 1566432} | |
| {"current_steps": 168, "total_steps": 168, "epoch": 2.986666666666667, "percentage": 100.0, "elapsed_time": "0:17:43", "remaining_time": "0:00:00", "throughput": 1501.4, "total_tokens": 1596080} | |