Files
sera-3160__Qwen3-8B/trainer_log.jsonl

53 lines
9.4 KiB
Plaintext
Raw Permalink Normal View History

{"current_steps": 5, "total_steps": 231, "loss": 0.4313, "lr": 6.666666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:02:41", "remaining_time": "2:01:28"}
{"current_steps": 10, "total_steps": 231, "loss": 0.3895, "lr": 1.5000000000000002e-05, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:05:14", "remaining_time": "1:56:01"}
{"current_steps": 15, "total_steps": 231, "loss": 0.3418, "lr": 2.3333333333333336e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:07:48", "remaining_time": "1:52:21"}
{"current_steps": 20, "total_steps": 231, "loss": 0.3153, "lr": 3.1666666666666666e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:10:20", "remaining_time": "1:49:07"}
{"current_steps": 25, "total_steps": 231, "loss": 0.2946, "lr": 4e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:12:53", "remaining_time": "1:46:10"}
{"current_steps": 30, "total_steps": 231, "loss": 0.2711, "lr": 3.994244399375679e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:15:25", "remaining_time": "1:43:19"}
{"current_steps": 35, "total_steps": 231, "loss": 0.2525, "lr": 3.977010724441261e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:17:57", "remaining_time": "1:40:31"}
{"current_steps": 40, "total_steps": 231, "loss": 0.2416, "lr": 3.9483981653469586e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:20:29", "remaining_time": "1:37:49"}
{"current_steps": 45, "total_steps": 231, "loss": 0.2317, "lr": 3.908571404555758e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:23:01", "remaining_time": "1:35:11"}
{"current_steps": 50, "total_steps": 231, "loss": 0.2282, "lr": 3.8577596689969346e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:25:34", "remaining_time": "1:32:33"}
{"current_steps": 55, "total_steps": 231, "loss": 0.2185, "lr": 3.7962554107273926e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:28:06", "remaining_time": "1:29:57"}
{"current_steps": 60, "total_steps": 231, "loss": 0.2129, "lr": 3.724412623694427e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:30:38", "remaining_time": "1:27:20"}
{"current_steps": 65, "total_steps": 231, "loss": 0.2075, "lr": 3.642644806287938e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:33:11", "remaining_time": "1:24:44"}
{"current_steps": 70, "total_steps": 231, "loss": 0.206, "lr": 3.55142258140884e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:35:42", "remaining_time": "1:22:07"}
{"current_steps": 75, "total_steps": 231, "loss": 0.206, "lr": 3.451270987751598e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:38:15", "remaining_time": "1:19:33"}
{"current_steps": 80, "total_steps": 231, "loss": 0.1969, "lr": 3.342766457891194e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:40:46", "remaining_time": "1:16:57"}
{"current_steps": 85, "total_steps": 231, "loss": 0.1944, "lr": 3.226533500567433e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:43:18", "remaining_time": "1:14:23"}
{"current_steps": 90, "total_steps": 231, "loss": 0.1965, "lr": 3.1032411062620544e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:45:50", "remaining_time": "1:11:49"}
{"current_steps": 95, "total_steps": 231, "loss": 0.192, "lr": 2.973598896756697e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "0:48:23", "remaining_time": "1:09:16"}
{"current_steps": 100, "total_steps": 231, "loss": 0.1911, "lr": 2.8383530408333285e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "0:50:55", "remaining_time": "1:06:43"}
{"current_steps": 105, "total_steps": 231, "loss": 0.1887, "lr": 2.6982819596247373e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:53:27", "remaining_time": "1:04:08"}
{"current_steps": 110, "total_steps": 231, "loss": 0.1847, "lr": 2.554191846333378e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:55:58", "remaining_time": "1:01:34"}
{"current_steps": 115, "total_steps": 231, "loss": 0.1857, "lr": 2.4069120261052682e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:58:30", "remaining_time": "0:59:00"}
{"current_steps": 120, "total_steps": 231, "loss": 0.1867, "lr": 2.2572901827656626e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "1:01:00", "remaining_time": "0:56:26"}
{"current_steps": 125, "total_steps": 231, "loss": 0.1845, "lr": 2.1061874798894992e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "1:03:32", "remaining_time": "0:53:52"}
{"current_steps": 130, "total_steps": 231, "loss": 0.1823, "lr": 1.9544736042877886e-05, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:06:03", "remaining_time": "0:51:19"}
{"current_steps": 135, "total_steps": 231, "loss": 0.1826, "lr": 1.8030217604376628e-05, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:08:37", "remaining_time": "0:48:47"}
{"current_steps": 140, "total_steps": 231, "loss": 0.1834, "lr": 1.6527036446661396e-05, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:11:09", "remaining_time": "0:46:15"}
{"current_steps": 145, "total_steps": 231, "loss": 0.1806, "lr": 1.5043844280142005e-05, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:13:42", "remaining_time": "0:43:42"}
{"current_steps": 150, "total_steps": 231, "loss": 0.1778, "lr": 1.358917776657806e-05, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:16:13", "remaining_time": "0:41:09"}
{"current_steps": 155, "total_steps": 231, "loss": 0.1763, "lr": 1.2171409385463218e-05, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:18:44", "remaining_time": "0:38:36"}
{"current_steps": 160, "total_steps": 231, "loss": 0.1777, "lr": 1.0798699245376959e-05, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:21:15", "remaining_time": "0:36:03"}
{"current_steps": 165, "total_steps": 231, "loss": 0.1781, "lr": 9.478948117658577e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:23:47", "remaining_time": "0:33:30"}
{"current_steps": 170, "total_steps": 231, "loss": 0.1799, "lr": 8.219751962722726e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:26:19", "remaining_time": "0:30:58"}
{"current_steps": 175, "total_steps": 231, "loss": 0.1719, "lr": 7.028358210744881e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:28:50", "remaining_time": "0:28:25"}
{"current_steps": 180, "total_steps": 231, "loss": 0.1778, "lr": 5.911624048347757e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:31:22", "remaining_time": "0:25:53"}
{"current_steps": 185, "total_steps": 231, "loss": 0.1766, "lr": 4.875976951373633e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:33:54", "remaining_time": "0:23:21"}
{"current_steps": 190, "total_steps": 231, "loss": 0.1751, "lr": 3.927377690900436e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:36:26", "remaining_time": "0:20:48"}
{"current_steps": 195, "total_steps": 231, "loss": 0.1757, "lr": 3.071286025423983e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:38:57", "remaining_time": "0:18:16"}
{"current_steps": 200, "total_steps": 231, "loss": 0.1741, "lr": 2.312629276668554e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:41:29", "remaining_time": "0:15:43"}
{"current_steps": 205, "total_steps": 231, "loss": 0.176, "lr": 1.6557739698909436e-06, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:44:00", "remaining_time": "0:13:11"}
{"current_steps": 210, "total_steps": 231, "loss": 0.1749, "lr": 1.1045007019049182e-06, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "1:46:32", "remaining_time": "0:10:39"}
{"current_steps": 215, "total_steps": 231, "loss": 0.172, "lr": 6.619823814758786e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "1:49:03", "remaining_time": "0:08:06"}
{"current_steps": 220, "total_steps": 231, "loss": 0.1755, "lr": 3.307659673251595e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "1:51:36", "remaining_time": "0:05:34"}
{"current_steps": 225, "total_steps": 231, "loss": 0.1759, "lr": 1.1275780885282806e-07, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "1:54:07", "remaining_time": "0:03:02"}
{"current_steps": 230, "total_steps": 231, "loss": 0.1756, "lr": 9.212673951897177e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "1:56:37", "remaining_time": "0:00:30"}
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:57:16", "remaining_time": "0:00:00"}
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}