s1K_reformat_v2 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
0ca78b1 verified
{"current_steps": 1, "total_steps": 30, "loss": 0.4418, "lr": 3.3333333333333333e-06, "epoch": 0.09375, "percentage": 3.33, "elapsed_time": "0:00:18", "remaining_time": "0:09:07"}
{"current_steps": 2, "total_steps": 30, "loss": 0.5045, "lr": 6.666666666666667e-06, "epoch": 0.1875, "percentage": 6.67, "elapsed_time": "0:00:26", "remaining_time": "0:06:14"}
{"current_steps": 3, "total_steps": 30, "loss": 0.4981, "lr": 1e-05, "epoch": 0.28125, "percentage": 10.0, "elapsed_time": "0:00:35", "remaining_time": "0:05:16"}
{"current_steps": 4, "total_steps": 30, "loss": 0.4423, "lr": 9.966191788709716e-06, "epoch": 0.375, "percentage": 13.33, "elapsed_time": "0:00:43", "remaining_time": "0:04:44"}
{"current_steps": 5, "total_steps": 30, "loss": 0.4336, "lr": 9.86522435289912e-06, "epoch": 0.46875, "percentage": 16.67, "elapsed_time": "0:00:52", "remaining_time": "0:04:21"}
{"current_steps": 6, "total_steps": 30, "loss": 0.4162, "lr": 9.698463103929542e-06, "epoch": 0.5625, "percentage": 20.0, "elapsed_time": "0:01:00", "remaining_time": "0:04:03"}
{"current_steps": 7, "total_steps": 30, "loss": 0.3872, "lr": 9.468163201617063e-06, "epoch": 0.65625, "percentage": 23.33, "elapsed_time": "0:01:09", "remaining_time": "0:03:47"}
{"current_steps": 8, "total_steps": 30, "loss": 0.3715, "lr": 9.177439057064684e-06, "epoch": 0.75, "percentage": 26.67, "elapsed_time": "0:01:17", "remaining_time": "0:03:34"}
{"current_steps": 9, "total_steps": 30, "loss": 0.3734, "lr": 8.83022221559489e-06, "epoch": 0.84375, "percentage": 30.0, "elapsed_time": "0:01:27", "remaining_time": "0:03:23"}
{"current_steps": 10, "total_steps": 30, "loss": 0.3755, "lr": 8.43120818934367e-06, "epoch": 0.9375, "percentage": 33.33, "elapsed_time": "0:01:35", "remaining_time": "0:03:11"}
{"current_steps": 11, "total_steps": 30, "loss": 0.578, "lr": 7.985792958513932e-06, "epoch": 1.0625, "percentage": 36.67, "elapsed_time": "0:02:32", "remaining_time": "0:04:23"}
{"current_steps": 12, "total_steps": 30, "loss": 0.3221, "lr": 7.500000000000001e-06, "epoch": 1.15625, "percentage": 40.0, "elapsed_time": "0:02:40", "remaining_time": "0:04:01"}
{"current_steps": 13, "total_steps": 30, "loss": 0.3391, "lr": 6.980398830195785e-06, "epoch": 1.25, "percentage": 43.33, "elapsed_time": "0:02:49", "remaining_time": "0:03:41"}
{"current_steps": 14, "total_steps": 30, "loss": 0.3351, "lr": 6.434016163555452e-06, "epoch": 1.34375, "percentage": 46.67, "elapsed_time": "0:02:57", "remaining_time": "0:03:23"}
{"current_steps": 15, "total_steps": 30, "loss": 0.3254, "lr": 5.8682408883346535e-06, "epoch": 1.4375, "percentage": 50.0, "elapsed_time": "0:03:06", "remaining_time": "0:03:06"}
{"current_steps": 16, "total_steps": 30, "loss": 0.3213, "lr": 5.290724144552379e-06, "epoch": 1.53125, "percentage": 53.33, "elapsed_time": "0:03:15", "remaining_time": "0:02:51"}
{"current_steps": 17, "total_steps": 30, "loss": 0.28, "lr": 4.7092758554476215e-06, "epoch": 1.625, "percentage": 56.67, "elapsed_time": "0:03:24", "remaining_time": "0:02:36"}
{"current_steps": 18, "total_steps": 30, "loss": 0.3087, "lr": 4.131759111665349e-06, "epoch": 1.71875, "percentage": 60.0, "elapsed_time": "0:03:33", "remaining_time": "0:02:22"}
{"current_steps": 19, "total_steps": 30, "loss": 0.3169, "lr": 3.5659838364445505e-06, "epoch": 1.8125, "percentage": 63.33, "elapsed_time": "0:03:42", "remaining_time": "0:02:08"}
{"current_steps": 20, "total_steps": 30, "loss": 0.2951, "lr": 3.019601169804216e-06, "epoch": 1.90625, "percentage": 66.67, "elapsed_time": "0:03:50", "remaining_time": "0:01:55"}
{"current_steps": 21, "total_steps": 30, "loss": 0.5593, "lr": 2.5000000000000015e-06, "epoch": 2.03125, "percentage": 70.0, "elapsed_time": "0:04:33", "remaining_time": "0:01:57"}
{"current_steps": 22, "total_steps": 30, "loss": 0.2949, "lr": 2.0142070414860704e-06, "epoch": 2.125, "percentage": 73.33, "elapsed_time": "0:04:42", "remaining_time": "0:01:42"}
{"current_steps": 23, "total_steps": 30, "loss": 0.3198, "lr": 1.5687918106563326e-06, "epoch": 2.21875, "percentage": 76.67, "elapsed_time": "0:04:51", "remaining_time": "0:01:28"}
{"current_steps": 24, "total_steps": 30, "loss": 0.2861, "lr": 1.1697777844051105e-06, "epoch": 2.3125, "percentage": 80.0, "elapsed_time": "0:04:59", "remaining_time": "0:01:14"}
{"current_steps": 25, "total_steps": 30, "loss": 0.2944, "lr": 8.225609429353187e-07, "epoch": 2.40625, "percentage": 83.33, "elapsed_time": "0:05:07", "remaining_time": "0:01:01"}
{"current_steps": 26, "total_steps": 30, "loss": 0.3017, "lr": 5.318367983829393e-07, "epoch": 2.5, "percentage": 86.67, "elapsed_time": "0:05:15", "remaining_time": "0:00:48"}
{"current_steps": 27, "total_steps": 30, "loss": 0.2762, "lr": 3.015368960704584e-07, "epoch": 2.59375, "percentage": 90.0, "elapsed_time": "0:05:24", "remaining_time": "0:00:36"}
{"current_steps": 28, "total_steps": 30, "loss": 0.2966, "lr": 1.3477564710088097e-07, "epoch": 2.6875, "percentage": 93.33, "elapsed_time": "0:05:33", "remaining_time": "0:00:23"}
{"current_steps": 29, "total_steps": 30, "loss": 0.2969, "lr": 3.3808211290284886e-08, "epoch": 2.78125, "percentage": 96.67, "elapsed_time": "0:05:42", "remaining_time": "0:00:11"}
{"current_steps": 30, "total_steps": 30, "loss": 0.2782, "lr": 0.0, "epoch": 2.875, "percentage": 100.0, "elapsed_time": "0:05:51", "remaining_time": "0:00:00"}
{"current_steps": 30, "total_steps": 30, "epoch": 2.875, "percentage": 100.0, "elapsed_time": "0:07:25", "remaining_time": "0:00:00"}