s1K_reformat / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 0
31cccde verified
raw
history blame
5.49 kB
{"current_steps": 1, "total_steps": 30, "loss": 0.5625, "lr": 3.3333333333333333e-06, "epoch": 0.09375, "percentage": 3.33, "elapsed_time": "0:00:14", "remaining_time": "0:07:08"}
{"current_steps": 2, "total_steps": 30, "loss": 0.5852, "lr": 6.666666666666667e-06, "epoch": 0.1875, "percentage": 6.67, "elapsed_time": "0:00:19", "remaining_time": "0:04:32"}
{"current_steps": 3, "total_steps": 30, "loss": 0.5712, "lr": 1e-05, "epoch": 0.28125, "percentage": 10.0, "elapsed_time": "0:00:23", "remaining_time": "0:03:33"}
{"current_steps": 4, "total_steps": 30, "loss": 0.5382, "lr": 9.966191788709716e-06, "epoch": 0.375, "percentage": 13.33, "elapsed_time": "0:00:28", "remaining_time": "0:03:02"}
{"current_steps": 5, "total_steps": 30, "loss": 0.4693, "lr": 9.86522435289912e-06, "epoch": 0.46875, "percentage": 16.67, "elapsed_time": "0:00:32", "remaining_time": "0:02:42"}
{"current_steps": 6, "total_steps": 30, "loss": 0.423, "lr": 9.698463103929542e-06, "epoch": 0.5625, "percentage": 20.0, "elapsed_time": "0:00:36", "remaining_time": "0:02:27"}
{"current_steps": 7, "total_steps": 30, "loss": 0.4039, "lr": 9.468163201617063e-06, "epoch": 0.65625, "percentage": 23.33, "elapsed_time": "0:00:41", "remaining_time": "0:02:15"}
{"current_steps": 8, "total_steps": 30, "loss": 0.3673, "lr": 9.177439057064684e-06, "epoch": 0.75, "percentage": 26.67, "elapsed_time": "0:00:45", "remaining_time": "0:02:05"}
{"current_steps": 9, "total_steps": 30, "loss": 0.3763, "lr": 8.83022221559489e-06, "epoch": 0.84375, "percentage": 30.0, "elapsed_time": "0:00:49", "remaining_time": "0:01:56"}
{"current_steps": 10, "total_steps": 30, "loss": 0.3948, "lr": 8.43120818934367e-06, "epoch": 0.9375, "percentage": 33.33, "elapsed_time": "0:00:54", "remaining_time": "0:01:48"}
{"current_steps": 11, "total_steps": 30, "loss": 0.56, "lr": 7.985792958513932e-06, "epoch": 1.0625, "percentage": 36.67, "elapsed_time": "0:01:45", "remaining_time": "0:03:01"}
{"current_steps": 12, "total_steps": 30, "loss": 0.3337, "lr": 7.500000000000001e-06, "epoch": 1.15625, "percentage": 40.0, "elapsed_time": "0:01:49", "remaining_time": "0:02:44"}
{"current_steps": 13, "total_steps": 30, "loss": 0.3273, "lr": 6.980398830195785e-06, "epoch": 1.25, "percentage": 43.33, "elapsed_time": "0:01:54", "remaining_time": "0:02:29"}
{"current_steps": 14, "total_steps": 30, "loss": 0.3234, "lr": 6.434016163555452e-06, "epoch": 1.34375, "percentage": 46.67, "elapsed_time": "0:01:58", "remaining_time": "0:02:15"}
{"current_steps": 15, "total_steps": 30, "loss": 0.2844, "lr": 5.8682408883346535e-06, "epoch": 1.4375, "percentage": 50.0, "elapsed_time": "0:02:03", "remaining_time": "0:02:03"}
{"current_steps": 16, "total_steps": 30, "loss": 0.3171, "lr": 5.290724144552379e-06, "epoch": 1.53125, "percentage": 53.33, "elapsed_time": "0:02:08", "remaining_time": "0:01:52"}
{"current_steps": 17, "total_steps": 30, "loss": 0.2731, "lr": 4.7092758554476215e-06, "epoch": 1.625, "percentage": 56.67, "elapsed_time": "0:02:13", "remaining_time": "0:01:42"}
{"current_steps": 18, "total_steps": 30, "loss": 0.2861, "lr": 4.131759111665349e-06, "epoch": 1.71875, "percentage": 60.0, "elapsed_time": "0:02:18", "remaining_time": "0:01:32"}
{"current_steps": 19, "total_steps": 30, "loss": 0.2572, "lr": 3.5659838364445505e-06, "epoch": 1.8125, "percentage": 63.33, "elapsed_time": "0:02:22", "remaining_time": "0:01:22"}
{"current_steps": 20, "total_steps": 30, "loss": 0.2949, "lr": 3.019601169804216e-06, "epoch": 1.90625, "percentage": 66.67, "elapsed_time": "0:02:27", "remaining_time": "0:01:13"}
{"current_steps": 21, "total_steps": 30, "loss": 0.4905, "lr": 2.5000000000000015e-06, "epoch": 2.03125, "percentage": 70.0, "elapsed_time": "0:03:05", "remaining_time": "0:01:19"}
{"current_steps": 22, "total_steps": 30, "loss": 0.2487, "lr": 2.0142070414860704e-06, "epoch": 2.125, "percentage": 73.33, "elapsed_time": "0:03:11", "remaining_time": "0:01:09"}
{"current_steps": 23, "total_steps": 30, "loss": 0.2562, "lr": 1.5687918106563326e-06, "epoch": 2.21875, "percentage": 76.67, "elapsed_time": "0:03:16", "remaining_time": "0:00:59"}
{"current_steps": 24, "total_steps": 30, "loss": 0.2216, "lr": 1.1697777844051105e-06, "epoch": 2.3125, "percentage": 80.0, "elapsed_time": "0:03:21", "remaining_time": "0:00:50"}
{"current_steps": 25, "total_steps": 30, "loss": 0.244, "lr": 8.225609429353187e-07, "epoch": 2.40625, "percentage": 83.33, "elapsed_time": "0:03:26", "remaining_time": "0:00:41"}
{"current_steps": 26, "total_steps": 30, "loss": 0.2334, "lr": 5.318367983829393e-07, "epoch": 2.5, "percentage": 86.67, "elapsed_time": "0:03:31", "remaining_time": "0:00:32"}
{"current_steps": 27, "total_steps": 30, "loss": 0.2174, "lr": 3.015368960704584e-07, "epoch": 2.59375, "percentage": 90.0, "elapsed_time": "0:03:36", "remaining_time": "0:00:24"}
{"current_steps": 28, "total_steps": 30, "loss": 0.2514, "lr": 1.3477564710088097e-07, "epoch": 2.6875, "percentage": 93.33, "elapsed_time": "0:03:40", "remaining_time": "0:00:15"}
{"current_steps": 29, "total_steps": 30, "loss": 0.2288, "lr": 3.3808211290284886e-08, "epoch": 2.78125, "percentage": 96.67, "elapsed_time": "0:03:45", "remaining_time": "0:00:07"}
{"current_steps": 30, "total_steps": 30, "loss": 0.2172, "lr": 0.0, "epoch": 2.875, "percentage": 100.0, "elapsed_time": "0:03:50", "remaining_time": "0:00:00"}
{"current_steps": 30, "total_steps": 30, "epoch": 2.875, "percentage": 100.0, "elapsed_time": "0:05:05", "remaining_time": "0:00:00"}