sdar4b-rm-K1-esft-intent / trainer_log.jsonl
autoprogrammer's picture
SDAR-4B random_mask K=1 ESFT-intent (final)
51d7357 verified
{"current_steps": 5, "total_steps": 171, "loss": 1.0312, "lr": 9.986505025774137e-06, "epoch": 0.08771929824561403, "percentage": 2.92, "elapsed_time": "0:00:27", "remaining_time": "0:15:17"}
{"current_steps": 10, "total_steps": 171, "loss": 0.194, "lr": 9.931806517013612e-06, "epoch": 0.17543859649122806, "percentage": 5.85, "elapsed_time": "0:00:48", "remaining_time": "0:12:53"}
{"current_steps": 15, "total_steps": 171, "loss": 0.1074, "lr": 9.835521911952554e-06, "epoch": 0.2631578947368421, "percentage": 8.77, "elapsed_time": "0:01:08", "remaining_time": "0:11:52"}
{"current_steps": 20, "total_steps": 171, "loss": 0.1067, "lr": 9.698463103929542e-06, "epoch": 0.3508771929824561, "percentage": 11.7, "elapsed_time": "0:01:28", "remaining_time": "0:11:11"}
{"current_steps": 25, "total_steps": 171, "loss": 0.0831, "lr": 9.521785803487888e-06, "epoch": 0.43859649122807015, "percentage": 14.62, "elapsed_time": "0:01:49", "remaining_time": "0:10:38"}
{"current_steps": 30, "total_steps": 171, "loss": 0.0777, "lr": 9.306979793165682e-06, "epoch": 0.5263157894736842, "percentage": 17.54, "elapsed_time": "0:02:09", "remaining_time": "0:10:09"}
{"current_steps": 35, "total_steps": 171, "loss": 0.0689, "lr": 9.055856365316012e-06, "epoch": 0.6140350877192983, "percentage": 20.47, "elapsed_time": "0:02:30", "remaining_time": "0:09:43"}
{"current_steps": 40, "total_steps": 171, "loss": 0.0631, "lr": 8.770533048884483e-06, "epoch": 0.7017543859649122, "percentage": 23.39, "elapsed_time": "0:02:50", "remaining_time": "0:09:18"}
{"current_steps": 45, "total_steps": 171, "loss": 0.0516, "lr": 8.453415753931223e-06, "epoch": 0.7894736842105263, "percentage": 26.32, "elapsed_time": "0:03:11", "remaining_time": "0:08:54"}
{"current_steps": 50, "total_steps": 171, "loss": 0.0599, "lr": 8.107178484458825e-06, "epoch": 0.8771929824561403, "percentage": 29.24, "elapsed_time": "0:03:31", "remaining_time": "0:08:31"}
{"current_steps": 55, "total_steps": 171, "loss": 0.0568, "lr": 7.734740790612137e-06, "epoch": 0.9649122807017544, "percentage": 32.16, "elapsed_time": "0:03:51", "remaining_time": "0:08:08"}
{"current_steps": 60, "total_steps": 171, "loss": 0.0391, "lr": 7.33924315037804e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "0:04:30", "remaining_time": "0:08:20"}
{"current_steps": 65, "total_steps": 171, "loss": 0.028, "lr": 6.924020488372229e-06, "epoch": 1.1403508771929824, "percentage": 38.01, "elapsed_time": "0:04:51", "remaining_time": "0:07:54"}
{"current_steps": 70, "total_steps": 171, "loss": 0.0301, "lr": 6.492574055008474e-06, "epoch": 1.2280701754385965, "percentage": 40.94, "elapsed_time": "0:05:11", "remaining_time": "0:07:29"}
{"current_steps": 75, "total_steps": 171, "loss": 0.0321, "lr": 6.048541903171552e-06, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "0:05:31", "remaining_time": "0:07:04"}
{"current_steps": 80, "total_steps": 171, "loss": 0.0263, "lr": 5.5956682113411184e-06, "epoch": 1.4035087719298245, "percentage": 46.78, "elapsed_time": "0:05:52", "remaining_time": "0:06:40"}
{"current_steps": 85, "total_steps": 171, "loss": 0.0281, "lr": 5.137771711840811e-06, "epoch": 1.4912280701754386, "percentage": 49.71, "elapsed_time": "0:06:12", "remaining_time": "0:06:17"}
{"current_steps": 90, "total_steps": 171, "loss": 0.026, "lr": 4.67871349043265e-06, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "0:06:33", "remaining_time": "0:05:53"}
{"current_steps": 95, "total_steps": 171, "loss": 0.0334, "lr": 4.222364428777786e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:06:53", "remaining_time": "0:05:30"}
{"current_steps": 100, "total_steps": 171, "loss": 0.0266, "lr": 3.7725725642960047e-06, "epoch": 1.7543859649122808, "percentage": 58.48, "elapsed_time": "0:07:13", "remaining_time": "0:05:08"}
{"current_steps": 105, "total_steps": 171, "loss": 0.0194, "lr": 3.333130642653024e-06, "epoch": 1.8421052631578947, "percentage": 61.4, "elapsed_time": "0:07:34", "remaining_time": "0:04:45"}
{"current_steps": 110, "total_steps": 171, "loss": 0.0194, "lr": 2.907744136480194e-06, "epoch": 1.9298245614035088, "percentage": 64.33, "elapsed_time": "0:07:54", "remaining_time": "0:04:23"}
{"current_steps": 115, "total_steps": 171, "loss": 0.0231, "lr": 2.5000000000000015e-06, "epoch": 2.017543859649123, "percentage": 67.25, "elapsed_time": "0:08:33", "remaining_time": "0:04:10"}
{"current_steps": 120, "total_steps": 171, "loss": 0.0063, "lr": 2.113336423025269e-06, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "0:08:53", "remaining_time": "0:03:46"}
{"current_steps": 125, "total_steps": 171, "loss": 0.01, "lr": 1.7510138393732029e-06, "epoch": 2.192982456140351, "percentage": 73.1, "elapsed_time": "0:09:14", "remaining_time": "0:03:23"}
{"current_steps": 130, "total_steps": 171, "loss": 0.0078, "lr": 1.4160874341577447e-06, "epoch": 2.280701754385965, "percentage": 76.02, "elapsed_time": "0:09:34", "remaining_time": "0:03:01"}
{"current_steps": 135, "total_steps": 171, "loss": 0.0113, "lr": 1.1113813817849312e-06, "epoch": 2.3684210526315788, "percentage": 78.95, "elapsed_time": "0:09:55", "remaining_time": "0:02:38"}
{"current_steps": 140, "total_steps": 171, "loss": 0.0086, "lr": 8.3946503188225e-07, "epoch": 2.456140350877193, "percentage": 81.87, "elapsed_time": "0:10:15", "remaining_time": "0:02:16"}
{"current_steps": 145, "total_steps": 171, "loss": 0.0075, "lr": 6.026312439675553e-07, "epoch": 2.543859649122807, "percentage": 84.8, "elapsed_time": "0:10:35", "remaining_time": "0:01:54"}
{"current_steps": 150, "total_steps": 171, "loss": 0.0072, "lr": 4.0287705354446147e-07, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "0:10:56", "remaining_time": "0:01:31"}
{"current_steps": 155, "total_steps": 171, "loss": 0.0101, "lr": 2.4188683265204125e-07, "epoch": 2.719298245614035, "percentage": 90.64, "elapsed_time": "0:11:16", "remaining_time": "0:01:09"}
{"current_steps": 160, "total_steps": 171, "loss": 0.0077, "lr": 1.210180868628219e-07, "epoch": 2.807017543859649, "percentage": 93.57, "elapsed_time": "0:11:37", "remaining_time": "0:00:47"}
{"current_steps": 165, "total_steps": 171, "loss": 0.0088, "lr": 4.129000849198872e-08, "epoch": 2.8947368421052633, "percentage": 96.49, "elapsed_time": "0:11:57", "remaining_time": "0:00:26"}
{"current_steps": 170, "total_steps": 171, "loss": 0.0077, "lr": 3.3748825396817675e-09, "epoch": 2.982456140350877, "percentage": 99.42, "elapsed_time": "0:12:18", "remaining_time": "0:00:04"}
{"current_steps": 171, "total_steps": 171, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:12:39", "remaining_time": "0:00:00"}