sdar4b-mbc-K1-esft-intent / trainer_log.jsonl
autoprogrammer's picture
SDAR-4B multi_block_causal K=1 ESFT-intent (final)
4b7f218 verified
{"current_steps": 5, "total_steps": 171, "loss": 0.7867, "lr": 9.986505025774137e-06, "epoch": 0.08771929824561403, "percentage": 2.92, "elapsed_time": "0:00:29", "remaining_time": "0:16:05"}
{"current_steps": 10, "total_steps": 171, "loss": 0.1302, "lr": 9.931806517013612e-06, "epoch": 0.17543859649122806, "percentage": 5.85, "elapsed_time": "0:00:49", "remaining_time": "0:13:17"}
{"current_steps": 15, "total_steps": 171, "loss": 0.0532, "lr": 9.835521911952554e-06, "epoch": 0.2631578947368421, "percentage": 8.77, "elapsed_time": "0:01:10", "remaining_time": "0:12:08"}
{"current_steps": 20, "total_steps": 171, "loss": 0.0318, "lr": 9.698463103929542e-06, "epoch": 0.3508771929824561, "percentage": 11.7, "elapsed_time": "0:01:30", "remaining_time": "0:11:23"}
{"current_steps": 25, "total_steps": 171, "loss": 0.0336, "lr": 9.521785803487888e-06, "epoch": 0.43859649122807015, "percentage": 14.62, "elapsed_time": "0:01:50", "remaining_time": "0:10:48"}
{"current_steps": 30, "total_steps": 171, "loss": 0.0276, "lr": 9.306979793165682e-06, "epoch": 0.5263157894736842, "percentage": 17.54, "elapsed_time": "0:02:11", "remaining_time": "0:10:17"}
{"current_steps": 35, "total_steps": 171, "loss": 0.0205, "lr": 9.055856365316012e-06, "epoch": 0.6140350877192983, "percentage": 20.47, "elapsed_time": "0:02:31", "remaining_time": "0:09:50"}
{"current_steps": 40, "total_steps": 171, "loss": 0.0186, "lr": 8.770533048884483e-06, "epoch": 0.7017543859649122, "percentage": 23.39, "elapsed_time": "0:02:52", "remaining_time": "0:09:24"}
{"current_steps": 45, "total_steps": 171, "loss": 0.0168, "lr": 8.453415753931223e-06, "epoch": 0.7894736842105263, "percentage": 26.32, "elapsed_time": "0:03:12", "remaining_time": "0:08:59"}
{"current_steps": 50, "total_steps": 171, "loss": 0.0158, "lr": 8.107178484458825e-06, "epoch": 0.8771929824561403, "percentage": 29.24, "elapsed_time": "0:03:33", "remaining_time": "0:08:36"}
{"current_steps": 55, "total_steps": 171, "loss": 0.0158, "lr": 7.734740790612137e-06, "epoch": 0.9649122807017544, "percentage": 32.16, "elapsed_time": "0:03:53", "remaining_time": "0:08:13"}
{"current_steps": 60, "total_steps": 171, "loss": 0.0109, "lr": 7.33924315037804e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "0:04:32", "remaining_time": "0:08:23"}
{"current_steps": 65, "total_steps": 171, "loss": 0.0093, "lr": 6.924020488372229e-06, "epoch": 1.1403508771929824, "percentage": 38.01, "elapsed_time": "0:04:52", "remaining_time": "0:07:57"}
{"current_steps": 70, "total_steps": 171, "loss": 0.0078, "lr": 6.492574055008474e-06, "epoch": 1.2280701754385965, "percentage": 40.94, "elapsed_time": "0:05:13", "remaining_time": "0:07:32"}
{"current_steps": 75, "total_steps": 171, "loss": 0.0069, "lr": 6.048541903171552e-06, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "0:05:33", "remaining_time": "0:07:07"}
{"current_steps": 80, "total_steps": 171, "loss": 0.0084, "lr": 5.5956682113411184e-06, "epoch": 1.4035087719298245, "percentage": 46.78, "elapsed_time": "0:05:54", "remaining_time": "0:06:42"}
{"current_steps": 85, "total_steps": 171, "loss": 0.0075, "lr": 5.137771711840811e-06, "epoch": 1.4912280701754386, "percentage": 49.71, "elapsed_time": "0:06:14", "remaining_time": "0:06:19"}
{"current_steps": 90, "total_steps": 171, "loss": 0.0064, "lr": 4.67871349043265e-06, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "0:06:35", "remaining_time": "0:05:55"}
{"current_steps": 95, "total_steps": 171, "loss": 0.0059, "lr": 4.222364428777786e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:06:55", "remaining_time": "0:05:32"}
{"current_steps": 100, "total_steps": 171, "loss": 0.0082, "lr": 3.7725725642960047e-06, "epoch": 1.7543859649122808, "percentage": 58.48, "elapsed_time": "0:07:16", "remaining_time": "0:05:09"}
{"current_steps": 105, "total_steps": 171, "loss": 0.0054, "lr": 3.333130642653024e-06, "epoch": 1.8421052631578947, "percentage": 61.4, "elapsed_time": "0:07:36", "remaining_time": "0:04:47"}
{"current_steps": 110, "total_steps": 171, "loss": 0.0085, "lr": 2.907744136480194e-06, "epoch": 1.9298245614035088, "percentage": 64.33, "elapsed_time": "0:07:57", "remaining_time": "0:04:24"}
{"current_steps": 115, "total_steps": 171, "loss": 0.0067, "lr": 2.5000000000000015e-06, "epoch": 2.017543859649123, "percentage": 67.25, "elapsed_time": "0:08:34", "remaining_time": "0:04:10"}
{"current_steps": 120, "total_steps": 171, "loss": 0.0028, "lr": 2.113336423025269e-06, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "0:08:55", "remaining_time": "0:03:47"}
{"current_steps": 125, "total_steps": 171, "loss": 0.0028, "lr": 1.7510138393732029e-06, "epoch": 2.192982456140351, "percentage": 73.1, "elapsed_time": "0:09:15", "remaining_time": "0:03:24"}
{"current_steps": 130, "total_steps": 171, "loss": 0.0023, "lr": 1.4160874341577447e-06, "epoch": 2.280701754385965, "percentage": 76.02, "elapsed_time": "0:09:36", "remaining_time": "0:03:01"}
{"current_steps": 135, "total_steps": 171, "loss": 0.0029, "lr": 1.1113813817849312e-06, "epoch": 2.3684210526315788, "percentage": 78.95, "elapsed_time": "0:09:56", "remaining_time": "0:02:39"}
{"current_steps": 140, "total_steps": 171, "loss": 0.0027, "lr": 8.3946503188225e-07, "epoch": 2.456140350877193, "percentage": 81.87, "elapsed_time": "0:10:17", "remaining_time": "0:02:16"}
{"current_steps": 145, "total_steps": 171, "loss": 0.0025, "lr": 6.026312439675553e-07, "epoch": 2.543859649122807, "percentage": 84.8, "elapsed_time": "0:10:37", "remaining_time": "0:01:54"}
{"current_steps": 150, "total_steps": 171, "loss": 0.0024, "lr": 4.0287705354446147e-07, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "0:10:58", "remaining_time": "0:01:32"}
{"current_steps": 155, "total_steps": 171, "loss": 0.0031, "lr": 2.4188683265204125e-07, "epoch": 2.719298245614035, "percentage": 90.64, "elapsed_time": "0:11:18", "remaining_time": "0:01:10"}
{"current_steps": 160, "total_steps": 171, "loss": 0.0021, "lr": 1.210180868628219e-07, "epoch": 2.807017543859649, "percentage": 93.57, "elapsed_time": "0:11:38", "remaining_time": "0:00:48"}
{"current_steps": 165, "total_steps": 171, "loss": 0.002, "lr": 4.129000849198872e-08, "epoch": 2.8947368421052633, "percentage": 96.49, "elapsed_time": "0:11:59", "remaining_time": "0:00:26"}
{"current_steps": 170, "total_steps": 171, "loss": 0.0027, "lr": 3.3748825396817675e-09, "epoch": 2.982456140350877, "percentage": 99.42, "elapsed_time": "0:12:19", "remaining_time": "0:00:04"}
{"current_steps": 171, "total_steps": 171, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:12:40", "remaining_time": "0:00:00"}