sdar4b-trace-sft-esft-intent / trainer_log.jsonl
autoprogrammer's picture
SDAR-4B trace_sft on ESFT-intent (final)
c20ea2f verified
{"current_steps": 5, "total_steps": 684, "loss": 4.2805, "lr": 1.904761904761905e-06, "epoch": 0.02197802197802198, "percentage": 0.73, "elapsed_time": "0:00:30", "remaining_time": "1:08:49"}
{"current_steps": 10, "total_steps": 684, "loss": 3.0271, "lr": 4.2857142857142855e-06, "epoch": 0.04395604395604396, "percentage": 1.46, "elapsed_time": "0:00:54", "remaining_time": "1:00:40"}
{"current_steps": 15, "total_steps": 684, "loss": 1.3784, "lr": 6.666666666666667e-06, "epoch": 0.06593406593406594, "percentage": 2.19, "elapsed_time": "0:01:17", "remaining_time": "0:57:50"}
{"current_steps": 20, "total_steps": 684, "loss": 0.6998, "lr": 9.047619047619049e-06, "epoch": 0.08791208791208792, "percentage": 2.92, "elapsed_time": "0:01:41", "remaining_time": "0:56:14"}
{"current_steps": 25, "total_steps": 684, "loss": 0.379, "lr": 9.999494817970498e-06, "epoch": 0.10989010989010989, "percentage": 3.65, "elapsed_time": "0:02:05", "remaining_time": "0:55:07"}
{"current_steps": 30, "total_steps": 684, "loss": 0.3151, "lr": 9.996407964134416e-06, "epoch": 0.13186813186813187, "percentage": 4.39, "elapsed_time": "0:02:29", "remaining_time": "0:54:14"}
{"current_steps": 35, "total_steps": 684, "loss": 0.2672, "lr": 9.990516643685222e-06, "epoch": 0.15384615384615385, "percentage": 5.12, "elapsed_time": "0:02:53", "remaining_time": "0:53:30"}
{"current_steps": 40, "total_steps": 684, "loss": 0.2517, "lr": 9.981824163400827e-06, "epoch": 0.17582417582417584, "percentage": 5.85, "elapsed_time": "0:03:16", "remaining_time": "0:52:51"}
{"current_steps": 45, "total_steps": 684, "loss": 0.2419, "lr": 9.970335402340534e-06, "epoch": 0.1978021978021978, "percentage": 6.58, "elapsed_time": "0:03:40", "remaining_time": "0:52:15"}
{"current_steps": 50, "total_steps": 684, "loss": 0.1812, "lr": 9.956056809106426e-06, "epoch": 0.21978021978021978, "percentage": 7.31, "elapsed_time": "0:04:04", "remaining_time": "0:51:42"}
{"current_steps": 55, "total_steps": 684, "loss": 0.1831, "lr": 9.938996398223802e-06, "epoch": 0.24175824175824176, "percentage": 8.04, "elapsed_time": "0:04:28", "remaining_time": "0:51:10"}
{"current_steps": 60, "total_steps": 684, "loss": 0.1958, "lr": 9.919163745642633e-06, "epoch": 0.26373626373626374, "percentage": 8.77, "elapsed_time": "0:04:52", "remaining_time": "0:50:40"}
{"current_steps": 65, "total_steps": 684, "loss": 0.1636, "lr": 9.896569983362632e-06, "epoch": 0.2857142857142857, "percentage": 9.5, "elapsed_time": "0:05:16", "remaining_time": "0:50:10"}
{"current_steps": 70, "total_steps": 684, "loss": 0.1847, "lr": 9.871227793184893e-06, "epoch": 0.3076923076923077, "percentage": 10.23, "elapsed_time": "0:05:39", "remaining_time": "0:49:42"}
{"current_steps": 75, "total_steps": 684, "loss": 0.1879, "lr": 9.843151399593636e-06, "epoch": 0.32967032967032966, "percentage": 10.96, "elapsed_time": "0:06:03", "remaining_time": "0:49:13"}
{"current_steps": 80, "total_steps": 684, "loss": 0.1914, "lr": 9.81235656177206e-06, "epoch": 0.3516483516483517, "percentage": 11.7, "elapsed_time": "0:06:27", "remaining_time": "0:48:46"}
{"current_steps": 85, "total_steps": 684, "loss": 0.1889, "lr": 9.778860564756769e-06, "epoch": 0.37362637362637363, "percentage": 12.43, "elapsed_time": "0:06:51", "remaining_time": "0:48:19"}
{"current_steps": 90, "total_steps": 684, "loss": 0.1475, "lr": 9.742682209735727e-06, "epoch": 0.3956043956043956, "percentage": 13.16, "elapsed_time": "0:07:15", "remaining_time": "0:47:52"}
{"current_steps": 95, "total_steps": 684, "loss": 0.1618, "lr": 9.703841803495234e-06, "epoch": 0.4175824175824176, "percentage": 13.89, "elapsed_time": "0:07:39", "remaining_time": "0:47:26"}
{"current_steps": 100, "total_steps": 684, "loss": 0.1849, "lr": 9.66236114702178e-06, "epoch": 0.43956043956043955, "percentage": 14.62, "elapsed_time": "0:08:02", "remaining_time": "0:47:00"}
{"current_steps": 105, "total_steps": 684, "loss": 0.1994, "lr": 9.618263523265238e-06, "epoch": 0.46153846153846156, "percentage": 15.35, "elapsed_time": "0:08:26", "remaining_time": "0:46:34"}
{"current_steps": 110, "total_steps": 684, "loss": 0.1643, "lr": 9.57157368407022e-06, "epoch": 0.4835164835164835, "percentage": 16.08, "elapsed_time": "0:08:50", "remaining_time": "0:46:08"}
{"current_steps": 115, "total_steps": 684, "loss": 0.1589, "lr": 9.522317836282949e-06, "epoch": 0.5054945054945055, "percentage": 16.81, "elapsed_time": "0:09:14", "remaining_time": "0:45:42"}
{"current_steps": 120, "total_steps": 684, "loss": 0.1246, "lr": 9.470523627041452e-06, "epoch": 0.5274725274725275, "percentage": 17.54, "elapsed_time": "0:09:38", "remaining_time": "0:45:17"}
{"current_steps": 125, "total_steps": 684, "loss": 0.1561, "lr": 9.416220128257317e-06, "epoch": 0.5494505494505495, "percentage": 18.27, "elapsed_time": "0:10:02", "remaining_time": "0:44:52"}
{"current_steps": 130, "total_steps": 684, "loss": 0.13, "lr": 9.359437820297716e-06, "epoch": 0.5714285714285714, "percentage": 19.01, "elapsed_time": "0:10:25", "remaining_time": "0:44:27"}
{"current_steps": 135, "total_steps": 684, "loss": 0.1064, "lr": 9.300208574876897e-06, "epoch": 0.5934065934065934, "percentage": 19.74, "elapsed_time": "0:10:49", "remaining_time": "0:44:02"}
{"current_steps": 140, "total_steps": 684, "loss": 0.1985, "lr": 9.238565637166692e-06, "epoch": 0.6153846153846154, "percentage": 20.47, "elapsed_time": "0:11:13", "remaining_time": "0:43:37"}
{"current_steps": 145, "total_steps": 684, "loss": 0.1587, "lr": 9.174543607136111e-06, "epoch": 0.6373626373626373, "percentage": 21.2, "elapsed_time": "0:11:37", "remaining_time": "0:43:12"}
{"current_steps": 150, "total_steps": 684, "loss": 0.1558, "lr": 9.108178420130514e-06, "epoch": 0.6593406593406593, "percentage": 21.93, "elapsed_time": "0:12:01", "remaining_time": "0:42:47"}
{"current_steps": 155, "total_steps": 684, "loss": 0.1562, "lr": 9.039507326701207e-06, "epoch": 0.6813186813186813, "percentage": 22.66, "elapsed_time": "0:12:25", "remaining_time": "0:42:22"}
{"current_steps": 160, "total_steps": 684, "loss": 0.1243, "lr": 8.968568871696847e-06, "epoch": 0.7032967032967034, "percentage": 23.39, "elapsed_time": "0:12:48", "remaining_time": "0:41:57"}
{"current_steps": 165, "total_steps": 684, "loss": 0.1176, "lr": 8.895402872628352e-06, "epoch": 0.7252747252747253, "percentage": 24.12, "elapsed_time": "0:13:12", "remaining_time": "0:41:33"}
{"current_steps": 170, "total_steps": 684, "loss": 0.1382, "lr": 8.82005039731946e-06, "epoch": 0.7472527472527473, "percentage": 24.85, "elapsed_time": "0:13:36", "remaining_time": "0:41:08"}
{"current_steps": 175, "total_steps": 684, "loss": 0.1343, "lr": 8.742553740855507e-06, "epoch": 0.7692307692307693, "percentage": 25.58, "elapsed_time": "0:14:00", "remaining_time": "0:40:44"}
{"current_steps": 180, "total_steps": 684, "loss": 0.1503, "lr": 8.66295640184334e-06, "epoch": 0.7912087912087912, "percentage": 26.32, "elapsed_time": "0:14:24", "remaining_time": "0:40:19"}
{"current_steps": 185, "total_steps": 684, "loss": 0.1009, "lr": 8.581303057995697e-06, "epoch": 0.8131868131868132, "percentage": 27.05, "elapsed_time": "0:14:48", "remaining_time": "0:39:55"}
{"current_steps": 190, "total_steps": 684, "loss": 0.1297, "lr": 8.497639541053769e-06, "epoch": 0.8351648351648352, "percentage": 27.78, "elapsed_time": "0:15:11", "remaining_time": "0:39:30"}
{"current_steps": 195, "total_steps": 684, "loss": 0.1501, "lr": 8.412012811061985e-06, "epoch": 0.8571428571428571, "percentage": 28.51, "elapsed_time": "0:15:35", "remaining_time": "0:39:06"}
{"current_steps": 200, "total_steps": 684, "loss": 0.1333, "lr": 8.324470930009514e-06, "epoch": 0.8791208791208791, "percentage": 29.24, "elapsed_time": "0:15:59", "remaining_time": "0:38:41"}
{"current_steps": 205, "total_steps": 684, "loss": 0.1034, "lr": 8.235063034853228e-06, "epoch": 0.9010989010989011, "percentage": 29.97, "elapsed_time": "0:16:23", "remaining_time": "0:38:17"}
{"current_steps": 210, "total_steps": 684, "loss": 0.1048, "lr": 8.143839309937307e-06, "epoch": 0.9230769230769231, "percentage": 30.7, "elapsed_time": "0:16:47", "remaining_time": "0:37:53"}
{"current_steps": 215, "total_steps": 684, "loss": 0.068, "lr": 8.050850958824926e-06, "epoch": 0.945054945054945, "percentage": 31.43, "elapsed_time": "0:17:10", "remaining_time": "0:37:28"}
{"current_steps": 220, "total_steps": 684, "loss": 0.1117, "lr": 7.95615017555788e-06, "epoch": 0.967032967032967, "percentage": 32.16, "elapsed_time": "0:17:34", "remaining_time": "0:37:04"}
{"current_steps": 225, "total_steps": 684, "loss": 0.1327, "lr": 7.859790115360243e-06, "epoch": 0.989010989010989, "percentage": 32.89, "elapsed_time": "0:17:58", "remaining_time": "0:36:40"}
{"current_steps": 230, "total_steps": 684, "loss": 0.0843, "lr": 7.76182486480253e-06, "epoch": 1.0087912087912088, "percentage": 33.63, "elapsed_time": "0:18:36", "remaining_time": "0:36:44"}
{"current_steps": 235, "total_steps": 684, "loss": 0.0637, "lr": 7.662309411443084e-06, "epoch": 1.0307692307692307, "percentage": 34.36, "elapsed_time": "0:19:00", "remaining_time": "0:36:19"}
{"current_steps": 240, "total_steps": 684, "loss": 0.0848, "lr": 7.56129961296375e-06, "epoch": 1.0527472527472528, "percentage": 35.09, "elapsed_time": "0:19:24", "remaining_time": "0:35:54"}
{"current_steps": 245, "total_steps": 684, "loss": 0.0683, "lr": 7.458852165817153e-06, "epoch": 1.0747252747252747, "percentage": 35.82, "elapsed_time": "0:19:48", "remaining_time": "0:35:29"}
{"current_steps": 250, "total_steps": 684, "loss": 0.0627, "lr": 7.355024573403174e-06, "epoch": 1.0967032967032968, "percentage": 36.55, "elapsed_time": "0:20:12", "remaining_time": "0:35:04"}
{"current_steps": 255, "total_steps": 684, "loss": 0.0644, "lr": 7.249875113792485e-06, "epoch": 1.1186813186813187, "percentage": 37.28, "elapsed_time": "0:20:36", "remaining_time": "0:34:39"}
{"current_steps": 260, "total_steps": 684, "loss": 0.0561, "lr": 7.143462807015271e-06, "epoch": 1.1406593406593406, "percentage": 38.01, "elapsed_time": "0:20:59", "remaining_time": "0:34:14"}
{"current_steps": 265, "total_steps": 684, "loss": 0.0676, "lr": 7.035847381933494e-06, "epoch": 1.1626373626373627, "percentage": 38.74, "elapsed_time": "0:21:23", "remaining_time": "0:33:49"}
{"current_steps": 270, "total_steps": 684, "loss": 0.0734, "lr": 6.927089242715277e-06, "epoch": 1.1846153846153846, "percentage": 39.47, "elapsed_time": "0:21:47", "remaining_time": "0:33:24"}
{"current_steps": 275, "total_steps": 684, "loss": 0.0604, "lr": 6.817249434930267e-06, "epoch": 1.2065934065934065, "percentage": 40.2, "elapsed_time": "0:22:11", "remaining_time": "0:33:00"}
{"current_steps": 280, "total_steps": 684, "loss": 0.056, "lr": 6.706389611284953e-06, "epoch": 1.2285714285714286, "percentage": 40.94, "elapsed_time": "0:22:35", "remaining_time": "0:32:35"}
{"current_steps": 285, "total_steps": 684, "loss": 0.0765, "lr": 6.594571997017224e-06, "epoch": 1.2505494505494505, "percentage": 41.67, "elapsed_time": "0:22:59", "remaining_time": "0:32:10"}
{"current_steps": 290, "total_steps": 684, "loss": 0.0789, "lr": 6.481859354969549e-06, "epoch": 1.2725274725274724, "percentage": 42.4, "elapsed_time": "0:23:22", "remaining_time": "0:31:45"}
{"current_steps": 295, "total_steps": 684, "loss": 0.0507, "lr": 6.368314950360416e-06, "epoch": 1.2945054945054946, "percentage": 43.13, "elapsed_time": "0:23:46", "remaining_time": "0:31:21"}
{"current_steps": 300, "total_steps": 684, "loss": 0.0532, "lr": 6.254002515273775e-06, "epoch": 1.3164835164835165, "percentage": 43.86, "elapsed_time": "0:24:10", "remaining_time": "0:30:56"}
{"current_steps": 305, "total_steps": 684, "loss": 0.0608, "lr": 6.13898621288645e-06, "epoch": 1.3384615384615386, "percentage": 44.59, "elapsed_time": "0:24:34", "remaining_time": "0:30:32"}
{"current_steps": 310, "total_steps": 684, "loss": 0.0644, "lr": 6.0233306014535505e-06, "epoch": 1.3604395604395605, "percentage": 45.32, "elapsed_time": "0:24:58", "remaining_time": "0:30:07"}
{"current_steps": 315, "total_steps": 684, "loss": 0.0776, "lr": 5.907100598072166e-06, "epoch": 1.3824175824175824, "percentage": 46.05, "elapsed_time": "0:25:21", "remaining_time": "0:29:42"}
{"current_steps": 320, "total_steps": 684, "loss": 0.0787, "lr": 5.790361442243605e-06, "epoch": 1.4043956043956043, "percentage": 46.78, "elapsed_time": "0:25:45", "remaining_time": "0:29:18"}
{"current_steps": 325, "total_steps": 684, "loss": 0.0533, "lr": 5.673178659254698e-06, "epoch": 1.4263736263736264, "percentage": 47.51, "elapsed_time": "0:26:09", "remaining_time": "0:28:53"}
{"current_steps": 330, "total_steps": 684, "loss": 0.0569, "lr": 5.555618023398671e-06, "epoch": 1.4483516483516483, "percentage": 48.25, "elapsed_time": "0:26:33", "remaining_time": "0:28:29"}
{"current_steps": 335, "total_steps": 684, "loss": 0.0627, "lr": 5.437745521056272e-06, "epoch": 1.4703296703296704, "percentage": 48.98, "elapsed_time": "0:26:57", "remaining_time": "0:28:04"}
{"current_steps": 340, "total_steps": 684, "loss": 0.068, "lr": 5.319627313657829e-06, "epoch": 1.4923076923076923, "percentage": 49.71, "elapsed_time": "0:27:21", "remaining_time": "0:27:40"}
{"current_steps": 345, "total_steps": 684, "loss": 0.0483, "lr": 5.201329700547077e-06, "epoch": 1.5142857142857142, "percentage": 50.44, "elapsed_time": "0:27:44", "remaining_time": "0:27:16"}
{"current_steps": 350, "total_steps": 684, "loss": 0.0349, "lr": 5.082919081767558e-06, "epoch": 1.5362637362637361, "percentage": 51.17, "elapsed_time": "0:28:08", "remaining_time": "0:26:51"}
{"current_steps": 355, "total_steps": 684, "loss": 0.0772, "lr": 4.964461920792512e-06, "epoch": 1.5582417582417583, "percentage": 51.9, "elapsed_time": "0:28:33", "remaining_time": "0:26:27"}
{"current_steps": 360, "total_steps": 684, "loss": 0.0681, "lr": 4.846024707219149e-06, "epoch": 1.5802197802197804, "percentage": 52.63, "elapsed_time": "0:28:57", "remaining_time": "0:26:03"}
{"current_steps": 365, "total_steps": 684, "loss": 0.0826, "lr": 4.727673919448271e-06, "epoch": 1.6021978021978023, "percentage": 53.36, "elapsed_time": "0:29:21", "remaining_time": "0:25:39"}
{"current_steps": 370, "total_steps": 684, "loss": 0.0477, "lr": 4.609475987370177e-06, "epoch": 1.6241758241758242, "percentage": 54.09, "elapsed_time": "0:29:44", "remaining_time": "0:25:14"}
{"current_steps": 375, "total_steps": 684, "loss": 0.0826, "lr": 4.49149725507779e-06, "epoch": 1.646153846153846, "percentage": 54.82, "elapsed_time": "0:30:09", "remaining_time": "0:24:50"}
{"current_steps": 380, "total_steps": 684, "loss": 0.0483, "lr": 4.373803943627946e-06, "epoch": 1.668131868131868, "percentage": 55.56, "elapsed_time": "0:30:33", "remaining_time": "0:24:26"}
{"current_steps": 385, "total_steps": 684, "loss": 0.05, "lr": 4.256462113871741e-06, "epoch": 1.69010989010989, "percentage": 56.29, "elapsed_time": "0:30:56", "remaining_time": "0:24:02"}
{"current_steps": 390, "total_steps": 684, "loss": 0.0575, "lr": 4.139537629374814e-06, "epoch": 1.7120879120879122, "percentage": 57.02, "elapsed_time": "0:31:21", "remaining_time": "0:23:38"}
{"current_steps": 395, "total_steps": 684, "loss": 0.0639, "lr": 4.0230961194483325e-06, "epoch": 1.7340659340659341, "percentage": 57.75, "elapsed_time": "0:31:44", "remaining_time": "0:23:13"}
{"current_steps": 400, "total_steps": 684, "loss": 0.059, "lr": 3.907202942311506e-06, "epoch": 1.756043956043956, "percentage": 58.48, "elapsed_time": "0:32:08", "remaining_time": "0:22:49"}
{"current_steps": 405, "total_steps": 684, "loss": 0.0552, "lr": 3.7919231484062334e-06, "epoch": 1.778021978021978, "percentage": 59.21, "elapsed_time": "0:32:32", "remaining_time": "0:22:25"}
{"current_steps": 410, "total_steps": 684, "loss": 0.0477, "lr": 3.677321443884509e-06, "epoch": 1.8, "percentage": 59.94, "elapsed_time": "0:32:56", "remaining_time": "0:22:01"}
{"current_steps": 415, "total_steps": 684, "loss": 0.0432, "lr": 3.563462154289098e-06, "epoch": 1.821978021978022, "percentage": 60.67, "elapsed_time": "0:33:20", "remaining_time": "0:21:36"}
{"current_steps": 420, "total_steps": 684, "loss": 0.0437, "lr": 3.4504091884478076e-06, "epoch": 1.843956043956044, "percentage": 61.4, "elapsed_time": "0:33:44", "remaining_time": "0:21:12"}
{"current_steps": 425, "total_steps": 684, "loss": 0.0364, "lr": 3.3382260026017027e-06, "epoch": 1.865934065934066, "percentage": 62.13, "elapsed_time": "0:34:08", "remaining_time": "0:20:48"}
{"current_steps": 430, "total_steps": 684, "loss": 0.046, "lr": 3.226975564787322e-06, "epoch": 1.8879120879120879, "percentage": 62.87, "elapsed_time": "0:34:32", "remaining_time": "0:20:24"}
{"current_steps": 435, "total_steps": 684, "loss": 0.0478, "lr": 3.1167203194929447e-06, "epoch": 1.9098901098901098, "percentage": 63.6, "elapsed_time": "0:34:56", "remaining_time": "0:19:59"}
{"current_steps": 440, "total_steps": 684, "loss": 0.0547, "lr": 3.0075221526087083e-06, "epoch": 1.9318681318681319, "percentage": 64.33, "elapsed_time": "0:35:20", "remaining_time": "0:19:35"}
{"current_steps": 445, "total_steps": 684, "loss": 0.0527, "lr": 2.899442356690271e-06, "epoch": 1.953846153846154, "percentage": 65.06, "elapsed_time": "0:35:43", "remaining_time": "0:19:11"}
{"current_steps": 450, "total_steps": 684, "loss": 0.0402, "lr": 2.7925415965555126e-06, "epoch": 1.975824175824176, "percentage": 65.79, "elapsed_time": "0:36:07", "remaining_time": "0:18:47"}
{"current_steps": 455, "total_steps": 684, "loss": 0.0469, "lr": 2.6868798752335867e-06, "epoch": 1.9978021978021978, "percentage": 66.52, "elapsed_time": "0:36:31", "remaining_time": "0:18:22"}
{"current_steps": 460, "total_steps": 684, "loss": 0.0219, "lr": 2.5825165002854124e-06, "epoch": 2.0175824175824175, "percentage": 67.25, "elapsed_time": "0:37:10", "remaining_time": "0:18:06"}
{"current_steps": 465, "total_steps": 684, "loss": 0.0232, "lr": 2.479510050514561e-06, "epoch": 2.0395604395604394, "percentage": 67.98, "elapsed_time": "0:37:34", "remaining_time": "0:17:41"}
{"current_steps": 470, "total_steps": 684, "loss": 0.0252, "lr": 2.3779183430871596e-06, "epoch": 2.0615384615384613, "percentage": 68.71, "elapsed_time": "0:37:58", "remaining_time": "0:17:17"}
{"current_steps": 475, "total_steps": 684, "loss": 0.0231, "lr": 2.2777984010793264e-06, "epoch": 2.0835164835164837, "percentage": 69.44, "elapsed_time": "0:38:22", "remaining_time": "0:16:52"}
{"current_steps": 480, "total_steps": 684, "loss": 0.0145, "lr": 2.17920642147031e-06, "epoch": 2.1054945054945056, "percentage": 70.18, "elapsed_time": "0:38:45", "remaining_time": "0:16:28"}
{"current_steps": 485, "total_steps": 684, "loss": 0.021, "lr": 2.082197743599314e-06, "epoch": 2.1274725274725275, "percentage": 70.91, "elapsed_time": "0:39:09", "remaining_time": "0:16:04"}
{"current_steps": 490, "total_steps": 684, "loss": 0.0113, "lr": 1.9868268181037186e-06, "epoch": 2.1494505494505494, "percentage": 71.64, "elapsed_time": "0:39:33", "remaining_time": "0:15:39"}
{"current_steps": 495, "total_steps": 684, "loss": 0.0209, "lr": 1.893147176356131e-06, "epoch": 2.1714285714285713, "percentage": 72.37, "elapsed_time": "0:39:57", "remaining_time": "0:15:15"}
{"current_steps": 500, "total_steps": 684, "loss": 0.0267, "lr": 1.8012114004174048e-06, "epoch": 2.1934065934065936, "percentage": 73.1, "elapsed_time": "0:40:21", "remaining_time": "0:14:50"}
{"current_steps": 505, "total_steps": 684, "loss": 0.0223, "lr": 1.7110710935225055e-06, "epoch": 2.2153846153846155, "percentage": 73.83, "elapsed_time": "0:40:44", "remaining_time": "0:14:26"}
{"current_steps": 510, "total_steps": 684, "loss": 0.0209, "lr": 1.6227768511157976e-06, "epoch": 2.2373626373626374, "percentage": 74.56, "elapsed_time": "0:41:08", "remaining_time": "0:14:02"}
{"current_steps": 515, "total_steps": 684, "loss": 0.0141, "lr": 1.5363782324520033e-06, "epoch": 2.2593406593406593, "percentage": 75.29, "elapsed_time": "0:41:32", "remaining_time": "0:13:37"}
{"current_steps": 520, "total_steps": 684, "loss": 0.0197, "lr": 1.451923732778745e-06, "epoch": 2.281318681318681, "percentage": 76.02, "elapsed_time": "0:41:56", "remaining_time": "0:13:13"}
{"current_steps": 525, "total_steps": 684, "loss": 0.0175, "lr": 1.369460756116342e-06, "epoch": 2.303296703296703, "percentage": 76.75, "elapsed_time": "0:42:20", "remaining_time": "0:12:49"}
{"current_steps": 530, "total_steps": 684, "loss": 0.0198, "lr": 1.2890355886500971e-06, "epoch": 2.3252747252747255, "percentage": 77.49, "elapsed_time": "0:42:44", "remaining_time": "0:12:25"}
{"current_steps": 535, "total_steps": 684, "loss": 0.0141, "lr": 1.210693372750017e-06, "epoch": 2.3472527472527474, "percentage": 78.22, "elapsed_time": "0:43:07", "remaining_time": "0:12:00"}
{"current_steps": 540, "total_steps": 684, "loss": 0.019, "lr": 1.1344780816325512e-06, "epoch": 2.3692307692307693, "percentage": 78.95, "elapsed_time": "0:43:31", "remaining_time": "0:11:36"}
{"current_steps": 545, "total_steps": 684, "loss": 0.0267, "lr": 1.0604324946785826e-06, "epoch": 2.391208791208791, "percentage": 79.68, "elapsed_time": "0:43:55", "remaining_time": "0:11:12"}
{"current_steps": 550, "total_steps": 684, "loss": 0.0139, "lr": 9.885981734215094e-07, "epoch": 2.413186813186813, "percentage": 80.41, "elapsed_time": "0:44:19", "remaining_time": "0:10:47"}
{"current_steps": 555, "total_steps": 684, "loss": 0.0163, "lr": 9.190154382188921e-07, "epoch": 2.4351648351648354, "percentage": 81.14, "elapsed_time": "0:44:43", "remaining_time": "0:10:23"}
{"current_steps": 560, "total_steps": 684, "loss": 0.0138, "lr": 8.517233456207819e-07, "epoch": 2.4571428571428573, "percentage": 81.87, "elapsed_time": "0:45:06", "remaining_time": "0:09:59"}
{"current_steps": 565, "total_steps": 684, "loss": 0.0134, "lr": 7.86759666447412e-07, "epoch": 2.479120879120879, "percentage": 82.6, "elapsed_time": "0:45:30", "remaining_time": "0:09:35"}
{"current_steps": 570, "total_steps": 684, "loss": 0.0259, "lr": 7.241608645885629e-07, "epoch": 2.501098901098901, "percentage": 83.33, "elapsed_time": "0:45:54", "remaining_time": "0:09:10"}
{"current_steps": 575, "total_steps": 684, "loss": 0.0133, "lr": 6.639620765365074e-07, "epoch": 2.523076923076923, "percentage": 84.06, "elapsed_time": "0:46:18", "remaining_time": "0:08:46"}
{"current_steps": 580, "total_steps": 684, "loss": 0.0134, "lr": 6.061970916640236e-07, "epoch": 2.545054945054945, "percentage": 84.8, "elapsed_time": "0:46:42", "remaining_time": "0:08:22"}
{"current_steps": 585, "total_steps": 684, "loss": 0.0088, "lr": 5.508983332585316e-07, "epoch": 2.567032967032967, "percentage": 85.53, "elapsed_time": "0:47:06", "remaining_time": "0:07:58"}
{"current_steps": 590, "total_steps": 684, "loss": 0.0104, "lr": 4.980968403230097e-07, "epoch": 2.589010989010989, "percentage": 86.26, "elapsed_time": "0:47:30", "remaining_time": "0:07:34"}
{"current_steps": 595, "total_steps": 684, "loss": 0.0227, "lr": 4.4782225015391754e-07, "epoch": 2.610989010989011, "percentage": 86.99, "elapsed_time": "0:47:53", "remaining_time": "0:07:09"}
{"current_steps": 600, "total_steps": 684, "loss": 0.0227, "lr": 4.001027817058789e-07, "epoch": 2.632967032967033, "percentage": 87.72, "elapsed_time": "0:48:17", "remaining_time": "0:06:45"}
{"current_steps": 605, "total_steps": 684, "loss": 0.0148, "lr": 3.549652197524783e-07, "epoch": 2.654945054945055, "percentage": 88.45, "elapsed_time": "0:48:41", "remaining_time": "0:06:21"}
{"current_steps": 610, "total_steps": 684, "loss": 0.0126, "lr": 3.1243489985206097e-07, "epoch": 2.676923076923077, "percentage": 89.18, "elapsed_time": "0:49:05", "remaining_time": "0:05:57"}
{"current_steps": 615, "total_steps": 684, "loss": 0.0148, "lr": 2.7253569412697244e-07, "epoch": 2.698901098901099, "percentage": 89.91, "elapsed_time": "0:49:29", "remaining_time": "0:05:33"}
{"current_steps": 620, "total_steps": 684, "loss": 0.0193, "lr": 2.3528999786421758e-07, "epoch": 2.720879120879121, "percentage": 90.64, "elapsed_time": "0:49:52", "remaining_time": "0:05:08"}
{"current_steps": 625, "total_steps": 684, "loss": 0.016, "lr": 2.007187169450603e-07, "epoch": 2.742857142857143, "percentage": 91.37, "elapsed_time": "0:50:16", "remaining_time": "0:04:44"}
{"current_steps": 630, "total_steps": 684, "loss": 0.019, "lr": 1.688412561106284e-07, "epoch": 2.764835164835165, "percentage": 92.11, "elapsed_time": "0:50:40", "remaining_time": "0:04:20"}
{"current_steps": 635, "total_steps": 684, "loss": 0.0092, "lr": 1.3967550807009677e-07, "epoch": 2.7868131868131867, "percentage": 92.84, "elapsed_time": "0:51:04", "remaining_time": "0:03:56"}
{"current_steps": 640, "total_steps": 684, "loss": 0.0183, "lr": 1.1323784345757205e-07, "epoch": 2.8087912087912086, "percentage": 93.57, "elapsed_time": "0:51:28", "remaining_time": "0:03:32"}
{"current_steps": 645, "total_steps": 684, "loss": 0.0068, "lr": 8.954310164331015e-08, "epoch": 2.830769230769231, "percentage": 94.3, "elapsed_time": "0:51:51", "remaining_time": "0:03:08"}
{"current_steps": 650, "total_steps": 684, "loss": 0.0228, "lr": 6.860458240443179e-08, "epoch": 2.852747252747253, "percentage": 95.03, "elapsed_time": "0:52:15", "remaining_time": "0:02:44"}
{"current_steps": 655, "total_steps": 684, "loss": 0.011, "lr": 5.0434038459801213e-08, "epoch": 2.8747252747252747, "percentage": 95.76, "elapsed_time": "0:52:39", "remaining_time": "0:02:19"}
{"current_steps": 660, "total_steps": 684, "loss": 0.0214, "lr": 3.504166887326688e-08, "epoch": 2.8967032967032966, "percentage": 96.49, "elapsed_time": "0:53:03", "remaining_time": "0:01:55"}
{"current_steps": 665, "total_steps": 684, "loss": 0.0122, "lr": 2.2436113328958565e-08, "epoch": 2.9186813186813185, "percentage": 97.22, "elapsed_time": "0:53:27", "remaining_time": "0:01:31"}
{"current_steps": 670, "total_steps": 684, "loss": 0.0083, "lr": 1.2624447281867625e-08, "epoch": 2.940659340659341, "percentage": 97.95, "elapsed_time": "0:53:50", "remaining_time": "0:01:07"}
{"current_steps": 675, "total_steps": 684, "loss": 0.0075, "lr": 5.612177986414891e-09, "epoch": 2.9626373626373628, "percentage": 98.68, "elapsed_time": "0:54:14", "remaining_time": "0:00:43"}
{"current_steps": 680, "total_steps": 684, "loss": 0.0122, "lr": 1.4032414052478348e-09, "epoch": 2.9846153846153847, "percentage": 99.42, "elapsed_time": "0:54:38", "remaining_time": "0:00:19"}
{"current_steps": 684, "total_steps": 684, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:55:11", "remaining_time": "0:00:00"}