Files
sft__Kimi-2-5-swesmith-orac…/trainer_log.jsonl

139 lines
26 KiB
Plaintext
Raw Permalink Normal View History

{"current_steps": 5, "total_steps": 686, "loss": 0.8837, "lr": 2.3188405797101453e-06, "epoch": 0.051194539249146756, "percentage": 0.73, "elapsed_time": "0:02:13", "remaining_time": "5:03:44"}
{"current_steps": 10, "total_steps": 686, "loss": 0.7924, "lr": 5.2173913043478265e-06, "epoch": 0.10238907849829351, "percentage": 1.46, "elapsed_time": "0:04:14", "remaining_time": "4:46:51"}
{"current_steps": 15, "total_steps": 686, "loss": 0.629, "lr": 8.115942028985508e-06, "epoch": 0.15358361774744028, "percentage": 2.19, "elapsed_time": "0:06:11", "remaining_time": "4:37:00"}
{"current_steps": 20, "total_steps": 686, "loss": 0.5623, "lr": 1.101449275362319e-05, "epoch": 0.20477815699658702, "percentage": 2.92, "elapsed_time": "0:08:10", "remaining_time": "4:32:23"}
{"current_steps": 25, "total_steps": 686, "loss": 0.5276, "lr": 1.391304347826087e-05, "epoch": 0.25597269624573377, "percentage": 3.64, "elapsed_time": "0:10:09", "remaining_time": "4:28:38"}
{"current_steps": 30, "total_steps": 686, "loss": 0.4868, "lr": 1.681159420289855e-05, "epoch": 0.30716723549488056, "percentage": 4.37, "elapsed_time": "0:12:04", "remaining_time": "4:24:09"}
{"current_steps": 35, "total_steps": 686, "loss": 0.4641, "lr": 1.9710144927536236e-05, "epoch": 0.3583617747440273, "percentage": 5.1, "elapsed_time": "0:14:00", "remaining_time": "4:20:32"}
{"current_steps": 40, "total_steps": 686, "loss": 0.4417, "lr": 2.2608695652173914e-05, "epoch": 0.40955631399317405, "percentage": 5.83, "elapsed_time": "0:16:02", "remaining_time": "4:19:06"}
{"current_steps": 45, "total_steps": 686, "loss": 0.4245, "lr": 2.5507246376811593e-05, "epoch": 0.46075085324232085, "percentage": 6.56, "elapsed_time": "0:18:06", "remaining_time": "4:17:53"}
{"current_steps": 50, "total_steps": 686, "loss": 0.4008, "lr": 2.840579710144928e-05, "epoch": 0.5119453924914675, "percentage": 7.29, "elapsed_time": "0:20:00", "remaining_time": "4:14:29"}
{"current_steps": 55, "total_steps": 686, "loss": 0.3861, "lr": 3.130434782608696e-05, "epoch": 0.5631399317406144, "percentage": 8.02, "elapsed_time": "0:22:01", "remaining_time": "4:12:37"}
{"current_steps": 60, "total_steps": 686, "loss": 0.3798, "lr": 3.420289855072464e-05, "epoch": 0.6143344709897611, "percentage": 8.75, "elapsed_time": "0:24:08", "remaining_time": "4:11:51"}
{"current_steps": 65, "total_steps": 686, "loss": 0.3636, "lr": 3.7101449275362325e-05, "epoch": 0.6655290102389079, "percentage": 9.48, "elapsed_time": "0:26:08", "remaining_time": "4:09:48"}
{"current_steps": 70, "total_steps": 686, "loss": 0.3524, "lr": 4e-05, "epoch": 0.7167235494880546, "percentage": 10.2, "elapsed_time": "0:28:07", "remaining_time": "4:07:27"}
{"current_steps": 75, "total_steps": 686, "loss": 0.3337, "lr": 3.999351894109228e-05, "epoch": 0.7679180887372014, "percentage": 10.93, "elapsed_time": "0:30:05", "remaining_time": "4:05:09"}
{"current_steps": 80, "total_steps": 686, "loss": 0.3345, "lr": 3.997407996478158e-05, "epoch": 0.8191126279863481, "percentage": 11.66, "elapsed_time": "0:32:06", "remaining_time": "4:03:13"}
{"current_steps": 85, "total_steps": 686, "loss": 0.3304, "lr": 3.9941695669582944e-05, "epoch": 0.8703071672354948, "percentage": 12.39, "elapsed_time": "0:34:07", "remaining_time": "4:01:18"}
{"current_steps": 90, "total_steps": 686, "loss": 0.3168, "lr": 3.989638704394887e-05, "epoch": 0.9215017064846417, "percentage": 13.12, "elapsed_time": "0:36:00", "remaining_time": "3:58:28"}
{"current_steps": 95, "total_steps": 686, "loss": 0.3149, "lr": 3.983818345266653e-05, "epoch": 0.9726962457337884, "percentage": 13.85, "elapsed_time": "0:37:53", "remaining_time": "3:55:41"}
{"current_steps": 100, "total_steps": 686, "loss": 0.3204, "lr": 3.976712261782631e-05, "epoch": 1.0204778156996588, "percentage": 14.58, "elapsed_time": "0:39:41", "remaining_time": "3:52:38"}
{"current_steps": 105, "total_steps": 686, "loss": 0.3154, "lr": 3.968325059437385e-05, "epoch": 1.0716723549488054, "percentage": 15.31, "elapsed_time": "0:41:42", "remaining_time": "3:50:48"}
{"current_steps": 110, "total_steps": 686, "loss": 0.3121, "lr": 3.958662174026164e-05, "epoch": 1.1228668941979523, "percentage": 16.03, "elapsed_time": "0:43:42", "remaining_time": "3:48:50"}
{"current_steps": 115, "total_steps": 686, "loss": 0.3053, "lr": 3.947729868121924e-05, "epoch": 1.174061433447099, "percentage": 16.76, "elapsed_time": "0:45:39", "remaining_time": "3:46:43"}
{"current_steps": 120, "total_steps": 686, "loss": 0.3076, "lr": 3.935535227016521e-05, "epoch": 1.2252559726962458, "percentage": 17.49, "elapsed_time": "0:47:33", "remaining_time": "3:44:20"}
{"current_steps": 125, "total_steps": 686, "loss": 0.2968, "lr": 3.922086154128693e-05, "epoch": 1.2764505119453924, "percentage": 18.22, "elapsed_time": "0:49:29", "remaining_time": "3:42:09"}
{"current_steps": 130, "total_steps": 686, "loss": 0.3075, "lr": 3.907391365881802e-05, "epoch": 1.3276450511945392, "percentage": 18.95, "elapsed_time": "0:51:32", "remaining_time": "3:40:27"}
{"current_steps": 135, "total_steps": 686, "loss": 0.299, "lr": 3.891460386054675e-05, "epoch": 1.378839590443686, "percentage": 19.68, "elapsed_time": "0:53:27", "remaining_time": "3:38:12"}
{"current_steps": 140, "total_steps": 686, "loss": 0.2998, "lr": 3.8743035396091845e-05, "epoch": 1.4300341296928327, "percentage": 20.41, "elapsed_time": "0:55:19", "remaining_time": "3:35:46"}
{"current_steps": 145, "total_steps": 686, "loss": 0.2969, "lr": 3.8559319459985776e-05, "epoch": 1.4812286689419796, "percentage": 21.14, "elapsed_time": "0:57:13", "remaining_time": "3:33:31"}
{"current_steps": 150, "total_steps": 686, "loss": 0.2946, "lr": 3.836357511960898e-05, "epoch": 1.5324232081911262, "percentage": 21.87, "elapsed_time": "0:59:10", "remaining_time": "3:31:28"}
{"current_steps": 155, "total_steps": 686, "loss": 0.2922, "lr": 3.815592923802152e-05, "epoch": 1.583617747440273, "percentage": 22.59, "elapsed_time": "1:01:09", "remaining_time": "3:29:31"}
{"current_steps": 160, "total_steps": 686, "loss": 0.2881, "lr": 3.793651639174246e-05, "epoch": 1.63481228668942, "percentage": 23.32, "elapsed_time": "1:03:06", "remaining_time": "3:27:29"}
{"current_steps": 165, "total_steps": 686, "loss": 0.2971, "lr": 3.7705478783529986e-05, "epoch": 1.6860068259385665, "percentage": 24.05, "elapsed_time": "1:05:04", "remaining_time": "3:25:29"}
{"current_steps": 170, "total_steps": 686, "loss": 0.296, "lr": 3.746296615021896e-05, "epoch": 1.7372013651877132, "percentage": 24.78, "elapsed_time": "1:07:03", "remaining_time": "3:23:32"}
{"current_steps": 175, "total_steps": 686, "loss": 0.2894, "lr": 3.720913566567562e-05, "epoch": 1.78839590443686, "percentage": 25.51, "elapsed_time": "1:09:01", "remaining_time": "3:21:33"}
{"current_steps": 180, "total_steps": 686, "loss": 0.2935, "lr": 3.6944151838932274e-05, "epoch": 1.8395904436860069, "percentage": 26.24, "elapsed_time": "1:10:55", "remaining_time": "3:19:22"}
{"current_steps": 185, "total_steps": 686, "loss": 0.2902, "lr": 3.666818640756797e-05, "epoch": 1.8907849829351537, "percentage": 26.97, "elapsed_time": "1:12:49", "remaining_time": "3:17:13"}
{"current_steps": 190, "total_steps": 686, "loss": 0.2908, "lr": 3.638141822640444e-05, "epoch": 1.9419795221843004, "percentage": 27.7, "elapsed_time": "1:14:46", "remaining_time": "3:15:13"}
{"current_steps": 195, "total_steps": 686, "loss": 0.2915, "lr": 3.608403315158917e-05, "epoch": 1.993174061433447, "percentage": 28.43, "elapsed_time": "1:16:48", "remaining_time": "3:13:24"}
{"current_steps": 200, "total_steps": 686, "loss": 0.2833, "lr": 3.5776223920140985e-05, "epoch": 2.0409556313993176, "percentage": 29.15, "elapsed_time": "1:18:36", "remaining_time": "3:11:01"}
{"current_steps": 205, "total_steps": 686, "loss": 0.284, "lr": 3.545819002503602e-05, "epoch": 2.092150170648464, "percentage": 29.88, "elapsed_time": "1:20:36", "remaining_time": "3:09:07"}
{"current_steps": 210, "total_steps": 686, "loss": 0.2815, "lr": 3.513013758591515e-05, "epoch": 2.143344709897611, "percentage": 30.61, "elapsed_time": "1:22:33", "remaining_time": "3:07:07"}
{"current_steps": 215, "total_steps": 686, "loss": 0.281, "lr": 3.479227921549666e-05, "epoch": 2.1945392491467577, "percentage": 31.34, "elapsed_time": "1:24:34", "remaining_time": "3:05:16"}
{"current_steps": 220, "total_steps": 686, "loss": 0.27, "lr": 3.444483388178066e-05, "epoch": 2.2457337883959045, "percentage": 32.07, "elapsed_time": "1:26:28", "remaining_time": "3:03:09"}
{"current_steps": 225, "total_steps": 686, "loss": 0.2782, "lr": 3.4088026766134654e-05, "epoch": 2.296928327645051, "percentage": 32.8, "elapsed_time": "1:28:28", "remaining_time": "3:01:16"}
{"current_steps": 230, "total_steps": 686, "loss": 0.2856, "lr": 3.372208911735216e-05, "epoch": 2.348122866894198, "percentage": 33.53, "elapsed_time": "1:31:02", "remaining_time": "3:00:30"}
{"current_steps": 235, "total_steps": 686, "loss": 0.282, "lr": 3.3347258101779015e-05, "epoch": 2.3993174061433447, "percentage": 34.26, "elapsed_time": "1:32:59", "remaining_time": "2:58:28"}
{"current_steps": 240, "total_steps": 686, "loss": 0.2708, "lr": 3.296377664960445e-05, "epoch": 2.4505119453924915, "percentage": 34.99, "elapsed_time": "1:34:55", "remaining_time": "2:56:24"}
{"current_steps": 245, "total_steps": 686, "loss": 0.2723, "lr": 3.257189329741662e-05, "epoch": 2.5017064846416384, "percentage": 35.71, "elapsed_time": "1:36:52", "remaining_time": "2:54:23"}
{"current_steps": 250, "total_steps": 686, "loss": 0.274, "lr": 3.217186202712458e-05, "epoch": 2.5529010238907848, "percentage": 36.44, "elapsed_time": "1:38:51", "remaining_time": "2:52:24"}
{"current_steps": 255, "total_steps": 686, "loss": 0.2773, "lr": 3.1763942101351095e-05, "epoch": 2.6040955631399316, "percentage": 37.17, "elapsed_time": "1:40:47", "remaining_time": "2:50:20"}
{"current_steps": 260, "total_steps": 686, "loss": 0.2752, "lr": 3.134839789540302e-05, "epoch": 2.6552901023890785, "percentage": 37.9, "elapsed_time": "1:42:42", "remaining_time": "2:48:16"}
{"current_steps": 265, "total_steps": 686, "loss": 0.2702, "lr": 3.0925498725928115e-05, "epoch": 2.7064846416382253, "percentage": 38.63, "elapsed_time": "1:44:36", "remaining_time": "2:46:11"}
{"current_steps": 270, "total_steps": 686, "loss": 0.2767, "lr": 3.0495518676369306e-05, "epoch": 2.757679180887372, "percentage": 39.36, "elapsed_time": "1:46:34", "remaining_time": "2:44:12"}
{"current_steps": 275, "total_steps": 686, "loss": 0.2693, "lr": 3.0058736419329643e-05, "epoch": 2.8088737201365186, "percentage": 40.09, "elapsed_time": "1:48:27", "remaining_time": "2:42:05"}
{"current_steps": 280, "total_steps": 686, "loss": 0.2774, "lr": 2.9615435035962878e-05, "epoch": 2.8600682593856654, "percentage": 40.82, "elapsed_time": "1:50:24", "remaining_time": "2:40:06"}
{"current_steps": 285, "total_steps": 686, "loss": 0.2714, "lr": 2.9165901832506977e-05, "epoch": 2.9112627986348123, "percentage": 41.55, "elapsed_time": "1:52:20", "remaining_time": "2:38:03"}
{"current_steps": 290, "total_steps": 686, "loss": 0.2684, "lr": 2.8710428154079185e-05, "epoch": 2.962457337883959, "percentage": 42.27, "elapsed_time": "1:54:15", "remaining_time": "2:36:00"}
{"current_steps": 295, "total_steps": 686, "loss": 0.2695, "lr": 2.824930919585359e-05, "epoch": 3.0102389078498293, "percentage": 43.0, "elapsed_time": "1:56:09", "remaining_time": "2:33:57"}
{"current_steps": 300, "total_steps": 686, "loss": 0.2619, "lr": 2.778284381174336e-05, "epoch": 3.061433447098976, "percentage": 43.73, "elapsed_time": "1:58:04", "remaining_time": "2:31:54"}
{"current_steps": 305, "total_steps": 686, "loss": 0.2627, "lr": 2.7311334320711784e-05, "epoch": 3.112627986348123, "percentage": 44.46, "elapsed_time": "2:00:02", "remaining_time": "2:29:57"}
{"current_steps": 310, "total_steps": 686, "loss": 0.2664, "lr": 2.683508631083755e-05, "epoch": 3.1638225255972694, "percentage": 45.19, "elapsed_time": "2:02:00", "remaining_time": "2:27:59"}
{"current_steps": 315, "total_steps": 686, "loss": 0.2679, "lr": 2.6354408441261324e-05, "epoch": 3.2150170648464163, "percentage": 45.92, "elapsed_time": "2:03:57", "remaining_time": "2:25:59"}
{"current_steps": 320, "total_steps": 686, "loss": 0.2664, "lr": 2.5869612242141946e-05, "epoch": 3.266211604095563, "percentage": 46.65, "elapsed_time": "2:05:51", "remaining_time": "2:23:57"}
{"current_steps": 325, "total_steps": 686, "loss": 0.2647, "lr": 2.538101191275189e-05, "epoch": 3.31740614334471, "percentage": 47.38, "elapsed_time": "2:07:46", "remaining_time": "2:21:55"}
{"current_steps": 330, "total_steps": 686, "loss": 0.2601, "lr": 2.488892411784286e-05, "epoch": 3.368600682593857, "percentage": 48.1, "elapsed_time": "2:09:37", "remaining_time": "2:19:49"}
{"current_steps": 335, "total_steps": 686, "loss": 0.2706, "lr": 2.439366778241352e-05, "epoch": 3.419795221843003, "percentage": 48.83, "elapsed_time": "2:11:34", "remaining_time": "2:17:51"}
{"current_steps": 340, "total_steps": 686, "loss": 0.2604, "lr": 2.3895563885012303e-05, "epoch": 3.47098976109215, "percentage": 49.56, "elapsed_time": "2:13:30", "remaining_time": "2:15:51"}
{"current_steps": 345, "total_steps": 686, "loss": 0.2641, "lr": 2.3394935249709332e-05, "epoch": 3.522184300341297, "percentage": 50.29, "elapsed_time": "2:15:24", "remaining_time": "2:13:50"}
{"current_steps": 350, "total_steps": 686, "loss": 0.2659, "lr": 2.2892106336872234e-05, "epoch": 3.573378839590444, "percentage": 51.02, "elapsed_time": "2:17:21", "remaining_time": "2:11:52"}
{"current_steps": 355, "total_steps": 686, "loss": 0.2622, "lr": 2.2387403032881467e-05, "epoch": 3.6245733788395906, "percentage": 51.75, "elapsed_time": "2:19:16", "remaining_time": "2:09:51"}
{"current_steps": 360, "total_steps": 686, "loss": 0.2624, "lr": 2.1881152438921447e-05, "epoch": 3.675767918088737, "percentage": 52.48, "elapsed_time": "2:21:15", "remaining_time": "2:07:55"}
{"current_steps": 365, "total_steps": 686, "loss": 0.2639, "lr": 2.1373682658984317e-05, "epoch": 3.726962457337884, "percentage": 53.21, "elapsed_time": "2:23:06", "remaining_time": "2:05:51"}
{"current_steps": 370, "total_steps": 686, "loss": 0.2585, "lr": 2.0865322587223855e-05, "epoch": 3.7781569965870307, "percentage": 53.94, "elapsed_time": "2:25:02", "remaining_time": "2:03:52"}
{"current_steps": 375, "total_steps": 686, "loss": 0.2617, "lr": 2.035640169479719e-05, "epoch": 3.8293515358361776, "percentage": 54.66, "elapsed_time": "2:26:58", "remaining_time": "2:01:53"}
{"current_steps": 380, "total_steps": 686, "loss": 0.2679, "lr": 1.9847249816332644e-05, "epoch": 3.8805460750853245, "percentage": 55.39, "elapsed_time": "2:28:56", "remaining_time": "1:59:56"}
{"current_steps": 385, "total_steps": 686, "loss": 0.2529, "lr": 1.933819693616195e-05, "epoch": 3.931740614334471, "percentage": 56.12, "elapsed_time": "2:30:46", "remaining_time": "1:57:52"}
{"current_steps": 390, "total_steps": 686, "loss": 0.2689, "lr": 1.8829572974455465e-05, "epoch": 3.9829351535836177, "percentage": 56.85, "elapsed_time": "2:32:45", "remaining_time": "1:55:56"}
{"current_steps": 395, "total_steps": 686, "loss": 0.2607, "lr": 1.832170757339895e-05, "epoch": 4.030716723549488, "percentage": 57.58, "elapsed_time": "2:34:38", "remaining_time": "1:53:55"}
{"current_steps": 400, "total_steps": 686, "loss": 0.2591, "lr": 1.781492988355056e-05, "epoch": 4.081911262798635, "percentage": 58.31, "elapsed_time": "2:36:35", "remaining_time": "1:51:57"}
{"current_steps": 405, "total_steps": 686, "loss": 0.254, "lr": 1.7309568350516376e-05, "epoch": 4.1331058020477816, "percentage": 59.04, "elapsed_time": "2:38:28", "remaining_time": "1:49:57"}
{"current_steps": 410, "total_steps": 686, "loss": 0.2549, "lr": 1.680595050208296e-05, "epoch": 4.184300341296928, "percentage": 59.77, "elapsed_time": "2:40:19", "remaining_time": "1:47:55"}
{"current_steps": 415, "total_steps": 686, "loss": 0.2647, "lr": 1.630440273594455e-05, "epoch": 4.235494880546075, "percentage": 60.5, "elapsed_time": "2:42:23", "remaining_time": "1:46:02"}
{"current_steps": 420, "total_steps": 686, "loss": 0.2493, "lr": 1.5805250108162898e-05, "epoch": 4.286689419795222, "percentage": 61.22, "elapsed_time": "2:44:15", "remaining_time": "1:44:01"}
{"current_steps": 425, "total_steps": 686, "loss": 0.2581, "lr": 1.530881612249646e-05, "epoch": 4.337883959044369, "percentage": 61.95, "elapsed_time": "2:46:11", "remaining_time": "1:42:03"}
{"current_steps": 430, "total_steps": 686, "loss": 0.2536, "lr": 1.4815422520735735e-05, "epoch": 4.389078498293515, "percentage": 62.68, "elapsed_time": "2:48:03", "remaining_time": "1:40:03"}
{"current_steps": 435, "total_steps": 686, "loss": 0.2548, "lr": 1.432538907418047e-05, "epoch": 4.440273037542662, "percentage": 63.41, "elapsed_time": "2:49:58", "remaining_time": "1:38:04"}
{"current_steps": 440, "total_steps": 686, "loss": 0.257, "lr": 1.3839033376394082e-05, "epoch": 4.491467576791809, "percentage": 64.14, "elapsed_time": "2:51:51", "remaining_time": "1:36:05"}
{"current_steps": 445, "total_steps": 686, "loss": 0.2599, "lr": 1.33566706373693e-05, "epoch": 4.5426621160409555, "percentage": 64.87, "elapsed_time": "2:53:50", "remaining_time": "1:34:08"}
{"current_steps": 450, "total_steps": 686, "loss": 0.2541, "lr": 1.2878613479238774e-05, "epoch": 4.593856655290102, "percentage": 65.6, "elapsed_time": "2:55:40", "remaining_time": "1:32:07"}
{"current_steps": 455, "total_steps": 686, "loss": 0.2519, "lr": 1.2405171733662822e-05, "epoch": 4.645051194539249, "percentage": 66.33, "elapsed_time": "2:57:32", "remaining_time": "1:30:08"}
{"current_steps": 460, "total_steps": 686, "loss": 0.2499, "lr": 1.1936652241025679e-05, "epoch": 4.696245733788396, "percentage": 67.06, "elapsed_time": "2:59:24", "remaining_time": "1:28:08"}
{"current_steps": 465, "total_steps": 686, "loss": 0.2589, "lr": 1.1473358651570479e-05, "epoch": 4.747440273037543, "percentage": 67.78, "elapsed_time": "3:01:18", "remaining_time": "1:26:10"}
{"current_steps": 470, "total_steps": 686, "loss": 0.2523, "lr": 1.1015591228601692e-05, "epoch": 4.798634812286689, "percentage": 68.51, "elapsed_time": "3:03:15", "remaining_time": "1:24:13"}
{"current_steps": 475, "total_steps": 686, "loss": 0.2543, "lr": 1.0563646653882755e-05, "epoch": 4.849829351535837, "percentage": 69.24, "elapsed_time": "3:05:05", "remaining_time": "1:22:13"}
{"current_steps": 480, "total_steps": 686, "loss": 0.2545, "lr": 1.0117817835354851e-05, "epoch": 4.901023890784983, "percentage": 69.97, "elapsed_time": "3:07:02", "remaining_time": "1:20:16"}
{"current_steps": 485, "total_steps": 686, "loss": 0.2609, "lr": 9.678393717301526e-06, "epoch": 4.952218430034129, "percentage": 70.7, "elapsed_time": "3:08:58", "remaining_time": "1:18:18"}
{"current_steps": 490, "total_steps": 686, "loss": 0.2541, "lr": 9.245659093082243e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "3:10:47", "remaining_time": "1:16:18"}
{"current_steps": 495, "total_steps": 686, "loss": 0.246, "lr": 8.819894420556112e-06, "epoch": 5.051194539249146, "percentage": 72.16, "elapsed_time": "3:12:42", "remaining_time": "1:14:21"}
{"current_steps": 500, "total_steps": 686, "loss": 0.2511, "lr": 8.40137564031547e-06, "epoch": 5.102389078498294, "percentage": 72.89, "elapsed_time": "3:14:39", "remaining_time": "1:12:24"}
{"current_steps": 505, "total_steps": 686, "loss": 0.2511, "lr": 7.990373996847194e-06, "epoch": 5.15358361774744, "percentage": 73.62, "elapsed_time": "3:16:30", "remaining_time": "1:10:25"}
{"current_steps": 510, "total_steps": 686, "loss": 0.2481, "lr": 7.5871558627375295e-06, "epoch": 5.204778156996587, "percentage": 74.34, "elapsed_time": "3:18:20", "remaining_time": "1:08:26"}
{"current_steps": 515, "total_steps": 686, "loss": 0.255, "lr": 7.1919825660344696e-06, "epoch": 5.255972696245734, "percentage": 75.07, "elapsed_time": "3:20:19", "remaining_time": "1:06:30"}
{"current_steps": 520, "total_steps": 686, "loss": 0.2543, "lr": 6.805110220879459e-06, "epoch": 5.30716723549488, "percentage": 75.8, "elapsed_time": "3:22:10", "remaining_time": "1:04:32"}
{"current_steps": 525, "total_steps": 686, "loss": 0.2547, "lr": 6.4267895615183915e-06, "epoch": 5.3583617747440275, "percentage": 76.53, "elapsed_time": "3:24:07", "remaining_time": "1:02:35"}
{"current_steps": 530, "total_steps": 686, "loss": 0.2553, "lr": 6.057265779799193e-06, "epoch": 5.409556313993174, "percentage": 77.26, "elapsed_time": "3:26:02", "remaining_time": "1:00:38"}
{"current_steps": 535, "total_steps": 686, "loss": 0.2459, "lr": 5.696778366261575e-06, "epoch": 5.460750853242321, "percentage": 77.99, "elapsed_time": "3:27:52", "remaining_time": "0:58:40"}
{"current_steps": 540, "total_steps": 686, "loss": 0.2492, "lr": 5.345560954921802e-06, "epoch": 5.511945392491468, "percentage": 78.72, "elapsed_time": "3:29:48", "remaining_time": "0:56:43"}
{"current_steps": 545, "total_steps": 686, "loss": 0.2506, "lr": 5.00384117185311e-06, "epoch": 5.563139931740614, "percentage": 79.45, "elapsed_time": "3:31:45", "remaining_time": "0:54:47"}
{"current_steps": 550, "total_steps": 686, "loss": 0.2509, "lr": 4.671840487659882e-06, "epoch": 5.614334470989761, "percentage": 80.17, "elapsed_time": "3:33:43", "remaining_time": "0:52:50"}
{"current_steps": 555, "total_steps": 686, "loss": 0.2492, "lr": 4.3497740739413015e-06, "epoch": 5.665529010238908, "percentage": 80.9, "elapsed_time": "3:35:35", "remaining_time": "0:50:53"}
{"current_steps": 560, "total_steps": 686, "loss": 0.2534, "lr": 4.037850663837315e-06, "epoch": 5.716723549488055, "percentage": 81.63, "elapsed_time": "3:37:32", "remaining_time": "0:48:56"}
{"current_steps": 565, "total_steps": 686, "loss": 0.2558, "lr": 3.7362724167474774e-06, "epoch": 5.7679180887372015, "percentage": 82.36, "elapsed_time": "3:39:33", "remaining_time": "0:47:01"}
{"current_steps": 570, "total_steps": 686, "loss": 0.2451, "lr": 3.4452347873102565e-06, "epoch": 5.819112627986348, "percentage": 83.09, "elapsed_time": "3:41:26", "remaining_time": "0:45:03"}
{"current_steps": 575, "total_steps": 686, "loss": 0.247, "lr": 3.1649263987277303e-06, "epoch": 5.870307167235495, "percentage": 83.82, "elapsed_time": "3:43:23", "remaining_time": "0:43:07"}
{"current_steps": 580, "total_steps": 686, "loss": 0.2462, "lr": 2.8955289205177696e-06, "epoch": 5.921501706484642, "percentage": 84.55, "elapsed_time": "3:45:16", "remaining_time": "0:41:10"}
{"current_steps": 585, "total_steps": 686, "loss": 0.2588, "lr": 2.6372169507729627e-06, "epoch": 5.972696245733788, "percentage": 85.28, "elapsed_time": "3:47:15", "remaining_time": "0:39:14"}
{"current_steps": 590, "total_steps": 686, "loss": 0.2553, "lr": 2.3901579030025566e-06, "epoch": 6.020477815699659, "percentage": 86.01, "elapsed_time": "3:48:59", "remaining_time": "0:37:15"}
{"current_steps": 595, "total_steps": 686, "loss": 0.2474, "lr": 2.15451189763078e-06, "epoch": 6.071672354948806, "percentage": 86.73, "elapsed_time": "3:50:53", "remaining_time": "0:35:18"}
{"current_steps": 600, "total_steps": 686, "loss": 0.2486, "lr": 1.930431658221854e-06, "epoch": 6.122866894197952, "percentage": 87.46, "elapsed_time": "3:52:48", "remaining_time": "0:33:22"}
{"current_steps": 605, "total_steps": 686, "loss": 0.2543, "lr": 1.7180624124989398e-06, "epoch": 6.174061433447099, "percentage": 88.19, "elapsed_time": "3:54:54", "remaining_time": "0:31:26"}
{"current_steps": 610, "total_steps": 686, "loss": 0.2475, "lr": 1.5175417982212138e-06, "epoch": 6.225255972696246, "percentage": 88.92, "elapsed_time": "3:56:44", "remaining_time": "0:29:29"}
{"current_steps": 615, "total_steps": 686, "loss": 0.2481, "lr": 1.3289997739800108e-06, "epoch": 6.276450511945392, "percentage": 89.65, "elapsed_time": "3:58:39", "remaining_time": "0:27:33"}
{"current_steps": 620, "total_steps": 686, "loss": 0.2465, "lr": 1.1525585349718948e-06, "epoch": 6.327645051194539, "percentage": 90.38, "elapsed_time": "4:00:31", "remaining_time": "0:25:36"}
{"current_steps": 625, "total_steps": 686, "loss": 0.2525, "lr": 9.883324338032474e-07, "epoch": 6.378839590443686, "percentage": 91.11, "elapsed_time": "4:02:30", "remaining_time": "0:23:40"}
{"current_steps": 630, "total_steps": 686, "loss": 0.2458, "lr": 8.364279063776526e-07, "epoch": 6.4300341296928325, "percentage": 91.84, "elapsed_time": "4:04:24", "remaining_time": "0:21:43"}
{"current_steps": 635, "total_steps": 686, "loss": 0.2456, "lr": 6.969434029141676e-07, "epoch": 6.48122866894198, "percentage": 92.57, "elapsed_time": "4:06:17", "remaining_time": "0:19:46"}
{"current_steps": 640, "total_steps": 686, "loss": 0.248, "lr": 5.699693241411619e-07, "epoch": 6.532423208191126, "percentage": 93.29, "elapsed_time": "4:08:11", "remaining_time": "0:17:50"}
{"current_steps": 645, "total_steps": 686, "loss": 0.2469, "lr": 4.5558796270706254e-07, "epoch": 6.5836177474402735, "percentage": 94.02, "elapsed_time": "4:10:01", "remaining_time": "0:15:53"}
{"current_steps": 650, "total_steps": 686, "loss": 0.2454, "lr": 3.5387344984600946e-07, "epoch": 6.63481228668942, "percentage": 94.75, "elapsed_time": "4:11:55", "remaining_time": "0:13:57"}
{"current_steps": 655, "total_steps": 686, "loss": 0.2494, "lr": 2.64891707332966e-07, "epoch": 6.686006825938566, "percentage": 95.48, "elapsed_time": "4:13:51", "remaining_time": "0:12:00"}
{"current_steps": 660, "total_steps": 686, "loss": 0.239, "lr": 1.887004047594232e-07, "epoch": 6.737201365187714, "percentage": 96.21, "elapsed_time": "4:15:42", "remaining_time": "0:10:04"}
{"current_steps": 665, "total_steps": 686, "loss": 0.2517, "lr": 1.2534892215740667e-07, "epoch": 6.78839590443686, "percentage": 96.94, "elapsed_time": "4:17:39", "remaining_time": "0:08:08"}
{"current_steps": 670, "total_steps": 686, "loss": 0.2463, "lr": 7.487831799597889e-08, "epoch": 6.839590443686006, "percentage": 97.67, "elapsed_time": "4:19:33", "remaining_time": "0:06:11"}
{"current_steps": 675, "total_steps": 686, "loss": 0.2511, "lr": 3.73213025710073e-08, "epoch": 6.890784982935154, "percentage": 98.4, "elapsed_time": "4:21:28", "remaining_time": "0:04:15"}
{"current_steps": 680, "total_steps": 686, "loss": 0.257, "lr": 1.2702216805431377e-08, "epoch": 6.9419795221843, "percentage": 99.13, "elapsed_time": "4:23:26", "remaining_time": "0:02:19"}
{"current_steps": 685, "total_steps": 686, "loss": 0.2553, "lr": 1.037016473757202e-09, "epoch": 6.993174061433447, "percentage": 99.85, "elapsed_time": "4:25:21", "remaining_time": "0:00:23"}
{"current_steps": 686, "total_steps": 686, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:25:43", "remaining_time": "0:00:00"}