QwenGuard-v1.2-7B / trainer_log.jsonl
LukasHug's picture
Upload model files
2439f83 verified
{"current_steps": 1, "total_steps": 136, "loss": 0.7048, "lr": 1e-05, "epoch": 0.014598540145985401, "percentage": 0.74, "elapsed_time": "0:00:11", "remaining_time": "0:26:58"}
{"current_steps": 2, "total_steps": 136, "loss": 0.706, "lr": 2e-05, "epoch": 0.029197080291970802, "percentage": 1.47, "elapsed_time": "0:00:18", "remaining_time": "0:20:13"}
{"current_steps": 3, "total_steps": 136, "loss": 0.6427, "lr": 3e-05, "epoch": 0.043795620437956206, "percentage": 2.21, "elapsed_time": "0:00:23", "remaining_time": "0:17:29"}
{"current_steps": 4, "total_steps": 136, "loss": 0.7227, "lr": 4e-05, "epoch": 0.058394160583941604, "percentage": 2.94, "elapsed_time": "0:00:29", "remaining_time": "0:16:04"}
{"current_steps": 5, "total_steps": 136, "loss": 0.8235, "lr": 5e-05, "epoch": 0.072992700729927, "percentage": 3.68, "elapsed_time": "0:00:34", "remaining_time": "0:15:13"}
{"current_steps": 6, "total_steps": 136, "loss": 0.8702, "lr": 4.9992811366328926e-05, "epoch": 0.08759124087591241, "percentage": 4.41, "elapsed_time": "0:00:40", "remaining_time": "0:14:37"}
{"current_steps": 7, "total_steps": 136, "loss": 0.7634, "lr": 4.997124959943201e-05, "epoch": 0.10218978102189781, "percentage": 5.15, "elapsed_time": "0:00:46", "remaining_time": "0:14:09"}
{"current_steps": 8, "total_steps": 136, "loss": 0.7925, "lr": 4.993532709928075e-05, "epoch": 0.11678832116788321, "percentage": 5.88, "elapsed_time": "0:00:51", "remaining_time": "0:13:48"}
{"current_steps": 9, "total_steps": 136, "loss": 0.7246, "lr": 4.9885064524570665e-05, "epoch": 0.13138686131386862, "percentage": 6.62, "elapsed_time": "0:00:57", "remaining_time": "0:13:36"}
{"current_steps": 10, "total_steps": 136, "loss": 0.6298, "lr": 4.982049078084071e-05, "epoch": 0.145985401459854, "percentage": 7.35, "elapsed_time": "0:01:03", "remaining_time": "0:13:20"}
{"current_steps": 11, "total_steps": 136, "loss": 0.5719, "lr": 4.974164300384998e-05, "epoch": 0.16058394160583941, "percentage": 8.09, "elapsed_time": "0:01:09", "remaining_time": "0:13:04"}
{"current_steps": 12, "total_steps": 136, "loss": 0.5577, "lr": 4.964856653822122e-05, "epoch": 0.17518248175182483, "percentage": 8.82, "elapsed_time": "0:01:15", "remaining_time": "0:12:57"}
{"current_steps": 13, "total_steps": 136, "loss": 0.484, "lr": 4.954131491136362e-05, "epoch": 0.1897810218978102, "percentage": 9.56, "elapsed_time": "0:01:20", "remaining_time": "0:12:46"}
{"current_steps": 14, "total_steps": 136, "loss": 0.4394, "lr": 4.9419949802689666e-05, "epoch": 0.20437956204379562, "percentage": 10.29, "elapsed_time": "0:01:26", "remaining_time": "0:12:34"}
{"current_steps": 15, "total_steps": 136, "loss": 0.4575, "lr": 4.92845410081439e-05, "epoch": 0.21897810218978103, "percentage": 11.03, "elapsed_time": "0:01:32", "remaining_time": "0:12:23"}
{"current_steps": 16, "total_steps": 136, "loss": 0.4642, "lr": 4.913516640006392e-05, "epoch": 0.23357664233576642, "percentage": 11.76, "elapsed_time": "0:01:37", "remaining_time": "0:12:13"}
{"current_steps": 17, "total_steps": 136, "loss": 0.434, "lr": 4.897191188239667e-05, "epoch": 0.24817518248175183, "percentage": 12.5, "elapsed_time": "0:01:43", "remaining_time": "0:12:03"}
{"current_steps": 18, "total_steps": 136, "loss": 0.405, "lr": 4.8794871341296e-05, "epoch": 0.26277372262773724, "percentage": 13.24, "elapsed_time": "0:01:48", "remaining_time": "0:11:54"}
{"current_steps": 19, "total_steps": 136, "loss": 0.3909, "lr": 4.8604146591129485e-05, "epoch": 0.2773722627737226, "percentage": 13.97, "elapsed_time": "0:01:54", "remaining_time": "0:11:45"}
{"current_steps": 20, "total_steps": 136, "loss": 0.4086, "lr": 4.8399847315926e-05, "epoch": 0.291970802919708, "percentage": 14.71, "elapsed_time": "0:02:00", "remaining_time": "0:11:36"}
{"current_steps": 20, "total_steps": 136, "eval_loss": 0.5058628916740417, "epoch": 0.291970802919708, "percentage": 14.71, "elapsed_time": "0:02:02", "remaining_time": "0:11:50"}
{"current_steps": 21, "total_steps": 136, "loss": 0.3901, "lr": 4.818209100629745e-05, "epoch": 0.30656934306569344, "percentage": 15.44, "elapsed_time": "0:02:08", "remaining_time": "0:11:41"}
{"current_steps": 22, "total_steps": 136, "loss": 0.3723, "lr": 4.795100289187099e-05, "epoch": 0.32116788321167883, "percentage": 16.18, "elapsed_time": "0:02:13", "remaining_time": "0:11:33"}
{"current_steps": 23, "total_steps": 136, "loss": 0.3757, "lr": 4.7706715869270635e-05, "epoch": 0.3357664233576642, "percentage": 16.91, "elapsed_time": "0:02:19", "remaining_time": "0:11:24"}
{"current_steps": 24, "total_steps": 136, "loss": 0.377, "lr": 4.74493704256897e-05, "epoch": 0.35036496350364965, "percentage": 17.65, "elapsed_time": "0:02:25", "remaining_time": "0:11:16"}
{"current_steps": 25, "total_steps": 136, "loss": 0.3599, "lr": 4.717911455809782e-05, "epoch": 0.36496350364963503, "percentage": 18.38, "elapsed_time": "0:02:30", "remaining_time": "0:11:08"}
{"current_steps": 26, "total_steps": 136, "loss": 0.3235, "lr": 4.6896103688129385e-05, "epoch": 0.3795620437956204, "percentage": 19.12, "elapsed_time": "0:02:36", "remaining_time": "0:11:00"}
{"current_steps": 27, "total_steps": 136, "loss": 0.3538, "lr": 4.660050057270191e-05, "epoch": 0.39416058394160586, "percentage": 19.85, "elapsed_time": "0:02:41", "remaining_time": "0:10:52"}
{"current_steps": 28, "total_steps": 136, "loss": 0.347, "lr": 4.6292475210416106e-05, "epoch": 0.40875912408759124, "percentage": 20.59, "elapsed_time": "0:02:47", "remaining_time": "0:10:45"}
{"current_steps": 29, "total_steps": 136, "loss": 0.3239, "lr": 4.597220474379125e-05, "epoch": 0.4233576642335766, "percentage": 21.32, "elapsed_time": "0:02:53", "remaining_time": "0:10:40"}
{"current_steps": 30, "total_steps": 136, "loss": 0.3172, "lr": 4.563987335739216e-05, "epoch": 0.43795620437956206, "percentage": 22.06, "elapsed_time": "0:02:59", "remaining_time": "0:10:33"}
{"current_steps": 31, "total_steps": 136, "loss": 0.3161, "lr": 4.5295672171906364e-05, "epoch": 0.45255474452554745, "percentage": 22.79, "elapsed_time": "0:03:04", "remaining_time": "0:10:25"}
{"current_steps": 32, "total_steps": 136, "loss": 0.3231, "lr": 4.49397991342324e-05, "epoch": 0.46715328467153283, "percentage": 23.53, "elapsed_time": "0:03:10", "remaining_time": "0:10:20"}
{"current_steps": 33, "total_steps": 136, "loss": 0.3305, "lr": 4.4572458903642354e-05, "epoch": 0.48175182481751827, "percentage": 24.26, "elapsed_time": "0:03:16", "remaining_time": "0:10:13"}
{"current_steps": 34, "total_steps": 136, "loss": 0.3384, "lr": 4.419386273408428e-05, "epoch": 0.49635036496350365, "percentage": 25.0, "elapsed_time": "0:03:22", "remaining_time": "0:10:06"}
{"current_steps": 35, "total_steps": 136, "loss": 0.3178, "lr": 4.3804228352691935e-05, "epoch": 0.5109489051094891, "percentage": 25.74, "elapsed_time": "0:03:27", "remaining_time": "0:09:59"}
{"current_steps": 36, "total_steps": 136, "loss": 0.3346, "lr": 4.3403779834572004e-05, "epoch": 0.5255474452554745, "percentage": 26.47, "elapsed_time": "0:03:33", "remaining_time": "0:09:52"}
{"current_steps": 37, "total_steps": 136, "loss": 0.3268, "lr": 4.2992747473940556e-05, "epoch": 0.5401459854014599, "percentage": 27.21, "elapsed_time": "0:03:38", "remaining_time": "0:09:45"}
{"current_steps": 38, "total_steps": 136, "loss": 0.2861, "lr": 4.2571367651683e-05, "epoch": 0.5547445255474452, "percentage": 27.94, "elapsed_time": "0:03:44", "remaining_time": "0:09:39"}
{"current_steps": 39, "total_steps": 136, "loss": 0.2516, "lr": 4.213988269941362e-05, "epoch": 0.5693430656934306, "percentage": 28.68, "elapsed_time": "0:03:50", "remaining_time": "0:09:32"}
{"current_steps": 40, "total_steps": 136, "loss": 0.2844, "lr": 4.169854076011292e-05, "epoch": 0.583941605839416, "percentage": 29.41, "elapsed_time": "0:03:55", "remaining_time": "0:09:25"}
{"current_steps": 40, "total_steps": 136, "eval_loss": 0.5329129099845886, "epoch": 0.583941605839416, "percentage": 29.41, "elapsed_time": "0:03:57", "remaining_time": "0:09:29"}
{"current_steps": 41, "total_steps": 136, "loss": 0.2759, "lr": 4.124759564542295e-05, "epoch": 0.5985401459854015, "percentage": 30.15, "elapsed_time": "0:04:03", "remaining_time": "0:09:23"}
{"current_steps": 42, "total_steps": 136, "loss": 0.2614, "lr": 4.078730668968253e-05, "epoch": 0.6131386861313869, "percentage": 30.88, "elapsed_time": "0:04:08", "remaining_time": "0:09:16"}
{"current_steps": 43, "total_steps": 136, "loss": 0.2577, "lr": 4.031793860078649e-05, "epoch": 0.6277372262773723, "percentage": 31.62, "elapsed_time": "0:04:14", "remaining_time": "0:09:10"}
{"current_steps": 44, "total_steps": 136, "loss": 0.2518, "lr": 3.9839761307954675e-05, "epoch": 0.6423357664233577, "percentage": 32.35, "elapsed_time": "0:04:19", "remaining_time": "0:09:03"}
{"current_steps": 45, "total_steps": 136, "loss": 0.3, "lr": 3.935304980649813e-05, "epoch": 0.656934306569343, "percentage": 33.09, "elapsed_time": "0:04:25", "remaining_time": "0:08:56"}
{"current_steps": 46, "total_steps": 136, "loss": 0.2604, "lr": 3.8858083999671855e-05, "epoch": 0.6715328467153284, "percentage": 33.82, "elapsed_time": "0:04:31", "remaining_time": "0:08:50"}
{"current_steps": 47, "total_steps": 136, "loss": 0.2716, "lr": 3.835514853770505e-05, "epoch": 0.6861313868613139, "percentage": 34.56, "elapsed_time": "0:04:36", "remaining_time": "0:08:44"}
{"current_steps": 48, "total_steps": 136, "loss": 0.2535, "lr": 3.784453265410141e-05, "epoch": 0.7007299270072993, "percentage": 35.29, "elapsed_time": "0:04:42", "remaining_time": "0:08:37"}
{"current_steps": 49, "total_steps": 136, "loss": 0.2341, "lr": 3.732652999930364e-05, "epoch": 0.7153284671532847, "percentage": 36.03, "elapsed_time": "0:04:48", "remaining_time": "0:08:31"}
{"current_steps": 50, "total_steps": 136, "loss": 0.2702, "lr": 3.680143847181783e-05, "epoch": 0.7299270072992701, "percentage": 36.76, "elapsed_time": "0:04:53", "remaining_time": "0:08:25"}
{"current_steps": 51, "total_steps": 136, "loss": 0.2579, "lr": 3.6269560046894766e-05, "epoch": 0.7445255474452555, "percentage": 37.5, "elapsed_time": "0:04:59", "remaining_time": "0:08:19"}
{"current_steps": 52, "total_steps": 136, "loss": 0.2287, "lr": 3.573120060286679e-05, "epoch": 0.7591240875912408, "percentage": 38.24, "elapsed_time": "0:05:05", "remaining_time": "0:08:12"}
{"current_steps": 53, "total_steps": 136, "loss": 0.2501, "lr": 3.5186669745240026e-05, "epoch": 0.7737226277372263, "percentage": 38.97, "elapsed_time": "0:05:10", "remaining_time": "0:08:06"}
{"current_steps": 54, "total_steps": 136, "loss": 0.2195, "lr": 3.463628062864312e-05, "epoch": 0.7883211678832117, "percentage": 39.71, "elapsed_time": "0:05:16", "remaining_time": "0:08:01"}
{"current_steps": 55, "total_steps": 136, "loss": 0.2243, "lr": 3.4080349776734925e-05, "epoch": 0.8029197080291971, "percentage": 40.44, "elapsed_time": "0:05:22", "remaining_time": "0:07:54"}
{"current_steps": 56, "total_steps": 136, "loss": 0.2184, "lr": 3.351919690017473e-05, "epoch": 0.8175182481751825, "percentage": 41.18, "elapsed_time": "0:05:28", "remaining_time": "0:07:48"}
{"current_steps": 57, "total_steps": 136, "loss": 0.2255, "lr": 3.2953144712759545e-05, "epoch": 0.8321167883211679, "percentage": 41.91, "elapsed_time": "0:05:33", "remaining_time": "0:07:42"}
{"current_steps": 58, "total_steps": 136, "loss": 0.24, "lr": 3.238251874583452e-05, "epoch": 0.8467153284671532, "percentage": 42.65, "elapsed_time": "0:05:39", "remaining_time": "0:07:36"}
{"current_steps": 59, "total_steps": 136, "loss": 0.2246, "lr": 3.1807647161082795e-05, "epoch": 0.8613138686131386, "percentage": 43.38, "elapsed_time": "0:05:44", "remaining_time": "0:07:30"}
{"current_steps": 60, "total_steps": 136, "loss": 0.232, "lr": 3.122886056180284e-05, "epoch": 0.8759124087591241, "percentage": 44.12, "elapsed_time": "0:05:50", "remaining_time": "0:07:23"}
{"current_steps": 60, "total_steps": 136, "eval_loss": 0.5338236093521118, "epoch": 0.8759124087591241, "percentage": 44.12, "elapsed_time": "0:05:52", "remaining_time": "0:07:26"}
{"current_steps": 61, "total_steps": 136, "loss": 0.2636, "lr": 3.064649180278152e-05, "epoch": 0.8905109489051095, "percentage": 44.85, "elapsed_time": "0:05:57", "remaining_time": "0:07:19"}
{"current_steps": 62, "total_steps": 136, "loss": 0.2112, "lr": 3.006087579887244e-05, "epoch": 0.9051094890510949, "percentage": 45.59, "elapsed_time": "0:06:03", "remaining_time": "0:07:13"}
{"current_steps": 63, "total_steps": 136, "loss": 0.1924, "lr": 2.9472349332389525e-05, "epoch": 0.9197080291970803, "percentage": 46.32, "elapsed_time": "0:06:08", "remaining_time": "0:07:07"}
{"current_steps": 64, "total_steps": 136, "loss": 0.2254, "lr": 2.8881250859426646e-05, "epoch": 0.9343065693430657, "percentage": 47.06, "elapsed_time": "0:06:14", "remaining_time": "0:07:01"}
{"current_steps": 65, "total_steps": 136, "loss": 0.2074, "lr": 2.8287920315214643e-05, "epoch": 0.948905109489051, "percentage": 47.79, "elapsed_time": "0:06:20", "remaining_time": "0:06:55"}
{"current_steps": 66, "total_steps": 136, "loss": 0.1833, "lr": 2.7692698918627778e-05, "epoch": 0.9635036496350365, "percentage": 48.53, "elapsed_time": "0:06:25", "remaining_time": "0:06:49"}
{"current_steps": 67, "total_steps": 136, "loss": 0.2125, "lr": 2.7095928975951913e-05, "epoch": 0.9781021897810219, "percentage": 49.26, "elapsed_time": "0:06:31", "remaining_time": "0:06:43"}
{"current_steps": 68, "total_steps": 136, "loss": 0.2373, "lr": 2.649795368402735e-05, "epoch": 0.9927007299270073, "percentage": 50.0, "elapsed_time": "0:06:37", "remaining_time": "0:06:37"}
{"current_steps": 69, "total_steps": 136, "loss": 0.1027, "lr": 2.649795368402735e-05, "epoch": 1.0, "percentage": 50.74, "elapsed_time": "0:06:39", "remaining_time": "0:06:28"}
{"current_steps": 70, "total_steps": 136, "loss": 0.1039, "lr": 2.5899116932879534e-05, "epoch": 1.0145985401459854, "percentage": 51.47, "elapsed_time": "0:07:32", "remaining_time": "0:07:07"}
{"current_steps": 71, "total_steps": 136, "loss": 0.1075, "lr": 2.529976310795108e-05, "epoch": 1.0291970802919708, "percentage": 52.21, "elapsed_time": "0:07:38", "remaining_time": "0:06:59"}
{"current_steps": 72, "total_steps": 136, "loss": 0.1053, "lr": 2.470023689204893e-05, "epoch": 1.0437956204379562, "percentage": 52.94, "elapsed_time": "0:07:44", "remaining_time": "0:06:52"}
{"current_steps": 73, "total_steps": 136, "loss": 0.1048, "lr": 2.4100883067120475e-05, "epoch": 1.0583941605839415, "percentage": 53.68, "elapsed_time": "0:07:49", "remaining_time": "0:06:45"}
{"current_steps": 74, "total_steps": 136, "loss": 0.0987, "lr": 2.3502046315972656e-05, "epoch": 1.072992700729927, "percentage": 54.41, "elapsed_time": "0:07:55", "remaining_time": "0:06:38"}
{"current_steps": 75, "total_steps": 136, "loss": 0.0836, "lr": 2.290407102404809e-05, "epoch": 1.0875912408759123, "percentage": 55.15, "elapsed_time": "0:08:01", "remaining_time": "0:06:31"}
{"current_steps": 76, "total_steps": 136, "loss": 0.1159, "lr": 2.2307301081372224e-05, "epoch": 1.102189781021898, "percentage": 55.88, "elapsed_time": "0:08:06", "remaining_time": "0:06:24"}
{"current_steps": 77, "total_steps": 136, "loss": 0.0816, "lr": 2.1712079684785363e-05, "epoch": 1.1167883211678833, "percentage": 56.62, "elapsed_time": "0:08:12", "remaining_time": "0:06:17"}
{"current_steps": 78, "total_steps": 136, "loss": 0.1141, "lr": 2.111874914057336e-05, "epoch": 1.1313868613138687, "percentage": 57.35, "elapsed_time": "0:08:17", "remaining_time": "0:06:10"}
{"current_steps": 79, "total_steps": 136, "loss": 0.1146, "lr": 2.0527650667610478e-05, "epoch": 1.145985401459854, "percentage": 58.09, "elapsed_time": "0:08:23", "remaining_time": "0:06:03"}
{"current_steps": 80, "total_steps": 136, "loss": 0.0847, "lr": 1.993912420112756e-05, "epoch": 1.1605839416058394, "percentage": 58.82, "elapsed_time": "0:08:29", "remaining_time": "0:05:56"}
{"current_steps": 80, "total_steps": 136, "eval_loss": 0.6174606084823608, "epoch": 1.1605839416058394, "percentage": 58.82, "elapsed_time": "0:08:30", "remaining_time": "0:05:57"}
{"current_steps": 81, "total_steps": 136, "loss": 0.1019, "lr": 1.935350819721849e-05, "epoch": 1.1751824817518248, "percentage": 59.56, "elapsed_time": "0:08:36", "remaining_time": "0:05:50"}
{"current_steps": 82, "total_steps": 136, "loss": 0.1077, "lr": 1.8771139438197168e-05, "epoch": 1.1897810218978102, "percentage": 60.29, "elapsed_time": "0:08:42", "remaining_time": "0:05:43"}
{"current_steps": 83, "total_steps": 136, "loss": 0.091, "lr": 1.819235283891721e-05, "epoch": 1.2043795620437956, "percentage": 61.03, "elapsed_time": "0:08:47", "remaining_time": "0:05:36"}
{"current_steps": 84, "total_steps": 136, "loss": 0.1081, "lr": 1.7617481254165487e-05, "epoch": 1.218978102189781, "percentage": 61.76, "elapsed_time": "0:08:53", "remaining_time": "0:05:30"}
{"current_steps": 85, "total_steps": 136, "loss": 0.1087, "lr": 1.704685528724046e-05, "epoch": 1.2335766423357664, "percentage": 62.5, "elapsed_time": "0:08:58", "remaining_time": "0:05:23"}
{"current_steps": 86, "total_steps": 136, "loss": 0.1094, "lr": 1.648080309982528e-05, "epoch": 1.2481751824817517, "percentage": 63.24, "elapsed_time": "0:09:04", "remaining_time": "0:05:16"}
{"current_steps": 87, "total_steps": 136, "loss": 0.1018, "lr": 1.591965022326507e-05, "epoch": 1.2627737226277373, "percentage": 63.97, "elapsed_time": "0:09:09", "remaining_time": "0:05:09"}
{"current_steps": 88, "total_steps": 136, "loss": 0.0921, "lr": 1.536371937135688e-05, "epoch": 1.2773722627737225, "percentage": 64.71, "elapsed_time": "0:09:15", "remaining_time": "0:05:03"}
{"current_steps": 89, "total_steps": 136, "loss": 0.1044, "lr": 1.4813330254759985e-05, "epoch": 1.2919708029197081, "percentage": 65.44, "elapsed_time": "0:09:21", "remaining_time": "0:04:56"}
{"current_steps": 90, "total_steps": 136, "loss": 0.0816, "lr": 1.426879939713322e-05, "epoch": 1.3065693430656935, "percentage": 66.18, "elapsed_time": "0:09:26", "remaining_time": "0:04:49"}
{"current_steps": 91, "total_steps": 136, "loss": 0.0842, "lr": 1.3730439953105243e-05, "epoch": 1.3211678832116789, "percentage": 66.91, "elapsed_time": "0:09:32", "remaining_time": "0:04:43"}
{"current_steps": 92, "total_steps": 136, "loss": 0.0744, "lr": 1.3198561528182183e-05, "epoch": 1.3357664233576643, "percentage": 67.65, "elapsed_time": "0:09:38", "remaining_time": "0:04:36"}
{"current_steps": 93, "total_steps": 136, "loss": 0.1033, "lr": 1.2673470000696364e-05, "epoch": 1.3503649635036497, "percentage": 68.38, "elapsed_time": "0:09:44", "remaining_time": "0:04:30"}
{"current_steps": 94, "total_steps": 136, "loss": 0.1001, "lr": 1.2155467345898602e-05, "epoch": 1.364963503649635, "percentage": 69.12, "elapsed_time": "0:09:49", "remaining_time": "0:04:23"}
{"current_steps": 95, "total_steps": 136, "loss": 0.101, "lr": 1.1644851462294957e-05, "epoch": 1.3795620437956204, "percentage": 69.85, "elapsed_time": "0:09:55", "remaining_time": "0:04:16"}
{"current_steps": 96, "total_steps": 136, "loss": 0.0863, "lr": 1.114191600032815e-05, "epoch": 1.3941605839416058, "percentage": 70.59, "elapsed_time": "0:10:01", "remaining_time": "0:04:10"}
{"current_steps": 97, "total_steps": 136, "loss": 0.0855, "lr": 1.064695019350187e-05, "epoch": 1.4087591240875912, "percentage": 71.32, "elapsed_time": "0:10:06", "remaining_time": "0:04:03"}
{"current_steps": 98, "total_steps": 136, "loss": 0.111, "lr": 1.0160238692045332e-05, "epoch": 1.4233576642335766, "percentage": 72.06, "elapsed_time": "0:10:12", "remaining_time": "0:03:57"}
{"current_steps": 99, "total_steps": 136, "loss": 0.0939, "lr": 9.682061399213525e-06, "epoch": 1.437956204379562, "percentage": 72.79, "elapsed_time": "0:10:17", "remaining_time": "0:03:50"}
{"current_steps": 100, "total_steps": 136, "loss": 0.0882, "lr": 9.21269331031748e-06, "epoch": 1.4525547445255476, "percentage": 73.53, "elapsed_time": "0:10:23", "remaining_time": "0:03:44"}
{"current_steps": 100, "total_steps": 136, "eval_loss": 0.5955010652542114, "epoch": 1.4525547445255476, "percentage": 73.53, "elapsed_time": "0:10:25", "remaining_time": "0:03:45"}
{"current_steps": 101, "total_steps": 136, "loss": 0.0937, "lr": 8.752404354577052e-06, "epoch": 1.4671532846715327, "percentage": 74.26, "elapsed_time": "0:10:31", "remaining_time": "0:03:38"}
{"current_steps": 102, "total_steps": 136, "loss": 0.0803, "lr": 8.301459239887074e-06, "epoch": 1.4817518248175183, "percentage": 75.0, "elapsed_time": "0:10:36", "remaining_time": "0:03:32"}
{"current_steps": 103, "total_steps": 136, "loss": 0.1008, "lr": 7.860117300586383e-06, "epoch": 1.4963503649635037, "percentage": 75.74, "elapsed_time": "0:10:42", "remaining_time": "0:03:25"}
{"current_steps": 104, "total_steps": 136, "loss": 0.0731, "lr": 7.428632348317005e-06, "epoch": 1.510948905109489, "percentage": 76.47, "elapsed_time": "0:10:47", "remaining_time": "0:03:19"}
{"current_steps": 105, "total_steps": 136, "loss": 0.075, "lr": 7.007252526059446e-06, "epoch": 1.5255474452554745, "percentage": 77.21, "elapsed_time": "0:10:53", "remaining_time": "0:03:12"}
{"current_steps": 106, "total_steps": 136, "loss": 0.0797, "lr": 6.596220165428002e-06, "epoch": 1.5401459854014599, "percentage": 77.94, "elapsed_time": "0:10:59", "remaining_time": "0:03:06"}
{"current_steps": 107, "total_steps": 136, "loss": 0.1031, "lr": 6.195771647308074e-06, "epoch": 1.5547445255474452, "percentage": 78.68, "elapsed_time": "0:11:04", "remaining_time": "0:03:00"}
{"current_steps": 108, "total_steps": 136, "loss": 0.0876, "lr": 5.806137265915732e-06, "epoch": 1.5693430656934306, "percentage": 79.41, "elapsed_time": "0:11:10", "remaining_time": "0:02:53"}
{"current_steps": 109, "total_steps": 136, "loss": 0.0859, "lr": 5.427541096357647e-06, "epoch": 1.583941605839416, "percentage": 80.15, "elapsed_time": "0:11:16", "remaining_time": "0:02:47"}
{"current_steps": 110, "total_steps": 136, "loss": 0.0914, "lr": 5.060200865767606e-06, "epoch": 1.5985401459854014, "percentage": 80.88, "elapsed_time": "0:11:22", "remaining_time": "0:02:41"}
{"current_steps": 111, "total_steps": 136, "loss": 0.0891, "lr": 4.704327828093641e-06, "epoch": 1.613138686131387, "percentage": 81.62, "elapsed_time": "0:11:27", "remaining_time": "0:02:34"}
{"current_steps": 112, "total_steps": 136, "loss": 0.0802, "lr": 4.3601266426078426e-06, "epoch": 1.6277372262773722, "percentage": 82.35, "elapsed_time": "0:11:33", "remaining_time": "0:02:28"}
{"current_steps": 113, "total_steps": 136, "loss": 0.0837, "lr": 4.02779525620875e-06, "epoch": 1.6423357664233578, "percentage": 83.09, "elapsed_time": "0:11:38", "remaining_time": "0:02:22"}
{"current_steps": 114, "total_steps": 136, "loss": 0.0733, "lr": 3.707524789583891e-06, "epoch": 1.656934306569343, "percentage": 83.82, "elapsed_time": "0:11:44", "remaining_time": "0:02:15"}
{"current_steps": 115, "total_steps": 136, "loss": 0.0816, "lr": 3.3994994272980946e-06, "epoch": 1.6715328467153285, "percentage": 84.56, "elapsed_time": "0:11:50", "remaining_time": "0:02:09"}
{"current_steps": 116, "total_steps": 136, "loss": 0.0947, "lr": 3.1038963118706244e-06, "epoch": 1.686131386861314, "percentage": 85.29, "elapsed_time": "0:11:55", "remaining_time": "0:02:03"}
{"current_steps": 117, "total_steps": 136, "loss": 0.0807, "lr": 2.8208854419021824e-06, "epoch": 1.7007299270072993, "percentage": 86.03, "elapsed_time": "0:12:01", "remaining_time": "0:01:57"}
{"current_steps": 118, "total_steps": 136, "loss": 0.0576, "lr": 2.5506295743103094e-06, "epoch": 1.7153284671532847, "percentage": 86.76, "elapsed_time": "0:12:07", "remaining_time": "0:01:50"}
{"current_steps": 119, "total_steps": 136, "loss": 0.0857, "lr": 2.2932841307293644e-06, "epoch": 1.72992700729927, "percentage": 87.5, "elapsed_time": "0:12:12", "remaining_time": "0:01:44"}
{"current_steps": 120, "total_steps": 136, "loss": 0.0868, "lr": 2.0489971081290195e-06, "epoch": 1.7445255474452555, "percentage": 88.24, "elapsed_time": "0:12:18", "remaining_time": "0:01:38"}
{"current_steps": 120, "total_steps": 136, "eval_loss": 0.6069221496582031, "epoch": 1.7445255474452555, "percentage": 88.24, "elapsed_time": "0:12:20", "remaining_time": "0:01:38"}
{"current_steps": 121, "total_steps": 136, "loss": 0.0781, "lr": 1.817908993702555e-06, "epoch": 1.7591240875912408, "percentage": 88.97, "elapsed_time": "0:12:25", "remaining_time": "0:01:32"}
{"current_steps": 122, "total_steps": 136, "loss": 0.0773, "lr": 1.6001526840740049e-06, "epoch": 1.7737226277372264, "percentage": 89.71, "elapsed_time": "0:12:31", "remaining_time": "0:01:26"}
{"current_steps": 123, "total_steps": 136, "loss": 0.0648, "lr": 1.3958534088705206e-06, "epoch": 1.7883211678832116, "percentage": 90.44, "elapsed_time": "0:12:36", "remaining_time": "0:01:19"}
{"current_steps": 124, "total_steps": 136, "loss": 0.0685, "lr": 1.205128658704005e-06, "epoch": 1.8029197080291972, "percentage": 91.18, "elapsed_time": "0:12:42", "remaining_time": "0:01:13"}
{"current_steps": 125, "total_steps": 136, "loss": 0.0597, "lr": 1.028088117603332e-06, "epoch": 1.8175182481751824, "percentage": 91.91, "elapsed_time": "0:12:48", "remaining_time": "0:01:07"}
{"current_steps": 126, "total_steps": 136, "loss": 0.0851, "lr": 8.648335999360935e-07, "epoch": 1.832116788321168, "percentage": 92.65, "elapsed_time": "0:12:53", "remaining_time": "0:01:01"}
{"current_steps": 127, "total_steps": 136, "loss": 0.0775, "lr": 7.154589918561022e-07, "epoch": 1.8467153284671531, "percentage": 93.38, "elapsed_time": "0:12:59", "remaining_time": "0:00:55"}
{"current_steps": 128, "total_steps": 136, "loss": 0.0837, "lr": 5.800501973103362e-07, "epoch": 1.8613138686131387, "percentage": 94.12, "elapsed_time": "0:13:05", "remaining_time": "0:00:49"}
{"current_steps": 129, "total_steps": 136, "loss": 0.104, "lr": 4.586850886363875e-07, "epoch": 1.8759124087591241, "percentage": 94.85, "elapsed_time": "0:13:10", "remaining_time": "0:00:42"}
{"current_steps": 130, "total_steps": 136, "loss": 0.0694, "lr": 3.514334617787857e-07, "epoch": 1.8905109489051095, "percentage": 95.59, "elapsed_time": "0:13:16", "remaining_time": "0:00:36"}
{"current_steps": 131, "total_steps": 136, "loss": 0.0617, "lr": 2.5835699615002764e-07, "epoch": 1.905109489051095, "percentage": 96.32, "elapsed_time": "0:13:22", "remaining_time": "0:00:30"}
{"current_steps": 132, "total_steps": 136, "loss": 0.0792, "lr": 1.7950921915928788e-07, "epoch": 1.9197080291970803, "percentage": 97.06, "elapsed_time": "0:13:27", "remaining_time": "0:00:24"}
{"current_steps": 133, "total_steps": 136, "loss": 0.0919, "lr": 1.1493547542933969e-07, "epoch": 1.9343065693430657, "percentage": 97.79, "elapsed_time": "0:13:33", "remaining_time": "0:00:18"}
{"current_steps": 134, "total_steps": 136, "loss": 0.0655, "lr": 6.467290071925647e-08, "epoch": 1.948905109489051, "percentage": 98.53, "elapsed_time": "0:13:38", "remaining_time": "0:00:12"}
{"current_steps": 135, "total_steps": 136, "loss": 0.0607, "lr": 2.8750400567992274e-08, "epoch": 1.9635036496350367, "percentage": 99.26, "elapsed_time": "0:13:44", "remaining_time": "0:00:06"}
{"current_steps": 136, "total_steps": 136, "loss": 0.0823, "lr": 7.188633671079137e-09, "epoch": 1.9781021897810218, "percentage": 100.0, "elapsed_time": "0:13:50", "remaining_time": "0:00:00"}
{"current_steps": 136, "total_steps": 136, "epoch": 1.9781021897810218, "percentage": 100.0, "elapsed_time": "0:15:16", "remaining_time": "0:00:00"}