Files
llama3-8b-full-pretrain-was…/trainer_log.jsonl

239 lines
48 KiB
Plaintext
Raw Permalink Normal View History

{"current_steps": 1, "total_steps": 237, "loss": 2.204664945602417, "lr": 0.0, "epoch": 0.012738853503184714, "percentage": 0.42, "elapsed_time": "0:00:04", "remaining_time": "0:18:59"}
{"current_steps": 2, "total_steps": 237, "loss": 2.1723523139953613, "lr": 4.1666666666666667e-07, "epoch": 0.025477707006369428, "percentage": 0.84, "elapsed_time": "0:00:06", "remaining_time": "0:13:29"}
{"current_steps": 3, "total_steps": 237, "loss": 2.153947114944458, "lr": 8.333333333333333e-07, "epoch": 0.03821656050955414, "percentage": 1.27, "elapsed_time": "0:00:08", "remaining_time": "0:11:38"}
{"current_steps": 4, "total_steps": 237, "loss": 2.111192464828491, "lr": 1.25e-06, "epoch": 0.050955414012738856, "percentage": 1.69, "elapsed_time": "0:00:11", "remaining_time": "0:10:50"}
{"current_steps": 5, "total_steps": 237, "loss": 2.31960391998291, "lr": 1.6666666666666667e-06, "epoch": 0.06369426751592357, "percentage": 2.11, "elapsed_time": "0:00:13", "remaining_time": "0:10:23"}
{"current_steps": 6, "total_steps": 237, "loss": 2.1123697757720947, "lr": 2.0833333333333334e-06, "epoch": 0.07643312101910828, "percentage": 2.53, "elapsed_time": "0:00:15", "remaining_time": "0:09:55"}
{"current_steps": 7, "total_steps": 237, "loss": 1.7801592350006104, "lr": 2.5e-06, "epoch": 0.08917197452229299, "percentage": 2.95, "elapsed_time": "0:00:18", "remaining_time": "0:09:55"}
{"current_steps": 8, "total_steps": 237, "loss": 1.7316594123840332, "lr": 2.916666666666667e-06, "epoch": 0.10191082802547771, "percentage": 3.38, "elapsed_time": "0:00:20", "remaining_time": "0:09:38"}
{"current_steps": 9, "total_steps": 237, "loss": 1.7363145351409912, "lr": 3.3333333333333333e-06, "epoch": 0.11464968152866242, "percentage": 3.8, "elapsed_time": "0:00:22", "remaining_time": "0:09:25"}
{"current_steps": 10, "total_steps": 237, "loss": 1.7367324829101562, "lr": 3.7500000000000005e-06, "epoch": 0.12738853503184713, "percentage": 4.22, "elapsed_time": "0:00:24", "remaining_time": "0:09:13"}
{"current_steps": 11, "total_steps": 237, "loss": 1.66728937625885, "lr": 4.166666666666667e-06, "epoch": 0.14012738853503184, "percentage": 4.64, "elapsed_time": "0:00:26", "remaining_time": "0:09:04"}
{"current_steps": 12, "total_steps": 237, "loss": 1.5918991565704346, "lr": 4.583333333333333e-06, "epoch": 0.15286624203821655, "percentage": 5.06, "elapsed_time": "0:00:28", "remaining_time": "0:08:57"}
{"current_steps": 13, "total_steps": 237, "loss": 1.7058830261230469, "lr": 5e-06, "epoch": 0.16560509554140126, "percentage": 5.49, "elapsed_time": "0:00:30", "remaining_time": "0:08:49"}
{"current_steps": 14, "total_steps": 237, "loss": 1.6408886909484863, "lr": 5.416666666666667e-06, "epoch": 0.17834394904458598, "percentage": 5.91, "elapsed_time": "0:00:32", "remaining_time": "0:08:42"}
{"current_steps": 15, "total_steps": 237, "loss": 1.5164024829864502, "lr": 5.833333333333334e-06, "epoch": 0.1910828025477707, "percentage": 6.33, "elapsed_time": "0:00:34", "remaining_time": "0:08:36"}
{"current_steps": 16, "total_steps": 237, "loss": 1.494221568107605, "lr": 6.25e-06, "epoch": 0.20382165605095542, "percentage": 6.75, "elapsed_time": "0:00:36", "remaining_time": "0:08:30"}
{"current_steps": 17, "total_steps": 237, "loss": 1.5182886123657227, "lr": 6.666666666666667e-06, "epoch": 0.21656050955414013, "percentage": 7.17, "elapsed_time": "0:00:39", "remaining_time": "0:08:25"}
{"current_steps": 18, "total_steps": 237, "loss": 1.3058141469955444, "lr": 7.083333333333335e-06, "epoch": 0.22929936305732485, "percentage": 7.59, "elapsed_time": "0:00:41", "remaining_time": "0:08:19"}
{"current_steps": 19, "total_steps": 237, "loss": 1.5823700428009033, "lr": 7.500000000000001e-06, "epoch": 0.24203821656050956, "percentage": 8.02, "elapsed_time": "0:00:43", "remaining_time": "0:08:15"}
{"current_steps": 20, "total_steps": 237, "loss": 1.4739738702774048, "lr": 7.916666666666667e-06, "epoch": 0.25477707006369427, "percentage": 8.44, "elapsed_time": "0:00:45", "remaining_time": "0:08:11"}
{"current_steps": 21, "total_steps": 237, "loss": 1.4684441089630127, "lr": 8.333333333333334e-06, "epoch": 0.267515923566879, "percentage": 8.86, "elapsed_time": "0:00:47", "remaining_time": "0:08:08"}
{"current_steps": 22, "total_steps": 237, "loss": 1.3878852128982544, "lr": 8.750000000000001e-06, "epoch": 0.2802547770700637, "percentage": 9.28, "elapsed_time": "0:00:49", "remaining_time": "0:08:05"}
{"current_steps": 23, "total_steps": 237, "loss": 1.412501335144043, "lr": 9.166666666666666e-06, "epoch": 0.2929936305732484, "percentage": 9.7, "elapsed_time": "0:00:51", "remaining_time": "0:08:00"}
{"current_steps": 24, "total_steps": 237, "loss": 1.5133357048034668, "lr": 9.583333333333335e-06, "epoch": 0.3057324840764331, "percentage": 10.13, "elapsed_time": "0:00:53", "remaining_time": "0:07:56"}
{"current_steps": 25, "total_steps": 237, "loss": 1.3026769161224365, "lr": 1e-05, "epoch": 0.3184713375796178, "percentage": 10.55, "elapsed_time": "0:00:56", "remaining_time": "0:07:55"}
{"current_steps": 26, "total_steps": 237, "loss": 1.3877103328704834, "lr": 9.999456158087994e-06, "epoch": 0.33121019108280253, "percentage": 10.97, "elapsed_time": "0:00:58", "remaining_time": "0:07:52"}
{"current_steps": 27, "total_steps": 237, "loss": 1.4998736381530762, "lr": 9.997824750657586e-06, "epoch": 0.34394904458598724, "percentage": 11.39, "elapsed_time": "0:01:00", "remaining_time": "0:07:49"}
{"current_steps": 28, "total_steps": 237, "loss": 1.3498817682266235, "lr": 9.995106132599869e-06, "epoch": 0.35668789808917195, "percentage": 11.81, "elapsed_time": "0:01:02", "remaining_time": "0:07:46"}
{"current_steps": 29, "total_steps": 237, "loss": 1.254498839378357, "lr": 9.99130089531422e-06, "epoch": 0.36942675159235666, "percentage": 12.24, "elapsed_time": "0:01:04", "remaining_time": "0:07:45"}
{"current_steps": 30, "total_steps": 237, "loss": 1.5459938049316406, "lr": 9.98640986657965e-06, "epoch": 0.3821656050955414, "percentage": 12.66, "elapsed_time": "0:01:06", "remaining_time": "0:07:41"}
{"current_steps": 31, "total_steps": 237, "loss": 1.3755627870559692, "lr": 9.980434110374725e-06, "epoch": 0.39490445859872614, "percentage": 13.08, "elapsed_time": "0:01:08", "remaining_time": "0:07:38"}
{"current_steps": 32, "total_steps": 237, "loss": 1.5573776960372925, "lr": 9.973374926646117e-06, "epoch": 0.40764331210191085, "percentage": 13.5, "elapsed_time": "0:01:11", "remaining_time": "0:07:35"}
{"current_steps": 33, "total_steps": 237, "loss": 1.379699945449829, "lr": 9.965233851025816e-06, "epoch": 0.42038216560509556, "percentage": 13.92, "elapsed_time": "0:01:13", "remaining_time": "0:07:32"}
{"current_steps": 34, "total_steps": 237, "loss": 1.5177006721496582, "lr": 9.956012654497073e-06, "epoch": 0.43312101910828027, "percentage": 14.35, "elapsed_time": "0:01:15", "remaining_time": "0:07:29"}
{"current_steps": 35, "total_steps": 237, "loss": 1.4899232387542725, "lr": 9.945713343009154e-06, "epoch": 0.445859872611465, "percentage": 14.77, "elapsed_time": "0:01:17", "remaining_time": "0:07:26"}
{"current_steps": 36, "total_steps": 237, "loss": 1.3931883573532104, "lr": 9.934338157040953e-06, "epoch": 0.4585987261146497, "percentage": 15.19, "elapsed_time": "0:01:19", "remaining_time": "0:07:23"}
{"current_steps": 37, "total_steps": 237, "loss": 1.4822924137115479, "lr": 9.921889571113629e-06, "epoch": 0.4713375796178344, "percentage": 15.61, "elapsed_time": "0:01:21", "remaining_time": "0:07:20"}
{"current_steps": 38, "total_steps": 237, "loss": 1.3738588094711304, "lr": 9.90837029325229e-06, "epoch": 0.4840764331210191, "percentage": 16.03, "elapsed_time": "0:01:23", "remaining_time": "0:07:17"}
{"current_steps": 39, "total_steps": 237, "loss": 1.378421664237976, "lr": 9.893783264396903e-06, "epoch": 0.4968152866242038, "percentage": 16.46, "elapsed_time": "0:01:25", "remaining_time": "0:07:14"}
{"current_steps": 40, "total_steps": 237, "loss": 1.3855531215667725, "lr": 9.878131657762535e-06, "epoch": 0.5095541401273885, "percentage": 16.88, "elapsed_time": "0:01:27", "remaining_time": "0:07:12"}
{"current_steps": 41, "total_steps": 237, "loss": 1.35617196559906, "lr": 9.861418878149056e-06, "epoch": 0.5222929936305732, "percentage": 17.3, "elapsed_time": "0:01:29", "remaining_time": "0:07:10"}
{"current_steps": 42, "total_steps": 237, "loss": 1.4202051162719727, "lr": 9.843648561200476e-06, "epoch": 0.535031847133758, "percentage": 17.72, "elapsed_time": "0:01:32", "remaining_time": "0:07:07"}
{"current_steps": 43, "total_steps": 237, "loss": 1.551034688949585, "lr": 9.82482457261405e-06, "epoch": 0.5477707006369427, "percentage": 18.14, "elapsed_time": "0:01:34", "remaining_time": "0:07:04"}
{"current_steps": 44, "total_steps": 237, "loss": 1.452345848083496, "lr": 9.80495100729936e-06, "epoch": 0.5605095541401274, "percentage": 18.57, "elapsed_time": "0:01:36", "remaining_time": "0:07:02"}
{"current_steps": 45, "total_steps": 237, "loss": 1.410866618156433, "lr": 9.784032188487507e-06, "epoch": 0.5732484076433121, "percentage": 18.99, "elapsed_time": "0:01:38", "remaining_time": "0:06:59"}
{"current_steps": 46, "total_steps": 237, "loss": 1.503042221069336, "lr": 9.762072666790658e-06, "epoch": 0.5859872611464968, "percentage": 19.41, "elapsed_time": "0:01:40", "remaining_time": "0:06:56"}
{"current_steps": 47, "total_steps": 237, "loss": 1.5886300802230835, "lr": 9.73907721921212e-06, "epoch": 0.5987261146496815, "percentage": 19.83, "elapsed_time": "0:01:42", "remaining_time": "0:06:54"}
{"current_steps": 48, "total_steps": 237, "loss": 1.3965404033660889, "lr": 9.715050848107167e-06, "epoch": 0.6114649681528662, "percentage": 20.25, "elapsed_time": "0:01:44", "remaining_time": "0:06:52"}
{"current_steps": 49, "total_steps": 237, "loss": 1.3509052991867065, "lr": 9.689998780094839e-06, "epoch": 0.6242038216560509, "percentage": 20.68, "elapsed_time": "0:01:46", "remaining_time": "0:06:49"}
{"current_steps": 50, "total_steps": 237, "loss": 1.445689082145691, "lr": 9.663926464920959e-06, "epoch": 0.6369426751592356, "percentage": 21.1, "elapsed_time": "0:01:48", "remaining_time": "0:06:46"}
{"current_steps": 51, "total_steps": 237, "loss": 1.485785961151123, "lr": 9.636839574272623e-06, "epoch": 0.6496815286624203, "percentage": 21.52, "elapsed_time": "0:01:50", "remaining_time": "0:06:44"}
{"current_steps": 52, "total_steps": 237, "loss": 1.4493248462677002, "lr": 9.608744000544392e-06, "epoch": 0.6624203821656051, "percentage": 21.94, "elapsed_time": "0:01:52", "remaining_time": "0:06:41"}
{"current_steps": 53, "total_steps": 237, "loss": 1.2050189971923828, "lr": 9.579645855556481e-06, "epoch": 0.6751592356687898, "percentage": 22.36, "elapsed_time": "0:01:54", "remaining_time": "0:06:39"}
{"current_steps": 54, "total_steps": 237, "loss": 1.3595759868621826, "lr": 9.54955146922521e-06, "epoch": 0.6878980891719745, "percentage": 22.78, "elapsed_time": "0:01:57", "remaining_time": "0:06:37"}
{"current_steps": 55, "total_steps": 237, "loss": 1.314743161201477, "lr": 9.51846738818602e-06, "epoch": 0.7006369426751592, "percentage": 23.21, "elapsed_time": "0:01:59", "remaining_time": "0:06:35"}
{"current_steps": 56, "total_steps": 237, "loss": 1.298832654953003, "lr": 9.48640037436934e-06, "epoch": 0.7133757961783439, "percentage": 23.63, "elapsed_time": "0:02:01", "remaining_time": "0:06:32"}
{"current_steps": 57, "total_steps": 237, "loss": 1.361107587814331, "lr": 9.453357403529609e-06, "epoch": 0.7261146496815286, "percentage": 24.05, "elapsed_time": "0:02:03", "remaining_time": "0:06:30"}
{"current_steps": 58, "total_steps": 237, "loss": 1.423778772354126, "lr": 9.419345663727805e-06, "epoch": 0.7388535031847133, "percentage": 24.47, "elapsed_time": "0:02:05", "remaining_time": "0:06:27"}
{"current_steps": 59, "total_steps": 237, "loss": 1.2938448190689087, "lr": 9.38437255376777e-06, "epoch": 0.7515923566878981, "percentage": 24.89, "elapsed_time": "0:02:07", "remaining_time": "0:06:25"}
{"current_steps": 60, "total_steps": 237, "loss": 1.4098949432373047, "lr": 9.348445681586703e-06, "epoch": 0.7643312101910829, "percentage": 25.32, "elapsed_time": "0:02:09", "remaining_time": "0:06:22"}
{"current_steps": 61, "total_steps": 237, "loss": 1.4088222980499268, "lr": 9.31157286260014e-06, "epoch": 0.7770700636942676, "percentage": 25.74, "elapsed_time": "0:02:11", "remaining_time": "0:06:20"}
{"current_steps": 62, "total_steps": 237, "loss": 1.3028312921524048, "lr": 9.273762118001837e-06, "epoch": 0.7898089171974523, "percentage": 26.16, "elapsed_time": "0:02:13", "remaining_time": "0:06:18"}
{"current_steps": 63, "total_steps": 237, "loss": 1.3086093664169312, "lr": 9.235021673018849e-06, "epoch": 0.802547770700637, "percentage": 26.58, "elapsed_time": "0:02:16", "remaining_time": "0:06:15"}
{"current_steps": 64, "total_steps": 237, "loss": 1.315887212753296, "lr": 9.195359955122244e-06, "epoch": 0.8152866242038217, "percentage": 27.0, "elapsed_time": "0:02:18", "remaining_time": "0:06:13"}
{"current_steps": 65, "total_steps": 237, "loss": 1.315997838973999, "lr": 9.15478559219382e-06, "epoch": 0.8280254777070064, "percentage": 27.43, "elapsed_time": "0:02:20", "remaining_time": "0:06:10"}
{"current_steps": 66, "total_steps": 237, "loss": 1.458491563796997, "lr": 9.113307410649222e-06, "epoch": 0.8407643312101911, "percentage": 27.85, "elapsed_time": "0:02:22", "remaining_time": "0:06:08"}
{"current_steps": 67, "total_steps": 237, "loss": 1.3889572620391846, "lr": 9.070934433517872e-06, "epoch": 0.8535031847133758, "percentage": 28.27, "elapsed_time": "0:02:24", "remaining_time": "0:06:06"}
{"current_steps": 68, "total_steps": 237, "loss": 1.3981947898864746, "lr": 9.027675878480131e-06, "epoch": 0.8662420382165605, "percentage": 28.69, "elapsed_time": "0:02:26", "remaining_time": "0:06:03"}
{"current_steps": 69, "total_steps": 237, "loss": 1.3850674629211426, "lr": 8.983541155862114e-06, "epoch": 0.8789808917197452, "percentage": 29.11, "elapsed_time": "0:02:28", "remaining_time": "0:06:01"}
{"current_steps": 70, "total_steps": 237, "loss": 1.295424222946167, "lr": 8.938539866588593e-06, "epoch": 0.89171974522293, "percentage": 29.54, "elapsed_time": "0:02:30", "remaining_time": "0:05:58"}
{"current_steps": 71, "total_steps": 237, "loss": 1.363633155822754, "lr": 8.892681800094447e-06, "epoch": 0.9044585987261147, "percentage": 29.96, "elapsed_time": "0:02:32", "remaining_time": "0:05:56"}
{"current_steps": 72, "total_steps": 237, "loss": 1.4875047206878662, "lr": 8.845976932195104e-06, "epoch": 0.9171974522292994, "percentage": 30.38, "elapsed_time": "0:02:34", "remaining_time": "0:05:54"}
{"current_steps": 73, "total_steps": 237, "loss": 1.5263020992279053, "lr": 8.798435422916425e-06, "epoch": 0.9299363057324841, "percentage": 30.8, "elapsed_time": "0:02:36", "remaining_time": "0:05:52"}
{"current_steps": 74, "total_steps": 237, "loss": 1.2648515701293945, "lr": 8.750067614284534e-06, "epoch": 0.9426751592356688, "percentage": 31.22, "elapsed_time": "0:02:38", "remaining_time": "0:05:49"}
{"current_steps": 75, "total_steps": 237, "loss": 1.4778409004211426, "lr": 8.700884028076042e-06, "epoch": 0.9554140127388535, "percentage": 31.65, "elapsed_time": "0:02:40", "remaining_time": "0:05:47"}
{"current_steps": 76, "total_steps": 237, "loss": 1.3080174922943115, "lr": 8.650895363529172e-06, "epoch": 0.9681528662420382, "percentage": 32.07, "elapsed_time": "0:02:43", "remaining_time": "0:05:45"}
{"current_steps": 77, "total_steps": 237, "loss": 1.280280351638794, "lr": 8.600112495016289e-06, "epoch": 0.9808917197452229, "percentage": 32.49, "elapsed_time": "0:02:45", "remaining_time": "0:05:43"}
{"current_steps": 78, "total_steps": 237, "loss": 1.4732855558395386, "lr": 8.548546469678311e-06, "epoch": 0.9936305732484076, "percentage": 32.91, "elapsed_time": "0:02:47", "remaining_time": "0:05:40"}
{"current_steps": 79, "total_steps": 237, "loss": 1.4152028560638428, "lr": 8.496208505021572e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:02:48", "remaining_time": "0:05:36"}
{"current_steps": 80, "total_steps": 237, "loss": 0.8762488961219788, "lr": 8.443109986477574e-06, "epoch": 1.0127388535031847, "percentage": 33.76, "elapsed_time": "0:02:50", "remaining_time": "0:05:34"}
{"current_steps": 81, "total_steps": 237, "loss": 0.6149323582649231, "lr": 8.389262464926256e-06, "epoch": 1.0254777070063694, "percentage": 34.18, "elapsed_time": "0:02:52", "remaining_time": "0:05:32"}
{"current_steps": 82, "total_steps": 237, "loss": 0.5834047198295593, "lr": 8.334677654183254e-06, "epoch": 1.0382165605095541, "percentage": 34.6, "elapsed_time": "0:02:55", "remaining_time": "0:05:30"}
{"current_steps": 83, "total_steps": 237, "loss": 0.7202398777008057, "lr": 8.279367428451703e-06, "epoch": 1.0509554140127388, "percentage": 35.02, "elapsed_time": "0:02:57", "remaining_time": "0:05:28"}
{"current_steps": 84, "total_steps": 237, "loss": 0.6720321178436279, "lr": 8.223343819739164e-06, "epoch": 1.0636942675159236, "percentage": 35.44, "elapsed_time": "0:02:59", "remaining_time": "0:05:26"}
{"current_steps": 85, "total_steps": 237, "loss": 0.649234414100647, "lr": 8.166619015240236e-06, "epoch": 1.0764331210191083, "percentage": 35.86, "elapsed_time": "0:03:01", "remaining_time": "0:05:24"}
{"current_steps": 86, "total_steps": 237, "loss": 0.5240166187286377, "lr": 8.109205354685367e-06, "epoch": 1.089171974522293, "percentage": 36.29, "elapsed_time": "0:03:03", "remaining_time": "0:05:22"}
{"current_steps": 87, "total_steps": 237, "loss": 0.6379250288009644, "lr": 8.051115327656538e-06, "epoch": 1.1019108280254777, "percentage": 36.71, "elapsed_time": "0:03:05", "remaining_time": "0:05:20"}
{"current_steps": 88, "total_steps": 237, "loss": 0.5528343915939331, "lr": 7.992361570870289e-06, "epoch": 1.1146496815286624, "percentage": 37.13, "elapsed_time": "0:03:07", "remaining_time": "0:05:17"}
{"current_steps": 89, "total_steps": 237, "loss": 0.5705242156982422, "lr": 7.932956865428792e-06, "epoch": 1.127388535031847, "percentage": 37.55, "elapsed_time": "0:03:09", "remaining_time": "0:05:15"}
{"current_steps": 90, "total_steps": 237, "loss": 0.5572481751441956, "lr": 7.872914134039485e-06, "epoch": 1.1401273885350318, "percentage": 37.97, "elapsed_time": "0:03:11", "remaining_time": "0:05:13"}
{"current_steps": 91, "total_steps": 237, "loss": 0.5195884704589844, "lr": 7.812246438203905e-06, "epoch": 1.1528662420382165, "percentage": 38.4, "elapsed_time": "0:03:13", "remaining_time": "0:05:11"}
{"current_steps": 92, "total_steps": 237, "loss": 0.6274910569190979, "lr": 7.750966975376328e-06, "epoch": 1.1656050955414012, "percentage": 38.82, "elapsed_time": "0:03:16", "remaining_time": "0:05:08"}
{"current_steps": 93, "total_steps": 237, "loss": 0.5522801876068115, "lr": 7.689089076092851e-06, "epoch": 1.178343949044586, "percentage": 39.24, "elapsed_time": "0:03:18", "remaining_time": "0:05:07"}
{"current_steps": 94, "total_steps": 237, "loss": 0.5603713393211365, "lr": 7.626626201071494e-06, "epoch": 1.1910828025477707, "percentage": 39.66, "elapsed_time": "0:03:20", "remaining_time": "0:05:04"}
{"current_steps": 95, "total_steps": 237, "loss": 0.6916147470474243, "lr": 7.563591938284012e-06, "epoch": 1.2038216560509554, "percentage": 40.08, "elapsed_time": "0:03:22", "remaining_time": "0:05:02"}
{"current_steps": 96, "total_steps": 237, "loss": 0.5662163496017456, "lr": 7.500000000000001e-06, "epoch": 1.21656050955414, "percentage": 40.51, "elapsed_time": "0:03:24", "remaining_time": "0:05:00"}
{"current_steps": 97, "total_steps": 237, "loss": 0.5646359324455261, "lr": 7.4358642198039835e-06, "epoch": 1.2292993630573248, "percentage": 40.93, "elapsed_time": "0:03:26", "remaining_time": "0:04:58"}
{"current_steps": 98, "total_steps": 237, "loss": 0.6762713193893433, "lr": 7.371198549586091e-06, "epoch": 1.2420382165605095, "percentage": 41.35, "elapsed_time": "0:03:28", "remaining_time": "0:04:55"}
{"current_steps": 99, "total_steps": 237, "loss": 0.559114933013916, "lr": 7.306017056507018e-06, "epoch": 1.2547770700636942, "percentage": 41.77, "elapsed_time": "0:03:30", "remaining_time": "0:04:53"}
{"current_steps": 100, "total_steps": 237, "loss": 0.5288341641426086, "lr": 7.240333919937893e-06, "epoch": 1.267515923566879, "percentage": 42.19, "elapsed_time": "0:03:32", "remaining_time": "0:04:51"}
{"current_steps": 101, "total_steps": 237, "loss": 0.5319011211395264, "lr": 7.174163428375748e-06, "epoch": 1.2802547770700636, "percentage": 42.62, "elapsed_time": "0:03:34", "remaining_time": "0:04:49"}
{"current_steps": 102, "total_steps": 237, "loss": 0.48553094267845154, "lr": 7.107519976335241e-06, "epoch": 1.2929936305732483, "percentage": 43.04, "elapsed_time": "0:03:36", "remaining_time": "0:04:47"}
{"current_steps": 103, "total_steps": 237, "loss": 0.5285497903823853, "lr": 7.040418061217325e-06, "epoch": 1.305732484076433, "percentage": 43.46, "elapsed_time": "0:03:38", "remaining_time": "0:04:44"}
{"current_steps": 104, "total_steps": 237, "loss": 0.5997939109802246, "lr": 6.972872280155528e-06, "epoch": 1.3184713375796178, "percentage": 43.88, "elapsed_time": "0:03:40", "remaining_time": "0:04:42"}
{"current_steps": 105, "total_steps": 237, "loss": 0.6326049566268921, "lr": 6.9048973268405375e-06, "epoch": 1.3312101910828025, "percentage": 44.3, "elapsed_time": "0:03:43", "remaining_time": "0:04:40"}
{"current_steps": 106, "total_steps": 237, "loss": 0.5815468430519104, "lr": 6.836507988323785e-06, "epoch": 1.3439490445859872, "percentage": 44.73, "elapsed_time": "0:03:45", "remaining_time": "0:04:38"}
{"current_steps": 107, "total_steps": 237, "loss": 0.5802133083343506, "lr": 6.767719141800718e-06, "epoch": 1.356687898089172, "percentage": 45.15, "elapsed_time": "0:03:47", "remaining_time": "0:04:36"}
{"current_steps": 108, "total_steps": 237, "loss": 0.6018631458282471, "lr": 6.698545751374465e-06, "epoch": 1.3694267515923566, "percentage": 45.57, "elapsed_time": "0:03:49", "remaining_time": "0:04:34"}
{"current_steps": 109, "total_steps": 237, "loss": 0.5609556436538696, "lr": 6.629002864800589e-06, "epoch": 1.3821656050955413, "percentage": 45.99, "elapsed_time": "0:03:51", "remaining_time": "0:04:31"}
{"current_steps": 110, "total_steps": 237, "loss": 0.5887218117713928, "lr": 6.55910561021365e-06, "epoch": 1.394904458598726, "percentage": 46.41, "elapsed_time": "0:03:53", "remaining_time": "0:04:29"}
{"current_steps": 111, "total_steps": 237, "loss": 0.616321325302124, "lr": 6.488869192836279e-06, "epoch": 1.4076433121019107, "percentage": 46.84, "elapsed_time": "0:03:55", "remaining_time": "0:04:27"}
{"current_steps": 112, "total_steps": 237, "loss": 0.5054444670677185, "lr": 6.418308891671484e-06, "epoch": 1.4203821656050954, "percentage": 47.26, "elapsed_time": "0:03:57", "remaining_time": "0:04:25"}
{"current_steps": 113, "total_steps": 237, "loss": 0.5750362277030945, "lr": 6.347440056178904e-06, "epoch": 1.4331210191082802, "percentage": 47.68, "elapsed_time": "0:03:59", "remaining_time": "0:04:23"}
{"current_steps": 114, "total_steps": 237, "loss": 0.5615164041519165, "lr": 6.27627810293574e-06, "epoch": 1.4458598726114649, "percentage": 48.1, "elapsed_time": "0:04:01", "remaining_time": "0:04:21"}
{"current_steps": 115, "total_steps": 237, "loss": 0.5763839483261108, "lr": 6.204838512283073e-06, "epoch": 1.4585987261146496, "percentage": 48.52, "elapsed_time": "0:04:04", "remaining_time": "0:04:18"}
{"current_steps": 116, "total_steps": 237, "loss": 0.5372281670570374, "lr": 6.133136824958334e-06, "epoch": 1.4713375796178343, "percentage": 48.95, "elapsed_time": "0:04:06", "remaining_time": "0:04:16"}
{"current_steps": 117, "total_steps": 237, "loss": 0.5346398949623108, "lr": 6.061188638714616e-06, "epoch": 1.484076433121019, "percentage": 49.37, "elapsed_time": "0:04:08", "remaining_time": "0:04:14"}
{"current_steps": 118, "total_steps": 237, "loss": 0.5711431503295898, "lr": 5.989009604927587e-06, "epoch": 1.4968152866242037, "percentage": 49.79, "elapsed_time": "0:04:10", "remaining_time": "0:04:12"}
{"current_steps": 119, "total_steps": 237, "loss": 0.5970295667648315, "lr": 5.916615425190744e-06, "epoch": 1.5095541401273884, "percentage": 50.21, "elapsed_time": "0:04:12", "remaining_time": "0:04:10"}
{"current_steps": 120, "total_steps": 237, "loss": 0.5636259317398071, "lr": 5.844021847899735e-06, "epoch": 1.5222929936305731, "percentage": 50.63, "elapsed_time": "0:04:14", "remaining_time": "0:04:08"}
{"current_steps": 121, "total_steps": 237, "loss": 0.5143004655838013, "lr": 5.771244664826512e-06, "epoch": 1.5350318471337578, "percentage": 51.05, "elapsed_time": "0:04:16", "remaining_time": "0:04:05"}
{"current_steps": 122, "total_steps": 237, "loss": 0.634333610534668, "lr": 5.698299707684031e-06, "epoch": 1.5477707006369426, "percentage": 51.48, "elapsed_time": "0:04:18", "remaining_time": "0:04:03"}
{"current_steps": 123, "total_steps": 237, "loss": 0.5898275375366211, "lr": 5.6252028446822805e-06, "epoch": 1.5605095541401273, "percentage": 51.9, "elapsed_time": "0:04:20", "remaining_time": "0:04:01"}
{"current_steps": 124, "total_steps": 237, "loss": 0.6043866872787476, "lr": 5.55196997707635e-06, "epoch": 1.573248407643312, "percentage": 52.32, "elapsed_time": "0:04:22", "remaining_time": "0:03:59"}
{"current_steps": 125, "total_steps": 237, "loss": 0.5746797919273376, "lr": 5.478617035707337e-06, "epoch": 1.5859872611464967, "percentage": 52.74, "elapsed_time": "0:04:24", "remaining_time": "0:03:57"}
{"current_steps": 126, "total_steps": 237, "loss": 0.524669885635376, "lr": 5.4051599775368e-06, "epoch": 1.5987261146496814, "percentage": 53.16, "elapsed_time": "0:04:27", "remaining_time": "0:03:55"}
{"current_steps": 127, "total_steps": 237, "loss": 0.6246596574783325, "lr": 5.33161478217552e-06, "epoch": 1.611464968152866, "percentage": 53.59, "elapsed_time": "0:04:29", "remaining_time": "0:03:53"}
{"current_steps": 128, "total_steps": 237, "loss": 0.6094903349876404, "lr": 5.257997448407366e-06, "epoch": 1.6242038216560508, "percentage": 54.01, "elapsed_time": "0:04:31", "remaining_time": "0:03:51"}
{"current_steps": 129, "total_steps": 237, "loss": 0.49196183681488037, "lr": 5.184323990708959e-06, "epoch": 1.6369426751592355, "percentage": 54.43, "elapsed_time": "0:04:33", "remaining_time": "0:03:49"}
{"current_steps": 130, "total_steps": 237, "loss": 0.6224831342697144, "lr": 5.110610435765935e-06, "epoch": 1.6496815286624202, "percentage": 54.85, "elapsed_time": "0:04:35", "remaining_time": "0:03:47"}
{"current_steps": 131, "total_steps": 237, "loss": 0.4744587242603302, "lr": 5.0368728189865624e-06, "epoch": 1.662420382165605, "percentage": 55.27, "elapsed_time": "0:04:37", "remaining_time": "0:03:44"}
{"current_steps": 132, "total_steps": 237, "loss": 0.5607740879058838, "lr": 4.9631271810134375e-06, "epoch": 1.6751592356687897, "percentage": 55.7, "elapsed_time": "0:04:40", "remaining_time": "0:03:42"}
{"current_steps": 133, "total_steps": 237, "loss": 0.47886720299720764, "lr": 4.8893895642340665e-06, "epoch": 1.6878980891719744, "percentage": 56.12, "elapsed_time": "0:04:42", "remaining_time": "0:03:40"}
{"current_steps": 134, "total_steps": 237, "loss": 0.6378889083862305, "lr": 4.815676009291044e-06, "epoch": 1.700636942675159, "percentage": 56.54, "elapsed_time": "0:04:44", "remaining_time": "0:03:38"}
{"current_steps": 135, "total_steps": 237, "loss": 0.5452113747596741, "lr": 4.742002551592635e-06, "epoch": 1.7133757961783438, "percentage": 56.96, "elapsed_time": "0:04:46", "remaining_time": "0:03:36"}
{"current_steps": 136, "total_steps": 237, "loss": 0.5272756814956665, "lr": 4.668385217824482e-06, "epoch": 1.7261146496815285, "percentage": 57.38, "elapsed_time": "0:04:48", "remaining_time": "0:03:34"}
{"current_steps": 137, "total_steps": 237, "loss": 0.6110852360725403, "lr": 4.594840022463201e-06, "epoch": 1.7388535031847132, "percentage": 57.81, "elapsed_time": "0:04:50", "remaining_time": "0:03:32"}
{"current_steps": 138, "total_steps": 237, "loss": 0.48610061407089233, "lr": 4.5213829642926635e-06, "epoch": 1.7515923566878981, "percentage": 58.23, "elapsed_time": "0:04:52", "remaining_time": "0:03:30"}
{"current_steps": 139, "total_steps": 237, "loss": 0.5987544655799866, "lr": 4.4480300229236525e-06, "epoch": 1.7643312101910829, "percentage": 58.65, "elapsed_time": "0:04:54", "remaining_time": "0:03:27"}
{"current_steps": 140, "total_steps": 237, "loss": 0.5608366131782532, "lr": 4.374797155317721e-06, "epoch": 1.7770700636942676, "percentage": 59.07, "elapsed_time": "0:04:56", "remaining_time": "0:03:25"}
{"current_steps": 141, "total_steps": 237, "loss": 0.5552262663841248, "lr": 4.30170029231597e-06, "epoch": 1.7898089171974523, "percentage": 59.49, "elapsed_time": "0:04:59", "remaining_time": "0:03:23"}
{"current_steps": 142, "total_steps": 237, "loss": 0.5241175889968872, "lr": 4.228755335173488e-06, "epoch": 1.802547770700637, "percentage": 59.92, "elapsed_time": "0:05:01", "remaining_time": "0:03:21"}
{"current_steps": 143, "total_steps": 237, "loss": 0.5550262331962585, "lr": 4.155978152100266e-06, "epoch": 1.8152866242038217, "percentage": 60.34, "elapsed_time": "0:05:03", "remaining_time": "0:03:19"}
{"current_steps": 144, "total_steps": 237, "loss": 0.6294139623641968, "lr": 4.0833845748092586e-06, "epoch": 1.8280254777070064, "percentage": 60.76, "elapsed_time": "0:05:05", "remaining_time": "0:03:17"}
{"current_steps": 145, "total_steps": 237, "loss": 0.5444466471672058, "lr": 4.010990395072414e-06, "epoch": 1.8407643312101911, "percentage": 61.18, "elapsed_time": "0:05:07", "remaining_time": "0:03:15"}
{"current_steps": 146, "total_steps": 237, "loss": 0.5602942705154419, "lr": 3.938811361285386e-06, "epoch": 1.8535031847133758, "percentage": 61.6, "elapsed_time": "0:05:09", "remaining_time": "0:03:12"}
{"current_steps": 147, "total_steps": 237, "loss": 0.69739830493927, "lr": 3.866863175041666e-06, "epoch": 1.8662420382165605, "percentage": 62.03, "elapsed_time": "0:05:11", "remaining_time": "0:03:10"}
{"current_steps": 148, "total_steps": 237, "loss": 0.6405459642410278, "lr": 3.7951614877169285e-06, "epoch": 1.8789808917197452, "percentage": 62.45, "elapsed_time": "0:05:13", "remaining_time": "0:03:08"}
{"current_steps": 149, "total_steps": 237, "loss": 0.47495120763778687, "lr": 3.7237218970642624e-06, "epoch": 1.89171974522293, "percentage": 62.87, "elapsed_time": "0:05:15", "remaining_time": "0:03:06"}
{"current_steps": 150, "total_steps": 237, "loss": 0.533926784992218, "lr": 3.6525599438210956e-06, "epoch": 1.9044585987261147, "percentage": 63.29, "elapsed_time": "0:05:17", "remaining_time": "0:03:04"}
{"current_steps": 151, "total_steps": 237, "loss": 0.5802039504051208, "lr": 3.5816911083285165e-06, "epoch": 1.9171974522292994, "percentage": 63.71, "elapsed_time": "0:05:20", "remaining_time": "0:03:02"}
{"current_steps": 152, "total_steps": 237, "loss": 0.4674309492111206, "lr": 3.511130807163724e-06, "epoch": 1.929936305732484, "percentage": 64.14, "elapsed_time": "0:05:22", "remaining_time": "0:03:00"}
{"current_steps": 153, "total_steps": 237, "loss": 0.5465418696403503, "lr": 3.440894389786352e-06, "epoch": 1.9426751592356688, "percentage": 64.56, "elapsed_time": "0:05:24", "remaining_time": "0:02:57"}
{"current_steps": 154, "total_steps": 237, "loss": 0.6482961177825928, "lr": 3.370997135199413e-06, "epoch": 1.9554140127388535, "percentage": 64.98, "elapsed_time": "0:05:26", "remaining_time": "0:02:55"}
{"current_steps": 155, "total_steps": 237, "loss": 0.6017758846282959, "lr": 3.3014542486255365e-06, "epoch": 1.9681528662420382, "percentage": 65.4, "elapsed_time": "0:05:28", "remaining_time": "0:02:53"}
{"current_steps": 156, "total_steps": 237, "loss": 0.5690503120422363, "lr": 3.2322808581992825e-06, "epoch": 1.980891719745223, "percentage": 65.82, "elapsed_time": "0:05:30", "remaining_time": "0:02:51"}
{"current_steps": 157, "total_steps": 237, "loss": 0.4827248752117157, "lr": 3.1634920116762175e-06, "epoch": 1.9936305732484076, "percentage": 66.24, "elapsed_time": "0:05:32", "remaining_time": "0:02:49"}
{"current_steps": 158, "total_steps": 237, "loss": 0.38495004177093506, "lr": 3.0951026731594634e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:05:33", "remaining_time": "0:02:46"}
{"current_steps": 159, "total_steps": 237, "loss": 0.12544472515583038, "lr": 3.0271277198444737e-06, "epoch": 2.0127388535031847, "percentage": 67.09, "elapsed_time": "0:05:35", "remaining_time": "0:02:44"}
{"current_steps": 160, "total_steps": 237, "loss": 0.16235066950321198, "lr": 2.9595819387826753e-06, "epoch": 2.0254777070063694, "percentage": 67.51, "elapsed_time": "0:05:37", "remaining_time": "0:02:42"}
{"current_steps": 161, "total_steps": 237, "loss": 0.12846337258815765, "lr": 2.89248002366476e-06, "epoch": 2.038216560509554, "percentage": 67.93, "elapsed_time": "0:05:39", "remaining_time": "0:02:40"}
{"current_steps": 162, "total_steps": 237, "loss": 0.1838989555835724, "lr": 2.8258365716242543e-06, "epoch": 2.050955414012739, "percentage": 68.35, "elapsed_time": "0:05:41", "remaining_time": "0:02:38"}
{"current_steps": 163, "total_steps": 237, "loss": 0.2500256597995758, "lr": 2.7596660800621076e-06, "epoch": 2.0636942675159236, "percentage": 68.78, "elapsed_time": "0:05:44", "remaining_time": "0:02:36"}
{"current_steps": 164, "total_steps": 237, "loss": 0.1671365201473236, "lr": 2.6939829434929834e-06, "epoch": 2.0764331210191083, "percentage": 69.2, "elapsed_time": "0:05:46", "remaining_time": "0:02:34"}
{"current_steps": 165, "total_steps": 237, "loss": 0.15608271956443787, "lr": 2.6288014504139104e-06, "epoch": 2.089171974522293, "percentage": 69.62, "elapsed_time": "0:05:48", "remaining_time": "0:02:31"}
{"current_steps": 166, "total_steps": 237, "loss": 0.11306923627853394, "lr": 2.5641357801960186e-06, "epoch": 2.1019108280254777, "percentage": 70.04, "elapsed_time": "0:05:50", "remaining_time": "0:02:29"}
{"current_steps": 167, "total_steps": 237, "loss": 0.13365235924720764, "lr": 2.5000000000000015e-06, "epoch": 2.1146496815286624, "percentage": 70.46, "elapsed_time": "0:05:52", "remaining_time": "0:02:27"}
{"current_steps": 168, "total_steps": 237, "loss": 0.09948678314685822, "lr": 2.4364080617159885e-06, "epoch": 2.127388535031847, "percentage": 70.89, "elapsed_time": "0:05:54", "remaining_time": "0:02:25"}
{"current_steps": 169, "total_steps": 237, "loss": 0.1527547836303711, "lr": 2.373373798928507e-06, "epoch": 2.140127388535032, "percentage": 71.31, "elapsed_time": "0:05:56", "remaining_time": "0:02:23"}
{"current_steps": 170, "total_steps": 237, "loss": 0.15944325923919678, "lr": 2.310910923907149e-06, "epoch": 2.1528662420382165, "percentage": 71.73, "elapsed_time": "0:05:58", "remaining_time": "0:02:21"}
{"current_steps": 171, "total_steps": 237, "loss": 0.15103012323379517, "lr": 2.249033024623672e-06, "epoch": 2.1656050955414012, "percentage": 72.15, "elapsed_time": "0:06:00", "remaining_time": "0:02:19"}
{"current_steps": 172, "total_steps": 237, "loss": 0.13296693563461304, "lr": 2.187753561796097e-06, "epoch": 2.178343949044586, "percentage": 72.57, "elapsed_time": "0:06:03", "remaining_time": "0:02:17"}
{"current_steps": 173, "total_steps": 237, "loss": 0.13463032245635986, "lr": 2.127085865960516e-06, "epoch": 2.1910828025477707, "percentage": 73.0, "elapsed_time": "0:06:05", "remaining_time": "0:02:15"}
{"current_steps": 174, "total_steps": 237, "loss": 0.12961144745349884, "lr": 2.0670431345712092e-06, "epoch": 2.2038216560509554, "percentage": 73.42, "elapsed_time": "0:06:07", "remaining_time": "0:02:12"}
{"current_steps": 175, "total_steps": 237, "loss": 0.12983323633670807, "lr": 2.0076384291297134e-06, "epoch": 2.21656050955414, "percentage": 73.84, "elapsed_time": "0:06:09", "remaining_time": "0:02:10"}
{"current_steps": 176, "total_steps": 237, "loss": 0.119496189057827, "lr": 1.9488846723434646e-06, "epoch": 2.229299363057325, "percentage": 74.26, "elapsed_time": "0:06:11", "remaining_time": "0:02:08"}
{"current_steps": 177, "total_steps": 237, "loss": 0.12940484285354614, "lr": 1.890794645314633e-06, "epoch": 2.2420382165605095, "percentage": 74.68, "elapsed_time": "0:06:13", "remaining_time": "0:02:06"}
{"current_steps": 178, "total_steps": 237, "loss": 0.1462250053882599, "lr": 1.8333809847597644e-06, "epoch": 2.254777070063694, "percentage": 75.11, "elapsed_time": "0:06:15", "remaining_time": "0:02:04"}
{"current_steps": 179, "total_steps": 237, "loss": 0.13999441266059875, "lr": 1.7766561802608374e-06, "epoch": 2.267515923566879, "percentage": 75.53, "elapsed_time": "0:06:17", "remaining_time": "0:02:02"}
{"current_steps": 180, "total_steps": 237, "loss": 0.11394088715314865, "lr": 1.7206325715483003e-06, "epoch": 2.2802547770700636, "percentage": 75.95, "elapsed_time": "0:06:19", "remaining_time": "0:02:00"}
{"current_steps": 181, "total_steps": 237, "loss": 0.09988190978765488, "lr": 1.665322345816746e-06, "epoch": 2.2929936305732483, "percentage": 76.37, "elapsed_time": "0:06:22", "remaining_time": "0:01:58"}
{"current_steps": 182, "total_steps": 237, "loss": 0.11190064251422882, "lr": 1.6107375350737437e-06, "epoch": 2.305732484076433, "percentage": 76.79, "elapsed_time": "0:06:24", "remaining_time": "0:01:56"}
{"current_steps": 183, "total_steps": 237, "loss": 0.08351559937000275, "lr": 1.556890013522428e-06, "epoch": 2.3184713375796178, "percentage": 77.22, "elapsed_time": "0:06:26", "remaining_time": "0:01:54"}
{"current_steps": 184, "total_steps": 237, "loss": 0.1370660662651062, "lr": 1.50379149497843e-06, "epoch": 2.3312101910828025, "percentage": 77.64, "elapsed_time": "0:06:28", "remaining_time": "0:01:51"}
{"current_steps": 185, "total_steps": 237, "loss": 0.08024761080741882, "lr": 1.4514535303216893e-06, "epoch": 2.343949044585987, "percentage": 78.06, "elapsed_time": "0:06:30", "remaining_time": "0:01:49"}
{"current_steps": 186, "total_steps": 237, "loss": 0.10259030014276505, "lr": 1.3998875049837141e-06, "epoch": 2.356687898089172, "percentage": 78.48, "elapsed_time": "0:06:32", "remaining_time": "0:01:47"}
{"current_steps": 187, "total_steps": 237, "loss": 0.13259188830852509, "lr": 1.3491046364708294e-06, "epoch": 2.3694267515923566, "percentage": 78.9, "elapsed_time": "0:06:34", "remaining_time": "0:01:45"}
{"current_steps": 188, "total_steps": 237, "loss": 0.12017001956701279, "lr": 1.2991159719239581e-06, "epoch": 2.3821656050955413, "percentage": 79.32, "elapsed_time": "0:06:36", "remaining_time": "0:01:43"}
{"current_steps": 189, "total_steps": 237, "loss": 0.12285889685153961, "lr": 1.249932385715467e-06, "epoch": 2.394904458598726, "percentage": 79.75, "elapsed_time": "0:06:38", "remaining_time": "0:01:41"}
{"current_steps": 190, "total_steps": 237, "loss": 0.09309563040733337, "lr": 1.2015645770835765e-06, "epoch": 2.4076433121019107, "percentage": 80.17, "elapsed_time": "0:06:40", "remaining_time": "0:01:39"}
{"current_steps": 191, "total_steps": 237, "loss": 0.11122546344995499, "lr": 1.1540230678048969e-06, "epoch": 2.4203821656050954, "percentage": 80.59, "elapsed_time": "0:06:43", "remaining_time": "0:01:37"}
{"current_steps": 192, "total_steps": 237, "loss": 0.12660224735736847, "lr": 1.1073181999055538e-06, "epoch": 2.43312101910828, "percentage": 81.01, "elapsed_time": "0:06:45", "remaining_time": "0:01:34"}
{"current_steps": 193, "total_steps": 237, "loss": 0.1464449167251587, "lr": 1.0614601334114099e-06, "epoch": 2.445859872611465, "percentage": 81.43, "elapsed_time": "0:06:47", "remaining_time": "0:01:32"}
{"current_steps": 194, "total_steps": 237, "loss": 0.09679687768220901, "lr": 1.016458844137887e-06, "epoch": 2.4585987261146496, "percentage": 81.86, "elapsed_time": "0:06:49", "remaining_time": "0:01:30"}
{"current_steps": 195, "total_steps": 237, "loss": 0.08872199058532715, "lr": 9.723241215198692e-07, "epoch": 2.4713375796178343, "percentage": 82.28, "elapsed_time": "0:06:51", "remaining_time": "0:01:28"}
{"current_steps": 196, "total_steps": 237, "loss": 0.10168588161468506, "lr": 9.290655664821296e-07, "epoch": 2.484076433121019, "percentage": 82.7, "elapsed_time": "0:06:53", "remaining_time": "0:01:26"}
{"current_steps": 197, "total_steps": 237, "loss": 0.14432820677757263, "lr": 8.866925893507805e-07, "epoch": 2.4968152866242037, "percentage": 83.12, "elapsed_time": "0:06:55", "remaining_time": "0:01:24"}
{"current_steps": 198, "total_steps": 237, "loss": 0.11949631571769714, "lr": 8.45214407806182e-07, "epoch": 2.5095541401273884, "percentage": 83.54, "elapsed_time": "0:06:57", "remaining_time": "0:01:22"}
{"current_steps": 199, "total_steps": 237, "loss": 0.11557848751544952, "lr": 8.046400448777575e-07, "epoch": 2.522292993630573, "percentage": 83.97, "elapsed_time": "0:06:59", "remaining_time": "0:01:20"}
{"current_steps": 200, "total_steps": 237, "loss": 0.10243324935436249, "lr": 7.649783269811523e-07, "epoch": 2.535031847133758, "percentage": 84.39, "elapsed_time": "0:07:01", "remaining_time": "0:01:18"}
{"current_steps": 201, "total_steps": 237, "loss": 0.11662459373474121, "lr": 7.26237881998163e-07, "epoch": 2.5477707006369426, "percentage": 84.81, "elapsed_time": "0:07:03", "remaining_time": "0:01:15"}
{"current_steps": 202, "total_steps": 237, "loss": 0.10627827048301697, "lr": 6.884271373998608e-07, "epoch": 2.5605095541401273, "percentage": 85.23, "elapsed_time": "0:07:05", "remaining_time": "0:01:13"}
{"current_steps": 203, "total_steps": 237, "loss": 0.10284646600484848, "lr": 6.515543184133e-07, "epoch": 2.573248407643312, "percentage": 85.65, "elapsed_time": "0:07:08", "remaining_time": "0:01:11"}
{"current_steps": 204, "total_steps": 237, "loss": 0.1466551274061203, "lr": 6.156274462322292e-07, "epoch": 2.5859872611464967, "percentage": 86.08, "elapsed_time": "0:07:10", "remaining_time": "0:01:09"}
{"current_steps": 205, "total_steps": 237, "loss": 0.10568629205226898, "lr": 5.806543362721945e-07, "epoch": 2.5987261146496814, "percentage": 86.5, "elapsed_time": "0:07:12", "remaining_time": "0:01:07"}
{"current_steps": 206, "total_steps": 237, "loss": 0.09872505813837051, "lr": 5.466425964703914e-07, "epoch": 2.611464968152866, "percentage": 86.92, "elapsed_time": "0:07:14", "remaining_time": "0:01:05"}
{"current_steps": 207, "total_steps": 237, "loss": 0.1210833191871643, "lr": 5.135996256306619e-07, "epoch": 2.624203821656051, "percentage": 87.34, "elapsed_time": "0:07:16", "remaining_time": "0:01:03"}
{"current_steps": 208, "total_steps": 237, "loss": 0.24636077880859375, "lr": 4.815326118139813e-07, "epoch": 2.6369426751592355, "percentage": 87.76, "elapsed_time": "0:07:18", "remaining_time": "0:01:01"}
{"current_steps": 209, "total_steps": 237, "loss": 0.07508023083209991, "lr": 4.5044853077479134e-07, "epoch": 2.6496815286624202, "percentage": 88.19, "elapsed_time": "0:07:20", "remaining_time": "0:00:59"}
{"current_steps": 210, "total_steps": 237, "loss": 0.07860185205936432, "lr": 4.203541444435211e-07, "epoch": 2.662420382165605, "percentage": 88.61, "elapsed_time": "0:07:22", "remaining_time": "0:00:56"}
{"current_steps": 211, "total_steps": 237, "loss": 0.11880528926849365, "lr": 3.9125599945560866e-07, "epoch": 2.6751592356687897, "percentage": 89.03, "elapsed_time": "0:07:24", "remaining_time": "0:00:54"}
{"current_steps": 212, "total_steps": 237, "loss": 0.1202847883105278, "lr": 3.631604257273774e-07, "epoch": 2.6878980891719744, "percentage": 89.45, "elapsed_time": "0:07:26", "remaining_time": "0:00:52"}
{"current_steps": 213, "total_steps": 237, "loss": 0.12516042590141296, "lr": 3.360735350790428e-07, "epoch": 2.700636942675159, "percentage": 89.87, "elapsed_time": "0:07:28", "remaining_time": "0:00:50"}
{"current_steps": 214, "total_steps": 237, "loss": 0.11824316531419754, "lr": 3.100012199051627e-07, "epoch": 2.713375796178344, "percentage": 90.3, "elapsed_time": "0:07:30", "remaining_time": "0:00:48"}
{"current_steps": 215, "total_steps": 237, "loss": 0.13357584178447723, "lr": 2.8494915189283325e-07, "epoch": 2.7261146496815285, "percentage": 90.72, "elapsed_time": "0:07:33", "remaining_time": "0:00:46"}
{"current_steps": 216, "total_steps": 237, "loss": 0.12523603439331055, "lr": 2.6092278078788004e-07, "epoch": 2.738853503184713, "percentage": 91.14, "elapsed_time": "0:07:35", "remaining_time": "0:00:44"}
{"current_steps": 217, "total_steps": 237, "loss": 0.14257697761058807, "lr": 2.3792733320934348e-07, "epoch": 2.7515923566878984, "percentage": 91.56, "elapsed_time": "0:07:37", "remaining_time": "0:00:42"}
{"current_steps": 218, "total_steps": 237, "loss": 0.1564294397830963, "lr": 2.1596781151249524e-07, "epoch": 2.7643312101910826, "percentage": 91.98, "elapsed_time": "0:07:39", "remaining_time": "0:00:40"}
{"current_steps": 219, "total_steps": 237, "loss": 0.10454589128494263, "lr": 1.9504899270064105e-07, "epoch": 2.777070063694268, "percentage": 92.41, "elapsed_time": "0:07:41", "remaining_time": "0:00:37"}
{"current_steps": 220, "total_steps": 237, "loss": 0.1108865737915039, "lr": 1.7517542738595071e-07, "epoch": 2.789808917197452, "percentage": 92.83, "elapsed_time": "0:07:43", "remaining_time": "0:00:35"}
{"current_steps": 221, "total_steps": 237, "loss": 0.11421318352222443, "lr": 1.5635143879952575e-07, "epoch": 2.802547770700637, "percentage": 93.25, "elapsed_time": "0:07:45", "remaining_time": "0:00:33"}
{"current_steps": 222, "total_steps": 237, "loss": 0.11534243822097778, "lr": 1.3858112185094418e-07, "epoch": 2.8152866242038215, "percentage": 93.67, "elapsed_time": "0:07:47", "remaining_time": "0:00:31"}
{"current_steps": 223, "total_steps": 237, "loss": 0.11710705608129501, "lr": 1.2186834223746612e-07, "epoch": 2.8280254777070066, "percentage": 94.09, "elapsed_time": "0:07:50", "remaining_time": "0:00:29"}
{"current_steps": 224, "total_steps": 237, "loss": 0.10814360529184341, "lr": 1.0621673560309798e-07, "epoch": 2.840764331210191, "percentage": 94.51, "elapsed_time": "0:07:52", "remaining_time": "0:00:27"}
{"current_steps": 225, "total_steps": 237, "loss": 0.10685160011053085, "lr": 9.162970674771177e-08, "epoch": 2.853503184713376, "percentage": 94.94, "elapsed_time": "0:07:54", "remaining_time": "0:00:25"}
{"current_steps": 226, "total_steps": 237, "loss": 0.09749080240726471, "lr": 7.81104288863721e-08, "epoch": 2.8662420382165603, "percentage": 95.36, "elapsed_time": "0:07:56", "remaining_time": "0:00:23"}
{"current_steps": 227, "total_steps": 237, "loss": 0.1170835793018341, "lr": 6.566184295904777e-08, "epoch": 2.8789808917197455, "percentage": 95.78, "elapsed_time": "0:07:58", "remaining_time": "0:00:21"}
{"current_steps": 228, "total_steps": 237, "loss": 0.12243887782096863, "lr": 5.4286656990847897e-08, "epoch": 2.8917197452229297, "percentage": 96.2, "elapsed_time": "0:08:00", "remaining_time": "0:00:18"}
{"current_steps": 229, "total_steps": 237, "loss": 0.09864116460084915, "lr": 4.398734550292716e-08, "epoch": 2.904458598726115, "percentage": 96.62, "elapsed_time": "0:08:02", "remaining_time": "0:00:16"}
{"current_steps": 230, "total_steps": 237, "loss": 0.09943774342536926, "lr": 3.476614897418573e-08, "epoch": 2.917197452229299, "percentage": 97.05, "elapsed_time": "0:08:04", "remaining_time": "0:00:14"}
{"current_steps": 231, "total_steps": 237, "loss": 0.11451989412307739, "lr": 2.6625073353884756e-08, "epoch": 2.9299363057324843, "percentage": 97.47, "elapsed_time": "0:08:07", "remaining_time": "0:00:12"}
{"current_steps": 232, "total_steps": 237, "loss": 0.10823914408683777, "lr": 1.9565889625275945e-08, "epoch": 2.9426751592356686, "percentage": 97.89, "elapsed_time": "0:08:09", "remaining_time": "0:00:10"}
{"current_steps": 233, "total_steps": 237, "loss": 0.09565119445323944, "lr": 1.3590133420350315e-08, "epoch": 2.9554140127388537, "percentage": 98.31, "elapsed_time": "0:08:11", "remaining_time": "0:00:08"}
{"current_steps": 234, "total_steps": 237, "loss": 0.14359764754772186, "lr": 8.699104685779835e-09, "epoch": 2.968152866242038, "percentage": 98.73, "elapsed_time": "0:08:13", "remaining_time": "0:00:06"}
{"current_steps": 235, "total_steps": 237, "loss": 0.12467635422945023, "lr": 4.89386740013198e-09, "epoch": 2.980891719745223, "percentage": 99.16, "elapsed_time": "0:08:15", "remaining_time": "0:00:04"}
{"current_steps": 236, "total_steps": 237, "loss": 0.1296227127313614, "lr": 2.1752493424148647e-09, "epoch": 2.9936305732484074, "percentage": 99.58, "elapsed_time": "0:08:17", "remaining_time": "0:00:02"}
{"current_steps": 237, "total_steps": 237, "loss": 0.056546278297901154, "lr": 5.438419120062933e-10, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:08:18", "remaining_time": "0:00:00"}
{"current_steps": 237, "total_steps": 237, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:50", "remaining_time": "0:00:00"}