deepspeed_no_offload / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
58a83be verified
{"current_steps": 1, "total_steps": 156, "loss": 1.3429, "lr": 6.25e-07, "epoch": 0.01910828025477707, "percentage": 0.64, "elapsed_time": "0:00:12", "remaining_time": "0:32:17"}
{"current_steps": 2, "total_steps": 156, "loss": 1.3616, "lr": 1.25e-06, "epoch": 0.03821656050955414, "percentage": 1.28, "elapsed_time": "0:00:20", "remaining_time": "0:25:56"}
{"current_steps": 3, "total_steps": 156, "loss": 1.296, "lr": 1.8750000000000003e-06, "epoch": 0.05732484076433121, "percentage": 1.92, "elapsed_time": "0:00:32", "remaining_time": "0:27:23"}
{"current_steps": 4, "total_steps": 156, "loss": 1.3065, "lr": 2.5e-06, "epoch": 0.07643312101910828, "percentage": 2.56, "elapsed_time": "0:00:44", "remaining_time": "0:28:13"}
{"current_steps": 5, "total_steps": 156, "loss": 1.3084, "lr": 3.125e-06, "epoch": 0.09554140127388536, "percentage": 3.21, "elapsed_time": "0:00:55", "remaining_time": "0:27:44"}
{"current_steps": 6, "total_steps": 156, "loss": 1.2615, "lr": 3.7500000000000005e-06, "epoch": 0.11464968152866242, "percentage": 3.85, "elapsed_time": "0:01:02", "remaining_time": "0:26:04"}
{"current_steps": 7, "total_steps": 156, "loss": 1.1771, "lr": 4.3750000000000005e-06, "epoch": 0.1337579617834395, "percentage": 4.49, "elapsed_time": "0:01:12", "remaining_time": "0:25:43"}
{"current_steps": 8, "total_steps": 156, "loss": 1.2099, "lr": 5e-06, "epoch": 0.15286624203821655, "percentage": 5.13, "elapsed_time": "0:01:20", "remaining_time": "0:24:43"}
{"current_steps": 9, "total_steps": 156, "loss": 1.1225, "lr": 5.625e-06, "epoch": 0.17197452229299362, "percentage": 5.77, "elapsed_time": "0:01:32", "remaining_time": "0:25:14"}
{"current_steps": 10, "total_steps": 156, "loss": 1.0774, "lr": 6.25e-06, "epoch": 0.1910828025477707, "percentage": 6.41, "elapsed_time": "0:01:41", "remaining_time": "0:24:46"}
{"current_steps": 11, "total_steps": 156, "loss": 1.0759, "lr": 6.875e-06, "epoch": 0.21019108280254778, "percentage": 7.05, "elapsed_time": "0:01:50", "remaining_time": "0:24:18"}
{"current_steps": 12, "total_steps": 156, "loss": 1.0191, "lr": 7.500000000000001e-06, "epoch": 0.22929936305732485, "percentage": 7.69, "elapsed_time": "0:02:01", "remaining_time": "0:24:22"}
{"current_steps": 13, "total_steps": 156, "loss": 1.0475, "lr": 8.125000000000001e-06, "epoch": 0.2484076433121019, "percentage": 8.33, "elapsed_time": "0:02:12", "remaining_time": "0:24:18"}
{"current_steps": 14, "total_steps": 156, "loss": 1.0031, "lr": 8.750000000000001e-06, "epoch": 0.267515923566879, "percentage": 8.97, "elapsed_time": "0:02:24", "remaining_time": "0:24:28"}
{"current_steps": 15, "total_steps": 156, "loss": 0.9644, "lr": 9.375000000000001e-06, "epoch": 0.28662420382165604, "percentage": 9.62, "elapsed_time": "0:02:36", "remaining_time": "0:24:29"}
{"current_steps": 16, "total_steps": 156, "loss": 0.958, "lr": 1e-05, "epoch": 0.3057324840764331, "percentage": 10.26, "elapsed_time": "0:02:49", "remaining_time": "0:24:41"}
{"current_steps": 17, "total_steps": 156, "loss": 0.9513, "lr": 9.998741174712534e-06, "epoch": 0.3248407643312102, "percentage": 10.9, "elapsed_time": "0:02:58", "remaining_time": "0:24:20"}
{"current_steps": 18, "total_steps": 156, "loss": 0.9529, "lr": 9.994965332706574e-06, "epoch": 0.34394904458598724, "percentage": 11.54, "elapsed_time": "0:03:06", "remaining_time": "0:23:46"}
{"current_steps": 19, "total_steps": 156, "loss": 0.9513, "lr": 9.98867437523228e-06, "epoch": 0.3630573248407643, "percentage": 12.18, "elapsed_time": "0:03:20", "remaining_time": "0:24:02"}
{"current_steps": 20, "total_steps": 156, "loss": 0.9268, "lr": 9.979871469976197e-06, "epoch": 0.3821656050955414, "percentage": 12.82, "elapsed_time": "0:03:28", "remaining_time": "0:23:37"}
{"current_steps": 21, "total_steps": 156, "loss": 0.9387, "lr": 9.968561049466214e-06, "epoch": 0.4012738853503185, "percentage": 13.46, "elapsed_time": "0:03:40", "remaining_time": "0:23:37"}
{"current_steps": 22, "total_steps": 156, "loss": 0.8954, "lr": 9.954748808839675e-06, "epoch": 0.42038216560509556, "percentage": 14.1, "elapsed_time": "0:03:53", "remaining_time": "0:23:44"}
{"current_steps": 23, "total_steps": 156, "loss": 0.8937, "lr": 9.938441702975689e-06, "epoch": 0.4394904458598726, "percentage": 14.74, "elapsed_time": "0:04:05", "remaining_time": "0:23:38"}
{"current_steps": 24, "total_steps": 156, "loss": 0.9142, "lr": 9.91964794299315e-06, "epoch": 0.4585987261146497, "percentage": 15.38, "elapsed_time": "0:04:17", "remaining_time": "0:23:34"}
{"current_steps": 25, "total_steps": 156, "loss": 0.8878, "lr": 9.898376992116179e-06, "epoch": 0.47770700636942676, "percentage": 16.03, "elapsed_time": "0:04:32", "remaining_time": "0:23:47"}
{"current_steps": 26, "total_steps": 156, "loss": 0.8914, "lr": 9.874639560909118e-06, "epoch": 0.4968152866242038, "percentage": 16.67, "elapsed_time": "0:04:42", "remaining_time": "0:23:32"}
{"current_steps": 27, "total_steps": 156, "loss": 0.918, "lr": 9.848447601883436e-06, "epoch": 0.5159235668789809, "percentage": 17.31, "elapsed_time": "0:04:55", "remaining_time": "0:23:33"}
{"current_steps": 28, "total_steps": 156, "loss": 0.9225, "lr": 9.819814303479268e-06, "epoch": 0.535031847133758, "percentage": 17.95, "elapsed_time": "0:05:05", "remaining_time": "0:23:14"}
{"current_steps": 29, "total_steps": 156, "loss": 0.8652, "lr": 9.788754083424654e-06, "epoch": 0.554140127388535, "percentage": 18.59, "elapsed_time": "0:05:22", "remaining_time": "0:23:33"}
{"current_steps": 30, "total_steps": 156, "loss": 0.8733, "lr": 9.755282581475769e-06, "epoch": 0.5732484076433121, "percentage": 19.23, "elapsed_time": "0:05:34", "remaining_time": "0:23:26"}
{"current_steps": 31, "total_steps": 156, "loss": 0.8964, "lr": 9.719416651541839e-06, "epoch": 0.5923566878980892, "percentage": 19.87, "elapsed_time": "0:05:46", "remaining_time": "0:23:16"}
{"current_steps": 32, "total_steps": 156, "loss": 0.896, "lr": 9.681174353198687e-06, "epoch": 0.6114649681528662, "percentage": 20.51, "elapsed_time": "0:05:59", "remaining_time": "0:23:14"}
{"current_steps": 33, "total_steps": 156, "loss": 0.8807, "lr": 9.640574942595195e-06, "epoch": 0.6305732484076433, "percentage": 21.15, "elapsed_time": "0:06:10", "remaining_time": "0:22:59"}
{"current_steps": 34, "total_steps": 156, "loss": 0.8396, "lr": 9.597638862757255e-06, "epoch": 0.6496815286624203, "percentage": 21.79, "elapsed_time": "0:06:21", "remaining_time": "0:22:49"}
{"current_steps": 35, "total_steps": 156, "loss": 0.8644, "lr": 9.552387733294081e-06, "epoch": 0.6687898089171974, "percentage": 22.44, "elapsed_time": "0:06:30", "remaining_time": "0:22:30"}
{"current_steps": 36, "total_steps": 156, "loss": 0.8791, "lr": 9.504844339512096e-06, "epoch": 0.6878980891719745, "percentage": 23.08, "elapsed_time": "0:06:41", "remaining_time": "0:22:18"}
{"current_steps": 37, "total_steps": 156, "loss": 0.8776, "lr": 9.45503262094184e-06, "epoch": 0.7070063694267515, "percentage": 23.72, "elapsed_time": "0:06:51", "remaining_time": "0:22:04"}
{"current_steps": 38, "total_steps": 156, "loss": 0.8911, "lr": 9.40297765928369e-06, "epoch": 0.7261146496815286, "percentage": 24.36, "elapsed_time": "0:07:00", "remaining_time": "0:21:45"}
{"current_steps": 39, "total_steps": 156, "loss": 0.8545, "lr": 9.348705665778479e-06, "epoch": 0.7452229299363057, "percentage": 25.0, "elapsed_time": "0:07:13", "remaining_time": "0:21:40"}
{"current_steps": 40, "total_steps": 156, "loss": 0.8032, "lr": 9.292243968009332e-06, "epoch": 0.7643312101910829, "percentage": 25.64, "elapsed_time": "0:07:22", "remaining_time": "0:21:22"}
{"current_steps": 41, "total_steps": 156, "loss": 0.8763, "lr": 9.233620996141421e-06, "epoch": 0.7834394904458599, "percentage": 26.28, "elapsed_time": "0:07:30", "remaining_time": "0:21:03"}
{"current_steps": 42, "total_steps": 156, "loss": 0.8522, "lr": 9.172866268606514e-06, "epoch": 0.802547770700637, "percentage": 26.92, "elapsed_time": "0:07:40", "remaining_time": "0:20:48"}
{"current_steps": 43, "total_steps": 156, "loss": 0.8872, "lr": 9.110010377239552e-06, "epoch": 0.821656050955414, "percentage": 27.56, "elapsed_time": "0:07:47", "remaining_time": "0:20:27"}
{"current_steps": 44, "total_steps": 156, "loss": 0.8448, "lr": 9.045084971874738e-06, "epoch": 0.8407643312101911, "percentage": 28.21, "elapsed_time": "0:08:00", "remaining_time": "0:20:23"}
{"current_steps": 45, "total_steps": 156, "loss": 0.8585, "lr": 8.978122744408905e-06, "epoch": 0.8598726114649682, "percentage": 28.85, "elapsed_time": "0:08:09", "remaining_time": "0:20:07"}
{"current_steps": 46, "total_steps": 156, "loss": 0.8294, "lr": 8.90915741234015e-06, "epoch": 0.8789808917197452, "percentage": 29.49, "elapsed_time": "0:08:20", "remaining_time": "0:19:55"}
{"current_steps": 47, "total_steps": 156, "loss": 0.8258, "lr": 8.838223701790057e-06, "epoch": 0.8980891719745223, "percentage": 30.13, "elapsed_time": "0:08:32", "remaining_time": "0:19:48"}
{"current_steps": 48, "total_steps": 156, "loss": 0.823, "lr": 8.765357330018056e-06, "epoch": 0.9171974522292994, "percentage": 30.77, "elapsed_time": "0:08:48", "remaining_time": "0:19:48"}
{"current_steps": 49, "total_steps": 156, "loss": 0.8533, "lr": 8.690594987436705e-06, "epoch": 0.9363057324840764, "percentage": 31.41, "elapsed_time": "0:09:01", "remaining_time": "0:19:41"}
{"current_steps": 50, "total_steps": 156, "loss": 0.8479, "lr": 8.613974319136959e-06, "epoch": 0.9554140127388535, "percentage": 32.05, "elapsed_time": "0:09:10", "remaining_time": "0:19:26"}
{"current_steps": 51, "total_steps": 156, "loss": 0.871, "lr": 8.535533905932739e-06, "epoch": 0.9745222929936306, "percentage": 32.69, "elapsed_time": "0:09:27", "remaining_time": "0:19:28"}
{"current_steps": 52, "total_steps": 156, "loss": 0.8503, "lr": 8.455313244934324e-06, "epoch": 0.9936305732484076, "percentage": 33.33, "elapsed_time": "0:09:38", "remaining_time": "0:19:16"}
{"current_steps": 53, "total_steps": 156, "loss": 1.2777, "lr": 8.373352729660373e-06, "epoch": 1.0127388535031847, "percentage": 33.97, "elapsed_time": "0:10:33", "remaining_time": "0:20:30"}
{"current_steps": 54, "total_steps": 156, "loss": 0.7338, "lr": 8.289693629698564e-06, "epoch": 1.0318471337579618, "percentage": 34.62, "elapsed_time": "0:10:43", "remaining_time": "0:20:14"}
{"current_steps": 55, "total_steps": 156, "loss": 0.7477, "lr": 8.204378069925121e-06, "epoch": 1.0509554140127388, "percentage": 35.26, "elapsed_time": "0:10:53", "remaining_time": "0:19:59"}
{"current_steps": 56, "total_steps": 156, "loss": 0.7373, "lr": 8.117449009293668e-06, "epoch": 1.070063694267516, "percentage": 35.9, "elapsed_time": "0:11:07", "remaining_time": "0:19:51"}
{"current_steps": 57, "total_steps": 156, "loss": 0.6939, "lr": 8.0289502192041e-06, "epoch": 1.089171974522293, "percentage": 36.54, "elapsed_time": "0:11:16", "remaining_time": "0:19:34"}
{"current_steps": 58, "total_steps": 156, "loss": 0.7188, "lr": 7.938926261462366e-06, "epoch": 1.10828025477707, "percentage": 37.18, "elapsed_time": "0:11:36", "remaining_time": "0:19:36"}
{"current_steps": 59, "total_steps": 156, "loss": 0.7351, "lr": 7.84742246584226e-06, "epoch": 1.127388535031847, "percentage": 37.82, "elapsed_time": "0:11:50", "remaining_time": "0:19:28"}
{"current_steps": 60, "total_steps": 156, "loss": 0.6817, "lr": 7.754484907260513e-06, "epoch": 1.1464968152866242, "percentage": 38.46, "elapsed_time": "0:11:58", "remaining_time": "0:19:09"}
{"current_steps": 61, "total_steps": 156, "loss": 0.7569, "lr": 7.660160382576683e-06, "epoch": 1.1656050955414012, "percentage": 39.1, "elapsed_time": "0:12:06", "remaining_time": "0:18:51"}
{"current_steps": 62, "total_steps": 156, "loss": 0.6861, "lr": 7.564496387029532e-06, "epoch": 1.1847133757961783, "percentage": 39.74, "elapsed_time": "0:12:18", "remaining_time": "0:18:40"}
{"current_steps": 63, "total_steps": 156, "loss": 0.7372, "lr": 7.467541090321735e-06, "epoch": 1.2038216560509554, "percentage": 40.38, "elapsed_time": "0:12:29", "remaining_time": "0:18:26"}
{"current_steps": 64, "total_steps": 156, "loss": 0.6683, "lr": 7.369343312364994e-06, "epoch": 1.2229299363057324, "percentage": 41.03, "elapsed_time": "0:12:43", "remaining_time": "0:18:17"}
{"current_steps": 65, "total_steps": 156, "loss": 0.7442, "lr": 7.269952498697734e-06, "epoch": 1.2420382165605095, "percentage": 41.67, "elapsed_time": "0:12:50", "remaining_time": "0:17:59"}
{"current_steps": 66, "total_steps": 156, "loss": 0.721, "lr": 7.169418695587791e-06, "epoch": 1.2611464968152866, "percentage": 42.31, "elapsed_time": "0:12:57", "remaining_time": "0:17:40"}
{"current_steps": 67, "total_steps": 156, "loss": 0.7401, "lr": 7.067792524832604e-06, "epoch": 1.2802547770700636, "percentage": 42.95, "elapsed_time": "0:13:09", "remaining_time": "0:17:29"}
{"current_steps": 68, "total_steps": 156, "loss": 0.689, "lr": 6.965125158269619e-06, "epoch": 1.2993630573248407, "percentage": 43.59, "elapsed_time": "0:13:18", "remaining_time": "0:17:13"}
{"current_steps": 69, "total_steps": 156, "loss": 0.7508, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:13:29", "remaining_time": "0:17:01"}
{"current_steps": 70, "total_steps": 156, "loss": 0.6699, "lr": 6.7568741204067145e-06, "epoch": 1.3375796178343948, "percentage": 44.87, "elapsed_time": "0:13:50", "remaining_time": "0:17:00"}
{"current_steps": 71, "total_steps": 156, "loss": 0.7125, "lr": 6.651395309775837e-06, "epoch": 1.356687898089172, "percentage": 45.51, "elapsed_time": "0:14:01", "remaining_time": "0:16:47"}
{"current_steps": 72, "total_steps": 156, "loss": 0.6811, "lr": 6.545084971874738e-06, "epoch": 1.3757961783439492, "percentage": 46.15, "elapsed_time": "0:14:14", "remaining_time": "0:16:36"}
{"current_steps": 73, "total_steps": 156, "loss": 0.7014, "lr": 6.437996637160086e-06, "epoch": 1.394904458598726, "percentage": 46.79, "elapsed_time": "0:14:26", "remaining_time": "0:16:25"}
{"current_steps": 74, "total_steps": 156, "loss": 0.6723, "lr": 6.330184227833376e-06, "epoch": 1.4140127388535033, "percentage": 47.44, "elapsed_time": "0:14:39", "remaining_time": "0:16:14"}
{"current_steps": 75, "total_steps": 156, "loss": 0.6753, "lr": 6.2217020306894705e-06, "epoch": 1.4331210191082802, "percentage": 48.08, "elapsed_time": "0:14:48", "remaining_time": "0:15:59"}
{"current_steps": 76, "total_steps": 156, "loss": 0.703, "lr": 6.112604669781572e-06, "epoch": 1.4522292993630574, "percentage": 48.72, "elapsed_time": "0:15:17", "remaining_time": "0:16:05"}
{"current_steps": 77, "total_steps": 156, "loss": 0.7443, "lr": 6.002947078916365e-06, "epoch": 1.4713375796178343, "percentage": 49.36, "elapsed_time": "0:15:28", "remaining_time": "0:15:52"}
{"current_steps": 78, "total_steps": 156, "loss": 0.6685, "lr": 5.892784473993184e-06, "epoch": 1.4904458598726116, "percentage": 50.0, "elapsed_time": "0:15:35", "remaining_time": "0:15:35"}
{"current_steps": 79, "total_steps": 156, "loss": 0.6591, "lr": 5.782172325201155e-06, "epoch": 1.5095541401273884, "percentage": 50.64, "elapsed_time": "0:15:43", "remaining_time": "0:15:19"}
{"current_steps": 80, "total_steps": 156, "loss": 0.6936, "lr": 5.671166329088278e-06, "epoch": 1.5286624203821657, "percentage": 51.28, "elapsed_time": "0:15:56", "remaining_time": "0:15:08"}
{"current_steps": 81, "total_steps": 156, "loss": 0.6929, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:16:02", "remaining_time": "0:14:51"}
{"current_steps": 82, "total_steps": 156, "loss": 0.7198, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:16:12", "remaining_time": "0:14:37"}
{"current_steps": 83, "total_steps": 156, "loss": 0.7355, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:16:24", "remaining_time": "0:14:26"}
{"current_steps": 84, "total_steps": 156, "loss": 0.6984, "lr": 5.224324151752575e-06, "epoch": 1.605095541401274, "percentage": 53.85, "elapsed_time": "0:16:38", "remaining_time": "0:14:16"}
{"current_steps": 85, "total_steps": 156, "loss": 0.7028, "lr": 5.112190321479026e-06, "epoch": 1.6242038216560508, "percentage": 54.49, "elapsed_time": "0:16:46", "remaining_time": "0:14:00"}
{"current_steps": 86, "total_steps": 156, "loss": 0.666, "lr": 5e-06, "epoch": 1.643312101910828, "percentage": 55.13, "elapsed_time": "0:16:56", "remaining_time": "0:13:47"}
{"current_steps": 87, "total_steps": 156, "loss": 0.7537, "lr": 4.887809678520976e-06, "epoch": 1.662420382165605, "percentage": 55.77, "elapsed_time": "0:17:05", "remaining_time": "0:13:33"}
{"current_steps": 88, "total_steps": 156, "loss": 0.7102, "lr": 4.775675848247427e-06, "epoch": 1.6815286624203822, "percentage": 56.41, "elapsed_time": "0:17:17", "remaining_time": "0:13:21"}
{"current_steps": 89, "total_steps": 156, "loss": 0.6781, "lr": 4.663654971939802e-06, "epoch": 1.700636942675159, "percentage": 57.05, "elapsed_time": "0:17:24", "remaining_time": "0:13:06"}
{"current_steps": 90, "total_steps": 156, "loss": 0.7141, "lr": 4.551803455482833e-06, "epoch": 1.7197452229299364, "percentage": 57.69, "elapsed_time": "0:17:35", "remaining_time": "0:12:53"}
{"current_steps": 91, "total_steps": 156, "loss": 0.7032, "lr": 4.4401776194834615e-06, "epoch": 1.7388535031847132, "percentage": 58.33, "elapsed_time": "0:17:45", "remaining_time": "0:12:40"}
{"current_steps": 92, "total_steps": 156, "loss": 0.7434, "lr": 4.3288336709117246e-06, "epoch": 1.7579617834394905, "percentage": 58.97, "elapsed_time": "0:17:55", "remaining_time": "0:12:28"}
{"current_steps": 93, "total_steps": 156, "loss": 0.68, "lr": 4.217827674798845e-06, "epoch": 1.7770700636942676, "percentage": 59.62, "elapsed_time": "0:18:05", "remaining_time": "0:12:15"}
{"current_steps": 94, "total_steps": 156, "loss": 0.6568, "lr": 4.107215526006818e-06, "epoch": 1.7961783439490446, "percentage": 60.26, "elapsed_time": "0:18:14", "remaining_time": "0:12:02"}
{"current_steps": 95, "total_steps": 156, "loss": 0.7393, "lr": 3.997052921083637e-06, "epoch": 1.8152866242038217, "percentage": 60.9, "elapsed_time": "0:18:25", "remaining_time": "0:11:49"}
{"current_steps": 96, "total_steps": 156, "loss": 0.6979, "lr": 3.887395330218429e-06, "epoch": 1.8343949044585988, "percentage": 61.54, "elapsed_time": "0:18:36", "remaining_time": "0:11:37"}
{"current_steps": 97, "total_steps": 156, "loss": 0.7, "lr": 3.778297969310529e-06, "epoch": 1.8535031847133758, "percentage": 62.18, "elapsed_time": "0:18:46", "remaining_time": "0:11:25"}
{"current_steps": 98, "total_steps": 156, "loss": 0.7173, "lr": 3.669815772166625e-06, "epoch": 1.872611464968153, "percentage": 62.82, "elapsed_time": "0:18:55", "remaining_time": "0:11:11"}
{"current_steps": 99, "total_steps": 156, "loss": 0.6773, "lr": 3.562003362839914e-06, "epoch": 1.89171974522293, "percentage": 63.46, "elapsed_time": "0:19:06", "remaining_time": "0:10:59"}
{"current_steps": 100, "total_steps": 156, "loss": 0.6369, "lr": 3.4549150281252635e-06, "epoch": 1.910828025477707, "percentage": 64.1, "elapsed_time": "0:19:12", "remaining_time": "0:10:45"}
{"current_steps": 101, "total_steps": 156, "loss": 0.7553, "lr": 3.3486046902241663e-06, "epoch": 1.929936305732484, "percentage": 64.74, "elapsed_time": "0:19:24", "remaining_time": "0:10:33"}
{"current_steps": 102, "total_steps": 156, "loss": 0.6749, "lr": 3.2431258795932863e-06, "epoch": 1.9490445859872612, "percentage": 65.38, "elapsed_time": "0:19:31", "remaining_time": "0:10:20"}
{"current_steps": 103, "total_steps": 156, "loss": 0.6918, "lr": 3.1385317079902743e-06, "epoch": 1.9681528662420382, "percentage": 66.03, "elapsed_time": "0:19:45", "remaining_time": "0:10:10"}
{"current_steps": 104, "total_steps": 156, "loss": 0.6841, "lr": 3.0348748417303826e-06, "epoch": 1.9872611464968153, "percentage": 66.67, "elapsed_time": "0:19:58", "remaining_time": "0:09:59"}
{"current_steps": 105, "total_steps": 156, "loss": 1.1013, "lr": 2.932207475167398e-06, "epoch": 2.0063694267515926, "percentage": 67.31, "elapsed_time": "0:20:57", "remaining_time": "0:10:10"}
{"current_steps": 106, "total_steps": 156, "loss": 0.6537, "lr": 2.83058130441221e-06, "epoch": 2.0254777070063694, "percentage": 67.95, "elapsed_time": "0:21:10", "remaining_time": "0:09:59"}
{"current_steps": 107, "total_steps": 156, "loss": 0.5645, "lr": 2.7300475013022666e-06, "epoch": 2.0445859872611467, "percentage": 68.59, "elapsed_time": "0:21:18", "remaining_time": "0:09:45"}
{"current_steps": 108, "total_steps": 156, "loss": 0.5989, "lr": 2.6306566876350072e-06, "epoch": 2.0636942675159236, "percentage": 69.23, "elapsed_time": "0:21:30", "remaining_time": "0:09:33"}
{"current_steps": 109, "total_steps": 156, "loss": 0.574, "lr": 2.532458909678266e-06, "epoch": 2.082802547770701, "percentage": 69.87, "elapsed_time": "0:21:41", "remaining_time": "0:09:21"}
{"current_steps": 110, "total_steps": 156, "loss": 0.6267, "lr": 2.43550361297047e-06, "epoch": 2.1019108280254777, "percentage": 70.51, "elapsed_time": "0:21:48", "remaining_time": "0:09:07"}
{"current_steps": 111, "total_steps": 156, "loss": 0.635, "lr": 2.339839617423318e-06, "epoch": 2.121019108280255, "percentage": 71.15, "elapsed_time": "0:22:01", "remaining_time": "0:08:55"}
{"current_steps": 112, "total_steps": 156, "loss": 0.6011, "lr": 2.245515092739488e-06, "epoch": 2.140127388535032, "percentage": 71.79, "elapsed_time": "0:22:13", "remaining_time": "0:08:43"}
{"current_steps": 113, "total_steps": 156, "loss": 0.6377, "lr": 2.1525775341577404e-06, "epoch": 2.159235668789809, "percentage": 72.44, "elapsed_time": "0:22:25", "remaining_time": "0:08:32"}
{"current_steps": 114, "total_steps": 156, "loss": 0.5621, "lr": 2.061073738537635e-06, "epoch": 2.178343949044586, "percentage": 73.08, "elapsed_time": "0:22:37", "remaining_time": "0:08:20"}
{"current_steps": 115, "total_steps": 156, "loss": 0.5837, "lr": 1.971049780795901e-06, "epoch": 2.1974522292993632, "percentage": 73.72, "elapsed_time": "0:22:45", "remaining_time": "0:08:06"}
{"current_steps": 116, "total_steps": 156, "loss": 0.5976, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:22:53", "remaining_time": "0:07:53"}
{"current_steps": 117, "total_steps": 156, "loss": 0.6231, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:23:05", "remaining_time": "0:07:41"}
{"current_steps": 118, "total_steps": 156, "loss": 0.5705, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:23:16", "remaining_time": "0:07:29"}
{"current_steps": 119, "total_steps": 156, "loss": 0.6073, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:26", "remaining_time": "0:07:17"}
{"current_steps": 120, "total_steps": 156, "loss": 0.6255, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:34", "remaining_time": "0:07:04"}
{"current_steps": 121, "total_steps": 156, "loss": 0.5905, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:41", "remaining_time": "0:06:51"}
{"current_steps": 122, "total_steps": 156, "loss": 0.5853, "lr": 1.3860256808630429e-06, "epoch": 2.3312101910828025, "percentage": 78.21, "elapsed_time": "0:23:52", "remaining_time": "0:06:39"}
{"current_steps": 123, "total_steps": 156, "loss": 0.6085, "lr": 1.3094050125632973e-06, "epoch": 2.3503184713375798, "percentage": 78.85, "elapsed_time": "0:24:06", "remaining_time": "0:06:28"}
{"current_steps": 124, "total_steps": 156, "loss": 0.5548, "lr": 1.234642669981946e-06, "epoch": 2.3694267515923566, "percentage": 79.49, "elapsed_time": "0:24:19", "remaining_time": "0:06:16"}
{"current_steps": 125, "total_steps": 156, "loss": 0.6369, "lr": 1.1617762982099446e-06, "epoch": 2.388535031847134, "percentage": 80.13, "elapsed_time": "0:24:31", "remaining_time": "0:06:04"}
{"current_steps": 126, "total_steps": 156, "loss": 0.5646, "lr": 1.0908425876598512e-06, "epoch": 2.4076433121019107, "percentage": 80.77, "elapsed_time": "0:24:40", "remaining_time": "0:05:52"}
{"current_steps": 127, "total_steps": 156, "loss": 0.6004, "lr": 1.0218772555910955e-06, "epoch": 2.426751592356688, "percentage": 81.41, "elapsed_time": "0:24:49", "remaining_time": "0:05:40"}
{"current_steps": 128, "total_steps": 156, "loss": 0.6111, "lr": 9.549150281252633e-07, "epoch": 2.445859872611465, "percentage": 82.05, "elapsed_time": "0:25:01", "remaining_time": "0:05:28"}
{"current_steps": 129, "total_steps": 156, "loss": 0.6004, "lr": 8.899896227604509e-07, "epoch": 2.464968152866242, "percentage": 82.69, "elapsed_time": "0:25:20", "remaining_time": "0:05:18"}
{"current_steps": 130, "total_steps": 156, "loss": 0.5499, "lr": 8.271337313934869e-07, "epoch": 2.484076433121019, "percentage": 83.33, "elapsed_time": "0:25:26", "remaining_time": "0:05:05"}
{"current_steps": 131, "total_steps": 156, "loss": 0.6805, "lr": 7.663790038585794e-07, "epoch": 2.5031847133757963, "percentage": 83.97, "elapsed_time": "0:25:36", "remaining_time": "0:04:53"}
{"current_steps": 132, "total_steps": 156, "loss": 0.5708, "lr": 7.077560319906696e-07, "epoch": 2.522292993630573, "percentage": 84.62, "elapsed_time": "0:25:47", "remaining_time": "0:04:41"}
{"current_steps": 133, "total_steps": 156, "loss": 0.6088, "lr": 6.512943342215234e-07, "epoch": 2.5414012738853504, "percentage": 85.26, "elapsed_time": "0:25:58", "remaining_time": "0:04:29"}
{"current_steps": 134, "total_steps": 156, "loss": 0.558, "lr": 5.9702234071631e-07, "epoch": 2.5605095541401273, "percentage": 85.9, "elapsed_time": "0:26:07", "remaining_time": "0:04:17"}
{"current_steps": 135, "total_steps": 156, "loss": 0.5846, "lr": 5.449673790581611e-07, "epoch": 2.5796178343949046, "percentage": 86.54, "elapsed_time": "0:26:15", "remaining_time": "0:04:05"}
{"current_steps": 136, "total_steps": 156, "loss": 0.5835, "lr": 4.951556604879049e-07, "epoch": 2.5987261146496814, "percentage": 87.18, "elapsed_time": "0:26:26", "remaining_time": "0:03:53"}
{"current_steps": 137, "total_steps": 156, "loss": 0.5937, "lr": 4.4761226670592074e-07, "epoch": 2.6178343949044587, "percentage": 87.82, "elapsed_time": "0:26:33", "remaining_time": "0:03:41"}
{"current_steps": 138, "total_steps": 156, "loss": 0.5975, "lr": 4.0236113724274716e-07, "epoch": 2.6369426751592355, "percentage": 88.46, "elapsed_time": "0:26:42", "remaining_time": "0:03:28"}
{"current_steps": 139, "total_steps": 156, "loss": 0.5917, "lr": 3.5942505740480583e-07, "epoch": 2.656050955414013, "percentage": 89.1, "elapsed_time": "0:26:52", "remaining_time": "0:03:17"}
{"current_steps": 140, "total_steps": 156, "loss": 0.58, "lr": 3.18825646801314e-07, "epoch": 2.6751592356687897, "percentage": 89.74, "elapsed_time": "0:27:00", "remaining_time": "0:03:05"}
{"current_steps": 141, "total_steps": 156, "loss": 0.6181, "lr": 2.8058334845816214e-07, "epoch": 2.694267515923567, "percentage": 90.38, "elapsed_time": "0:27:10", "remaining_time": "0:02:53"}
{"current_steps": 142, "total_steps": 156, "loss": 0.6212, "lr": 2.447174185242324e-07, "epoch": 2.713375796178344, "percentage": 91.03, "elapsed_time": "0:27:19", "remaining_time": "0:02:41"}
{"current_steps": 143, "total_steps": 156, "loss": 0.6067, "lr": 2.1124591657534776e-07, "epoch": 2.732484076433121, "percentage": 91.67, "elapsed_time": "0:27:32", "remaining_time": "0:02:30"}
{"current_steps": 144, "total_steps": 156, "loss": 0.545, "lr": 1.801856965207338e-07, "epoch": 2.7515923566878984, "percentage": 92.31, "elapsed_time": "0:27:42", "remaining_time": "0:02:18"}
{"current_steps": 145, "total_steps": 156, "loss": 0.5746, "lr": 1.5155239811656562e-07, "epoch": 2.770700636942675, "percentage": 92.95, "elapsed_time": "0:27:50", "remaining_time": "0:02:06"}
{"current_steps": 146, "total_steps": 156, "loss": 0.6175, "lr": 1.253604390908819e-07, "epoch": 2.789808917197452, "percentage": 93.59, "elapsed_time": "0:28:05", "remaining_time": "0:01:55"}
{"current_steps": 147, "total_steps": 156, "loss": 0.6413, "lr": 1.0162300788382263e-07, "epoch": 2.8089171974522293, "percentage": 94.23, "elapsed_time": "0:28:17", "remaining_time": "0:01:43"}
{"current_steps": 148, "total_steps": 156, "loss": 0.5595, "lr": 8.035205700685167e-08, "epoch": 2.8280254777070066, "percentage": 94.87, "elapsed_time": "0:28:28", "remaining_time": "0:01:32"}
{"current_steps": 149, "total_steps": 156, "loss": 0.5932, "lr": 6.15582970243117e-08, "epoch": 2.8471337579617835, "percentage": 95.51, "elapsed_time": "0:28:53", "remaining_time": "0:01:21"}
{"current_steps": 150, "total_steps": 156, "loss": 0.583, "lr": 4.52511911603265e-08, "epoch": 2.8662420382165603, "percentage": 96.15, "elapsed_time": "0:29:06", "remaining_time": "0:01:09"}
{"current_steps": 151, "total_steps": 156, "loss": 0.5961, "lr": 3.143895053378698e-08, "epoch": 2.8853503184713376, "percentage": 96.79, "elapsed_time": "0:29:13", "remaining_time": "0:00:58"}
{"current_steps": 152, "total_steps": 156, "loss": 0.5726, "lr": 2.012853002380466e-08, "epoch": 2.904458598726115, "percentage": 97.44, "elapsed_time": "0:29:25", "remaining_time": "0:00:46"}
{"current_steps": 153, "total_steps": 156, "loss": 0.6533, "lr": 1.132562476771959e-08, "epoch": 2.9235668789808917, "percentage": 98.08, "elapsed_time": "0:29:55", "remaining_time": "0:00:35"}
{"current_steps": 154, "total_steps": 156, "loss": 0.5776, "lr": 5.034667293427053e-09, "epoch": 2.9426751592356686, "percentage": 98.72, "elapsed_time": "0:30:04", "remaining_time": "0:00:23"}
{"current_steps": 155, "total_steps": 156, "loss": 0.5784, "lr": 1.2588252874673469e-09, "epoch": 2.961783439490446, "percentage": 99.36, "elapsed_time": "0:30:11", "remaining_time": "0:00:11"}
{"current_steps": 156, "total_steps": 156, "loss": 0.6064, "lr": 0.0, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:30:19", "remaining_time": "0:00:00"}
{"current_steps": 156, "total_steps": 156, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:31:50", "remaining_time": "0:00:00"}