taskmaster2-8ep / trainer_log.jsonl
penfever's picture
Model save
ad6cf29 verified
{"current_steps": 5, "total_steps": 785, "loss": 0.7567, "lr": 2.0253164556962026e-06, "epoch": 0.032, "percentage": 0.64, "elapsed_time": "0:01:57", "remaining_time": "5:06:10"}
{"current_steps": 10, "total_steps": 785, "loss": 0.7794, "lr": 4.556962025316456e-06, "epoch": 0.064, "percentage": 1.27, "elapsed_time": "0:03:53", "remaining_time": "5:01:57"}
{"current_steps": 15, "total_steps": 785, "loss": 0.6953, "lr": 7.08860759493671e-06, "epoch": 0.096, "percentage": 1.91, "elapsed_time": "0:05:44", "remaining_time": "4:54:56"}
{"current_steps": 20, "total_steps": 785, "loss": 0.6589, "lr": 9.620253164556963e-06, "epoch": 0.128, "percentage": 2.55, "elapsed_time": "0:07:34", "remaining_time": "4:49:40"}
{"current_steps": 25, "total_steps": 785, "loss": 0.6197, "lr": 1.2151898734177216e-05, "epoch": 0.16, "percentage": 3.18, "elapsed_time": "0:09:26", "remaining_time": "4:47:04"}
{"current_steps": 30, "total_steps": 785, "loss": 0.6075, "lr": 1.468354430379747e-05, "epoch": 0.192, "percentage": 3.82, "elapsed_time": "0:11:13", "remaining_time": "4:42:39"}
{"current_steps": 35, "total_steps": 785, "loss": 0.5811, "lr": 1.7215189873417723e-05, "epoch": 0.224, "percentage": 4.46, "elapsed_time": "0:13:04", "remaining_time": "4:40:09"}
{"current_steps": 40, "total_steps": 785, "loss": 0.5498, "lr": 1.974683544303798e-05, "epoch": 0.256, "percentage": 5.1, "elapsed_time": "0:14:49", "remaining_time": "4:36:14"}
{"current_steps": 45, "total_steps": 785, "loss": 0.5237, "lr": 2.2278481012658228e-05, "epoch": 0.288, "percentage": 5.73, "elapsed_time": "0:16:32", "remaining_time": "4:32:07"}
{"current_steps": 50, "total_steps": 785, "loss": 0.5187, "lr": 2.481012658227848e-05, "epoch": 0.32, "percentage": 6.37, "elapsed_time": "0:18:23", "remaining_time": "4:30:15"}
{"current_steps": 55, "total_steps": 785, "loss": 0.5075, "lr": 2.7341772151898737e-05, "epoch": 0.352, "percentage": 7.01, "elapsed_time": "0:20:14", "remaining_time": "4:28:43"}
{"current_steps": 60, "total_steps": 785, "loss": 0.4896, "lr": 2.987341772151899e-05, "epoch": 0.384, "percentage": 7.64, "elapsed_time": "0:22:02", "remaining_time": "4:26:14"}
{"current_steps": 65, "total_steps": 785, "loss": 0.5092, "lr": 3.240506329113924e-05, "epoch": 0.416, "percentage": 8.28, "elapsed_time": "0:23:57", "remaining_time": "4:25:24"}
{"current_steps": 70, "total_steps": 785, "loss": 0.4782, "lr": 3.49367088607595e-05, "epoch": 0.448, "percentage": 8.92, "elapsed_time": "0:25:39", "remaining_time": "4:22:09"}
{"current_steps": 75, "total_steps": 785, "loss": 0.4919, "lr": 3.746835443037975e-05, "epoch": 0.48, "percentage": 9.55, "elapsed_time": "0:27:25", "remaining_time": "4:19:33"}
{"current_steps": 80, "total_steps": 785, "loss": 0.4723, "lr": 4e-05, "epoch": 0.512, "percentage": 10.19, "elapsed_time": "0:29:20", "remaining_time": "4:18:32"}
{"current_steps": 85, "total_steps": 785, "loss": 0.4625, "lr": 3.999504991751045e-05, "epoch": 0.544, "percentage": 10.83, "elapsed_time": "0:31:12", "remaining_time": "4:17:04"}
{"current_steps": 90, "total_steps": 785, "loss": 0.4583, "lr": 3.9980202120373464e-05, "epoch": 0.576, "percentage": 11.46, "elapsed_time": "0:32:57", "remaining_time": "4:14:34"}
{"current_steps": 95, "total_steps": 785, "loss": 0.4651, "lr": 3.995546395837111e-05, "epoch": 0.608, "percentage": 12.1, "elapsed_time": "0:34:40", "remaining_time": "4:11:54"}
{"current_steps": 100, "total_steps": 785, "loss": 0.4522, "lr": 3.992084767709763e-05, "epoch": 0.64, "percentage": 12.74, "elapsed_time": "0:36:27", "remaining_time": "4:09:43"}
{"current_steps": 105, "total_steps": 785, "loss": 0.4475, "lr": 3.987637041189781e-05, "epoch": 0.672, "percentage": 13.38, "elapsed_time": "0:38:22", "remaining_time": "4:08:28"}
{"current_steps": 110, "total_steps": 785, "loss": 0.4461, "lr": 3.982205417938482e-05, "epoch": 0.704, "percentage": 14.01, "elapsed_time": "0:40:19", "remaining_time": "4:07:24"}
{"current_steps": 115, "total_steps": 785, "loss": 0.4432, "lr": 3.975792586654179e-05, "epoch": 0.736, "percentage": 14.65, "elapsed_time": "0:42:04", "remaining_time": "4:05:10"}
{"current_steps": 120, "total_steps": 785, "loss": 0.4506, "lr": 3.968401721741259e-05, "epoch": 0.768, "percentage": 15.29, "elapsed_time": "0:43:54", "remaining_time": "4:03:19"}
{"current_steps": 125, "total_steps": 785, "loss": 0.4472, "lr": 3.960036481738819e-05, "epoch": 0.8, "percentage": 15.92, "elapsed_time": "0:45:49", "remaining_time": "4:01:55"}
{"current_steps": 130, "total_steps": 785, "loss": 0.4518, "lr": 3.950701007509667e-05, "epoch": 0.832, "percentage": 16.56, "elapsed_time": "0:47:37", "remaining_time": "3:59:55"}
{"current_steps": 135, "total_steps": 785, "loss": 0.4548, "lr": 3.940399920190552e-05, "epoch": 0.864, "percentage": 17.2, "elapsed_time": "0:49:28", "remaining_time": "3:58:14"}
{"current_steps": 140, "total_steps": 785, "loss": 0.4363, "lr": 3.92913831890467e-05, "epoch": 0.896, "percentage": 17.83, "elapsed_time": "0:51:13", "remaining_time": "3:56:00"}
{"current_steps": 145, "total_steps": 785, "loss": 0.4187, "lr": 3.916921778237556e-05, "epoch": 0.928, "percentage": 18.47, "elapsed_time": "0:53:05", "remaining_time": "3:54:19"}
{"current_steps": 150, "total_steps": 785, "loss": 0.4305, "lr": 3.903756345477612e-05, "epoch": 0.96, "percentage": 19.11, "elapsed_time": "0:54:51", "remaining_time": "3:52:14"}
{"current_steps": 155, "total_steps": 785, "loss": 0.4237, "lr": 3.889648537622657e-05, "epoch": 0.992, "percentage": 19.75, "elapsed_time": "0:56:42", "remaining_time": "3:50:29"}
{"current_steps": 160, "total_steps": 785, "loss": 0.431, "lr": 3.874605338153952e-05, "epoch": 1.0192, "percentage": 20.38, "elapsed_time": "0:58:17", "remaining_time": "3:47:41"}
{"current_steps": 165, "total_steps": 785, "loss": 0.4317, "lr": 3.8586341935793265e-05, "epoch": 1.0512, "percentage": 21.02, "elapsed_time": "1:00:05", "remaining_time": "3:45:48"}
{"current_steps": 170, "total_steps": 785, "loss": 0.429, "lr": 3.841743009747089e-05, "epoch": 1.0832, "percentage": 21.66, "elapsed_time": "1:01:52", "remaining_time": "3:43:49"}
{"current_steps": 175, "total_steps": 785, "loss": 0.4194, "lr": 3.8239401479325714e-05, "epoch": 1.1152, "percentage": 22.29, "elapsed_time": "1:03:45", "remaining_time": "3:42:13"}
{"current_steps": 180, "total_steps": 785, "loss": 0.4215, "lr": 3.8052344206992276e-05, "epoch": 1.1472, "percentage": 22.93, "elapsed_time": "1:05:31", "remaining_time": "3:40:14"}
{"current_steps": 185, "total_steps": 785, "loss": 0.4164, "lr": 3.7856350875363396e-05, "epoch": 1.1792, "percentage": 23.57, "elapsed_time": "1:07:15", "remaining_time": "3:38:07"}
{"current_steps": 190, "total_steps": 785, "loss": 0.4213, "lr": 3.765151850275497e-05, "epoch": 1.2112, "percentage": 24.2, "elapsed_time": "1:09:03", "remaining_time": "3:36:16"}
{"current_steps": 195, "total_steps": 785, "loss": 0.4156, "lr": 3.7437948482881104e-05, "epoch": 1.2432, "percentage": 24.84, "elapsed_time": "1:10:52", "remaining_time": "3:34:27"}
{"current_steps": 200, "total_steps": 785, "loss": 0.421, "lr": 3.721574653466336e-05, "epoch": 1.2752, "percentage": 25.48, "elapsed_time": "1:12:38", "remaining_time": "3:32:28"}
{"current_steps": 205, "total_steps": 785, "loss": 0.4152, "lr": 3.698502264989903e-05, "epoch": 1.3072, "percentage": 26.11, "elapsed_time": "1:14:36", "remaining_time": "3:31:06"}
{"current_steps": 210, "total_steps": 785, "loss": 0.4312, "lr": 3.674589103881432e-05, "epoch": 1.3392, "percentage": 26.75, "elapsed_time": "1:16:34", "remaining_time": "3:29:41"}
{"current_steps": 215, "total_steps": 785, "loss": 0.4268, "lr": 3.64984700735293e-05, "epoch": 1.3712, "percentage": 27.39, "elapsed_time": "1:18:20", "remaining_time": "3:27:41"}
{"current_steps": 220, "total_steps": 785, "loss": 0.4154, "lr": 3.624288222946273e-05, "epoch": 1.4032, "percentage": 28.03, "elapsed_time": "1:20:10", "remaining_time": "3:25:54"}
{"current_steps": 225, "total_steps": 785, "loss": 0.4217, "lr": 3.597925402470578e-05, "epoch": 1.4352, "percentage": 28.66, "elapsed_time": "1:21:59", "remaining_time": "3:24:03"}
{"current_steps": 230, "total_steps": 785, "loss": 0.4207, "lr": 3.570771595739445e-05, "epoch": 1.4672, "percentage": 29.3, "elapsed_time": "1:23:51", "remaining_time": "3:22:21"}
{"current_steps": 235, "total_steps": 785, "loss": 0.4161, "lr": 3.5428402441111964e-05, "epoch": 1.4992, "percentage": 29.94, "elapsed_time": "1:25:29", "remaining_time": "3:20:05"}
{"current_steps": 240, "total_steps": 785, "loss": 0.4152, "lr": 3.5141451738352936e-05, "epoch": 1.5312000000000001, "percentage": 30.57, "elapsed_time": "1:27:27", "remaining_time": "3:18:36"}
{"current_steps": 245, "total_steps": 785, "loss": 0.415, "lr": 3.4847005892082266e-05, "epoch": 1.5632000000000001, "percentage": 31.21, "elapsed_time": "1:29:11", "remaining_time": "3:16:35"}
{"current_steps": 250, "total_steps": 785, "loss": 0.4301, "lr": 3.454521065542273e-05, "epoch": 1.5952, "percentage": 31.85, "elapsed_time": "1:30:55", "remaining_time": "3:14:34"}
{"current_steps": 255, "total_steps": 785, "loss": 0.4155, "lr": 3.423621541950597e-05, "epoch": 1.6272, "percentage": 32.48, "elapsed_time": "1:32:45", "remaining_time": "3:12:46"}
{"current_steps": 260, "total_steps": 785, "loss": 0.41, "lr": 3.3920173139522664e-05, "epoch": 1.6592, "percentage": 33.12, "elapsed_time": "1:34:39", "remaining_time": "3:11:08"}
{"current_steps": 265, "total_steps": 785, "loss": 0.415, "lr": 3.35972402590084e-05, "epoch": 1.6912, "percentage": 33.76, "elapsed_time": "1:36:23", "remaining_time": "3:09:09"}
{"current_steps": 270, "total_steps": 785, "loss": 0.4045, "lr": 3.326757663240291e-05, "epoch": 1.7231999999999998, "percentage": 34.39, "elapsed_time": "1:38:16", "remaining_time": "3:07:26"}
{"current_steps": 275, "total_steps": 785, "loss": 0.4091, "lr": 3.293134544592073e-05, "epoch": 1.7551999999999999, "percentage": 35.03, "elapsed_time": "1:39:57", "remaining_time": "3:05:23"}
{"current_steps": 280, "total_steps": 785, "loss": 0.4108, "lr": 3.258871313677274e-05, "epoch": 1.7872, "percentage": 35.67, "elapsed_time": "1:41:58", "remaining_time": "3:03:54"}
{"current_steps": 285, "total_steps": 785, "loss": 0.4042, "lr": 3.2239849310778316e-05, "epoch": 1.8192, "percentage": 36.31, "elapsed_time": "1:43:39", "remaining_time": "3:01:51"}
{"current_steps": 290, "total_steps": 785, "loss": 0.4058, "lr": 3.188492665840909e-05, "epoch": 1.8512, "percentage": 36.94, "elapsed_time": "1:45:23", "remaining_time": "2:59:53"}
{"current_steps": 295, "total_steps": 785, "loss": 0.4185, "lr": 3.1524120869305726e-05, "epoch": 1.8832, "percentage": 37.58, "elapsed_time": "1:47:13", "remaining_time": "2:58:06"}
{"current_steps": 300, "total_steps": 785, "loss": 0.4115, "lr": 3.11576105453101e-05, "epoch": 1.9152, "percentage": 38.22, "elapsed_time": "1:48:54", "remaining_time": "2:56:04"}
{"current_steps": 305, "total_steps": 785, "loss": 0.4114, "lr": 3.0785577112055916e-05, "epoch": 1.9472, "percentage": 38.85, "elapsed_time": "1:50:45", "remaining_time": "2:54:18"}
{"current_steps": 310, "total_steps": 785, "loss": 0.4222, "lr": 3.040820472916153e-05, "epoch": 1.9792, "percentage": 39.49, "elapsed_time": "1:52:26", "remaining_time": "2:52:17"}
{"current_steps": 315, "total_steps": 785, "loss": 0.41, "lr": 3.002568019906939e-05, "epoch": 2.0064, "percentage": 40.13, "elapsed_time": "1:53:51", "remaining_time": "2:49:52"}
{"current_steps": 320, "total_steps": 785, "loss": 0.4129, "lr": 2.963819287457733e-05, "epoch": 2.0384, "percentage": 40.76, "elapsed_time": "1:55:34", "remaining_time": "2:47:56"}
{"current_steps": 325, "total_steps": 785, "loss": 0.4019, "lr": 2.924593456510733e-05, "epoch": 2.0704, "percentage": 41.4, "elapsed_time": "1:57:24", "remaining_time": "2:46:10"}
{"current_steps": 330, "total_steps": 785, "loss": 0.3927, "lr": 2.8849099441758306e-05, "epoch": 2.1024, "percentage": 42.04, "elapsed_time": "1:59:07", "remaining_time": "2:44:15"}
{"current_steps": 335, "total_steps": 785, "loss": 0.3994, "lr": 2.844788394118979e-05, "epoch": 2.1344, "percentage": 42.68, "elapsed_time": "2:00:50", "remaining_time": "2:42:19"}
{"current_steps": 340, "total_steps": 785, "loss": 0.4016, "lr": 2.8042486668384164e-05, "epoch": 2.1664, "percentage": 43.31, "elapsed_time": "2:02:34", "remaining_time": "2:40:26"}
{"current_steps": 345, "total_steps": 785, "loss": 0.4001, "lr": 2.7633108298335582e-05, "epoch": 2.1984, "percentage": 43.95, "elapsed_time": "2:04:19", "remaining_time": "2:38:33"}
{"current_steps": 350, "total_steps": 785, "loss": 0.3948, "lr": 2.721995147671416e-05, "epoch": 2.2304, "percentage": 44.59, "elapsed_time": "2:06:00", "remaining_time": "2:36:36"}
{"current_steps": 355, "total_steps": 785, "loss": 0.3934, "lr": 2.68032207195547e-05, "epoch": 2.2624, "percentage": 45.22, "elapsed_time": "2:07:50", "remaining_time": "2:34:51"}
{"current_steps": 360, "total_steps": 785, "loss": 0.3937, "lr": 2.6383122312019604e-05, "epoch": 2.2944, "percentage": 45.86, "elapsed_time": "2:09:38", "remaining_time": "2:33:02"}
{"current_steps": 365, "total_steps": 785, "loss": 0.4013, "lr": 2.595986420628597e-05, "epoch": 2.3264, "percentage": 46.5, "elapsed_time": "2:11:24", "remaining_time": "2:31:12"}
{"current_steps": 370, "total_steps": 785, "loss": 0.4004, "lr": 2.5533655918607573e-05, "epoch": 2.3584, "percentage": 47.13, "elapsed_time": "2:13:14", "remaining_time": "2:29:26"}
{"current_steps": 375, "total_steps": 785, "loss": 0.3997, "lr": 2.510470842560259e-05, "epoch": 2.3904, "percentage": 47.77, "elapsed_time": "2:15:05", "remaining_time": "2:27:42"}
{"current_steps": 380, "total_steps": 785, "loss": 0.4004, "lr": 2.467323405981841e-05, "epoch": 2.4224, "percentage": 48.41, "elapsed_time": "2:16:51", "remaining_time": "2:25:51"}
{"current_steps": 385, "total_steps": 785, "loss": 0.3962, "lr": 2.423944640462533e-05, "epoch": 2.4544, "percentage": 49.04, "elapsed_time": "2:18:42", "remaining_time": "2:24:06"}
{"current_steps": 390, "total_steps": 785, "loss": 0.3975, "lr": 2.3803560188490968e-05, "epoch": 2.4864, "percentage": 49.68, "elapsed_time": "2:20:34", "remaining_time": "2:22:22"}
{"current_steps": 395, "total_steps": 785, "loss": 0.3978, "lr": 2.336579117868789e-05, "epoch": 2.5183999999999997, "percentage": 50.32, "elapsed_time": "2:22:18", "remaining_time": "2:20:30"}
{"current_steps": 400, "total_steps": 785, "loss": 0.3947, "lr": 2.292635607448711e-05, "epoch": 2.5504, "percentage": 50.96, "elapsed_time": "2:24:04", "remaining_time": "2:18:40"}
{"current_steps": 405, "total_steps": 785, "loss": 0.4058, "lr": 2.248547239989008e-05, "epoch": 2.5824, "percentage": 51.59, "elapsed_time": "2:25:57", "remaining_time": "2:16:56"}
{"current_steps": 410, "total_steps": 785, "loss": 0.4028, "lr": 2.204335839595255e-05, "epoch": 2.6144, "percentage": 52.23, "elapsed_time": "2:27:46", "remaining_time": "2:15:09"}
{"current_steps": 415, "total_steps": 785, "loss": 0.3977, "lr": 2.1600232912753452e-05, "epoch": 2.6464, "percentage": 52.87, "elapsed_time": "2:29:33", "remaining_time": "2:13:20"}
{"current_steps": 420, "total_steps": 785, "loss": 0.4036, "lr": 2.1156315301062293e-05, "epoch": 2.6784, "percentage": 53.5, "elapsed_time": "2:31:15", "remaining_time": "2:11:27"}
{"current_steps": 425, "total_steps": 785, "loss": 0.3979, "lr": 2.0711825303758712e-05, "epoch": 2.7104, "percentage": 54.14, "elapsed_time": "2:33:04", "remaining_time": "2:09:39"}
{"current_steps": 430, "total_steps": 785, "loss": 0.3976, "lr": 2.0266982947057962e-05, "epoch": 2.7424, "percentage": 54.78, "elapsed_time": "2:34:54", "remaining_time": "2:07:53"}
{"current_steps": 435, "total_steps": 785, "loss": 0.391, "lr": 1.9822008431596083e-05, "epoch": 2.7744, "percentage": 55.41, "elapsed_time": "2:36:45", "remaining_time": "2:06:07"}
{"current_steps": 440, "total_steps": 785, "loss": 0.3926, "lr": 1.937712202342881e-05, "epoch": 2.8064, "percentage": 56.05, "elapsed_time": "2:38:41", "remaining_time": "2:04:26"}
{"current_steps": 445, "total_steps": 785, "loss": 0.4027, "lr": 1.8932543944998037e-05, "epoch": 2.8384, "percentage": 56.69, "elapsed_time": "2:40:30", "remaining_time": "2:02:37"}
{"current_steps": 450, "total_steps": 785, "loss": 0.3976, "lr": 1.8488494266119877e-05, "epoch": 2.8704, "percentage": 57.32, "elapsed_time": "2:42:10", "remaining_time": "2:00:43"}
{"current_steps": 455, "total_steps": 785, "loss": 0.3873, "lr": 1.804519279504834e-05, "epoch": 2.9024, "percentage": 57.96, "elapsed_time": "2:43:57", "remaining_time": "1:58:54"}
{"current_steps": 460, "total_steps": 785, "loss": 0.3965, "lr": 1.7602858969668365e-05, "epoch": 2.9344, "percentage": 58.6, "elapsed_time": "2:45:45", "remaining_time": "1:57:06"}
{"current_steps": 465, "total_steps": 785, "loss": 0.3926, "lr": 1.716171174887231e-05, "epoch": 2.9664, "percentage": 59.24, "elapsed_time": "2:47:30", "remaining_time": "1:55:16"}
{"current_steps": 470, "total_steps": 785, "loss": 0.3944, "lr": 1.6721969504173484e-05, "epoch": 2.9984, "percentage": 59.87, "elapsed_time": "2:49:18", "remaining_time": "1:53:28"}
{"current_steps": 475, "total_steps": 785, "loss": 0.3944, "lr": 1.628384991161041e-05, "epoch": 3.0256, "percentage": 60.51, "elapsed_time": "2:50:49", "remaining_time": "1:51:29"}
{"current_steps": 480, "total_steps": 785, "loss": 0.3951, "lr": 1.5847569843995452e-05, "epoch": 3.0576, "percentage": 61.15, "elapsed_time": "2:52:33", "remaining_time": "1:49:38"}
{"current_steps": 485, "total_steps": 785, "loss": 0.3832, "lr": 1.5413345263560922e-05, "epoch": 3.0896, "percentage": 61.78, "elapsed_time": "2:54:12", "remaining_time": "1:47:45"}
{"current_steps": 490, "total_steps": 785, "loss": 0.3882, "lr": 1.4981391115056032e-05, "epoch": 3.1216, "percentage": 62.42, "elapsed_time": "2:55:58", "remaining_time": "1:45:56"}
{"current_steps": 495, "total_steps": 785, "loss": 0.3931, "lr": 1.455192121934748e-05, "epoch": 3.1536, "percentage": 63.06, "elapsed_time": "2:57:45", "remaining_time": "1:44:08"}
{"current_steps": 500, "total_steps": 785, "loss": 0.3919, "lr": 1.4125148167576303e-05, "epoch": 3.1856, "percentage": 63.69, "elapsed_time": "2:59:18", "remaining_time": "1:42:12"}
{"current_steps": 505, "total_steps": 785, "loss": 0.3912, "lr": 1.3701283215923563e-05, "epoch": 3.2176, "percentage": 64.33, "elapsed_time": "3:01:05", "remaining_time": "1:40:24"}
{"current_steps": 510, "total_steps": 785, "loss": 0.3857, "lr": 1.328053618103677e-05, "epoch": 3.2496, "percentage": 64.97, "elapsed_time": "3:03:01", "remaining_time": "1:38:41"}
{"current_steps": 515, "total_steps": 785, "loss": 0.3884, "lr": 1.2863115336168916e-05, "epoch": 3.2816, "percentage": 65.61, "elapsed_time": "3:04:48", "remaining_time": "1:36:53"}
{"current_steps": 520, "total_steps": 785, "loss": 0.3929, "lr": 1.2449227308081509e-05, "epoch": 3.3136, "percentage": 66.24, "elapsed_time": "3:06:35", "remaining_time": "1:35:05"}
{"current_steps": 525, "total_steps": 785, "loss": 0.3775, "lr": 1.2039076974762587e-05, "epoch": 3.3456, "percentage": 66.88, "elapsed_time": "3:08:23", "remaining_time": "1:33:17"}
{"current_steps": 530, "total_steps": 785, "loss": 0.3767, "lr": 1.163286736401044e-05, "epoch": 3.3776, "percentage": 67.52, "elapsed_time": "3:10:08", "remaining_time": "1:31:29"}
{"current_steps": 535, "total_steps": 785, "loss": 0.3878, "lr": 1.123079955293322e-05, "epoch": 3.4096, "percentage": 68.15, "elapsed_time": "3:11:58", "remaining_time": "1:29:42"}
{"current_steps": 540, "total_steps": 785, "loss": 0.3957, "lr": 1.0833072568414037e-05, "epoch": 3.4416, "percentage": 68.79, "elapsed_time": "3:13:44", "remaining_time": "1:27:54"}
{"current_steps": 545, "total_steps": 785, "loss": 0.3768, "lr": 1.0439883288591057e-05, "epoch": 3.4736000000000002, "percentage": 69.43, "elapsed_time": "3:15:30", "remaining_time": "1:26:05"}
{"current_steps": 550, "total_steps": 785, "loss": 0.3891, "lr": 1.0051426345401202e-05, "epoch": 3.5056000000000003, "percentage": 70.06, "elapsed_time": "3:17:15", "remaining_time": "1:24:16"}
{"current_steps": 555, "total_steps": 785, "loss": 0.3918, "lr": 9.667894028235704e-06, "epoch": 3.5376, "percentage": 70.7, "elapsed_time": "3:19:02", "remaining_time": "1:22:29"}
{"current_steps": 560, "total_steps": 785, "loss": 0.3973, "lr": 9.289476188755315e-06, "epoch": 3.5696, "percentage": 71.34, "elapsed_time": "3:20:58", "remaining_time": "1:20:45"}
{"current_steps": 565, "total_steps": 785, "loss": 0.3853, "lr": 8.916360146912122e-06, "epoch": 3.6016, "percentage": 71.97, "elapsed_time": "3:22:43", "remaining_time": "1:18:56"}
{"current_steps": 570, "total_steps": 785, "loss": 0.3894, "lr": 8.548730598224646e-06, "epoch": 3.6336, "percentage": 72.61, "elapsed_time": "3:24:24", "remaining_time": "1:17:06"}
{"current_steps": 575, "total_steps": 785, "loss": 0.3904, "lr": 8.186769522352053e-06, "epoch": 3.6656, "percentage": 73.25, "elapsed_time": "3:26:15", "remaining_time": "1:15:19"}
{"current_steps": 580, "total_steps": 785, "loss": 0.3925, "lr": 7.830656093012714e-06, "epoch": 3.6976, "percentage": 73.89, "elapsed_time": "3:28:00", "remaining_time": "1:13:31"}
{"current_steps": 585, "total_steps": 785, "loss": 0.3873, "lr": 7.480566589291696e-06, "epoch": 3.7296, "percentage": 74.52, "elapsed_time": "3:29:49", "remaining_time": "1:11:44"}
{"current_steps": 590, "total_steps": 785, "loss": 0.3774, "lr": 7.1366743083812285e-06, "epoch": 3.7616, "percentage": 75.16, "elapsed_time": "3:31:35", "remaining_time": "1:09:56"}
{"current_steps": 595, "total_steps": 785, "loss": 0.3844, "lr": 6.799149479797101e-06, "epoch": 3.7936, "percentage": 75.8, "elapsed_time": "3:33:32", "remaining_time": "1:08:11"}
{"current_steps": 600, "total_steps": 785, "loss": 0.3893, "lr": 6.4681591811137e-06, "epoch": 3.8256, "percentage": 76.43, "elapsed_time": "3:35:04", "remaining_time": "1:06:18"}
{"current_steps": 605, "total_steps": 785, "loss": 0.3842, "lr": 6.143867255259197e-06, "epoch": 3.8576, "percentage": 77.07, "elapsed_time": "3:36:41", "remaining_time": "1:04:28"}
{"current_steps": 610, "total_steps": 785, "loss": 0.3955, "lr": 5.8264342294119504e-06, "epoch": 3.8895999999999997, "percentage": 77.71, "elapsed_time": "3:38:25", "remaining_time": "1:02:39"}
{"current_steps": 615, "total_steps": 785, "loss": 0.385, "lr": 5.516017235538258e-06, "epoch": 3.9215999999999998, "percentage": 78.34, "elapsed_time": "3:40:08", "remaining_time": "1:00:51"}
{"current_steps": 620, "total_steps": 785, "loss": 0.389, "lr": 5.212769932610695e-06, "epoch": 3.9536, "percentage": 78.98, "elapsed_time": "3:41:56", "remaining_time": "0:59:03"}
{"current_steps": 625, "total_steps": 785, "loss": 0.3848, "lr": 4.916842430545681e-06, "epoch": 3.9856, "percentage": 79.62, "elapsed_time": "3:43:41", "remaining_time": "0:57:15"}
{"current_steps": 630, "total_steps": 785, "loss": 0.3832, "lr": 4.628381215897837e-06, "epoch": 4.0128, "percentage": 80.25, "elapsed_time": "3:45:07", "remaining_time": "0:55:23"}
{"current_steps": 635, "total_steps": 785, "loss": 0.3891, "lr": 4.347529079347914e-06, "epoch": 4.0448, "percentage": 80.89, "elapsed_time": "3:46:45", "remaining_time": "0:53:33"}
{"current_steps": 640, "total_steps": 785, "loss": 0.3799, "lr": 4.074425045020247e-06, "epoch": 4.0768, "percentage": 81.53, "elapsed_time": "3:48:27", "remaining_time": "0:51:45"}
{"current_steps": 645, "total_steps": 785, "loss": 0.3813, "lr": 3.8092043016646487e-06, "epoch": 4.1088, "percentage": 82.17, "elapsed_time": "3:50:11", "remaining_time": "0:49:57"}
{"current_steps": 650, "total_steps": 785, "loss": 0.3793, "lr": 3.551998135736867e-06, "epoch": 4.1408, "percentage": 82.8, "elapsed_time": "3:51:51", "remaining_time": "0:48:09"}
{"current_steps": 655, "total_steps": 785, "loss": 0.3811, "lr": 3.3029338664107267e-06, "epoch": 4.1728, "percentage": 83.44, "elapsed_time": "3:53:34", "remaining_time": "0:46:21"}
{"current_steps": 660, "total_steps": 785, "loss": 0.3872, "lr": 3.0621347825540625e-06, "epoch": 4.2048, "percentage": 84.08, "elapsed_time": "3:55:24", "remaining_time": "0:44:35"}
{"current_steps": 665, "total_steps": 785, "loss": 0.3861, "lr": 2.8297200816997183e-06, "epoch": 4.2368, "percentage": 84.71, "elapsed_time": "3:57:08", "remaining_time": "0:42:47"}
{"current_steps": 670, "total_steps": 785, "loss": 0.3799, "lr": 2.605804811041803e-06, "epoch": 4.2688, "percentage": 85.35, "elapsed_time": "3:59:01", "remaining_time": "0:41:01"}
{"current_steps": 675, "total_steps": 785, "loss": 0.3678, "lr": 2.390499810486351e-06, "epoch": 4.3008, "percentage": 85.99, "elapsed_time": "4:00:53", "remaining_time": "0:39:15"}
{"current_steps": 680, "total_steps": 785, "loss": 0.3829, "lr": 2.183911657784685e-06, "epoch": 4.3328, "percentage": 86.62, "elapsed_time": "4:02:36", "remaining_time": "0:37:27"}
{"current_steps": 685, "total_steps": 785, "loss": 0.3849, "lr": 1.986142615776532e-06, "epoch": 4.3648, "percentage": 87.26, "elapsed_time": "4:04:21", "remaining_time": "0:35:40"}
{"current_steps": 690, "total_steps": 785, "loss": 0.3873, "lr": 1.7972905817690644e-06, "epoch": 4.3968, "percentage": 87.9, "elapsed_time": "4:06:03", "remaining_time": "0:33:52"}
{"current_steps": 695, "total_steps": 785, "loss": 0.3821, "lr": 1.617449039076955e-06, "epoch": 4.4288, "percentage": 88.54, "elapsed_time": "4:07:52", "remaining_time": "0:32:05"}
{"current_steps": 700, "total_steps": 785, "loss": 0.3906, "lr": 1.4467070107473413e-06, "epoch": 4.4608, "percentage": 89.17, "elapsed_time": "4:09:35", "remaining_time": "0:30:18"}
{"current_steps": 705, "total_steps": 785, "loss": 0.3793, "lr": 1.2851490154926816e-06, "epoch": 4.4928, "percentage": 89.81, "elapsed_time": "4:11:26", "remaining_time": "0:28:31"}
{"current_steps": 710, "total_steps": 785, "loss": 0.3853, "lr": 1.1328550258533211e-06, "epoch": 4.5248, "percentage": 90.45, "elapsed_time": "4:13:08", "remaining_time": "0:26:44"}
{"current_steps": 715, "total_steps": 785, "loss": 0.3871, "lr": 9.899004286103953e-07, "epoch": 4.5568, "percentage": 91.08, "elapsed_time": "4:14:47", "remaining_time": "0:24:56"}
{"current_steps": 720, "total_steps": 785, "loss": 0.3799, "lr": 8.5635598746876e-07, "epoch": 4.5888, "percentage": 91.72, "elapsed_time": "4:16:28", "remaining_time": "0:23:09"}
{"current_steps": 725, "total_steps": 785, "loss": 0.3891, "lr": 7.32287808028389e-07, "epoch": 4.6208, "percentage": 92.36, "elapsed_time": "4:18:07", "remaining_time": "0:21:21"}
{"current_steps": 730, "total_steps": 785, "loss": 0.3775, "lr": 6.177573050615327e-07, "epoch": 4.6528, "percentage": 92.99, "elapsed_time": "4:19:49", "remaining_time": "0:19:34"}
{"current_steps": 735, "total_steps": 785, "loss": 0.3855, "lr": 5.128211721119213e-07, "epoch": 4.6848, "percentage": 93.63, "elapsed_time": "4:21:36", "remaining_time": "0:17:47"}
{"current_steps": 740, "total_steps": 785, "loss": 0.3838, "lr": 4.175313534309755e-07, "epoch": 4.7168, "percentage": 94.27, "elapsed_time": "4:23:25", "remaining_time": "0:16:01"}
{"current_steps": 745, "total_steps": 785, "loss": 0.3845, "lr": 3.319350182649861e-07, "epoch": 4.7488, "percentage": 94.9, "elapsed_time": "4:25:15", "remaining_time": "0:14:14"}
{"current_steps": 750, "total_steps": 785, "loss": 0.3757, "lr": 2.560745375059392e-07, "epoch": 4.7808, "percentage": 95.54, "elapsed_time": "4:26:58", "remaining_time": "0:12:27"}
{"current_steps": 755, "total_steps": 785, "loss": 0.3807, "lr": 1.8998746271758016e-07, "epoch": 4.8128, "percentage": 96.18, "elapsed_time": "4:28:37", "remaining_time": "0:10:40"}
{"current_steps": 760, "total_steps": 785, "loss": 0.3916, "lr": 1.337065075470778e-07, "epoch": 4.8448, "percentage": 96.82, "elapsed_time": "4:30:31", "remaining_time": "0:08:53"}
{"current_steps": 765, "total_steps": 785, "loss": 0.3829, "lr": 8.725953153150279e-08, "epoch": 4.8768, "percentage": 97.45, "elapsed_time": "4:32:21", "remaining_time": "0:07:07"}
{"current_steps": 770, "total_steps": 785, "loss": 0.3808, "lr": 5.066952630711886e-08, "epoch": 4.9088, "percentage": 98.09, "elapsed_time": "4:34:09", "remaining_time": "0:05:20"}
{"current_steps": 775, "total_steps": 785, "loss": 0.383, "lr": 2.3954604228342283e-08, "epoch": 4.9408, "percentage": 98.73, "elapsed_time": "4:35:56", "remaining_time": "0:03:33"}
{"current_steps": 780, "total_steps": 785, "loss": 0.3951, "lr": 7.12798940197601e-09, "epoch": 4.9728, "percentage": 99.36, "elapsed_time": "4:37:46", "remaining_time": "0:01:46"}
{"current_steps": 785, "total_steps": 785, "loss": 0.3805, "lr": 1.9801114115480802e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "4:39:09", "remaining_time": "0:00:00"}
{"current_steps": 785, "total_steps": 785, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "4:39:09", "remaining_time": "0:00:00"}