top_7_ranking_stackexchange / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
0ea0b99 verified
{"current_steps": 10, "total_steps": 756, "loss": 1.0725, "lr": 5e-06, "epoch": 0.0396235760277365, "percentage": 1.32, "elapsed_time": "0:09:42", "remaining_time": "12:04:04"}
{"current_steps": 20, "total_steps": 756, "loss": 0.9867, "lr": 5e-06, "epoch": 0.079247152055473, "percentage": 2.65, "elapsed_time": "0:19:19", "remaining_time": "11:51:27"}
{"current_steps": 30, "total_steps": 756, "loss": 0.9489, "lr": 5e-06, "epoch": 0.1188707280832095, "percentage": 3.97, "elapsed_time": "0:28:57", "remaining_time": "11:40:53"}
{"current_steps": 40, "total_steps": 756, "loss": 0.9168, "lr": 5e-06, "epoch": 0.158494304110946, "percentage": 5.29, "elapsed_time": "0:38:35", "remaining_time": "11:30:50"}
{"current_steps": 50, "total_steps": 756, "loss": 0.903, "lr": 5e-06, "epoch": 0.1981178801386825, "percentage": 6.61, "elapsed_time": "0:48:13", "remaining_time": "11:21:02"}
{"current_steps": 60, "total_steps": 756, "loss": 0.884, "lr": 5e-06, "epoch": 0.237741456166419, "percentage": 7.94, "elapsed_time": "0:57:52", "remaining_time": "11:11:16"}
{"current_steps": 70, "total_steps": 756, "loss": 0.8732, "lr": 5e-06, "epoch": 0.27736503219415554, "percentage": 9.26, "elapsed_time": "1:07:29", "remaining_time": "11:01:23"}
{"current_steps": 80, "total_steps": 756, "loss": 0.8701, "lr": 5e-06, "epoch": 0.316988608221892, "percentage": 10.58, "elapsed_time": "1:17:07", "remaining_time": "10:51:38"}
{"current_steps": 90, "total_steps": 756, "loss": 0.8641, "lr": 5e-06, "epoch": 0.35661218424962854, "percentage": 11.9, "elapsed_time": "1:26:45", "remaining_time": "10:42:00"}
{"current_steps": 100, "total_steps": 756, "loss": 0.8597, "lr": 5e-06, "epoch": 0.396235760277365, "percentage": 13.23, "elapsed_time": "1:36:23", "remaining_time": "10:32:16"}
{"current_steps": 110, "total_steps": 756, "loss": 0.8538, "lr": 5e-06, "epoch": 0.43585933630510154, "percentage": 14.55, "elapsed_time": "1:46:01", "remaining_time": "10:22:36"}
{"current_steps": 120, "total_steps": 756, "loss": 0.8493, "lr": 5e-06, "epoch": 0.475482912332838, "percentage": 15.87, "elapsed_time": "1:55:39", "remaining_time": "10:12:57"}
{"current_steps": 130, "total_steps": 756, "loss": 0.8491, "lr": 5e-06, "epoch": 0.5151064883605745, "percentage": 17.2, "elapsed_time": "2:05:16", "remaining_time": "10:03:16"}
{"current_steps": 140, "total_steps": 756, "loss": 0.8519, "lr": 5e-06, "epoch": 0.5547300643883111, "percentage": 18.52, "elapsed_time": "2:14:54", "remaining_time": "9:53:37"}
{"current_steps": 150, "total_steps": 756, "loss": 0.8388, "lr": 5e-06, "epoch": 0.5943536404160475, "percentage": 19.84, "elapsed_time": "2:24:33", "remaining_time": "9:43:59"}
{"current_steps": 160, "total_steps": 756, "loss": 0.842, "lr": 5e-06, "epoch": 0.633977216443784, "percentage": 21.16, "elapsed_time": "2:34:11", "remaining_time": "9:34:21"}
{"current_steps": 170, "total_steps": 756, "loss": 0.8381, "lr": 5e-06, "epoch": 0.6736007924715206, "percentage": 22.49, "elapsed_time": "2:43:50", "remaining_time": "9:24:44"}
{"current_steps": 180, "total_steps": 756, "loss": 0.8341, "lr": 5e-06, "epoch": 0.7132243684992571, "percentage": 23.81, "elapsed_time": "2:53:28", "remaining_time": "9:15:07"}
{"current_steps": 190, "total_steps": 756, "loss": 0.8375, "lr": 5e-06, "epoch": 0.7528479445269936, "percentage": 25.13, "elapsed_time": "3:03:07", "remaining_time": "9:05:30"}
{"current_steps": 200, "total_steps": 756, "loss": 0.8381, "lr": 5e-06, "epoch": 0.79247152055473, "percentage": 26.46, "elapsed_time": "3:12:45", "remaining_time": "8:55:52"}
{"current_steps": 210, "total_steps": 756, "loss": 0.8342, "lr": 5e-06, "epoch": 0.8320950965824666, "percentage": 27.78, "elapsed_time": "3:22:23", "remaining_time": "8:46:13"}
{"current_steps": 220, "total_steps": 756, "loss": 0.8308, "lr": 5e-06, "epoch": 0.8717186726102031, "percentage": 29.1, "elapsed_time": "3:32:02", "remaining_time": "8:36:36"}
{"current_steps": 230, "total_steps": 756, "loss": 0.8302, "lr": 5e-06, "epoch": 0.9113422486379396, "percentage": 30.42, "elapsed_time": "3:41:40", "remaining_time": "8:26:58"}
{"current_steps": 240, "total_steps": 756, "loss": 0.8272, "lr": 5e-06, "epoch": 0.950965824665676, "percentage": 31.75, "elapsed_time": "3:51:18", "remaining_time": "8:17:18"}
{"current_steps": 250, "total_steps": 756, "loss": 0.8269, "lr": 5e-06, "epoch": 0.9905894006934126, "percentage": 33.07, "elapsed_time": "4:00:55", "remaining_time": "8:07:37"}
{"current_steps": 252, "total_steps": 756, "eval_loss": 0.8291837573051453, "epoch": 0.9985141158989599, "percentage": 33.33, "elapsed_time": "4:07:42", "remaining_time": "8:15:25"}
{"current_steps": 260, "total_steps": 756, "loss": 0.8491, "lr": 5e-06, "epoch": 1.030212976721149, "percentage": 34.39, "elapsed_time": "4:16:13", "remaining_time": "8:08:47"}
{"current_steps": 270, "total_steps": 756, "loss": 0.785, "lr": 5e-06, "epoch": 1.0698365527488856, "percentage": 35.71, "elapsed_time": "4:25:51", "remaining_time": "7:58:33"}
{"current_steps": 280, "total_steps": 756, "loss": 0.7887, "lr": 5e-06, "epoch": 1.1094601287766221, "percentage": 37.04, "elapsed_time": "4:35:31", "remaining_time": "7:48:22"}
{"current_steps": 290, "total_steps": 756, "loss": 0.7862, "lr": 5e-06, "epoch": 1.1490837048043585, "percentage": 38.36, "elapsed_time": "4:45:09", "remaining_time": "7:38:13"}
{"current_steps": 300, "total_steps": 756, "loss": 0.7793, "lr": 5e-06, "epoch": 1.188707280832095, "percentage": 39.68, "elapsed_time": "4:54:48", "remaining_time": "7:28:06"}
{"current_steps": 310, "total_steps": 756, "loss": 0.7795, "lr": 5e-06, "epoch": 1.2283308568598317, "percentage": 41.01, "elapsed_time": "5:04:26", "remaining_time": "7:18:00"}
{"current_steps": 320, "total_steps": 756, "loss": 0.7798, "lr": 5e-06, "epoch": 1.267954432887568, "percentage": 42.33, "elapsed_time": "5:14:05", "remaining_time": "7:07:57"}
{"current_steps": 330, "total_steps": 756, "loss": 0.7832, "lr": 5e-06, "epoch": 1.3075780089153046, "percentage": 43.65, "elapsed_time": "5:23:44", "remaining_time": "6:57:55"}
{"current_steps": 340, "total_steps": 756, "loss": 0.7835, "lr": 5e-06, "epoch": 1.3472015849430412, "percentage": 44.97, "elapsed_time": "5:33:23", "remaining_time": "6:47:55"}
{"current_steps": 350, "total_steps": 756, "loss": 0.7841, "lr": 5e-06, "epoch": 1.3868251609707776, "percentage": 46.3, "elapsed_time": "5:43:02", "remaining_time": "6:37:55"}
{"current_steps": 360, "total_steps": 756, "loss": 0.7809, "lr": 5e-06, "epoch": 1.4264487369985142, "percentage": 47.62, "elapsed_time": "5:52:40", "remaining_time": "6:27:57"}
{"current_steps": 370, "total_steps": 756, "loss": 0.7839, "lr": 5e-06, "epoch": 1.4660723130262507, "percentage": 48.94, "elapsed_time": "6:02:19", "remaining_time": "6:17:59"}
{"current_steps": 380, "total_steps": 756, "loss": 0.78, "lr": 5e-06, "epoch": 1.505695889053987, "percentage": 50.26, "elapsed_time": "6:11:57", "remaining_time": "6:08:02"}
{"current_steps": 390, "total_steps": 756, "loss": 0.7812, "lr": 5e-06, "epoch": 1.5453194650817235, "percentage": 51.59, "elapsed_time": "6:21:36", "remaining_time": "5:58:07"}
{"current_steps": 400, "total_steps": 756, "loss": 0.7855, "lr": 5e-06, "epoch": 1.5849430411094603, "percentage": 52.91, "elapsed_time": "6:31:15", "remaining_time": "5:48:12"}
{"current_steps": 410, "total_steps": 756, "loss": 0.7826, "lr": 5e-06, "epoch": 1.6245666171371966, "percentage": 54.23, "elapsed_time": "6:40:53", "remaining_time": "5:38:18"}
{"current_steps": 420, "total_steps": 756, "loss": 0.7767, "lr": 5e-06, "epoch": 1.664190193164933, "percentage": 55.56, "elapsed_time": "6:50:32", "remaining_time": "5:28:25"}
{"current_steps": 430, "total_steps": 756, "loss": 0.7776, "lr": 5e-06, "epoch": 1.7038137691926698, "percentage": 56.88, "elapsed_time": "7:00:11", "remaining_time": "5:18:33"}
{"current_steps": 440, "total_steps": 756, "loss": 0.7786, "lr": 5e-06, "epoch": 1.7434373452204062, "percentage": 58.2, "elapsed_time": "7:09:49", "remaining_time": "5:08:41"}
{"current_steps": 450, "total_steps": 756, "loss": 0.7775, "lr": 5e-06, "epoch": 1.7830609212481425, "percentage": 59.52, "elapsed_time": "7:19:28", "remaining_time": "4:58:50"}
{"current_steps": 460, "total_steps": 756, "loss": 0.7759, "lr": 5e-06, "epoch": 1.8226844972758791, "percentage": 60.85, "elapsed_time": "7:29:08", "remaining_time": "4:49:00"}
{"current_steps": 470, "total_steps": 756, "loss": 0.778, "lr": 5e-06, "epoch": 1.8623080733036157, "percentage": 62.17, "elapsed_time": "7:38:46", "remaining_time": "4:39:10"}
{"current_steps": 480, "total_steps": 756, "loss": 0.7728, "lr": 5e-06, "epoch": 1.901931649331352, "percentage": 63.49, "elapsed_time": "7:48:25", "remaining_time": "4:29:20"}
{"current_steps": 490, "total_steps": 756, "loss": 0.7817, "lr": 5e-06, "epoch": 1.9415552253590886, "percentage": 64.81, "elapsed_time": "7:58:04", "remaining_time": "4:19:31"}
{"current_steps": 500, "total_steps": 756, "loss": 0.7778, "lr": 5e-06, "epoch": 1.9811788013868252, "percentage": 66.14, "elapsed_time": "8:07:42", "remaining_time": "4:09:42"}
{"current_steps": 504, "total_steps": 756, "eval_loss": 0.8146935701370239, "epoch": 1.9970282317979198, "percentage": 66.67, "elapsed_time": "8:16:45", "remaining_time": "4:08:22"}
{"current_steps": 510, "total_steps": 756, "loss": 0.8016, "lr": 5e-06, "epoch": 2.0208023774145616, "percentage": 67.46, "elapsed_time": "8:23:05", "remaining_time": "4:02:39"}
{"current_steps": 520, "total_steps": 756, "loss": 0.7316, "lr": 5e-06, "epoch": 2.060425953442298, "percentage": 68.78, "elapsed_time": "8:32:44", "remaining_time": "3:52:42"}
{"current_steps": 530, "total_steps": 756, "loss": 0.7265, "lr": 5e-06, "epoch": 2.1000495294700348, "percentage": 70.11, "elapsed_time": "8:42:24", "remaining_time": "3:42:45"}
{"current_steps": 540, "total_steps": 756, "loss": 0.7311, "lr": 5e-06, "epoch": 2.139673105497771, "percentage": 71.43, "elapsed_time": "8:52:03", "remaining_time": "3:32:49"}
{"current_steps": 550, "total_steps": 756, "loss": 0.7294, "lr": 5e-06, "epoch": 2.1792966815255075, "percentage": 72.75, "elapsed_time": "9:01:42", "remaining_time": "3:22:53"}
{"current_steps": 560, "total_steps": 756, "loss": 0.7307, "lr": 5e-06, "epoch": 2.2189202575532443, "percentage": 74.07, "elapsed_time": "9:11:21", "remaining_time": "3:12:58"}
{"current_steps": 570, "total_steps": 756, "loss": 0.7325, "lr": 5e-06, "epoch": 2.2585438335809807, "percentage": 75.4, "elapsed_time": "9:21:01", "remaining_time": "3:03:04"}
{"current_steps": 580, "total_steps": 756, "loss": 0.7352, "lr": 5e-06, "epoch": 2.298167409608717, "percentage": 76.72, "elapsed_time": "9:30:40", "remaining_time": "2:53:10"}
{"current_steps": 590, "total_steps": 756, "loss": 0.7317, "lr": 5e-06, "epoch": 2.337790985636454, "percentage": 78.04, "elapsed_time": "9:40:18", "remaining_time": "2:43:16"}
{"current_steps": 600, "total_steps": 756, "loss": 0.7274, "lr": 5e-06, "epoch": 2.37741456166419, "percentage": 79.37, "elapsed_time": "9:49:58", "remaining_time": "2:33:23"}
{"current_steps": 610, "total_steps": 756, "loss": 0.7301, "lr": 5e-06, "epoch": 2.4170381376919265, "percentage": 80.69, "elapsed_time": "9:59:38", "remaining_time": "2:23:31"}
{"current_steps": 620, "total_steps": 756, "loss": 0.734, "lr": 5e-06, "epoch": 2.4566617137196634, "percentage": 82.01, "elapsed_time": "10:09:17", "remaining_time": "2:13:38"}
{"current_steps": 630, "total_steps": 756, "loss": 0.7361, "lr": 5e-06, "epoch": 2.4962852897473997, "percentage": 83.33, "elapsed_time": "10:18:56", "remaining_time": "2:03:47"}
{"current_steps": 640, "total_steps": 756, "loss": 0.7327, "lr": 5e-06, "epoch": 2.535908865775136, "percentage": 84.66, "elapsed_time": "10:28:34", "remaining_time": "1:53:55"}
{"current_steps": 650, "total_steps": 756, "loss": 0.7346, "lr": 5e-06, "epoch": 2.5755324418028724, "percentage": 85.98, "elapsed_time": "10:38:12", "remaining_time": "1:44:04"}
{"current_steps": 660, "total_steps": 756, "loss": 0.7314, "lr": 5e-06, "epoch": 2.6151560178306092, "percentage": 87.3, "elapsed_time": "10:47:51", "remaining_time": "1:34:14"}
{"current_steps": 670, "total_steps": 756, "loss": 0.7352, "lr": 5e-06, "epoch": 2.6547795938583456, "percentage": 88.62, "elapsed_time": "10:57:29", "remaining_time": "1:24:23"}
{"current_steps": 680, "total_steps": 756, "loss": 0.7328, "lr": 5e-06, "epoch": 2.6944031698860824, "percentage": 89.95, "elapsed_time": "11:07:08", "remaining_time": "1:14:33"}
{"current_steps": 690, "total_steps": 756, "loss": 0.7353, "lr": 5e-06, "epoch": 2.734026745913819, "percentage": 91.27, "elapsed_time": "11:16:47", "remaining_time": "1:04:44"}
{"current_steps": 700, "total_steps": 756, "loss": 0.7359, "lr": 5e-06, "epoch": 2.773650321941555, "percentage": 92.59, "elapsed_time": "11:26:27", "remaining_time": "0:54:54"}
{"current_steps": 710, "total_steps": 756, "loss": 0.7289, "lr": 5e-06, "epoch": 2.8132738979692915, "percentage": 93.92, "elapsed_time": "11:36:06", "remaining_time": "0:45:05"}
{"current_steps": 720, "total_steps": 756, "loss": 0.7321, "lr": 5e-06, "epoch": 2.8528974739970283, "percentage": 95.24, "elapsed_time": "11:45:44", "remaining_time": "0:35:17"}
{"current_steps": 730, "total_steps": 756, "loss": 0.7363, "lr": 5e-06, "epoch": 2.8925210500247647, "percentage": 96.56, "elapsed_time": "11:55:23", "remaining_time": "0:25:28"}
{"current_steps": 740, "total_steps": 756, "loss": 0.7317, "lr": 5e-06, "epoch": 2.9321446260525015, "percentage": 97.88, "elapsed_time": "12:05:02", "remaining_time": "0:15:40"}
{"current_steps": 750, "total_steps": 756, "loss": 0.7327, "lr": 5e-06, "epoch": 2.971768202080238, "percentage": 99.21, "elapsed_time": "12:14:41", "remaining_time": "0:05:52"}
{"current_steps": 756, "total_steps": 756, "eval_loss": 0.8128942847251892, "epoch": 2.9955423476968797, "percentage": 100.0, "elapsed_time": "12:26:13", "remaining_time": "0:00:00"}
{"current_steps": 756, "total_steps": 756, "epoch": 2.9955423476968797, "percentage": 100.0, "elapsed_time": "12:27:39", "remaining_time": "0:00:00"}