top_8_ranking_stackexchange / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 3
6ec1fa9 verified
{"current_steps": 10, "total_steps": 882, "loss": 1.0253, "lr": 5e-06, "epoch": 0.034013605442176874, "percentage": 1.13, "elapsed_time": "0:09:43", "remaining_time": "14:07:22"}
{"current_steps": 20, "total_steps": 882, "loss": 0.9164, "lr": 5e-06, "epoch": 0.06802721088435375, "percentage": 2.27, "elapsed_time": "0:19:22", "remaining_time": "13:54:43"}
{"current_steps": 30, "total_steps": 882, "loss": 0.8837, "lr": 5e-06, "epoch": 0.10204081632653061, "percentage": 3.4, "elapsed_time": "0:29:00", "remaining_time": "13:43:39"}
{"current_steps": 40, "total_steps": 882, "loss": 0.8662, "lr": 5e-06, "epoch": 0.1360544217687075, "percentage": 4.54, "elapsed_time": "0:38:38", "remaining_time": "13:33:29"}
{"current_steps": 50, "total_steps": 882, "loss": 0.8474, "lr": 5e-06, "epoch": 0.17006802721088435, "percentage": 5.67, "elapsed_time": "0:48:16", "remaining_time": "13:23:18"}
{"current_steps": 60, "total_steps": 882, "loss": 0.8403, "lr": 5e-06, "epoch": 0.20408163265306123, "percentage": 6.8, "elapsed_time": "0:57:55", "remaining_time": "13:13:33"}
{"current_steps": 70, "total_steps": 882, "loss": 0.8324, "lr": 5e-06, "epoch": 0.23809523809523808, "percentage": 7.94, "elapsed_time": "1:07:33", "remaining_time": "13:03:37"}
{"current_steps": 80, "total_steps": 882, "loss": 0.8255, "lr": 5e-06, "epoch": 0.272108843537415, "percentage": 9.07, "elapsed_time": "1:17:12", "remaining_time": "12:53:56"}
{"current_steps": 90, "total_steps": 882, "loss": 0.8268, "lr": 5e-06, "epoch": 0.30612244897959184, "percentage": 10.2, "elapsed_time": "1:26:49", "remaining_time": "12:44:02"}
{"current_steps": 100, "total_steps": 882, "loss": 0.8244, "lr": 5e-06, "epoch": 0.3401360544217687, "percentage": 11.34, "elapsed_time": "1:36:25", "remaining_time": "12:34:06"}
{"current_steps": 110, "total_steps": 882, "loss": 0.8204, "lr": 5e-06, "epoch": 0.3741496598639456, "percentage": 12.47, "elapsed_time": "1:46:03", "remaining_time": "12:24:22"}
{"current_steps": 120, "total_steps": 882, "loss": 0.8162, "lr": 5e-06, "epoch": 0.40816326530612246, "percentage": 13.61, "elapsed_time": "1:55:41", "remaining_time": "12:14:36"}
{"current_steps": 130, "total_steps": 882, "loss": 0.8145, "lr": 5e-06, "epoch": 0.4421768707482993, "percentage": 14.74, "elapsed_time": "2:05:18", "remaining_time": "12:04:54"}
{"current_steps": 140, "total_steps": 882, "loss": 0.8055, "lr": 5e-06, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "2:14:56", "remaining_time": "11:55:09"}
{"current_steps": 150, "total_steps": 882, "loss": 0.8046, "lr": 5e-06, "epoch": 0.5102040816326531, "percentage": 17.01, "elapsed_time": "2:24:32", "remaining_time": "11:45:23"}
{"current_steps": 160, "total_steps": 882, "loss": 0.8038, "lr": 5e-06, "epoch": 0.54421768707483, "percentage": 18.14, "elapsed_time": "2:34:11", "remaining_time": "11:35:45"}
{"current_steps": 170, "total_steps": 882, "loss": 0.7984, "lr": 5e-06, "epoch": 0.5782312925170068, "percentage": 19.27, "elapsed_time": "2:43:47", "remaining_time": "11:26:01"}
{"current_steps": 180, "total_steps": 882, "loss": 0.8053, "lr": 5e-06, "epoch": 0.6122448979591837, "percentage": 20.41, "elapsed_time": "2:53:26", "remaining_time": "11:16:24"}
{"current_steps": 190, "total_steps": 882, "loss": 0.7971, "lr": 5e-06, "epoch": 0.6462585034013606, "percentage": 21.54, "elapsed_time": "3:03:04", "remaining_time": "11:06:48"}
{"current_steps": 200, "total_steps": 882, "loss": 0.7962, "lr": 5e-06, "epoch": 0.6802721088435374, "percentage": 22.68, "elapsed_time": "3:12:43", "remaining_time": "10:57:11"}
{"current_steps": 210, "total_steps": 882, "loss": 0.7965, "lr": 5e-06, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "3:22:20", "remaining_time": "10:47:29"}
{"current_steps": 220, "total_steps": 882, "loss": 0.7934, "lr": 5e-06, "epoch": 0.7482993197278912, "percentage": 24.94, "elapsed_time": "3:31:57", "remaining_time": "10:37:47"}
{"current_steps": 230, "total_steps": 882, "loss": 0.7989, "lr": 5e-06, "epoch": 0.782312925170068, "percentage": 26.08, "elapsed_time": "3:41:33", "remaining_time": "10:28:04"}
{"current_steps": 240, "total_steps": 882, "loss": 0.7969, "lr": 5e-06, "epoch": 0.8163265306122449, "percentage": 27.21, "elapsed_time": "3:51:10", "remaining_time": "10:18:24"}
{"current_steps": 250, "total_steps": 882, "loss": 0.7919, "lr": 5e-06, "epoch": 0.8503401360544217, "percentage": 28.34, "elapsed_time": "4:00:48", "remaining_time": "10:08:46"}
{"current_steps": 260, "total_steps": 882, "loss": 0.7902, "lr": 5e-06, "epoch": 0.8843537414965986, "percentage": 29.48, "elapsed_time": "4:10:25", "remaining_time": "9:59:06"}
{"current_steps": 270, "total_steps": 882, "loss": 0.7906, "lr": 5e-06, "epoch": 0.9183673469387755, "percentage": 30.61, "elapsed_time": "4:20:04", "remaining_time": "9:49:29"}
{"current_steps": 280, "total_steps": 882, "loss": 0.7883, "lr": 5e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "4:29:42", "remaining_time": "9:39:51"}
{"current_steps": 290, "total_steps": 882, "loss": 0.7865, "lr": 5e-06, "epoch": 0.9863945578231292, "percentage": 32.88, "elapsed_time": "4:39:20", "remaining_time": "9:30:13"}
{"current_steps": 294, "total_steps": 882, "eval_loss": 0.787599503993988, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "4:48:22", "remaining_time": "9:36:44"}
{"current_steps": 300, "total_steps": 882, "loss": 0.7746, "lr": 5e-06, "epoch": 1.0204081632653061, "percentage": 34.01, "elapsed_time": "4:55:18", "remaining_time": "9:32:53"}
{"current_steps": 310, "total_steps": 882, "loss": 0.7488, "lr": 5e-06, "epoch": 1.054421768707483, "percentage": 35.15, "elapsed_time": "5:04:57", "remaining_time": "9:22:41"}
{"current_steps": 320, "total_steps": 882, "loss": 0.7475, "lr": 5e-06, "epoch": 1.08843537414966, "percentage": 36.28, "elapsed_time": "5:14:36", "remaining_time": "9:12:31"}
{"current_steps": 330, "total_steps": 882, "loss": 0.7431, "lr": 5e-06, "epoch": 1.1224489795918366, "percentage": 37.41, "elapsed_time": "5:24:15", "remaining_time": "9:02:23"}
{"current_steps": 340, "total_steps": 882, "loss": 0.7462, "lr": 5e-06, "epoch": 1.1564625850340136, "percentage": 38.55, "elapsed_time": "5:33:54", "remaining_time": "8:52:17"}
{"current_steps": 350, "total_steps": 882, "loss": 0.747, "lr": 5e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "5:43:33", "remaining_time": "8:42:12"}
{"current_steps": 360, "total_steps": 882, "loss": 0.7455, "lr": 5e-06, "epoch": 1.2244897959183674, "percentage": 40.82, "elapsed_time": "5:53:11", "remaining_time": "8:32:07"}
{"current_steps": 370, "total_steps": 882, "loss": 0.7406, "lr": 5e-06, "epoch": 1.2585034013605443, "percentage": 41.95, "elapsed_time": "6:02:49", "remaining_time": "8:22:03"}
{"current_steps": 380, "total_steps": 882, "loss": 0.7538, "lr": 5e-06, "epoch": 1.2925170068027212, "percentage": 43.08, "elapsed_time": "6:12:26", "remaining_time": "8:12:01"}
{"current_steps": 390, "total_steps": 882, "loss": 0.7458, "lr": 5e-06, "epoch": 1.3265306122448979, "percentage": 44.22, "elapsed_time": "6:22:05", "remaining_time": "8:02:01"}
{"current_steps": 400, "total_steps": 882, "loss": 0.7446, "lr": 5e-06, "epoch": 1.3605442176870748, "percentage": 45.35, "elapsed_time": "6:31:44", "remaining_time": "7:52:02"}
{"current_steps": 410, "total_steps": 882, "loss": 0.7497, "lr": 5e-06, "epoch": 1.3945578231292517, "percentage": 46.49, "elapsed_time": "6:41:22", "remaining_time": "7:42:04"}
{"current_steps": 420, "total_steps": 882, "loss": 0.7469, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "6:51:01", "remaining_time": "7:32:08"}
{"current_steps": 430, "total_steps": 882, "loss": 0.7424, "lr": 5e-06, "epoch": 1.4625850340136055, "percentage": 48.75, "elapsed_time": "7:00:40", "remaining_time": "7:22:11"}
{"current_steps": 440, "total_steps": 882, "loss": 0.7445, "lr": 5e-06, "epoch": 1.4965986394557822, "percentage": 49.89, "elapsed_time": "7:10:19", "remaining_time": "7:12:16"}
{"current_steps": 450, "total_steps": 882, "loss": 0.7492, "lr": 5e-06, "epoch": 1.5306122448979593, "percentage": 51.02, "elapsed_time": "7:19:58", "remaining_time": "7:02:22"}
{"current_steps": 460, "total_steps": 882, "loss": 0.7423, "lr": 5e-06, "epoch": 1.564625850340136, "percentage": 52.15, "elapsed_time": "7:29:36", "remaining_time": "6:52:28"}
{"current_steps": 470, "total_steps": 882, "loss": 0.7434, "lr": 5e-06, "epoch": 1.598639455782313, "percentage": 53.29, "elapsed_time": "7:39:14", "remaining_time": "6:42:34"}
{"current_steps": 480, "total_steps": 882, "loss": 0.7365, "lr": 5e-06, "epoch": 1.6326530612244898, "percentage": 54.42, "elapsed_time": "7:48:54", "remaining_time": "6:32:42"}
{"current_steps": 490, "total_steps": 882, "loss": 0.7421, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "7:58:33", "remaining_time": "6:22:50"}
{"current_steps": 500, "total_steps": 882, "loss": 0.7463, "lr": 5e-06, "epoch": 1.7006802721088436, "percentage": 56.69, "elapsed_time": "8:08:12", "remaining_time": "6:12:59"}
{"current_steps": 510, "total_steps": 882, "loss": 0.7376, "lr": 5e-06, "epoch": 1.7346938775510203, "percentage": 57.82, "elapsed_time": "8:17:51", "remaining_time": "6:03:08"}
{"current_steps": 520, "total_steps": 882, "loss": 0.7441, "lr": 5e-06, "epoch": 1.7687074829931972, "percentage": 58.96, "elapsed_time": "8:27:30", "remaining_time": "5:53:18"}
{"current_steps": 530, "total_steps": 882, "loss": 0.7431, "lr": 5e-06, "epoch": 1.8027210884353742, "percentage": 60.09, "elapsed_time": "8:37:08", "remaining_time": "5:43:27"}
{"current_steps": 540, "total_steps": 882, "loss": 0.7438, "lr": 5e-06, "epoch": 1.836734693877551, "percentage": 61.22, "elapsed_time": "8:46:47", "remaining_time": "5:33:37"}
{"current_steps": 550, "total_steps": 882, "loss": 0.7393, "lr": 5e-06, "epoch": 1.870748299319728, "percentage": 62.36, "elapsed_time": "8:56:26", "remaining_time": "5:23:49"}
{"current_steps": 560, "total_steps": 882, "loss": 0.7397, "lr": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "9:06:05", "remaining_time": "5:14:00"}
{"current_steps": 570, "total_steps": 882, "loss": 0.7397, "lr": 5e-06, "epoch": 1.9387755102040818, "percentage": 64.63, "elapsed_time": "9:15:45", "remaining_time": "5:04:12"}
{"current_steps": 580, "total_steps": 882, "loss": 0.7399, "lr": 5e-06, "epoch": 1.9727891156462585, "percentage": 65.76, "elapsed_time": "9:25:25", "remaining_time": "4:54:24"}
{"current_steps": 588, "total_steps": 882, "eval_loss": 0.7747776508331299, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "9:38:24", "remaining_time": "4:49:12"}
{"current_steps": 590, "total_steps": 882, "loss": 0.7322, "lr": 5e-06, "epoch": 2.006802721088435, "percentage": 66.89, "elapsed_time": "9:41:32", "remaining_time": "4:47:48"}
{"current_steps": 600, "total_steps": 882, "loss": 0.6959, "lr": 5e-06, "epoch": 2.0408163265306123, "percentage": 68.03, "elapsed_time": "9:51:12", "remaining_time": "4:37:51"}
{"current_steps": 610, "total_steps": 882, "loss": 0.6963, "lr": 5e-06, "epoch": 2.074829931972789, "percentage": 69.16, "elapsed_time": "10:00:51", "remaining_time": "4:27:55"}
{"current_steps": 620, "total_steps": 882, "loss": 0.6919, "lr": 5e-06, "epoch": 2.108843537414966, "percentage": 70.29, "elapsed_time": "10:10:30", "remaining_time": "4:17:59"}
{"current_steps": 630, "total_steps": 882, "loss": 0.6885, "lr": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "10:20:09", "remaining_time": "4:08:03"}
{"current_steps": 640, "total_steps": 882, "loss": 0.696, "lr": 5e-06, "epoch": 2.17687074829932, "percentage": 72.56, "elapsed_time": "10:29:48", "remaining_time": "3:58:08"}
{"current_steps": 650, "total_steps": 882, "loss": 0.6937, "lr": 5e-06, "epoch": 2.2108843537414966, "percentage": 73.7, "elapsed_time": "10:39:27", "remaining_time": "3:48:14"}
{"current_steps": 660, "total_steps": 882, "loss": 0.6981, "lr": 5e-06, "epoch": 2.2448979591836733, "percentage": 74.83, "elapsed_time": "10:49:05", "remaining_time": "3:38:19"}
{"current_steps": 670, "total_steps": 882, "loss": 0.7015, "lr": 5e-06, "epoch": 2.2789115646258504, "percentage": 75.96, "elapsed_time": "10:58:45", "remaining_time": "3:28:26"}
{"current_steps": 680, "total_steps": 882, "loss": 0.7012, "lr": 5e-06, "epoch": 2.312925170068027, "percentage": 77.1, "elapsed_time": "11:08:25", "remaining_time": "3:18:33"}
{"current_steps": 690, "total_steps": 882, "loss": 0.6952, "lr": 5e-06, "epoch": 2.3469387755102042, "percentage": 78.23, "elapsed_time": "11:18:03", "remaining_time": "3:08:40"}
{"current_steps": 700, "total_steps": 882, "loss": 0.6953, "lr": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "11:27:42", "remaining_time": "2:58:48"}
{"current_steps": 710, "total_steps": 882, "loss": 0.6997, "lr": 5e-06, "epoch": 2.4149659863945576, "percentage": 80.5, "elapsed_time": "11:37:20", "remaining_time": "2:48:56"}
{"current_steps": 720, "total_steps": 882, "loss": 0.6947, "lr": 5e-06, "epoch": 2.4489795918367347, "percentage": 81.63, "elapsed_time": "11:46:57", "remaining_time": "2:39:04"}
{"current_steps": 730, "total_steps": 882, "loss": 0.7002, "lr": 5e-06, "epoch": 2.4829931972789114, "percentage": 82.77, "elapsed_time": "11:56:36", "remaining_time": "2:29:12"}
{"current_steps": 740, "total_steps": 882, "loss": 0.7, "lr": 5e-06, "epoch": 2.5170068027210886, "percentage": 83.9, "elapsed_time": "12:06:14", "remaining_time": "2:19:21"}
{"current_steps": 750, "total_steps": 882, "loss": 0.6977, "lr": 5e-06, "epoch": 2.5510204081632653, "percentage": 85.03, "elapsed_time": "12:15:52", "remaining_time": "2:09:30"}
{"current_steps": 760, "total_steps": 882, "loss": 0.6972, "lr": 5e-06, "epoch": 2.5850340136054424, "percentage": 86.17, "elapsed_time": "12:25:31", "remaining_time": "1:59:40"}
{"current_steps": 770, "total_steps": 882, "loss": 0.6988, "lr": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "12:35:10", "remaining_time": "1:49:50"}
{"current_steps": 780, "total_steps": 882, "loss": 0.6977, "lr": 5e-06, "epoch": 2.6530612244897958, "percentage": 88.44, "elapsed_time": "12:44:48", "remaining_time": "1:40:00"}
{"current_steps": 790, "total_steps": 882, "loss": 0.6987, "lr": 5e-06, "epoch": 2.687074829931973, "percentage": 89.57, "elapsed_time": "12:54:26", "remaining_time": "1:30:11"}
{"current_steps": 800, "total_steps": 882, "loss": 0.6982, "lr": 5e-06, "epoch": 2.7210884353741496, "percentage": 90.7, "elapsed_time": "13:04:03", "remaining_time": "1:20:22"}
{"current_steps": 810, "total_steps": 882, "loss": 0.7006, "lr": 5e-06, "epoch": 2.7551020408163263, "percentage": 91.84, "elapsed_time": "13:13:42", "remaining_time": "1:10:33"}
{"current_steps": 820, "total_steps": 882, "loss": 0.7038, "lr": 5e-06, "epoch": 2.7891156462585034, "percentage": 92.97, "elapsed_time": "13:23:20", "remaining_time": "1:00:44"}
{"current_steps": 830, "total_steps": 882, "loss": 0.7031, "lr": 5e-06, "epoch": 2.8231292517006805, "percentage": 94.1, "elapsed_time": "13:32:57", "remaining_time": "0:50:55"}
{"current_steps": 840, "total_steps": 882, "loss": 0.7001, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "13:42:35", "remaining_time": "0:41:07"}
{"current_steps": 850, "total_steps": 882, "loss": 0.6999, "lr": 5e-06, "epoch": 2.891156462585034, "percentage": 96.37, "elapsed_time": "13:52:13", "remaining_time": "0:31:19"}
{"current_steps": 860, "total_steps": 882, "loss": 0.7007, "lr": 5e-06, "epoch": 2.925170068027211, "percentage": 97.51, "elapsed_time": "14:01:53", "remaining_time": "0:21:32"}
{"current_steps": 870, "total_steps": 882, "loss": 0.7029, "lr": 5e-06, "epoch": 2.9591836734693877, "percentage": 98.64, "elapsed_time": "14:11:30", "remaining_time": "0:11:44"}
{"current_steps": 880, "total_steps": 882, "loss": 0.7006, "lr": 5e-06, "epoch": 2.9931972789115644, "percentage": 99.77, "elapsed_time": "14:21:09", "remaining_time": "0:01:57"}
{"current_steps": 882, "total_steps": 882, "eval_loss": 0.7735684514045715, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "14:29:33", "remaining_time": "0:00:00"}
{"current_steps": 882, "total_steps": 882, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "14:31:03", "remaining_time": "0:00:00"}