hp_ablations_qwen_bsz1024 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
8d89333 verified
{"current_steps": 10, "total_steps": 657, "loss": 0.7529, "learning_rate": 5e-06, "epoch": 0.045584045584045586, "percentage": 1.52, "elapsed_time": "0:08:54", "remaining_time": "9:36:19"}
{"current_steps": 20, "total_steps": 657, "loss": 0.6963, "learning_rate": 5e-06, "epoch": 0.09116809116809117, "percentage": 3.04, "elapsed_time": "0:17:44", "remaining_time": "9:25:07"}
{"current_steps": 30, "total_steps": 657, "loss": 0.6838, "learning_rate": 5e-06, "epoch": 0.13675213675213677, "percentage": 4.57, "elapsed_time": "0:26:34", "remaining_time": "9:15:33"}
{"current_steps": 40, "total_steps": 657, "loss": 0.6731, "learning_rate": 5e-06, "epoch": 0.18233618233618235, "percentage": 6.09, "elapsed_time": "0:35:25", "remaining_time": "9:06:21"}
{"current_steps": 50, "total_steps": 657, "loss": 0.6568, "learning_rate": 5e-06, "epoch": 0.22792022792022792, "percentage": 7.61, "elapsed_time": "0:44:15", "remaining_time": "8:57:15"}
{"current_steps": 60, "total_steps": 657, "loss": 0.6482, "learning_rate": 5e-06, "epoch": 0.27350427350427353, "percentage": 9.13, "elapsed_time": "0:53:05", "remaining_time": "8:48:15"}
{"current_steps": 70, "total_steps": 657, "loss": 0.6508, "learning_rate": 5e-06, "epoch": 0.3190883190883191, "percentage": 10.65, "elapsed_time": "1:01:55", "remaining_time": "8:39:18"}
{"current_steps": 80, "total_steps": 657, "loss": 0.6449, "learning_rate": 5e-06, "epoch": 0.3646723646723647, "percentage": 12.18, "elapsed_time": "1:10:46", "remaining_time": "8:30:24"}
{"current_steps": 90, "total_steps": 657, "loss": 0.6411, "learning_rate": 5e-06, "epoch": 0.41025641025641024, "percentage": 13.7, "elapsed_time": "1:19:35", "remaining_time": "8:21:26"}
{"current_steps": 100, "total_steps": 657, "loss": 0.6402, "learning_rate": 5e-06, "epoch": 0.45584045584045585, "percentage": 15.22, "elapsed_time": "1:28:26", "remaining_time": "8:12:34"}
{"current_steps": 110, "total_steps": 657, "loss": 0.6422, "learning_rate": 5e-06, "epoch": 0.5014245014245015, "percentage": 16.74, "elapsed_time": "1:37:15", "remaining_time": "8:03:40"}
{"current_steps": 120, "total_steps": 657, "loss": 0.6374, "learning_rate": 5e-06, "epoch": 0.5470085470085471, "percentage": 18.26, "elapsed_time": "1:46:06", "remaining_time": "7:54:50"}
{"current_steps": 130, "total_steps": 657, "loss": 0.6395, "learning_rate": 5e-06, "epoch": 0.5925925925925926, "percentage": 19.79, "elapsed_time": "1:54:57", "remaining_time": "7:46:00"}
{"current_steps": 140, "total_steps": 657, "loss": 0.6412, "learning_rate": 5e-06, "epoch": 0.6381766381766382, "percentage": 21.31, "elapsed_time": "2:03:47", "remaining_time": "7:37:09"}
{"current_steps": 150, "total_steps": 657, "loss": 0.6337, "learning_rate": 5e-06, "epoch": 0.6837606837606838, "percentage": 22.83, "elapsed_time": "2:12:38", "remaining_time": "7:28:19"}
{"current_steps": 160, "total_steps": 657, "loss": 0.6333, "learning_rate": 5e-06, "epoch": 0.7293447293447294, "percentage": 24.35, "elapsed_time": "2:21:28", "remaining_time": "7:19:27"}
{"current_steps": 170, "total_steps": 657, "loss": 0.633, "learning_rate": 5e-06, "epoch": 0.7749287749287749, "percentage": 25.88, "elapsed_time": "2:30:19", "remaining_time": "7:10:37"}
{"current_steps": 180, "total_steps": 657, "loss": 0.6386, "learning_rate": 5e-06, "epoch": 0.8205128205128205, "percentage": 27.4, "elapsed_time": "2:39:09", "remaining_time": "7:01:46"}
{"current_steps": 190, "total_steps": 657, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 0.8660968660968661, "percentage": 28.92, "elapsed_time": "2:47:59", "remaining_time": "6:52:55"}
{"current_steps": 200, "total_steps": 657, "loss": 0.6408, "learning_rate": 5e-06, "epoch": 0.9116809116809117, "percentage": 30.44, "elapsed_time": "2:56:49", "remaining_time": "6:44:03"}
{"current_steps": 210, "total_steps": 657, "loss": 0.6322, "learning_rate": 5e-06, "epoch": 0.9572649572649573, "percentage": 31.96, "elapsed_time": "3:05:39", "remaining_time": "6:35:11"}
{"current_steps": 219, "total_steps": 657, "eval_loss": 0.6290858387947083, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "3:17:38", "remaining_time": "6:35:16"}
{"current_steps": 220, "total_steps": 657, "loss": 0.6672, "learning_rate": 5e-06, "epoch": 1.002849002849003, "percentage": 33.49, "elapsed_time": "3:19:02", "remaining_time": "6:35:21"}
{"current_steps": 230, "total_steps": 657, "loss": 0.6126, "learning_rate": 5e-06, "epoch": 1.0484330484330484, "percentage": 35.01, "elapsed_time": "3:27:53", "remaining_time": "6:25:57"}
{"current_steps": 240, "total_steps": 657, "loss": 0.6122, "learning_rate": 5e-06, "epoch": 1.0940170940170941, "percentage": 36.53, "elapsed_time": "3:36:44", "remaining_time": "6:16:35"}
{"current_steps": 250, "total_steps": 657, "loss": 0.6147, "learning_rate": 5e-06, "epoch": 1.1396011396011396, "percentage": 38.05, "elapsed_time": "3:45:34", "remaining_time": "6:07:14"}
{"current_steps": 260, "total_steps": 657, "loss": 0.6104, "learning_rate": 5e-06, "epoch": 1.1851851851851851, "percentage": 39.57, "elapsed_time": "3:54:25", "remaining_time": "5:57:57"}
{"current_steps": 270, "total_steps": 657, "loss": 0.6109, "learning_rate": 5e-06, "epoch": 1.2307692307692308, "percentage": 41.1, "elapsed_time": "4:03:17", "remaining_time": "5:48:43"}
{"current_steps": 280, "total_steps": 657, "loss": 0.6137, "learning_rate": 5e-06, "epoch": 1.2763532763532763, "percentage": 42.62, "elapsed_time": "4:12:08", "remaining_time": "5:39:29"}
{"current_steps": 290, "total_steps": 657, "loss": 0.6102, "learning_rate": 5e-06, "epoch": 1.3219373219373218, "percentage": 44.14, "elapsed_time": "4:21:00", "remaining_time": "5:30:18"}
{"current_steps": 300, "total_steps": 657, "loss": 0.609, "learning_rate": 5e-06, "epoch": 1.3675213675213675, "percentage": 45.66, "elapsed_time": "4:29:51", "remaining_time": "5:21:07"}
{"current_steps": 310, "total_steps": 657, "loss": 0.613, "learning_rate": 5e-06, "epoch": 1.413105413105413, "percentage": 47.18, "elapsed_time": "4:38:42", "remaining_time": "5:11:58"}
{"current_steps": 320, "total_steps": 657, "loss": 0.6105, "learning_rate": 5e-06, "epoch": 1.4586894586894588, "percentage": 48.71, "elapsed_time": "4:47:33", "remaining_time": "5:02:49"}
{"current_steps": 330, "total_steps": 657, "loss": 0.6049, "learning_rate": 5e-06, "epoch": 1.5042735042735043, "percentage": 50.23, "elapsed_time": "4:56:24", "remaining_time": "4:53:42"}
{"current_steps": 340, "total_steps": 657, "loss": 0.6081, "learning_rate": 5e-06, "epoch": 1.54985754985755, "percentage": 51.75, "elapsed_time": "5:05:16", "remaining_time": "4:44:37"}
{"current_steps": 350, "total_steps": 657, "loss": 0.6129, "learning_rate": 5e-06, "epoch": 1.5954415954415955, "percentage": 53.27, "elapsed_time": "5:14:08", "remaining_time": "4:35:32"}
{"current_steps": 360, "total_steps": 657, "loss": 0.6092, "learning_rate": 5e-06, "epoch": 1.641025641025641, "percentage": 54.79, "elapsed_time": "5:22:59", "remaining_time": "4:26:27"}
{"current_steps": 370, "total_steps": 657, "loss": 0.6057, "learning_rate": 5e-06, "epoch": 1.6866096866096867, "percentage": 56.32, "elapsed_time": "5:31:50", "remaining_time": "4:17:23"}
{"current_steps": 380, "total_steps": 657, "loss": 0.6065, "learning_rate": 5e-06, "epoch": 1.7321937321937322, "percentage": 57.84, "elapsed_time": "5:40:41", "remaining_time": "4:08:20"}
{"current_steps": 390, "total_steps": 657, "loss": 0.6075, "learning_rate": 5e-06, "epoch": 1.7777777777777777, "percentage": 59.36, "elapsed_time": "5:49:33", "remaining_time": "3:59:18"}
{"current_steps": 400, "total_steps": 657, "loss": 0.6028, "learning_rate": 5e-06, "epoch": 1.8233618233618234, "percentage": 60.88, "elapsed_time": "5:58:24", "remaining_time": "3:50:16"}
{"current_steps": 410, "total_steps": 657, "loss": 0.6003, "learning_rate": 5e-06, "epoch": 1.868945868945869, "percentage": 62.4, "elapsed_time": "6:07:14", "remaining_time": "3:41:14"}
{"current_steps": 420, "total_steps": 657, "loss": 0.6067, "learning_rate": 5e-06, "epoch": 1.9145299145299144, "percentage": 63.93, "elapsed_time": "6:16:05", "remaining_time": "3:32:13"}
{"current_steps": 430, "total_steps": 657, "loss": 0.6083, "learning_rate": 5e-06, "epoch": 1.96011396011396, "percentage": 65.45, "elapsed_time": "6:24:56", "remaining_time": "3:23:12"}
{"current_steps": 438, "total_steps": 657, "eval_loss": 0.6215006709098816, "epoch": 1.9965811965811966, "percentage": 66.67, "elapsed_time": "6:36:21", "remaining_time": "3:18:10"}
{"current_steps": 440, "total_steps": 657, "loss": 0.6421, "learning_rate": 5e-06, "epoch": 2.005698005698006, "percentage": 66.97, "elapsed_time": "6:38:26", "remaining_time": "3:16:30"}
{"current_steps": 450, "total_steps": 657, "loss": 0.5803, "learning_rate": 5e-06, "epoch": 2.051282051282051, "percentage": 68.49, "elapsed_time": "6:47:18", "remaining_time": "3:07:21"}
{"current_steps": 460, "total_steps": 657, "loss": 0.5869, "learning_rate": 5e-06, "epoch": 2.096866096866097, "percentage": 70.02, "elapsed_time": "6:56:09", "remaining_time": "2:58:13"}
{"current_steps": 470, "total_steps": 657, "loss": 0.5845, "learning_rate": 5e-06, "epoch": 2.1424501424501425, "percentage": 71.54, "elapsed_time": "7:05:00", "remaining_time": "2:49:05"}
{"current_steps": 480, "total_steps": 657, "loss": 0.5837, "learning_rate": 5e-06, "epoch": 2.1880341880341883, "percentage": 73.06, "elapsed_time": "7:13:50", "remaining_time": "2:39:58"}
{"current_steps": 490, "total_steps": 657, "loss": 0.5828, "learning_rate": 5e-06, "epoch": 2.2336182336182335, "percentage": 74.58, "elapsed_time": "7:22:42", "remaining_time": "2:30:52"}
{"current_steps": 500, "total_steps": 657, "loss": 0.5831, "learning_rate": 5e-06, "epoch": 2.2792022792022792, "percentage": 76.1, "elapsed_time": "7:31:33", "remaining_time": "2:21:47"}
{"current_steps": 510, "total_steps": 657, "loss": 0.5838, "learning_rate": 5e-06, "epoch": 2.324786324786325, "percentage": 77.63, "elapsed_time": "7:40:25", "remaining_time": "2:12:42"}
{"current_steps": 520, "total_steps": 657, "loss": 0.586, "learning_rate": 5e-06, "epoch": 2.3703703703703702, "percentage": 79.15, "elapsed_time": "7:49:16", "remaining_time": "2:03:38"}
{"current_steps": 530, "total_steps": 657, "loss": 0.5883, "learning_rate": 5e-06, "epoch": 2.415954415954416, "percentage": 80.67, "elapsed_time": "7:58:07", "remaining_time": "1:54:34"}
{"current_steps": 540, "total_steps": 657, "loss": 0.5927, "learning_rate": 5e-06, "epoch": 2.4615384615384617, "percentage": 82.19, "elapsed_time": "8:06:58", "remaining_time": "1:45:30"}
{"current_steps": 550, "total_steps": 657, "loss": 0.5914, "learning_rate": 5e-06, "epoch": 2.5071225071225074, "percentage": 83.71, "elapsed_time": "8:15:49", "remaining_time": "1:36:27"}
{"current_steps": 560, "total_steps": 657, "loss": 0.5859, "learning_rate": 5e-06, "epoch": 2.5527065527065527, "percentage": 85.24, "elapsed_time": "8:24:39", "remaining_time": "1:27:24"}
{"current_steps": 570, "total_steps": 657, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 2.5982905982905984, "percentage": 86.76, "elapsed_time": "8:33:30", "remaining_time": "1:18:22"}
{"current_steps": 580, "total_steps": 657, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 2.6438746438746437, "percentage": 88.28, "elapsed_time": "8:42:20", "remaining_time": "1:09:20"}
{"current_steps": 590, "total_steps": 657, "loss": 0.5865, "learning_rate": 5e-06, "epoch": 2.6894586894586894, "percentage": 89.8, "elapsed_time": "8:51:11", "remaining_time": "1:00:19"}
{"current_steps": 600, "total_steps": 657, "loss": 0.5862, "learning_rate": 5e-06, "epoch": 2.735042735042735, "percentage": 91.32, "elapsed_time": "9:00:03", "remaining_time": "0:51:18"}
{"current_steps": 610, "total_steps": 657, "loss": 0.5856, "learning_rate": 5e-06, "epoch": 2.780626780626781, "percentage": 92.85, "elapsed_time": "9:08:55", "remaining_time": "0:42:17"}
{"current_steps": 620, "total_steps": 657, "loss": 0.5874, "learning_rate": 5e-06, "epoch": 2.826210826210826, "percentage": 94.37, "elapsed_time": "9:17:47", "remaining_time": "0:33:17"}
{"current_steps": 630, "total_steps": 657, "loss": 0.5889, "learning_rate": 5e-06, "epoch": 2.871794871794872, "percentage": 95.89, "elapsed_time": "9:26:38", "remaining_time": "0:24:17"}
{"current_steps": 640, "total_steps": 657, "loss": 0.585, "learning_rate": 5e-06, "epoch": 2.9173789173789175, "percentage": 97.41, "elapsed_time": "9:35:29", "remaining_time": "0:15:17"}
{"current_steps": 650, "total_steps": 657, "loss": 0.58, "learning_rate": 5e-06, "epoch": 2.962962962962963, "percentage": 98.93, "elapsed_time": "9:44:20", "remaining_time": "0:06:17"}
{"current_steps": 657, "total_steps": 657, "eval_loss": 0.6190248131752014, "epoch": 2.994871794871795, "percentage": 100.0, "elapsed_time": "9:55:11", "remaining_time": "0:00:00"}
{"current_steps": 657, "total_steps": 657, "epoch": 2.994871794871795, "percentage": 100.0, "elapsed_time": "9:56:16", "remaining_time": "0:00:00"}