oh_v1.3_evol_instruct_x.125 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
ab03b83 verified
{"current_steps": 10, "total_steps": 792, "loss": 1.0395, "lr": 5e-06, "epoch": 0.03777148253068933, "percentage": 1.26, "elapsed_time": "0:05:24", "remaining_time": "7:02:57"}
{"current_steps": 20, "total_steps": 792, "loss": 0.9048, "lr": 5e-06, "epoch": 0.07554296506137866, "percentage": 2.53, "elapsed_time": "0:10:42", "remaining_time": "6:53:24"}
{"current_steps": 30, "total_steps": 792, "loss": 0.8676, "lr": 5e-06, "epoch": 0.11331444759206799, "percentage": 3.79, "elapsed_time": "0:16:02", "remaining_time": "6:47:37"}
{"current_steps": 40, "total_steps": 792, "loss": 0.8452, "lr": 5e-06, "epoch": 0.1510859301227573, "percentage": 5.05, "elapsed_time": "0:21:22", "remaining_time": "6:41:48"}
{"current_steps": 50, "total_steps": 792, "loss": 0.8261, "lr": 5e-06, "epoch": 0.18885741265344666, "percentage": 6.31, "elapsed_time": "0:26:41", "remaining_time": "6:36:06"}
{"current_steps": 60, "total_steps": 792, "loss": 0.8055, "lr": 5e-06, "epoch": 0.22662889518413598, "percentage": 7.58, "elapsed_time": "0:32:02", "remaining_time": "6:30:51"}
{"current_steps": 70, "total_steps": 792, "loss": 0.7953, "lr": 5e-06, "epoch": 0.26440037771482533, "percentage": 8.84, "elapsed_time": "0:37:22", "remaining_time": "6:25:29"}
{"current_steps": 80, "total_steps": 792, "loss": 0.786, "lr": 5e-06, "epoch": 0.3021718602455146, "percentage": 10.1, "elapsed_time": "0:42:39", "remaining_time": "6:19:35"}
{"current_steps": 90, "total_steps": 792, "loss": 0.7725, "lr": 5e-06, "epoch": 0.33994334277620397, "percentage": 11.36, "elapsed_time": "0:47:57", "remaining_time": "6:14:02"}
{"current_steps": 100, "total_steps": 792, "loss": 0.7813, "lr": 5e-06, "epoch": 0.3777148253068933, "percentage": 12.63, "elapsed_time": "0:53:17", "remaining_time": "6:08:44"}
{"current_steps": 110, "total_steps": 792, "loss": 0.7702, "lr": 5e-06, "epoch": 0.4154863078375826, "percentage": 13.89, "elapsed_time": "0:58:38", "remaining_time": "6:03:32"}
{"current_steps": 120, "total_steps": 792, "loss": 0.7601, "lr": 5e-06, "epoch": 0.45325779036827196, "percentage": 15.15, "elapsed_time": "1:03:58", "remaining_time": "5:58:15"}
{"current_steps": 130, "total_steps": 792, "loss": 0.765, "lr": 5e-06, "epoch": 0.4910292728989613, "percentage": 16.41, "elapsed_time": "1:09:16", "remaining_time": "5:52:46"}
{"current_steps": 140, "total_steps": 792, "loss": 0.7585, "lr": 5e-06, "epoch": 0.5288007554296507, "percentage": 17.68, "elapsed_time": "1:14:37", "remaining_time": "5:47:30"}
{"current_steps": 150, "total_steps": 792, "loss": 0.7582, "lr": 5e-06, "epoch": 0.56657223796034, "percentage": 18.94, "elapsed_time": "1:19:57", "remaining_time": "5:42:14"}
{"current_steps": 160, "total_steps": 792, "loss": 0.7535, "lr": 5e-06, "epoch": 0.6043437204910292, "percentage": 20.2, "elapsed_time": "1:25:19", "remaining_time": "5:37:01"}
{"current_steps": 170, "total_steps": 792, "loss": 0.7506, "lr": 5e-06, "epoch": 0.6421152030217187, "percentage": 21.46, "elapsed_time": "1:30:38", "remaining_time": "5:31:38"}
{"current_steps": 180, "total_steps": 792, "loss": 0.7538, "lr": 5e-06, "epoch": 0.6798866855524079, "percentage": 22.73, "elapsed_time": "1:35:59", "remaining_time": "5:26:21"}
{"current_steps": 190, "total_steps": 792, "loss": 0.7512, "lr": 5e-06, "epoch": 0.7176581680830972, "percentage": 23.99, "elapsed_time": "1:41:20", "remaining_time": "5:21:05"}
{"current_steps": 200, "total_steps": 792, "loss": 0.7432, "lr": 5e-06, "epoch": 0.7554296506137866, "percentage": 25.25, "elapsed_time": "1:46:41", "remaining_time": "5:15:47"}
{"current_steps": 210, "total_steps": 792, "loss": 0.7523, "lr": 5e-06, "epoch": 0.7932011331444759, "percentage": 26.52, "elapsed_time": "1:52:01", "remaining_time": "5:10:28"}
{"current_steps": 220, "total_steps": 792, "loss": 0.7475, "lr": 5e-06, "epoch": 0.8309726156751652, "percentage": 27.78, "elapsed_time": "1:57:22", "remaining_time": "5:05:09"}
{"current_steps": 230, "total_steps": 792, "loss": 0.7384, "lr": 5e-06, "epoch": 0.8687440982058546, "percentage": 29.04, "elapsed_time": "2:02:43", "remaining_time": "4:59:51"}
{"current_steps": 240, "total_steps": 792, "loss": 0.742, "lr": 5e-06, "epoch": 0.9065155807365439, "percentage": 30.3, "elapsed_time": "2:08:04", "remaining_time": "4:54:34"}
{"current_steps": 250, "total_steps": 792, "loss": 0.7415, "lr": 5e-06, "epoch": 0.9442870632672332, "percentage": 31.57, "elapsed_time": "2:13:25", "remaining_time": "4:49:15"}
{"current_steps": 260, "total_steps": 792, "loss": 0.7413, "lr": 5e-06, "epoch": 0.9820585457979226, "percentage": 32.83, "elapsed_time": "2:18:46", "remaining_time": "4:43:56"}
{"current_steps": 264, "total_steps": 792, "eval_loss": 0.7381541132926941, "epoch": 0.9971671388101983, "percentage": 33.33, "elapsed_time": "2:24:23", "remaining_time": "4:48:47"}
{"current_steps": 270, "total_steps": 792, "loss": 0.7317, "lr": 5e-06, "epoch": 1.019830028328612, "percentage": 34.09, "elapsed_time": "2:28:27", "remaining_time": "4:47:01"}
{"current_steps": 280, "total_steps": 792, "loss": 0.6852, "lr": 5e-06, "epoch": 1.0576015108593013, "percentage": 35.35, "elapsed_time": "2:33:45", "remaining_time": "4:41:09"}
{"current_steps": 290, "total_steps": 792, "loss": 0.6903, "lr": 5e-06, "epoch": 1.0953729933899905, "percentage": 36.62, "elapsed_time": "2:39:03", "remaining_time": "4:35:19"}
{"current_steps": 300, "total_steps": 792, "loss": 0.684, "lr": 5e-06, "epoch": 1.13314447592068, "percentage": 37.88, "elapsed_time": "2:44:20", "remaining_time": "4:29:30"}
{"current_steps": 310, "total_steps": 792, "loss": 0.6899, "lr": 5e-06, "epoch": 1.1709159584513693, "percentage": 39.14, "elapsed_time": "2:49:37", "remaining_time": "4:23:44"}
{"current_steps": 320, "total_steps": 792, "loss": 0.6886, "lr": 5e-06, "epoch": 1.2086874409820585, "percentage": 40.4, "elapsed_time": "2:54:56", "remaining_time": "4:18:02"}
{"current_steps": 330, "total_steps": 792, "loss": 0.6876, "lr": 5e-06, "epoch": 1.246458923512748, "percentage": 41.67, "elapsed_time": "3:00:13", "remaining_time": "4:12:19"}
{"current_steps": 340, "total_steps": 792, "loss": 0.6841, "lr": 5e-06, "epoch": 1.284230406043437, "percentage": 42.93, "elapsed_time": "3:05:31", "remaining_time": "4:06:37"}
{"current_steps": 350, "total_steps": 792, "loss": 0.6875, "lr": 5e-06, "epoch": 1.3220018885741265, "percentage": 44.19, "elapsed_time": "3:10:52", "remaining_time": "4:01:02"}
{"current_steps": 360, "total_steps": 792, "loss": 0.6835, "lr": 5e-06, "epoch": 1.3597733711048159, "percentage": 45.45, "elapsed_time": "3:16:09", "remaining_time": "3:55:23"}
{"current_steps": 370, "total_steps": 792, "loss": 0.6839, "lr": 5e-06, "epoch": 1.3975448536355053, "percentage": 46.72, "elapsed_time": "3:21:28", "remaining_time": "3:49:47"}
{"current_steps": 380, "total_steps": 792, "loss": 0.6888, "lr": 5e-06, "epoch": 1.4353163361661945, "percentage": 47.98, "elapsed_time": "3:26:48", "remaining_time": "3:44:13"}
{"current_steps": 390, "total_steps": 792, "loss": 0.6844, "lr": 5e-06, "epoch": 1.4730878186968839, "percentage": 49.24, "elapsed_time": "3:32:08", "remaining_time": "3:38:40"}
{"current_steps": 400, "total_steps": 792, "loss": 0.6835, "lr": 5e-06, "epoch": 1.510859301227573, "percentage": 50.51, "elapsed_time": "3:37:27", "remaining_time": "3:33:06"}
{"current_steps": 410, "total_steps": 792, "loss": 0.6894, "lr": 5e-06, "epoch": 1.5486307837582625, "percentage": 51.77, "elapsed_time": "3:42:46", "remaining_time": "3:27:33"}
{"current_steps": 420, "total_steps": 792, "loss": 0.6892, "lr": 5e-06, "epoch": 1.5864022662889519, "percentage": 53.03, "elapsed_time": "3:48:04", "remaining_time": "3:22:00"}
{"current_steps": 430, "total_steps": 792, "loss": 0.6854, "lr": 5e-06, "epoch": 1.6241737488196413, "percentage": 54.29, "elapsed_time": "3:53:22", "remaining_time": "3:16:28"}
{"current_steps": 440, "total_steps": 792, "loss": 0.6874, "lr": 5e-06, "epoch": 1.6619452313503305, "percentage": 55.56, "elapsed_time": "3:58:41", "remaining_time": "3:10:56"}
{"current_steps": 450, "total_steps": 792, "loss": 0.6891, "lr": 5e-06, "epoch": 1.6997167138810199, "percentage": 56.82, "elapsed_time": "4:04:00", "remaining_time": "3:05:26"}
{"current_steps": 460, "total_steps": 792, "loss": 0.6813, "lr": 5e-06, "epoch": 1.737488196411709, "percentage": 58.08, "elapsed_time": "4:09:18", "remaining_time": "2:59:55"}
{"current_steps": 470, "total_steps": 792, "loss": 0.6835, "lr": 5e-06, "epoch": 1.7752596789423984, "percentage": 59.34, "elapsed_time": "4:14:37", "remaining_time": "2:54:26"}
{"current_steps": 480, "total_steps": 792, "loss": 0.6835, "lr": 5e-06, "epoch": 1.8130311614730878, "percentage": 60.61, "elapsed_time": "4:19:57", "remaining_time": "2:48:58"}
{"current_steps": 490, "total_steps": 792, "loss": 0.68, "lr": 5e-06, "epoch": 1.8508026440037773, "percentage": 61.87, "elapsed_time": "4:25:16", "remaining_time": "2:43:29"}
{"current_steps": 500, "total_steps": 792, "loss": 0.6805, "lr": 5e-06, "epoch": 1.8885741265344664, "percentage": 63.13, "elapsed_time": "4:30:36", "remaining_time": "2:38:01"}
{"current_steps": 510, "total_steps": 792, "loss": 0.6821, "lr": 5e-06, "epoch": 1.9263456090651558, "percentage": 64.39, "elapsed_time": "4:35:57", "remaining_time": "2:32:35"}
{"current_steps": 520, "total_steps": 792, "loss": 0.6815, "lr": 5e-06, "epoch": 1.964117091595845, "percentage": 65.66, "elapsed_time": "4:41:16", "remaining_time": "2:27:07"}
{"current_steps": 529, "total_steps": 792, "eval_loss": 0.7243772149085999, "epoch": 1.9981114258734656, "percentage": 66.79, "elapsed_time": "4:49:11", "remaining_time": "2:23:46"}
{"current_steps": 530, "total_steps": 792, "loss": 0.7, "lr": 5e-06, "epoch": 2.0018885741265344, "percentage": 66.92, "elapsed_time": "4:50:48", "remaining_time": "2:23:45"}
{"current_steps": 540, "total_steps": 792, "loss": 0.6295, "lr": 5e-06, "epoch": 2.039660056657224, "percentage": 68.18, "elapsed_time": "4:56:06", "remaining_time": "2:18:11"}
{"current_steps": 550, "total_steps": 792, "loss": 0.6269, "lr": 5e-06, "epoch": 2.0774315391879132, "percentage": 69.44, "elapsed_time": "5:01:27", "remaining_time": "2:12:38"}
{"current_steps": 560, "total_steps": 792, "loss": 0.6306, "lr": 5e-06, "epoch": 2.1152030217186026, "percentage": 70.71, "elapsed_time": "5:06:47", "remaining_time": "2:07:05"}
{"current_steps": 570, "total_steps": 792, "loss": 0.6302, "lr": 5e-06, "epoch": 2.1529745042492916, "percentage": 71.97, "elapsed_time": "5:12:08", "remaining_time": "2:01:34"}
{"current_steps": 580, "total_steps": 792, "loss": 0.6278, "lr": 5e-06, "epoch": 2.190745986779981, "percentage": 73.23, "elapsed_time": "5:17:28", "remaining_time": "1:56:02"}
{"current_steps": 590, "total_steps": 792, "loss": 0.6364, "lr": 5e-06, "epoch": 2.2285174693106704, "percentage": 74.49, "elapsed_time": "5:22:49", "remaining_time": "1:50:31"}
{"current_steps": 600, "total_steps": 792, "loss": 0.6326, "lr": 5e-06, "epoch": 2.26628895184136, "percentage": 75.76, "elapsed_time": "5:28:09", "remaining_time": "1:45:00"}
{"current_steps": 610, "total_steps": 792, "loss": 0.6322, "lr": 5e-06, "epoch": 2.304060434372049, "percentage": 77.02, "elapsed_time": "5:33:30", "remaining_time": "1:39:30"}
{"current_steps": 620, "total_steps": 792, "loss": 0.632, "lr": 5e-06, "epoch": 2.3418319169027386, "percentage": 78.28, "elapsed_time": "5:38:49", "remaining_time": "1:33:59"}
{"current_steps": 630, "total_steps": 792, "loss": 0.6359, "lr": 5e-06, "epoch": 2.3796033994334276, "percentage": 79.55, "elapsed_time": "5:44:10", "remaining_time": "1:28:30"}
{"current_steps": 640, "total_steps": 792, "loss": 0.6351, "lr": 5e-06, "epoch": 2.417374881964117, "percentage": 80.81, "elapsed_time": "5:49:31", "remaining_time": "1:23:00"}
{"current_steps": 650, "total_steps": 792, "loss": 0.6304, "lr": 5e-06, "epoch": 2.4551463644948064, "percentage": 82.07, "elapsed_time": "5:54:52", "remaining_time": "1:17:31"}
{"current_steps": 660, "total_steps": 792, "loss": 0.6348, "lr": 5e-06, "epoch": 2.492917847025496, "percentage": 83.33, "elapsed_time": "6:00:13", "remaining_time": "1:12:02"}
{"current_steps": 670, "total_steps": 792, "loss": 0.6335, "lr": 5e-06, "epoch": 2.530689329556185, "percentage": 84.6, "elapsed_time": "6:05:34", "remaining_time": "1:06:33"}
{"current_steps": 680, "total_steps": 792, "loss": 0.6349, "lr": 5e-06, "epoch": 2.568460812086874, "percentage": 85.86, "elapsed_time": "6:10:54", "remaining_time": "1:01:05"}
{"current_steps": 690, "total_steps": 792, "loss": 0.6285, "lr": 5e-06, "epoch": 2.6062322946175636, "percentage": 87.12, "elapsed_time": "6:16:15", "remaining_time": "0:55:37"}
{"current_steps": 700, "total_steps": 792, "loss": 0.6341, "lr": 5e-06, "epoch": 2.644003777148253, "percentage": 88.38, "elapsed_time": "6:21:36", "remaining_time": "0:50:09"}
{"current_steps": 710, "total_steps": 792, "loss": 0.6393, "lr": 5e-06, "epoch": 2.6817752596789424, "percentage": 89.65, "elapsed_time": "6:26:56", "remaining_time": "0:44:41"}
{"current_steps": 720, "total_steps": 792, "loss": 0.6397, "lr": 5e-06, "epoch": 2.7195467422096318, "percentage": 90.91, "elapsed_time": "6:32:15", "remaining_time": "0:39:13"}
{"current_steps": 730, "total_steps": 792, "loss": 0.6356, "lr": 5e-06, "epoch": 2.757318224740321, "percentage": 92.17, "elapsed_time": "6:37:34", "remaining_time": "0:33:45"}
{"current_steps": 740, "total_steps": 792, "loss": 0.6394, "lr": 5e-06, "epoch": 2.7950897072710106, "percentage": 93.43, "elapsed_time": "6:42:53", "remaining_time": "0:28:18"}
{"current_steps": 750, "total_steps": 792, "loss": 0.6321, "lr": 5e-06, "epoch": 2.8328611898017, "percentage": 94.7, "elapsed_time": "6:48:14", "remaining_time": "0:22:51"}
{"current_steps": 760, "total_steps": 792, "loss": 0.6351, "lr": 5e-06, "epoch": 2.870632672332389, "percentage": 95.96, "elapsed_time": "6:53:33", "remaining_time": "0:17:24"}
{"current_steps": 770, "total_steps": 792, "loss": 0.6333, "lr": 5e-06, "epoch": 2.9084041548630784, "percentage": 97.22, "elapsed_time": "6:58:54", "remaining_time": "0:11:58"}
{"current_steps": 780, "total_steps": 792, "loss": 0.6412, "lr": 5e-06, "epoch": 2.9461756373937678, "percentage": 98.48, "elapsed_time": "7:04:14", "remaining_time": "0:06:31"}
{"current_steps": 790, "total_steps": 792, "loss": 0.6392, "lr": 5e-06, "epoch": 2.983947119924457, "percentage": 99.75, "elapsed_time": "7:09:35", "remaining_time": "0:01:05"}
{"current_steps": 792, "total_steps": 792, "eval_loss": 0.7273694276809692, "epoch": 2.991501416430595, "percentage": 100.0, "elapsed_time": "7:14:54", "remaining_time": "0:00:00"}
{"current_steps": 792, "total_steps": 792, "epoch": 2.991501416430595, "percentage": 100.0, "elapsed_time": "7:16:28", "remaining_time": "0:00:00"}