oh_v1-2_only_slim_orca / trainer_log.jsonl
esfrankel17's picture
Training in progress, epoch 2
0f59f2a verified
{"current_steps": 10, "total_steps": 525, "loss": 1.1357, "learning_rate": 5e-06, "epoch": 0.05706134094151213, "percentage": 1.9, "elapsed_time": "0:05:19", "remaining_time": "4:33:59"}
{"current_steps": 20, "total_steps": 525, "loss": 0.9928, "learning_rate": 5e-06, "epoch": 0.11412268188302425, "percentage": 3.81, "elapsed_time": "0:10:32", "remaining_time": "4:26:20"}
{"current_steps": 30, "total_steps": 525, "loss": 0.9322, "learning_rate": 5e-06, "epoch": 0.17118402282453637, "percentage": 5.71, "elapsed_time": "0:15:41", "remaining_time": "4:18:58"}
{"current_steps": 40, "total_steps": 525, "loss": 0.8899, "learning_rate": 5e-06, "epoch": 0.2282453637660485, "percentage": 7.62, "elapsed_time": "0:20:49", "remaining_time": "4:12:33"}
{"current_steps": 50, "total_steps": 525, "loss": 0.8676, "learning_rate": 5e-06, "epoch": 0.28530670470756064, "percentage": 9.52, "elapsed_time": "0:25:57", "remaining_time": "4:06:37"}
{"current_steps": 60, "total_steps": 525, "loss": 0.8394, "learning_rate": 5e-06, "epoch": 0.34236804564907275, "percentage": 11.43, "elapsed_time": "0:31:05", "remaining_time": "4:01:00"}
{"current_steps": 70, "total_steps": 525, "loss": 0.8166, "learning_rate": 5e-06, "epoch": 0.39942938659058486, "percentage": 13.33, "elapsed_time": "0:36:14", "remaining_time": "3:55:31"}
{"current_steps": 80, "total_steps": 525, "loss": 0.8095, "learning_rate": 5e-06, "epoch": 0.456490727532097, "percentage": 15.24, "elapsed_time": "0:41:24", "remaining_time": "3:50:17"}
{"current_steps": 90, "total_steps": 525, "loss": 0.8023, "learning_rate": 5e-06, "epoch": 0.5135520684736091, "percentage": 17.14, "elapsed_time": "0:46:33", "remaining_time": "3:45:02"}
{"current_steps": 100, "total_steps": 525, "loss": 0.7912, "learning_rate": 5e-06, "epoch": 0.5706134094151213, "percentage": 19.05, "elapsed_time": "0:51:43", "remaining_time": "3:39:49"}
{"current_steps": 110, "total_steps": 525, "loss": 0.7844, "learning_rate": 5e-06, "epoch": 0.6276747503566333, "percentage": 20.95, "elapsed_time": "0:56:52", "remaining_time": "3:34:34"}
{"current_steps": 120, "total_steps": 525, "loss": 0.7821, "learning_rate": 5e-06, "epoch": 0.6847360912981455, "percentage": 22.86, "elapsed_time": "1:02:01", "remaining_time": "3:29:19"}
{"current_steps": 130, "total_steps": 525, "loss": 0.7761, "learning_rate": 5e-06, "epoch": 0.7417974322396577, "percentage": 24.76, "elapsed_time": "1:07:10", "remaining_time": "3:24:05"}
{"current_steps": 140, "total_steps": 525, "loss": 0.7747, "learning_rate": 5e-06, "epoch": 0.7988587731811697, "percentage": 26.67, "elapsed_time": "1:12:19", "remaining_time": "3:18:53"}
{"current_steps": 150, "total_steps": 525, "loss": 0.7722, "learning_rate": 5e-06, "epoch": 0.8559201141226819, "percentage": 28.57, "elapsed_time": "1:17:26", "remaining_time": "3:13:36"}
{"current_steps": 160, "total_steps": 525, "loss": 0.7698, "learning_rate": 5e-06, "epoch": 0.912981455064194, "percentage": 30.48, "elapsed_time": "1:22:40", "remaining_time": "3:08:36"}
{"current_steps": 170, "total_steps": 525, "loss": 0.7665, "learning_rate": 5e-06, "epoch": 0.9700427960057061, "percentage": 32.38, "elapsed_time": "1:27:55", "remaining_time": "3:03:35"}
{"current_steps": 175, "total_steps": 525, "eval_loss": 0.7644989490509033, "epoch": 0.9985734664764622, "percentage": 33.33, "elapsed_time": "1:32:35", "remaining_time": "3:05:11"}
{"current_steps": 180, "total_steps": 525, "loss": 0.7951, "learning_rate": 5e-06, "epoch": 1.027817403708987, "percentage": 34.29, "elapsed_time": "1:36:15", "remaining_time": "3:04:29"}
{"current_steps": 190, "total_steps": 525, "loss": 0.7077, "learning_rate": 5e-06, "epoch": 1.0848787446504993, "percentage": 36.19, "elapsed_time": "1:41:24", "remaining_time": "2:58:48"}
{"current_steps": 200, "total_steps": 525, "loss": 0.7039, "learning_rate": 5e-06, "epoch": 1.1419400855920114, "percentage": 38.1, "elapsed_time": "1:46:33", "remaining_time": "2:53:09"}
{"current_steps": 210, "total_steps": 525, "loss": 0.7018, "learning_rate": 5e-06, "epoch": 1.1990014265335236, "percentage": 40.0, "elapsed_time": "1:51:42", "remaining_time": "2:47:34"}
{"current_steps": 220, "total_steps": 525, "loss": 0.6986, "learning_rate": 5e-06, "epoch": 1.2560627674750355, "percentage": 41.9, "elapsed_time": "1:56:51", "remaining_time": "2:42:00"}
{"current_steps": 230, "total_steps": 525, "loss": 0.7016, "learning_rate": 5e-06, "epoch": 1.313124108416548, "percentage": 43.81, "elapsed_time": "2:01:59", "remaining_time": "2:36:28"}
{"current_steps": 240, "total_steps": 525, "loss": 0.7005, "learning_rate": 5e-06, "epoch": 1.3701854493580599, "percentage": 45.71, "elapsed_time": "2:07:07", "remaining_time": "2:30:58"}
{"current_steps": 250, "total_steps": 525, "loss": 0.7047, "learning_rate": 5e-06, "epoch": 1.427246790299572, "percentage": 47.62, "elapsed_time": "2:12:17", "remaining_time": "2:25:31"}
{"current_steps": 260, "total_steps": 525, "loss": 0.7011, "learning_rate": 5e-06, "epoch": 1.4843081312410842, "percentage": 49.52, "elapsed_time": "2:17:27", "remaining_time": "2:20:06"}
{"current_steps": 270, "total_steps": 525, "loss": 0.6988, "learning_rate": 5e-06, "epoch": 1.5413694721825963, "percentage": 51.43, "elapsed_time": "2:22:35", "remaining_time": "2:14:40"}
{"current_steps": 280, "total_steps": 525, "loss": 0.6987, "learning_rate": 5e-06, "epoch": 1.5984308131241085, "percentage": 53.33, "elapsed_time": "2:27:45", "remaining_time": "2:09:17"}
{"current_steps": 290, "total_steps": 525, "loss": 0.7045, "learning_rate": 5e-06, "epoch": 1.6554921540656204, "percentage": 55.24, "elapsed_time": "2:32:56", "remaining_time": "2:03:55"}
{"current_steps": 300, "total_steps": 525, "loss": 0.6981, "learning_rate": 5e-06, "epoch": 1.7125534950071328, "percentage": 57.14, "elapsed_time": "2:38:05", "remaining_time": "1:58:33"}
{"current_steps": 310, "total_steps": 525, "loss": 0.7043, "learning_rate": 5e-06, "epoch": 1.7696148359486448, "percentage": 59.05, "elapsed_time": "2:43:16", "remaining_time": "1:53:14"}
{"current_steps": 320, "total_steps": 525, "loss": 0.7002, "learning_rate": 5e-06, "epoch": 1.826676176890157, "percentage": 60.95, "elapsed_time": "2:48:26", "remaining_time": "1:47:54"}
{"current_steps": 330, "total_steps": 525, "loss": 0.7029, "learning_rate": 5e-06, "epoch": 1.883737517831669, "percentage": 62.86, "elapsed_time": "2:53:35", "remaining_time": "1:42:34"}
{"current_steps": 340, "total_steps": 525, "loss": 0.7038, "learning_rate": 5e-06, "epoch": 1.940798858773181, "percentage": 64.76, "elapsed_time": "2:58:43", "remaining_time": "1:37:15"}
{"current_steps": 350, "total_steps": 525, "loss": 0.6988, "learning_rate": 5e-06, "epoch": 1.9978601997146934, "percentage": 66.67, "elapsed_time": "3:03:52", "remaining_time": "1:31:56"}
{"current_steps": 350, "total_steps": 525, "eval_loss": 0.752321720123291, "epoch": 1.9978601997146934, "percentage": 66.67, "elapsed_time": "3:05:58", "remaining_time": "1:32:59"}
{"current_steps": 360, "total_steps": 525, "loss": 0.697, "learning_rate": 5e-06, "epoch": 2.055634807417974, "percentage": 68.57, "elapsed_time": "3:11:58", "remaining_time": "1:27:59"}
{"current_steps": 370, "total_steps": 525, "loss": 0.6309, "learning_rate": 5e-06, "epoch": 2.1126961483594866, "percentage": 70.48, "elapsed_time": "3:17:07", "remaining_time": "1:22:34"}
{"current_steps": 380, "total_steps": 525, "loss": 0.6301, "learning_rate": 5e-06, "epoch": 2.1697574893009985, "percentage": 72.38, "elapsed_time": "3:22:15", "remaining_time": "1:17:10"}
{"current_steps": 390, "total_steps": 525, "loss": 0.6274, "learning_rate": 5e-06, "epoch": 2.226818830242511, "percentage": 74.29, "elapsed_time": "3:27:25", "remaining_time": "1:11:47"}
{"current_steps": 400, "total_steps": 525, "loss": 0.631, "learning_rate": 5e-06, "epoch": 2.283880171184023, "percentage": 76.19, "elapsed_time": "3:32:34", "remaining_time": "1:06:25"}
{"current_steps": 410, "total_steps": 525, "loss": 0.6321, "learning_rate": 5e-06, "epoch": 2.340941512125535, "percentage": 78.1, "elapsed_time": "3:37:44", "remaining_time": "1:01:04"}
{"current_steps": 420, "total_steps": 525, "loss": 0.6352, "learning_rate": 5e-06, "epoch": 2.398002853067047, "percentage": 80.0, "elapsed_time": "3:42:53", "remaining_time": "0:55:43"}
{"current_steps": 430, "total_steps": 525, "loss": 0.6356, "learning_rate": 5e-06, "epoch": 2.455064194008559, "percentage": 81.9, "elapsed_time": "3:48:02", "remaining_time": "0:50:22"}
{"current_steps": 440, "total_steps": 525, "loss": 0.635, "learning_rate": 5e-06, "epoch": 2.512125534950071, "percentage": 83.81, "elapsed_time": "3:53:11", "remaining_time": "0:45:02"}
{"current_steps": 450, "total_steps": 525, "loss": 0.6349, "learning_rate": 5e-06, "epoch": 2.5691868758915835, "percentage": 85.71, "elapsed_time": "3:58:19", "remaining_time": "0:39:43"}
{"current_steps": 460, "total_steps": 525, "loss": 0.6355, "learning_rate": 5e-06, "epoch": 2.626248216833096, "percentage": 87.62, "elapsed_time": "4:03:28", "remaining_time": "0:34:24"}
{"current_steps": 470, "total_steps": 525, "loss": 0.6377, "learning_rate": 5e-06, "epoch": 2.683309557774608, "percentage": 89.52, "elapsed_time": "4:08:36", "remaining_time": "0:29:05"}
{"current_steps": 480, "total_steps": 525, "loss": 0.6367, "learning_rate": 5e-06, "epoch": 2.7403708987161197, "percentage": 91.43, "elapsed_time": "4:13:43", "remaining_time": "0:23:47"}
{"current_steps": 490, "total_steps": 525, "loss": 0.6382, "learning_rate": 5e-06, "epoch": 2.797432239657632, "percentage": 93.33, "elapsed_time": "4:18:50", "remaining_time": "0:18:29"}
{"current_steps": 500, "total_steps": 525, "loss": 0.6357, "learning_rate": 5e-06, "epoch": 2.854493580599144, "percentage": 95.24, "elapsed_time": "4:23:57", "remaining_time": "0:13:11"}
{"current_steps": 510, "total_steps": 525, "loss": 0.6363, "learning_rate": 5e-06, "epoch": 2.911554921540656, "percentage": 97.14, "elapsed_time": "4:29:05", "remaining_time": "0:07:54"}
{"current_steps": 520, "total_steps": 525, "loss": 0.644, "learning_rate": 5e-06, "epoch": 2.9686162624821684, "percentage": 99.05, "elapsed_time": "4:34:14", "remaining_time": "0:02:38"}
{"current_steps": 525, "total_steps": 525, "eval_loss": 0.7613628506660461, "epoch": 2.9971469329529246, "percentage": 100.0, "elapsed_time": "4:39:50", "remaining_time": "0:00:00"}
{"current_steps": 525, "total_steps": 525, "epoch": 2.9971469329529246, "percentage": 100.0, "elapsed_time": "4:41:03", "remaining_time": "0:00:00"}