oh_v1.3_alpaca_x.5 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 3
f9bd3ef verified
{"current_steps": 10, "total_steps": 813, "loss": 1.0277, "lr": 5e-06, "epoch": 0.03690036900369004, "percentage": 1.23, "elapsed_time": "0:09:41", "remaining_time": "12:57:45"}
{"current_steps": 20, "total_steps": 813, "loss": 0.8984, "lr": 5e-06, "epoch": 0.07380073800738007, "percentage": 2.46, "elapsed_time": "0:19:17", "remaining_time": "12:45:09"}
{"current_steps": 30, "total_steps": 813, "loss": 0.8623, "lr": 5e-06, "epoch": 0.11070110701107011, "percentage": 3.69, "elapsed_time": "0:28:54", "remaining_time": "12:34:34"}
{"current_steps": 40, "total_steps": 813, "loss": 0.838, "lr": 5e-06, "epoch": 0.14760147601476015, "percentage": 4.92, "elapsed_time": "0:38:31", "remaining_time": "12:24:33"}
{"current_steps": 50, "total_steps": 813, "loss": 0.8183, "lr": 5e-06, "epoch": 0.18450184501845018, "percentage": 6.15, "elapsed_time": "0:48:09", "remaining_time": "12:14:46"}
{"current_steps": 60, "total_steps": 813, "loss": 0.8026, "lr": 5e-06, "epoch": 0.22140221402214022, "percentage": 7.38, "elapsed_time": "0:57:45", "remaining_time": "12:04:58"}
{"current_steps": 70, "total_steps": 813, "loss": 0.7983, "lr": 5e-06, "epoch": 0.25830258302583026, "percentage": 8.61, "elapsed_time": "1:07:22", "remaining_time": "11:55:12"}
{"current_steps": 80, "total_steps": 813, "loss": 0.7874, "lr": 5e-06, "epoch": 0.2952029520295203, "percentage": 9.84, "elapsed_time": "1:16:58", "remaining_time": "11:45:19"}
{"current_steps": 90, "total_steps": 813, "loss": 0.7782, "lr": 5e-06, "epoch": 0.33210332103321033, "percentage": 11.07, "elapsed_time": "1:26:35", "remaining_time": "11:35:33"}
{"current_steps": 100, "total_steps": 813, "loss": 0.7777, "lr": 5e-06, "epoch": 0.36900369003690037, "percentage": 12.3, "elapsed_time": "1:36:11", "remaining_time": "11:25:47"}
{"current_steps": 110, "total_steps": 813, "loss": 0.7734, "lr": 5e-06, "epoch": 0.4059040590405904, "percentage": 13.53, "elapsed_time": "1:45:47", "remaining_time": "11:16:05"}
{"current_steps": 120, "total_steps": 813, "loss": 0.7644, "lr": 5e-06, "epoch": 0.44280442804428044, "percentage": 14.76, "elapsed_time": "1:55:23", "remaining_time": "11:06:24"}
{"current_steps": 130, "total_steps": 813, "loss": 0.7669, "lr": 5e-06, "epoch": 0.4797047970479705, "percentage": 15.99, "elapsed_time": "2:05:00", "remaining_time": "10:56:46"}
{"current_steps": 140, "total_steps": 813, "loss": 0.76, "lr": 5e-06, "epoch": 0.5166051660516605, "percentage": 17.22, "elapsed_time": "2:14:37", "remaining_time": "10:47:10"}
{"current_steps": 150, "total_steps": 813, "loss": 0.761, "lr": 5e-06, "epoch": 0.5535055350553506, "percentage": 18.45, "elapsed_time": "2:24:14", "remaining_time": "10:37:34"}
{"current_steps": 160, "total_steps": 813, "loss": 0.7523, "lr": 5e-06, "epoch": 0.5904059040590406, "percentage": 19.68, "elapsed_time": "2:33:52", "remaining_time": "10:27:58"}
{"current_steps": 170, "total_steps": 813, "loss": 0.7561, "lr": 5e-06, "epoch": 0.6273062730627307, "percentage": 20.91, "elapsed_time": "2:43:29", "remaining_time": "10:18:22"}
{"current_steps": 180, "total_steps": 813, "loss": 0.7537, "lr": 5e-06, "epoch": 0.6642066420664207, "percentage": 22.14, "elapsed_time": "2:53:06", "remaining_time": "10:08:45"}
{"current_steps": 190, "total_steps": 813, "loss": 0.7481, "lr": 5e-06, "epoch": 0.7011070110701108, "percentage": 23.37, "elapsed_time": "3:02:43", "remaining_time": "9:59:08"}
{"current_steps": 200, "total_steps": 813, "loss": 0.7486, "lr": 5e-06, "epoch": 0.7380073800738007, "percentage": 24.6, "elapsed_time": "3:12:20", "remaining_time": "9:49:32"}
{"current_steps": 210, "total_steps": 813, "loss": 0.7515, "lr": 5e-06, "epoch": 0.7749077490774908, "percentage": 25.83, "elapsed_time": "3:21:58", "remaining_time": "9:39:55"}
{"current_steps": 220, "total_steps": 813, "loss": 0.7465, "lr": 5e-06, "epoch": 0.8118081180811808, "percentage": 27.06, "elapsed_time": "3:31:34", "remaining_time": "9:30:18"}
{"current_steps": 230, "total_steps": 813, "loss": 0.7442, "lr": 5e-06, "epoch": 0.8487084870848709, "percentage": 28.29, "elapsed_time": "3:41:11", "remaining_time": "9:20:41"}
{"current_steps": 240, "total_steps": 813, "loss": 0.739, "lr": 5e-06, "epoch": 0.8856088560885609, "percentage": 29.52, "elapsed_time": "3:50:48", "remaining_time": "9:11:03"}
{"current_steps": 250, "total_steps": 813, "loss": 0.7405, "lr": 5e-06, "epoch": 0.922509225092251, "percentage": 30.75, "elapsed_time": "4:00:25", "remaining_time": "9:01:25"}
{"current_steps": 260, "total_steps": 813, "loss": 0.7416, "lr": 5e-06, "epoch": 0.959409594095941, "percentage": 31.98, "elapsed_time": "4:10:02", "remaining_time": "8:51:49"}
{"current_steps": 270, "total_steps": 813, "loss": 0.7428, "lr": 5e-06, "epoch": 0.996309963099631, "percentage": 33.21, "elapsed_time": "4:19:40", "remaining_time": "8:42:13"}
{"current_steps": 271, "total_steps": 813, "eval_loss": 0.74024897813797, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "4:25:28", "remaining_time": "8:50:57"}
{"current_steps": 280, "total_steps": 813, "loss": 0.6914, "lr": 5e-06, "epoch": 1.033210332103321, "percentage": 34.44, "elapsed_time": "4:35:16", "remaining_time": "8:43:59"}
{"current_steps": 290, "total_steps": 813, "loss": 0.6857, "lr": 5e-06, "epoch": 1.070110701107011, "percentage": 35.67, "elapsed_time": "4:44:54", "remaining_time": "8:33:48"}
{"current_steps": 300, "total_steps": 813, "loss": 0.6868, "lr": 5e-06, "epoch": 1.1070110701107012, "percentage": 36.9, "elapsed_time": "4:54:32", "remaining_time": "8:23:39"}
{"current_steps": 310, "total_steps": 813, "loss": 0.6823, "lr": 5e-06, "epoch": 1.1439114391143912, "percentage": 38.13, "elapsed_time": "5:04:10", "remaining_time": "8:13:32"}
{"current_steps": 320, "total_steps": 813, "loss": 0.683, "lr": 5e-06, "epoch": 1.1808118081180812, "percentage": 39.36, "elapsed_time": "5:13:48", "remaining_time": "8:03:28"}
{"current_steps": 330, "total_steps": 813, "loss": 0.6847, "lr": 5e-06, "epoch": 1.2177121771217712, "percentage": 40.59, "elapsed_time": "5:23:27", "remaining_time": "7:53:24"}
{"current_steps": 340, "total_steps": 813, "loss": 0.6852, "lr": 5e-06, "epoch": 1.2546125461254611, "percentage": 41.82, "elapsed_time": "5:33:04", "remaining_time": "7:43:22"}
{"current_steps": 350, "total_steps": 813, "loss": 0.6865, "lr": 5e-06, "epoch": 1.2915129151291513, "percentage": 43.05, "elapsed_time": "5:42:42", "remaining_time": "7:33:21"}
{"current_steps": 360, "total_steps": 813, "loss": 0.6886, "lr": 5e-06, "epoch": 1.3284132841328413, "percentage": 44.28, "elapsed_time": "5:52:20", "remaining_time": "7:23:21"}
{"current_steps": 370, "total_steps": 813, "loss": 0.6874, "lr": 5e-06, "epoch": 1.3653136531365313, "percentage": 45.51, "elapsed_time": "6:01:57", "remaining_time": "7:13:22"}
{"current_steps": 380, "total_steps": 813, "loss": 0.6838, "lr": 5e-06, "epoch": 1.4022140221402215, "percentage": 46.74, "elapsed_time": "6:11:35", "remaining_time": "7:03:25"}
{"current_steps": 390, "total_steps": 813, "loss": 0.6861, "lr": 5e-06, "epoch": 1.4391143911439115, "percentage": 47.97, "elapsed_time": "6:21:13", "remaining_time": "6:53:28"}
{"current_steps": 400, "total_steps": 813, "loss": 0.689, "lr": 5e-06, "epoch": 1.4760147601476015, "percentage": 49.2, "elapsed_time": "6:30:51", "remaining_time": "6:43:33"}
{"current_steps": 410, "total_steps": 813, "loss": 0.6881, "lr": 5e-06, "epoch": 1.5129151291512914, "percentage": 50.43, "elapsed_time": "6:40:29", "remaining_time": "6:33:38"}
{"current_steps": 420, "total_steps": 813, "loss": 0.6874, "lr": 5e-06, "epoch": 1.5498154981549814, "percentage": 51.66, "elapsed_time": "6:50:07", "remaining_time": "6:23:45"}
{"current_steps": 430, "total_steps": 813, "loss": 0.6866, "lr": 5e-06, "epoch": 1.5867158671586716, "percentage": 52.89, "elapsed_time": "6:59:44", "remaining_time": "6:13:51"}
{"current_steps": 440, "total_steps": 813, "loss": 0.6908, "lr": 5e-06, "epoch": 1.6236162361623616, "percentage": 54.12, "elapsed_time": "7:09:22", "remaining_time": "6:03:59"}
{"current_steps": 450, "total_steps": 813, "loss": 0.6895, "lr": 5e-06, "epoch": 1.6605166051660518, "percentage": 55.35, "elapsed_time": "7:19:00", "remaining_time": "5:54:08"}
{"current_steps": 460, "total_steps": 813, "loss": 0.6882, "lr": 5e-06, "epoch": 1.6974169741697418, "percentage": 56.58, "elapsed_time": "7:28:38", "remaining_time": "5:44:17"}
{"current_steps": 470, "total_steps": 813, "loss": 0.6794, "lr": 5e-06, "epoch": 1.7343173431734318, "percentage": 57.81, "elapsed_time": "7:38:16", "remaining_time": "5:34:26"}
{"current_steps": 480, "total_steps": 813, "loss": 0.6853, "lr": 5e-06, "epoch": 1.7712177121771218, "percentage": 59.04, "elapsed_time": "7:47:53", "remaining_time": "5:24:36"}
{"current_steps": 490, "total_steps": 813, "loss": 0.6883, "lr": 5e-06, "epoch": 1.8081180811808117, "percentage": 60.27, "elapsed_time": "7:57:31", "remaining_time": "5:14:46"}
{"current_steps": 500, "total_steps": 813, "loss": 0.6841, "lr": 5e-06, "epoch": 1.8450184501845017, "percentage": 61.5, "elapsed_time": "8:07:09", "remaining_time": "5:04:57"}
{"current_steps": 510, "total_steps": 813, "loss": 0.6857, "lr": 5e-06, "epoch": 1.881918819188192, "percentage": 62.73, "elapsed_time": "8:16:46", "remaining_time": "4:55:08"}
{"current_steps": 520, "total_steps": 813, "loss": 0.6839, "lr": 5e-06, "epoch": 1.918819188191882, "percentage": 63.96, "elapsed_time": "8:26:23", "remaining_time": "4:45:19"}
{"current_steps": 530, "total_steps": 813, "loss": 0.6862, "lr": 5e-06, "epoch": 1.9557195571955721, "percentage": 65.19, "elapsed_time": "8:36:00", "remaining_time": "4:35:31"}
{"current_steps": 540, "total_steps": 813, "loss": 0.6821, "lr": 5e-06, "epoch": 1.992619926199262, "percentage": 66.42, "elapsed_time": "8:45:38", "remaining_time": "4:25:44"}
{"current_steps": 542, "total_steps": 813, "eval_loss": 0.727390468120575, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "8:52:24", "remaining_time": "4:26:12"}
{"current_steps": 550, "total_steps": 813, "loss": 0.6378, "lr": 5e-06, "epoch": 2.029520295202952, "percentage": 67.65, "elapsed_time": "9:01:18", "remaining_time": "4:18:50"}
{"current_steps": 560, "total_steps": 813, "loss": 0.6283, "lr": 5e-06, "epoch": 2.066420664206642, "percentage": 68.88, "elapsed_time": "9:10:55", "remaining_time": "4:08:53"}
{"current_steps": 570, "total_steps": 813, "loss": 0.6266, "lr": 5e-06, "epoch": 2.103321033210332, "percentage": 70.11, "elapsed_time": "9:20:32", "remaining_time": "3:58:58"}
{"current_steps": 580, "total_steps": 813, "loss": 0.6308, "lr": 5e-06, "epoch": 2.140221402214022, "percentage": 71.34, "elapsed_time": "9:30:10", "remaining_time": "3:49:03"}
{"current_steps": 590, "total_steps": 813, "loss": 0.6314, "lr": 5e-06, "epoch": 2.177121771217712, "percentage": 72.57, "elapsed_time": "9:39:48", "remaining_time": "3:39:08"}
{"current_steps": 600, "total_steps": 813, "loss": 0.6282, "lr": 5e-06, "epoch": 2.2140221402214024, "percentage": 73.8, "elapsed_time": "9:49:25", "remaining_time": "3:29:14"}
{"current_steps": 610, "total_steps": 813, "loss": 0.6338, "lr": 5e-06, "epoch": 2.2509225092250924, "percentage": 75.03, "elapsed_time": "9:59:02", "remaining_time": "3:19:21"}
{"current_steps": 620, "total_steps": 813, "loss": 0.6363, "lr": 5e-06, "epoch": 2.2878228782287824, "percentage": 76.26, "elapsed_time": "10:08:40", "remaining_time": "3:09:28"}
{"current_steps": 630, "total_steps": 813, "loss": 0.63, "lr": 5e-06, "epoch": 2.3247232472324724, "percentage": 77.49, "elapsed_time": "10:18:17", "remaining_time": "2:59:36"}
{"current_steps": 640, "total_steps": 813, "loss": 0.629, "lr": 5e-06, "epoch": 2.3616236162361623, "percentage": 78.72, "elapsed_time": "10:27:54", "remaining_time": "2:49:44"}
{"current_steps": 650, "total_steps": 813, "loss": 0.6301, "lr": 5e-06, "epoch": 2.3985239852398523, "percentage": 79.95, "elapsed_time": "10:37:31", "remaining_time": "2:39:52"}
{"current_steps": 660, "total_steps": 813, "loss": 0.6359, "lr": 5e-06, "epoch": 2.4354243542435423, "percentage": 81.18, "elapsed_time": "10:47:08", "remaining_time": "2:30:01"}
{"current_steps": 670, "total_steps": 813, "loss": 0.6353, "lr": 5e-06, "epoch": 2.4723247232472323, "percentage": 82.41, "elapsed_time": "10:56:46", "remaining_time": "2:20:10"}
{"current_steps": 680, "total_steps": 813, "loss": 0.6329, "lr": 5e-06, "epoch": 2.5092250922509223, "percentage": 83.64, "elapsed_time": "11:06:23", "remaining_time": "2:10:20"}
{"current_steps": 690, "total_steps": 813, "loss": 0.6312, "lr": 5e-06, "epoch": 2.5461254612546127, "percentage": 84.87, "elapsed_time": "11:16:01", "remaining_time": "2:00:30"}
{"current_steps": 700, "total_steps": 813, "loss": 0.6343, "lr": 5e-06, "epoch": 2.5830258302583027, "percentage": 86.1, "elapsed_time": "11:25:39", "remaining_time": "1:50:41"}
{"current_steps": 710, "total_steps": 813, "loss": 0.636, "lr": 5e-06, "epoch": 2.6199261992619927, "percentage": 87.33, "elapsed_time": "11:35:16", "remaining_time": "1:40:51"}
{"current_steps": 720, "total_steps": 813, "loss": 0.6347, "lr": 5e-06, "epoch": 2.6568265682656826, "percentage": 88.56, "elapsed_time": "11:44:53", "remaining_time": "1:31:02"}
{"current_steps": 730, "total_steps": 813, "loss": 0.6348, "lr": 5e-06, "epoch": 2.6937269372693726, "percentage": 89.79, "elapsed_time": "11:54:31", "remaining_time": "1:21:14"}
{"current_steps": 740, "total_steps": 813, "loss": 0.6359, "lr": 5e-06, "epoch": 2.7306273062730626, "percentage": 91.02, "elapsed_time": "12:04:09", "remaining_time": "1:11:26"}
{"current_steps": 750, "total_steps": 813, "loss": 0.6345, "lr": 5e-06, "epoch": 2.767527675276753, "percentage": 92.25, "elapsed_time": "12:13:46", "remaining_time": "1:01:38"}
{"current_steps": 760, "total_steps": 813, "loss": 0.6395, "lr": 5e-06, "epoch": 2.804428044280443, "percentage": 93.48, "elapsed_time": "12:23:24", "remaining_time": "0:51:50"}
{"current_steps": 770, "total_steps": 813, "loss": 0.6382, "lr": 5e-06, "epoch": 2.841328413284133, "percentage": 94.71, "elapsed_time": "12:33:02", "remaining_time": "0:42:03"}
{"current_steps": 780, "total_steps": 813, "loss": 0.6386, "lr": 5e-06, "epoch": 2.878228782287823, "percentage": 95.94, "elapsed_time": "12:42:40", "remaining_time": "0:32:16"}
{"current_steps": 790, "total_steps": 813, "loss": 0.6345, "lr": 5e-06, "epoch": 2.915129151291513, "percentage": 97.17, "elapsed_time": "12:52:17", "remaining_time": "0:22:29"}
{"current_steps": 800, "total_steps": 813, "loss": 0.6345, "lr": 5e-06, "epoch": 2.952029520295203, "percentage": 98.4, "elapsed_time": "13:01:55", "remaining_time": "0:12:42"}
{"current_steps": 810, "total_steps": 813, "loss": 0.6351, "lr": 5e-06, "epoch": 2.988929889298893, "percentage": 99.63, "elapsed_time": "13:11:33", "remaining_time": "0:02:55"}
{"current_steps": 813, "total_steps": 813, "eval_loss": 0.7297624945640564, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "13:20:29", "remaining_time": "0:00:00"}
{"current_steps": 813, "total_steps": 813, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "13:21:57", "remaining_time": "0:00:00"}