oh_v1.3_alpaca_x2 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
a748df2 verified
{"current_steps": 10, "total_steps": 837, "loss": 1.0542, "lr": 5e-06, "epoch": 0.035794183445190156, "percentage": 1.19, "elapsed_time": "0:09:38", "remaining_time": "13:17:20"}
{"current_steps": 20, "total_steps": 837, "loss": 0.9185, "lr": 5e-06, "epoch": 0.07158836689038031, "percentage": 2.39, "elapsed_time": "0:19:12", "remaining_time": "13:04:34"}
{"current_steps": 30, "total_steps": 837, "loss": 0.8832, "lr": 5e-06, "epoch": 0.10738255033557047, "percentage": 3.58, "elapsed_time": "0:28:47", "remaining_time": "12:54:33"}
{"current_steps": 40, "total_steps": 837, "loss": 0.8514, "lr": 5e-06, "epoch": 0.14317673378076062, "percentage": 4.78, "elapsed_time": "0:38:22", "remaining_time": "12:44:37"}
{"current_steps": 50, "total_steps": 837, "loss": 0.8348, "lr": 5e-06, "epoch": 0.1789709172259508, "percentage": 5.97, "elapsed_time": "0:47:56", "remaining_time": "12:34:43"}
{"current_steps": 60, "total_steps": 837, "loss": 0.8123, "lr": 5e-06, "epoch": 0.21476510067114093, "percentage": 7.17, "elapsed_time": "0:57:33", "remaining_time": "12:25:19"}
{"current_steps": 70, "total_steps": 837, "loss": 0.803, "lr": 5e-06, "epoch": 0.2505592841163311, "percentage": 8.36, "elapsed_time": "1:07:09", "remaining_time": "12:15:56"}
{"current_steps": 80, "total_steps": 837, "loss": 0.7897, "lr": 5e-06, "epoch": 0.28635346756152125, "percentage": 9.56, "elapsed_time": "1:16:44", "remaining_time": "12:06:08"}
{"current_steps": 90, "total_steps": 837, "loss": 0.7885, "lr": 5e-06, "epoch": 0.3221476510067114, "percentage": 10.75, "elapsed_time": "1:26:20", "remaining_time": "11:56:34"}
{"current_steps": 100, "total_steps": 837, "loss": 0.7772, "lr": 5e-06, "epoch": 0.3579418344519016, "percentage": 11.95, "elapsed_time": "1:35:56", "remaining_time": "11:47:06"}
{"current_steps": 110, "total_steps": 837, "loss": 0.7786, "lr": 5e-06, "epoch": 0.39373601789709173, "percentage": 13.14, "elapsed_time": "1:45:33", "remaining_time": "11:37:39"}
{"current_steps": 120, "total_steps": 837, "loss": 0.7684, "lr": 5e-06, "epoch": 0.42953020134228187, "percentage": 14.34, "elapsed_time": "1:55:10", "remaining_time": "11:28:08"}
{"current_steps": 130, "total_steps": 837, "loss": 0.7688, "lr": 5e-06, "epoch": 0.465324384787472, "percentage": 15.53, "elapsed_time": "2:04:46", "remaining_time": "11:18:34"}
{"current_steps": 140, "total_steps": 837, "loss": 0.7706, "lr": 5e-06, "epoch": 0.5011185682326622, "percentage": 16.73, "elapsed_time": "2:14:21", "remaining_time": "11:08:53"}
{"current_steps": 150, "total_steps": 837, "loss": 0.762, "lr": 5e-06, "epoch": 0.5369127516778524, "percentage": 17.92, "elapsed_time": "2:23:57", "remaining_time": "10:59:19"}
{"current_steps": 160, "total_steps": 837, "loss": 0.7639, "lr": 5e-06, "epoch": 0.5727069351230425, "percentage": 19.12, "elapsed_time": "2:33:31", "remaining_time": "10:49:34"}
{"current_steps": 170, "total_steps": 837, "loss": 0.7568, "lr": 5e-06, "epoch": 0.6085011185682326, "percentage": 20.31, "elapsed_time": "2:43:06", "remaining_time": "10:39:59"}
{"current_steps": 180, "total_steps": 837, "loss": 0.7593, "lr": 5e-06, "epoch": 0.6442953020134228, "percentage": 21.51, "elapsed_time": "2:52:42", "remaining_time": "10:30:23"}
{"current_steps": 190, "total_steps": 837, "loss": 0.752, "lr": 5e-06, "epoch": 0.680089485458613, "percentage": 22.7, "elapsed_time": "3:02:18", "remaining_time": "10:20:46"}
{"current_steps": 200, "total_steps": 837, "loss": 0.7535, "lr": 5e-06, "epoch": 0.7158836689038032, "percentage": 23.89, "elapsed_time": "3:11:52", "remaining_time": "10:11:07"}
{"current_steps": 210, "total_steps": 837, "loss": 0.7509, "lr": 5e-06, "epoch": 0.7516778523489933, "percentage": 25.09, "elapsed_time": "3:21:28", "remaining_time": "10:01:33"}
{"current_steps": 220, "total_steps": 837, "loss": 0.7572, "lr": 5e-06, "epoch": 0.7874720357941835, "percentage": 26.28, "elapsed_time": "3:31:03", "remaining_time": "9:51:54"}
{"current_steps": 230, "total_steps": 837, "loss": 0.7445, "lr": 5e-06, "epoch": 0.8232662192393736, "percentage": 27.48, "elapsed_time": "3:40:39", "remaining_time": "9:42:21"}
{"current_steps": 240, "total_steps": 837, "loss": 0.7474, "lr": 5e-06, "epoch": 0.8590604026845637, "percentage": 28.67, "elapsed_time": "3:50:16", "remaining_time": "9:32:47"}
{"current_steps": 250, "total_steps": 837, "loss": 0.7497, "lr": 5e-06, "epoch": 0.8948545861297539, "percentage": 29.87, "elapsed_time": "3:59:51", "remaining_time": "9:23:10"}
{"current_steps": 260, "total_steps": 837, "loss": 0.7463, "lr": 5e-06, "epoch": 0.930648769574944, "percentage": 31.06, "elapsed_time": "4:09:27", "remaining_time": "9:13:37"}
{"current_steps": 270, "total_steps": 837, "loss": 0.7406, "lr": 5e-06, "epoch": 0.9664429530201343, "percentage": 32.26, "elapsed_time": "4:19:02", "remaining_time": "9:03:58"}
{"current_steps": 279, "total_steps": 837, "eval_loss": 0.7448742389678955, "epoch": 0.9986577181208054, "percentage": 33.33, "elapsed_time": "4:32:55", "remaining_time": "9:05:50"}
{"current_steps": 280, "total_steps": 837, "loss": 0.783, "lr": 5e-06, "epoch": 1.0022371364653244, "percentage": 33.45, "elapsed_time": "4:34:41", "remaining_time": "9:06:26"}
{"current_steps": 290, "total_steps": 837, "loss": 0.6946, "lr": 5e-06, "epoch": 1.0380313199105144, "percentage": 34.65, "elapsed_time": "4:44:19", "remaining_time": "8:56:16"}
{"current_steps": 300, "total_steps": 837, "loss": 0.6923, "lr": 5e-06, "epoch": 1.0738255033557047, "percentage": 35.84, "elapsed_time": "4:53:56", "remaining_time": "8:46:08"}
{"current_steps": 310, "total_steps": 837, "loss": 0.6925, "lr": 5e-06, "epoch": 1.109619686800895, "percentage": 37.04, "elapsed_time": "5:03:32", "remaining_time": "8:36:01"}
{"current_steps": 320, "total_steps": 837, "loss": 0.6938, "lr": 5e-06, "epoch": 1.145413870246085, "percentage": 38.23, "elapsed_time": "5:13:09", "remaining_time": "8:25:57"}
{"current_steps": 330, "total_steps": 837, "loss": 0.6897, "lr": 5e-06, "epoch": 1.1812080536912752, "percentage": 39.43, "elapsed_time": "5:22:46", "remaining_time": "8:15:53"}
{"current_steps": 340, "total_steps": 837, "loss": 0.6971, "lr": 5e-06, "epoch": 1.2170022371364653, "percentage": 40.62, "elapsed_time": "5:32:23", "remaining_time": "8:05:52"}
{"current_steps": 350, "total_steps": 837, "loss": 0.6912, "lr": 5e-06, "epoch": 1.2527964205816555, "percentage": 41.82, "elapsed_time": "5:41:59", "remaining_time": "7:55:51"}
{"current_steps": 360, "total_steps": 837, "loss": 0.6892, "lr": 5e-06, "epoch": 1.2885906040268456, "percentage": 43.01, "elapsed_time": "5:51:35", "remaining_time": "7:45:51"}
{"current_steps": 370, "total_steps": 837, "loss": 0.6895, "lr": 5e-06, "epoch": 1.3243847874720358, "percentage": 44.21, "elapsed_time": "6:01:11", "remaining_time": "7:35:52"}
{"current_steps": 380, "total_steps": 837, "loss": 0.6887, "lr": 5e-06, "epoch": 1.360178970917226, "percentage": 45.4, "elapsed_time": "6:10:47", "remaining_time": "7:25:56"}
{"current_steps": 390, "total_steps": 837, "loss": 0.6868, "lr": 5e-06, "epoch": 1.395973154362416, "percentage": 46.59, "elapsed_time": "6:20:26", "remaining_time": "7:16:02"}
{"current_steps": 400, "total_steps": 837, "loss": 0.6862, "lr": 5e-06, "epoch": 1.4317673378076063, "percentage": 47.79, "elapsed_time": "6:30:04", "remaining_time": "7:06:09"}
{"current_steps": 410, "total_steps": 837, "loss": 0.6887, "lr": 5e-06, "epoch": 1.4675615212527964, "percentage": 48.98, "elapsed_time": "6:39:41", "remaining_time": "6:56:16"}
{"current_steps": 420, "total_steps": 837, "loss": 0.6866, "lr": 5e-06, "epoch": 1.5033557046979866, "percentage": 50.18, "elapsed_time": "6:49:19", "remaining_time": "6:46:24"}
{"current_steps": 430, "total_steps": 837, "loss": 0.6904, "lr": 5e-06, "epoch": 1.5391498881431769, "percentage": 51.37, "elapsed_time": "6:58:56", "remaining_time": "6:36:31"}
{"current_steps": 440, "total_steps": 837, "loss": 0.6944, "lr": 5e-06, "epoch": 1.574944071588367, "percentage": 52.57, "elapsed_time": "7:08:30", "remaining_time": "6:26:37"}
{"current_steps": 450, "total_steps": 837, "loss": 0.6848, "lr": 5e-06, "epoch": 1.610738255033557, "percentage": 53.76, "elapsed_time": "7:18:06", "remaining_time": "6:16:46"}
{"current_steps": 460, "total_steps": 837, "loss": 0.6873, "lr": 5e-06, "epoch": 1.6465324384787472, "percentage": 54.96, "elapsed_time": "7:27:43", "remaining_time": "6:06:56"}
{"current_steps": 470, "total_steps": 837, "loss": 0.6834, "lr": 5e-06, "epoch": 1.6823266219239374, "percentage": 56.15, "elapsed_time": "7:37:19", "remaining_time": "5:57:06"}
{"current_steps": 480, "total_steps": 837, "loss": 0.6831, "lr": 5e-06, "epoch": 1.7181208053691275, "percentage": 57.35, "elapsed_time": "7:46:55", "remaining_time": "5:47:16"}
{"current_steps": 490, "total_steps": 837, "loss": 0.6842, "lr": 5e-06, "epoch": 1.7539149888143175, "percentage": 58.54, "elapsed_time": "7:56:33", "remaining_time": "5:37:28"}
{"current_steps": 500, "total_steps": 837, "loss": 0.687, "lr": 5e-06, "epoch": 1.7897091722595078, "percentage": 59.74, "elapsed_time": "8:06:09", "remaining_time": "5:27:40"}
{"current_steps": 510, "total_steps": 837, "loss": 0.6891, "lr": 5e-06, "epoch": 1.825503355704698, "percentage": 60.93, "elapsed_time": "8:15:47", "remaining_time": "5:17:53"}
{"current_steps": 520, "total_steps": 837, "loss": 0.6906, "lr": 5e-06, "epoch": 1.8612975391498883, "percentage": 62.13, "elapsed_time": "8:25:24", "remaining_time": "5:08:06"}
{"current_steps": 530, "total_steps": 837, "loss": 0.684, "lr": 5e-06, "epoch": 1.8970917225950783, "percentage": 63.32, "elapsed_time": "8:35:00", "remaining_time": "4:58:18"}
{"current_steps": 540, "total_steps": 837, "loss": 0.6882, "lr": 5e-06, "epoch": 1.9328859060402683, "percentage": 64.52, "elapsed_time": "8:44:36", "remaining_time": "4:48:32"}
{"current_steps": 550, "total_steps": 837, "loss": 0.6867, "lr": 5e-06, "epoch": 1.9686800894854586, "percentage": 65.71, "elapsed_time": "8:54:13", "remaining_time": "4:38:45"}
{"current_steps": 558, "total_steps": 837, "eval_loss": 0.7317517399787903, "epoch": 1.9973154362416108, "percentage": 66.67, "elapsed_time": "9:07:29", "remaining_time": "4:33:44"}
{"current_steps": 560, "total_steps": 837, "loss": 0.7203, "lr": 5e-06, "epoch": 2.004474272930649, "percentage": 66.91, "elapsed_time": "9:09:59", "remaining_time": "4:32:03"}
{"current_steps": 570, "total_steps": 837, "loss": 0.6303, "lr": 5e-06, "epoch": 2.040268456375839, "percentage": 68.1, "elapsed_time": "9:19:35", "remaining_time": "4:22:07"}
{"current_steps": 580, "total_steps": 837, "loss": 0.6299, "lr": 5e-06, "epoch": 2.076062639821029, "percentage": 69.3, "elapsed_time": "9:29:12", "remaining_time": "4:12:13"}
{"current_steps": 590, "total_steps": 837, "loss": 0.6341, "lr": 5e-06, "epoch": 2.111856823266219, "percentage": 70.49, "elapsed_time": "9:38:49", "remaining_time": "4:02:19"}
{"current_steps": 600, "total_steps": 837, "loss": 0.6354, "lr": 5e-06, "epoch": 2.1476510067114094, "percentage": 71.68, "elapsed_time": "9:48:25", "remaining_time": "3:52:25"}
{"current_steps": 610, "total_steps": 837, "loss": 0.6307, "lr": 5e-06, "epoch": 2.1834451901565997, "percentage": 72.88, "elapsed_time": "9:58:02", "remaining_time": "3:42:32"}
{"current_steps": 620, "total_steps": 837, "loss": 0.6333, "lr": 5e-06, "epoch": 2.21923937360179, "percentage": 74.07, "elapsed_time": "10:07:38", "remaining_time": "3:32:40"}
{"current_steps": 630, "total_steps": 837, "loss": 0.6358, "lr": 5e-06, "epoch": 2.2550335570469797, "percentage": 75.27, "elapsed_time": "10:17:14", "remaining_time": "3:22:48"}
{"current_steps": 640, "total_steps": 837, "loss": 0.6352, "lr": 5e-06, "epoch": 2.29082774049217, "percentage": 76.46, "elapsed_time": "10:26:51", "remaining_time": "3:12:57"}
{"current_steps": 650, "total_steps": 837, "loss": 0.6355, "lr": 5e-06, "epoch": 2.3266219239373602, "percentage": 77.66, "elapsed_time": "10:36:27", "remaining_time": "3:03:06"}
{"current_steps": 660, "total_steps": 837, "loss": 0.6337, "lr": 5e-06, "epoch": 2.3624161073825505, "percentage": 78.85, "elapsed_time": "10:46:02", "remaining_time": "2:53:15"}
{"current_steps": 670, "total_steps": 837, "loss": 0.6361, "lr": 5e-06, "epoch": 2.3982102908277403, "percentage": 80.05, "elapsed_time": "10:55:39", "remaining_time": "2:43:25"}
{"current_steps": 680, "total_steps": 837, "loss": 0.6363, "lr": 5e-06, "epoch": 2.4340044742729305, "percentage": 81.24, "elapsed_time": "11:05:17", "remaining_time": "2:33:36"}
{"current_steps": 690, "total_steps": 837, "loss": 0.6361, "lr": 5e-06, "epoch": 2.469798657718121, "percentage": 82.44, "elapsed_time": "11:14:51", "remaining_time": "2:23:46"}
{"current_steps": 700, "total_steps": 837, "loss": 0.6357, "lr": 5e-06, "epoch": 2.505592841163311, "percentage": 83.63, "elapsed_time": "11:24:28", "remaining_time": "2:13:57"}
{"current_steps": 710, "total_steps": 837, "loss": 0.6378, "lr": 5e-06, "epoch": 2.5413870246085013, "percentage": 84.83, "elapsed_time": "11:34:04", "remaining_time": "2:04:09"}
{"current_steps": 720, "total_steps": 837, "loss": 0.6364, "lr": 5e-06, "epoch": 2.577181208053691, "percentage": 86.02, "elapsed_time": "11:43:40", "remaining_time": "1:54:20"}
{"current_steps": 730, "total_steps": 837, "loss": 0.6397, "lr": 5e-06, "epoch": 2.6129753914988814, "percentage": 87.22, "elapsed_time": "11:53:17", "remaining_time": "1:44:33"}
{"current_steps": 740, "total_steps": 837, "loss": 0.6369, "lr": 5e-06, "epoch": 2.6487695749440716, "percentage": 88.41, "elapsed_time": "12:02:54", "remaining_time": "1:34:45"}
{"current_steps": 750, "total_steps": 837, "loss": 0.6382, "lr": 5e-06, "epoch": 2.684563758389262, "percentage": 89.61, "elapsed_time": "12:12:31", "remaining_time": "1:24:58"}
{"current_steps": 760, "total_steps": 837, "loss": 0.6353, "lr": 5e-06, "epoch": 2.720357941834452, "percentage": 90.8, "elapsed_time": "12:22:09", "remaining_time": "1:15:11"}
{"current_steps": 770, "total_steps": 837, "loss": 0.6398, "lr": 5e-06, "epoch": 2.756152125279642, "percentage": 92.0, "elapsed_time": "12:31:46", "remaining_time": "1:05:24"}
{"current_steps": 780, "total_steps": 837, "loss": 0.6411, "lr": 5e-06, "epoch": 2.791946308724832, "percentage": 93.19, "elapsed_time": "12:41:21", "remaining_time": "0:55:38"}
{"current_steps": 790, "total_steps": 837, "loss": 0.6367, "lr": 5e-06, "epoch": 2.8277404921700224, "percentage": 94.38, "elapsed_time": "12:50:59", "remaining_time": "0:45:52"}
{"current_steps": 800, "total_steps": 837, "loss": 0.6361, "lr": 5e-06, "epoch": 2.8635346756152127, "percentage": 95.58, "elapsed_time": "13:00:33", "remaining_time": "0:36:06"}
{"current_steps": 810, "total_steps": 837, "loss": 0.6442, "lr": 5e-06, "epoch": 2.899328859060403, "percentage": 96.77, "elapsed_time": "13:10:07", "remaining_time": "0:26:20"}
{"current_steps": 820, "total_steps": 837, "loss": 0.6395, "lr": 5e-06, "epoch": 2.9351230425055927, "percentage": 97.97, "elapsed_time": "13:19:45", "remaining_time": "0:16:34"}
{"current_steps": 830, "total_steps": 837, "loss": 0.64, "lr": 5e-06, "epoch": 2.970917225950783, "percentage": 99.16, "elapsed_time": "13:29:20", "remaining_time": "0:06:49"}
{"current_steps": 837, "total_steps": 837, "eval_loss": 0.733113169670105, "epoch": 2.995973154362416, "percentage": 100.0, "elapsed_time": "13:42:11", "remaining_time": "0:00:00"}
{"current_steps": 837, "total_steps": 837, "epoch": 2.995973154362416, "percentage": 100.0, "elapsed_time": "13:43:40", "remaining_time": "0:00:00"}