sedrickkeh's picture
Training in progress, epoch 3
cf53e88 verified
{"current_steps": 10, "total_steps": 771, "loss": 0.7894, "lr": 5e-06, "epoch": 0.038910505836575876, "percentage": 1.3, "elapsed_time": "0:09:42", "remaining_time": "12:18:22"}
{"current_steps": 20, "total_steps": 771, "loss": 0.7077, "lr": 5e-06, "epoch": 0.07782101167315175, "percentage": 2.59, "elapsed_time": "0:19:20", "remaining_time": "12:06:05"}
{"current_steps": 30, "total_steps": 771, "loss": 0.6773, "lr": 5e-06, "epoch": 0.11673151750972763, "percentage": 3.89, "elapsed_time": "0:28:57", "remaining_time": "11:55:17"}
{"current_steps": 40, "total_steps": 771, "loss": 0.6672, "lr": 5e-06, "epoch": 0.1556420233463035, "percentage": 5.19, "elapsed_time": "0:38:33", "remaining_time": "11:44:30"}
{"current_steps": 50, "total_steps": 771, "loss": 0.655, "lr": 5e-06, "epoch": 0.19455252918287938, "percentage": 6.49, "elapsed_time": "0:48:09", "remaining_time": "11:34:27"}
{"current_steps": 60, "total_steps": 771, "loss": 0.646, "lr": 5e-06, "epoch": 0.23346303501945526, "percentage": 7.78, "elapsed_time": "0:57:47", "remaining_time": "11:24:52"}
{"current_steps": 70, "total_steps": 771, "loss": 0.6403, "lr": 5e-06, "epoch": 0.2723735408560311, "percentage": 9.08, "elapsed_time": "1:07:25", "remaining_time": "11:15:13"}
{"current_steps": 80, "total_steps": 771, "loss": 0.6418, "lr": 5e-06, "epoch": 0.311284046692607, "percentage": 10.38, "elapsed_time": "1:17:02", "remaining_time": "11:05:26"}
{"current_steps": 90, "total_steps": 771, "loss": 0.6327, "lr": 5e-06, "epoch": 0.35019455252918286, "percentage": 11.67, "elapsed_time": "1:26:40", "remaining_time": "10:55:47"}
{"current_steps": 100, "total_steps": 771, "loss": 0.6193, "lr": 5e-06, "epoch": 0.38910505836575876, "percentage": 12.97, "elapsed_time": "1:36:17", "remaining_time": "10:46:09"}
{"current_steps": 110, "total_steps": 771, "loss": 0.6207, "lr": 5e-06, "epoch": 0.4280155642023346, "percentage": 14.27, "elapsed_time": "1:45:54", "remaining_time": "10:36:24"}
{"current_steps": 120, "total_steps": 771, "loss": 0.6163, "lr": 5e-06, "epoch": 0.4669260700389105, "percentage": 15.56, "elapsed_time": "1:55:31", "remaining_time": "10:26:43"}
{"current_steps": 130, "total_steps": 771, "loss": 0.6274, "lr": 5e-06, "epoch": 0.5058365758754864, "percentage": 16.86, "elapsed_time": "2:05:07", "remaining_time": "10:16:58"}
{"current_steps": 140, "total_steps": 771, "loss": 0.6072, "lr": 5e-06, "epoch": 0.5447470817120622, "percentage": 18.16, "elapsed_time": "2:14:44", "remaining_time": "10:07:17"}
{"current_steps": 150, "total_steps": 771, "loss": 0.6133, "lr": 5e-06, "epoch": 0.5836575875486382, "percentage": 19.46, "elapsed_time": "2:24:22", "remaining_time": "9:57:40"}
{"current_steps": 160, "total_steps": 771, "loss": 0.6082, "lr": 5e-06, "epoch": 0.622568093385214, "percentage": 20.75, "elapsed_time": "2:34:00", "remaining_time": "9:48:06"}
{"current_steps": 170, "total_steps": 771, "loss": 0.623, "lr": 5e-06, "epoch": 0.6614785992217899, "percentage": 22.05, "elapsed_time": "2:43:38", "remaining_time": "9:38:32"}
{"current_steps": 180, "total_steps": 771, "loss": 0.6028, "lr": 5e-06, "epoch": 0.7003891050583657, "percentage": 23.35, "elapsed_time": "2:53:15", "remaining_time": "9:28:52"}
{"current_steps": 190, "total_steps": 771, "loss": 0.6084, "lr": 5e-06, "epoch": 0.7392996108949417, "percentage": 24.64, "elapsed_time": "3:02:53", "remaining_time": "9:19:15"}
{"current_steps": 200, "total_steps": 771, "loss": 0.6084, "lr": 5e-06, "epoch": 0.7782101167315175, "percentage": 25.94, "elapsed_time": "3:12:31", "remaining_time": "9:09:39"}
{"current_steps": 210, "total_steps": 771, "loss": 0.6115, "lr": 5e-06, "epoch": 0.8171206225680934, "percentage": 27.24, "elapsed_time": "3:22:09", "remaining_time": "9:00:02"}
{"current_steps": 220, "total_steps": 771, "loss": 0.6084, "lr": 5e-06, "epoch": 0.8560311284046692, "percentage": 28.53, "elapsed_time": "3:31:46", "remaining_time": "8:50:24"}
{"current_steps": 230, "total_steps": 771, "loss": 0.6074, "lr": 5e-06, "epoch": 0.8949416342412452, "percentage": 29.83, "elapsed_time": "3:41:25", "remaining_time": "8:40:50"}
{"current_steps": 240, "total_steps": 771, "loss": 0.5988, "lr": 5e-06, "epoch": 0.933852140077821, "percentage": 31.13, "elapsed_time": "3:51:03", "remaining_time": "8:31:12"}
{"current_steps": 250, "total_steps": 771, "loss": 0.5983, "lr": 5e-06, "epoch": 0.9727626459143969, "percentage": 32.43, "elapsed_time": "4:00:40", "remaining_time": "8:21:34"}
{"current_steps": 257, "total_steps": 771, "eval_loss": 0.6058223843574524, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "4:11:59", "remaining_time": "8:23:59"}
{"current_steps": 260, "total_steps": 771, "loss": 0.5823, "lr": 5e-06, "epoch": 1.0116731517509727, "percentage": 33.72, "elapsed_time": "4:16:01", "remaining_time": "8:23:11"}
{"current_steps": 270, "total_steps": 771, "loss": 0.5545, "lr": 5e-06, "epoch": 1.0505836575875487, "percentage": 35.02, "elapsed_time": "4:25:40", "remaining_time": "8:12:58"}
{"current_steps": 280, "total_steps": 771, "loss": 0.5519, "lr": 5e-06, "epoch": 1.0894941634241244, "percentage": 36.32, "elapsed_time": "4:35:18", "remaining_time": "8:02:46"}
{"current_steps": 290, "total_steps": 771, "loss": 0.5524, "lr": 5e-06, "epoch": 1.1284046692607004, "percentage": 37.61, "elapsed_time": "4:44:56", "remaining_time": "7:52:37"}
{"current_steps": 300, "total_steps": 771, "loss": 0.5522, "lr": 5e-06, "epoch": 1.1673151750972763, "percentage": 38.91, "elapsed_time": "4:54:35", "remaining_time": "7:42:29"}
{"current_steps": 310, "total_steps": 771, "loss": 0.5501, "lr": 5e-06, "epoch": 1.206225680933852, "percentage": 40.21, "elapsed_time": "5:04:13", "remaining_time": "7:32:24"}
{"current_steps": 320, "total_steps": 771, "loss": 0.5593, "lr": 5e-06, "epoch": 1.245136186770428, "percentage": 41.5, "elapsed_time": "5:13:50", "remaining_time": "7:22:19"}
{"current_steps": 330, "total_steps": 771, "loss": 0.5529, "lr": 5e-06, "epoch": 1.2840466926070038, "percentage": 42.8, "elapsed_time": "5:23:27", "remaining_time": "7:12:15"}
{"current_steps": 340, "total_steps": 771, "loss": 0.5516, "lr": 5e-06, "epoch": 1.3229571984435797, "percentage": 44.1, "elapsed_time": "5:33:04", "remaining_time": "7:02:13"}
{"current_steps": 350, "total_steps": 771, "loss": 0.5478, "lr": 5e-06, "epoch": 1.3618677042801557, "percentage": 45.4, "elapsed_time": "5:42:42", "remaining_time": "6:52:13"}
{"current_steps": 360, "total_steps": 771, "loss": 0.5648, "lr": 5e-06, "epoch": 1.4007782101167314, "percentage": 46.69, "elapsed_time": "5:52:20", "remaining_time": "6:42:15"}
{"current_steps": 370, "total_steps": 771, "loss": 0.5513, "lr": 5e-06, "epoch": 1.4396887159533074, "percentage": 47.99, "elapsed_time": "6:01:57", "remaining_time": "6:32:17"}
{"current_steps": 380, "total_steps": 771, "loss": 0.5544, "lr": 5e-06, "epoch": 1.4785992217898833, "percentage": 49.29, "elapsed_time": "6:11:37", "remaining_time": "6:22:22"}
{"current_steps": 390, "total_steps": 771, "loss": 0.5528, "lr": 5e-06, "epoch": 1.517509727626459, "percentage": 50.58, "elapsed_time": "6:21:15", "remaining_time": "6:12:27"}
{"current_steps": 400, "total_steps": 771, "loss": 0.5481, "lr": 5e-06, "epoch": 1.556420233463035, "percentage": 51.88, "elapsed_time": "6:30:54", "remaining_time": "6:02:33"}
{"current_steps": 410, "total_steps": 771, "loss": 0.5545, "lr": 5e-06, "epoch": 1.595330739299611, "percentage": 53.18, "elapsed_time": "6:40:32", "remaining_time": "5:52:40"}
{"current_steps": 420, "total_steps": 771, "loss": 0.553, "lr": 5e-06, "epoch": 1.6342412451361867, "percentage": 54.47, "elapsed_time": "6:50:11", "remaining_time": "5:42:48"}
{"current_steps": 430, "total_steps": 771, "loss": 0.5391, "lr": 5e-06, "epoch": 1.6731517509727627, "percentage": 55.77, "elapsed_time": "6:59:50", "remaining_time": "5:32:57"}
{"current_steps": 440, "total_steps": 771, "loss": 0.5576, "lr": 5e-06, "epoch": 1.7120622568093387, "percentage": 57.07, "elapsed_time": "7:09:29", "remaining_time": "5:23:06"}
{"current_steps": 450, "total_steps": 771, "loss": 0.5439, "lr": 5e-06, "epoch": 1.7509727626459144, "percentage": 58.37, "elapsed_time": "7:19:08", "remaining_time": "5:13:15"}
{"current_steps": 460, "total_steps": 771, "loss": 0.5509, "lr": 5e-06, "epoch": 1.7898832684824901, "percentage": 59.66, "elapsed_time": "7:28:45", "remaining_time": "5:03:24"}
{"current_steps": 470, "total_steps": 771, "loss": 0.5547, "lr": 5e-06, "epoch": 1.8287937743190663, "percentage": 60.96, "elapsed_time": "7:38:24", "remaining_time": "4:53:34"}
{"current_steps": 480, "total_steps": 771, "loss": 0.5466, "lr": 5e-06, "epoch": 1.867704280155642, "percentage": 62.26, "elapsed_time": "7:48:03", "remaining_time": "4:43:45"}
{"current_steps": 490, "total_steps": 771, "loss": 0.5505, "lr": 5e-06, "epoch": 1.9066147859922178, "percentage": 63.55, "elapsed_time": "7:57:41", "remaining_time": "4:33:56"}
{"current_steps": 500, "total_steps": 771, "loss": 0.548, "lr": 5e-06, "epoch": 1.9455252918287937, "percentage": 64.85, "elapsed_time": "8:07:19", "remaining_time": "4:24:07"}
{"current_steps": 510, "total_steps": 771, "loss": 0.5559, "lr": 5e-06, "epoch": 1.9844357976653697, "percentage": 66.15, "elapsed_time": "8:16:57", "remaining_time": "4:14:19"}
{"current_steps": 514, "total_steps": 771, "eval_loss": 0.5962130427360535, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "8:25:21", "remaining_time": "4:12:40"}
{"current_steps": 520, "total_steps": 771, "loss": 0.5269, "lr": 5e-06, "epoch": 2.0233463035019454, "percentage": 67.44, "elapsed_time": "8:32:21", "remaining_time": "4:07:18"}
{"current_steps": 530, "total_steps": 771, "loss": 0.4971, "lr": 5e-06, "epoch": 2.062256809338521, "percentage": 68.74, "elapsed_time": "8:41:59", "remaining_time": "3:57:21"}
{"current_steps": 540, "total_steps": 771, "loss": 0.4955, "lr": 5e-06, "epoch": 2.1011673151750974, "percentage": 70.04, "elapsed_time": "8:51:37", "remaining_time": "3:47:24"}
{"current_steps": 550, "total_steps": 771, "loss": 0.5002, "lr": 5e-06, "epoch": 2.140077821011673, "percentage": 71.34, "elapsed_time": "9:01:15", "remaining_time": "3:37:29"}
{"current_steps": 560, "total_steps": 771, "loss": 0.5012, "lr": 5e-06, "epoch": 2.178988326848249, "percentage": 72.63, "elapsed_time": "9:10:54", "remaining_time": "3:27:34"}
{"current_steps": 570, "total_steps": 771, "loss": 0.4955, "lr": 5e-06, "epoch": 2.217898832684825, "percentage": 73.93, "elapsed_time": "9:20:32", "remaining_time": "3:17:39"}
{"current_steps": 580, "total_steps": 771, "loss": 0.5055, "lr": 5e-06, "epoch": 2.2568093385214008, "percentage": 75.23, "elapsed_time": "9:30:08", "remaining_time": "3:07:45"}
{"current_steps": 590, "total_steps": 771, "loss": 0.503, "lr": 5e-06, "epoch": 2.2957198443579765, "percentage": 76.52, "elapsed_time": "9:39:48", "remaining_time": "2:57:52"}
{"current_steps": 600, "total_steps": 771, "loss": 0.5027, "lr": 5e-06, "epoch": 2.3346303501945527, "percentage": 77.82, "elapsed_time": "9:49:27", "remaining_time": "2:47:59"}
{"current_steps": 610, "total_steps": 771, "loss": 0.497, "lr": 5e-06, "epoch": 2.3735408560311284, "percentage": 79.12, "elapsed_time": "9:59:05", "remaining_time": "2:38:07"}
{"current_steps": 620, "total_steps": 771, "loss": 0.4932, "lr": 5e-06, "epoch": 2.412451361867704, "percentage": 80.42, "elapsed_time": "10:08:44", "remaining_time": "2:28:15"}
{"current_steps": 630, "total_steps": 771, "loss": 0.5024, "lr": 5e-06, "epoch": 2.4513618677042803, "percentage": 81.71, "elapsed_time": "10:18:22", "remaining_time": "2:18:23"}
{"current_steps": 640, "total_steps": 771, "loss": 0.4985, "lr": 5e-06, "epoch": 2.490272373540856, "percentage": 83.01, "elapsed_time": "10:28:00", "remaining_time": "2:08:32"}
{"current_steps": 650, "total_steps": 771, "loss": 0.5107, "lr": 5e-06, "epoch": 2.529182879377432, "percentage": 84.31, "elapsed_time": "10:37:38", "remaining_time": "1:58:42"}
{"current_steps": 660, "total_steps": 771, "loss": 0.4941, "lr": 5e-06, "epoch": 2.5680933852140075, "percentage": 85.6, "elapsed_time": "10:47:18", "remaining_time": "1:48:51"}
{"current_steps": 670, "total_steps": 771, "loss": 0.5018, "lr": 5e-06, "epoch": 2.6070038910505837, "percentage": 86.9, "elapsed_time": "10:56:57", "remaining_time": "1:39:01"}
{"current_steps": 680, "total_steps": 771, "loss": 0.5104, "lr": 5e-06, "epoch": 2.6459143968871595, "percentage": 88.2, "elapsed_time": "11:06:35", "remaining_time": "1:29:12"}
{"current_steps": 690, "total_steps": 771, "loss": 0.4999, "lr": 5e-06, "epoch": 2.6848249027237356, "percentage": 89.49, "elapsed_time": "11:16:14", "remaining_time": "1:19:23"}
{"current_steps": 700, "total_steps": 771, "loss": 0.5009, "lr": 5e-06, "epoch": 2.7237354085603114, "percentage": 90.79, "elapsed_time": "11:25:53", "remaining_time": "1:09:34"}
{"current_steps": 710, "total_steps": 771, "loss": 0.5055, "lr": 5e-06, "epoch": 2.762645914396887, "percentage": 92.09, "elapsed_time": "11:35:32", "remaining_time": "0:59:45"}
{"current_steps": 720, "total_steps": 771, "loss": 0.5075, "lr": 5e-06, "epoch": 2.801556420233463, "percentage": 93.39, "elapsed_time": "11:45:11", "remaining_time": "0:49:57"}
{"current_steps": 730, "total_steps": 771, "loss": 0.4927, "lr": 5e-06, "epoch": 2.840466926070039, "percentage": 94.68, "elapsed_time": "11:54:50", "remaining_time": "0:40:08"}
{"current_steps": 740, "total_steps": 771, "loss": 0.51, "lr": 5e-06, "epoch": 2.8793774319066148, "percentage": 95.98, "elapsed_time": "12:04:28", "remaining_time": "0:30:20"}
{"current_steps": 750, "total_steps": 771, "loss": 0.4998, "lr": 5e-06, "epoch": 2.9182879377431905, "percentage": 97.28, "elapsed_time": "12:14:08", "remaining_time": "0:20:33"}
{"current_steps": 760, "total_steps": 771, "loss": 0.5119, "lr": 5e-06, "epoch": 2.9571984435797667, "percentage": 98.57, "elapsed_time": "12:23:48", "remaining_time": "0:10:45"}
{"current_steps": 770, "total_steps": 771, "loss": 0.5053, "lr": 5e-06, "epoch": 2.9961089494163424, "percentage": 99.87, "elapsed_time": "12:33:28", "remaining_time": "0:00:58"}
{"current_steps": 771, "total_steps": 771, "eval_loss": 0.6005940437316895, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "12:40:15", "remaining_time": "0:00:00"}
{"current_steps": 771, "total_steps": 771, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "12:41:41", "remaining_time": "0:00:00"}