penguin2-weights / trainer_log.jsonl
saim1212's picture
second model upload
c3e22bc verified
{"current_steps": 10, "total_steps": 620, "loss": 14.2026, "lr": 2.580645161290323e-06, "epoch": 0.16, "percentage": 1.61, "elapsed_time": "0:08:09", "remaining_time": "8:18:05"}
{"current_steps": 20, "total_steps": 620, "loss": 6.1329, "lr": 5.806451612903226e-06, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:16:20", "remaining_time": "8:10:05"}
{"current_steps": 30, "total_steps": 620, "loss": 4.058, "lr": 9.03225806451613e-06, "epoch": 0.48, "percentage": 4.84, "elapsed_time": "0:24:30", "remaining_time": "8:02:04"}
{"current_steps": 40, "total_steps": 620, "loss": 3.097, "lr": 1.2258064516129034e-05, "epoch": 0.64, "percentage": 6.45, "elapsed_time": "0:32:41", "remaining_time": "7:54:02"}
{"current_steps": 50, "total_steps": 620, "loss": 2.8274, "lr": 1.5483870967741936e-05, "epoch": 0.8, "percentage": 8.06, "elapsed_time": "0:40:51", "remaining_time": "7:45:49"}
{"current_steps": 60, "total_steps": 620, "loss": 2.4626, "lr": 1.870967741935484e-05, "epoch": 0.96, "percentage": 9.68, "elapsed_time": "0:49:02", "remaining_time": "7:37:42"}
{"current_steps": 70, "total_steps": 620, "loss": 2.1131, "lr": 1.999429490929718e-05, "epoch": 1.112, "percentage": 11.29, "elapsed_time": "0:56:48", "remaining_time": "7:26:22"}
{"current_steps": 80, "total_steps": 620, "loss": 2.0099, "lr": 1.9959454037227215e-05, "epoch": 1.272, "percentage": 12.9, "elapsed_time": "1:04:59", "remaining_time": "7:18:38"}
{"current_steps": 90, "total_steps": 620, "loss": 1.8846, "lr": 1.989305206325792e-05, "epoch": 1.432, "percentage": 14.52, "elapsed_time": "1:13:08", "remaining_time": "7:10:44"}
{"current_steps": 100, "total_steps": 620, "loss": 1.8903, "lr": 1.9795299412524948e-05, "epoch": 1.592, "percentage": 16.13, "elapsed_time": "1:21:19", "remaining_time": "7:02:52"}
{"current_steps": 110, "total_steps": 620, "loss": 1.7584, "lr": 1.9666505859174462e-05, "epoch": 1.752, "percentage": 17.74, "elapsed_time": "1:29:30", "remaining_time": "6:54:58"}
{"current_steps": 120, "total_steps": 620, "loss": 1.7185, "lr": 1.9507079544701583e-05, "epoch": 1.912, "percentage": 19.35, "elapsed_time": "1:37:41", "remaining_time": "6:47:04"}
{"current_steps": 130, "total_steps": 620, "loss": 1.5598, "lr": 1.9317525684566686e-05, "epoch": 2.064, "percentage": 20.97, "elapsed_time": "1:45:28", "remaining_time": "6:37:33"}
{"current_steps": 140, "total_steps": 620, "loss": 1.6693, "lr": 1.9098444967188308e-05, "epoch": 2.224, "percentage": 22.58, "elapsed_time": "1:53:40", "remaining_time": "6:29:43"}
{"current_steps": 150, "total_steps": 620, "loss": 1.5646, "lr": 1.8850531650386154e-05, "epoch": 2.384, "percentage": 24.19, "elapsed_time": "2:01:51", "remaining_time": "6:21:50"}
{"current_steps": 160, "total_steps": 620, "loss": 1.4366, "lr": 1.857457136130651e-05, "epoch": 2.544, "percentage": 25.81, "elapsed_time": "2:10:02", "remaining_time": "6:13:51"}
{"current_steps": 170, "total_steps": 620, "loss": 1.4132, "lr": 1.827143860680199e-05, "epoch": 2.7039999999999997, "percentage": 27.42, "elapsed_time": "2:18:13", "remaining_time": "6:05:53"}
{"current_steps": 180, "total_steps": 620, "loss": 1.3689, "lr": 1.7942094002155122e-05, "epoch": 2.864, "percentage": 29.03, "elapsed_time": "2:26:24", "remaining_time": "5:57:52"}
{"current_steps": 190, "total_steps": 620, "loss": 1.2682, "lr": 1.758758122692791e-05, "epoch": 3.016, "percentage": 30.65, "elapsed_time": "2:34:11", "remaining_time": "5:48:57"}
{"current_steps": 200, "total_steps": 620, "loss": 1.2686, "lr": 1.7209023717584013e-05, "epoch": 3.176, "percentage": 32.26, "elapsed_time": "2:42:22", "remaining_time": "5:40:59"}
{"current_steps": 210, "total_steps": 620, "loss": 1.2347, "lr": 1.6807621107364613e-05, "epoch": 3.336, "percentage": 33.87, "elapsed_time": "2:50:34", "remaining_time": "5:33:00"}
{"current_steps": 220, "total_steps": 620, "loss": 1.2462, "lr": 1.6384645424699835e-05, "epoch": 3.496, "percentage": 35.48, "elapsed_time": "2:58:44", "remaining_time": "5:24:59"}
{"current_steps": 230, "total_steps": 620, "loss": 1.2536, "lr": 1.594143706220273e-05, "epoch": 3.656, "percentage": 37.1, "elapsed_time": "3:06:56", "remaining_time": "5:16:58"}
{"current_steps": 240, "total_steps": 620, "loss": 1.2723, "lr": 1.5479400529019987e-05, "epoch": 3.816, "percentage": 38.71, "elapsed_time": "3:15:08", "remaining_time": "5:08:57"}
{"current_steps": 250, "total_steps": 620, "loss": 1.2036, "lr": 1.5000000000000002e-05, "epoch": 3.976, "percentage": 40.32, "elapsed_time": "3:23:18", "remaining_time": "5:00:53"}
{"current_steps": 260, "total_steps": 620, "loss": 1.0922, "lr": 1.4504754675782731e-05, "epoch": 4.128, "percentage": 41.94, "elapsed_time": "3:31:04", "remaining_time": "4:52:15"}
{"current_steps": 270, "total_steps": 620, "loss": 1.0985, "lr": 1.3995233968515105e-05, "epoch": 4.288, "percentage": 43.55, "elapsed_time": "3:39:15", "remaining_time": "4:44:13"}
{"current_steps": 280, "total_steps": 620, "loss": 1.1152, "lr": 1.3473052528448203e-05, "epoch": 4.448, "percentage": 45.16, "elapsed_time": "3:47:27", "remaining_time": "4:36:11"}
{"current_steps": 290, "total_steps": 620, "loss": 1.1175, "lr": 1.2939865127176771e-05, "epoch": 4.608, "percentage": 46.77, "elapsed_time": "3:55:38", "remaining_time": "4:28:08"}
{"current_steps": 300, "total_steps": 620, "loss": 1.119, "lr": 1.2397361413735785e-05, "epoch": 4.768, "percentage": 48.39, "elapsed_time": "4:03:50", "remaining_time": "4:20:05"}
{"current_steps": 310, "total_steps": 620, "loss": 1.1175, "lr": 1.1847260560171895e-05, "epoch": 4.928, "percentage": 50.0, "elapsed_time": "4:12:01", "remaining_time": "4:12:01"}
{"current_steps": 320, "total_steps": 620, "loss": 1.0205, "lr": 1.1291305813557616e-05, "epoch": 5.08, "percentage": 51.61, "elapsed_time": "4:19:49", "remaining_time": "4:03:34"}
{"current_steps": 330, "total_steps": 620, "loss": 1.0235, "lr": 1.0731258971712762e-05, "epoch": 5.24, "percentage": 53.23, "elapsed_time": "4:28:00", "remaining_time": "3:55:31"}
{"current_steps": 340, "total_steps": 620, "loss": 1.0103, "lr": 1.0168894800139311e-05, "epoch": 5.4, "percentage": 54.84, "elapsed_time": "4:36:11", "remaining_time": "3:47:27"}
{"current_steps": 350, "total_steps": 620, "loss": 0.999, "lr": 9.605995407862248e-06, "epoch": 5.5600000000000005, "percentage": 56.45, "elapsed_time": "4:44:22", "remaining_time": "3:39:22"}
{"current_steps": 360, "total_steps": 620, "loss": 0.9866, "lr": 9.04434459999902e-06, "epoch": 5.72, "percentage": 58.06, "elapsed_time": "4:52:33", "remaining_time": "3:31:17"}
{"current_steps": 370, "total_steps": 620, "loss": 1.0309, "lr": 8.485722224954237e-06, "epoch": 5.88, "percentage": 59.68, "elapsed_time": "5:00:45", "remaining_time": "3:23:12"}
{"current_steps": 380, "total_steps": 620, "loss": 0.9126, "lr": 7.93189853415293e-06, "epoch": 6.032, "percentage": 61.29, "elapsed_time": "5:08:32", "remaining_time": "3:14:52"}
{"current_steps": 390, "total_steps": 620, "loss": 0.9194, "lr": 7.384628572186334e-06, "epoch": 6.192, "percentage": 62.9, "elapsed_time": "5:16:43", "remaining_time": "3:06:47"}
{"current_steps": 400, "total_steps": 620, "loss": 0.907, "lr": 6.845646615147445e-06, "epoch": 6.352, "percentage": 64.52, "elapsed_time": "5:24:54", "remaining_time": "2:58:42"}
{"current_steps": 410, "total_steps": 620, "loss": 0.9, "lr": 6.31666067478113e-06, "epoch": 6.5120000000000005, "percentage": 66.13, "elapsed_time": "5:33:05", "remaining_time": "2:50:36"}
{"current_steps": 420, "total_steps": 620, "loss": 0.8984, "lr": 5.799347085864851e-06, "epoch": 6.672, "percentage": 67.74, "elapsed_time": "5:41:16", "remaining_time": "2:42:30"}
{"current_steps": 430, "total_steps": 620, "loss": 0.8658, "lr": 5.295345193972445e-06, "epoch": 6.832, "percentage": 69.35, "elapsed_time": "5:49:27", "remaining_time": "2:34:24"}
{"current_steps": 440, "total_steps": 620, "loss": 0.9213, "lr": 4.8062521604551245e-06, "epoch": 6.992, "percentage": 70.97, "elapsed_time": "5:57:39", "remaining_time": "2:26:18"}
{"current_steps": 450, "total_steps": 620, "loss": 0.7661, "lr": 4.333617901102592e-06, "epoch": 7.144, "percentage": 72.58, "elapsed_time": "6:05:26", "remaining_time": "2:18:03"}
{"current_steps": 460, "total_steps": 620, "loss": 0.791, "lr": 3.878940174523371e-06, "epoch": 7.304, "percentage": 74.19, "elapsed_time": "6:13:37", "remaining_time": "2:09:57"}
{"current_steps": 470, "total_steps": 620, "loss": 0.8174, "lr": 3.4436598358091577e-06, "epoch": 7.464, "percentage": 75.81, "elapsed_time": "6:21:49", "remaining_time": "2:01:51"}
{"current_steps": 480, "total_steps": 620, "loss": 0.8107, "lr": 3.0291562705240107e-06, "epoch": 7.624, "percentage": 77.42, "elapsed_time": "6:30:00", "remaining_time": "1:53:45"}
{"current_steps": 490, "total_steps": 620, "loss": 0.8199, "lr": 2.6367430234880286e-06, "epoch": 7.784, "percentage": 79.03, "elapsed_time": "6:38:11", "remaining_time": "1:45:38"}
{"current_steps": 500, "total_steps": 620, "loss": 0.819, "lr": 2.2676636362076075e-06, "epoch": 7.944, "percentage": 80.65, "elapsed_time": "6:46:23", "remaining_time": "1:37:31"}
{"current_steps": 510, "total_steps": 620, "loss": 0.7425, "lr": 1.9230877061433505e-06, "epoch": 8.096, "percentage": 82.26, "elapsed_time": "6:54:10", "remaining_time": "1:29:19"}
{"current_steps": 520, "total_steps": 620, "loss": 0.731, "lr": 1.60410718030361e-06, "epoch": 8.256, "percentage": 83.87, "elapsed_time": "7:02:22", "remaining_time": "1:21:13"}
{"current_steps": 530, "total_steps": 620, "loss": 0.7354, "lr": 1.3117328949091634e-06, "epoch": 8.416, "percentage": 85.48, "elapsed_time": "7:10:33", "remaining_time": "1:13:06"}
{"current_steps": 540, "total_steps": 620, "loss": 0.7442, "lr": 1.0468913720946084e-06, "epoch": 8.576, "percentage": 87.1, "elapsed_time": "7:18:45", "remaining_time": "1:05:00"}
{"current_steps": 550, "total_steps": 620, "loss": 0.7333, "lr": 8.10421883797694e-07, "epoch": 8.736, "percentage": 88.71, "elapsed_time": "7:26:56", "remaining_time": "0:56:53"}
{"current_steps": 560, "total_steps": 620, "loss": 0.7399, "lr": 6.030737921409169e-07, "epoch": 8.896, "percentage": 90.32, "elapsed_time": "7:35:08", "remaining_time": "0:48:45"}
{"current_steps": 570, "total_steps": 620, "loss": 0.6996, "lr": 4.2550417473364524e-07, "epoch": 9.048, "percentage": 91.94, "elapsed_time": "7:42:54", "remaining_time": "0:40:36"}
{"current_steps": 580, "total_steps": 620, "loss": 0.7126, "lr": 2.7827574242009434e-07, "epoch": 9.208, "percentage": 93.55, "elapsed_time": "7:51:05", "remaining_time": "0:32:29"}
{"current_steps": 590, "total_steps": 620, "loss": 0.6958, "lr": 1.6185505607171027e-07, "epoch": 9.368, "percentage": 95.16, "elapsed_time": "7:59:17", "remaining_time": "0:24:22"}
{"current_steps": 600, "total_steps": 620, "loss": 0.7154, "lr": 7.661104807487607e-08, "epoch": 9.528, "percentage": 96.77, "elapsed_time": "8:07:28", "remaining_time": "0:16:14"}
{"current_steps": 610, "total_steps": 620, "loss": 0.7047, "lr": 2.2813853199292745e-08, "epoch": 9.688, "percentage": 98.39, "elapsed_time": "8:15:40", "remaining_time": "0:08:07"}
{"current_steps": 620, "total_steps": 620, "loss": 0.7091, "lr": 6.339525519594159e-10, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "8:23:51", "remaining_time": "0:00:00"}
{"current_steps": 620, "total_steps": 620, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "8:23:53", "remaining_time": "0:00:00"}