OpenO1-LLama-8B-v0.1 / trainer_log.jsonl
paralym's picture
add sft model
49758f8
{"current_steps": 10, "total_steps": 2193, "loss": 0.9255, "learning_rate": 4.5454545454545457e-07, "epoch": 0.013679890560875513, "percentage": 0.46, "elapsed_time": "0:01:33", "remaining_time": "5:39:03"}
{"current_steps": 20, "total_steps": 2193, "loss": 0.863, "learning_rate": 9.090909090909091e-07, "epoch": 0.027359781121751026, "percentage": 0.91, "elapsed_time": "0:03:00", "remaining_time": "5:26:44"}
{"current_steps": 30, "total_steps": 2193, "loss": 0.7599, "learning_rate": 1.3636363636363636e-06, "epoch": 0.04103967168262654, "percentage": 1.37, "elapsed_time": "0:04:42", "remaining_time": "5:39:52"}
{"current_steps": 40, "total_steps": 2193, "loss": 0.7184, "learning_rate": 1.8181818181818183e-06, "epoch": 0.05471956224350205, "percentage": 1.82, "elapsed_time": "0:06:08", "remaining_time": "5:30:18"}
{"current_steps": 50, "total_steps": 2193, "loss": 0.6981, "learning_rate": 2.2727272727272728e-06, "epoch": 0.06839945280437756, "percentage": 2.28, "elapsed_time": "0:07:38", "remaining_time": "5:27:23"}
{"current_steps": 60, "total_steps": 2193, "loss": 0.6943, "learning_rate": 2.7272727272727272e-06, "epoch": 0.08207934336525308, "percentage": 2.74, "elapsed_time": "0:09:12", "remaining_time": "5:27:29"}
{"current_steps": 70, "total_steps": 2193, "loss": 0.6687, "learning_rate": 3.181818181818182e-06, "epoch": 0.09575923392612859, "percentage": 3.19, "elapsed_time": "0:10:48", "remaining_time": "5:27:44"}
{"current_steps": 80, "total_steps": 2193, "loss": 0.6694, "learning_rate": 3.6363636363636366e-06, "epoch": 0.1094391244870041, "percentage": 3.65, "elapsed_time": "0:12:25", "remaining_time": "5:28:01"}
{"current_steps": 90, "total_steps": 2193, "loss": 0.6602, "learning_rate": 4.0909090909090915e-06, "epoch": 0.12311901504787962, "percentage": 4.1, "elapsed_time": "0:14:02", "remaining_time": "5:28:17"}
{"current_steps": 100, "total_steps": 2193, "loss": 0.6514, "learning_rate": 4.5454545454545455e-06, "epoch": 0.13679890560875513, "percentage": 4.56, "elapsed_time": "0:15:30", "remaining_time": "5:24:34"}
{"current_steps": 110, "total_steps": 2193, "loss": 0.6413, "learning_rate": 5e-06, "epoch": 0.15047879616963064, "percentage": 5.02, "elapsed_time": "0:17:01", "remaining_time": "5:22:16"}
{"current_steps": 120, "total_steps": 2193, "loss": 0.6584, "learning_rate": 5.4545454545454545e-06, "epoch": 0.16415868673050615, "percentage": 5.47, "elapsed_time": "0:18:22", "remaining_time": "5:17:30"}
{"current_steps": 130, "total_steps": 2193, "loss": 0.6292, "learning_rate": 5.90909090909091e-06, "epoch": 0.17783857729138167, "percentage": 5.93, "elapsed_time": "0:19:51", "remaining_time": "5:15:06"}
{"current_steps": 140, "total_steps": 2193, "loss": 0.6487, "learning_rate": 6.363636363636364e-06, "epoch": 0.19151846785225718, "percentage": 6.38, "elapsed_time": "0:21:21", "remaining_time": "5:13:12"}
{"current_steps": 150, "total_steps": 2193, "loss": 0.6294, "learning_rate": 6.818181818181818e-06, "epoch": 0.2051983584131327, "percentage": 6.84, "elapsed_time": "0:22:48", "remaining_time": "5:10:45"}
{"current_steps": 160, "total_steps": 2193, "loss": 0.6443, "learning_rate": 7.272727272727273e-06, "epoch": 0.2188782489740082, "percentage": 7.3, "elapsed_time": "0:24:20", "remaining_time": "5:09:19"}
{"current_steps": 170, "total_steps": 2193, "loss": 0.6411, "learning_rate": 7.727272727272727e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:25:49", "remaining_time": "5:07:23"}
{"current_steps": 180, "total_steps": 2193, "loss": 0.6385, "learning_rate": 8.181818181818183e-06, "epoch": 0.24623803009575923, "percentage": 8.21, "elapsed_time": "0:27:18", "remaining_time": "5:05:28"}
{"current_steps": 190, "total_steps": 2193, "loss": 0.6466, "learning_rate": 8.636363636363637e-06, "epoch": 0.25991792065663477, "percentage": 8.66, "elapsed_time": "0:28:56", "remaining_time": "5:05:01"}
{"current_steps": 200, "total_steps": 2193, "loss": 0.6185, "learning_rate": 9.090909090909091e-06, "epoch": 0.27359781121751026, "percentage": 9.12, "elapsed_time": "0:30:19", "remaining_time": "5:02:08"}
{"current_steps": 200, "total_steps": 2193, "eval_loss": 0.6430878043174744, "epoch": 0.27359781121751026, "percentage": 9.12, "elapsed_time": "0:33:07", "remaining_time": "5:30:08"}
{"current_steps": 210, "total_steps": 2193, "loss": 0.6235, "learning_rate": 9.545454545454547e-06, "epoch": 0.2872777017783858, "percentage": 9.58, "elapsed_time": "0:34:43", "remaining_time": "5:27:50"}
{"current_steps": 220, "total_steps": 2193, "loss": 0.6305, "learning_rate": 1e-05, "epoch": 0.3009575923392613, "percentage": 10.03, "elapsed_time": "0:36:08", "remaining_time": "5:24:08"}
{"current_steps": 230, "total_steps": 2193, "loss": 0.6308, "learning_rate": 9.99936616472178e-06, "epoch": 0.3146374829001368, "percentage": 10.49, "elapsed_time": "0:37:42", "remaining_time": "5:21:49"}
{"current_steps": 240, "total_steps": 2193, "loss": 0.6331, "learning_rate": 9.997464819585985e-06, "epoch": 0.3283173734610123, "percentage": 10.94, "elapsed_time": "0:39:04", "remaining_time": "5:17:54"}
{"current_steps": 250, "total_steps": 2193, "loss": 0.6319, "learning_rate": 9.994296446648463e-06, "epoch": 0.34199726402188785, "percentage": 11.4, "elapsed_time": "0:40:37", "remaining_time": "5:15:45"}
{"current_steps": 260, "total_steps": 2193, "loss": 0.6368, "learning_rate": 9.989861849199833e-06, "epoch": 0.35567715458276333, "percentage": 11.86, "elapsed_time": "0:42:11", "remaining_time": "5:13:39"}
{"current_steps": 270, "total_steps": 2193, "loss": 0.628, "learning_rate": 9.984162151561814e-06, "epoch": 0.3693570451436389, "percentage": 12.31, "elapsed_time": "0:43:40", "remaining_time": "5:11:02"}
{"current_steps": 280, "total_steps": 2193, "loss": 0.6191, "learning_rate": 9.977198798802186e-06, "epoch": 0.38303693570451436, "percentage": 12.77, "elapsed_time": "0:45:06", "remaining_time": "5:08:09"}
{"current_steps": 290, "total_steps": 2193, "loss": 0.6311, "learning_rate": 9.9689735563684e-06, "epoch": 0.3967168262653899, "percentage": 13.22, "elapsed_time": "0:46:43", "remaining_time": "5:06:33"}
{"current_steps": 300, "total_steps": 2193, "loss": 0.6204, "learning_rate": 9.959488509639986e-06, "epoch": 0.4103967168262654, "percentage": 13.68, "elapsed_time": "0:48:27", "remaining_time": "5:05:48"}
{"current_steps": 310, "total_steps": 2193, "loss": 0.6185, "learning_rate": 9.948746063399836e-06, "epoch": 0.4240766073871409, "percentage": 14.14, "elapsed_time": "0:49:56", "remaining_time": "5:03:21"}
{"current_steps": 320, "total_steps": 2193, "loss": 0.63, "learning_rate": 9.936748941224514e-06, "epoch": 0.4377564979480164, "percentage": 14.59, "elapsed_time": "0:51:25", "remaining_time": "5:00:57"}
{"current_steps": 330, "total_steps": 2193, "loss": 0.6325, "learning_rate": 9.923500184793728e-06, "epoch": 0.45143638850889195, "percentage": 15.05, "elapsed_time": "0:52:57", "remaining_time": "4:58:56"}
{"current_steps": 340, "total_steps": 2193, "loss": 0.6202, "learning_rate": 9.909003153119165e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:54:29", "remaining_time": "4:57:01"}
{"current_steps": 350, "total_steps": 2193, "loss": 0.6157, "learning_rate": 9.893261521692865e-06, "epoch": 0.478796169630643, "percentage": 15.96, "elapsed_time": "0:56:02", "remaining_time": "4:55:07"}
{"current_steps": 360, "total_steps": 2193, "loss": 0.6244, "learning_rate": 9.876279281555363e-06, "epoch": 0.49247606019151846, "percentage": 16.42, "elapsed_time": "0:57:30", "remaining_time": "4:52:49"}
{"current_steps": 370, "total_steps": 2193, "loss": 0.6209, "learning_rate": 9.858060738283819e-06, "epoch": 0.506155950752394, "percentage": 16.87, "elapsed_time": "0:58:59", "remaining_time": "4:50:40"}
{"current_steps": 380, "total_steps": 2193, "loss": 0.6168, "learning_rate": 9.838610510900412e-06, "epoch": 0.5198358413132695, "percentage": 17.33, "elapsed_time": "1:00:25", "remaining_time": "4:48:16"}
{"current_steps": 390, "total_steps": 2193, "loss": 0.6273, "learning_rate": 9.817933530701258e-06, "epoch": 0.533515731874145, "percentage": 17.78, "elapsed_time": "1:02:02", "remaining_time": "4:46:48"}
{"current_steps": 400, "total_steps": 2193, "loss": 0.6088, "learning_rate": 9.79603504000615e-06, "epoch": 0.5471956224350205, "percentage": 18.24, "elapsed_time": "1:03:33", "remaining_time": "4:44:54"}
{"current_steps": 400, "total_steps": 2193, "eval_loss": 0.6271325945854187, "epoch": 0.5471956224350205, "percentage": 18.24, "elapsed_time": "1:06:21", "remaining_time": "4:57:26"}
{"current_steps": 410, "total_steps": 2193, "loss": 0.6137, "learning_rate": 9.772920590829471e-06, "epoch": 0.560875512995896, "percentage": 18.7, "elapsed_time": "1:08:00", "remaining_time": "4:55:46"}
{"current_steps": 420, "total_steps": 2193, "loss": 0.6143, "learning_rate": 9.748596043472547e-06, "epoch": 0.5745554035567716, "percentage": 19.15, "elapsed_time": "1:09:34", "remaining_time": "4:53:44"}
{"current_steps": 430, "total_steps": 2193, "loss": 0.6068, "learning_rate": 9.723067565037874e-06, "epoch": 0.5882352941176471, "percentage": 19.61, "elapsed_time": "1:11:15", "remaining_time": "4:52:10"}
{"current_steps": 440, "total_steps": 2193, "loss": 0.6263, "learning_rate": 9.696341627865548e-06, "epoch": 0.6019151846785226, "percentage": 20.06, "elapsed_time": "1:12:40", "remaining_time": "4:49:31"}
{"current_steps": 450, "total_steps": 2193, "loss": 0.624, "learning_rate": 9.668425007892298e-06, "epoch": 0.615595075239398, "percentage": 20.52, "elapsed_time": "1:14:16", "remaining_time": "4:47:42"}
{"current_steps": 460, "total_steps": 2193, "loss": 0.6115, "learning_rate": 9.639324782933556e-06, "epoch": 0.6292749658002736, "percentage": 20.98, "elapsed_time": "1:15:44", "remaining_time": "4:45:21"}
{"current_steps": 470, "total_steps": 2193, "loss": 0.6231, "learning_rate": 9.609048330888996e-06, "epoch": 0.6429548563611491, "percentage": 21.43, "elapsed_time": "1:17:17", "remaining_time": "4:43:20"}
{"current_steps": 480, "total_steps": 2193, "loss": 0.6087, "learning_rate": 9.577603327871983e-06, "epoch": 0.6566347469220246, "percentage": 21.89, "elapsed_time": "1:18:47", "remaining_time": "4:41:12"}
{"current_steps": 490, "total_steps": 2193, "loss": 0.6207, "learning_rate": 9.544997746263409e-06, "epoch": 0.6703146374829001, "percentage": 22.34, "elapsed_time": "1:20:16", "remaining_time": "4:38:58"}
{"current_steps": 500, "total_steps": 2193, "loss": 0.5912, "learning_rate": 9.511239852690429e-06, "epoch": 0.6839945280437757, "percentage": 22.8, "elapsed_time": "1:21:54", "remaining_time": "4:37:20"}
{"current_steps": 510, "total_steps": 2193, "loss": 0.6084, "learning_rate": 9.476338205930593e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "1:23:39", "remaining_time": "4:36:04"}
{"current_steps": 520, "total_steps": 2193, "loss": 0.6132, "learning_rate": 9.440301654741889e-06, "epoch": 0.7113543091655267, "percentage": 23.71, "elapsed_time": "1:25:10", "remaining_time": "4:34:00"}
{"current_steps": 530, "total_steps": 2193, "loss": 0.6194, "learning_rate": 9.403139335619302e-06, "epoch": 0.7250341997264022, "percentage": 24.17, "elapsed_time": "1:26:42", "remaining_time": "4:32:05"}
{"current_steps": 540, "total_steps": 2193, "loss": 0.5951, "learning_rate": 9.36486067047838e-06, "epoch": 0.7387140902872777, "percentage": 24.62, "elapsed_time": "1:28:14", "remaining_time": "4:30:08"}
{"current_steps": 550, "total_steps": 2193, "loss": 0.6007, "learning_rate": 9.325475364266474e-06, "epoch": 0.7523939808481532, "percentage": 25.08, "elapsed_time": "1:29:44", "remaining_time": "4:28:03"}
{"current_steps": 560, "total_steps": 2193, "loss": 0.6146, "learning_rate": 9.28499340250219e-06, "epoch": 0.7660738714090287, "percentage": 25.54, "elapsed_time": "1:31:10", "remaining_time": "4:25:50"}
{"current_steps": 570, "total_steps": 2193, "loss": 0.6077, "learning_rate": 9.24342504874373e-06, "epoch": 0.7797537619699042, "percentage": 25.99, "elapsed_time": "1:32:51", "remaining_time": "4:24:25"}
{"current_steps": 580, "total_steps": 2193, "loss": 0.6001, "learning_rate": 9.200780841986717e-06, "epoch": 0.7934336525307798, "percentage": 26.45, "elapsed_time": "1:34:26", "remaining_time": "4:22:38"}
{"current_steps": 590, "total_steps": 2193, "loss": 0.6289, "learning_rate": 9.157071593992217e-06, "epoch": 0.8071135430916553, "percentage": 26.9, "elapsed_time": "1:35:59", "remaining_time": "4:20:49"}
{"current_steps": 600, "total_steps": 2193, "loss": 0.6083, "learning_rate": 9.112308386545574e-06, "epoch": 0.8207934336525308, "percentage": 27.36, "elapsed_time": "1:37:29", "remaining_time": "4:18:49"}
{"current_steps": 600, "total_steps": 2193, "eval_loss": 0.6138648390769958, "epoch": 0.8207934336525308, "percentage": 27.36, "elapsed_time": "1:40:18", "remaining_time": "4:26:17"}
{"current_steps": 610, "total_steps": 2193, "loss": 0.6028, "learning_rate": 9.066502568646805e-06, "epoch": 0.8344733242134063, "percentage": 27.82, "elapsed_time": "1:41:58", "remaining_time": "4:24:37"}
{"current_steps": 620, "total_steps": 2193, "loss": 0.6025, "learning_rate": 9.019665753633247e-06, "epoch": 0.8481532147742818, "percentage": 28.27, "elapsed_time": "1:43:20", "remaining_time": "4:22:12"}
{"current_steps": 630, "total_steps": 2193, "loss": 0.6072, "learning_rate": 8.971809816235164e-06, "epoch": 0.8618331053351573, "percentage": 28.73, "elapsed_time": "1:44:56", "remaining_time": "4:20:22"}
{"current_steps": 640, "total_steps": 2193, "loss": 0.6014, "learning_rate": 8.922946889565119e-06, "epoch": 0.8755129958960328, "percentage": 29.18, "elapsed_time": "1:46:21", "remaining_time": "4:18:06"}
{"current_steps": 650, "total_steps": 2193, "loss": 0.584, "learning_rate": 8.873089362041797e-06, "epoch": 0.8891928864569083, "percentage": 29.64, "elapsed_time": "1:47:57", "remaining_time": "4:16:16"}
{"current_steps": 660, "total_steps": 2193, "loss": 0.5929, "learning_rate": 8.822249874249131e-06, "epoch": 0.9028727770177839, "percentage": 30.1, "elapsed_time": "1:49:31", "remaining_time": "4:14:24"}
{"current_steps": 670, "total_steps": 2193, "loss": 0.5954, "learning_rate": 8.770441315731477e-06, "epoch": 0.9165526675786594, "percentage": 30.55, "elapsed_time": "1:51:03", "remaining_time": "4:12:26"}
{"current_steps": 680, "total_steps": 2193, "loss": 0.5876, "learning_rate": 8.717676821725679e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "1:52:31", "remaining_time": "4:10:21"}
{"current_steps": 690, "total_steps": 2193, "loss": 0.6006, "learning_rate": 8.663969769830824e-06, "epoch": 0.9439124487004104, "percentage": 31.46, "elapsed_time": "1:53:52", "remaining_time": "4:08:03"}
{"current_steps": 700, "total_steps": 2193, "loss": 0.5974, "learning_rate": 8.609333776616592e-06, "epoch": 0.957592339261286, "percentage": 31.92, "elapsed_time": "1:55:30", "remaining_time": "4:06:21"}
{"current_steps": 710, "total_steps": 2193, "loss": 0.6043, "learning_rate": 8.553782694170963e-06, "epoch": 0.9712722298221614, "percentage": 32.38, "elapsed_time": "1:57:04", "remaining_time": "4:04:32"}
{"current_steps": 720, "total_steps": 2193, "loss": 0.5779, "learning_rate": 8.497330606588257e-06, "epoch": 0.9849521203830369, "percentage": 32.83, "elapsed_time": "1:58:37", "remaining_time": "4:02:41"}
{"current_steps": 730, "total_steps": 2193, "loss": 0.6108, "learning_rate": 8.439991826398331e-06, "epoch": 0.9986320109439124, "percentage": 33.29, "elapsed_time": "2:00:09", "remaining_time": "4:00:49"}
{"current_steps": 740, "total_steps": 2193, "loss": 0.4662, "learning_rate": 8.38178089093786e-06, "epoch": 1.012311901504788, "percentage": 33.74, "elapsed_time": "2:01:40", "remaining_time": "3:58:55"}
{"current_steps": 750, "total_steps": 2193, "loss": 0.4296, "learning_rate": 8.322712558664635e-06, "epoch": 1.0259917920656634, "percentage": 34.2, "elapsed_time": "2:03:09", "remaining_time": "3:56:58"}
{"current_steps": 760, "total_steps": 2193, "loss": 0.4295, "learning_rate": 8.262801805415783e-06, "epoch": 1.039671682626539, "percentage": 34.66, "elapsed_time": "2:04:40", "remaining_time": "3:55:04"}
{"current_steps": 770, "total_steps": 2193, "loss": 0.4244, "learning_rate": 8.202063820610887e-06, "epoch": 1.0533515731874146, "percentage": 35.11, "elapsed_time": "2:06:11", "remaining_time": "3:53:11"}
{"current_steps": 780, "total_steps": 2193, "loss": 0.4257, "learning_rate": 8.140514003400945e-06, "epoch": 1.06703146374829, "percentage": 35.57, "elapsed_time": "2:07:46", "remaining_time": "3:51:27"}
{"current_steps": 790, "total_steps": 2193, "loss": 0.4325, "learning_rate": 8.078167958764162e-06, "epoch": 1.0807113543091655, "percentage": 36.02, "elapsed_time": "2:09:20", "remaining_time": "3:49:42"}
{"current_steps": 800, "total_steps": 2193, "loss": 0.4314, "learning_rate": 8.015041493549562e-06, "epoch": 1.094391244870041, "percentage": 36.48, "elapsed_time": "2:10:45", "remaining_time": "3:47:41"}
{"current_steps": 800, "total_steps": 2193, "eval_loss": 0.6188511848449707, "epoch": 1.094391244870041, "percentage": 36.48, "elapsed_time": "2:13:34", "remaining_time": "3:52:34"}
{"current_steps": 810, "total_steps": 2193, "loss": 0.4335, "learning_rate": 7.951150612469396e-06, "epoch": 1.1080711354309165, "percentage": 36.94, "elapsed_time": "2:15:02", "remaining_time": "3:50:34"}
{"current_steps": 820, "total_steps": 2193, "loss": 0.4271, "learning_rate": 7.886511514041422e-06, "epoch": 1.121751025991792, "percentage": 37.39, "elapsed_time": "2:16:28", "remaining_time": "3:48:30"}
{"current_steps": 830, "total_steps": 2193, "loss": 0.4367, "learning_rate": 7.821140586482013e-06, "epoch": 1.1354309165526675, "percentage": 37.85, "elapsed_time": "2:18:02", "remaining_time": "3:46:41"}
{"current_steps": 840, "total_steps": 2193, "loss": 0.4359, "learning_rate": 7.755054403551191e-06, "epoch": 1.1491108071135432, "percentage": 38.3, "elapsed_time": "2:19:38", "remaining_time": "3:44:55"}
{"current_steps": 850, "total_steps": 2193, "loss": 0.433, "learning_rate": 7.688269720350616e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "2:21:12", "remaining_time": "3:43:05"}
{"current_steps": 860, "total_steps": 2193, "loss": 0.4387, "learning_rate": 7.620803469075588e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "2:22:37", "remaining_time": "3:41:04"}
{"current_steps": 870, "total_steps": 2193, "loss": 0.4198, "learning_rate": 7.552672754722169e-06, "epoch": 1.1901504787961696, "percentage": 39.67, "elapsed_time": "2:24:06", "remaining_time": "3:39:08"}
{"current_steps": 880, "total_steps": 2193, "loss": 0.4356, "learning_rate": 7.483894850750473e-06, "epoch": 1.2038303693570451, "percentage": 40.13, "elapsed_time": "2:25:38", "remaining_time": "3:37:18"}
{"current_steps": 890, "total_steps": 2193, "loss": 0.4334, "learning_rate": 7.414487194705258e-06, "epoch": 1.2175102599179206, "percentage": 40.58, "elapsed_time": "2:27:07", "remaining_time": "3:35:23"}
{"current_steps": 900, "total_steps": 2193, "loss": 0.4335, "learning_rate": 7.344467383794917e-06, "epoch": 1.231190150478796, "percentage": 41.04, "elapsed_time": "2:28:35", "remaining_time": "3:33:28"}
{"current_steps": 910, "total_steps": 2193, "loss": 0.4338, "learning_rate": 7.2738531704299845e-06, "epoch": 1.2448700410396718, "percentage": 41.5, "elapsed_time": "2:30:05", "remaining_time": "3:31:36"}
{"current_steps": 920, "total_steps": 2193, "loss": 0.4506, "learning_rate": 7.2026624577222855e-06, "epoch": 1.2585499316005473, "percentage": 41.95, "elapsed_time": "2:31:34", "remaining_time": "3:29:44"}
{"current_steps": 930, "total_steps": 2193, "loss": 0.4356, "learning_rate": 7.1309132949459e-06, "epoch": 1.2722298221614228, "percentage": 42.41, "elapsed_time": "2:33:09", "remaining_time": "3:28:00"}
{"current_steps": 940, "total_steps": 2193, "loss": 0.4293, "learning_rate": 7.058623872961051e-06, "epoch": 1.2859097127222983, "percentage": 42.86, "elapsed_time": "2:34:33", "remaining_time": "3:26:01"}
{"current_steps": 950, "total_steps": 2193, "loss": 0.4268, "learning_rate": 6.985812519602094e-06, "epoch": 1.2995896032831737, "percentage": 43.32, "elapsed_time": "2:35:59", "remaining_time": "3:24:06"}
{"current_steps": 960, "total_steps": 2193, "loss": 0.4286, "learning_rate": 6.912497695030796e-06, "epoch": 1.3132694938440492, "percentage": 43.78, "elapsed_time": "2:37:35", "remaining_time": "3:22:24"}
{"current_steps": 970, "total_steps": 2193, "loss": 0.4313, "learning_rate": 6.838697987056046e-06, "epoch": 1.3269493844049247, "percentage": 44.23, "elapsed_time": "2:38:58", "remaining_time": "3:20:25"}
{"current_steps": 980, "total_steps": 2193, "loss": 0.4279, "learning_rate": 6.764432106421223e-06, "epoch": 1.3406292749658002, "percentage": 44.69, "elapsed_time": "2:40:25", "remaining_time": "3:18:33"}
{"current_steps": 990, "total_steps": 2193, "loss": 0.4305, "learning_rate": 6.68971888206037e-06, "epoch": 1.3543091655266757, "percentage": 45.14, "elapsed_time": "2:41:56", "remaining_time": "3:16:46"}
{"current_steps": 1000, "total_steps": 2193, "loss": 0.4322, "learning_rate": 6.614577256324426e-06, "epoch": 1.3679890560875512, "percentage": 45.6, "elapsed_time": "2:43:24", "remaining_time": "3:14:56"}
{"current_steps": 1000, "total_steps": 2193, "eval_loss": 0.617301881313324, "epoch": 1.3679890560875512, "percentage": 45.6, "elapsed_time": "2:46:12", "remaining_time": "3:18:17"}
{"current_steps": 1010, "total_steps": 2193, "loss": 0.4279, "learning_rate": 6.539026280178695e-06, "epoch": 1.3816689466484269, "percentage": 46.06, "elapsed_time": "2:49:25", "remaining_time": "3:18:26"}
{"current_steps": 1020, "total_steps": 2193, "loss": 0.4309, "learning_rate": 6.46308510837277e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "2:50:43", "remaining_time": "3:16:20"}
{"current_steps": 1030, "total_steps": 2193, "loss": 0.4349, "learning_rate": 6.386772994584156e-06, "epoch": 1.4090287277701778, "percentage": 46.97, "elapsed_time": "2:52:22", "remaining_time": "3:14:37"}
{"current_steps": 1040, "total_steps": 2193, "loss": 0.4232, "learning_rate": 6.310109286536801e-06, "epoch": 1.4227086183310533, "percentage": 47.42, "elapsed_time": "2:54:02", "remaining_time": "3:12:57"}
{"current_steps": 1050, "total_steps": 2193, "loss": 0.4355, "learning_rate": 6.233113421095794e-06, "epoch": 1.4363885088919288, "percentage": 47.88, "elapsed_time": "2:55:43", "remaining_time": "3:11:17"}
{"current_steps": 1060, "total_steps": 2193, "loss": 0.4286, "learning_rate": 6.155804919339453e-06, "epoch": 1.4500683994528043, "percentage": 48.34, "elapsed_time": "2:57:16", "remaining_time": "3:09:28"}
{"current_steps": 1070, "total_steps": 2193, "loss": 0.4314, "learning_rate": 6.078203381610064e-06, "epoch": 1.46374829001368, "percentage": 48.79, "elapsed_time": "2:58:48", "remaining_time": "3:07:40"}
{"current_steps": 1080, "total_steps": 2193, "loss": 0.4292, "learning_rate": 6.000328482544532e-06, "epoch": 1.4774281805745555, "percentage": 49.25, "elapsed_time": "3:00:20", "remaining_time": "3:05:50"}
{"current_steps": 1090, "total_steps": 2193, "loss": 0.4295, "learning_rate": 5.92219996608618e-06, "epoch": 1.491108071135431, "percentage": 49.7, "elapsed_time": "3:01:48", "remaining_time": "3:03:59"}
{"current_steps": 1100, "total_steps": 2193, "loss": 0.4399, "learning_rate": 5.843837640479e-06, "epoch": 1.5047879616963065, "percentage": 50.16, "elapsed_time": "3:03:17", "remaining_time": "3:02:07"}
{"current_steps": 1110, "total_steps": 2193, "loss": 0.424, "learning_rate": 5.765261373245567e-06, "epoch": 1.518467852257182, "percentage": 50.62, "elapsed_time": "3:04:53", "remaining_time": "3:00:23"}
{"current_steps": 1120, "total_steps": 2193, "loss": 0.4285, "learning_rate": 5.686491086149965e-06, "epoch": 1.5321477428180574, "percentage": 51.07, "elapsed_time": "3:06:36", "remaining_time": "2:58:46"}
{"current_steps": 1130, "total_steps": 2193, "loss": 0.4397, "learning_rate": 5.60754675014693e-06, "epoch": 1.545827633378933, "percentage": 51.53, "elapsed_time": "3:08:20", "remaining_time": "2:57:10"}
{"current_steps": 1140, "total_steps": 2193, "loss": 0.4184, "learning_rate": 5.528448380318532e-06, "epoch": 1.5595075239398084, "percentage": 51.98, "elapsed_time": "3:09:48", "remaining_time": "2:55:19"}
{"current_steps": 1150, "total_steps": 2193, "loss": 0.4199, "learning_rate": 5.449216030799667e-06, "epoch": 1.573187414500684, "percentage": 52.44, "elapsed_time": "3:11:29", "remaining_time": "2:53:40"}
{"current_steps": 1160, "total_steps": 2193, "loss": 0.4392, "learning_rate": 5.369869789693656e-06, "epoch": 1.5868673050615594, "percentage": 52.9, "elapsed_time": "3:12:55", "remaining_time": "2:51:47"}
{"current_steps": 1170, "total_steps": 2193, "loss": 0.4337, "learning_rate": 5.290429773979224e-06, "epoch": 1.6005471956224349, "percentage": 53.35, "elapsed_time": "3:14:33", "remaining_time": "2:50:06"}
{"current_steps": 1180, "total_steps": 2193, "loss": 0.4448, "learning_rate": 5.2109161244101545e-06, "epoch": 1.6142270861833106, "percentage": 53.81, "elapsed_time": "3:16:11", "remaining_time": "2:48:25"}
{"current_steps": 1190, "total_steps": 2193, "loss": 0.4286, "learning_rate": 5.1313490004089265e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "3:17:33", "remaining_time": "2:46:31"}
{"current_steps": 1200, "total_steps": 2193, "loss": 0.4368, "learning_rate": 5.05174857495561e-06, "epoch": 1.6415868673050615, "percentage": 54.72, "elapsed_time": "3:19:08", "remaining_time": "2:44:47"}
{"current_steps": 1200, "total_steps": 2193, "eval_loss": 0.608180046081543, "epoch": 1.6415868673050615, "percentage": 54.72, "elapsed_time": "3:21:56", "remaining_time": "2:47:06"}
{"current_steps": 1210, "total_steps": 2193, "loss": 0.4276, "learning_rate": 4.972135029473333e-06, "epoch": 1.655266757865937, "percentage": 55.18, "elapsed_time": "3:23:25", "remaining_time": "2:45:16"}
{"current_steps": 1220, "total_steps": 2193, "loss": 0.4334, "learning_rate": 4.892528548711594e-06, "epoch": 1.6689466484268127, "percentage": 55.63, "elapsed_time": "3:24:52", "remaining_time": "2:43:23"}
{"current_steps": 1230, "total_steps": 2193, "loss": 0.4272, "learning_rate": 4.812949315628746e-06, "epoch": 1.6826265389876882, "percentage": 56.09, "elapsed_time": "3:26:25", "remaining_time": "2:41:36"}
{"current_steps": 1240, "total_steps": 2193, "loss": 0.4164, "learning_rate": 4.7334175062749275e-06, "epoch": 1.6963064295485637, "percentage": 56.54, "elapsed_time": "3:28:03", "remaining_time": "2:39:54"}
{"current_steps": 1250, "total_steps": 2193, "loss": 0.4415, "learning_rate": 4.653953284676737e-06, "epoch": 1.7099863201094392, "percentage": 57.0, "elapsed_time": "3:29:36", "remaining_time": "2:38:07"}
{"current_steps": 1260, "total_steps": 2193, "loss": 0.4161, "learning_rate": 4.574576797724984e-06, "epoch": 1.7236662106703147, "percentage": 57.46, "elapsed_time": "3:31:06", "remaining_time": "2:36:19"}
{"current_steps": 1270, "total_steps": 2193, "loss": 0.4326, "learning_rate": 4.495308170066739e-06, "epoch": 1.7373461012311902, "percentage": 57.91, "elapsed_time": "3:32:36", "remaining_time": "2:34:30"}
{"current_steps": 1280, "total_steps": 2193, "loss": 0.4426, "learning_rate": 4.4161674990030715e-06, "epoch": 1.7510259917920656, "percentage": 58.37, "elapsed_time": "3:34:17", "remaining_time": "2:32:51"}
{"current_steps": 1290, "total_steps": 2193, "loss": 0.4263, "learning_rate": 4.3371748493936834e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "3:35:40", "remaining_time": "2:30:58"}
{"current_steps": 1300, "total_steps": 2193, "loss": 0.422, "learning_rate": 4.2583502485697945e-06, "epoch": 1.7783857729138166, "percentage": 59.28, "elapsed_time": "3:37:06", "remaining_time": "2:29:08"}
{"current_steps": 1310, "total_steps": 2193, "loss": 0.4278, "learning_rate": 4.179713681256523e-06, "epoch": 1.792065663474692, "percentage": 59.74, "elapsed_time": "3:38:35", "remaining_time": "2:27:20"}
{"current_steps": 1320, "total_steps": 2193, "loss": 0.4126, "learning_rate": 4.101285084506075e-06, "epoch": 1.8057455540355676, "percentage": 60.19, "elapsed_time": "3:39:55", "remaining_time": "2:25:27"}
{"current_steps": 1330, "total_steps": 2193, "loss": 0.4302, "learning_rate": 4.023084342643026e-06, "epoch": 1.819425444596443, "percentage": 60.65, "elapsed_time": "3:41:17", "remaining_time": "2:23:35"}
{"current_steps": 1340, "total_steps": 2193, "loss": 0.4308, "learning_rate": 3.94513128222297e-06, "epoch": 1.8331053351573188, "percentage": 61.1, "elapsed_time": "3:42:47", "remaining_time": "2:21:49"}
{"current_steps": 1350, "total_steps": 2193, "loss": 0.4343, "learning_rate": 3.867445667005801e-06, "epoch": 1.8467852257181943, "percentage": 61.56, "elapsed_time": "3:44:12", "remaining_time": "2:20:00"}
{"current_steps": 1360, "total_steps": 2193, "loss": 0.4301, "learning_rate": 3.790047192944931e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "3:45:47", "remaining_time": "2:18:17"}
{"current_steps": 1370, "total_steps": 2193, "loss": 0.4175, "learning_rate": 3.7129554831936998e-06, "epoch": 1.8741450068399452, "percentage": 62.47, "elapsed_time": "3:47:18", "remaining_time": "2:16:33"}
{"current_steps": 1380, "total_steps": 2193, "loss": 0.4175, "learning_rate": 3.6361900831302264e-06, "epoch": 1.887824897400821, "percentage": 62.93, "elapsed_time": "3:48:54", "remaining_time": "2:14:51"}
{"current_steps": 1390, "total_steps": 2193, "loss": 0.4211, "learning_rate": 3.5597704554019907e-06, "epoch": 1.9015047879616964, "percentage": 63.38, "elapsed_time": "3:50:20", "remaining_time": "2:13:04"}
{"current_steps": 1400, "total_steps": 2193, "loss": 0.4195, "learning_rate": 3.4837159749913944e-06, "epoch": 1.915184678522572, "percentage": 63.84, "elapsed_time": "3:51:49", "remaining_time": "2:11:18"}
{"current_steps": 1400, "total_steps": 2193, "eval_loss": 0.6006618142127991, "epoch": 1.915184678522572, "percentage": 63.84, "elapsed_time": "3:54:36", "remaining_time": "2:12:53"}
{"current_steps": 1410, "total_steps": 2193, "loss": 0.4205, "learning_rate": 3.40804592430354e-06, "epoch": 1.9288645690834474, "percentage": 64.3, "elapsed_time": "3:56:08", "remaining_time": "2:11:07"}
{"current_steps": 1420, "total_steps": 2193, "loss": 0.4295, "learning_rate": 3.3327794882774785e-06, "epoch": 1.9425444596443229, "percentage": 64.75, "elapsed_time": "3:57:40", "remaining_time": "2:09:23"}
{"current_steps": 1430, "total_steps": 2193, "loss": 0.4104, "learning_rate": 3.2579357495221786e-06, "epoch": 1.9562243502051984, "percentage": 65.21, "elapsed_time": "3:59:15", "remaining_time": "2:07:39"}
{"current_steps": 1440, "total_steps": 2193, "loss": 0.4091, "learning_rate": 3.183533683478427e-06, "epoch": 1.9699042407660738, "percentage": 65.66, "elapsed_time": "4:00:56", "remaining_time": "2:05:59"}
{"current_steps": 1450, "total_steps": 2193, "loss": 0.43, "learning_rate": 3.1095921536079215e-06, "epoch": 1.9835841313269493, "percentage": 66.12, "elapsed_time": "4:02:24", "remaining_time": "2:04:12"}
{"current_steps": 1460, "total_steps": 2193, "loss": 0.4146, "learning_rate": 3.0361299066107225e-06, "epoch": 1.9972640218878248, "percentage": 66.58, "elapsed_time": "4:03:51", "remaining_time": "2:02:25"}
{"current_steps": 1470, "total_steps": 2193, "loss": 0.3057, "learning_rate": 2.9631655676723358e-06, "epoch": 2.0109439124487003, "percentage": 67.03, "elapsed_time": "4:05:26", "remaining_time": "2:00:43"}
{"current_steps": 1480, "total_steps": 2193, "loss": 0.2671, "learning_rate": 2.890717635741589e-06, "epoch": 2.024623803009576, "percentage": 67.49, "elapsed_time": "4:06:52", "remaining_time": "1:58:56"}
{"current_steps": 1490, "total_steps": 2193, "loss": 0.2676, "learning_rate": 2.81880447884052e-06, "epoch": 2.0383036935704513, "percentage": 67.94, "elapsed_time": "4:08:26", "remaining_time": "1:57:12"}
{"current_steps": 1500, "total_steps": 2193, "loss": 0.2593, "learning_rate": 2.7474443294074537e-06, "epoch": 2.0519835841313268, "percentage": 68.4, "elapsed_time": "4:09:58", "remaining_time": "1:55:29"}
{"current_steps": 1510, "total_steps": 2193, "loss": 0.2703, "learning_rate": 2.6766552796744583e-06, "epoch": 2.0656634746922027, "percentage": 68.86, "elapsed_time": "4:11:21", "remaining_time": "1:53:41"}
{"current_steps": 1520, "total_steps": 2193, "loss": 0.2708, "learning_rate": 2.606455277080346e-06, "epoch": 2.079343365253078, "percentage": 69.31, "elapsed_time": "4:12:54", "remaining_time": "1:51:58"}
{"current_steps": 1530, "total_steps": 2193, "loss": 0.2664, "learning_rate": 2.536862119720387e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "4:14:27", "remaining_time": "1:50:15"}
{"current_steps": 1540, "total_steps": 2193, "loss": 0.2673, "learning_rate": 2.467893451833884e-06, "epoch": 2.106703146374829, "percentage": 70.22, "elapsed_time": "4:16:09", "remaining_time": "1:48:37"}
{"current_steps": 1550, "total_steps": 2193, "loss": 0.2622, "learning_rate": 2.3995667593307563e-06, "epoch": 2.1203830369357046, "percentage": 70.68, "elapsed_time": "4:17:37", "remaining_time": "1:46:52"}
{"current_steps": 1560, "total_steps": 2193, "loss": 0.2695, "learning_rate": 2.331899365358266e-06, "epoch": 2.13406292749658, "percentage": 71.14, "elapsed_time": "4:19:10", "remaining_time": "1:45:09"}
{"current_steps": 1570, "total_steps": 2193, "loss": 0.2593, "learning_rate": 2.2649084259090058e-06, "epoch": 2.1477428180574556, "percentage": 71.59, "elapsed_time": "4:20:40", "remaining_time": "1:43:26"}
{"current_steps": 1580, "total_steps": 2193, "loss": 0.2708, "learning_rate": 2.1986109254712745e-06, "epoch": 2.161422708618331, "percentage": 72.05, "elapsed_time": "4:22:10", "remaining_time": "1:41:43"}
{"current_steps": 1590, "total_steps": 2193, "loss": 0.2697, "learning_rate": 2.133023672722923e-06, "epoch": 2.1751025991792066, "percentage": 72.5, "elapsed_time": "4:23:37", "remaining_time": "1:39:58"}
{"current_steps": 1600, "total_steps": 2193, "loss": 0.2528, "learning_rate": 2.0681632962697955e-06, "epoch": 2.188782489740082, "percentage": 72.96, "elapsed_time": "4:25:10", "remaining_time": "1:38:16"}
{"current_steps": 1600, "total_steps": 2193, "eval_loss": 0.6378765106201172, "epoch": 2.188782489740082, "percentage": 72.96, "elapsed_time": "4:28:01", "remaining_time": "1:39:20"}
{"current_steps": 1610, "total_steps": 2193, "loss": 0.2719, "learning_rate": 2.0040462404297873e-06, "epoch": 2.2024623803009575, "percentage": 73.42, "elapsed_time": "4:29:28", "remaining_time": "1:37:34"}
{"current_steps": 1620, "total_steps": 2193, "loss": 0.2659, "learning_rate": 1.9406887610636716e-06, "epoch": 2.216142270861833, "percentage": 73.87, "elapsed_time": "4:30:55", "remaining_time": "1:35:49"}
{"current_steps": 1630, "total_steps": 2193, "loss": 0.2677, "learning_rate": 1.8781069214536711e-06, "epoch": 2.2298221614227085, "percentage": 74.33, "elapsed_time": "4:32:27", "remaining_time": "1:34:06"}
{"current_steps": 1640, "total_steps": 2193, "loss": 0.2662, "learning_rate": 1.8163165882308776e-06, "epoch": 2.243502051983584, "percentage": 74.78, "elapsed_time": "4:33:56", "remaining_time": "1:32:22"}
{"current_steps": 1650, "total_steps": 2193, "loss": 0.2648, "learning_rate": 1.7553334273525107e-06, "epoch": 2.2571819425444595, "percentage": 75.24, "elapsed_time": "4:35:33", "remaining_time": "1:30:41"}
{"current_steps": 1660, "total_steps": 2193, "loss": 0.2659, "learning_rate": 1.6951729001300626e-06, "epoch": 2.270861833105335, "percentage": 75.7, "elapsed_time": "4:36:58", "remaining_time": "1:28:55"}
{"current_steps": 1670, "total_steps": 2193, "loss": 0.2638, "learning_rate": 1.6358502593093417e-06, "epoch": 2.2845417236662104, "percentage": 76.15, "elapsed_time": "4:38:26", "remaining_time": "1:27:12"}
{"current_steps": 1680, "total_steps": 2193, "loss": 0.2647, "learning_rate": 1.5773805452033664e-06, "epoch": 2.2982216142270864, "percentage": 76.61, "elapsed_time": "4:39:45", "remaining_time": "1:25:25"}
{"current_steps": 1690, "total_steps": 2193, "loss": 0.2611, "learning_rate": 1.5197785818791395e-06, "epoch": 2.311901504787962, "percentage": 77.06, "elapsed_time": "4:41:20", "remaining_time": "1:23:44"}
{"current_steps": 1700, "total_steps": 2193, "loss": 0.2597, "learning_rate": 1.463058973399241e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "4:42:54", "remaining_time": "1:22:02"}
{"current_steps": 1710, "total_steps": 2193, "loss": 0.2664, "learning_rate": 1.4072361001191997e-06, "epoch": 2.339261285909713, "percentage": 77.98, "elapsed_time": "4:44:25", "remaining_time": "1:20:20"}
{"current_steps": 1720, "total_steps": 2193, "loss": 0.2579, "learning_rate": 1.3523241150415822e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "4:46:02", "remaining_time": "1:18:39"}
{"current_steps": 1730, "total_steps": 2193, "loss": 0.2627, "learning_rate": 1.298336940227724e-06, "epoch": 2.366621067031464, "percentage": 78.89, "elapsed_time": "4:47:32", "remaining_time": "1:16:57"}
{"current_steps": 1740, "total_steps": 2193, "loss": 0.2629, "learning_rate": 1.2452882632680125e-06, "epoch": 2.3803009575923393, "percentage": 79.34, "elapsed_time": "4:49:04", "remaining_time": "1:15:15"}
{"current_steps": 1750, "total_steps": 2193, "loss": 0.2579, "learning_rate": 1.1931915338116157e-06, "epoch": 2.3939808481532148, "percentage": 79.8, "elapsed_time": "4:50:42", "remaining_time": "1:13:35"}
{"current_steps": 1760, "total_steps": 2193, "loss": 0.2655, "learning_rate": 1.1420599601565375e-06, "epoch": 2.4076607387140903, "percentage": 80.26, "elapsed_time": "4:52:10", "remaining_time": "1:11:52"}
{"current_steps": 1770, "total_steps": 2193, "loss": 0.2614, "learning_rate": 1.0919065059008626e-06, "epoch": 2.4213406292749657, "percentage": 80.71, "elapsed_time": "4:53:46", "remaining_time": "1:10:12"}
{"current_steps": 1780, "total_steps": 2193, "loss": 0.2633, "learning_rate": 1.042743886656043e-06, "epoch": 2.4350205198358412, "percentage": 81.17, "elapsed_time": "4:55:21", "remaining_time": "1:08:31"}
{"current_steps": 1790, "total_steps": 2193, "loss": 0.2626, "learning_rate": 9.94584566823062e-07, "epoch": 2.4487004103967167, "percentage": 81.62, "elapsed_time": "4:56:51", "remaining_time": "1:06:50"}
{"current_steps": 1800, "total_steps": 2193, "loss": 0.2648, "learning_rate": 9.474407564322685e-07, "epoch": 2.462380300957592, "percentage": 82.08, "elapsed_time": "4:58:23", "remaining_time": "1:05:08"}
{"current_steps": 1800, "total_steps": 2193, "eval_loss": 0.6390905976295471, "epoch": 2.462380300957592, "percentage": 82.08, "elapsed_time": "5:01:10", "remaining_time": "1:05:45"}
{"current_steps": 1810, "total_steps": 2193, "loss": 0.2649, "learning_rate": 9.01324408047734e-07, "epoch": 2.4760601915184677, "percentage": 82.54, "elapsed_time": "5:02:42", "remaining_time": "1:04:03"}
{"current_steps": 1820, "total_steps": 2193, "loss": 0.2598, "learning_rate": 8.562472137368638e-07, "epoch": 2.4897400820793436, "percentage": 82.99, "elapsed_time": "5:04:10", "remaining_time": "1:02:20"}
{"current_steps": 1830, "total_steps": 2193, "loss": 0.2627, "learning_rate": 8.122206021060552e-07, "epoch": 2.503419972640219, "percentage": 83.45, "elapsed_time": "5:05:41", "remaining_time": "1:00:38"}
{"current_steps": 1840, "total_steps": 2193, "loss": 0.2554, "learning_rate": 7.692557354031633e-07, "epoch": 2.5170998632010946, "percentage": 83.9, "elapsed_time": "5:07:10", "remaining_time": "0:58:55"}
{"current_steps": 1850, "total_steps": 2193, "loss": 0.2595, "learning_rate": 7.273635066874796e-07, "epoch": 2.53077975376197, "percentage": 84.36, "elapsed_time": "5:08:46", "remaining_time": "0:57:14"}
{"current_steps": 1860, "total_steps": 2193, "loss": 0.2562, "learning_rate": 6.86554537067986e-07, "epoch": 2.5444596443228455, "percentage": 84.82, "elapsed_time": "5:10:10", "remaining_time": "0:55:31"}
{"current_steps": 1870, "total_steps": 2193, "loss": 0.2589, "learning_rate": 6.46839173010525e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "5:11:32", "remaining_time": "0:53:48"}
{"current_steps": 1880, "total_steps": 2193, "loss": 0.2565, "learning_rate": 6.08227483714629e-07, "epoch": 2.5718194254445965, "percentage": 85.73, "elapsed_time": "5:12:56", "remaining_time": "0:52:06"}
{"current_steps": 1890, "total_steps": 2193, "loss": 0.2646, "learning_rate": 5.707292585606277e-07, "epoch": 2.585499316005472, "percentage": 86.18, "elapsed_time": "5:14:25", "remaining_time": "0:50:24"}
{"current_steps": 1900, "total_steps": 2193, "loss": 0.2571, "learning_rate": 5.343540046277113e-07, "epoch": 2.5991792065663475, "percentage": 86.64, "elapsed_time": "5:15:50", "remaining_time": "0:48:42"}
{"current_steps": 1910, "total_steps": 2193, "loss": 0.2605, "learning_rate": 4.991109442835578e-07, "epoch": 2.612859097127223, "percentage": 87.1, "elapsed_time": "5:17:14", "remaining_time": "0:47:00"}
{"current_steps": 1920, "total_steps": 2193, "loss": 0.2621, "learning_rate": 4.6500901284615094e-07, "epoch": 2.6265389876880985, "percentage": 87.55, "elapsed_time": "5:18:44", "remaining_time": "0:45:19"}
{"current_steps": 1930, "total_steps": 2193, "loss": 0.2646, "learning_rate": 4.320568563183708e-07, "epoch": 2.640218878248974, "percentage": 88.01, "elapsed_time": "5:20:17", "remaining_time": "0:43:38"}
{"current_steps": 1940, "total_steps": 2193, "loss": 0.2653, "learning_rate": 4.0026282919593815e-07, "epoch": 2.6538987688098494, "percentage": 88.46, "elapsed_time": "5:21:57", "remaining_time": "0:41:59"}
{"current_steps": 1950, "total_steps": 2193, "loss": 0.2675, "learning_rate": 3.6963499234926314e-07, "epoch": 2.667578659370725, "percentage": 88.92, "elapsed_time": "5:23:33", "remaining_time": "0:40:19"}
{"current_steps": 1960, "total_steps": 2193, "loss": 0.2805, "learning_rate": 3.401811109797404e-07, "epoch": 2.6812585499316004, "percentage": 89.38, "elapsed_time": "5:25:05", "remaining_time": "0:38:38"}
{"current_steps": 1970, "total_steps": 2193, "loss": 0.2594, "learning_rate": 3.1190865265100954e-07, "epoch": 2.694938440492476, "percentage": 89.83, "elapsed_time": "5:26:46", "remaining_time": "0:36:59"}
{"current_steps": 1980, "total_steps": 2193, "loss": 0.2662, "learning_rate": 2.8482478539566595e-07, "epoch": 2.7086183310533514, "percentage": 90.29, "elapsed_time": "5:28:21", "remaining_time": "0:35:19"}
{"current_steps": 1990, "total_steps": 2193, "loss": 0.2688, "learning_rate": 2.58936375897923e-07, "epoch": 2.722298221614227, "percentage": 90.74, "elapsed_time": "5:29:51", "remaining_time": "0:33:38"}
{"current_steps": 2000, "total_steps": 2193, "loss": 0.2586, "learning_rate": 2.342499877526755e-07, "epoch": 2.7359781121751023, "percentage": 91.2, "elapsed_time": "5:31:26", "remaining_time": "0:31:59"}
{"current_steps": 2000, "total_steps": 2193, "eval_loss": 0.6391583681106567, "epoch": 2.7359781121751023, "percentage": 91.2, "elapsed_time": "5:34:14", "remaining_time": "0:32:15"}
{"current_steps": 2010, "total_steps": 2193, "loss": 0.2616, "learning_rate": 2.1077187980140467e-07, "epoch": 2.7496580027359783, "percentage": 91.66, "elapsed_time": "5:37:07", "remaining_time": "0:30:41"}
{"current_steps": 2020, "total_steps": 2193, "loss": 0.2591, "learning_rate": 1.8850800454534358e-07, "epoch": 2.7633378932968538, "percentage": 92.11, "elapsed_time": "5:38:40", "remaining_time": "0:29:00"}
{"current_steps": 2030, "total_steps": 2193, "loss": 0.2608, "learning_rate": 1.6746400663631923e-07, "epoch": 2.7770177838577292, "percentage": 92.57, "elapsed_time": "5:40:23", "remaining_time": "0:27:19"}
{"current_steps": 2040, "total_steps": 2193, "loss": 0.2625, "learning_rate": 1.4764522144563865e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "5:41:46", "remaining_time": "0:25:37"}
{"current_steps": 2050, "total_steps": 2193, "loss": 0.259, "learning_rate": 1.2905667371139298e-07, "epoch": 2.80437756497948, "percentage": 93.48, "elapsed_time": "5:43:16", "remaining_time": "0:23:56"}
{"current_steps": 2060, "total_steps": 2193, "loss": 0.2613, "learning_rate": 1.117030762645116e-07, "epoch": 2.8180574555403557, "percentage": 93.94, "elapsed_time": "5:44:56", "remaining_time": "0:22:16"}
{"current_steps": 2070, "total_steps": 2193, "loss": 0.2607, "learning_rate": 9.558882883390075e-08, "epoch": 2.831737346101231, "percentage": 94.39, "elapsed_time": "5:46:33", "remaining_time": "0:20:35"}
{"current_steps": 2080, "total_steps": 2193, "loss": 0.2575, "learning_rate": 8.071801693096237e-08, "epoch": 2.8454172366621067, "percentage": 94.85, "elapsed_time": "5:48:02", "remaining_time": "0:18:54"}
{"current_steps": 2090, "total_steps": 2193, "loss": 0.2601, "learning_rate": 6.70944108137761e-08, "epoch": 2.859097127222982, "percentage": 95.3, "elapsed_time": "5:49:26", "remaining_time": "0:17:13"}
{"current_steps": 2100, "total_steps": 2193, "loss": 0.2565, "learning_rate": 5.472146453121163e-08, "epoch": 2.8727770177838576, "percentage": 95.76, "elapsed_time": "5:51:02", "remaining_time": "0:15:32"}
{"current_steps": 2110, "total_steps": 2193, "loss": 0.2726, "learning_rate": 4.360231504720813e-08, "epoch": 2.886456908344733, "percentage": 96.22, "elapsed_time": "5:52:36", "remaining_time": "0:13:52"}
{"current_steps": 2120, "total_steps": 2193, "loss": 0.2544, "learning_rate": 3.3739781445449316e-08, "epoch": 2.9001367989056086, "percentage": 96.67, "elapsed_time": "5:54:08", "remaining_time": "0:12:11"}
{"current_steps": 2130, "total_steps": 2193, "loss": 0.2587, "learning_rate": 2.513636421462573e-08, "epoch": 2.9138166894664845, "percentage": 97.13, "elapsed_time": "5:55:33", "remaining_time": "0:10:30"}
{"current_steps": 2140, "total_steps": 2193, "loss": 0.2622, "learning_rate": 1.779424461447965e-08, "epoch": 2.92749658002736, "percentage": 97.58, "elapsed_time": "5:57:05", "remaining_time": "0:08:50"}
{"current_steps": 2150, "total_steps": 2193, "loss": 0.261, "learning_rate": 1.1715284122779114e-08, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "5:58:34", "remaining_time": "0:07:10"}
{"current_steps": 2160, "total_steps": 2193, "loss": 0.2581, "learning_rate": 6.901023963369336e-09, "epoch": 2.954856361149111, "percentage": 98.5, "elapsed_time": "6:00:12", "remaining_time": "0:05:30"}
{"current_steps": 2170, "total_steps": 2193, "loss": 0.2577, "learning_rate": 3.3526847154219387e-09, "epoch": 2.9685362517099865, "percentage": 98.95, "elapsed_time": "6:01:44", "remaining_time": "0:03:50"}
{"current_steps": 2180, "total_steps": 2193, "loss": 0.2691, "learning_rate": 1.0711660039747219e-09, "epoch": 2.982216142270862, "percentage": 99.41, "elapsed_time": "6:03:14", "remaining_time": "0:02:09"}
{"current_steps": 2190, "total_steps": 2193, "loss": 0.2604, "learning_rate": 5.704627184577316e-11, "epoch": 2.9958960328317374, "percentage": 99.86, "elapsed_time": "6:04:44", "remaining_time": "0:00:29"}
{"current_steps": 2193, "total_steps": 2193, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:06:33", "remaining_time": "0:00:00"}