oh-dcft-v3.1-SN-405B-hacky-qwen / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 3
1992bde verified
{"current_steps": 10, "total_steps": 4023, "loss": 0.6314, "lr": 5e-06, "epoch": 0.007457121551081283, "percentage": 0.25, "elapsed_time": "0:02:16", "remaining_time": "15:14:27"}
{"current_steps": 20, "total_steps": 4023, "loss": 0.5957, "lr": 5e-06, "epoch": 0.014914243102162566, "percentage": 0.5, "elapsed_time": "0:04:29", "remaining_time": "14:57:44"}
{"current_steps": 30, "total_steps": 4023, "loss": 0.5858, "lr": 5e-06, "epoch": 0.02237136465324385, "percentage": 0.75, "elapsed_time": "0:06:41", "remaining_time": "14:50:55"}
{"current_steps": 40, "total_steps": 4023, "loss": 0.6083, "lr": 5e-06, "epoch": 0.02982848620432513, "percentage": 0.99, "elapsed_time": "0:08:54", "remaining_time": "14:46:19"}
{"current_steps": 50, "total_steps": 4023, "loss": 0.5833, "lr": 5e-06, "epoch": 0.037285607755406416, "percentage": 1.24, "elapsed_time": "0:11:06", "remaining_time": "14:42:40"}
{"current_steps": 60, "total_steps": 4023, "loss": 0.5615, "lr": 5e-06, "epoch": 0.0447427293064877, "percentage": 1.49, "elapsed_time": "0:13:18", "remaining_time": "14:39:30"}
{"current_steps": 70, "total_steps": 4023, "loss": 0.5599, "lr": 5e-06, "epoch": 0.05219985085756898, "percentage": 1.74, "elapsed_time": "0:15:31", "remaining_time": "14:36:26"}
{"current_steps": 80, "total_steps": 4023, "loss": 0.5738, "lr": 5e-06, "epoch": 0.05965697240865026, "percentage": 1.99, "elapsed_time": "0:17:43", "remaining_time": "14:33:31"}
{"current_steps": 90, "total_steps": 4023, "loss": 0.5513, "lr": 5e-06, "epoch": 0.06711409395973154, "percentage": 2.24, "elapsed_time": "0:19:55", "remaining_time": "14:30:50"}
{"current_steps": 100, "total_steps": 4023, "loss": 0.5723, "lr": 5e-06, "epoch": 0.07457121551081283, "percentage": 2.49, "elapsed_time": "0:22:08", "remaining_time": "14:28:19"}
{"current_steps": 110, "total_steps": 4023, "loss": 0.5666, "lr": 5e-06, "epoch": 0.08202833706189411, "percentage": 2.73, "elapsed_time": "0:24:20", "remaining_time": "14:25:56"}
{"current_steps": 120, "total_steps": 4023, "loss": 0.5475, "lr": 5e-06, "epoch": 0.0894854586129754, "percentage": 2.98, "elapsed_time": "0:26:33", "remaining_time": "14:23:33"}
{"current_steps": 130, "total_steps": 4023, "loss": 0.5532, "lr": 5e-06, "epoch": 0.09694258016405667, "percentage": 3.23, "elapsed_time": "0:28:45", "remaining_time": "14:21:03"}
{"current_steps": 140, "total_steps": 4023, "loss": 0.5561, "lr": 5e-06, "epoch": 0.10439970171513796, "percentage": 3.48, "elapsed_time": "0:30:57", "remaining_time": "14:18:37"}
{"current_steps": 150, "total_steps": 4023, "loss": 0.5542, "lr": 5e-06, "epoch": 0.11185682326621924, "percentage": 3.73, "elapsed_time": "0:33:09", "remaining_time": "14:16:12"}
{"current_steps": 160, "total_steps": 4023, "loss": 0.55, "lr": 5e-06, "epoch": 0.11931394481730052, "percentage": 3.98, "elapsed_time": "0:35:21", "remaining_time": "14:13:47"}
{"current_steps": 170, "total_steps": 4023, "loss": 0.5577, "lr": 5e-06, "epoch": 0.1267710663683818, "percentage": 4.23, "elapsed_time": "0:37:33", "remaining_time": "14:11:24"}
{"current_steps": 180, "total_steps": 4023, "loss": 0.5579, "lr": 5e-06, "epoch": 0.1342281879194631, "percentage": 4.47, "elapsed_time": "0:39:46", "remaining_time": "14:09:03"}
{"current_steps": 190, "total_steps": 4023, "loss": 0.5691, "lr": 5e-06, "epoch": 0.14168530947054436, "percentage": 4.72, "elapsed_time": "0:41:58", "remaining_time": "14:06:44"}
{"current_steps": 200, "total_steps": 4023, "loss": 0.5441, "lr": 5e-06, "epoch": 0.14914243102162567, "percentage": 4.97, "elapsed_time": "0:44:10", "remaining_time": "14:04:24"}
{"current_steps": 210, "total_steps": 4023, "loss": 0.5438, "lr": 5e-06, "epoch": 0.15659955257270694, "percentage": 5.22, "elapsed_time": "0:46:22", "remaining_time": "14:02:05"}
{"current_steps": 220, "total_steps": 4023, "loss": 0.5552, "lr": 5e-06, "epoch": 0.16405667412378822, "percentage": 5.47, "elapsed_time": "0:48:34", "remaining_time": "13:59:48"}
{"current_steps": 230, "total_steps": 4023, "loss": 0.57, "lr": 5e-06, "epoch": 0.1715137956748695, "percentage": 5.72, "elapsed_time": "0:50:47", "remaining_time": "13:57:30"}
{"current_steps": 240, "total_steps": 4023, "loss": 0.5588, "lr": 5e-06, "epoch": 0.1789709172259508, "percentage": 5.97, "elapsed_time": "0:52:59", "remaining_time": "13:55:13"}
{"current_steps": 250, "total_steps": 4023, "loss": 0.5435, "lr": 5e-06, "epoch": 0.18642803877703207, "percentage": 6.21, "elapsed_time": "0:55:11", "remaining_time": "13:52:58"}
{"current_steps": 260, "total_steps": 4023, "loss": 0.5371, "lr": 5e-06, "epoch": 0.19388516032811334, "percentage": 6.46, "elapsed_time": "0:57:23", "remaining_time": "13:50:42"}
{"current_steps": 270, "total_steps": 4023, "loss": 0.554, "lr": 5e-06, "epoch": 0.20134228187919462, "percentage": 6.71, "elapsed_time": "0:59:36", "remaining_time": "13:48:26"}
{"current_steps": 280, "total_steps": 4023, "loss": 0.5648, "lr": 5e-06, "epoch": 0.20879940343027592, "percentage": 6.96, "elapsed_time": "1:01:48", "remaining_time": "13:46:10"}
{"current_steps": 290, "total_steps": 4023, "loss": 0.5626, "lr": 5e-06, "epoch": 0.2162565249813572, "percentage": 7.21, "elapsed_time": "1:04:00", "remaining_time": "13:43:55"}
{"current_steps": 300, "total_steps": 4023, "loss": 0.5495, "lr": 5e-06, "epoch": 0.22371364653243847, "percentage": 7.46, "elapsed_time": "1:06:12", "remaining_time": "13:41:39"}
{"current_steps": 310, "total_steps": 4023, "loss": 0.5492, "lr": 5e-06, "epoch": 0.23117076808351977, "percentage": 7.71, "elapsed_time": "1:08:24", "remaining_time": "13:39:23"}
{"current_steps": 320, "total_steps": 4023, "loss": 0.5382, "lr": 5e-06, "epoch": 0.23862788963460105, "percentage": 7.95, "elapsed_time": "1:10:36", "remaining_time": "13:37:08"}
{"current_steps": 330, "total_steps": 4023, "loss": 0.5626, "lr": 5e-06, "epoch": 0.24608501118568232, "percentage": 8.2, "elapsed_time": "1:12:48", "remaining_time": "13:34:51"}
{"current_steps": 340, "total_steps": 4023, "loss": 0.5537, "lr": 5e-06, "epoch": 0.2535421327367636, "percentage": 8.45, "elapsed_time": "1:15:00", "remaining_time": "13:32:36"}
{"current_steps": 350, "total_steps": 4023, "loss": 0.5577, "lr": 5e-06, "epoch": 0.2609992542878449, "percentage": 8.7, "elapsed_time": "1:17:13", "remaining_time": "13:30:21"}
{"current_steps": 360, "total_steps": 4023, "loss": 0.5514, "lr": 5e-06, "epoch": 0.2684563758389262, "percentage": 8.95, "elapsed_time": "1:19:25", "remaining_time": "13:28:06"}
{"current_steps": 370, "total_steps": 4023, "loss": 0.5415, "lr": 5e-06, "epoch": 0.2759134973900075, "percentage": 9.2, "elapsed_time": "1:21:37", "remaining_time": "13:25:52"}
{"current_steps": 380, "total_steps": 4023, "loss": 0.5641, "lr": 5e-06, "epoch": 0.2833706189410887, "percentage": 9.45, "elapsed_time": "1:23:49", "remaining_time": "13:23:39"}
{"current_steps": 390, "total_steps": 4023, "loss": 0.5481, "lr": 5e-06, "epoch": 0.29082774049217003, "percentage": 9.69, "elapsed_time": "1:26:01", "remaining_time": "13:21:24"}
{"current_steps": 400, "total_steps": 4023, "loss": 0.5513, "lr": 5e-06, "epoch": 0.29828486204325133, "percentage": 9.94, "elapsed_time": "1:28:14", "remaining_time": "13:19:10"}
{"current_steps": 410, "total_steps": 4023, "loss": 0.5638, "lr": 5e-06, "epoch": 0.3057419835943326, "percentage": 10.19, "elapsed_time": "1:30:26", "remaining_time": "13:16:56"}
{"current_steps": 420, "total_steps": 4023, "loss": 0.5492, "lr": 5e-06, "epoch": 0.3131991051454139, "percentage": 10.44, "elapsed_time": "1:32:38", "remaining_time": "13:14:43"}
{"current_steps": 430, "total_steps": 4023, "loss": 0.5607, "lr": 5e-06, "epoch": 0.32065622669649513, "percentage": 10.69, "elapsed_time": "1:34:50", "remaining_time": "13:12:30"}
{"current_steps": 440, "total_steps": 4023, "loss": 0.5645, "lr": 5e-06, "epoch": 0.32811334824757643, "percentage": 10.94, "elapsed_time": "1:37:02", "remaining_time": "13:10:16"}
{"current_steps": 450, "total_steps": 4023, "loss": 0.5549, "lr": 5e-06, "epoch": 0.33557046979865773, "percentage": 11.19, "elapsed_time": "1:39:15", "remaining_time": "13:08:03"}
{"current_steps": 460, "total_steps": 4023, "loss": 0.5548, "lr": 5e-06, "epoch": 0.343027591349739, "percentage": 11.43, "elapsed_time": "1:41:27", "remaining_time": "13:05:51"}
{"current_steps": 470, "total_steps": 4023, "loss": 0.5583, "lr": 5e-06, "epoch": 0.3504847129008203, "percentage": 11.68, "elapsed_time": "1:43:39", "remaining_time": "13:03:38"}
{"current_steps": 480, "total_steps": 4023, "loss": 0.545, "lr": 5e-06, "epoch": 0.3579418344519016, "percentage": 11.93, "elapsed_time": "1:45:52", "remaining_time": "13:01:26"}
{"current_steps": 490, "total_steps": 4023, "loss": 0.5395, "lr": 5e-06, "epoch": 0.36539895600298283, "percentage": 12.18, "elapsed_time": "1:48:04", "remaining_time": "12:59:14"}
{"current_steps": 500, "total_steps": 4023, "loss": 0.5456, "lr": 5e-06, "epoch": 0.37285607755406414, "percentage": 12.43, "elapsed_time": "1:50:16", "remaining_time": "12:57:03"}
{"current_steps": 510, "total_steps": 4023, "loss": 0.5367, "lr": 5e-06, "epoch": 0.38031319910514544, "percentage": 12.68, "elapsed_time": "1:52:29", "remaining_time": "12:54:52"}
{"current_steps": 520, "total_steps": 4023, "loss": 0.5716, "lr": 5e-06, "epoch": 0.3877703206562267, "percentage": 12.93, "elapsed_time": "1:54:42", "remaining_time": "12:52:40"}
{"current_steps": 530, "total_steps": 4023, "loss": 0.5545, "lr": 5e-06, "epoch": 0.395227442207308, "percentage": 13.17, "elapsed_time": "1:56:54", "remaining_time": "12:50:29"}
{"current_steps": 540, "total_steps": 4023, "loss": 0.5646, "lr": 5e-06, "epoch": 0.40268456375838924, "percentage": 13.42, "elapsed_time": "1:59:06", "remaining_time": "12:48:17"}
{"current_steps": 550, "total_steps": 4023, "loss": 0.559, "lr": 5e-06, "epoch": 0.41014168530947054, "percentage": 13.67, "elapsed_time": "2:01:19", "remaining_time": "12:46:05"}
{"current_steps": 560, "total_steps": 4023, "loss": 0.5398, "lr": 5e-06, "epoch": 0.41759880686055184, "percentage": 13.92, "elapsed_time": "2:03:31", "remaining_time": "12:43:54"}
{"current_steps": 570, "total_steps": 4023, "loss": 0.5506, "lr": 5e-06, "epoch": 0.4250559284116331, "percentage": 14.17, "elapsed_time": "2:05:44", "remaining_time": "12:41:43"}
{"current_steps": 580, "total_steps": 4023, "loss": 0.5624, "lr": 5e-06, "epoch": 0.4325130499627144, "percentage": 14.42, "elapsed_time": "2:07:56", "remaining_time": "12:39:31"}
{"current_steps": 590, "total_steps": 4023, "loss": 0.5493, "lr": 5e-06, "epoch": 0.4399701715137957, "percentage": 14.67, "elapsed_time": "2:10:09", "remaining_time": "12:37:20"}
{"current_steps": 600, "total_steps": 4023, "loss": 0.5495, "lr": 5e-06, "epoch": 0.44742729306487694, "percentage": 14.91, "elapsed_time": "2:12:21", "remaining_time": "12:35:08"}
{"current_steps": 610, "total_steps": 4023, "loss": 0.5422, "lr": 5e-06, "epoch": 0.45488441461595824, "percentage": 15.16, "elapsed_time": "2:14:34", "remaining_time": "12:32:55"}
{"current_steps": 620, "total_steps": 4023, "loss": 0.5575, "lr": 5e-06, "epoch": 0.46234153616703955, "percentage": 15.41, "elapsed_time": "2:16:46", "remaining_time": "12:30:43"}
{"current_steps": 630, "total_steps": 4023, "loss": 0.552, "lr": 5e-06, "epoch": 0.4697986577181208, "percentage": 15.66, "elapsed_time": "2:18:58", "remaining_time": "12:28:30"}
{"current_steps": 640, "total_steps": 4023, "loss": 0.5574, "lr": 5e-06, "epoch": 0.4772557792692021, "percentage": 15.91, "elapsed_time": "2:21:11", "remaining_time": "12:26:17"}
{"current_steps": 650, "total_steps": 4023, "loss": 0.5515, "lr": 5e-06, "epoch": 0.48471290082028334, "percentage": 16.16, "elapsed_time": "2:23:23", "remaining_time": "12:24:05"}
{"current_steps": 660, "total_steps": 4023, "loss": 0.5574, "lr": 5e-06, "epoch": 0.49217002237136465, "percentage": 16.41, "elapsed_time": "2:25:36", "remaining_time": "12:21:53"}
{"current_steps": 670, "total_steps": 4023, "loss": 0.5585, "lr": 5e-06, "epoch": 0.49962714392244595, "percentage": 16.65, "elapsed_time": "2:27:48", "remaining_time": "12:19:41"}
{"current_steps": 680, "total_steps": 4023, "loss": 0.556, "lr": 5e-06, "epoch": 0.5070842654735273, "percentage": 16.9, "elapsed_time": "2:30:00", "remaining_time": "12:17:28"}
{"current_steps": 690, "total_steps": 4023, "loss": 0.5437, "lr": 5e-06, "epoch": 0.5145413870246085, "percentage": 17.15, "elapsed_time": "2:32:12", "remaining_time": "12:15:15"}
{"current_steps": 700, "total_steps": 4023, "loss": 0.5568, "lr": 5e-06, "epoch": 0.5219985085756897, "percentage": 17.4, "elapsed_time": "2:34:25", "remaining_time": "12:13:02"}
{"current_steps": 710, "total_steps": 4023, "loss": 0.5431, "lr": 5e-06, "epoch": 0.5294556301267711, "percentage": 17.65, "elapsed_time": "2:36:37", "remaining_time": "12:10:50"}
{"current_steps": 720, "total_steps": 4023, "loss": 0.5552, "lr": 5e-06, "epoch": 0.5369127516778524, "percentage": 17.9, "elapsed_time": "2:38:49", "remaining_time": "12:08:37"}
{"current_steps": 730, "total_steps": 4023, "loss": 0.554, "lr": 5e-06, "epoch": 0.5443698732289336, "percentage": 18.15, "elapsed_time": "2:41:01", "remaining_time": "12:06:24"}
{"current_steps": 740, "total_steps": 4023, "loss": 0.5495, "lr": 5e-06, "epoch": 0.551826994780015, "percentage": 18.39, "elapsed_time": "2:43:14", "remaining_time": "12:04:12"}
{"current_steps": 750, "total_steps": 4023, "loss": 0.5561, "lr": 5e-06, "epoch": 0.5592841163310962, "percentage": 18.64, "elapsed_time": "2:45:26", "remaining_time": "12:01:59"}
{"current_steps": 760, "total_steps": 4023, "loss": 0.5532, "lr": 5e-06, "epoch": 0.5667412378821775, "percentage": 18.89, "elapsed_time": "2:47:38", "remaining_time": "11:59:46"}
{"current_steps": 770, "total_steps": 4023, "loss": 0.5567, "lr": 5e-06, "epoch": 0.5741983594332588, "percentage": 19.14, "elapsed_time": "2:49:51", "remaining_time": "11:57:34"}
{"current_steps": 780, "total_steps": 4023, "loss": 0.5411, "lr": 5e-06, "epoch": 0.5816554809843401, "percentage": 19.39, "elapsed_time": "2:52:03", "remaining_time": "11:55:21"}
{"current_steps": 790, "total_steps": 4023, "loss": 0.5598, "lr": 5e-06, "epoch": 0.5891126025354213, "percentage": 19.64, "elapsed_time": "2:54:15", "remaining_time": "11:53:08"}
{"current_steps": 800, "total_steps": 4023, "loss": 0.5505, "lr": 5e-06, "epoch": 0.5965697240865027, "percentage": 19.89, "elapsed_time": "2:56:27", "remaining_time": "11:50:54"}
{"current_steps": 810, "total_steps": 4023, "loss": 0.5301, "lr": 5e-06, "epoch": 0.6040268456375839, "percentage": 20.13, "elapsed_time": "2:58:39", "remaining_time": "11:48:41"}
{"current_steps": 820, "total_steps": 4023, "loss": 0.5616, "lr": 5e-06, "epoch": 0.6114839671886652, "percentage": 20.38, "elapsed_time": "3:00:52", "remaining_time": "11:46:28"}
{"current_steps": 830, "total_steps": 4023, "loss": 0.5444, "lr": 5e-06, "epoch": 0.6189410887397464, "percentage": 20.63, "elapsed_time": "3:03:04", "remaining_time": "11:44:15"}
{"current_steps": 840, "total_steps": 4023, "loss": 0.5596, "lr": 5e-06, "epoch": 0.6263982102908278, "percentage": 20.88, "elapsed_time": "3:05:16", "remaining_time": "11:42:02"}
{"current_steps": 850, "total_steps": 4023, "loss": 0.5469, "lr": 5e-06, "epoch": 0.633855331841909, "percentage": 21.13, "elapsed_time": "3:07:28", "remaining_time": "11:39:49"}
{"current_steps": 860, "total_steps": 4023, "loss": 0.562, "lr": 5e-06, "epoch": 0.6413124533929903, "percentage": 21.38, "elapsed_time": "3:09:40", "remaining_time": "11:37:37"}
{"current_steps": 870, "total_steps": 4023, "loss": 0.5388, "lr": 5e-06, "epoch": 0.6487695749440716, "percentage": 21.63, "elapsed_time": "3:11:52", "remaining_time": "11:35:24"}
{"current_steps": 880, "total_steps": 4023, "loss": 0.5406, "lr": 5e-06, "epoch": 0.6562266964951529, "percentage": 21.87, "elapsed_time": "3:14:05", "remaining_time": "11:33:11"}
{"current_steps": 890, "total_steps": 4023, "loss": 0.5549, "lr": 5e-06, "epoch": 0.6636838180462341, "percentage": 22.12, "elapsed_time": "3:16:17", "remaining_time": "11:30:59"}
{"current_steps": 900, "total_steps": 4023, "loss": 0.5291, "lr": 5e-06, "epoch": 0.6711409395973155, "percentage": 22.37, "elapsed_time": "3:18:29", "remaining_time": "11:28:46"}
{"current_steps": 910, "total_steps": 4023, "loss": 0.5523, "lr": 5e-06, "epoch": 0.6785980611483967, "percentage": 22.62, "elapsed_time": "3:20:41", "remaining_time": "11:26:34"}
{"current_steps": 920, "total_steps": 4023, "loss": 0.5448, "lr": 5e-06, "epoch": 0.686055182699478, "percentage": 22.87, "elapsed_time": "3:22:54", "remaining_time": "11:24:21"}
{"current_steps": 930, "total_steps": 4023, "loss": 0.5415, "lr": 5e-06, "epoch": 0.6935123042505593, "percentage": 23.12, "elapsed_time": "3:25:06", "remaining_time": "11:22:08"}
{"current_steps": 940, "total_steps": 4023, "loss": 0.5712, "lr": 5e-06, "epoch": 0.7009694258016406, "percentage": 23.37, "elapsed_time": "3:27:18", "remaining_time": "11:19:55"}
{"current_steps": 950, "total_steps": 4023, "loss": 0.5519, "lr": 5e-06, "epoch": 0.7084265473527218, "percentage": 23.61, "elapsed_time": "3:29:30", "remaining_time": "11:17:43"}
{"current_steps": 960, "total_steps": 4023, "loss": 0.5551, "lr": 5e-06, "epoch": 0.7158836689038032, "percentage": 23.86, "elapsed_time": "3:31:43", "remaining_time": "11:15:30"}
{"current_steps": 970, "total_steps": 4023, "loss": 0.5561, "lr": 5e-06, "epoch": 0.7233407904548844, "percentage": 24.11, "elapsed_time": "3:33:55", "remaining_time": "11:13:17"}
{"current_steps": 980, "total_steps": 4023, "loss": 0.553, "lr": 5e-06, "epoch": 0.7307979120059657, "percentage": 24.36, "elapsed_time": "3:36:07", "remaining_time": "11:11:04"}
{"current_steps": 990, "total_steps": 4023, "loss": 0.5403, "lr": 5e-06, "epoch": 0.738255033557047, "percentage": 24.61, "elapsed_time": "3:38:19", "remaining_time": "11:08:52"}
{"current_steps": 1000, "total_steps": 4023, "loss": 0.548, "lr": 5e-06, "epoch": 0.7457121551081283, "percentage": 24.86, "elapsed_time": "3:40:31", "remaining_time": "11:06:39"}
{"current_steps": 1010, "total_steps": 4023, "loss": 0.5466, "lr": 5e-06, "epoch": 0.7531692766592095, "percentage": 25.11, "elapsed_time": "3:42:44", "remaining_time": "11:04:27"}
{"current_steps": 1020, "total_steps": 4023, "loss": 0.5519, "lr": 5e-06, "epoch": 0.7606263982102909, "percentage": 25.35, "elapsed_time": "3:44:56", "remaining_time": "11:02:14"}
{"current_steps": 1030, "total_steps": 4023, "loss": 0.5465, "lr": 5e-06, "epoch": 0.7680835197613721, "percentage": 25.6, "elapsed_time": "3:47:08", "remaining_time": "11:00:02"}
{"current_steps": 1040, "total_steps": 4023, "loss": 0.5478, "lr": 5e-06, "epoch": 0.7755406413124534, "percentage": 25.85, "elapsed_time": "3:49:21", "remaining_time": "10:57:51"}
{"current_steps": 1050, "total_steps": 4023, "loss": 0.5578, "lr": 5e-06, "epoch": 0.7829977628635347, "percentage": 26.1, "elapsed_time": "3:51:33", "remaining_time": "10:55:39"}
{"current_steps": 1060, "total_steps": 4023, "loss": 0.5486, "lr": 5e-06, "epoch": 0.790454884414616, "percentage": 26.35, "elapsed_time": "3:53:46", "remaining_time": "10:53:27"}
{"current_steps": 1070, "total_steps": 4023, "loss": 0.5453, "lr": 5e-06, "epoch": 0.7979120059656972, "percentage": 26.6, "elapsed_time": "3:55:58", "remaining_time": "10:51:15"}
{"current_steps": 1080, "total_steps": 4023, "loss": 0.54, "lr": 5e-06, "epoch": 0.8053691275167785, "percentage": 26.85, "elapsed_time": "3:58:11", "remaining_time": "10:49:04"}
{"current_steps": 1090, "total_steps": 4023, "loss": 0.5536, "lr": 5e-06, "epoch": 0.8128262490678598, "percentage": 27.09, "elapsed_time": "4:00:23", "remaining_time": "10:46:52"}
{"current_steps": 1100, "total_steps": 4023, "loss": 0.5645, "lr": 5e-06, "epoch": 0.8202833706189411, "percentage": 27.34, "elapsed_time": "4:02:36", "remaining_time": "10:44:40"}
{"current_steps": 1110, "total_steps": 4023, "loss": 0.5618, "lr": 5e-06, "epoch": 0.8277404921700223, "percentage": 27.59, "elapsed_time": "4:04:48", "remaining_time": "10:42:28"}
{"current_steps": 1120, "total_steps": 4023, "loss": 0.5378, "lr": 5e-06, "epoch": 0.8351976137211037, "percentage": 27.84, "elapsed_time": "4:07:01", "remaining_time": "10:40:16"}
{"current_steps": 1130, "total_steps": 4023, "loss": 0.552, "lr": 5e-06, "epoch": 0.8426547352721849, "percentage": 28.09, "elapsed_time": "4:09:13", "remaining_time": "10:38:04"}
{"current_steps": 1140, "total_steps": 4023, "loss": 0.5474, "lr": 5e-06, "epoch": 0.8501118568232662, "percentage": 28.34, "elapsed_time": "4:11:26", "remaining_time": "10:35:51"}
{"current_steps": 1150, "total_steps": 4023, "loss": 0.5568, "lr": 5e-06, "epoch": 0.8575689783743475, "percentage": 28.59, "elapsed_time": "4:13:38", "remaining_time": "10:33:39"}
{"current_steps": 1160, "total_steps": 4023, "loss": 0.5343, "lr": 5e-06, "epoch": 0.8650260999254288, "percentage": 28.83, "elapsed_time": "4:15:50", "remaining_time": "10:31:26"}
{"current_steps": 1170, "total_steps": 4023, "loss": 0.5428, "lr": 5e-06, "epoch": 0.87248322147651, "percentage": 29.08, "elapsed_time": "4:18:02", "remaining_time": "10:29:14"}
{"current_steps": 1180, "total_steps": 4023, "loss": 0.5356, "lr": 5e-06, "epoch": 0.8799403430275914, "percentage": 29.33, "elapsed_time": "4:20:15", "remaining_time": "10:27:01"}
{"current_steps": 1190, "total_steps": 4023, "loss": 0.5499, "lr": 5e-06, "epoch": 0.8873974645786726, "percentage": 29.58, "elapsed_time": "4:22:27", "remaining_time": "10:24:49"}
{"current_steps": 1200, "total_steps": 4023, "loss": 0.5288, "lr": 5e-06, "epoch": 0.8948545861297539, "percentage": 29.83, "elapsed_time": "4:24:39", "remaining_time": "10:22:36"}
{"current_steps": 1210, "total_steps": 4023, "loss": 0.5563, "lr": 5e-06, "epoch": 0.9023117076808352, "percentage": 30.08, "elapsed_time": "4:26:51", "remaining_time": "10:20:24"}
{"current_steps": 1220, "total_steps": 4023, "loss": 0.5392, "lr": 5e-06, "epoch": 0.9097688292319165, "percentage": 30.33, "elapsed_time": "4:29:04", "remaining_time": "10:18:12"}
{"current_steps": 1230, "total_steps": 4023, "loss": 0.551, "lr": 5e-06, "epoch": 0.9172259507829977, "percentage": 30.57, "elapsed_time": "4:31:16", "remaining_time": "10:15:59"}
{"current_steps": 1240, "total_steps": 4023, "loss": 0.5603, "lr": 5e-06, "epoch": 0.9246830723340791, "percentage": 30.82, "elapsed_time": "4:33:28", "remaining_time": "10:13:47"}
{"current_steps": 1250, "total_steps": 4023, "loss": 0.5468, "lr": 5e-06, "epoch": 0.9321401938851603, "percentage": 31.07, "elapsed_time": "4:35:41", "remaining_time": "10:11:34"}
{"current_steps": 1260, "total_steps": 4023, "loss": 0.5609, "lr": 5e-06, "epoch": 0.9395973154362416, "percentage": 31.32, "elapsed_time": "4:37:53", "remaining_time": "10:09:21"}
{"current_steps": 1270, "total_steps": 4023, "loss": 0.5592, "lr": 5e-06, "epoch": 0.947054436987323, "percentage": 31.57, "elapsed_time": "4:40:05", "remaining_time": "10:07:09"}
{"current_steps": 1280, "total_steps": 4023, "loss": 0.5554, "lr": 5e-06, "epoch": 0.9545115585384042, "percentage": 31.82, "elapsed_time": "4:42:17", "remaining_time": "10:04:56"}
{"current_steps": 1290, "total_steps": 4023, "loss": 0.5646, "lr": 5e-06, "epoch": 0.9619686800894854, "percentage": 32.07, "elapsed_time": "4:44:30", "remaining_time": "10:02:44"}
{"current_steps": 1300, "total_steps": 4023, "loss": 0.5559, "lr": 5e-06, "epoch": 0.9694258016405667, "percentage": 32.31, "elapsed_time": "4:46:42", "remaining_time": "10:00:32"}
{"current_steps": 1310, "total_steps": 4023, "loss": 0.5486, "lr": 5e-06, "epoch": 0.976882923191648, "percentage": 32.56, "elapsed_time": "4:48:54", "remaining_time": "9:58:20"}
{"current_steps": 1320, "total_steps": 4023, "loss": 0.5341, "lr": 5e-06, "epoch": 0.9843400447427293, "percentage": 32.81, "elapsed_time": "4:51:07", "remaining_time": "9:56:08"}
{"current_steps": 1330, "total_steps": 4023, "loss": 0.5446, "lr": 5e-06, "epoch": 0.9917971662938105, "percentage": 33.06, "elapsed_time": "4:53:19", "remaining_time": "9:53:55"}
{"current_steps": 1340, "total_steps": 4023, "loss": 0.5404, "lr": 5e-06, "epoch": 0.9992542878448919, "percentage": 33.31, "elapsed_time": "4:55:31", "remaining_time": "9:51:42"}
{"current_steps": 1341, "total_steps": 4023, "eval_loss": 0.5463822484016418, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:01:23", "remaining_time": "10:02:46"}
{"current_steps": 1350, "total_steps": 4023, "loss": 0.4824, "lr": 5e-06, "epoch": 1.0067114093959733, "percentage": 33.56, "elapsed_time": "5:04:27", "remaining_time": "10:02:50"}
{"current_steps": 1360, "total_steps": 4023, "loss": 0.4797, "lr": 5e-06, "epoch": 1.0141685309470545, "percentage": 33.81, "elapsed_time": "5:06:40", "remaining_time": "10:00:29"}
{"current_steps": 1370, "total_steps": 4023, "loss": 0.4686, "lr": 5e-06, "epoch": 1.0216256524981358, "percentage": 34.05, "elapsed_time": "5:08:52", "remaining_time": "9:58:08"}
{"current_steps": 1380, "total_steps": 4023, "loss": 0.469, "lr": 5e-06, "epoch": 1.029082774049217, "percentage": 34.3, "elapsed_time": "5:11:05", "remaining_time": "9:55:48"}
{"current_steps": 1390, "total_steps": 4023, "loss": 0.4903, "lr": 5e-06, "epoch": 1.0365398956002982, "percentage": 34.55, "elapsed_time": "5:13:17", "remaining_time": "9:53:27"}
{"current_steps": 1400, "total_steps": 4023, "loss": 0.4956, "lr": 5e-06, "epoch": 1.0439970171513795, "percentage": 34.8, "elapsed_time": "5:15:30", "remaining_time": "9:51:07"}
{"current_steps": 1410, "total_steps": 4023, "loss": 0.4933, "lr": 5e-06, "epoch": 1.0514541387024607, "percentage": 35.05, "elapsed_time": "5:17:42", "remaining_time": "9:48:47"}
{"current_steps": 1420, "total_steps": 4023, "loss": 0.486, "lr": 5e-06, "epoch": 1.0589112602535422, "percentage": 35.3, "elapsed_time": "5:19:55", "remaining_time": "9:46:27"}
{"current_steps": 1430, "total_steps": 4023, "loss": 0.4968, "lr": 5e-06, "epoch": 1.0663683818046235, "percentage": 35.55, "elapsed_time": "5:22:08", "remaining_time": "9:44:07"}
{"current_steps": 1440, "total_steps": 4023, "loss": 0.4902, "lr": 5e-06, "epoch": 1.0738255033557047, "percentage": 35.79, "elapsed_time": "5:24:20", "remaining_time": "9:41:47"}
{"current_steps": 1450, "total_steps": 4023, "loss": 0.4703, "lr": 5e-06, "epoch": 1.081282624906786, "percentage": 36.04, "elapsed_time": "5:26:33", "remaining_time": "9:39:28"}
{"current_steps": 1460, "total_steps": 4023, "loss": 0.4816, "lr": 5e-06, "epoch": 1.0887397464578672, "percentage": 36.29, "elapsed_time": "5:28:45", "remaining_time": "9:37:08"}
{"current_steps": 1470, "total_steps": 4023, "loss": 0.479, "lr": 5e-06, "epoch": 1.0961968680089484, "percentage": 36.54, "elapsed_time": "5:30:58", "remaining_time": "9:34:48"}
{"current_steps": 1480, "total_steps": 4023, "loss": 0.4834, "lr": 5e-06, "epoch": 1.10365398956003, "percentage": 36.79, "elapsed_time": "5:33:10", "remaining_time": "9:32:29"}
{"current_steps": 1490, "total_steps": 4023, "loss": 0.4807, "lr": 5e-06, "epoch": 1.1111111111111112, "percentage": 37.04, "elapsed_time": "5:35:23", "remaining_time": "9:30:09"}
{"current_steps": 1500, "total_steps": 4023, "loss": 0.4945, "lr": 5e-06, "epoch": 1.1185682326621924, "percentage": 37.29, "elapsed_time": "5:37:35", "remaining_time": "9:27:50"}
{"current_steps": 1510, "total_steps": 4023, "loss": 0.4756, "lr": 5e-06, "epoch": 1.1260253542132737, "percentage": 37.53, "elapsed_time": "5:39:48", "remaining_time": "9:25:31"}
{"current_steps": 1520, "total_steps": 4023, "loss": 0.4753, "lr": 5e-06, "epoch": 1.133482475764355, "percentage": 37.78, "elapsed_time": "5:42:00", "remaining_time": "9:23:11"}
{"current_steps": 1530, "total_steps": 4023, "loss": 0.474, "lr": 5e-06, "epoch": 1.1409395973154361, "percentage": 38.03, "elapsed_time": "5:44:13", "remaining_time": "9:20:53"}
{"current_steps": 1540, "total_steps": 4023, "loss": 0.4786, "lr": 5e-06, "epoch": 1.1483967188665176, "percentage": 38.28, "elapsed_time": "5:46:26", "remaining_time": "9:18:34"}
{"current_steps": 1550, "total_steps": 4023, "loss": 0.4658, "lr": 5e-06, "epoch": 1.1558538404175989, "percentage": 38.53, "elapsed_time": "5:48:39", "remaining_time": "9:16:15"}
{"current_steps": 1560, "total_steps": 4023, "loss": 0.4884, "lr": 5e-06, "epoch": 1.1633109619686801, "percentage": 38.78, "elapsed_time": "5:50:51", "remaining_time": "9:13:57"}
{"current_steps": 1570, "total_steps": 4023, "loss": 0.4907, "lr": 5e-06, "epoch": 1.1707680835197614, "percentage": 39.03, "elapsed_time": "5:53:04", "remaining_time": "9:11:38"}
{"current_steps": 1580, "total_steps": 4023, "loss": 0.4872, "lr": 5e-06, "epoch": 1.1782252050708426, "percentage": 39.27, "elapsed_time": "5:55:17", "remaining_time": "9:09:20"}
{"current_steps": 1590, "total_steps": 4023, "loss": 0.4816, "lr": 5e-06, "epoch": 1.1856823266219239, "percentage": 39.52, "elapsed_time": "5:57:29", "remaining_time": "9:07:01"}
{"current_steps": 1600, "total_steps": 4023, "loss": 0.4676, "lr": 5e-06, "epoch": 1.1931394481730053, "percentage": 39.77, "elapsed_time": "5:59:42", "remaining_time": "9:04:43"}
{"current_steps": 1610, "total_steps": 4023, "loss": 0.4789, "lr": 5e-06, "epoch": 1.2005965697240866, "percentage": 40.02, "elapsed_time": "6:01:54", "remaining_time": "9:02:25"}
{"current_steps": 1620, "total_steps": 4023, "loss": 0.4816, "lr": 5e-06, "epoch": 1.2080536912751678, "percentage": 40.27, "elapsed_time": "6:04:07", "remaining_time": "9:00:06"}
{"current_steps": 1630, "total_steps": 4023, "loss": 0.4852, "lr": 5e-06, "epoch": 1.215510812826249, "percentage": 40.52, "elapsed_time": "6:06:19", "remaining_time": "8:57:48"}
{"current_steps": 1640, "total_steps": 4023, "loss": 0.4986, "lr": 5e-06, "epoch": 1.2229679343773303, "percentage": 40.77, "elapsed_time": "6:08:32", "remaining_time": "8:55:30"}
{"current_steps": 1650, "total_steps": 4023, "loss": 0.4811, "lr": 5e-06, "epoch": 1.2304250559284116, "percentage": 41.01, "elapsed_time": "6:10:45", "remaining_time": "8:53:12"}
{"current_steps": 1660, "total_steps": 4023, "loss": 0.4886, "lr": 5e-06, "epoch": 1.2378821774794928, "percentage": 41.26, "elapsed_time": "6:12:57", "remaining_time": "8:50:54"}
{"current_steps": 1670, "total_steps": 4023, "loss": 0.4656, "lr": 5e-06, "epoch": 1.2453392990305743, "percentage": 41.51, "elapsed_time": "6:15:10", "remaining_time": "8:48:36"}
{"current_steps": 1680, "total_steps": 4023, "loss": 0.4715, "lr": 5e-06, "epoch": 1.2527964205816555, "percentage": 41.76, "elapsed_time": "6:17:22", "remaining_time": "8:46:18"}
{"current_steps": 1690, "total_steps": 4023, "loss": 0.471, "lr": 5e-06, "epoch": 1.2602535421327368, "percentage": 42.01, "elapsed_time": "6:19:35", "remaining_time": "8:44:00"}
{"current_steps": 1700, "total_steps": 4023, "loss": 0.4736, "lr": 5e-06, "epoch": 1.267710663683818, "percentage": 42.26, "elapsed_time": "6:21:47", "remaining_time": "8:41:42"}
{"current_steps": 1710, "total_steps": 4023, "loss": 0.4798, "lr": 5e-06, "epoch": 1.2751677852348993, "percentage": 42.51, "elapsed_time": "6:24:00", "remaining_time": "8:39:25"}
{"current_steps": 1720, "total_steps": 4023, "loss": 0.4792, "lr": 5e-06, "epoch": 1.2826249067859807, "percentage": 42.75, "elapsed_time": "6:26:12", "remaining_time": "8:37:07"}
{"current_steps": 1730, "total_steps": 4023, "loss": 0.4843, "lr": 5e-06, "epoch": 1.290082028337062, "percentage": 43.0, "elapsed_time": "6:28:25", "remaining_time": "8:34:49"}
{"current_steps": 1740, "total_steps": 4023, "loss": 0.4869, "lr": 5e-06, "epoch": 1.2975391498881432, "percentage": 43.25, "elapsed_time": "6:30:37", "remaining_time": "8:32:32"}
{"current_steps": 1750, "total_steps": 4023, "loss": 0.4838, "lr": 5e-06, "epoch": 1.3049962714392245, "percentage": 43.5, "elapsed_time": "6:32:50", "remaining_time": "8:30:14"}
{"current_steps": 1760, "total_steps": 4023, "loss": 0.4746, "lr": 5e-06, "epoch": 1.3124533929903057, "percentage": 43.75, "elapsed_time": "6:35:02", "remaining_time": "8:27:56"}
{"current_steps": 1770, "total_steps": 4023, "loss": 0.4931, "lr": 5e-06, "epoch": 1.319910514541387, "percentage": 44.0, "elapsed_time": "6:37:14", "remaining_time": "8:25:39"}
{"current_steps": 1780, "total_steps": 4023, "loss": 0.4871, "lr": 5e-06, "epoch": 1.3273676360924682, "percentage": 44.25, "elapsed_time": "6:39:27", "remaining_time": "8:23:21"}
{"current_steps": 1790, "total_steps": 4023, "loss": 0.4841, "lr": 5e-06, "epoch": 1.3348247576435495, "percentage": 44.49, "elapsed_time": "6:41:39", "remaining_time": "8:21:04"}
{"current_steps": 1800, "total_steps": 4023, "loss": 0.4862, "lr": 5e-06, "epoch": 1.342281879194631, "percentage": 44.74, "elapsed_time": "6:43:52", "remaining_time": "8:18:46"}
{"current_steps": 1810, "total_steps": 4023, "loss": 0.4766, "lr": 5e-06, "epoch": 1.3497390007457122, "percentage": 44.99, "elapsed_time": "6:46:04", "remaining_time": "8:16:29"}
{"current_steps": 1820, "total_steps": 4023, "loss": 0.4812, "lr": 5e-06, "epoch": 1.3571961222967934, "percentage": 45.24, "elapsed_time": "6:48:16", "remaining_time": "8:14:12"}
{"current_steps": 1830, "total_steps": 4023, "loss": 0.4686, "lr": 5e-06, "epoch": 1.3646532438478747, "percentage": 45.49, "elapsed_time": "6:50:29", "remaining_time": "8:11:54"}
{"current_steps": 1840, "total_steps": 4023, "loss": 0.477, "lr": 5e-06, "epoch": 1.372110365398956, "percentage": 45.74, "elapsed_time": "6:52:41", "remaining_time": "8:09:37"}
{"current_steps": 1850, "total_steps": 4023, "loss": 0.4889, "lr": 5e-06, "epoch": 1.3795674869500374, "percentage": 45.99, "elapsed_time": "6:54:53", "remaining_time": "8:07:20"}
{"current_steps": 1860, "total_steps": 4023, "loss": 0.4792, "lr": 5e-06, "epoch": 1.3870246085011186, "percentage": 46.23, "elapsed_time": "6:57:06", "remaining_time": "8:05:03"}
{"current_steps": 1870, "total_steps": 4023, "loss": 0.4897, "lr": 5e-06, "epoch": 1.3944817300521999, "percentage": 46.48, "elapsed_time": "6:59:18", "remaining_time": "8:02:46"}
{"current_steps": 1880, "total_steps": 4023, "loss": 0.496, "lr": 5e-06, "epoch": 1.4019388516032811, "percentage": 46.73, "elapsed_time": "7:01:31", "remaining_time": "8:00:29"}
{"current_steps": 1890, "total_steps": 4023, "loss": 0.4671, "lr": 5e-06, "epoch": 1.4093959731543624, "percentage": 46.98, "elapsed_time": "7:03:44", "remaining_time": "7:58:12"}
{"current_steps": 1900, "total_steps": 4023, "loss": 0.4786, "lr": 5e-06, "epoch": 1.4168530947054436, "percentage": 47.23, "elapsed_time": "7:05:56", "remaining_time": "7:55:56"}
{"current_steps": 1910, "total_steps": 4023, "loss": 0.4886, "lr": 5e-06, "epoch": 1.4243102162565249, "percentage": 47.48, "elapsed_time": "7:08:09", "remaining_time": "7:53:39"}
{"current_steps": 1920, "total_steps": 4023, "loss": 0.497, "lr": 5e-06, "epoch": 1.4317673378076063, "percentage": 47.73, "elapsed_time": "7:10:21", "remaining_time": "7:51:22"}
{"current_steps": 1930, "total_steps": 4023, "loss": 0.4899, "lr": 5e-06, "epoch": 1.4392244593586876, "percentage": 47.97, "elapsed_time": "7:12:34", "remaining_time": "7:49:06"}
{"current_steps": 1940, "total_steps": 4023, "loss": 0.4775, "lr": 5e-06, "epoch": 1.4466815809097688, "percentage": 48.22, "elapsed_time": "7:14:46", "remaining_time": "7:46:49"}
{"current_steps": 1950, "total_steps": 4023, "loss": 0.4907, "lr": 5e-06, "epoch": 1.45413870246085, "percentage": 48.47, "elapsed_time": "7:16:59", "remaining_time": "7:44:33"}
{"current_steps": 1960, "total_steps": 4023, "loss": 0.4759, "lr": 5e-06, "epoch": 1.4615958240119313, "percentage": 48.72, "elapsed_time": "7:19:12", "remaining_time": "7:42:16"}
{"current_steps": 1970, "total_steps": 4023, "loss": 0.4897, "lr": 5e-06, "epoch": 1.4690529455630128, "percentage": 48.97, "elapsed_time": "7:21:24", "remaining_time": "7:40:00"}
{"current_steps": 1980, "total_steps": 4023, "loss": 0.4746, "lr": 5e-06, "epoch": 1.476510067114094, "percentage": 49.22, "elapsed_time": "7:23:37", "remaining_time": "7:37:44"}
{"current_steps": 1990, "total_steps": 4023, "loss": 0.4885, "lr": 5e-06, "epoch": 1.4839671886651753, "percentage": 49.47, "elapsed_time": "7:25:49", "remaining_time": "7:35:27"}
{"current_steps": 2000, "total_steps": 4023, "loss": 0.4884, "lr": 5e-06, "epoch": 1.4914243102162565, "percentage": 49.71, "elapsed_time": "7:28:02", "remaining_time": "7:33:11"}
{"current_steps": 2010, "total_steps": 4023, "loss": 0.4799, "lr": 5e-06, "epoch": 1.4988814317673378, "percentage": 49.96, "elapsed_time": "7:30:15", "remaining_time": "7:30:55"}
{"current_steps": 2020, "total_steps": 4023, "loss": 0.4832, "lr": 5e-06, "epoch": 1.506338553318419, "percentage": 50.21, "elapsed_time": "7:32:27", "remaining_time": "7:28:39"}
{"current_steps": 2030, "total_steps": 4023, "loss": 0.4765, "lr": 5e-06, "epoch": 1.5137956748695003, "percentage": 50.46, "elapsed_time": "7:34:40", "remaining_time": "7:26:23"}
{"current_steps": 2040, "total_steps": 4023, "loss": 0.4876, "lr": 5e-06, "epoch": 1.5212527964205815, "percentage": 50.71, "elapsed_time": "7:36:53", "remaining_time": "7:24:07"}
{"current_steps": 2050, "total_steps": 4023, "loss": 0.4867, "lr": 5e-06, "epoch": 1.5287099179716628, "percentage": 50.96, "elapsed_time": "7:39:06", "remaining_time": "7:21:51"}
{"current_steps": 2060, "total_steps": 4023, "loss": 0.4952, "lr": 5e-06, "epoch": 1.5361670395227442, "percentage": 51.21, "elapsed_time": "7:41:18", "remaining_time": "7:19:35"}
{"current_steps": 2070, "total_steps": 4023, "loss": 0.476, "lr": 5e-06, "epoch": 1.5436241610738255, "percentage": 51.45, "elapsed_time": "7:43:31", "remaining_time": "7:17:19"}
{"current_steps": 2080, "total_steps": 4023, "loss": 0.4937, "lr": 5e-06, "epoch": 1.5510812826249067, "percentage": 51.7, "elapsed_time": "7:45:43", "remaining_time": "7:15:03"}
{"current_steps": 2090, "total_steps": 4023, "loss": 0.4974, "lr": 5e-06, "epoch": 1.5585384041759882, "percentage": 51.95, "elapsed_time": "7:47:56", "remaining_time": "7:12:47"}
{"current_steps": 2100, "total_steps": 4023, "loss": 0.4877, "lr": 5e-06, "epoch": 1.5659955257270695, "percentage": 52.2, "elapsed_time": "7:50:08", "remaining_time": "7:10:31"}
{"current_steps": 2110, "total_steps": 4023, "loss": 0.4873, "lr": 5e-06, "epoch": 1.5734526472781507, "percentage": 52.45, "elapsed_time": "7:52:21", "remaining_time": "7:08:15"}
{"current_steps": 2120, "total_steps": 4023, "loss": 0.4798, "lr": 5e-06, "epoch": 1.580909768829232, "percentage": 52.7, "elapsed_time": "7:54:33", "remaining_time": "7:05:59"}
{"current_steps": 2130, "total_steps": 4023, "loss": 0.4699, "lr": 5e-06, "epoch": 1.5883668903803132, "percentage": 52.95, "elapsed_time": "7:56:46", "remaining_time": "7:03:43"}
{"current_steps": 2140, "total_steps": 4023, "loss": 0.4995, "lr": 5e-06, "epoch": 1.5958240119313944, "percentage": 53.19, "elapsed_time": "7:58:58", "remaining_time": "7:01:27"}
{"current_steps": 2150, "total_steps": 4023, "loss": 0.4959, "lr": 5e-06, "epoch": 1.6032811334824757, "percentage": 53.44, "elapsed_time": "8:01:11", "remaining_time": "6:59:11"}
{"current_steps": 2160, "total_steps": 4023, "loss": 0.4783, "lr": 5e-06, "epoch": 1.610738255033557, "percentage": 53.69, "elapsed_time": "8:03:24", "remaining_time": "6:56:55"}
{"current_steps": 2170, "total_steps": 4023, "loss": 0.4823, "lr": 5e-06, "epoch": 1.6181953765846382, "percentage": 53.94, "elapsed_time": "8:05:36", "remaining_time": "6:54:40"}
{"current_steps": 2180, "total_steps": 4023, "loss": 0.4761, "lr": 5e-06, "epoch": 1.6256524981357197, "percentage": 54.19, "elapsed_time": "8:07:49", "remaining_time": "6:52:24"}
{"current_steps": 2190, "total_steps": 4023, "loss": 0.4823, "lr": 5e-06, "epoch": 1.633109619686801, "percentage": 54.44, "elapsed_time": "8:10:01", "remaining_time": "6:50:09"}
{"current_steps": 2200, "total_steps": 4023, "loss": 0.4827, "lr": 5e-06, "epoch": 1.6405667412378822, "percentage": 54.69, "elapsed_time": "8:12:14", "remaining_time": "6:47:53"}
{"current_steps": 2210, "total_steps": 4023, "loss": 0.4878, "lr": 5e-06, "epoch": 1.6480238627889636, "percentage": 54.93, "elapsed_time": "8:14:26", "remaining_time": "6:45:37"}
{"current_steps": 2220, "total_steps": 4023, "loss": 0.4854, "lr": 5e-06, "epoch": 1.6554809843400449, "percentage": 55.18, "elapsed_time": "8:16:39", "remaining_time": "6:43:21"}
{"current_steps": 2230, "total_steps": 4023, "loss": 0.4876, "lr": 5e-06, "epoch": 1.6629381058911261, "percentage": 55.43, "elapsed_time": "8:18:51", "remaining_time": "6:41:06"}
{"current_steps": 2240, "total_steps": 4023, "loss": 0.4976, "lr": 5e-06, "epoch": 1.6703952274422074, "percentage": 55.68, "elapsed_time": "8:21:04", "remaining_time": "6:38:50"}
{"current_steps": 2250, "total_steps": 4023, "loss": 0.473, "lr": 5e-06, "epoch": 1.6778523489932886, "percentage": 55.93, "elapsed_time": "8:23:16", "remaining_time": "6:36:34"}
{"current_steps": 2260, "total_steps": 4023, "loss": 0.4866, "lr": 5e-06, "epoch": 1.6853094705443699, "percentage": 56.18, "elapsed_time": "8:25:28", "remaining_time": "6:34:19"}
{"current_steps": 2270, "total_steps": 4023, "loss": 0.4909, "lr": 5e-06, "epoch": 1.692766592095451, "percentage": 56.43, "elapsed_time": "8:27:40", "remaining_time": "6:32:03"}
{"current_steps": 2280, "total_steps": 4023, "loss": 0.4914, "lr": 5e-06, "epoch": 1.7002237136465324, "percentage": 56.67, "elapsed_time": "8:29:53", "remaining_time": "6:29:47"}
{"current_steps": 2290, "total_steps": 4023, "loss": 0.4804, "lr": 5e-06, "epoch": 1.7076808351976136, "percentage": 56.92, "elapsed_time": "8:32:05", "remaining_time": "6:27:32"}
{"current_steps": 2300, "total_steps": 4023, "loss": 0.4925, "lr": 5e-06, "epoch": 1.7151379567486948, "percentage": 57.17, "elapsed_time": "8:34:17", "remaining_time": "6:25:16"}
{"current_steps": 2310, "total_steps": 4023, "loss": 0.4913, "lr": 5e-06, "epoch": 1.7225950782997763, "percentage": 57.42, "elapsed_time": "8:36:30", "remaining_time": "6:23:01"}
{"current_steps": 2320, "total_steps": 4023, "loss": 0.4769, "lr": 5e-06, "epoch": 1.7300521998508576, "percentage": 57.67, "elapsed_time": "8:38:42", "remaining_time": "6:20:45"}
{"current_steps": 2330, "total_steps": 4023, "loss": 0.4898, "lr": 5e-06, "epoch": 1.7375093214019388, "percentage": 57.92, "elapsed_time": "8:40:54", "remaining_time": "6:18:30"}
{"current_steps": 2340, "total_steps": 4023, "loss": 0.4826, "lr": 5e-06, "epoch": 1.7449664429530203, "percentage": 58.17, "elapsed_time": "8:43:07", "remaining_time": "6:16:14"}
{"current_steps": 2350, "total_steps": 4023, "loss": 0.4777, "lr": 5e-06, "epoch": 1.7524235645041015, "percentage": 58.41, "elapsed_time": "8:45:19", "remaining_time": "6:13:59"}
{"current_steps": 2360, "total_steps": 4023, "loss": 0.4934, "lr": 5e-06, "epoch": 1.7598806860551828, "percentage": 58.66, "elapsed_time": "8:47:32", "remaining_time": "6:11:44"}
{"current_steps": 2370, "total_steps": 4023, "loss": 0.5053, "lr": 5e-06, "epoch": 1.767337807606264, "percentage": 58.91, "elapsed_time": "8:49:44", "remaining_time": "6:09:29"}
{"current_steps": 2380, "total_steps": 4023, "loss": 0.4817, "lr": 5e-06, "epoch": 1.7747949291573453, "percentage": 59.16, "elapsed_time": "8:51:57", "remaining_time": "6:07:13"}
{"current_steps": 2390, "total_steps": 4023, "loss": 0.4853, "lr": 5e-06, "epoch": 1.7822520507084265, "percentage": 59.41, "elapsed_time": "8:54:10", "remaining_time": "6:04:58"}
{"current_steps": 2400, "total_steps": 4023, "loss": 0.4791, "lr": 5e-06, "epoch": 1.7897091722595078, "percentage": 59.66, "elapsed_time": "8:56:23", "remaining_time": "6:02:43"}
{"current_steps": 2410, "total_steps": 4023, "loss": 0.4809, "lr": 5e-06, "epoch": 1.797166293810589, "percentage": 59.91, "elapsed_time": "8:58:35", "remaining_time": "6:00:28"}
{"current_steps": 2420, "total_steps": 4023, "loss": 0.4929, "lr": 5e-06, "epoch": 1.8046234153616703, "percentage": 60.15, "elapsed_time": "9:00:48", "remaining_time": "5:58:13"}
{"current_steps": 2430, "total_steps": 4023, "loss": 0.4847, "lr": 5e-06, "epoch": 1.8120805369127517, "percentage": 60.4, "elapsed_time": "9:03:01", "remaining_time": "5:55:58"}
{"current_steps": 2440, "total_steps": 4023, "loss": 0.4906, "lr": 5e-06, "epoch": 1.819537658463833, "percentage": 60.65, "elapsed_time": "9:05:13", "remaining_time": "5:53:43"}
{"current_steps": 2450, "total_steps": 4023, "loss": 0.4975, "lr": 5e-06, "epoch": 1.8269947800149142, "percentage": 60.9, "elapsed_time": "9:07:26", "remaining_time": "5:51:28"}
{"current_steps": 2460, "total_steps": 4023, "loss": 0.4814, "lr": 5e-06, "epoch": 1.8344519015659957, "percentage": 61.15, "elapsed_time": "9:09:39", "remaining_time": "5:49:13"}
{"current_steps": 2470, "total_steps": 4023, "loss": 0.4811, "lr": 5e-06, "epoch": 1.841909023117077, "percentage": 61.4, "elapsed_time": "9:11:51", "remaining_time": "5:46:58"}
{"current_steps": 2480, "total_steps": 4023, "loss": 0.496, "lr": 5e-06, "epoch": 1.8493661446681582, "percentage": 61.65, "elapsed_time": "9:14:04", "remaining_time": "5:44:44"}
{"current_steps": 2490, "total_steps": 4023, "loss": 0.4804, "lr": 5e-06, "epoch": 1.8568232662192394, "percentage": 61.89, "elapsed_time": "9:16:17", "remaining_time": "5:42:29"}
{"current_steps": 2500, "total_steps": 4023, "loss": 0.4863, "lr": 5e-06, "epoch": 1.8642803877703207, "percentage": 62.14, "elapsed_time": "9:18:29", "remaining_time": "5:40:14"}
{"current_steps": 2510, "total_steps": 4023, "loss": 0.4909, "lr": 5e-06, "epoch": 1.871737509321402, "percentage": 62.39, "elapsed_time": "9:20:42", "remaining_time": "5:37:59"}
{"current_steps": 2520, "total_steps": 4023, "loss": 0.4831, "lr": 5e-06, "epoch": 1.8791946308724832, "percentage": 62.64, "elapsed_time": "9:22:55", "remaining_time": "5:35:44"}
{"current_steps": 2530, "total_steps": 4023, "loss": 0.5042, "lr": 5e-06, "epoch": 1.8866517524235644, "percentage": 62.89, "elapsed_time": "9:25:08", "remaining_time": "5:33:29"}
{"current_steps": 2540, "total_steps": 4023, "loss": 0.5004, "lr": 5e-06, "epoch": 1.8941088739746457, "percentage": 63.14, "elapsed_time": "9:27:20", "remaining_time": "5:31:14"}
{"current_steps": 2550, "total_steps": 4023, "loss": 0.4802, "lr": 5e-06, "epoch": 1.901565995525727, "percentage": 63.39, "elapsed_time": "9:29:33", "remaining_time": "5:29:00"}
{"current_steps": 2560, "total_steps": 4023, "loss": 0.49, "lr": 5e-06, "epoch": 1.9090231170768084, "percentage": 63.63, "elapsed_time": "9:31:46", "remaining_time": "5:26:45"}
{"current_steps": 2570, "total_steps": 4023, "loss": 0.4961, "lr": 5e-06, "epoch": 1.9164802386278896, "percentage": 63.88, "elapsed_time": "9:33:58", "remaining_time": "5:24:30"}
{"current_steps": 2580, "total_steps": 4023, "loss": 0.493, "lr": 5e-06, "epoch": 1.9239373601789709, "percentage": 64.13, "elapsed_time": "9:36:11", "remaining_time": "5:22:15"}
{"current_steps": 2590, "total_steps": 4023, "loss": 0.4788, "lr": 5e-06, "epoch": 1.9313944817300523, "percentage": 64.38, "elapsed_time": "9:38:24", "remaining_time": "5:20:01"}
{"current_steps": 2600, "total_steps": 4023, "loss": 0.4944, "lr": 5e-06, "epoch": 1.9388516032811336, "percentage": 64.63, "elapsed_time": "9:40:36", "remaining_time": "5:17:46"}
{"current_steps": 2610, "total_steps": 4023, "loss": 0.4924, "lr": 5e-06, "epoch": 1.9463087248322148, "percentage": 64.88, "elapsed_time": "9:42:49", "remaining_time": "5:15:31"}
{"current_steps": 2620, "total_steps": 4023, "loss": 0.4909, "lr": 5e-06, "epoch": 1.953765846383296, "percentage": 65.13, "elapsed_time": "9:45:02", "remaining_time": "5:13:17"}
{"current_steps": 2630, "total_steps": 4023, "loss": 0.4981, "lr": 5e-06, "epoch": 1.9612229679343773, "percentage": 65.37, "elapsed_time": "9:47:14", "remaining_time": "5:11:02"}
{"current_steps": 2640, "total_steps": 4023, "loss": 0.498, "lr": 5e-06, "epoch": 1.9686800894854586, "percentage": 65.62, "elapsed_time": "9:49:27", "remaining_time": "5:08:47"}
{"current_steps": 2650, "total_steps": 4023, "loss": 0.4793, "lr": 5e-06, "epoch": 1.9761372110365398, "percentage": 65.87, "elapsed_time": "9:51:40", "remaining_time": "5:06:33"}
{"current_steps": 2660, "total_steps": 4023, "loss": 0.4877, "lr": 5e-06, "epoch": 1.983594332587621, "percentage": 66.12, "elapsed_time": "9:53:53", "remaining_time": "5:04:18"}
{"current_steps": 2670, "total_steps": 4023, "loss": 0.4852, "lr": 5e-06, "epoch": 1.9910514541387023, "percentage": 66.37, "elapsed_time": "9:56:05", "remaining_time": "5:02:04"}
{"current_steps": 2680, "total_steps": 4023, "loss": 0.4804, "lr": 5e-06, "epoch": 1.9985085756897838, "percentage": 66.62, "elapsed_time": "9:58:18", "remaining_time": "4:59:49"}
{"current_steps": 2682, "total_steps": 4023, "eval_loss": 0.5512435436248779, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "10:04:26", "remaining_time": "5:02:13"}
{"current_steps": 2690, "total_steps": 4023, "loss": 0.4215, "lr": 5e-06, "epoch": 2.005965697240865, "percentage": 66.87, "elapsed_time": "10:07:20", "remaining_time": "5:00:57"}
{"current_steps": 2700, "total_steps": 4023, "loss": 0.4033, "lr": 5e-06, "epoch": 2.0134228187919465, "percentage": 67.11, "elapsed_time": "10:09:32", "remaining_time": "4:58:40"}
{"current_steps": 2710, "total_steps": 4023, "loss": 0.3907, "lr": 5e-06, "epoch": 2.0208799403430278, "percentage": 67.36, "elapsed_time": "10:11:45", "remaining_time": "4:56:23"}
{"current_steps": 2720, "total_steps": 4023, "loss": 0.3977, "lr": 5e-06, "epoch": 2.028337061894109, "percentage": 67.61, "elapsed_time": "10:13:58", "remaining_time": "4:54:07"}
{"current_steps": 2730, "total_steps": 4023, "loss": 0.4112, "lr": 5e-06, "epoch": 2.0357941834451903, "percentage": 67.86, "elapsed_time": "10:16:10", "remaining_time": "4:51:50"}
{"current_steps": 2740, "total_steps": 4023, "loss": 0.4176, "lr": 5e-06, "epoch": 2.0432513049962715, "percentage": 68.11, "elapsed_time": "10:18:23", "remaining_time": "4:49:33"}
{"current_steps": 2750, "total_steps": 4023, "loss": 0.4026, "lr": 5e-06, "epoch": 2.0507084265473527, "percentage": 68.36, "elapsed_time": "10:20:35", "remaining_time": "4:47:16"}
{"current_steps": 2760, "total_steps": 4023, "loss": 0.409, "lr": 5e-06, "epoch": 2.058165548098434, "percentage": 68.61, "elapsed_time": "10:22:48", "remaining_time": "4:45:00"}
{"current_steps": 2770, "total_steps": 4023, "loss": 0.4024, "lr": 5e-06, "epoch": 2.0656226696495152, "percentage": 68.85, "elapsed_time": "10:25:01", "remaining_time": "4:42:43"}
{"current_steps": 2780, "total_steps": 4023, "loss": 0.4175, "lr": 5e-06, "epoch": 2.0730797912005965, "percentage": 69.1, "elapsed_time": "10:27:13", "remaining_time": "4:40:26"}
{"current_steps": 2790, "total_steps": 4023, "loss": 0.403, "lr": 5e-06, "epoch": 2.0805369127516777, "percentage": 69.35, "elapsed_time": "10:29:26", "remaining_time": "4:38:10"}
{"current_steps": 2800, "total_steps": 4023, "loss": 0.413, "lr": 5e-06, "epoch": 2.087994034302759, "percentage": 69.6, "elapsed_time": "10:31:39", "remaining_time": "4:35:53"}
{"current_steps": 2810, "total_steps": 4023, "loss": 0.4159, "lr": 5e-06, "epoch": 2.0954511558538402, "percentage": 69.85, "elapsed_time": "10:33:52", "remaining_time": "4:33:37"}
{"current_steps": 2820, "total_steps": 4023, "loss": 0.4107, "lr": 5e-06, "epoch": 2.1029082774049215, "percentage": 70.1, "elapsed_time": "10:36:04", "remaining_time": "4:31:21"}
{"current_steps": 2830, "total_steps": 4023, "loss": 0.415, "lr": 5e-06, "epoch": 2.110365398956003, "percentage": 70.35, "elapsed_time": "10:38:17", "remaining_time": "4:29:04"}
{"current_steps": 2840, "total_steps": 4023, "loss": 0.415, "lr": 5e-06, "epoch": 2.1178225205070844, "percentage": 70.59, "elapsed_time": "10:40:30", "remaining_time": "4:26:48"}
{"current_steps": 2850, "total_steps": 4023, "loss": 0.4096, "lr": 5e-06, "epoch": 2.1252796420581657, "percentage": 70.84, "elapsed_time": "10:42:43", "remaining_time": "4:24:31"}
{"current_steps": 2860, "total_steps": 4023, "loss": 0.4015, "lr": 5e-06, "epoch": 2.132736763609247, "percentage": 71.09, "elapsed_time": "10:44:55", "remaining_time": "4:22:15"}
{"current_steps": 2870, "total_steps": 4023, "loss": 0.4068, "lr": 5e-06, "epoch": 2.140193885160328, "percentage": 71.34, "elapsed_time": "10:47:08", "remaining_time": "4:19:58"}
{"current_steps": 2880, "total_steps": 4023, "loss": 0.4215, "lr": 5e-06, "epoch": 2.1476510067114094, "percentage": 71.59, "elapsed_time": "10:49:20", "remaining_time": "4:17:42"}
{"current_steps": 2890, "total_steps": 4023, "loss": 0.4141, "lr": 5e-06, "epoch": 2.1551081282624907, "percentage": 71.84, "elapsed_time": "10:51:33", "remaining_time": "4:15:26"}
{"current_steps": 2900, "total_steps": 4023, "loss": 0.407, "lr": 5e-06, "epoch": 2.162565249813572, "percentage": 72.09, "elapsed_time": "10:53:45", "remaining_time": "4:13:09"}
{"current_steps": 2910, "total_steps": 4023, "loss": 0.417, "lr": 5e-06, "epoch": 2.170022371364653, "percentage": 72.33, "elapsed_time": "10:55:58", "remaining_time": "4:10:53"}
{"current_steps": 2920, "total_steps": 4023, "loss": 0.4225, "lr": 5e-06, "epoch": 2.1774794929157344, "percentage": 72.58, "elapsed_time": "10:58:11", "remaining_time": "4:08:37"}
{"current_steps": 2930, "total_steps": 4023, "loss": 0.4138, "lr": 5e-06, "epoch": 2.1849366144668156, "percentage": 72.83, "elapsed_time": "11:00:23", "remaining_time": "4:06:21"}
{"current_steps": 2940, "total_steps": 4023, "loss": 0.4112, "lr": 5e-06, "epoch": 2.192393736017897, "percentage": 73.08, "elapsed_time": "11:02:36", "remaining_time": "4:04:04"}
{"current_steps": 2950, "total_steps": 4023, "loss": 0.4208, "lr": 5e-06, "epoch": 2.1998508575689786, "percentage": 73.33, "elapsed_time": "11:04:48", "remaining_time": "4:01:48"}
{"current_steps": 2960, "total_steps": 4023, "loss": 0.4167, "lr": 5e-06, "epoch": 2.20730797912006, "percentage": 73.58, "elapsed_time": "11:07:01", "remaining_time": "3:59:32"}
{"current_steps": 2970, "total_steps": 4023, "loss": 0.413, "lr": 5e-06, "epoch": 2.214765100671141, "percentage": 73.83, "elapsed_time": "11:09:13", "remaining_time": "3:57:16"}
{"current_steps": 2980, "total_steps": 4023, "loss": 0.4126, "lr": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "11:11:26", "remaining_time": "3:55:00"}
{"current_steps": 2990, "total_steps": 4023, "loss": 0.4189, "lr": 5e-06, "epoch": 2.2296793437733036, "percentage": 74.32, "elapsed_time": "11:13:38", "remaining_time": "3:52:44"}
{"current_steps": 3000, "total_steps": 4023, "loss": 0.416, "lr": 5e-06, "epoch": 2.237136465324385, "percentage": 74.57, "elapsed_time": "11:15:51", "remaining_time": "3:50:27"}
{"current_steps": 3010, "total_steps": 4023, "loss": 0.4182, "lr": 5e-06, "epoch": 2.244593586875466, "percentage": 74.82, "elapsed_time": "11:18:03", "remaining_time": "3:48:11"}
{"current_steps": 3020, "total_steps": 4023, "loss": 0.4401, "lr": 5e-06, "epoch": 2.2520507084265473, "percentage": 75.07, "elapsed_time": "11:20:16", "remaining_time": "3:45:55"}
{"current_steps": 3030, "total_steps": 4023, "loss": 0.4093, "lr": 5e-06, "epoch": 2.2595078299776286, "percentage": 75.32, "elapsed_time": "11:22:28", "remaining_time": "3:43:39"}
{"current_steps": 3040, "total_steps": 4023, "loss": 0.4201, "lr": 5e-06, "epoch": 2.26696495152871, "percentage": 75.57, "elapsed_time": "11:24:41", "remaining_time": "3:41:23"}
{"current_steps": 3050, "total_steps": 4023, "loss": 0.4216, "lr": 5e-06, "epoch": 2.274422073079791, "percentage": 75.81, "elapsed_time": "11:26:54", "remaining_time": "3:39:08"}
{"current_steps": 3060, "total_steps": 4023, "loss": 0.4225, "lr": 5e-06, "epoch": 2.2818791946308723, "percentage": 76.06, "elapsed_time": "11:29:06", "remaining_time": "3:36:52"}
{"current_steps": 3070, "total_steps": 4023, "loss": 0.4187, "lr": 5e-06, "epoch": 2.289336316181954, "percentage": 76.31, "elapsed_time": "11:31:19", "remaining_time": "3:34:36"}
{"current_steps": 3080, "total_steps": 4023, "loss": 0.4238, "lr": 5e-06, "epoch": 2.2967934377330352, "percentage": 76.56, "elapsed_time": "11:33:32", "remaining_time": "3:32:20"}
{"current_steps": 3090, "total_steps": 4023, "loss": 0.4219, "lr": 5e-06, "epoch": 2.3042505592841165, "percentage": 76.81, "elapsed_time": "11:35:44", "remaining_time": "3:30:04"}
{"current_steps": 3100, "total_steps": 4023, "loss": 0.4246, "lr": 5e-06, "epoch": 2.3117076808351977, "percentage": 77.06, "elapsed_time": "11:37:57", "remaining_time": "3:27:48"}
{"current_steps": 3110, "total_steps": 4023, "loss": 0.4071, "lr": 5e-06, "epoch": 2.319164802386279, "percentage": 77.31, "elapsed_time": "11:40:09", "remaining_time": "3:25:32"}
{"current_steps": 3120, "total_steps": 4023, "loss": 0.4114, "lr": 5e-06, "epoch": 2.3266219239373602, "percentage": 77.55, "elapsed_time": "11:42:22", "remaining_time": "3:23:16"}
{"current_steps": 3130, "total_steps": 4023, "loss": 0.4154, "lr": 5e-06, "epoch": 2.3340790454884415, "percentage": 77.8, "elapsed_time": "11:44:34", "remaining_time": "3:21:01"}
{"current_steps": 3140, "total_steps": 4023, "loss": 0.4342, "lr": 5e-06, "epoch": 2.3415361670395227, "percentage": 78.05, "elapsed_time": "11:46:47", "remaining_time": "3:18:45"}
{"current_steps": 3150, "total_steps": 4023, "loss": 0.4115, "lr": 5e-06, "epoch": 2.348993288590604, "percentage": 78.3, "elapsed_time": "11:48:59", "remaining_time": "3:16:29"}
{"current_steps": 3160, "total_steps": 4023, "loss": 0.4129, "lr": 5e-06, "epoch": 2.356450410141685, "percentage": 78.55, "elapsed_time": "11:51:11", "remaining_time": "3:14:13"}
{"current_steps": 3170, "total_steps": 4023, "loss": 0.4116, "lr": 5e-06, "epoch": 2.3639075316927665, "percentage": 78.8, "elapsed_time": "11:53:24", "remaining_time": "3:11:58"}
{"current_steps": 3180, "total_steps": 4023, "loss": 0.4257, "lr": 5e-06, "epoch": 2.3713646532438477, "percentage": 79.05, "elapsed_time": "11:55:36", "remaining_time": "3:09:42"}
{"current_steps": 3190, "total_steps": 4023, "loss": 0.4332, "lr": 5e-06, "epoch": 2.378821774794929, "percentage": 79.29, "elapsed_time": "11:57:49", "remaining_time": "3:07:26"}
{"current_steps": 3200, "total_steps": 4023, "loss": 0.4166, "lr": 5e-06, "epoch": 2.3862788963460106, "percentage": 79.54, "elapsed_time": "12:00:01", "remaining_time": "3:05:10"}
{"current_steps": 3210, "total_steps": 4023, "loss": 0.4214, "lr": 5e-06, "epoch": 2.393736017897092, "percentage": 79.79, "elapsed_time": "12:02:13", "remaining_time": "3:02:55"}
{"current_steps": 3220, "total_steps": 4023, "loss": 0.4175, "lr": 5e-06, "epoch": 2.401193139448173, "percentage": 80.04, "elapsed_time": "12:04:26", "remaining_time": "3:00:39"}
{"current_steps": 3230, "total_steps": 4023, "loss": 0.4205, "lr": 5e-06, "epoch": 2.4086502609992544, "percentage": 80.29, "elapsed_time": "12:06:38", "remaining_time": "2:58:23"}
{"current_steps": 3240, "total_steps": 4023, "loss": 0.4106, "lr": 5e-06, "epoch": 2.4161073825503356, "percentage": 80.54, "elapsed_time": "12:08:51", "remaining_time": "2:56:08"}
{"current_steps": 3250, "total_steps": 4023, "loss": 0.435, "lr": 5e-06, "epoch": 2.423564504101417, "percentage": 80.79, "elapsed_time": "12:11:03", "remaining_time": "2:53:52"}
{"current_steps": 3260, "total_steps": 4023, "loss": 0.4148, "lr": 5e-06, "epoch": 2.431021625652498, "percentage": 81.03, "elapsed_time": "12:13:15", "remaining_time": "2:51:37"}
{"current_steps": 3270, "total_steps": 4023, "loss": 0.4071, "lr": 5e-06, "epoch": 2.4384787472035794, "percentage": 81.28, "elapsed_time": "12:15:28", "remaining_time": "2:49:21"}
{"current_steps": 3280, "total_steps": 4023, "loss": 0.4222, "lr": 5e-06, "epoch": 2.4459358687546606, "percentage": 81.53, "elapsed_time": "12:17:40", "remaining_time": "2:47:06"}
{"current_steps": 3290, "total_steps": 4023, "loss": 0.4152, "lr": 5e-06, "epoch": 2.453392990305742, "percentage": 81.78, "elapsed_time": "12:19:52", "remaining_time": "2:44:50"}
{"current_steps": 3300, "total_steps": 4023, "loss": 0.4051, "lr": 5e-06, "epoch": 2.460850111856823, "percentage": 82.03, "elapsed_time": "12:22:05", "remaining_time": "2:42:35"}
{"current_steps": 3310, "total_steps": 4023, "loss": 0.4221, "lr": 5e-06, "epoch": 2.4683072334079044, "percentage": 82.28, "elapsed_time": "12:24:17", "remaining_time": "2:40:19"}
{"current_steps": 3320, "total_steps": 4023, "loss": 0.4116, "lr": 5e-06, "epoch": 2.4757643549589856, "percentage": 82.53, "elapsed_time": "12:26:29", "remaining_time": "2:38:04"}
{"current_steps": 3330, "total_steps": 4023, "loss": 0.4211, "lr": 5e-06, "epoch": 2.4832214765100673, "percentage": 82.77, "elapsed_time": "12:28:42", "remaining_time": "2:35:48"}
{"current_steps": 3340, "total_steps": 4023, "loss": 0.4176, "lr": 5e-06, "epoch": 2.4906785980611486, "percentage": 83.02, "elapsed_time": "12:30:54", "remaining_time": "2:33:33"}
{"current_steps": 3350, "total_steps": 4023, "loss": 0.4283, "lr": 5e-06, "epoch": 2.49813571961223, "percentage": 83.27, "elapsed_time": "12:33:06", "remaining_time": "2:31:17"}
{"current_steps": 3360, "total_steps": 4023, "loss": 0.4207, "lr": 5e-06, "epoch": 2.505592841163311, "percentage": 83.52, "elapsed_time": "12:35:19", "remaining_time": "2:29:02"}
{"current_steps": 3370, "total_steps": 4023, "loss": 0.4239, "lr": 5e-06, "epoch": 2.5130499627143923, "percentage": 83.77, "elapsed_time": "12:37:31", "remaining_time": "2:26:47"}
{"current_steps": 3380, "total_steps": 4023, "loss": 0.4266, "lr": 5e-06, "epoch": 2.5205070842654735, "percentage": 84.02, "elapsed_time": "12:39:43", "remaining_time": "2:24:31"}
{"current_steps": 3390, "total_steps": 4023, "loss": 0.4262, "lr": 5e-06, "epoch": 2.527964205816555, "percentage": 84.27, "elapsed_time": "12:41:56", "remaining_time": "2:22:16"}
{"current_steps": 3400, "total_steps": 4023, "loss": 0.4082, "lr": 5e-06, "epoch": 2.535421327367636, "percentage": 84.51, "elapsed_time": "12:44:08", "remaining_time": "2:20:01"}
{"current_steps": 3410, "total_steps": 4023, "loss": 0.4123, "lr": 5e-06, "epoch": 2.5428784489187173, "percentage": 84.76, "elapsed_time": "12:46:20", "remaining_time": "2:17:45"}
{"current_steps": 3420, "total_steps": 4023, "loss": 0.4177, "lr": 5e-06, "epoch": 2.5503355704697985, "percentage": 85.01, "elapsed_time": "12:48:33", "remaining_time": "2:15:30"}
{"current_steps": 3430, "total_steps": 4023, "loss": 0.4238, "lr": 5e-06, "epoch": 2.5577926920208798, "percentage": 85.26, "elapsed_time": "12:50:45", "remaining_time": "2:13:15"}
{"current_steps": 3440, "total_steps": 4023, "loss": 0.4333, "lr": 5e-06, "epoch": 2.5652498135719615, "percentage": 85.51, "elapsed_time": "12:52:58", "remaining_time": "2:11:00"}
{"current_steps": 3450, "total_steps": 4023, "loss": 0.4253, "lr": 5e-06, "epoch": 2.5727069351230423, "percentage": 85.76, "elapsed_time": "12:55:10", "remaining_time": "2:08:44"}
{"current_steps": 3460, "total_steps": 4023, "loss": 0.4249, "lr": 5e-06, "epoch": 2.580164056674124, "percentage": 86.01, "elapsed_time": "12:57:23", "remaining_time": "2:06:29"}
{"current_steps": 3470, "total_steps": 4023, "loss": 0.4177, "lr": 5e-06, "epoch": 2.587621178225205, "percentage": 86.25, "elapsed_time": "12:59:35", "remaining_time": "2:04:14"}
{"current_steps": 3480, "total_steps": 4023, "loss": 0.4161, "lr": 5e-06, "epoch": 2.5950782997762865, "percentage": 86.5, "elapsed_time": "13:01:48", "remaining_time": "2:01:59"}
{"current_steps": 3490, "total_steps": 4023, "loss": 0.4163, "lr": 5e-06, "epoch": 2.6025354213273677, "percentage": 86.75, "elapsed_time": "13:04:00", "remaining_time": "1:59:44"}
{"current_steps": 3500, "total_steps": 4023, "loss": 0.4186, "lr": 5e-06, "epoch": 2.609992542878449, "percentage": 87.0, "elapsed_time": "13:06:13", "remaining_time": "1:57:29"}
{"current_steps": 3510, "total_steps": 4023, "loss": 0.428, "lr": 5e-06, "epoch": 2.61744966442953, "percentage": 87.25, "elapsed_time": "13:08:25", "remaining_time": "1:55:13"}
{"current_steps": 3520, "total_steps": 4023, "loss": 0.4171, "lr": 5e-06, "epoch": 2.6249067859806114, "percentage": 87.5, "elapsed_time": "13:10:37", "remaining_time": "1:52:58"}
{"current_steps": 3530, "total_steps": 4023, "loss": 0.4208, "lr": 5e-06, "epoch": 2.6323639075316927, "percentage": 87.75, "elapsed_time": "13:12:50", "remaining_time": "1:50:43"}
{"current_steps": 3540, "total_steps": 4023, "loss": 0.4232, "lr": 5e-06, "epoch": 2.639821029082774, "percentage": 87.99, "elapsed_time": "13:15:02", "remaining_time": "1:48:28"}
{"current_steps": 3550, "total_steps": 4023, "loss": 0.4145, "lr": 5e-06, "epoch": 2.647278150633855, "percentage": 88.24, "elapsed_time": "13:17:14", "remaining_time": "1:46:13"}
{"current_steps": 3560, "total_steps": 4023, "loss": 0.428, "lr": 5e-06, "epoch": 2.6547352721849364, "percentage": 88.49, "elapsed_time": "13:19:27", "remaining_time": "1:43:58"}
{"current_steps": 3570, "total_steps": 4023, "loss": 0.4271, "lr": 5e-06, "epoch": 2.662192393736018, "percentage": 88.74, "elapsed_time": "13:21:39", "remaining_time": "1:41:43"}
{"current_steps": 3580, "total_steps": 4023, "loss": 0.4153, "lr": 5e-06, "epoch": 2.669649515287099, "percentage": 88.99, "elapsed_time": "13:23:52", "remaining_time": "1:39:28"}
{"current_steps": 3590, "total_steps": 4023, "loss": 0.4157, "lr": 5e-06, "epoch": 2.6771066368381806, "percentage": 89.24, "elapsed_time": "13:26:04", "remaining_time": "1:37:13"}
{"current_steps": 3600, "total_steps": 4023, "loss": 0.427, "lr": 5e-06, "epoch": 2.684563758389262, "percentage": 89.49, "elapsed_time": "13:28:16", "remaining_time": "1:34:58"}
{"current_steps": 3610, "total_steps": 4023, "loss": 0.4141, "lr": 5e-06, "epoch": 2.692020879940343, "percentage": 89.73, "elapsed_time": "13:30:29", "remaining_time": "1:32:43"}
{"current_steps": 3620, "total_steps": 4023, "loss": 0.4169, "lr": 5e-06, "epoch": 2.6994780014914244, "percentage": 89.98, "elapsed_time": "13:32:41", "remaining_time": "1:30:28"}
{"current_steps": 3630, "total_steps": 4023, "loss": 0.4363, "lr": 5e-06, "epoch": 2.7069351230425056, "percentage": 90.23, "elapsed_time": "13:34:54", "remaining_time": "1:28:13"}
{"current_steps": 3640, "total_steps": 4023, "loss": 0.4247, "lr": 5e-06, "epoch": 2.714392244593587, "percentage": 90.48, "elapsed_time": "13:37:06", "remaining_time": "1:25:58"}
{"current_steps": 3650, "total_steps": 4023, "loss": 0.4275, "lr": 5e-06, "epoch": 2.721849366144668, "percentage": 90.73, "elapsed_time": "13:39:18", "remaining_time": "1:23:43"}
{"current_steps": 3660, "total_steps": 4023, "loss": 0.4294, "lr": 5e-06, "epoch": 2.7293064876957494, "percentage": 90.98, "elapsed_time": "13:41:31", "remaining_time": "1:21:28"}
{"current_steps": 3670, "total_steps": 4023, "loss": 0.4274, "lr": 5e-06, "epoch": 2.7367636092468306, "percentage": 91.23, "elapsed_time": "13:43:43", "remaining_time": "1:19:13"}
{"current_steps": 3680, "total_steps": 4023, "loss": 0.4184, "lr": 5e-06, "epoch": 2.744220730797912, "percentage": 91.47, "elapsed_time": "13:45:56", "remaining_time": "1:16:58"}
{"current_steps": 3690, "total_steps": 4023, "loss": 0.4172, "lr": 5e-06, "epoch": 2.751677852348993, "percentage": 91.72, "elapsed_time": "13:48:08", "remaining_time": "1:14:44"}
{"current_steps": 3700, "total_steps": 4023, "loss": 0.4189, "lr": 5e-06, "epoch": 2.759134973900075, "percentage": 91.97, "elapsed_time": "13:50:21", "remaining_time": "1:12:29"}
{"current_steps": 3710, "total_steps": 4023, "loss": 0.4219, "lr": 5e-06, "epoch": 2.7665920954511556, "percentage": 92.22, "elapsed_time": "13:52:33", "remaining_time": "1:10:14"}
{"current_steps": 3720, "total_steps": 4023, "loss": 0.4199, "lr": 5e-06, "epoch": 2.7740492170022373, "percentage": 92.47, "elapsed_time": "13:54:46", "remaining_time": "1:07:59"}
{"current_steps": 3730, "total_steps": 4023, "loss": 0.417, "lr": 5e-06, "epoch": 2.7815063385533185, "percentage": 92.72, "elapsed_time": "13:56:58", "remaining_time": "1:05:44"}
{"current_steps": 3740, "total_steps": 4023, "loss": 0.4247, "lr": 5e-06, "epoch": 2.7889634601043998, "percentage": 92.97, "elapsed_time": "13:59:11", "remaining_time": "1:03:30"}
{"current_steps": 3750, "total_steps": 4023, "loss": 0.4185, "lr": 5e-06, "epoch": 2.796420581655481, "percentage": 93.21, "elapsed_time": "14:01:23", "remaining_time": "1:01:15"}
{"current_steps": 3760, "total_steps": 4023, "loss": 0.4289, "lr": 5e-06, "epoch": 2.8038777032065623, "percentage": 93.46, "elapsed_time": "14:03:36", "remaining_time": "0:59:00"}
{"current_steps": 3770, "total_steps": 4023, "loss": 0.4295, "lr": 5e-06, "epoch": 2.8113348247576435, "percentage": 93.71, "elapsed_time": "14:05:48", "remaining_time": "0:56:45"}
{"current_steps": 3780, "total_steps": 4023, "loss": 0.4278, "lr": 5e-06, "epoch": 2.8187919463087248, "percentage": 93.96, "elapsed_time": "14:08:01", "remaining_time": "0:54:30"}
{"current_steps": 3790, "total_steps": 4023, "loss": 0.4194, "lr": 5e-06, "epoch": 2.826249067859806, "percentage": 94.21, "elapsed_time": "14:10:13", "remaining_time": "0:52:16"}
{"current_steps": 3800, "total_steps": 4023, "loss": 0.4191, "lr": 5e-06, "epoch": 2.8337061894108873, "percentage": 94.46, "elapsed_time": "14:12:26", "remaining_time": "0:50:01"}
{"current_steps": 3810, "total_steps": 4023, "loss": 0.4249, "lr": 5e-06, "epoch": 2.841163310961969, "percentage": 94.71, "elapsed_time": "14:14:39", "remaining_time": "0:47:46"}
{"current_steps": 3820, "total_steps": 4023, "loss": 0.4141, "lr": 5e-06, "epoch": 2.8486204325130497, "percentage": 94.95, "elapsed_time": "14:16:51", "remaining_time": "0:45:32"}
{"current_steps": 3830, "total_steps": 4023, "loss": 0.4226, "lr": 5e-06, "epoch": 2.8560775540641314, "percentage": 95.2, "elapsed_time": "14:19:04", "remaining_time": "0:43:17"}
{"current_steps": 3840, "total_steps": 4023, "loss": 0.4237, "lr": 5e-06, "epoch": 2.8635346756152127, "percentage": 95.45, "elapsed_time": "14:21:16", "remaining_time": "0:41:02"}
{"current_steps": 3850, "total_steps": 4023, "loss": 0.4247, "lr": 5e-06, "epoch": 2.870991797166294, "percentage": 95.7, "elapsed_time": "14:23:28", "remaining_time": "0:38:48"}
{"current_steps": 3860, "total_steps": 4023, "loss": 0.4259, "lr": 5e-06, "epoch": 2.878448918717375, "percentage": 95.95, "elapsed_time": "14:25:41", "remaining_time": "0:36:33"}
{"current_steps": 3870, "total_steps": 4023, "loss": 0.4307, "lr": 5e-06, "epoch": 2.8859060402684564, "percentage": 96.2, "elapsed_time": "14:27:53", "remaining_time": "0:34:18"}
{"current_steps": 3880, "total_steps": 4023, "loss": 0.4302, "lr": 5e-06, "epoch": 2.8933631618195377, "percentage": 96.45, "elapsed_time": "14:30:06", "remaining_time": "0:32:04"}
{"current_steps": 3890, "total_steps": 4023, "loss": 0.4197, "lr": 5e-06, "epoch": 2.900820283370619, "percentage": 96.69, "elapsed_time": "14:32:18", "remaining_time": "0:29:49"}
{"current_steps": 3900, "total_steps": 4023, "loss": 0.4196, "lr": 5e-06, "epoch": 2.9082774049217, "percentage": 96.94, "elapsed_time": "14:34:31", "remaining_time": "0:27:34"}
{"current_steps": 3910, "total_steps": 4023, "loss": 0.4234, "lr": 5e-06, "epoch": 2.9157345264727814, "percentage": 97.19, "elapsed_time": "14:36:43", "remaining_time": "0:25:20"}
{"current_steps": 3920, "total_steps": 4023, "loss": 0.4155, "lr": 5e-06, "epoch": 2.9231916480238627, "percentage": 97.44, "elapsed_time": "14:38:56", "remaining_time": "0:23:05"}
{"current_steps": 3930, "total_steps": 4023, "loss": 0.4245, "lr": 5e-06, "epoch": 2.930648769574944, "percentage": 97.69, "elapsed_time": "14:41:08", "remaining_time": "0:20:51"}
{"current_steps": 3940, "total_steps": 4023, "loss": 0.4141, "lr": 5e-06, "epoch": 2.9381058911260256, "percentage": 97.94, "elapsed_time": "14:43:20", "remaining_time": "0:18:36"}
{"current_steps": 3950, "total_steps": 4023, "loss": 0.4111, "lr": 5e-06, "epoch": 2.9455630126771064, "percentage": 98.19, "elapsed_time": "14:45:33", "remaining_time": "0:16:21"}
{"current_steps": 3960, "total_steps": 4023, "loss": 0.413, "lr": 5e-06, "epoch": 2.953020134228188, "percentage": 98.43, "elapsed_time": "14:47:45", "remaining_time": "0:14:07"}
{"current_steps": 3970, "total_steps": 4023, "loss": 0.4254, "lr": 5e-06, "epoch": 2.9604772557792693, "percentage": 98.68, "elapsed_time": "14:49:57", "remaining_time": "0:11:52"}
{"current_steps": 3980, "total_steps": 4023, "loss": 0.4116, "lr": 5e-06, "epoch": 2.9679343773303506, "percentage": 98.93, "elapsed_time": "14:52:10", "remaining_time": "0:09:38"}
{"current_steps": 3990, "total_steps": 4023, "loss": 0.4188, "lr": 5e-06, "epoch": 2.975391498881432, "percentage": 99.18, "elapsed_time": "14:54:22", "remaining_time": "0:07:23"}
{"current_steps": 4000, "total_steps": 4023, "loss": 0.4393, "lr": 5e-06, "epoch": 2.982848620432513, "percentage": 99.43, "elapsed_time": "14:56:35", "remaining_time": "0:05:09"}
{"current_steps": 4010, "total_steps": 4023, "loss": 0.4298, "lr": 5e-06, "epoch": 2.9903057419835943, "percentage": 99.68, "elapsed_time": "14:58:47", "remaining_time": "0:02:54"}
{"current_steps": 4020, "total_steps": 4023, "loss": 0.4292, "lr": 5e-06, "epoch": 2.9977628635346756, "percentage": 99.93, "elapsed_time": "15:01:00", "remaining_time": "0:00:40"}
{"current_steps": 4023, "total_steps": 4023, "eval_loss": 0.5737335681915283, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "15:08:30", "remaining_time": "0:00:00"}
{"current_steps": 4023, "total_steps": 4023, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "15:09:54", "remaining_time": "0:00:00"}