oh_scale_x.125_compute_equal / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 88
a74468c verified
{"current_steps": 10, "total_steps": 4183, "loss": 1.0392, "lr": 5e-06, "epoch": 0.21220159151193635, "percentage": 0.24, "elapsed_time": "0:05:24", "remaining_time": "1 day, 13:34:26"}
{"current_steps": 20, "total_steps": 4183, "loss": 0.9332, "lr": 5e-06, "epoch": 0.4244031830238727, "percentage": 0.48, "elapsed_time": "0:10:42", "remaining_time": "1 day, 13:08:51"}
{"current_steps": 30, "total_steps": 4183, "loss": 0.8893, "lr": 5e-06, "epoch": 0.636604774535809, "percentage": 0.72, "elapsed_time": "0:15:59", "remaining_time": "1 day, 12:54:21"}
{"current_steps": 40, "total_steps": 4183, "loss": 0.8588, "lr": 5e-06, "epoch": 0.8488063660477454, "percentage": 0.96, "elapsed_time": "0:21:20", "remaining_time": "1 day, 12:50:19"}
{"current_steps": 47, "total_steps": 4183, "eval_loss": 0.8430517315864563, "epoch": 0.9973474801061007, "percentage": 1.12, "elapsed_time": "0:25:38", "remaining_time": "1 day, 13:36:51"}
{"current_steps": 50, "total_steps": 4183, "loss": 0.9067, "lr": 5e-06, "epoch": 1.0610079575596818, "percentage": 1.2, "elapsed_time": "0:28:21", "remaining_time": "1 day, 15:03:31"}
{"current_steps": 60, "total_steps": 4183, "loss": 0.7853, "lr": 5e-06, "epoch": 1.273209549071618, "percentage": 1.43, "elapsed_time": "0:33:39", "remaining_time": "1 day, 14:32:56"}
{"current_steps": 70, "total_steps": 4183, "loss": 0.7775, "lr": 5e-06, "epoch": 1.4854111405835544, "percentage": 1.67, "elapsed_time": "0:38:57", "remaining_time": "1 day, 14:09:24"}
{"current_steps": 80, "total_steps": 4183, "loss": 0.7712, "lr": 5e-06, "epoch": 1.6976127320954908, "percentage": 1.91, "elapsed_time": "0:44:17", "remaining_time": "1 day, 13:51:17"}
{"current_steps": 90, "total_steps": 4183, "loss": 0.7685, "lr": 5e-06, "epoch": 1.909814323607427, "percentage": 2.15, "elapsed_time": "0:49:36", "remaining_time": "1 day, 13:36:15"}
{"current_steps": 94, "total_steps": 4183, "eval_loss": 0.8077705502510071, "epoch": 1.9946949602122017, "percentage": 2.25, "elapsed_time": "0:52:22", "remaining_time": "1 day, 13:58:09"}
{"current_steps": 100, "total_steps": 4183, "loss": 0.7936, "lr": 5e-06, "epoch": 2.1220159151193636, "percentage": 2.39, "elapsed_time": "0:56:42", "remaining_time": "1 day, 14:35:08"}
{"current_steps": 110, "total_steps": 4183, "loss": 0.704, "lr": 5e-06, "epoch": 2.3342175066313, "percentage": 2.63, "elapsed_time": "1:01:58", "remaining_time": "1 day, 14:14:52"}
{"current_steps": 120, "total_steps": 4183, "loss": 0.7011, "lr": 5e-06, "epoch": 2.546419098143236, "percentage": 2.87, "elapsed_time": "1:07:15", "remaining_time": "1 day, 13:57:26"}
{"current_steps": 130, "total_steps": 4183, "loss": 0.7046, "lr": 5e-06, "epoch": 2.7586206896551726, "percentage": 3.11, "elapsed_time": "1:12:32", "remaining_time": "1 day, 13:41:44"}
{"current_steps": 140, "total_steps": 4183, "loss": 0.7039, "lr": 5e-06, "epoch": 2.970822281167109, "percentage": 3.35, "elapsed_time": "1:17:52", "remaining_time": "1 day, 13:28:55"}
{"current_steps": 141, "total_steps": 4183, "eval_loss": 0.8061403036117554, "epoch": 2.9920424403183024, "percentage": 3.37, "elapsed_time": "1:19:06", "remaining_time": "1 day, 13:47:49"}
{"current_steps": 150, "total_steps": 4183, "loss": 0.7147, "lr": 5e-06, "epoch": 3.183023872679045, "percentage": 3.59, "elapsed_time": "1:25:01", "remaining_time": "1 day, 14:06:11"}
{"current_steps": 160, "total_steps": 4183, "loss": 0.6462, "lr": 5e-06, "epoch": 3.3952254641909816, "percentage": 3.83, "elapsed_time": "1:30:21", "remaining_time": "1 day, 13:51:58"}
{"current_steps": 170, "total_steps": 4183, "loss": 0.6433, "lr": 5e-06, "epoch": 3.6074270557029178, "percentage": 4.06, "elapsed_time": "1:35:41", "remaining_time": "1 day, 13:38:45"}
{"current_steps": 180, "total_steps": 4183, "loss": 0.6431, "lr": 5e-06, "epoch": 3.819628647214854, "percentage": 4.3, "elapsed_time": "1:41:00", "remaining_time": "1 day, 13:26:13"}
{"current_steps": 188, "total_steps": 4183, "eval_loss": 0.8146327137947083, "epoch": 3.9893899204244034, "percentage": 4.49, "elapsed_time": "1:46:01", "remaining_time": "1 day, 13:32:58"}
{"current_steps": 190, "total_steps": 4183, "loss": 0.6923, "lr": 5e-06, "epoch": 4.031830238726791, "percentage": 4.54, "elapsed_time": "1:48:09", "remaining_time": "1 day, 13:52:53"}
{"current_steps": 200, "total_steps": 4183, "loss": 0.5978, "lr": 5e-06, "epoch": 4.244031830238727, "percentage": 4.78, "elapsed_time": "1:53:28", "remaining_time": "1 day, 13:39:45"}
{"current_steps": 210, "total_steps": 4183, "loss": 0.5998, "lr": 5e-06, "epoch": 4.456233421750663, "percentage": 5.02, "elapsed_time": "1:58:46", "remaining_time": "1 day, 13:27:11"}
{"current_steps": 220, "total_steps": 4183, "loss": 0.5999, "lr": 5e-06, "epoch": 4.6684350132626, "percentage": 5.26, "elapsed_time": "2:04:06", "remaining_time": "1 day, 13:15:45"}
{"current_steps": 230, "total_steps": 4183, "loss": 0.6047, "lr": 5e-06, "epoch": 4.880636604774535, "percentage": 5.5, "elapsed_time": "2:09:27", "remaining_time": "1 day, 13:04:52"}
{"current_steps": 235, "total_steps": 4183, "eval_loss": 0.8365211486816406, "epoch": 4.986737400530504, "percentage": 5.62, "elapsed_time": "2:12:53", "remaining_time": "1 day, 13:12:29"}
{"current_steps": 240, "total_steps": 4183, "loss": 0.6357, "lr": 5e-06, "epoch": 5.092838196286472, "percentage": 5.74, "elapsed_time": "2:16:34", "remaining_time": "1 day, 13:23:52"}
{"current_steps": 250, "total_steps": 4183, "loss": 0.5495, "lr": 5e-06, "epoch": 5.305039787798409, "percentage": 5.98, "elapsed_time": "2:21:55", "remaining_time": "1 day, 13:12:45"}
{"current_steps": 260, "total_steps": 4183, "loss": 0.5492, "lr": 5e-06, "epoch": 5.517241379310345, "percentage": 6.22, "elapsed_time": "2:27:16", "remaining_time": "1 day, 13:02:13"}
{"current_steps": 270, "total_steps": 4183, "loss": 0.5516, "lr": 5e-06, "epoch": 5.729442970822281, "percentage": 6.45, "elapsed_time": "2:32:37", "remaining_time": "1 day, 12:51:54"}
{"current_steps": 280, "total_steps": 4183, "loss": 0.5574, "lr": 5e-06, "epoch": 5.941644562334218, "percentage": 6.69, "elapsed_time": "2:37:57", "remaining_time": "1 day, 12:41:53"}
{"current_steps": 282, "total_steps": 4183, "eval_loss": 0.8701170086860657, "epoch": 5.984084880636605, "percentage": 6.74, "elapsed_time": "2:39:53", "remaining_time": "1 day, 12:51:52"}
{"current_steps": 290, "total_steps": 4183, "loss": 0.5594, "lr": 5e-06, "epoch": 6.153846153846154, "percentage": 6.93, "elapsed_time": "2:45:06", "remaining_time": "1 day, 12:56:29"}
{"current_steps": 300, "total_steps": 4183, "loss": 0.4983, "lr": 5e-06, "epoch": 6.36604774535809, "percentage": 7.17, "elapsed_time": "2:50:25", "remaining_time": "1 day, 12:45:48"}
{"current_steps": 310, "total_steps": 4183, "loss": 0.5038, "lr": 5e-06, "epoch": 6.5782493368700266, "percentage": 7.41, "elapsed_time": "2:55:46", "remaining_time": "1 day, 12:35:57"}
{"current_steps": 320, "total_steps": 4183, "loss": 0.5092, "lr": 5e-06, "epoch": 6.790450928381963, "percentage": 7.65, "elapsed_time": "3:01:05", "remaining_time": "1 day, 12:26:08"}
{"current_steps": 329, "total_steps": 4183, "eval_loss": 0.8984044790267944, "epoch": 6.981432360742706, "percentage": 7.87, "elapsed_time": "3:06:45", "remaining_time": "1 day, 12:27:44"}
{"current_steps": 330, "total_steps": 4183, "loss": 0.552, "lr": 5e-06, "epoch": 7.002652519893899, "percentage": 7.89, "elapsed_time": "3:08:13", "remaining_time": "1 day, 12:37:42"}
{"current_steps": 340, "total_steps": 4183, "loss": 0.4509, "lr": 5e-06, "epoch": 7.2148541114058355, "percentage": 8.13, "elapsed_time": "3:13:31", "remaining_time": "1 day, 12:27:20"}
{"current_steps": 350, "total_steps": 4183, "loss": 0.448, "lr": 5e-06, "epoch": 7.427055702917772, "percentage": 8.37, "elapsed_time": "3:18:50", "remaining_time": "1 day, 12:17:36"}
{"current_steps": 360, "total_steps": 4183, "loss": 0.4496, "lr": 5e-06, "epoch": 7.639257294429708, "percentage": 8.61, "elapsed_time": "3:24:08", "remaining_time": "1 day, 12:07:52"}
{"current_steps": 370, "total_steps": 4183, "loss": 0.4572, "lr": 5e-06, "epoch": 7.8514588859416445, "percentage": 8.85, "elapsed_time": "3:29:23", "remaining_time": "1 day, 11:57:55"}
{"current_steps": 377, "total_steps": 4183, "eval_loss": 0.9556245803833008, "epoch": 8.0, "percentage": 9.01, "elapsed_time": "3:33:29", "remaining_time": "1 day, 11:55:19"}
{"current_steps": 380, "total_steps": 4183, "loss": 0.4809, "lr": 5e-06, "epoch": 8.063660477453581, "percentage": 9.08, "elapsed_time": "3:36:21", "remaining_time": "1 day, 12:05:14"}
{"current_steps": 390, "total_steps": 4183, "loss": 0.3978, "lr": 5e-06, "epoch": 8.275862068965518, "percentage": 9.32, "elapsed_time": "3:41:39", "remaining_time": "1 day, 11:55:49"}
{"current_steps": 400, "total_steps": 4183, "loss": 0.3968, "lr": 5e-06, "epoch": 8.488063660477454, "percentage": 9.56, "elapsed_time": "3:46:56", "remaining_time": "1 day, 11:46:20"}
{"current_steps": 410, "total_steps": 4183, "loss": 0.3981, "lr": 5e-06, "epoch": 8.70026525198939, "percentage": 9.8, "elapsed_time": "3:52:16", "remaining_time": "1 day, 11:37:29"}
{"current_steps": 420, "total_steps": 4183, "loss": 0.4085, "lr": 5e-06, "epoch": 8.912466843501326, "percentage": 10.04, "elapsed_time": "3:57:35", "remaining_time": "1 day, 11:28:42"}
{"current_steps": 424, "total_steps": 4183, "eval_loss": 1.0192773342132568, "epoch": 8.9973474801061, "percentage": 10.14, "elapsed_time": "4:00:19", "remaining_time": "1 day, 11:30:35"}
{"current_steps": 430, "total_steps": 4183, "loss": 0.4024, "lr": 5e-06, "epoch": 9.124668435013263, "percentage": 10.28, "elapsed_time": "4:04:42", "remaining_time": "1 day, 11:35:50"}
{"current_steps": 440, "total_steps": 4183, "loss": 0.3435, "lr": 5e-06, "epoch": 9.3368700265252, "percentage": 10.52, "elapsed_time": "4:10:03", "remaining_time": "1 day, 11:27:09"}
{"current_steps": 450, "total_steps": 4183, "loss": 0.3426, "lr": 5e-06, "epoch": 9.549071618037136, "percentage": 10.76, "elapsed_time": "4:15:23", "remaining_time": "1 day, 11:18:38"}
{"current_steps": 460, "total_steps": 4183, "loss": 0.3466, "lr": 5e-06, "epoch": 9.761273209549072, "percentage": 11.0, "elapsed_time": "4:20:44", "remaining_time": "1 day, 11:10:15"}
{"current_steps": 470, "total_steps": 4183, "loss": 0.349, "lr": 5e-06, "epoch": 9.973474801061007, "percentage": 11.24, "elapsed_time": "4:26:04", "remaining_time": "1 day, 11:01:56"}
{"current_steps": 471, "total_steps": 4183, "eval_loss": 1.1014161109924316, "epoch": 9.994694960212202, "percentage": 11.26, "elapsed_time": "4:27:14", "remaining_time": "1 day, 11:06:10"}
{"current_steps": 480, "total_steps": 4183, "loss": 0.3269, "lr": 5e-06, "epoch": 10.185676392572944, "percentage": 11.48, "elapsed_time": "4:33:13", "remaining_time": "1 day, 11:07:48"}
{"current_steps": 490, "total_steps": 4183, "loss": 0.2895, "lr": 5e-06, "epoch": 10.39787798408488, "percentage": 11.71, "elapsed_time": "4:38:33", "remaining_time": "1 day, 10:59:25"}
{"current_steps": 500, "total_steps": 4183, "loss": 0.2906, "lr": 5e-06, "epoch": 10.610079575596817, "percentage": 11.95, "elapsed_time": "4:43:54", "remaining_time": "1 day, 10:51:14"}
{"current_steps": 510, "total_steps": 4183, "loss": 0.2917, "lr": 5e-06, "epoch": 10.822281167108754, "percentage": 12.19, "elapsed_time": "4:49:12", "remaining_time": "1 day, 10:42:52"}
{"current_steps": 518, "total_steps": 4183, "eval_loss": 1.1841471195220947, "epoch": 10.992042440318302, "percentage": 12.38, "elapsed_time": "4:54:09", "remaining_time": "1 day, 10:41:17"}
{"current_steps": 520, "total_steps": 4183, "loss": 0.3088, "lr": 5e-06, "epoch": 11.03448275862069, "percentage": 12.43, "elapsed_time": "4:56:21", "remaining_time": "1 day, 10:47:35"}
{"current_steps": 530, "total_steps": 4183, "loss": 0.2394, "lr": 5e-06, "epoch": 11.246684350132625, "percentage": 12.67, "elapsed_time": "5:01:40", "remaining_time": "1 day, 10:39:13"}
{"current_steps": 540, "total_steps": 4183, "loss": 0.2379, "lr": 5e-06, "epoch": 11.458885941644562, "percentage": 12.91, "elapsed_time": "5:07:00", "remaining_time": "1 day, 10:31:07"}
{"current_steps": 550, "total_steps": 4183, "loss": 0.2352, "lr": 5e-06, "epoch": 11.671087533156498, "percentage": 13.15, "elapsed_time": "5:12:19", "remaining_time": "1 day, 10:23:03"}
{"current_steps": 560, "total_steps": 4183, "loss": 0.2371, "lr": 5e-06, "epoch": 11.883289124668435, "percentage": 13.39, "elapsed_time": "5:17:39", "remaining_time": "1 day, 10:15:10"}
{"current_steps": 565, "total_steps": 4183, "eval_loss": 1.2766014337539673, "epoch": 11.989389920424403, "percentage": 13.51, "elapsed_time": "5:21:05", "remaining_time": "1 day, 10:16:05"}
{"current_steps": 570, "total_steps": 4183, "loss": 0.2351, "lr": 5e-06, "epoch": 12.095490716180372, "percentage": 13.63, "elapsed_time": "5:24:48", "remaining_time": "1 day, 10:18:49"}
{"current_steps": 580, "total_steps": 4183, "loss": 0.1892, "lr": 5e-06, "epoch": 12.307692307692308, "percentage": 13.87, "elapsed_time": "5:30:05", "remaining_time": "1 day, 10:10:35"}
{"current_steps": 590, "total_steps": 4183, "loss": 0.1891, "lr": 5e-06, "epoch": 12.519893899204243, "percentage": 14.1, "elapsed_time": "5:35:24", "remaining_time": "1 day, 10:02:36"}
{"current_steps": 600, "total_steps": 4183, "loss": 0.1946, "lr": 5e-06, "epoch": 12.73209549071618, "percentage": 14.34, "elapsed_time": "5:40:42", "remaining_time": "1 day, 9:54:37"}
{"current_steps": 610, "total_steps": 4183, "loss": 0.1947, "lr": 5e-06, "epoch": 12.944297082228116, "percentage": 14.58, "elapsed_time": "5:46:02", "remaining_time": "1 day, 9:46:53"}
{"current_steps": 612, "total_steps": 4183, "eval_loss": 1.4153589010238647, "epoch": 12.986737400530505, "percentage": 14.63, "elapsed_time": "5:47:54", "remaining_time": "1 day, 9:50:02"}
{"current_steps": 620, "total_steps": 4183, "loss": 0.181, "lr": 5e-06, "epoch": 13.156498673740053, "percentage": 14.82, "elapsed_time": "5:53:14", "remaining_time": "1 day, 9:50:00"}
{"current_steps": 630, "total_steps": 4183, "loss": 0.1524, "lr": 5e-06, "epoch": 13.36870026525199, "percentage": 15.06, "elapsed_time": "5:58:34", "remaining_time": "1 day, 9:42:16"}
{"current_steps": 640, "total_steps": 4183, "loss": 0.154, "lr": 5e-06, "epoch": 13.580901856763926, "percentage": 15.3, "elapsed_time": "6:03:53", "remaining_time": "1 day, 9:34:29"}
{"current_steps": 650, "total_steps": 4183, "loss": 0.1574, "lr": 5e-06, "epoch": 13.793103448275861, "percentage": 15.54, "elapsed_time": "6:09:12", "remaining_time": "1 day, 9:26:48"}
{"current_steps": 659, "total_steps": 4183, "eval_loss": 1.5164598226547241, "epoch": 13.984084880636605, "percentage": 15.75, "elapsed_time": "6:14:51", "remaining_time": "1 day, 9:24:33"}
{"current_steps": 660, "total_steps": 4183, "loss": 0.1685, "lr": 5e-06, "epoch": 14.005305039787798, "percentage": 15.78, "elapsed_time": "6:16:24", "remaining_time": "1 day, 9:29:11"}
{"current_steps": 670, "total_steps": 4183, "loss": 0.121, "lr": 5e-06, "epoch": 14.217506631299734, "percentage": 16.02, "elapsed_time": "6:21:44", "remaining_time": "1 day, 9:21:32"}
{"current_steps": 680, "total_steps": 4183, "loss": 0.1197, "lr": 5e-06, "epoch": 14.429708222811671, "percentage": 16.26, "elapsed_time": "6:27:03", "remaining_time": "1 day, 9:13:53"}
{"current_steps": 690, "total_steps": 4183, "loss": 0.1219, "lr": 5e-06, "epoch": 14.641909814323608, "percentage": 16.5, "elapsed_time": "6:32:22", "remaining_time": "1 day, 9:06:21"}
{"current_steps": 700, "total_steps": 4183, "loss": 0.1248, "lr": 5e-06, "epoch": 14.854111405835544, "percentage": 16.73, "elapsed_time": "6:37:40", "remaining_time": "1 day, 8:58:41"}
{"current_steps": 706, "total_steps": 4183, "eval_loss": 1.6125339269638062, "epoch": 14.981432360742705, "percentage": 16.88, "elapsed_time": "6:41:46", "remaining_time": "1 day, 8:58:40"}
{"current_steps": 710, "total_steps": 4183, "loss": 0.1246, "lr": 5e-06, "epoch": 15.066312997347481, "percentage": 16.97, "elapsed_time": "6:44:49", "remaining_time": "1 day, 9:00:14"}
{"current_steps": 720, "total_steps": 4183, "loss": 0.0923, "lr": 5e-06, "epoch": 15.278514588859416, "percentage": 17.21, "elapsed_time": "6:50:07", "remaining_time": "1 day, 8:52:33"}
{"current_steps": 730, "total_steps": 4183, "loss": 0.0942, "lr": 5e-06, "epoch": 15.490716180371352, "percentage": 17.45, "elapsed_time": "6:55:23", "remaining_time": "1 day, 8:44:52"}
{"current_steps": 740, "total_steps": 4183, "loss": 0.0932, "lr": 5e-06, "epoch": 15.702917771883289, "percentage": 17.69, "elapsed_time": "7:00:41", "remaining_time": "1 day, 8:37:18"}
{"current_steps": 750, "total_steps": 4183, "loss": 0.0949, "lr": 5e-06, "epoch": 15.915119363395226, "percentage": 17.93, "elapsed_time": "7:05:59", "remaining_time": "1 day, 8:29:53"}
{"current_steps": 754, "total_steps": 4183, "eval_loss": 1.7871086597442627, "epoch": 16.0, "percentage": 18.03, "elapsed_time": "7:08:32", "remaining_time": "1 day, 8:28:52"}
{"current_steps": 760, "total_steps": 4183, "loss": 0.085, "lr": 5e-06, "epoch": 16.127320954907162, "percentage": 18.17, "elapsed_time": "7:13:05", "remaining_time": "1 day, 8:30:35"}
{"current_steps": 770, "total_steps": 4183, "loss": 0.0696, "lr": 5e-06, "epoch": 16.339522546419097, "percentage": 18.41, "elapsed_time": "7:18:23", "remaining_time": "1 day, 8:23:09"}
{"current_steps": 780, "total_steps": 4183, "loss": 0.0718, "lr": 5e-06, "epoch": 16.551724137931036, "percentage": 18.65, "elapsed_time": "7:23:41", "remaining_time": "1 day, 8:15:44"}
{"current_steps": 790, "total_steps": 4183, "loss": 0.0735, "lr": 5e-06, "epoch": 16.76392572944297, "percentage": 18.89, "elapsed_time": "7:28:57", "remaining_time": "1 day, 8:08:14"}
{"current_steps": 800, "total_steps": 4183, "loss": 0.072, "lr": 5e-06, "epoch": 16.97612732095491, "percentage": 19.13, "elapsed_time": "7:34:14", "remaining_time": "1 day, 8:00:52"}
{"current_steps": 801, "total_steps": 4183, "eval_loss": 1.84310781955719, "epoch": 16.9973474801061, "percentage": 19.15, "elapsed_time": "7:35:21", "remaining_time": "1 day, 8:02:36"}
{"current_steps": 810, "total_steps": 4183, "loss": 0.0602, "lr": 5e-06, "epoch": 17.188328912466844, "percentage": 19.36, "elapsed_time": "7:41:26", "remaining_time": "1 day, 8:01:33"}
{"current_steps": 820, "total_steps": 4183, "loss": 0.0531, "lr": 5e-06, "epoch": 17.40053050397878, "percentage": 19.6, "elapsed_time": "7:46:47", "remaining_time": "1 day, 7:54:26"}
{"current_steps": 830, "total_steps": 4183, "loss": 0.0553, "lr": 5e-06, "epoch": 17.612732095490717, "percentage": 19.84, "elapsed_time": "7:52:08", "remaining_time": "1 day, 7:47:20"}
{"current_steps": 840, "total_steps": 4183, "loss": 0.0557, "lr": 5e-06, "epoch": 17.824933687002652, "percentage": 20.08, "elapsed_time": "7:57:30", "remaining_time": "1 day, 7:40:23"}
{"current_steps": 848, "total_steps": 4183, "eval_loss": 1.8931316137313843, "epoch": 17.9946949602122, "percentage": 20.27, "elapsed_time": "8:02:27", "remaining_time": "1 day, 7:37:24"}
{"current_steps": 850, "total_steps": 4183, "loss": 0.0588, "lr": 5e-06, "epoch": 18.03713527851459, "percentage": 20.32, "elapsed_time": "8:04:45", "remaining_time": "1 day, 7:40:48"}
{"current_steps": 860, "total_steps": 4183, "loss": 0.0431, "lr": 5e-06, "epoch": 18.249336870026525, "percentage": 20.56, "elapsed_time": "8:10:03", "remaining_time": "1 day, 7:33:32"}
{"current_steps": 870, "total_steps": 4183, "loss": 0.0448, "lr": 5e-06, "epoch": 18.46153846153846, "percentage": 20.8, "elapsed_time": "8:15:21", "remaining_time": "1 day, 7:26:20"}
{"current_steps": 880, "total_steps": 4183, "loss": 0.0459, "lr": 5e-06, "epoch": 18.6737400530504, "percentage": 21.04, "elapsed_time": "8:20:41", "remaining_time": "1 day, 7:19:19"}
{"current_steps": 890, "total_steps": 4183, "loss": 0.0476, "lr": 5e-06, "epoch": 18.885941644562333, "percentage": 21.28, "elapsed_time": "8:26:01", "remaining_time": "1 day, 7:12:16"}
{"current_steps": 895, "total_steps": 4183, "eval_loss": 1.883098840713501, "epoch": 18.9920424403183, "percentage": 21.4, "elapsed_time": "8:29:23", "remaining_time": "1 day, 7:11:23"}
{"current_steps": 900, "total_steps": 4183, "loss": 0.0489, "lr": 5e-06, "epoch": 19.09814323607427, "percentage": 21.52, "elapsed_time": "8:33:33", "remaining_time": "1 day, 7:13:20"}
{"current_steps": 910, "total_steps": 4183, "loss": 0.0356, "lr": 5e-06, "epoch": 19.310344827586206, "percentage": 21.75, "elapsed_time": "8:39:18", "remaining_time": "1 day, 7:07:49"}
{"current_steps": 920, "total_steps": 4183, "loss": 0.0394, "lr": 5e-06, "epoch": 19.522546419098145, "percentage": 21.99, "elapsed_time": "8:45:04", "remaining_time": "1 day, 7:02:18"}
{"current_steps": 930, "total_steps": 4183, "loss": 0.0385, "lr": 5e-06, "epoch": 19.73474801061008, "percentage": 22.23, "elapsed_time": "8:50:49", "remaining_time": "1 day, 6:56:45"}
{"current_steps": 940, "total_steps": 4183, "loss": 0.0389, "lr": 5e-06, "epoch": 19.946949602122015, "percentage": 22.47, "elapsed_time": "8:56:34", "remaining_time": "1 day, 6:51:12"}
{"current_steps": 942, "total_steps": 4183, "eval_loss": 2.0264878273010254, "epoch": 19.989389920424404, "percentage": 22.52, "elapsed_time": "8:58:33", "remaining_time": "1 day, 6:52:57"}
{"current_steps": 950, "total_steps": 4183, "loss": 0.0333, "lr": 5e-06, "epoch": 20.159151193633953, "percentage": 22.71, "elapsed_time": "9:04:07", "remaining_time": "1 day, 6:51:43"}
{"current_steps": 960, "total_steps": 4183, "loss": 0.0302, "lr": 5e-06, "epoch": 20.371352785145888, "percentage": 22.95, "elapsed_time": "9:09:26", "remaining_time": "1 day, 6:44:39"}
{"current_steps": 970, "total_steps": 4183, "loss": 0.0318, "lr": 5e-06, "epoch": 20.583554376657826, "percentage": 23.19, "elapsed_time": "9:14:46", "remaining_time": "1 day, 6:37:36"}
{"current_steps": 980, "total_steps": 4183, "loss": 0.0326, "lr": 5e-06, "epoch": 20.79575596816976, "percentage": 23.43, "elapsed_time": "9:20:05", "remaining_time": "1 day, 6:30:35"}
{"current_steps": 989, "total_steps": 4183, "eval_loss": 2.019073486328125, "epoch": 20.986737400530505, "percentage": 23.64, "elapsed_time": "9:25:40", "remaining_time": "1 day, 6:26:50"}
{"current_steps": 990, "total_steps": 4183, "loss": 0.0363, "lr": 5e-06, "epoch": 21.007957559681696, "percentage": 23.67, "elapsed_time": "9:27:25", "remaining_time": "1 day, 6:30:04"}
{"current_steps": 1000, "total_steps": 4183, "loss": 0.0253, "lr": 5e-06, "epoch": 21.220159151193634, "percentage": 23.91, "elapsed_time": "9:32:45", "remaining_time": "1 day, 6:23:06"}
{"current_steps": 1010, "total_steps": 4183, "loss": 0.0273, "lr": 5e-06, "epoch": 21.43236074270557, "percentage": 24.15, "elapsed_time": "9:38:05", "remaining_time": "1 day, 6:16:08"}
{"current_steps": 1020, "total_steps": 4183, "loss": 0.0288, "lr": 5e-06, "epoch": 21.644562334217508, "percentage": 24.38, "elapsed_time": "9:43:26", "remaining_time": "1 day, 6:09:15"}
{"current_steps": 1030, "total_steps": 4183, "loss": 0.0289, "lr": 5e-06, "epoch": 21.856763925729442, "percentage": 24.62, "elapsed_time": "9:48:47", "remaining_time": "1 day, 6:02:22"}
{"current_steps": 1036, "total_steps": 4183, "eval_loss": 2.077552318572998, "epoch": 21.984084880636605, "percentage": 24.77, "elapsed_time": "9:52:50", "remaining_time": "1 day, 6:00:51"}
{"current_steps": 1040, "total_steps": 4183, "loss": 0.0287, "lr": 5e-06, "epoch": 22.06896551724138, "percentage": 24.86, "elapsed_time": "9:55:58", "remaining_time": "1 day, 6:01:06"}
{"current_steps": 1050, "total_steps": 4183, "loss": 0.0215, "lr": 5e-06, "epoch": 22.281167108753316, "percentage": 25.1, "elapsed_time": "10:01:17", "remaining_time": "1 day, 5:54:08"}
{"current_steps": 1060, "total_steps": 4183, "loss": 0.0233, "lr": 5e-06, "epoch": 22.49336870026525, "percentage": 25.34, "elapsed_time": "10:06:36", "remaining_time": "1 day, 5:47:11"}
{"current_steps": 1070, "total_steps": 4183, "loss": 0.0243, "lr": 5e-06, "epoch": 22.70557029177719, "percentage": 25.58, "elapsed_time": "10:11:54", "remaining_time": "1 day, 5:40:15"}
{"current_steps": 1080, "total_steps": 4183, "loss": 0.0241, "lr": 5e-06, "epoch": 22.917771883289124, "percentage": 25.82, "elapsed_time": "10:17:14", "remaining_time": "1 day, 5:33:25"}
{"current_steps": 1083, "total_steps": 4183, "eval_loss": 2.1364665031433105, "epoch": 22.981432360742705, "percentage": 25.89, "elapsed_time": "10:19:44", "remaining_time": "1 day, 5:33:57"}
{"current_steps": 1090, "total_steps": 4183, "loss": 0.0222, "lr": 5e-06, "epoch": 23.129973474801062, "percentage": 26.06, "elapsed_time": "10:24:25", "remaining_time": "1 day, 5:31:52"}
{"current_steps": 1100, "total_steps": 4183, "loss": 0.0189, "lr": 5e-06, "epoch": 23.342175066312997, "percentage": 26.3, "elapsed_time": "10:29:45", "remaining_time": "1 day, 5:25:01"}
{"current_steps": 1110, "total_steps": 4183, "loss": 0.0202, "lr": 5e-06, "epoch": 23.554376657824935, "percentage": 26.54, "elapsed_time": "10:35:04", "remaining_time": "1 day, 5:18:11"}
{"current_steps": 1120, "total_steps": 4183, "loss": 0.0216, "lr": 5e-06, "epoch": 23.76657824933687, "percentage": 26.78, "elapsed_time": "10:40:24", "remaining_time": "1 day, 5:11:22"}
{"current_steps": 1130, "total_steps": 4183, "loss": 0.0224, "lr": 5e-06, "epoch": 23.978779840848805, "percentage": 27.01, "elapsed_time": "10:45:44", "remaining_time": "1 day, 5:04:38"}
{"current_steps": 1131, "total_steps": 4183, "eval_loss": 2.163296937942505, "epoch": 24.0, "percentage": 27.04, "elapsed_time": "10:46:41", "remaining_time": "1 day, 5:05:06"}
{"current_steps": 1140, "total_steps": 4183, "loss": 0.0182, "lr": 5e-06, "epoch": 24.190981432360743, "percentage": 27.25, "elapsed_time": "10:52:50", "remaining_time": "1 day, 5:02:38"}
{"current_steps": 1150, "total_steps": 4183, "loss": 0.0176, "lr": 5e-06, "epoch": 24.40318302387268, "percentage": 27.49, "elapsed_time": "10:58:10", "remaining_time": "1 day, 4:55:51"}
{"current_steps": 1160, "total_steps": 4183, "loss": 0.0186, "lr": 5e-06, "epoch": 24.615384615384617, "percentage": 27.73, "elapsed_time": "11:03:28", "remaining_time": "1 day, 4:49:03"}
{"current_steps": 1170, "total_steps": 4183, "loss": 0.0186, "lr": 5e-06, "epoch": 24.82758620689655, "percentage": 27.97, "elapsed_time": "11:08:48", "remaining_time": "1 day, 4:42:18"}
{"current_steps": 1178, "total_steps": 4183, "eval_loss": 2.14928936958313, "epoch": 24.9973474801061, "percentage": 28.16, "elapsed_time": "11:13:41", "remaining_time": "1 day, 4:38:32"}
{"current_steps": 1180, "total_steps": 4183, "loss": 0.0186, "lr": 5e-06, "epoch": 25.039787798408486, "percentage": 28.21, "elapsed_time": "11:16:04", "remaining_time": "1 day, 4:40:33"}
{"current_steps": 1190, "total_steps": 4183, "loss": 0.0138, "lr": 5e-06, "epoch": 25.251989389920425, "percentage": 28.45, "elapsed_time": "11:21:25", "remaining_time": "1 day, 4:33:51"}
{"current_steps": 1200, "total_steps": 4183, "loss": 0.0154, "lr": 5e-06, "epoch": 25.46419098143236, "percentage": 28.69, "elapsed_time": "11:26:45", "remaining_time": "1 day, 4:27:10"}
{"current_steps": 1210, "total_steps": 4183, "loss": 0.0165, "lr": 5e-06, "epoch": 25.676392572944298, "percentage": 28.93, "elapsed_time": "11:32:05", "remaining_time": "1 day, 4:20:29"}
{"current_steps": 1220, "total_steps": 4183, "loss": 0.0168, "lr": 5e-06, "epoch": 25.888594164456233, "percentage": 29.17, "elapsed_time": "11:37:27", "remaining_time": "1 day, 4:13:53"}
{"current_steps": 1225, "total_steps": 4183, "eval_loss": 2.188133955001831, "epoch": 25.9946949602122, "percentage": 29.29, "elapsed_time": "11:40:46", "remaining_time": "1 day, 4:12:09"}
{"current_steps": 1230, "total_steps": 4183, "loss": 0.0164, "lr": 5e-06, "epoch": 26.10079575596817, "percentage": 29.4, "elapsed_time": "11:44:42", "remaining_time": "1 day, 4:11:51"}
{"current_steps": 1240, "total_steps": 4183, "loss": 0.0146, "lr": 5e-06, "epoch": 26.312997347480106, "percentage": 29.64, "elapsed_time": "11:50:02", "remaining_time": "1 day, 4:05:12"}
{"current_steps": 1250, "total_steps": 4183, "loss": 0.0157, "lr": 5e-06, "epoch": 26.52519893899204, "percentage": 29.88, "elapsed_time": "11:55:23", "remaining_time": "1 day, 3:58:36"}
{"current_steps": 1260, "total_steps": 4183, "loss": 0.0161, "lr": 5e-06, "epoch": 26.73740053050398, "percentage": 30.12, "elapsed_time": "12:00:44", "remaining_time": "1 day, 3:52:01"}
{"current_steps": 1270, "total_steps": 4183, "loss": 0.0165, "lr": 5e-06, "epoch": 26.949602122015914, "percentage": 30.36, "elapsed_time": "12:06:05", "remaining_time": "1 day, 3:45:26"}
{"current_steps": 1272, "total_steps": 4183, "eval_loss": 2.211845636367798, "epoch": 26.9920424403183, "percentage": 30.41, "elapsed_time": "12:07:52", "remaining_time": "1 day, 3:45:44"}
{"current_steps": 1280, "total_steps": 4183, "loss": 0.0143, "lr": 5e-06, "epoch": 27.161803713527853, "percentage": 30.6, "elapsed_time": "12:13:21", "remaining_time": "1 day, 3:43:12"}
{"current_steps": 1290, "total_steps": 4183, "loss": 0.0137, "lr": 5e-06, "epoch": 27.374005305039788, "percentage": 30.84, "elapsed_time": "12:18:40", "remaining_time": "1 day, 3:36:34"}
{"current_steps": 1300, "total_steps": 4183, "loss": 0.0143, "lr": 5e-06, "epoch": 27.586206896551722, "percentage": 31.08, "elapsed_time": "12:23:58", "remaining_time": "1 day, 3:29:55"}
{"current_steps": 1310, "total_steps": 4183, "loss": 0.0149, "lr": 5e-06, "epoch": 27.79840848806366, "percentage": 31.32, "elapsed_time": "12:29:18", "remaining_time": "1 day, 3:23:20"}
{"current_steps": 1319, "total_steps": 4183, "eval_loss": 2.1889731884002686, "epoch": 27.989389920424404, "percentage": 31.53, "elapsed_time": "12:34:52", "remaining_time": "1 day, 3:19:05"}
{"current_steps": 1320, "total_steps": 4183, "loss": 0.0161, "lr": 5e-06, "epoch": 28.010610079575596, "percentage": 31.56, "elapsed_time": "12:36:34", "remaining_time": "1 day, 3:20:57"}
{"current_steps": 1330, "total_steps": 4183, "loss": 0.0119, "lr": 5e-06, "epoch": 28.222811671087534, "percentage": 31.8, "elapsed_time": "12:41:53", "remaining_time": "1 day, 3:14:21"}
{"current_steps": 1340, "total_steps": 4183, "loss": 0.0127, "lr": 5e-06, "epoch": 28.43501326259947, "percentage": 32.03, "elapsed_time": "12:47:13", "remaining_time": "1 day, 3:07:46"}
{"current_steps": 1350, "total_steps": 4183, "loss": 0.0136, "lr": 5e-06, "epoch": 28.647214854111407, "percentage": 32.27, "elapsed_time": "12:52:33", "remaining_time": "1 day, 3:01:13"}
{"current_steps": 1360, "total_steps": 4183, "loss": 0.0138, "lr": 5e-06, "epoch": 28.859416445623342, "percentage": 32.51, "elapsed_time": "12:57:52", "remaining_time": "1 day, 2:54:39"}
{"current_steps": 1366, "total_steps": 4183, "eval_loss": 2.2227890491485596, "epoch": 28.986737400530505, "percentage": 32.66, "elapsed_time": "13:01:51", "remaining_time": "1 day, 2:52:22"}
{"current_steps": 1370, "total_steps": 4183, "loss": 0.0139, "lr": 5e-06, "epoch": 29.071618037135277, "percentage": 32.75, "elapsed_time": "13:05:09", "remaining_time": "1 day, 2:52:09"}
{"current_steps": 1380, "total_steps": 4183, "loss": 0.011, "lr": 5e-06, "epoch": 29.283819628647215, "percentage": 32.99, "elapsed_time": "13:10:28", "remaining_time": "1 day, 2:45:34"}
{"current_steps": 1390, "total_steps": 4183, "loss": 0.0116, "lr": 5e-06, "epoch": 29.49602122015915, "percentage": 33.23, "elapsed_time": "13:15:46", "remaining_time": "1 day, 2:38:59"}
{"current_steps": 1400, "total_steps": 4183, "loss": 0.0121, "lr": 5e-06, "epoch": 29.70822281167109, "percentage": 33.47, "elapsed_time": "13:21:04", "remaining_time": "1 day, 2:32:25"}
{"current_steps": 1410, "total_steps": 4183, "loss": 0.0124, "lr": 5e-06, "epoch": 29.920424403183024, "percentage": 33.71, "elapsed_time": "13:26:23", "remaining_time": "1 day, 2:25:53"}
{"current_steps": 1413, "total_steps": 4183, "eval_loss": 2.2380588054656982, "epoch": 29.984084880636605, "percentage": 33.78, "elapsed_time": "13:28:48", "remaining_time": "1 day, 2:25:34"}
{"current_steps": 1420, "total_steps": 4183, "loss": 0.0106, "lr": 5e-06, "epoch": 30.132625994694962, "percentage": 33.95, "elapsed_time": "13:33:37", "remaining_time": "1 day, 2:23:07"}
{"current_steps": 1430, "total_steps": 4183, "loss": 0.009, "lr": 5e-06, "epoch": 30.344827586206897, "percentage": 34.19, "elapsed_time": "13:38:54", "remaining_time": "1 day, 2:16:31"}
{"current_steps": 1440, "total_steps": 4183, "loss": 0.0093, "lr": 5e-06, "epoch": 30.55702917771883, "percentage": 34.43, "elapsed_time": "13:44:11", "remaining_time": "1 day, 2:09:58"}
{"current_steps": 1450, "total_steps": 4183, "loss": 0.0095, "lr": 5e-06, "epoch": 30.76923076923077, "percentage": 34.66, "elapsed_time": "13:49:29", "remaining_time": "1 day, 2:03:26"}
{"current_steps": 1460, "total_steps": 4183, "loss": 0.0099, "lr": 5e-06, "epoch": 30.981432360742705, "percentage": 34.9, "elapsed_time": "13:54:48", "remaining_time": "1 day, 1:56:57"}
{"current_steps": 1460, "total_steps": 4183, "eval_loss": 2.263244867324829, "epoch": 30.981432360742705, "percentage": 34.9, "elapsed_time": "13:55:43", "remaining_time": "1 day, 1:58:40"}
{"current_steps": 1470, "total_steps": 4183, "loss": 0.0083, "lr": 5e-06, "epoch": 31.193633952254643, "percentage": 35.14, "elapsed_time": "14:02:06", "remaining_time": "1 day, 1:54:10"}
{"current_steps": 1480, "total_steps": 4183, "loss": 0.008, "lr": 5e-06, "epoch": 31.405835543766578, "percentage": 35.38, "elapsed_time": "14:07:28", "remaining_time": "1 day, 1:47:47"}
{"current_steps": 1490, "total_steps": 4183, "loss": 0.0082, "lr": 5e-06, "epoch": 31.618037135278513, "percentage": 35.62, "elapsed_time": "14:12:50", "remaining_time": "1 day, 1:41:25"}
{"current_steps": 1500, "total_steps": 4183, "loss": 0.0082, "lr": 5e-06, "epoch": 31.83023872679045, "percentage": 35.86, "elapsed_time": "14:18:12", "remaining_time": "1 day, 1:35:03"}
{"current_steps": 1508, "total_steps": 4183, "eval_loss": 2.3144571781158447, "epoch": 32.0, "percentage": 36.05, "elapsed_time": "14:22:56", "remaining_time": "1 day, 1:30:45"}
{"current_steps": 1510, "total_steps": 4183, "loss": 0.0083, "lr": 5e-06, "epoch": 32.04244031830239, "percentage": 36.1, "elapsed_time": "14:25:27", "remaining_time": "1 day, 1:32:02"}
{"current_steps": 1520, "total_steps": 4183, "loss": 0.0066, "lr": 5e-06, "epoch": 32.254641909814325, "percentage": 36.34, "elapsed_time": "14:30:47", "remaining_time": "1 day, 1:25:36"}
{"current_steps": 1530, "total_steps": 4183, "loss": 0.0071, "lr": 5e-06, "epoch": 32.46684350132626, "percentage": 36.58, "elapsed_time": "14:36:08", "remaining_time": "1 day, 1:19:12"}
{"current_steps": 1540, "total_steps": 4183, "loss": 0.0071, "lr": 5e-06, "epoch": 32.679045092838194, "percentage": 36.82, "elapsed_time": "14:41:28", "remaining_time": "1 day, 1:12:48"}
{"current_steps": 1550, "total_steps": 4183, "loss": 0.0074, "lr": 5e-06, "epoch": 32.89124668435013, "percentage": 37.05, "elapsed_time": "14:46:48", "remaining_time": "1 day, 1:06:25"}
{"current_steps": 1555, "total_steps": 4183, "eval_loss": 2.3310482501983643, "epoch": 32.9973474801061, "percentage": 37.17, "elapsed_time": "14:50:04", "remaining_time": "1 day, 1:04:14"}
{"current_steps": 1560, "total_steps": 4183, "loss": 0.0069, "lr": 5e-06, "epoch": 33.10344827586207, "percentage": 37.29, "elapsed_time": "14:54:02", "remaining_time": "1 day, 1:03:14"}
{"current_steps": 1570, "total_steps": 4183, "loss": 0.0061, "lr": 5e-06, "epoch": 33.315649867374006, "percentage": 37.53, "elapsed_time": "14:59:22", "remaining_time": "1 day, 0:56:51"}
{"current_steps": 1580, "total_steps": 4183, "loss": 0.0063, "lr": 5e-06, "epoch": 33.52785145888594, "percentage": 37.77, "elapsed_time": "15:04:42", "remaining_time": "1 day, 0:50:28"}
{"current_steps": 1590, "total_steps": 4183, "loss": 0.0063, "lr": 5e-06, "epoch": 33.740053050397876, "percentage": 38.01, "elapsed_time": "15:10:02", "remaining_time": "1 day, 0:44:07"}
{"current_steps": 1600, "total_steps": 4183, "loss": 0.0063, "lr": 5e-06, "epoch": 33.95225464190982, "percentage": 38.25, "elapsed_time": "15:15:23", "remaining_time": "1 day, 0:37:47"}
{"current_steps": 1602, "total_steps": 4183, "eval_loss": 2.289428472518921, "epoch": 33.9946949602122, "percentage": 38.3, "elapsed_time": "15:17:05", "remaining_time": "1 day, 0:37:32"}
{"current_steps": 1610, "total_steps": 4183, "loss": 0.0058, "lr": 5e-06, "epoch": 34.16445623342175, "percentage": 38.49, "elapsed_time": "15:22:36", "remaining_time": "1 day, 0:34:27"}
{"current_steps": 1620, "total_steps": 4183, "loss": 0.0057, "lr": 5e-06, "epoch": 34.37665782493369, "percentage": 38.73, "elapsed_time": "15:27:54", "remaining_time": "1 day, 0:28:01"}
{"current_steps": 1630, "total_steps": 4183, "loss": 0.0059, "lr": 5e-06, "epoch": 34.58885941644562, "percentage": 38.97, "elapsed_time": "15:33:13", "remaining_time": "1 day, 0:21:40"}
{"current_steps": 1640, "total_steps": 4183, "loss": 0.0058, "lr": 5e-06, "epoch": 34.80106100795756, "percentage": 39.21, "elapsed_time": "15:38:33", "remaining_time": "1 day, 0:15:20"}
{"current_steps": 1649, "total_steps": 4183, "eval_loss": 2.308171033859253, "epoch": 34.9920424403183, "percentage": 39.42, "elapsed_time": "15:44:02", "remaining_time": "1 day, 0:10:41"}
{"current_steps": 1650, "total_steps": 4183, "loss": 0.006, "lr": 5e-06, "epoch": 35.0132625994695, "percentage": 39.45, "elapsed_time": "15:45:48", "remaining_time": "1 day, 0:11:56"}
{"current_steps": 1660, "total_steps": 4183, "loss": 0.0048, "lr": 5e-06, "epoch": 35.225464190981434, "percentage": 39.68, "elapsed_time": "15:51:05", "remaining_time": "1 day, 0:05:32"}
{"current_steps": 1670, "total_steps": 4183, "loss": 0.005, "lr": 5e-06, "epoch": 35.43766578249337, "percentage": 39.92, "elapsed_time": "15:56:23", "remaining_time": "23:59:09"}
{"current_steps": 1680, "total_steps": 4183, "loss": 0.005, "lr": 5e-06, "epoch": 35.649867374005304, "percentage": 40.16, "elapsed_time": "16:01:41", "remaining_time": "23:52:48"}
{"current_steps": 1690, "total_steps": 4183, "loss": 0.0051, "lr": 5e-06, "epoch": 35.86206896551724, "percentage": 40.4, "elapsed_time": "16:07:00", "remaining_time": "23:46:29"}
{"current_steps": 1696, "total_steps": 4183, "eval_loss": 2.328826904296875, "epoch": 35.9893899204244, "percentage": 40.55, "elapsed_time": "16:10:56", "remaining_time": "23:43:46"}
{"current_steps": 1700, "total_steps": 4183, "loss": 0.005, "lr": 5e-06, "epoch": 36.07427055702918, "percentage": 40.64, "elapsed_time": "16:14:11", "remaining_time": "23:42:54"}
{"current_steps": 1710, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 36.286472148541115, "percentage": 40.88, "elapsed_time": "16:19:30", "remaining_time": "23:36:33"}
{"current_steps": 1720, "total_steps": 4183, "loss": 0.0048, "lr": 5e-06, "epoch": 36.49867374005305, "percentage": 41.12, "elapsed_time": "16:24:48", "remaining_time": "23:30:13"}
{"current_steps": 1730, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 36.710875331564985, "percentage": 41.36, "elapsed_time": "16:30:07", "remaining_time": "23:23:55"}
{"current_steps": 1740, "total_steps": 4183, "loss": 0.0048, "lr": 5e-06, "epoch": 36.92307692307692, "percentage": 41.6, "elapsed_time": "16:35:27", "remaining_time": "23:17:38"}
{"current_steps": 1743, "total_steps": 4183, "eval_loss": 2.3886594772338867, "epoch": 36.9867374005305, "percentage": 41.67, "elapsed_time": "16:37:51", "remaining_time": "23:16:53"}
{"current_steps": 1750, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 37.13527851458886, "percentage": 41.84, "elapsed_time": "16:42:41", "remaining_time": "23:14:01"}
{"current_steps": 1760, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 37.3474801061008, "percentage": 42.08, "elapsed_time": "16:48:02", "remaining_time": "23:07:46"}
{"current_steps": 1770, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 37.55968169761273, "percentage": 42.31, "elapsed_time": "16:53:24", "remaining_time": "23:01:33"}
{"current_steps": 1780, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 37.771883289124666, "percentage": 42.55, "elapsed_time": "16:58:44", "remaining_time": "22:55:18"}
{"current_steps": 1790, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 37.98408488063661, "percentage": 42.79, "elapsed_time": "17:04:04", "remaining_time": "22:49:03"}
{"current_steps": 1790, "total_steps": 4183, "eval_loss": 2.3352954387664795, "epoch": 37.98408488063661, "percentage": 42.79, "elapsed_time": "17:04:55", "remaining_time": "22:50:11"}
{"current_steps": 1800, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 38.19628647214854, "percentage": 43.03, "elapsed_time": "17:11:42", "remaining_time": "22:45:52"}
{"current_steps": 1810, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 38.40848806366048, "percentage": 43.27, "elapsed_time": "17:17:21", "remaining_time": "22:40:01"}
{"current_steps": 1820, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 38.62068965517241, "percentage": 43.51, "elapsed_time": "17:22:59", "remaining_time": "22:34:10"}
{"current_steps": 1830, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 38.83289124668435, "percentage": 43.75, "elapsed_time": "17:28:37", "remaining_time": "22:28:18"}
{"current_steps": 1837, "total_steps": 4183, "eval_loss": 2.331439256668091, "epoch": 38.98143236074271, "percentage": 43.92, "elapsed_time": "17:33:32", "remaining_time": "22:25:27"}
{"current_steps": 1840, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 39.04509283819629, "percentage": 43.99, "elapsed_time": "17:36:14", "remaining_time": "22:24:58"}
{"current_steps": 1850, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 39.257294429708224, "percentage": 44.23, "elapsed_time": "17:41:35", "remaining_time": "22:18:45"}
{"current_steps": 1860, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 39.46949602122016, "percentage": 44.47, "elapsed_time": "17:46:56", "remaining_time": "22:12:31"}
{"current_steps": 1870, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 39.681697612732094, "percentage": 44.7, "elapsed_time": "17:52:15", "remaining_time": "22:06:15"}
{"current_steps": 1880, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 39.89389920424403, "percentage": 44.94, "elapsed_time": "17:57:34", "remaining_time": "22:00:02"}
{"current_steps": 1885, "total_steps": 4183, "eval_loss": 2.352881908416748, "epoch": 40.0, "percentage": 45.06, "elapsed_time": "18:00:40", "remaining_time": "21:57:27"}
{"current_steps": 1890, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 40.10610079575597, "percentage": 45.18, "elapsed_time": "18:04:41", "remaining_time": "21:55:58"}
{"current_steps": 1900, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 40.318302387267906, "percentage": 45.42, "elapsed_time": "18:10:01", "remaining_time": "21:49:45"}
{"current_steps": 1910, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 40.53050397877984, "percentage": 45.66, "elapsed_time": "18:15:22", "remaining_time": "21:43:33"}
{"current_steps": 1920, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 40.742705570291776, "percentage": 45.9, "elapsed_time": "18:20:40", "remaining_time": "21:37:18"}
{"current_steps": 1930, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 40.95490716180371, "percentage": 46.14, "elapsed_time": "18:26:00", "remaining_time": "21:31:06"}
{"current_steps": 1932, "total_steps": 4183, "eval_loss": 2.2959542274475098, "epoch": 40.9973474801061, "percentage": 46.19, "elapsed_time": "18:27:38", "remaining_time": "21:30:32"}
{"current_steps": 1940, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 41.16710875331565, "percentage": 46.38, "elapsed_time": "18:33:17", "remaining_time": "21:27:10"}
{"current_steps": 1950, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 41.37931034482759, "percentage": 46.62, "elapsed_time": "18:38:36", "remaining_time": "21:20:57"}
{"current_steps": 1960, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 41.59151193633952, "percentage": 46.86, "elapsed_time": "18:43:55", "remaining_time": "21:14:43"}
{"current_steps": 1970, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 41.80371352785146, "percentage": 47.1, "elapsed_time": "18:49:12", "remaining_time": "21:08:30"}
{"current_steps": 1979, "total_steps": 4183, "eval_loss": 2.2469534873962402, "epoch": 41.9946949602122, "percentage": 47.31, "elapsed_time": "18:54:36", "remaining_time": "21:03:36"}
{"current_steps": 1980, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 42.01591511936339, "percentage": 47.33, "elapsed_time": "18:56:26", "remaining_time": "21:04:26"}
{"current_steps": 1990, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 42.228116710875334, "percentage": 47.57, "elapsed_time": "19:01:44", "remaining_time": "20:58:12"}
{"current_steps": 2000, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 42.44031830238727, "percentage": 47.81, "elapsed_time": "19:07:01", "remaining_time": "20:51:58"}
{"current_steps": 2010, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 42.6525198938992, "percentage": 48.05, "elapsed_time": "19:12:20", "remaining_time": "20:45:46"}
{"current_steps": 2020, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 42.86472148541114, "percentage": 48.29, "elapsed_time": "19:17:38", "remaining_time": "20:39:35"}
{"current_steps": 2026, "total_steps": 4183, "eval_loss": 2.2444722652435303, "epoch": 42.9920424403183, "percentage": 48.43, "elapsed_time": "19:21:31", "remaining_time": "20:36:37"}
{"current_steps": 2030, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 43.07692307692308, "percentage": 48.53, "elapsed_time": "19:25:02", "remaining_time": "20:35:38"}
{"current_steps": 2040, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 43.289124668435015, "percentage": 48.77, "elapsed_time": "19:30:42", "remaining_time": "20:29:49"}
{"current_steps": 2050, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 43.50132625994695, "percentage": 49.01, "elapsed_time": "19:36:23", "remaining_time": "20:24:00"}
{"current_steps": 2060, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 43.713527851458885, "percentage": 49.25, "elapsed_time": "19:42:03", "remaining_time": "20:18:12"}
{"current_steps": 2070, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 43.92572944297082, "percentage": 49.49, "elapsed_time": "19:47:41", "remaining_time": "20:12:22"}
{"current_steps": 2073, "total_steps": 4183, "eval_loss": 2.185729503631592, "epoch": 43.9893899204244, "percentage": 49.56, "elapsed_time": "19:50:12", "remaining_time": "20:11:27"}
{"current_steps": 2080, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 44.13793103448276, "percentage": 49.73, "elapsed_time": "19:55:08", "remaining_time": "20:08:21"}
{"current_steps": 2090, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 44.350132625994696, "percentage": 49.96, "elapsed_time": "20:00:33", "remaining_time": "20:02:17"}
{"current_steps": 2100, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 44.56233421750663, "percentage": 50.2, "elapsed_time": "20:05:57", "remaining_time": "19:56:12"}
{"current_steps": 2110, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 44.774535809018566, "percentage": 50.44, "elapsed_time": "20:11:20", "remaining_time": "19:50:05"}
{"current_steps": 2120, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 44.9867374005305, "percentage": 50.68, "elapsed_time": "20:16:43", "remaining_time": "19:44:00"}
{"current_steps": 2120, "total_steps": 4183, "eval_loss": 2.2820541858673096, "epoch": 44.9867374005305, "percentage": 50.68, "elapsed_time": "20:17:32", "remaining_time": "19:44:48"}
{"current_steps": 2130, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 45.19893899204244, "percentage": 50.92, "elapsed_time": "20:23:56", "remaining_time": "19:39:41"}
{"current_steps": 2140, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 45.41114058355438, "percentage": 51.16, "elapsed_time": "20:29:15", "remaining_time": "19:33:32"}
{"current_steps": 2150, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 45.62334217506631, "percentage": 51.4, "elapsed_time": "20:34:32", "remaining_time": "19:27:21"}
{"current_steps": 2160, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 45.83554376657825, "percentage": 51.64, "elapsed_time": "20:39:49", "remaining_time": "19:21:11"}
{"current_steps": 2167, "total_steps": 4183, "eval_loss": 2.1947340965270996, "epoch": 45.98408488063661, "percentage": 51.8, "elapsed_time": "20:44:20", "remaining_time": "19:17:38"}
{"current_steps": 2170, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 46.04774535809018, "percentage": 51.88, "elapsed_time": "20:47:02", "remaining_time": "19:16:49"}
{"current_steps": 2180, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 46.259946949602124, "percentage": 52.12, "elapsed_time": "20:52:19", "remaining_time": "19:10:38"}
{"current_steps": 2190, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 46.47214854111406, "percentage": 52.35, "elapsed_time": "20:57:35", "remaining_time": "19:04:28"}
{"current_steps": 2200, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 46.684350132625994, "percentage": 52.59, "elapsed_time": "21:02:53", "remaining_time": "18:58:19"}
{"current_steps": 2210, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 46.89655172413793, "percentage": 52.83, "elapsed_time": "21:08:11", "remaining_time": "18:52:11"}
{"current_steps": 2214, "total_steps": 4183, "eval_loss": 2.244826316833496, "epoch": 46.98143236074271, "percentage": 52.93, "elapsed_time": "21:11:13", "remaining_time": "18:50:32"}
{"current_steps": 2220, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 47.10875331564987, "percentage": 53.07, "elapsed_time": "21:15:27", "remaining_time": "18:47:48"}
{"current_steps": 2230, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 47.320954907161806, "percentage": 53.31, "elapsed_time": "21:20:48", "remaining_time": "18:41:42"}
{"current_steps": 2240, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 47.53315649867374, "percentage": 53.55, "elapsed_time": "21:26:09", "remaining_time": "18:35:37"}
{"current_steps": 2250, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 47.745358090185675, "percentage": 53.79, "elapsed_time": "21:31:29", "remaining_time": "18:29:32"}
{"current_steps": 2260, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 47.95755968169761, "percentage": 54.03, "elapsed_time": "21:36:48", "remaining_time": "18:23:26"}
{"current_steps": 2262, "total_steps": 4183, "eval_loss": 2.2752280235290527, "epoch": 48.0, "percentage": 54.08, "elapsed_time": "21:38:16", "remaining_time": "18:22:33"}
{"current_steps": 2270, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 48.16976127320955, "percentage": 54.27, "elapsed_time": "21:43:56", "remaining_time": "18:18:52"}
{"current_steps": 2280, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 48.38196286472149, "percentage": 54.51, "elapsed_time": "21:49:17", "remaining_time": "18:12:48"}
{"current_steps": 2290, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 48.59416445623342, "percentage": 54.75, "elapsed_time": "21:54:37", "remaining_time": "18:06:43"}
{"current_steps": 2300, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 48.80636604774536, "percentage": 54.98, "elapsed_time": "21:59:56", "remaining_time": "18:00:37"}
{"current_steps": 2309, "total_steps": 4183, "eval_loss": 2.191987991333008, "epoch": 48.9973474801061, "percentage": 55.2, "elapsed_time": "22:05:20", "remaining_time": "17:55:39"}
{"current_steps": 2310, "total_steps": 4183, "loss": 0.0048, "lr": 5e-06, "epoch": 49.01856763925729, "percentage": 55.22, "elapsed_time": "22:07:16", "remaining_time": "17:56:11"}
{"current_steps": 2320, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 49.23076923076923, "percentage": 55.46, "elapsed_time": "22:12:53", "remaining_time": "17:50:20"}
{"current_steps": 2330, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 49.44297082228117, "percentage": 55.7, "elapsed_time": "22:18:31", "remaining_time": "17:44:30"}
{"current_steps": 2340, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 49.6551724137931, "percentage": 55.94, "elapsed_time": "22:24:07", "remaining_time": "17:38:38"}
{"current_steps": 2350, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 49.86737400530504, "percentage": 56.18, "elapsed_time": "22:29:43", "remaining_time": "17:32:47"}
{"current_steps": 2356, "total_steps": 4183, "eval_loss": 2.2768940925598145, "epoch": 49.9946949602122, "percentage": 56.32, "elapsed_time": "22:33:48", "remaining_time": "17:29:49"}
{"current_steps": 2360, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 50.07957559681697, "percentage": 56.42, "elapsed_time": "22:37:10", "remaining_time": "17:28:21"}
{"current_steps": 2370, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 50.291777188328915, "percentage": 56.66, "elapsed_time": "22:42:30", "remaining_time": "17:22:17"}
{"current_steps": 2380, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 50.50397877984085, "percentage": 56.9, "elapsed_time": "22:47:48", "remaining_time": "17:16:12"}
{"current_steps": 2390, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 50.716180371352785, "percentage": 57.14, "elapsed_time": "22:53:06", "remaining_time": "17:10:07"}
{"current_steps": 2400, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 50.92838196286472, "percentage": 57.38, "elapsed_time": "22:58:26", "remaining_time": "17:04:03"}
{"current_steps": 2403, "total_steps": 4183, "eval_loss": 2.144993305206299, "epoch": 50.9920424403183, "percentage": 57.45, "elapsed_time": "23:00:44", "remaining_time": "17:02:46"}
{"current_steps": 2410, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 51.14058355437666, "percentage": 57.61, "elapsed_time": "23:05:58", "remaining_time": "16:59:38"}
{"current_steps": 2420, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 51.352785145888596, "percentage": 57.85, "elapsed_time": "23:11:36", "remaining_time": "16:53:48"}
{"current_steps": 2430, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 51.56498673740053, "percentage": 58.09, "elapsed_time": "23:17:14", "remaining_time": "16:47:58"}
{"current_steps": 2440, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 51.777188328912466, "percentage": 58.33, "elapsed_time": "23:22:53", "remaining_time": "16:42:08"}
{"current_steps": 2450, "total_steps": 4183, "loss": 0.0047, "lr": 5e-06, "epoch": 51.9893899204244, "percentage": 58.57, "elapsed_time": "23:28:32", "remaining_time": "16:36:19"}
{"current_steps": 2450, "total_steps": 4183, "eval_loss": 2.1438260078430176, "epoch": 51.9893899204244, "percentage": 58.57, "elapsed_time": "23:29:20", "remaining_time": "16:36:53"}
{"current_steps": 2460, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 52.20159151193634, "percentage": 58.81, "elapsed_time": "23:35:45", "remaining_time": "16:31:36"}
{"current_steps": 2470, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 52.41379310344828, "percentage": 59.05, "elapsed_time": "23:41:05", "remaining_time": "16:25:33"}
{"current_steps": 2480, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 52.62599469496021, "percentage": 59.29, "elapsed_time": "23:46:24", "remaining_time": "16:19:30"}
{"current_steps": 2490, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 52.83819628647215, "percentage": 59.53, "elapsed_time": "23:51:42", "remaining_time": "16:13:27"}
{"current_steps": 2497, "total_steps": 4183, "eval_loss": 2.208920955657959, "epoch": 52.9867374005305, "percentage": 59.69, "elapsed_time": "23:56:14", "remaining_time": "16:09:45"}
{"current_steps": 2500, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 53.05039787798408, "percentage": 59.77, "elapsed_time": "23:58:59", "remaining_time": "16:08:43"}
{"current_steps": 2510, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 53.262599469496024, "percentage": 60.0, "elapsed_time": "1 day, 0:04:19", "remaining_time": "16:02:41"}
{"current_steps": 2520, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 53.47480106100796, "percentage": 60.24, "elapsed_time": "1 day, 0:09:39", "remaining_time": "15:56:39"}
{"current_steps": 2530, "total_steps": 4183, "loss": 0.0045, "lr": 5e-06, "epoch": 53.687002652519894, "percentage": 60.48, "elapsed_time": "1 day, 0:14:59", "remaining_time": "15:50:38"}
{"current_steps": 2540, "total_steps": 4183, "loss": 0.0046, "lr": 5e-06, "epoch": 53.89920424403183, "percentage": 60.72, "elapsed_time": "1 day, 0:20:21", "remaining_time": "15:44:37"}
{"current_steps": 2544, "total_steps": 4183, "eval_loss": 2.123398542404175, "epoch": 53.98408488063661, "percentage": 60.82, "elapsed_time": "1 day, 0:23:20", "remaining_time": "15:42:46"}
{"current_steps": 2550, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 54.11140583554376, "percentage": 60.96, "elapsed_time": "1 day, 0:27:37", "remaining_time": "15:39:51"}
{"current_steps": 2560, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 54.323607427055705, "percentage": 61.2, "elapsed_time": "1 day, 0:32:58", "remaining_time": "15:33:50"}
{"current_steps": 2570, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 54.53580901856764, "percentage": 61.44, "elapsed_time": "1 day, 0:38:19", "remaining_time": "15:27:49"}
{"current_steps": 2580, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 54.748010610079575, "percentage": 61.68, "elapsed_time": "1 day, 0:43:41", "remaining_time": "15:21:50"}
{"current_steps": 2590, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 54.96021220159151, "percentage": 61.92, "elapsed_time": "1 day, 0:49:01", "remaining_time": "15:15:49"}
{"current_steps": 2591, "total_steps": 4183, "eval_loss": 2.098813533782959, "epoch": 54.98143236074271, "percentage": 61.94, "elapsed_time": "1 day, 0:50:27", "remaining_time": "15:15:47"}
{"current_steps": 2600, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 55.172413793103445, "percentage": 62.16, "elapsed_time": "1 day, 0:56:39", "remaining_time": "15:11:14"}
{"current_steps": 2610, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 55.38461538461539, "percentage": 62.4, "elapsed_time": "1 day, 1:02:20", "remaining_time": "15:05:25"}
{"current_steps": 2620, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 55.59681697612732, "percentage": 62.63, "elapsed_time": "1 day, 1:08:00", "remaining_time": "14:59:37"}
{"current_steps": 2630, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 55.80901856763926, "percentage": 62.87, "elapsed_time": "1 day, 1:13:41", "remaining_time": "14:53:49"}
{"current_steps": 2639, "total_steps": 4183, "eval_loss": 2.2261929512023926, "epoch": 56.0, "percentage": 63.09, "elapsed_time": "1 day, 1:19:16", "remaining_time": "14:48:52"}
{"current_steps": 2640, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 56.02122015915119, "percentage": 63.11, "elapsed_time": "1 day, 1:21:17", "remaining_time": "14:49:08"}
{"current_steps": 2650, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 56.23342175066313, "percentage": 63.35, "elapsed_time": "1 day, 1:27:01", "remaining_time": "14:43:21"}
{"current_steps": 2660, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 56.44562334217507, "percentage": 63.59, "elapsed_time": "1 day, 1:32:43", "remaining_time": "14:37:34"}
{"current_steps": 2670, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 56.657824933687, "percentage": 63.83, "elapsed_time": "1 day, 1:38:24", "remaining_time": "14:31:46"}
{"current_steps": 2680, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 56.87002652519894, "percentage": 64.07, "elapsed_time": "1 day, 1:44:06", "remaining_time": "14:25:57"}
{"current_steps": 2686, "total_steps": 4183, "eval_loss": 2.1829628944396973, "epoch": 56.9973474801061, "percentage": 64.21, "elapsed_time": "1 day, 1:48:10", "remaining_time": "14:22:51"}
{"current_steps": 2690, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 57.08222811671087, "percentage": 64.31, "elapsed_time": "1 day, 1:51:43", "remaining_time": "14:21:14"}
{"current_steps": 2700, "total_steps": 4183, "loss": 0.0039, "lr": 5e-06, "epoch": 57.294429708222815, "percentage": 64.55, "elapsed_time": "1 day, 1:57:05", "remaining_time": "14:15:14"}
{"current_steps": 2710, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 57.50663129973475, "percentage": 64.79, "elapsed_time": "1 day, 2:02:28", "remaining_time": "14:09:16"}
{"current_steps": 2720, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 57.718832891246684, "percentage": 65.03, "elapsed_time": "1 day, 2:07:51", "remaining_time": "14:03:18"}
{"current_steps": 2730, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 57.93103448275862, "percentage": 65.26, "elapsed_time": "1 day, 2:13:12", "remaining_time": "13:57:19"}
{"current_steps": 2733, "total_steps": 4183, "eval_loss": 2.0565218925476074, "epoch": 57.9946949602122, "percentage": 65.34, "elapsed_time": "1 day, 2:15:28", "remaining_time": "13:55:52"}
{"current_steps": 2740, "total_steps": 4183, "loss": 0.0039, "lr": 5e-06, "epoch": 58.143236074270554, "percentage": 65.5, "elapsed_time": "1 day, 2:20:35", "remaining_time": "13:52:24"}
{"current_steps": 2750, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 58.355437665782496, "percentage": 65.74, "elapsed_time": "1 day, 2:25:55", "remaining_time": "13:46:24"}
{"current_steps": 2760, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 58.56763925729443, "percentage": 65.98, "elapsed_time": "1 day, 2:31:15", "remaining_time": "13:40:25"}
{"current_steps": 2770, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 58.779840848806366, "percentage": 66.22, "elapsed_time": "1 day, 2:36:38", "remaining_time": "13:34:27"}
{"current_steps": 2780, "total_steps": 4183, "loss": 0.0044, "lr": 5e-06, "epoch": 58.9920424403183, "percentage": 66.46, "elapsed_time": "1 day, 2:42:00", "remaining_time": "13:28:29"}
{"current_steps": 2780, "total_steps": 4183, "eval_loss": 2.1349949836730957, "epoch": 58.9920424403183, "percentage": 66.46, "elapsed_time": "1 day, 2:42:43", "remaining_time": "13:28:51"}
{"current_steps": 2790, "total_steps": 4183, "loss": 0.0039, "lr": 5e-06, "epoch": 59.204244031830235, "percentage": 66.7, "elapsed_time": "1 day, 2:49:22", "remaining_time": "13:23:32"}
{"current_steps": 2800, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 59.41644562334218, "percentage": 66.94, "elapsed_time": "1 day, 2:54:45", "remaining_time": "13:17:34"}
{"current_steps": 2810, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 59.62864721485411, "percentage": 67.18, "elapsed_time": "1 day, 3:00:10", "remaining_time": "13:11:38"}
{"current_steps": 2820, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 59.84084880636605, "percentage": 67.42, "elapsed_time": "1 day, 3:05:36", "remaining_time": "13:05:42"}
{"current_steps": 2827, "total_steps": 4183, "eval_loss": 2.147503137588501, "epoch": 59.9893899204244, "percentage": 67.58, "elapsed_time": "1 day, 3:10:10", "remaining_time": "13:01:55"}
{"current_steps": 2830, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 60.05305039787798, "percentage": 67.65, "elapsed_time": "1 day, 3:13:04", "remaining_time": "13:00:45"}
{"current_steps": 2840, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 60.265251989389924, "percentage": 67.89, "elapsed_time": "1 day, 3:18:22", "remaining_time": "12:54:45"}
{"current_steps": 2850, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 60.47745358090186, "percentage": 68.13, "elapsed_time": "1 day, 3:23:39", "remaining_time": "12:48:46"}
{"current_steps": 2860, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 60.689655172413794, "percentage": 68.37, "elapsed_time": "1 day, 3:28:59", "remaining_time": "12:42:47"}
{"current_steps": 2870, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 60.90185676392573, "percentage": 68.61, "elapsed_time": "1 day, 3:34:17", "remaining_time": "12:36:49"}
{"current_steps": 2874, "total_steps": 4183, "eval_loss": 2.1589598655700684, "epoch": 60.9867374005305, "percentage": 68.71, "elapsed_time": "1 day, 3:37:13", "remaining_time": "12:34:48"}
{"current_steps": 2880, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 61.11405835543766, "percentage": 68.85, "elapsed_time": "1 day, 3:41:35", "remaining_time": "12:31:45"}
{"current_steps": 2890, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 61.326259946949605, "percentage": 69.09, "elapsed_time": "1 day, 3:46:55", "remaining_time": "12:25:47"}
{"current_steps": 2900, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 61.53846153846154, "percentage": 69.33, "elapsed_time": "1 day, 3:52:14", "remaining_time": "12:19:49"}
{"current_steps": 2910, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 61.750663129973475, "percentage": 69.57, "elapsed_time": "1 day, 3:57:34", "remaining_time": "12:13:51"}
{"current_steps": 2920, "total_steps": 4183, "loss": 0.0039, "lr": 5e-06, "epoch": 61.96286472148541, "percentage": 69.81, "elapsed_time": "1 day, 4:02:55", "remaining_time": "12:07:55"}
{"current_steps": 2921, "total_steps": 4183, "eval_loss": 2.175154209136963, "epoch": 61.98408488063661, "percentage": 69.83, "elapsed_time": "1 day, 4:04:18", "remaining_time": "12:07:41"}
{"current_steps": 2930, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 62.175066312997345, "percentage": 70.05, "elapsed_time": "1 day, 4:10:13", "remaining_time": "12:02:49"}
{"current_steps": 2940, "total_steps": 4183, "loss": 0.0041, "lr": 5e-06, "epoch": 62.38726790450929, "percentage": 70.28, "elapsed_time": "1 day, 4:15:33", "remaining_time": "11:56:51"}
{"current_steps": 2950, "total_steps": 4183, "loss": 0.0042, "lr": 5e-06, "epoch": 62.59946949602122, "percentage": 70.52, "elapsed_time": "1 day, 4:20:52", "remaining_time": "11:50:54"}
{"current_steps": 2960, "total_steps": 4183, "loss": 0.0043, "lr": 5e-06, "epoch": 62.811671087533156, "percentage": 70.76, "elapsed_time": "1 day, 4:26:13", "remaining_time": "11:44:58"}
{"current_steps": 2968, "total_steps": 4183, "eval_loss": 2.0755813121795654, "epoch": 62.98143236074271, "percentage": 70.95, "elapsed_time": "1 day, 4:31:24", "remaining_time": "11:40:35"}
{"current_steps": 2970, "total_steps": 4183, "loss": 0.0048, "lr": 5e-06, "epoch": 63.02387267904509, "percentage": 71.0, "elapsed_time": "1 day, 4:33:34", "remaining_time": "11:39:51"}
{"current_steps": 2980, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 63.236074270557026, "percentage": 71.24, "elapsed_time": "1 day, 4:39:10", "remaining_time": "11:34:00"}
{"current_steps": 2990, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 63.44827586206897, "percentage": 71.48, "elapsed_time": "1 day, 4:44:47", "remaining_time": "11:28:11"}
{"current_steps": 3000, "total_steps": 4183, "loss": 0.004, "lr": 5e-06, "epoch": 63.6604774535809, "percentage": 71.72, "elapsed_time": "1 day, 4:50:21", "remaining_time": "11:22:20"}
{"current_steps": 3010, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 63.87267904509284, "percentage": 71.96, "elapsed_time": "1 day, 4:55:52", "remaining_time": "11:16:28"}
{"current_steps": 3016, "total_steps": 4183, "eval_loss": 2.1628966331481934, "epoch": 64.0, "percentage": 72.1, "elapsed_time": "1 day, 4:59:40", "remaining_time": "11:13:08"}
{"current_steps": 3020, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 64.08488063660478, "percentage": 72.2, "elapsed_time": "1 day, 5:03:08", "remaining_time": "11:11:17"}
{"current_steps": 3030, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 64.29708222811671, "percentage": 72.44, "elapsed_time": "1 day, 5:08:29", "remaining_time": "11:05:21"}
{"current_steps": 3040, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 64.50928381962865, "percentage": 72.68, "elapsed_time": "1 day, 5:13:50", "remaining_time": "10:59:25"}
{"current_steps": 3050, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 64.72148541114058, "percentage": 72.91, "elapsed_time": "1 day, 5:19:13", "remaining_time": "10:53:30"}
{"current_steps": 3060, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 64.93368700265252, "percentage": 73.15, "elapsed_time": "1 day, 5:24:35", "remaining_time": "10:47:35"}
{"current_steps": 3063, "total_steps": 4183, "eval_loss": 2.1522464752197266, "epoch": 64.9973474801061, "percentage": 73.22, "elapsed_time": "1 day, 5:26:49", "remaining_time": "10:46:02"}
{"current_steps": 3070, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 65.14588859416446, "percentage": 73.39, "elapsed_time": "1 day, 5:31:58", "remaining_time": "10:42:24"}
{"current_steps": 3080, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 65.35809018567639, "percentage": 73.63, "elapsed_time": "1 day, 5:37:20", "remaining_time": "10:36:29"}
{"current_steps": 3090, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 65.57029177718833, "percentage": 73.87, "elapsed_time": "1 day, 5:42:42", "remaining_time": "10:30:34"}
{"current_steps": 3100, "total_steps": 4183, "loss": 0.0038, "lr": 5e-06, "epoch": 65.78249336870026, "percentage": 74.11, "elapsed_time": "1 day, 5:48:05", "remaining_time": "10:24:40"}
{"current_steps": 3110, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 65.9946949602122, "percentage": 74.35, "elapsed_time": "1 day, 5:53:26", "remaining_time": "10:18:46"}
{"current_steps": 3110, "total_steps": 4183, "eval_loss": 2.1448707580566406, "epoch": 65.9946949602122, "percentage": 74.35, "elapsed_time": "1 day, 5:54:05", "remaining_time": "10:18:59"}
{"current_steps": 3120, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 66.20689655172414, "percentage": 74.59, "elapsed_time": "1 day, 6:00:48", "remaining_time": "10:13:32"}
{"current_steps": 3130, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 66.41909814323607, "percentage": 74.83, "elapsed_time": "1 day, 6:06:09", "remaining_time": "10:07:37"}
{"current_steps": 3140, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 66.63129973474801, "percentage": 75.07, "elapsed_time": "1 day, 6:11:32", "remaining_time": "10:01:43"}
{"current_steps": 3150, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 66.84350132625995, "percentage": 75.3, "elapsed_time": "1 day, 6:16:54", "remaining_time": "9:55:49"}
{"current_steps": 3157, "total_steps": 4183, "eval_loss": 2.1888883113861084, "epoch": 66.9920424403183, "percentage": 75.47, "elapsed_time": "1 day, 6:21:23", "remaining_time": "9:51:56"}
{"current_steps": 3160, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 67.05570291777188, "percentage": 75.54, "elapsed_time": "1 day, 6:24:11", "remaining_time": "9:50:33"}
{"current_steps": 3170, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 67.26790450928382, "percentage": 75.78, "elapsed_time": "1 day, 6:29:32", "remaining_time": "9:44:38"}
{"current_steps": 3180, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 67.48010610079575, "percentage": 76.02, "elapsed_time": "1 day, 6:34:54", "remaining_time": "9:38:44"}
{"current_steps": 3190, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 67.6923076923077, "percentage": 76.26, "elapsed_time": "1 day, 6:40:14", "remaining_time": "9:32:50"}
{"current_steps": 3200, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 67.90450928381964, "percentage": 76.5, "elapsed_time": "1 day, 6:45:35", "remaining_time": "9:26:56"}
{"current_steps": 3204, "total_steps": 4183, "eval_loss": 2.02482271194458, "epoch": 67.9893899204244, "percentage": 76.6, "elapsed_time": "1 day, 6:48:29", "remaining_time": "9:24:49"}
{"current_steps": 3210, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 68.11671087533156, "percentage": 76.74, "elapsed_time": "1 day, 6:52:49", "remaining_time": "9:21:37"}
{"current_steps": 3220, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 68.3289124668435, "percentage": 76.98, "elapsed_time": "1 day, 6:58:09", "remaining_time": "9:15:43"}
{"current_steps": 3230, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 68.54111405835543, "percentage": 77.22, "elapsed_time": "1 day, 7:03:28", "remaining_time": "9:09:48"}
{"current_steps": 3240, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 68.75331564986737, "percentage": 77.46, "elapsed_time": "1 day, 7:08:49", "remaining_time": "9:03:55"}
{"current_steps": 3250, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 68.96551724137932, "percentage": 77.7, "elapsed_time": "1 day, 7:14:09", "remaining_time": "8:58:01"}
{"current_steps": 3251, "total_steps": 4183, "eval_loss": 2.153766632080078, "epoch": 68.9867374005305, "percentage": 77.72, "elapsed_time": "1 day, 7:15:29", "remaining_time": "8:57:40"}
{"current_steps": 3260, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 69.17771883289124, "percentage": 77.93, "elapsed_time": "1 day, 7:21:22", "remaining_time": "8:52:40"}
{"current_steps": 3270, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 69.38992042440319, "percentage": 78.17, "elapsed_time": "1 day, 7:26:40", "remaining_time": "8:46:46"}
{"current_steps": 3280, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 69.60212201591511, "percentage": 78.41, "elapsed_time": "1 day, 7:31:59", "remaining_time": "8:40:52"}
{"current_steps": 3290, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 69.81432360742706, "percentage": 78.65, "elapsed_time": "1 day, 7:37:18", "remaining_time": "8:34:59"}
{"current_steps": 3298, "total_steps": 4183, "eval_loss": 2.120227336883545, "epoch": 69.9840848806366, "percentage": 78.84, "elapsed_time": "1 day, 7:42:25", "remaining_time": "8:30:30"}
{"current_steps": 3300, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 70.026525198939, "percentage": 78.89, "elapsed_time": "1 day, 7:44:36", "remaining_time": "8:29:37"}
{"current_steps": 3310, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 70.23872679045093, "percentage": 79.13, "elapsed_time": "1 day, 7:49:55", "remaining_time": "8:23:44"}
{"current_steps": 3320, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 70.45092838196287, "percentage": 79.37, "elapsed_time": "1 day, 7:55:14", "remaining_time": "8:17:50"}
{"current_steps": 3330, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 70.6631299734748, "percentage": 79.61, "elapsed_time": "1 day, 8:00:33", "remaining_time": "8:11:57"}
{"current_steps": 3340, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 70.87533156498674, "percentage": 79.85, "elapsed_time": "1 day, 8:05:52", "remaining_time": "8:06:04"}
{"current_steps": 3345, "total_steps": 4183, "eval_loss": 2.0325770378112793, "epoch": 70.9814323607427, "percentage": 79.97, "elapsed_time": "1 day, 8:09:26", "remaining_time": "8:03:22"}
{"current_steps": 3350, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 71.08753315649868, "percentage": 80.09, "elapsed_time": "1 day, 8:13:05", "remaining_time": "8:00:40"}
{"current_steps": 3360, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.29973474801061, "percentage": 80.33, "elapsed_time": "1 day, 8:18:24", "remaining_time": "7:54:47"}
{"current_steps": 3370, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.51193633952255, "percentage": 80.56, "elapsed_time": "1 day, 8:23:43", "remaining_time": "7:48:54"}
{"current_steps": 3380, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.72413793103448, "percentage": 80.8, "elapsed_time": "1 day, 8:29:02", "remaining_time": "7:43:02"}
{"current_steps": 3390, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.93633952254642, "percentage": 81.04, "elapsed_time": "1 day, 8:34:21", "remaining_time": "7:37:10"}
{"current_steps": 3393, "total_steps": 4183, "eval_loss": 2.136025905609131, "epoch": 72.0, "percentage": 81.11, "elapsed_time": "1 day, 8:36:22", "remaining_time": "7:35:30"}
{"current_steps": 3400, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 72.14854111405836, "percentage": 81.28, "elapsed_time": "1 day, 8:41:24", "remaining_time": "7:31:42"}
{"current_steps": 3410, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 72.36074270557029, "percentage": 81.52, "elapsed_time": "1 day, 8:46:41", "remaining_time": "7:25:49"}
{"current_steps": 3420, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 72.57294429708223, "percentage": 81.76, "elapsed_time": "1 day, 8:51:59", "remaining_time": "7:19:57"}
{"current_steps": 3430, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 72.78514588859416, "percentage": 82.0, "elapsed_time": "1 day, 8:57:18", "remaining_time": "7:14:05"}
{"current_steps": 3440, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 72.9973474801061, "percentage": 82.24, "elapsed_time": "1 day, 9:02:37", "remaining_time": "7:08:13"}
{"current_steps": 3440, "total_steps": 4183, "eval_loss": 2.140444278717041, "epoch": 72.9973474801061, "percentage": 82.24, "elapsed_time": "1 day, 9:03:12", "remaining_time": "7:08:20"}
{"current_steps": 3450, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 73.20954907161804, "percentage": 82.48, "elapsed_time": "1 day, 9:09:48", "remaining_time": "7:02:45"}
{"current_steps": 3460, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 73.42175066312997, "percentage": 82.72, "elapsed_time": "1 day, 9:15:07", "remaining_time": "6:56:53"}
{"current_steps": 3470, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 73.63395225464191, "percentage": 82.95, "elapsed_time": "1 day, 9:20:26", "remaining_time": "6:51:02"}
{"current_steps": 3480, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 73.84615384615384, "percentage": 83.19, "elapsed_time": "1 day, 9:25:45", "remaining_time": "6:45:11"}
{"current_steps": 3487, "total_steps": 4183, "eval_loss": 2.0650992393493652, "epoch": 73.9946949602122, "percentage": 83.36, "elapsed_time": "1 day, 9:30:06", "remaining_time": "6:41:12"}
{"current_steps": 3490, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.05835543766578, "percentage": 83.43, "elapsed_time": "1 day, 9:32:59", "remaining_time": "6:39:42"}
{"current_steps": 3500, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 74.27055702917772, "percentage": 83.67, "elapsed_time": "1 day, 9:38:19", "remaining_time": "6:33:51"}
{"current_steps": 3510, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.48275862068965, "percentage": 83.91, "elapsed_time": "1 day, 9:43:40", "remaining_time": "6:28:00"}
{"current_steps": 3520, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.6949602122016, "percentage": 84.15, "elapsed_time": "1 day, 9:49:01", "remaining_time": "6:22:10"}
{"current_steps": 3530, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.90716180371352, "percentage": 84.39, "elapsed_time": "1 day, 9:54:21", "remaining_time": "6:16:19"}
{"current_steps": 3534, "total_steps": 4183, "eval_loss": 2.0981507301330566, "epoch": 74.9920424403183, "percentage": 84.48, "elapsed_time": "1 day, 9:57:11", "remaining_time": "6:14:07"}
{"current_steps": 3540, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 75.11936339522546, "percentage": 84.63, "elapsed_time": "1 day, 10:01:37", "remaining_time": "6:10:50"}
{"current_steps": 3550, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 75.3315649867374, "percentage": 84.87, "elapsed_time": "1 day, 10:06:57", "remaining_time": "6:04:59"}
{"current_steps": 3560, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 75.54376657824933, "percentage": 85.11, "elapsed_time": "1 day, 10:12:19", "remaining_time": "5:59:09"}
{"current_steps": 3570, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 75.75596816976127, "percentage": 85.35, "elapsed_time": "1 day, 10:17:40", "remaining_time": "5:53:19"}
{"current_steps": 3580, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 75.96816976127322, "percentage": 85.58, "elapsed_time": "1 day, 10:23:01", "remaining_time": "5:47:29"}
{"current_steps": 3581, "total_steps": 4183, "eval_loss": 2.103228807449341, "epoch": 75.9893899204244, "percentage": 85.61, "elapsed_time": "1 day, 10:24:18", "remaining_time": "5:47:01"}
{"current_steps": 3590, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 76.18037135278514, "percentage": 85.82, "elapsed_time": "1 day, 10:30:38", "remaining_time": "5:42:01"}
{"current_steps": 3600, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 76.39257294429709, "percentage": 86.06, "elapsed_time": "1 day, 10:36:17", "remaining_time": "5:36:14"}
{"current_steps": 3610, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 76.60477453580901, "percentage": 86.3, "elapsed_time": "1 day, 10:41:55", "remaining_time": "5:30:27"}
{"current_steps": 3620, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 76.81697612732096, "percentage": 86.54, "elapsed_time": "1 day, 10:47:32", "remaining_time": "5:24:39"}
{"current_steps": 3628, "total_steps": 4183, "eval_loss": 2.1027870178222656, "epoch": 76.9867374005305, "percentage": 86.73, "elapsed_time": "1 day, 10:52:54", "remaining_time": "5:20:10"}
{"current_steps": 3630, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 77.0291777188329, "percentage": 86.78, "elapsed_time": "1 day, 10:55:06", "remaining_time": "5:19:10"}
{"current_steps": 3640, "total_steps": 4183, "loss": 0.0029, "lr": 5e-06, "epoch": 77.24137931034483, "percentage": 87.02, "elapsed_time": "1 day, 11:00:28", "remaining_time": "5:13:20"}
{"current_steps": 3650, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 77.45358090185677, "percentage": 87.26, "elapsed_time": "1 day, 11:05:51", "remaining_time": "5:07:30"}
{"current_steps": 3660, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 77.6657824933687, "percentage": 87.5, "elapsed_time": "1 day, 11:11:13", "remaining_time": "5:01:41"}
{"current_steps": 3670, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 77.87798408488064, "percentage": 87.74, "elapsed_time": "1 day, 11:16:35", "remaining_time": "4:55:51"}
{"current_steps": 3675, "total_steps": 4183, "eval_loss": 2.1281707286834717, "epoch": 77.9840848806366, "percentage": 87.86, "elapsed_time": "1 day, 11:20:07", "remaining_time": "4:53:04"}
{"current_steps": 3680, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 78.09018567639258, "percentage": 87.98, "elapsed_time": "1 day, 11:23:59", "remaining_time": "4:50:19"}
{"current_steps": 3690, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 78.3023872679045, "percentage": 88.21, "elapsed_time": "1 day, 11:29:23", "remaining_time": "4:44:29"}
{"current_steps": 3700, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 78.51458885941645, "percentage": 88.45, "elapsed_time": "1 day, 11:34:46", "remaining_time": "4:38:40"}
{"current_steps": 3710, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 78.72679045092838, "percentage": 88.69, "elapsed_time": "1 day, 11:40:10", "remaining_time": "4:32:51"}
{"current_steps": 3720, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 78.93899204244032, "percentage": 88.93, "elapsed_time": "1 day, 11:45:33", "remaining_time": "4:27:02"}
{"current_steps": 3722, "total_steps": 4183, "eval_loss": 2.0912187099456787, "epoch": 78.9814323607427, "percentage": 88.98, "elapsed_time": "1 day, 11:47:33", "remaining_time": "4:25:59"}
{"current_steps": 3730, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 79.15119363395226, "percentage": 89.17, "elapsed_time": "1 day, 11:53:00", "remaining_time": "4:21:28"}
{"current_steps": 3740, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 79.36339522546419, "percentage": 89.41, "elapsed_time": "1 day, 11:58:34", "remaining_time": "4:15:40"}
{"current_steps": 3750, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 79.57559681697613, "percentage": 89.65, "elapsed_time": "1 day, 12:04:11", "remaining_time": "4:09:53"}
{"current_steps": 3760, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 79.78779840848806, "percentage": 89.89, "elapsed_time": "1 day, 12:09:45", "remaining_time": "4:04:05"}
{"current_steps": 3770, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:13", "remaining_time": "3:58:17"}
{"current_steps": 3770, "total_steps": 4183, "eval_loss": 2.0766139030456543, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:49", "remaining_time": "3:58:21"}
{"current_steps": 3780, "total_steps": 4183, "loss": 0.003, "lr": 5e-06, "epoch": 80.21220159151194, "percentage": 90.37, "elapsed_time": "1 day, 12:22:40", "remaining_time": "3:52:42"}
{"current_steps": 3790, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 80.42440318302387, "percentage": 90.6, "elapsed_time": "1 day, 12:28:01", "remaining_time": "3:46:53"}
{"current_steps": 3800, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 80.63660477453581, "percentage": 90.84, "elapsed_time": "1 day, 12:33:22", "remaining_time": "3:41:04"}
{"current_steps": 3810, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 80.84880636604774, "percentage": 91.08, "elapsed_time": "1 day, 12:38:42", "remaining_time": "3:35:15"}
{"current_steps": 3817, "total_steps": 4183, "eval_loss": 2.028625011444092, "epoch": 80.9973474801061, "percentage": 91.25, "elapsed_time": "1 day, 12:43:02", "remaining_time": "3:31:14"}
{"current_steps": 3820, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 81.06100795755968, "percentage": 91.32, "elapsed_time": "1 day, 12:46:04", "remaining_time": "3:29:38"}
{"current_steps": 3830, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 81.27320954907162, "percentage": 91.56, "elapsed_time": "1 day, 12:51:22", "remaining_time": "3:23:49"}
{"current_steps": 3840, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 81.48541114058355, "percentage": 91.8, "elapsed_time": "1 day, 12:56:43", "remaining_time": "3:18:00"}
{"current_steps": 3850, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 81.6976127320955, "percentage": 92.04, "elapsed_time": "1 day, 13:02:03", "remaining_time": "3:12:11"}
{"current_steps": 3860, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 81.90981432360742, "percentage": 92.28, "elapsed_time": "1 day, 13:07:24", "remaining_time": "3:06:23"}
{"current_steps": 3864, "total_steps": 4183, "eval_loss": 2.042055606842041, "epoch": 81.9946949602122, "percentage": 92.37, "elapsed_time": "1 day, 13:10:11", "remaining_time": "3:04:07"}
{"current_steps": 3870, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 82.12201591511936, "percentage": 92.52, "elapsed_time": "1 day, 13:14:46", "remaining_time": "3:00:44"}
{"current_steps": 3880, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 82.3342175066313, "percentage": 92.76, "elapsed_time": "1 day, 13:20:09", "remaining_time": "2:54:56"}
{"current_steps": 3890, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 82.54641909814323, "percentage": 93.0, "elapsed_time": "1 day, 13:25:31", "remaining_time": "2:49:08"}
{"current_steps": 3900, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 82.75862068965517, "percentage": 93.23, "elapsed_time": "1 day, 13:30:53", "remaining_time": "2:43:20"}
{"current_steps": 3910, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 82.9708222811671, "percentage": 93.47, "elapsed_time": "1 day, 13:36:14", "remaining_time": "2:37:31"}
{"current_steps": 3911, "total_steps": 4183, "eval_loss": 2.1120784282684326, "epoch": 82.9920424403183, "percentage": 93.5, "elapsed_time": "1 day, 13:37:27", "remaining_time": "2:37:00"}
{"current_steps": 3920, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 83.18302387267904, "percentage": 93.71, "elapsed_time": "1 day, 13:43:29", "remaining_time": "2:31:51"}
{"current_steps": 3930, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 83.39522546419099, "percentage": 93.95, "elapsed_time": "1 day, 13:48:48", "remaining_time": "2:26:03"}
{"current_steps": 3940, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 83.60742705570291, "percentage": 94.19, "elapsed_time": "1 day, 13:54:08", "remaining_time": "2:20:15"}
{"current_steps": 3950, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 83.81962864721486, "percentage": 94.43, "elapsed_time": "1 day, 13:59:28", "remaining_time": "2:14:27"}
{"current_steps": 3958, "total_steps": 4183, "eval_loss": 2.0832369327545166, "epoch": 83.9893899204244, "percentage": 94.62, "elapsed_time": "1 day, 14:04:28", "remaining_time": "2:09:51"}
{"current_steps": 3960, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 84.03183023872678, "percentage": 94.67, "elapsed_time": "1 day, 14:06:49", "remaining_time": "2:08:46"}
{"current_steps": 3970, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 84.24403183023873, "percentage": 94.91, "elapsed_time": "1 day, 14:12:08", "remaining_time": "2:02:58"}
{"current_steps": 3980, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 84.45623342175067, "percentage": 95.15, "elapsed_time": "1 day, 14:17:29", "remaining_time": "1:57:11"}
{"current_steps": 3990, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 84.6684350132626, "percentage": 95.39, "elapsed_time": "1 day, 14:22:51", "remaining_time": "1:51:23"}
{"current_steps": 4000, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 84.88063660477454, "percentage": 95.63, "elapsed_time": "1 day, 14:28:12", "remaining_time": "1:45:36"}
{"current_steps": 4005, "total_steps": 4183, "eval_loss": 2.062901020050049, "epoch": 84.9867374005305, "percentage": 95.74, "elapsed_time": "1 day, 14:31:41", "remaining_time": "1:42:44"}
{"current_steps": 4010, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 85.09283819628648, "percentage": 95.86, "elapsed_time": "1 day, 14:35:32", "remaining_time": "1:39:53"}
{"current_steps": 4020, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 85.3050397877984, "percentage": 96.1, "elapsed_time": "1 day, 14:40:50", "remaining_time": "1:34:06"}
{"current_steps": 4030, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 85.51724137931035, "percentage": 96.34, "elapsed_time": "1 day, 14:46:09", "remaining_time": "1:28:18"}
{"current_steps": 4040, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 85.72944297082228, "percentage": 96.58, "elapsed_time": "1 day, 14:51:28", "remaining_time": "1:22:31"}
{"current_steps": 4050, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 85.94164456233422, "percentage": 96.82, "elapsed_time": "1 day, 14:56:47", "remaining_time": "1:16:44"}
{"current_steps": 4052, "total_steps": 4183, "eval_loss": 2.139768600463867, "epoch": 85.9840848806366, "percentage": 96.87, "elapsed_time": "1 day, 14:58:43", "remaining_time": "1:15:36"}
{"current_steps": 4060, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 86.15384615384616, "percentage": 97.06, "elapsed_time": "1 day, 15:04:01", "remaining_time": "1:11:00"}
{"current_steps": 4070, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 86.36604774535809, "percentage": 97.3, "elapsed_time": "1 day, 15:09:21", "remaining_time": "1:05:13"}
{"current_steps": 4080, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 86.57824933687003, "percentage": 97.54, "elapsed_time": "1 day, 15:14:39", "remaining_time": "0:59:26"}
{"current_steps": 4090, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 86.79045092838196, "percentage": 97.78, "elapsed_time": "1 day, 15:19:59", "remaining_time": "0:53:39"}
{"current_steps": 4099, "total_steps": 4183, "eval_loss": 2.1202690601348877, "epoch": 86.9814323607427, "percentage": 97.99, "elapsed_time": "1 day, 15:25:41", "remaining_time": "0:48:28"}
{"current_steps": 4100, "total_steps": 4183, "loss": 0.0037, "lr": 5e-06, "epoch": 87.0026525198939, "percentage": 98.02, "elapsed_time": "1 day, 15:27:11", "remaining_time": "0:47:55"}
{"current_steps": 4110, "total_steps": 4183, "loss": 0.0029, "lr": 5e-06, "epoch": 87.21485411140584, "percentage": 98.25, "elapsed_time": "1 day, 15:32:28", "remaining_time": "0:42:08"}
{"current_steps": 4120, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 87.42705570291777, "percentage": 98.49, "elapsed_time": "1 day, 15:37:47", "remaining_time": "0:36:21"}
{"current_steps": 4130, "total_steps": 4183, "loss": 0.003, "lr": 5e-06, "epoch": 87.63925729442971, "percentage": 98.73, "elapsed_time": "1 day, 15:43:06", "remaining_time": "0:30:34"}
{"current_steps": 4140, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 87.85145888594164, "percentage": 98.97, "elapsed_time": "1 day, 15:48:26", "remaining_time": "0:24:48"}
{"current_steps": 4147, "total_steps": 4183, "eval_loss": 2.1025404930114746, "epoch": 88.0, "percentage": 99.14, "elapsed_time": "1 day, 15:52:35", "remaining_time": "0:20:46"}
{"current_steps": 4150, "total_steps": 4183, "loss": 0.003, "lr": 5e-06, "epoch": 88.06366047745358, "percentage": 99.21, "elapsed_time": "1 day, 15:55:31", "remaining_time": "0:19:02"}
{"current_steps": 4160, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 88.27586206896552, "percentage": 99.45, "elapsed_time": "1 day, 16:00:50", "remaining_time": "0:13:16"}
{"current_steps": 4170, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 88.48806366047745, "percentage": 99.69, "elapsed_time": "1 day, 16:06:09", "remaining_time": "0:07:30"}
{"current_steps": 4180, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 88.70026525198939, "percentage": 99.93, "elapsed_time": "1 day, 16:11:27", "remaining_time": "0:01:43"}
{"current_steps": 4183, "total_steps": 4183, "eval_loss": 2.0839004516601562, "epoch": 88.76392572944297, "percentage": 100.0, "elapsed_time": "1 day, 16:15:01", "remaining_time": "0:00:00"}
{"current_steps": 4183, "total_steps": 4183, "epoch": 88.76392572944297, "percentage": 100.0, "elapsed_time": "1 day, 16:16:26", "remaining_time": "0:00:00"}