rommel_importgenius_4b8 / trainer_log.jsonl
sizhkhy's picture
Upload folder using huggingface_hub
4c9e042 verified
{"current_steps": 1, "total_steps": 595, "loss": 0.0776, "lr": 1.6666666666666667e-06, "epoch": 0.008368200836820083, "percentage": 0.17, "elapsed_time": "0:00:25", "remaining_time": "4:10:06"}
{"current_steps": 2, "total_steps": 595, "loss": 0.0663, "lr": 3.3333333333333333e-06, "epoch": 0.016736401673640166, "percentage": 0.34, "elapsed_time": "0:00:43", "remaining_time": "3:35:35"}
{"current_steps": 3, "total_steps": 595, "loss": 0.0666, "lr": 5e-06, "epoch": 0.02510460251046025, "percentage": 0.5, "elapsed_time": "0:00:59", "remaining_time": "3:17:10"}
{"current_steps": 4, "total_steps": 595, "loss": 0.0596, "lr": 6.666666666666667e-06, "epoch": 0.03347280334728033, "percentage": 0.67, "elapsed_time": "0:01:15", "remaining_time": "3:05:02"}
{"current_steps": 5, "total_steps": 595, "loss": 0.0672, "lr": 8.333333333333334e-06, "epoch": 0.04184100418410042, "percentage": 0.84, "elapsed_time": "0:01:29", "remaining_time": "2:56:42"}
{"current_steps": 5, "total_steps": 595, "eval_loss": 0.07553808391094208, "epoch": 0.04184100418410042, "percentage": 0.84, "elapsed_time": "0:01:39", "remaining_time": "3:16:36"}
{"current_steps": 6, "total_steps": 595, "loss": 0.0618, "lr": 1e-05, "epoch": 0.0502092050209205, "percentage": 1.01, "elapsed_time": "0:01:53", "remaining_time": "3:05:43"}
{"current_steps": 7, "total_steps": 595, "loss": 0.0529, "lr": 1.1666666666666668e-05, "epoch": 0.058577405857740586, "percentage": 1.18, "elapsed_time": "0:02:06", "remaining_time": "2:57:38"}
{"current_steps": 8, "total_steps": 595, "loss": 0.0519, "lr": 1.3333333333333333e-05, "epoch": 0.06694560669456066, "percentage": 1.34, "elapsed_time": "0:02:21", "remaining_time": "2:52:51"}
{"current_steps": 9, "total_steps": 595, "loss": 0.0494, "lr": 1.5e-05, "epoch": 0.07531380753138076, "percentage": 1.51, "elapsed_time": "0:02:34", "remaining_time": "2:47:56"}
{"current_steps": 10, "total_steps": 595, "loss": 0.0476, "lr": 1.6666666666666667e-05, "epoch": 0.08368200836820083, "percentage": 1.68, "elapsed_time": "0:02:48", "remaining_time": "2:44:32"}
{"current_steps": 10, "total_steps": 595, "eval_loss": 0.04517042636871338, "epoch": 0.08368200836820083, "percentage": 1.68, "elapsed_time": "0:02:56", "remaining_time": "2:52:31"}
{"current_steps": 11, "total_steps": 595, "loss": 0.0382, "lr": 1.8333333333333333e-05, "epoch": 0.09205020920502092, "percentage": 1.85, "elapsed_time": "0:03:09", "remaining_time": "2:47:53"}
{"current_steps": 12, "total_steps": 595, "loss": 0.0374, "lr": 2e-05, "epoch": 0.100418410041841, "percentage": 2.02, "elapsed_time": "0:03:24", "remaining_time": "2:45:15"}
{"current_steps": 13, "total_steps": 595, "loss": 0.0365, "lr": 2.1666666666666667e-05, "epoch": 0.1087866108786611, "percentage": 2.18, "elapsed_time": "0:03:39", "remaining_time": "2:43:30"}
{"current_steps": 14, "total_steps": 595, "loss": 0.0323, "lr": 2.3333333333333336e-05, "epoch": 0.11715481171548117, "percentage": 2.35, "elapsed_time": "0:03:52", "remaining_time": "2:41:04"}
{"current_steps": 15, "total_steps": 595, "loss": 0.0337, "lr": 2.5e-05, "epoch": 0.12552301255230125, "percentage": 2.52, "elapsed_time": "0:04:07", "remaining_time": "2:39:31"}
{"current_steps": 15, "total_steps": 595, "eval_loss": 0.03555193170905113, "epoch": 0.12552301255230125, "percentage": 2.52, "elapsed_time": "0:04:15", "remaining_time": "2:44:49"}
{"current_steps": 16, "total_steps": 595, "loss": 0.0336, "lr": 2.6666666666666667e-05, "epoch": 0.13389121338912133, "percentage": 2.69, "elapsed_time": "0:04:30", "remaining_time": "2:43:00"}
{"current_steps": 17, "total_steps": 595, "loss": 0.0303, "lr": 2.8333333333333335e-05, "epoch": 0.14225941422594143, "percentage": 2.86, "elapsed_time": "0:04:44", "remaining_time": "2:41:16"}
{"current_steps": 18, "total_steps": 595, "loss": 0.0303, "lr": 3e-05, "epoch": 0.1506276150627615, "percentage": 3.03, "elapsed_time": "0:05:01", "remaining_time": "2:41:11"}
{"current_steps": 19, "total_steps": 595, "loss": 0.0329, "lr": 3.1666666666666666e-05, "epoch": 0.1589958158995816, "percentage": 3.19, "elapsed_time": "0:05:17", "remaining_time": "2:40:11"}
{"current_steps": 20, "total_steps": 595, "loss": 0.0333, "lr": 3.3333333333333335e-05, "epoch": 0.16736401673640167, "percentage": 3.36, "elapsed_time": "0:05:30", "remaining_time": "2:38:21"}
{"current_steps": 20, "total_steps": 595, "eval_loss": 0.030791474506258965, "epoch": 0.16736401673640167, "percentage": 3.36, "elapsed_time": "0:05:38", "remaining_time": "2:42:19"}
{"current_steps": 21, "total_steps": 595, "loss": 0.0302, "lr": 3.5e-05, "epoch": 0.17573221757322174, "percentage": 3.53, "elapsed_time": "0:05:52", "remaining_time": "2:40:35"}
{"current_steps": 22, "total_steps": 595, "loss": 0.0293, "lr": 3.6666666666666666e-05, "epoch": 0.18410041841004185, "percentage": 3.7, "elapsed_time": "0:06:06", "remaining_time": "2:39:17"}
{"current_steps": 23, "total_steps": 595, "loss": 0.0276, "lr": 3.8333333333333334e-05, "epoch": 0.19246861924686193, "percentage": 3.87, "elapsed_time": "0:06:22", "remaining_time": "2:38:26"}
{"current_steps": 24, "total_steps": 595, "loss": 0.0255, "lr": 4e-05, "epoch": 0.200836820083682, "percentage": 4.03, "elapsed_time": "0:06:36", "remaining_time": "2:37:10"}
{"current_steps": 25, "total_steps": 595, "loss": 0.0258, "lr": 4.166666666666667e-05, "epoch": 0.20920502092050208, "percentage": 4.2, "elapsed_time": "0:06:49", "remaining_time": "2:35:43"}
{"current_steps": 25, "total_steps": 595, "eval_loss": 0.027234511449933052, "epoch": 0.20920502092050208, "percentage": 4.2, "elapsed_time": "0:06:58", "remaining_time": "2:38:51"}
{"current_steps": 26, "total_steps": 595, "loss": 0.0265, "lr": 4.3333333333333334e-05, "epoch": 0.2175732217573222, "percentage": 4.37, "elapsed_time": "0:07:11", "remaining_time": "2:37:29"}
{"current_steps": 27, "total_steps": 595, "loss": 0.0248, "lr": 4.5e-05, "epoch": 0.22594142259414227, "percentage": 4.54, "elapsed_time": "0:07:25", "remaining_time": "2:36:10"}
{"current_steps": 28, "total_steps": 595, "loss": 0.0233, "lr": 4.666666666666667e-05, "epoch": 0.23430962343096234, "percentage": 4.71, "elapsed_time": "0:07:41", "remaining_time": "2:35:35"}
{"current_steps": 29, "total_steps": 595, "loss": 0.025, "lr": 4.8333333333333334e-05, "epoch": 0.24267782426778242, "percentage": 4.87, "elapsed_time": "0:07:54", "remaining_time": "2:34:21"}
{"current_steps": 30, "total_steps": 595, "loss": 0.023, "lr": 5e-05, "epoch": 0.2510460251046025, "percentage": 5.04, "elapsed_time": "0:08:08", "remaining_time": "2:33:22"}
{"current_steps": 30, "total_steps": 595, "eval_loss": 0.025461601093411446, "epoch": 0.2510460251046025, "percentage": 5.04, "elapsed_time": "0:08:16", "remaining_time": "2:35:56"}
{"current_steps": 31, "total_steps": 595, "loss": 0.0225, "lr": 5.166666666666667e-05, "epoch": 0.2594142259414226, "percentage": 5.21, "elapsed_time": "0:08:29", "remaining_time": "2:34:34"}
{"current_steps": 32, "total_steps": 595, "loss": 0.0212, "lr": 5.333333333333333e-05, "epoch": 0.26778242677824265, "percentage": 5.38, "elapsed_time": "0:08:42", "remaining_time": "2:33:12"}
{"current_steps": 33, "total_steps": 595, "loss": 0.0223, "lr": 5.500000000000001e-05, "epoch": 0.27615062761506276, "percentage": 5.55, "elapsed_time": "0:08:56", "remaining_time": "2:32:09"}
{"current_steps": 34, "total_steps": 595, "loss": 0.024, "lr": 5.666666666666667e-05, "epoch": 0.28451882845188287, "percentage": 5.71, "elapsed_time": "0:09:10", "remaining_time": "2:31:19"}
{"current_steps": 35, "total_steps": 595, "loss": 0.0202, "lr": 5.833333333333334e-05, "epoch": 0.2928870292887029, "percentage": 5.88, "elapsed_time": "0:09:25", "remaining_time": "2:30:54"}
{"current_steps": 35, "total_steps": 595, "eval_loss": 0.023448586463928223, "epoch": 0.2928870292887029, "percentage": 5.88, "elapsed_time": "0:09:34", "remaining_time": "2:33:05"}
{"current_steps": 36, "total_steps": 595, "loss": 0.0214, "lr": 6e-05, "epoch": 0.301255230125523, "percentage": 6.05, "elapsed_time": "0:09:48", "remaining_time": "2:32:11"}
{"current_steps": 37, "total_steps": 595, "loss": 0.0175, "lr": 6.166666666666667e-05, "epoch": 0.30962343096234307, "percentage": 6.22, "elapsed_time": "0:10:02", "remaining_time": "2:31:27"}
{"current_steps": 38, "total_steps": 595, "loss": 0.0207, "lr": 6.333333333333333e-05, "epoch": 0.3179916317991632, "percentage": 6.39, "elapsed_time": "0:10:15", "remaining_time": "2:30:21"}
{"current_steps": 39, "total_steps": 595, "loss": 0.019, "lr": 6.500000000000001e-05, "epoch": 0.3263598326359833, "percentage": 6.55, "elapsed_time": "0:10:29", "remaining_time": "2:29:31"}
{"current_steps": 40, "total_steps": 595, "loss": 0.0188, "lr": 6.666666666666667e-05, "epoch": 0.33472803347280333, "percentage": 6.72, "elapsed_time": "0:10:44", "remaining_time": "2:28:55"}
{"current_steps": 40, "total_steps": 595, "eval_loss": 0.02175285294651985, "epoch": 0.33472803347280333, "percentage": 6.72, "elapsed_time": "0:10:52", "remaining_time": "2:30:50"}
{"current_steps": 41, "total_steps": 595, "loss": 0.0198, "lr": 6.833333333333333e-05, "epoch": 0.34309623430962344, "percentage": 6.89, "elapsed_time": "0:11:05", "remaining_time": "2:29:50"}
{"current_steps": 42, "total_steps": 595, "loss": 0.0214, "lr": 7e-05, "epoch": 0.3514644351464435, "percentage": 7.06, "elapsed_time": "0:11:19", "remaining_time": "2:29:06"}
{"current_steps": 43, "total_steps": 595, "loss": 0.0228, "lr": 7.166666666666667e-05, "epoch": 0.3598326359832636, "percentage": 7.23, "elapsed_time": "0:11:33", "remaining_time": "2:28:20"}
{"current_steps": 44, "total_steps": 595, "loss": 0.0201, "lr": 7.333333333333333e-05, "epoch": 0.3682008368200837, "percentage": 7.39, "elapsed_time": "0:11:48", "remaining_time": "2:27:49"}
{"current_steps": 45, "total_steps": 595, "loss": 0.0185, "lr": 7.500000000000001e-05, "epoch": 0.37656903765690375, "percentage": 7.56, "elapsed_time": "0:12:01", "remaining_time": "2:26:57"}
{"current_steps": 45, "total_steps": 595, "eval_loss": 0.02076469548046589, "epoch": 0.37656903765690375, "percentage": 7.56, "elapsed_time": "0:12:09", "remaining_time": "2:28:38"}
{"current_steps": 46, "total_steps": 595, "loss": 0.0175, "lr": 7.666666666666667e-05, "epoch": 0.38493723849372385, "percentage": 7.73, "elapsed_time": "0:12:23", "remaining_time": "2:27:50"}
{"current_steps": 47, "total_steps": 595, "loss": 0.0199, "lr": 7.833333333333333e-05, "epoch": 0.39330543933054396, "percentage": 7.9, "elapsed_time": "0:12:38", "remaining_time": "2:27:22"}
{"current_steps": 48, "total_steps": 595, "loss": 0.0178, "lr": 8e-05, "epoch": 0.401673640167364, "percentage": 8.07, "elapsed_time": "0:12:52", "remaining_time": "2:26:48"}
{"current_steps": 49, "total_steps": 595, "loss": 0.0168, "lr": 8.166666666666667e-05, "epoch": 0.4100418410041841, "percentage": 8.24, "elapsed_time": "0:13:07", "remaining_time": "2:26:12"}
{"current_steps": 50, "total_steps": 595, "loss": 0.0199, "lr": 8.333333333333334e-05, "epoch": 0.41841004184100417, "percentage": 8.4, "elapsed_time": "0:13:22", "remaining_time": "2:25:48"}
{"current_steps": 50, "total_steps": 595, "eval_loss": 0.020035894587635994, "epoch": 0.41841004184100417, "percentage": 8.4, "elapsed_time": "0:13:30", "remaining_time": "2:27:17"}
{"current_steps": 51, "total_steps": 595, "loss": 0.0208, "lr": 8.5e-05, "epoch": 0.42677824267782427, "percentage": 8.57, "elapsed_time": "0:13:51", "remaining_time": "2:27:46"}
{"current_steps": 52, "total_steps": 595, "loss": 0.0166, "lr": 8.666666666666667e-05, "epoch": 0.4351464435146444, "percentage": 8.74, "elapsed_time": "0:14:05", "remaining_time": "2:27:05"}
{"current_steps": 53, "total_steps": 595, "loss": 0.021, "lr": 8.833333333333333e-05, "epoch": 0.4435146443514644, "percentage": 8.91, "elapsed_time": "0:14:19", "remaining_time": "2:26:26"}
{"current_steps": 54, "total_steps": 595, "loss": 0.0189, "lr": 9e-05, "epoch": 0.45188284518828453, "percentage": 9.08, "elapsed_time": "0:14:34", "remaining_time": "2:26:00"}
{"current_steps": 55, "total_steps": 595, "loss": 0.0198, "lr": 9.166666666666667e-05, "epoch": 0.4602510460251046, "percentage": 9.24, "elapsed_time": "0:14:47", "remaining_time": "2:25:17"}
{"current_steps": 55, "total_steps": 595, "eval_loss": 0.019482074305415154, "epoch": 0.4602510460251046, "percentage": 9.24, "elapsed_time": "0:14:56", "remaining_time": "2:26:38"}
{"current_steps": 56, "total_steps": 595, "loss": 0.0176, "lr": 9.333333333333334e-05, "epoch": 0.4686192468619247, "percentage": 9.41, "elapsed_time": "0:15:11", "remaining_time": "2:26:15"}
{"current_steps": 57, "total_steps": 595, "loss": 0.0189, "lr": 9.5e-05, "epoch": 0.4769874476987448, "percentage": 9.58, "elapsed_time": "0:15:26", "remaining_time": "2:25:44"}
{"current_steps": 58, "total_steps": 595, "loss": 0.0176, "lr": 9.666666666666667e-05, "epoch": 0.48535564853556484, "percentage": 9.75, "elapsed_time": "0:15:40", "remaining_time": "2:25:06"}
{"current_steps": 59, "total_steps": 595, "loss": 0.0208, "lr": 9.833333333333333e-05, "epoch": 0.49372384937238495, "percentage": 9.92, "elapsed_time": "0:15:55", "remaining_time": "2:24:43"}
{"current_steps": 60, "total_steps": 595, "loss": 0.0179, "lr": 0.0001, "epoch": 0.502092050209205, "percentage": 10.08, "elapsed_time": "0:16:12", "remaining_time": "2:24:27"}
{"current_steps": 60, "total_steps": 595, "eval_loss": 0.018894275650382042, "epoch": 0.502092050209205, "percentage": 10.08, "elapsed_time": "0:16:20", "remaining_time": "2:25:41"}
{"current_steps": 61, "total_steps": 595, "loss": 0.0183, "lr": 9.999913795300544e-05, "epoch": 0.5104602510460251, "percentage": 10.25, "elapsed_time": "0:16:34", "remaining_time": "2:25:03"}
{"current_steps": 62, "total_steps": 595, "loss": 0.0172, "lr": 9.999655184174672e-05, "epoch": 0.5188284518828452, "percentage": 10.42, "elapsed_time": "0:16:49", "remaining_time": "2:24:34"}
{"current_steps": 63, "total_steps": 595, "loss": 0.0172, "lr": 9.999224175539785e-05, "epoch": 0.5271966527196653, "percentage": 10.59, "elapsed_time": "0:17:04", "remaining_time": "2:24:07"}
{"current_steps": 64, "total_steps": 595, "loss": 0.0192, "lr": 9.99862078425787e-05, "epoch": 0.5355648535564853, "percentage": 10.76, "elapsed_time": "0:17:18", "remaining_time": "2:23:38"}
{"current_steps": 65, "total_steps": 595, "loss": 0.0185, "lr": 9.997845031134992e-05, "epoch": 0.5439330543933054, "percentage": 10.92, "elapsed_time": "0:17:32", "remaining_time": "2:23:04"}
{"current_steps": 65, "total_steps": 595, "eval_loss": 0.018585730344057083, "epoch": 0.5439330543933054, "percentage": 10.92, "elapsed_time": "0:17:41", "remaining_time": "2:24:11"}
{"current_steps": 66, "total_steps": 595, "loss": 0.0174, "lr": 9.996896942920578e-05, "epoch": 0.5523012552301255, "percentage": 11.09, "elapsed_time": "0:17:57", "remaining_time": "2:23:53"}
{"current_steps": 67, "total_steps": 595, "loss": 0.0155, "lr": 9.99577655230649e-05, "epoch": 0.5606694560669456, "percentage": 11.26, "elapsed_time": "0:18:11", "remaining_time": "2:23:21"}
{"current_steps": 68, "total_steps": 595, "loss": 0.0167, "lr": 9.994483897925905e-05, "epoch": 0.5690376569037657, "percentage": 11.43, "elapsed_time": "0:18:23", "remaining_time": "2:22:34"}
{"current_steps": 69, "total_steps": 595, "loss": 0.0184, "lr": 9.993019024351974e-05, "epoch": 0.5774058577405857, "percentage": 11.6, "elapsed_time": "0:18:37", "remaining_time": "2:21:56"}
{"current_steps": 70, "total_steps": 595, "loss": 0.0174, "lr": 9.991381982096292e-05, "epoch": 0.5857740585774058, "percentage": 11.76, "elapsed_time": "0:18:50", "remaining_time": "2:21:17"}
{"current_steps": 70, "total_steps": 595, "eval_loss": 0.018603580072522163, "epoch": 0.5857740585774058, "percentage": 11.76, "elapsed_time": "0:18:58", "remaining_time": "2:22:19"}
{"current_steps": 71, "total_steps": 595, "loss": 0.0151, "lr": 9.989572827607153e-05, "epoch": 0.5941422594142259, "percentage": 11.93, "elapsed_time": "0:19:13", "remaining_time": "2:21:55"}
{"current_steps": 72, "total_steps": 595, "loss": 0.0192, "lr": 9.987591623267606e-05, "epoch": 0.602510460251046, "percentage": 12.1, "elapsed_time": "0:19:27", "remaining_time": "2:21:22"}
{"current_steps": 73, "total_steps": 595, "loss": 0.0166, "lr": 9.9854384373933e-05, "epoch": 0.6108786610878661, "percentage": 12.27, "elapsed_time": "0:19:41", "remaining_time": "2:20:46"}
{"current_steps": 74, "total_steps": 595, "loss": 0.0181, "lr": 9.983113344230129e-05, "epoch": 0.6192468619246861, "percentage": 12.44, "elapsed_time": "0:19:58", "remaining_time": "2:20:34"}
{"current_steps": 75, "total_steps": 595, "loss": 0.0157, "lr": 9.98061642395168e-05, "epoch": 0.6276150627615062, "percentage": 12.61, "elapsed_time": "0:20:11", "remaining_time": "2:19:58"}
{"current_steps": 75, "total_steps": 595, "eval_loss": 0.0182618610560894, "epoch": 0.6276150627615062, "percentage": 12.61, "elapsed_time": "0:20:19", "remaining_time": "2:20:55"}
{"current_steps": 76, "total_steps": 595, "loss": 0.0183, "lr": 9.977947762656455e-05, "epoch": 0.6359832635983264, "percentage": 12.77, "elapsed_time": "0:20:34", "remaining_time": "2:20:27"}
{"current_steps": 77, "total_steps": 595, "loss": 0.0174, "lr": 9.975107452364913e-05, "epoch": 0.6443514644351465, "percentage": 12.94, "elapsed_time": "0:20:49", "remaining_time": "2:20:04"}
{"current_steps": 78, "total_steps": 595, "loss": 0.0158, "lr": 9.972095591016294e-05, "epoch": 0.6527196652719666, "percentage": 13.11, "elapsed_time": "0:21:03", "remaining_time": "2:19:31"}
{"current_steps": 79, "total_steps": 595, "loss": 0.0155, "lr": 9.968912282465236e-05, "epoch": 0.6610878661087866, "percentage": 13.28, "elapsed_time": "0:21:16", "remaining_time": "2:18:58"}
{"current_steps": 80, "total_steps": 595, "loss": 0.0175, "lr": 9.965557636478203e-05, "epoch": 0.6694560669456067, "percentage": 13.45, "elapsed_time": "0:21:30", "remaining_time": "2:18:26"}
{"current_steps": 80, "total_steps": 595, "eval_loss": 0.017632750794291496, "epoch": 0.6694560669456067, "percentage": 13.45, "elapsed_time": "0:21:38", "remaining_time": "2:19:19"}
{"current_steps": 81, "total_steps": 595, "loss": 0.0184, "lr": 9.962031768729693e-05, "epoch": 0.6778242677824268, "percentage": 13.61, "elapsed_time": "0:21:51", "remaining_time": "2:18:42"}
{"current_steps": 82, "total_steps": 595, "loss": 0.0162, "lr": 9.958334800798256e-05, "epoch": 0.6861924686192469, "percentage": 13.78, "elapsed_time": "0:22:05", "remaining_time": "2:18:11"}
{"current_steps": 83, "total_steps": 595, "loss": 0.0146, "lr": 9.954466860162295e-05, "epoch": 0.694560669456067, "percentage": 13.95, "elapsed_time": "0:22:19", "remaining_time": "2:17:41"}
{"current_steps": 84, "total_steps": 595, "loss": 0.0183, "lr": 9.950428080195675e-05, "epoch": 0.702928870292887, "percentage": 14.12, "elapsed_time": "0:22:33", "remaining_time": "2:17:16"}
{"current_steps": 85, "total_steps": 595, "loss": 0.0175, "lr": 9.94621860016312e-05, "epoch": 0.7112970711297071, "percentage": 14.29, "elapsed_time": "0:22:48", "remaining_time": "2:16:49"}
{"current_steps": 85, "total_steps": 595, "eval_loss": 0.01763150468468666, "epoch": 0.7112970711297071, "percentage": 14.29, "elapsed_time": "0:22:56", "remaining_time": "2:17:38"}
{"current_steps": 86, "total_steps": 595, "loss": 0.018, "lr": 9.941838565215413e-05, "epoch": 0.7196652719665272, "percentage": 14.45, "elapsed_time": "0:23:10", "remaining_time": "2:17:11"}
{"current_steps": 87, "total_steps": 595, "loss": 0.0189, "lr": 9.937288126384396e-05, "epoch": 0.7280334728033473, "percentage": 14.62, "elapsed_time": "0:23:24", "remaining_time": "2:16:39"}
{"current_steps": 88, "total_steps": 595, "loss": 0.0169, "lr": 9.932567440577751e-05, "epoch": 0.7364016736401674, "percentage": 14.79, "elapsed_time": "0:23:39", "remaining_time": "2:16:19"}
{"current_steps": 89, "total_steps": 595, "loss": 0.016, "lr": 9.9276766705736e-05, "epoch": 0.7447698744769874, "percentage": 14.96, "elapsed_time": "0:23:54", "remaining_time": "2:15:53"}
{"current_steps": 90, "total_steps": 595, "loss": 0.0164, "lr": 9.922615985014887e-05, "epoch": 0.7531380753138075, "percentage": 15.13, "elapsed_time": "0:24:08", "remaining_time": "2:15:29"}
{"current_steps": 90, "total_steps": 595, "eval_loss": 0.017131321132183075, "epoch": 0.7531380753138075, "percentage": 15.13, "elapsed_time": "0:24:16", "remaining_time": "2:16:15"}
{"current_steps": 91, "total_steps": 595, "loss": 0.0176, "lr": 9.91738555840356e-05, "epoch": 0.7615062761506276, "percentage": 15.29, "elapsed_time": "0:24:30", "remaining_time": "2:15:44"}
{"current_steps": 92, "total_steps": 595, "loss": 0.0178, "lr": 9.911985571094564e-05, "epoch": 0.7698744769874477, "percentage": 15.46, "elapsed_time": "0:24:45", "remaining_time": "2:15:20"}
{"current_steps": 93, "total_steps": 595, "loss": 0.0161, "lr": 9.906416209289608e-05, "epoch": 0.7782426778242678, "percentage": 15.63, "elapsed_time": "0:24:58", "remaining_time": "2:14:49"}
{"current_steps": 94, "total_steps": 595, "loss": 0.0161, "lr": 9.900677665030762e-05, "epoch": 0.7866108786610879, "percentage": 15.8, "elapsed_time": "0:25:11", "remaining_time": "2:14:17"}
{"current_steps": 95, "total_steps": 595, "loss": 0.0182, "lr": 9.894770136193814e-05, "epoch": 0.7949790794979079, "percentage": 15.97, "elapsed_time": "0:25:26", "remaining_time": "2:13:56"}
{"current_steps": 95, "total_steps": 595, "eval_loss": 0.016829807311296463, "epoch": 0.7949790794979079, "percentage": 15.97, "elapsed_time": "0:25:35", "remaining_time": "2:14:39"}
{"current_steps": 96, "total_steps": 595, "loss": 0.0154, "lr": 9.888693826481467e-05, "epoch": 0.803347280334728, "percentage": 16.13, "elapsed_time": "0:25:49", "remaining_time": "2:14:14"}
{"current_steps": 97, "total_steps": 595, "loss": 0.0168, "lr": 9.882448945416298e-05, "epoch": 0.8117154811715481, "percentage": 16.3, "elapsed_time": "0:26:03", "remaining_time": "2:13:48"}
{"current_steps": 98, "total_steps": 595, "loss": 0.0142, "lr": 9.87603570833355e-05, "epoch": 0.8200836820083682, "percentage": 16.47, "elapsed_time": "0:26:18", "remaining_time": "2:13:24"}
{"current_steps": 99, "total_steps": 595, "loss": 0.0163, "lr": 9.869454336373689e-05, "epoch": 0.8284518828451883, "percentage": 16.64, "elapsed_time": "0:26:32", "remaining_time": "2:13:00"}
{"current_steps": 100, "total_steps": 595, "loss": 0.019, "lr": 9.862705056474795e-05, "epoch": 0.8368200836820083, "percentage": 16.81, "elapsed_time": "0:26:49", "remaining_time": "2:12:48"}
{"current_steps": 100, "total_steps": 595, "eval_loss": 0.016707511618733406, "epoch": 0.8368200836820083, "percentage": 16.81, "elapsed_time": "0:26:58", "remaining_time": "2:13:30"}
{"current_steps": 101, "total_steps": 595, "loss": 0.0139, "lr": 9.855788101364722e-05, "epoch": 0.8451882845188284, "percentage": 16.97, "elapsed_time": "0:27:19", "remaining_time": "2:13:40"}
{"current_steps": 102, "total_steps": 595, "loss": 0.017, "lr": 9.848703709553089e-05, "epoch": 0.8535564853556485, "percentage": 17.14, "elapsed_time": "0:27:33", "remaining_time": "2:13:13"}
{"current_steps": 103, "total_steps": 595, "loss": 0.0171, "lr": 9.841452125323041e-05, "epoch": 0.8619246861924686, "percentage": 17.31, "elapsed_time": "0:27:47", "remaining_time": "2:12:47"}
{"current_steps": 104, "total_steps": 595, "loss": 0.0151, "lr": 9.834033598722831e-05, "epoch": 0.8702928870292888, "percentage": 17.48, "elapsed_time": "0:28:03", "remaining_time": "2:12:25"}
{"current_steps": 105, "total_steps": 595, "loss": 0.0163, "lr": 9.826448385557207e-05, "epoch": 0.8786610878661087, "percentage": 17.65, "elapsed_time": "0:28:18", "remaining_time": "2:12:07"}
{"current_steps": 105, "total_steps": 595, "eval_loss": 0.01583385095000267, "epoch": 0.8786610878661087, "percentage": 17.65, "elapsed_time": "0:28:27", "remaining_time": "2:12:46"}
{"current_steps": 106, "total_steps": 595, "loss": 0.0177, "lr": 9.818696747378573e-05, "epoch": 0.8870292887029289, "percentage": 17.82, "elapsed_time": "0:28:42", "remaining_time": "2:12:24"}
{"current_steps": 107, "total_steps": 595, "loss": 0.0144, "lr": 9.810778951477986e-05, "epoch": 0.895397489539749, "percentage": 17.98, "elapsed_time": "0:28:57", "remaining_time": "2:12:02"}
{"current_steps": 108, "total_steps": 595, "loss": 0.0154, "lr": 9.802695270875932e-05, "epoch": 0.9037656903765691, "percentage": 18.15, "elapsed_time": "0:29:11", "remaining_time": "2:11:35"}
{"current_steps": 109, "total_steps": 595, "loss": 0.0149, "lr": 9.794445984312915e-05, "epoch": 0.9121338912133892, "percentage": 18.32, "elapsed_time": "0:29:24", "remaining_time": "2:11:09"}
{"current_steps": 110, "total_steps": 595, "loss": 0.0145, "lr": 9.786031376239842e-05, "epoch": 0.9205020920502092, "percentage": 18.49, "elapsed_time": "0:29:41", "remaining_time": "2:10:54"}
{"current_steps": 110, "total_steps": 595, "eval_loss": 0.0157511904835701, "epoch": 0.9205020920502092, "percentage": 18.49, "elapsed_time": "0:29:49", "remaining_time": "2:11:30"}
{"current_steps": 111, "total_steps": 595, "loss": 0.0138, "lr": 9.777451736808216e-05, "epoch": 0.9288702928870293, "percentage": 18.66, "elapsed_time": "0:30:03", "remaining_time": "2:11:02"}
{"current_steps": 112, "total_steps": 595, "loss": 0.0155, "lr": 9.768707361860134e-05, "epoch": 0.9372384937238494, "percentage": 18.82, "elapsed_time": "0:30:17", "remaining_time": "2:10:39"}
{"current_steps": 113, "total_steps": 595, "loss": 0.0153, "lr": 9.75979855291808e-05, "epoch": 0.9456066945606695, "percentage": 18.99, "elapsed_time": "0:30:34", "remaining_time": "2:10:22"}
{"current_steps": 114, "total_steps": 595, "loss": 0.0162, "lr": 9.750725617174534e-05, "epoch": 0.9539748953974896, "percentage": 19.16, "elapsed_time": "0:30:49", "remaining_time": "2:10:04"}
{"current_steps": 115, "total_steps": 595, "loss": 0.0165, "lr": 9.741488867481376e-05, "epoch": 0.9623430962343096, "percentage": 19.33, "elapsed_time": "0:31:04", "remaining_time": "2:09:42"}
{"current_steps": 115, "total_steps": 595, "eval_loss": 0.015494490042328835, "epoch": 0.9623430962343096, "percentage": 19.33, "elapsed_time": "0:31:12", "remaining_time": "2:10:16"}
{"current_steps": 116, "total_steps": 595, "loss": 0.0153, "lr": 9.7320886223391e-05, "epoch": 0.9707112970711297, "percentage": 19.5, "elapsed_time": "0:31:28", "remaining_time": "2:09:58"}
{"current_steps": 117, "total_steps": 595, "loss": 0.0149, "lr": 9.722525205885825e-05, "epoch": 0.9790794979079498, "percentage": 19.66, "elapsed_time": "0:31:42", "remaining_time": "2:09:30"}
{"current_steps": 118, "total_steps": 595, "loss": 0.0148, "lr": 9.712798947886128e-05, "epoch": 0.9874476987447699, "percentage": 19.83, "elapsed_time": "0:31:58", "remaining_time": "2:09:13"}
{"current_steps": 119, "total_steps": 595, "loss": 0.0199, "lr": 9.702910183719671e-05, "epoch": 0.99581589958159, "percentage": 20.0, "elapsed_time": "0:32:12", "remaining_time": "2:08:48"}
{"current_steps": 120, "total_steps": 595, "loss": 0.0205, "lr": 9.692859254369631e-05, "epoch": 1.00418410041841, "percentage": 20.17, "elapsed_time": "0:32:24", "remaining_time": "2:08:15"}
{"current_steps": 120, "total_steps": 595, "eval_loss": 0.015181933529675007, "epoch": 1.00418410041841, "percentage": 20.17, "elapsed_time": "0:32:32", "remaining_time": "2:08:48"}
{"current_steps": 121, "total_steps": 595, "loss": 0.0152, "lr": 9.682646506410943e-05, "epoch": 1.0125523012552302, "percentage": 20.34, "elapsed_time": "0:32:47", "remaining_time": "2:08:27"}
{"current_steps": 122, "total_steps": 595, "loss": 0.0127, "lr": 9.672272291998355e-05, "epoch": 1.0209205020920502, "percentage": 20.5, "elapsed_time": "0:33:00", "remaining_time": "2:07:59"}
{"current_steps": 123, "total_steps": 595, "loss": 0.0143, "lr": 9.661736968854283e-05, "epoch": 1.0292887029288702, "percentage": 20.67, "elapsed_time": "0:33:13", "remaining_time": "2:07:30"}
{"current_steps": 124, "total_steps": 595, "loss": 0.0145, "lr": 9.651040900256471e-05, "epoch": 1.0376569037656904, "percentage": 20.84, "elapsed_time": "0:33:27", "remaining_time": "2:07:06"}
{"current_steps": 125, "total_steps": 595, "loss": 0.0105, "lr": 9.640184455025471e-05, "epoch": 1.0460251046025104, "percentage": 21.01, "elapsed_time": "0:33:41", "remaining_time": "2:06:42"}
{"current_steps": 125, "total_steps": 595, "eval_loss": 0.015529554337263107, "epoch": 1.0460251046025104, "percentage": 21.01, "elapsed_time": "0:33:50", "remaining_time": "2:07:13"}
{"current_steps": 126, "total_steps": 595, "loss": 0.0121, "lr": 9.629168007511924e-05, "epoch": 1.0543933054393306, "percentage": 21.18, "elapsed_time": "0:34:06", "remaining_time": "2:06:55"}
{"current_steps": 127, "total_steps": 595, "loss": 0.0154, "lr": 9.617991937583648e-05, "epoch": 1.0627615062761506, "percentage": 21.34, "elapsed_time": "0:34:20", "remaining_time": "2:06:34"}
{"current_steps": 128, "total_steps": 595, "loss": 0.0163, "lr": 9.60665663061254e-05, "epoch": 1.0711297071129706, "percentage": 21.51, "elapsed_time": "0:34:37", "remaining_time": "2:06:18"}
{"current_steps": 129, "total_steps": 595, "loss": 0.0126, "lr": 9.595162477461298e-05, "epoch": 1.0794979079497908, "percentage": 21.68, "elapsed_time": "0:34:51", "remaining_time": "2:05:53"}
{"current_steps": 130, "total_steps": 595, "loss": 0.0147, "lr": 9.583509874469923e-05, "epoch": 1.0878661087866108, "percentage": 21.85, "elapsed_time": "0:35:05", "remaining_time": "2:05:31"}
{"current_steps": 130, "total_steps": 595, "eval_loss": 0.015730947256088257, "epoch": 1.0878661087866108, "percentage": 21.85, "elapsed_time": "0:35:13", "remaining_time": "2:06:01"}
{"current_steps": 131, "total_steps": 595, "loss": 0.0129, "lr": 9.571699223442074e-05, "epoch": 1.096234309623431, "percentage": 22.02, "elapsed_time": "0:35:27", "remaining_time": "2:05:35"}
{"current_steps": 132, "total_steps": 595, "loss": 0.0137, "lr": 9.559730931631198e-05, "epoch": 1.104602510460251, "percentage": 22.18, "elapsed_time": "0:35:43", "remaining_time": "2:05:18"}
{"current_steps": 133, "total_steps": 595, "loss": 0.0119, "lr": 9.5476054117265e-05, "epoch": 1.112970711297071, "percentage": 22.35, "elapsed_time": "0:35:56", "remaining_time": "2:04:52"}
{"current_steps": 134, "total_steps": 595, "loss": 0.0153, "lr": 9.535323081838691e-05, "epoch": 1.1213389121338913, "percentage": 22.52, "elapsed_time": "0:36:10", "remaining_time": "2:04:28"}
{"current_steps": 135, "total_steps": 595, "loss": 0.0148, "lr": 9.522884365485598e-05, "epoch": 1.1297071129707112, "percentage": 22.69, "elapsed_time": "0:36:24", "remaining_time": "2:04:02"}
{"current_steps": 135, "total_steps": 595, "eval_loss": 0.015986260026693344, "epoch": 1.1297071129707112, "percentage": 22.69, "elapsed_time": "0:36:32", "remaining_time": "2:04:30"}
{"current_steps": 136, "total_steps": 595, "loss": 0.0138, "lr": 9.510289691577544e-05, "epoch": 1.1380753138075315, "percentage": 22.86, "elapsed_time": "0:36:46", "remaining_time": "2:04:07"}
{"current_steps": 137, "total_steps": 595, "loss": 0.017, "lr": 9.49753949440256e-05, "epoch": 1.1464435146443515, "percentage": 23.03, "elapsed_time": "0:36:59", "remaining_time": "2:03:41"}
{"current_steps": 138, "total_steps": 595, "loss": 0.0114, "lr": 9.484634213611411e-05, "epoch": 1.1548117154811715, "percentage": 23.19, "elapsed_time": "0:37:14", "remaining_time": "2:03:20"}
{"current_steps": 139, "total_steps": 595, "loss": 0.0132, "lr": 9.471574294202439e-05, "epoch": 1.1631799163179917, "percentage": 23.36, "elapsed_time": "0:37:28", "remaining_time": "2:02:55"}
{"current_steps": 140, "total_steps": 595, "loss": 0.0115, "lr": 9.458360186506213e-05, "epoch": 1.1715481171548117, "percentage": 23.53, "elapsed_time": "0:37:40", "remaining_time": "2:02:25"}
{"current_steps": 140, "total_steps": 595, "eval_loss": 0.015280088409781456, "epoch": 1.1715481171548117, "percentage": 23.53, "elapsed_time": "0:37:48", "remaining_time": "2:02:52"}
{"current_steps": 141, "total_steps": 595, "loss": 0.0131, "lr": 9.444992346170007e-05, "epoch": 1.1799163179916319, "percentage": 23.7, "elapsed_time": "0:38:01", "remaining_time": "2:02:25"}
{"current_steps": 142, "total_steps": 595, "loss": 0.0136, "lr": 9.431471234142087e-05, "epoch": 1.1882845188284519, "percentage": 23.87, "elapsed_time": "0:38:15", "remaining_time": "2:02:01"}
{"current_steps": 143, "total_steps": 595, "loss": 0.0149, "lr": 9.41779731665581e-05, "epoch": 1.196652719665272, "percentage": 24.03, "elapsed_time": "0:38:30", "remaining_time": "2:01:42"}
{"current_steps": 144, "total_steps": 595, "loss": 0.0128, "lr": 9.403971065213555e-05, "epoch": 1.205020920502092, "percentage": 24.2, "elapsed_time": "0:38:43", "remaining_time": "2:01:17"}
{"current_steps": 145, "total_steps": 595, "loss": 0.0166, "lr": 9.389992956570462e-05, "epoch": 1.213389121338912, "percentage": 24.37, "elapsed_time": "0:38:57", "remaining_time": "2:00:54"}
{"current_steps": 145, "total_steps": 595, "eval_loss": 0.015301547013223171, "epoch": 1.213389121338912, "percentage": 24.37, "elapsed_time": "0:39:05", "remaining_time": "2:01:19"}
{"current_steps": 146, "total_steps": 595, "loss": 0.0171, "lr": 9.375863472717993e-05, "epoch": 1.2217573221757323, "percentage": 24.54, "elapsed_time": "0:39:19", "remaining_time": "2:00:54"}
{"current_steps": 147, "total_steps": 595, "loss": 0.013, "lr": 9.361583100867313e-05, "epoch": 1.2301255230125523, "percentage": 24.71, "elapsed_time": "0:39:32", "remaining_time": "2:00:29"}
{"current_steps": 148, "total_steps": 595, "loss": 0.0139, "lr": 9.347152333432485e-05, "epoch": 1.2384937238493725, "percentage": 24.87, "elapsed_time": "0:39:46", "remaining_time": "2:00:08"}
{"current_steps": 149, "total_steps": 595, "loss": 0.0147, "lr": 9.332571668013499e-05, "epoch": 1.2468619246861925, "percentage": 25.04, "elapsed_time": "0:40:01", "remaining_time": "1:59:49"}
{"current_steps": 150, "total_steps": 595, "loss": 0.015, "lr": 9.317841607379107e-05, "epoch": 1.2552301255230125, "percentage": 25.21, "elapsed_time": "0:40:17", "remaining_time": "1:59:30"}
{"current_steps": 150, "total_steps": 595, "eval_loss": 0.015605509281158447, "epoch": 1.2552301255230125, "percentage": 25.21, "elapsed_time": "0:40:25", "remaining_time": "1:59:54"}
{"current_steps": 151, "total_steps": 595, "loss": 0.0125, "lr": 9.302962659449486e-05, "epoch": 1.2635983263598327, "percentage": 25.38, "elapsed_time": "0:40:48", "remaining_time": "2:00:00"}
{"current_steps": 152, "total_steps": 595, "loss": 0.0139, "lr": 9.287935337278733e-05, "epoch": 1.2719665271966527, "percentage": 25.55, "elapsed_time": "0:41:03", "remaining_time": "1:59:38"}
{"current_steps": 153, "total_steps": 595, "loss": 0.0168, "lr": 9.272760159037164e-05, "epoch": 1.280334728033473, "percentage": 25.71, "elapsed_time": "0:41:16", "remaining_time": "1:59:14"}
{"current_steps": 154, "total_steps": 595, "loss": 0.0107, "lr": 9.25743764799345e-05, "epoch": 1.288702928870293, "percentage": 25.88, "elapsed_time": "0:41:29", "remaining_time": "1:58:49"}
{"current_steps": 155, "total_steps": 595, "loss": 0.0148, "lr": 9.241968332496575e-05, "epoch": 1.297071129707113, "percentage": 26.05, "elapsed_time": "0:41:43", "remaining_time": "1:58:27"}
{"current_steps": 155, "total_steps": 595, "eval_loss": 0.015689246356487274, "epoch": 1.297071129707113, "percentage": 26.05, "elapsed_time": "0:41:51", "remaining_time": "1:58:50"}
{"current_steps": 156, "total_steps": 595, "loss": 0.0121, "lr": 9.226352745957616e-05, "epoch": 1.3054393305439331, "percentage": 26.22, "elapsed_time": "0:42:04", "remaining_time": "1:58:25"}
{"current_steps": 157, "total_steps": 595, "loss": 0.0138, "lr": 9.210591426831352e-05, "epoch": 1.3138075313807531, "percentage": 26.39, "elapsed_time": "0:42:21", "remaining_time": "1:58:10"}
{"current_steps": 158, "total_steps": 595, "loss": 0.0119, "lr": 9.194684918597694e-05, "epoch": 1.3221757322175733, "percentage": 26.55, "elapsed_time": "0:42:35", "remaining_time": "1:57:48"}
{"current_steps": 159, "total_steps": 595, "loss": 0.0122, "lr": 9.178633769742945e-05, "epoch": 1.3305439330543933, "percentage": 26.72, "elapsed_time": "0:42:50", "remaining_time": "1:57:27"}
{"current_steps": 160, "total_steps": 595, "loss": 0.0112, "lr": 9.162438533740892e-05, "epoch": 1.3389121338912133, "percentage": 26.89, "elapsed_time": "0:43:04", "remaining_time": "1:57:07"}
{"current_steps": 160, "total_steps": 595, "eval_loss": 0.01591303013265133, "epoch": 1.3389121338912133, "percentage": 26.89, "elapsed_time": "0:43:13", "remaining_time": "1:57:30"}
{"current_steps": 161, "total_steps": 595, "loss": 0.0141, "lr": 9.146099769033715e-05, "epoch": 1.3472803347280335, "percentage": 27.06, "elapsed_time": "0:43:28", "remaining_time": "1:57:10"}
{"current_steps": 162, "total_steps": 595, "loss": 0.0123, "lr": 9.129618039012736e-05, "epoch": 1.3556485355648535, "percentage": 27.23, "elapsed_time": "0:43:42", "remaining_time": "1:56:49"}
{"current_steps": 163, "total_steps": 595, "loss": 0.0142, "lr": 9.112993911998984e-05, "epoch": 1.3640167364016738, "percentage": 27.39, "elapsed_time": "0:43:56", "remaining_time": "1:56:28"}
{"current_steps": 164, "total_steps": 595, "loss": 0.0149, "lr": 9.096227961223613e-05, "epoch": 1.3723849372384938, "percentage": 27.56, "elapsed_time": "0:44:12", "remaining_time": "1:56:11"}
{"current_steps": 165, "total_steps": 595, "loss": 0.0128, "lr": 9.07932076480812e-05, "epoch": 1.3807531380753137, "percentage": 27.73, "elapsed_time": "0:44:27", "remaining_time": "1:55:52"}
{"current_steps": 165, "total_steps": 595, "eval_loss": 0.015296611934900284, "epoch": 1.3807531380753137, "percentage": 27.73, "elapsed_time": "0:44:36", "remaining_time": "1:56:14"}
{"current_steps": 166, "total_steps": 595, "loss": 0.0136, "lr": 9.06227290574442e-05, "epoch": 1.389121338912134, "percentage": 27.9, "elapsed_time": "0:44:51", "remaining_time": "1:55:54"}
{"current_steps": 167, "total_steps": 595, "loss": 0.0111, "lr": 9.045084971874738e-05, "epoch": 1.397489539748954, "percentage": 28.07, "elapsed_time": "0:45:04", "remaining_time": "1:55:31"}
{"current_steps": 168, "total_steps": 595, "loss": 0.0146, "lr": 9.027757555871344e-05, "epoch": 1.4058577405857742, "percentage": 28.24, "elapsed_time": "0:45:19", "remaining_time": "1:55:12"}
{"current_steps": 169, "total_steps": 595, "loss": 0.0142, "lr": 9.010291255216117e-05, "epoch": 1.4142259414225942, "percentage": 28.4, "elapsed_time": "0:45:34", "remaining_time": "1:54:53"}
{"current_steps": 170, "total_steps": 595, "loss": 0.0125, "lr": 8.99268667217993e-05, "epoch": 1.4225941422594142, "percentage": 28.57, "elapsed_time": "0:45:48", "remaining_time": "1:54:30"}
{"current_steps": 170, "total_steps": 595, "eval_loss": 0.015141828916966915, "epoch": 1.4225941422594142, "percentage": 28.57, "elapsed_time": "0:45:56", "remaining_time": "1:54:50"}
{"current_steps": 171, "total_steps": 595, "loss": 0.0158, "lr": 8.974944413801906e-05, "epoch": 1.4309623430962344, "percentage": 28.74, "elapsed_time": "0:46:10", "remaining_time": "1:54:29"}
{"current_steps": 172, "total_steps": 595, "loss": 0.0138, "lr": 8.957065091868459e-05, "epoch": 1.4393305439330544, "percentage": 28.91, "elapsed_time": "0:46:25", "remaining_time": "1:54:11"}
{"current_steps": 173, "total_steps": 595, "loss": 0.0104, "lr": 8.939049322892223e-05, "epoch": 1.4476987447698746, "percentage": 29.08, "elapsed_time": "0:46:38", "remaining_time": "1:53:46"}
{"current_steps": 174, "total_steps": 595, "loss": 0.0142, "lr": 8.920897728090777e-05, "epoch": 1.4560669456066946, "percentage": 29.24, "elapsed_time": "0:46:52", "remaining_time": "1:53:25"}
{"current_steps": 175, "total_steps": 595, "loss": 0.0137, "lr": 8.902610933365229e-05, "epoch": 1.4644351464435146, "percentage": 29.41, "elapsed_time": "0:47:05", "remaining_time": "1:53:02"}
{"current_steps": 175, "total_steps": 595, "eval_loss": 0.015005652792751789, "epoch": 1.4644351464435146, "percentage": 29.41, "elapsed_time": "0:47:14", "remaining_time": "1:53:22"}
{"current_steps": 176, "total_steps": 595, "loss": 0.0143, "lr": 8.88418956927864e-05, "epoch": 1.4728033472803348, "percentage": 29.58, "elapsed_time": "0:47:28", "remaining_time": "1:53:01"}
{"current_steps": 177, "total_steps": 595, "loss": 0.0144, "lr": 8.865634271034268e-05, "epoch": 1.4811715481171548, "percentage": 29.75, "elapsed_time": "0:47:43", "remaining_time": "1:52:42"}
{"current_steps": 178, "total_steps": 595, "loss": 0.0138, "lr": 8.846945678453677e-05, "epoch": 1.489539748953975, "percentage": 29.92, "elapsed_time": "0:47:59", "remaining_time": "1:52:25"}
{"current_steps": 179, "total_steps": 595, "loss": 0.0147, "lr": 8.828124435954672e-05, "epoch": 1.497907949790795, "percentage": 30.08, "elapsed_time": "0:48:14", "remaining_time": "1:52:07"}
{"current_steps": 180, "total_steps": 595, "loss": 0.0131, "lr": 8.809171192529073e-05, "epoch": 1.506276150627615, "percentage": 30.25, "elapsed_time": "0:48:30", "remaining_time": "1:51:49"}
{"current_steps": 180, "total_steps": 595, "eval_loss": 0.014517219737172127, "epoch": 1.506276150627615, "percentage": 30.25, "elapsed_time": "0:48:38", "remaining_time": "1:52:08"}
{"current_steps": 181, "total_steps": 595, "loss": 0.0137, "lr": 8.790086601720339e-05, "epoch": 1.514644351464435, "percentage": 30.42, "elapsed_time": "0:48:52", "remaining_time": "1:51:48"}
{"current_steps": 182, "total_steps": 595, "loss": 0.0126, "lr": 8.77087132160104e-05, "epoch": 1.5230125523012552, "percentage": 30.59, "elapsed_time": "0:49:06", "remaining_time": "1:51:27"}
{"current_steps": 183, "total_steps": 595, "loss": 0.0149, "lr": 8.751526014750153e-05, "epoch": 1.5313807531380754, "percentage": 30.76, "elapsed_time": "0:49:23", "remaining_time": "1:51:11"}
{"current_steps": 184, "total_steps": 595, "loss": 0.0114, "lr": 8.732051348230223e-05, "epoch": 1.5397489539748954, "percentage": 30.92, "elapsed_time": "0:49:37", "remaining_time": "1:50:50"}
{"current_steps": 185, "total_steps": 595, "loss": 0.0105, "lr": 8.712447993564361e-05, "epoch": 1.5481171548117154, "percentage": 31.09, "elapsed_time": "0:49:51", "remaining_time": "1:50:30"}
{"current_steps": 185, "total_steps": 595, "eval_loss": 0.014493227005004883, "epoch": 1.5481171548117154, "percentage": 31.09, "elapsed_time": "0:50:00", "remaining_time": "1:50:48"}
{"current_steps": 186, "total_steps": 595, "loss": 0.0133, "lr": 8.692716626713084e-05, "epoch": 1.5564853556485354, "percentage": 31.26, "elapsed_time": "0:50:15", "remaining_time": "1:50:31"}
{"current_steps": 187, "total_steps": 595, "loss": 0.014, "lr": 8.672857928051013e-05, "epoch": 1.5648535564853556, "percentage": 31.43, "elapsed_time": "0:50:28", "remaining_time": "1:50:07"}
{"current_steps": 188, "total_steps": 595, "loss": 0.011, "lr": 8.652872582343408e-05, "epoch": 1.5732217573221758, "percentage": 31.6, "elapsed_time": "0:50:42", "remaining_time": "1:49:46"}
{"current_steps": 189, "total_steps": 595, "loss": 0.0147, "lr": 8.632761278722556e-05, "epoch": 1.5815899581589958, "percentage": 31.76, "elapsed_time": "0:50:56", "remaining_time": "1:49:26"}
{"current_steps": 190, "total_steps": 595, "loss": 0.0126, "lr": 8.612524710664012e-05, "epoch": 1.5899581589958158, "percentage": 31.93, "elapsed_time": "0:51:09", "remaining_time": "1:49:03"}
{"current_steps": 190, "total_steps": 595, "eval_loss": 0.014403114095330238, "epoch": 1.5899581589958158, "percentage": 31.93, "elapsed_time": "0:51:18", "remaining_time": "1:49:21"}
{"current_steps": 191, "total_steps": 595, "loss": 0.0128, "lr": 8.592163575962682e-05, "epoch": 1.5983263598326358, "percentage": 32.1, "elapsed_time": "0:51:31", "remaining_time": "1:48:59"}
{"current_steps": 192, "total_steps": 595, "loss": 0.0117, "lr": 8.571678576708766e-05, "epoch": 1.606694560669456, "percentage": 32.27, "elapsed_time": "0:51:45", "remaining_time": "1:48:37"}
{"current_steps": 193, "total_steps": 595, "loss": 0.017, "lr": 8.551070419263545e-05, "epoch": 1.6150627615062763, "percentage": 32.44, "elapsed_time": "0:51:59", "remaining_time": "1:48:17"}
{"current_steps": 194, "total_steps": 595, "loss": 0.0123, "lr": 8.530339814235027e-05, "epoch": 1.6234309623430963, "percentage": 32.61, "elapsed_time": "0:52:13", "remaining_time": "1:47:56"}
{"current_steps": 195, "total_steps": 595, "loss": 0.0119, "lr": 8.509487476453442e-05, "epoch": 1.6317991631799162, "percentage": 32.77, "elapsed_time": "0:52:28", "remaining_time": "1:47:38"}
{"current_steps": 195, "total_steps": 595, "eval_loss": 0.014461501501500607, "epoch": 1.6317991631799162, "percentage": 32.77, "elapsed_time": "0:52:36", "remaining_time": "1:47:55"}
{"current_steps": 196, "total_steps": 595, "loss": 0.0137, "lr": 8.488514124946594e-05, "epoch": 1.6401673640167362, "percentage": 32.94, "elapsed_time": "0:52:50", "remaining_time": "1:47:34"}
{"current_steps": 197, "total_steps": 595, "loss": 0.0116, "lr": 8.46742048291507e-05, "epoch": 1.6485355648535565, "percentage": 33.11, "elapsed_time": "0:53:04", "remaining_time": "1:47:13"}
{"current_steps": 198, "total_steps": 595, "loss": 0.0135, "lr": 8.446207277707296e-05, "epoch": 1.6569037656903767, "percentage": 33.28, "elapsed_time": "0:53:19", "remaining_time": "1:46:54"}
{"current_steps": 199, "total_steps": 595, "loss": 0.0117, "lr": 8.424875240794467e-05, "epoch": 1.6652719665271967, "percentage": 33.45, "elapsed_time": "0:53:33", "remaining_time": "1:46:34"}
{"current_steps": 200, "total_steps": 595, "loss": 0.016, "lr": 8.403425107745316e-05, "epoch": 1.6736401673640167, "percentage": 33.61, "elapsed_time": "0:53:49", "remaining_time": "1:46:17"}
{"current_steps": 200, "total_steps": 595, "eval_loss": 0.014672570861876011, "epoch": 1.6736401673640167, "percentage": 33.61, "elapsed_time": "0:53:57", "remaining_time": "1:46:34"}
{"current_steps": 201, "total_steps": 595, "loss": 0.0107, "lr": 8.381857618200746e-05, "epoch": 1.6820083682008367, "percentage": 33.78, "elapsed_time": "0:54:18", "remaining_time": "1:46:28"}
{"current_steps": 202, "total_steps": 595, "loss": 0.0127, "lr": 8.360173515848343e-05, "epoch": 1.6903765690376569, "percentage": 33.95, "elapsed_time": "0:54:32", "remaining_time": "1:46:06"}
{"current_steps": 203, "total_steps": 595, "loss": 0.0099, "lr": 8.33837354839672e-05, "epoch": 1.698744769874477, "percentage": 34.12, "elapsed_time": "0:54:45", "remaining_time": "1:45:43"}
{"current_steps": 204, "total_steps": 595, "loss": 0.0131, "lr": 8.316458467549729e-05, "epoch": 1.707112970711297, "percentage": 34.29, "elapsed_time": "0:54:59", "remaining_time": "1:45:24"}
{"current_steps": 205, "total_steps": 595, "loss": 0.0143, "lr": 8.294429028980556e-05, "epoch": 1.715481171548117, "percentage": 34.45, "elapsed_time": "0:55:14", "remaining_time": "1:45:05"}
{"current_steps": 205, "total_steps": 595, "eval_loss": 0.014957732520997524, "epoch": 1.715481171548117, "percentage": 34.45, "elapsed_time": "0:55:22", "remaining_time": "1:45:21"}
{"current_steps": 206, "total_steps": 595, "loss": 0.014, "lr": 8.272285992305653e-05, "epoch": 1.723849372384937, "percentage": 34.62, "elapsed_time": "0:55:37", "remaining_time": "1:45:01"}
{"current_steps": 207, "total_steps": 595, "loss": 0.0112, "lr": 8.250030121058547e-05, "epoch": 1.7322175732217573, "percentage": 34.79, "elapsed_time": "0:55:51", "remaining_time": "1:44:41"}
{"current_steps": 208, "total_steps": 595, "loss": 0.0129, "lr": 8.227662182663518e-05, "epoch": 1.7405857740585775, "percentage": 34.96, "elapsed_time": "0:56:06", "remaining_time": "1:44:24"}
{"current_steps": 209, "total_steps": 595, "loss": 0.0131, "lr": 8.205182948409125e-05, "epoch": 1.7489539748953975, "percentage": 35.13, "elapsed_time": "0:56:20", "remaining_time": "1:44:04"}
{"current_steps": 210, "total_steps": 595, "loss": 0.0139, "lr": 8.182593193421625e-05, "epoch": 1.7573221757322175, "percentage": 35.29, "elapsed_time": "0:56:35", "remaining_time": "1:43:44"}
{"current_steps": 210, "total_steps": 595, "eval_loss": 0.014965851791203022, "epoch": 1.7573221757322175, "percentage": 35.29, "elapsed_time": "0:56:43", "remaining_time": "1:43:59"}
{"current_steps": 211, "total_steps": 595, "loss": 0.0122, "lr": 8.159893696638232e-05, "epoch": 1.7656903765690377, "percentage": 35.46, "elapsed_time": "0:56:57", "remaining_time": "1:43:39"}
{"current_steps": 212, "total_steps": 595, "loss": 0.0107, "lr": 8.137085240780262e-05, "epoch": 1.7740585774058577, "percentage": 35.63, "elapsed_time": "0:57:12", "remaining_time": "1:43:20"}
{"current_steps": 213, "total_steps": 595, "loss": 0.0106, "lr": 8.114168612326153e-05, "epoch": 1.782426778242678, "percentage": 35.8, "elapsed_time": "0:57:26", "remaining_time": "1:43:01"}
{"current_steps": 214, "total_steps": 595, "loss": 0.0131, "lr": 8.091144601484332e-05, "epoch": 1.790794979079498, "percentage": 35.97, "elapsed_time": "0:57:39", "remaining_time": "1:42:39"}
{"current_steps": 215, "total_steps": 595, "loss": 0.0139, "lr": 8.06801400216597e-05, "epoch": 1.799163179916318, "percentage": 36.13, "elapsed_time": "0:57:53", "remaining_time": "1:42:19"}
{"current_steps": 215, "total_steps": 595, "eval_loss": 0.01450226828455925, "epoch": 1.799163179916318, "percentage": 36.13, "elapsed_time": "0:58:01", "remaining_time": "1:42:33"}
{"current_steps": 216, "total_steps": 595, "loss": 0.0114, "lr": 8.044777611957613e-05, "epoch": 1.8075313807531381, "percentage": 36.3, "elapsed_time": "0:58:17", "remaining_time": "1:42:16"}
{"current_steps": 217, "total_steps": 595, "loss": 0.0136, "lr": 8.021436232093675e-05, "epoch": 1.8158995815899581, "percentage": 36.47, "elapsed_time": "0:58:31", "remaining_time": "1:41:56"}
{"current_steps": 218, "total_steps": 595, "loss": 0.013, "lr": 7.997990667428811e-05, "epoch": 1.8242677824267783, "percentage": 36.64, "elapsed_time": "0:58:46", "remaining_time": "1:41:38"}
{"current_steps": 219, "total_steps": 595, "loss": 0.0142, "lr": 7.974441726410164e-05, "epoch": 1.8326359832635983, "percentage": 36.81, "elapsed_time": "0:59:01", "remaining_time": "1:41:20"}
{"current_steps": 220, "total_steps": 595, "loss": 0.0161, "lr": 7.950790221049484e-05, "epoch": 1.8410041841004183, "percentage": 36.97, "elapsed_time": "0:59:16", "remaining_time": "1:41:02"}
{"current_steps": 220, "total_steps": 595, "eval_loss": 0.014255787245929241, "epoch": 1.8410041841004183, "percentage": 36.97, "elapsed_time": "0:59:24", "remaining_time": "1:41:16"}
{"current_steps": 221, "total_steps": 595, "loss": 0.0117, "lr": 7.927036966895138e-05, "epoch": 1.8493723849372385, "percentage": 37.14, "elapsed_time": "0:59:38", "remaining_time": "1:40:55"}
{"current_steps": 222, "total_steps": 595, "loss": 0.0132, "lr": 7.90318278300398e-05, "epoch": 1.8577405857740585, "percentage": 37.31, "elapsed_time": "0:59:51", "remaining_time": "1:40:34"}
{"current_steps": 223, "total_steps": 595, "loss": 0.012, "lr": 7.879228491913111e-05, "epoch": 1.8661087866108788, "percentage": 37.48, "elapsed_time": "1:00:06", "remaining_time": "1:40:15"}
{"current_steps": 224, "total_steps": 595, "loss": 0.0135, "lr": 7.855174919611517e-05, "epoch": 1.8744769874476988, "percentage": 37.65, "elapsed_time": "1:00:19", "remaining_time": "1:39:54"}
{"current_steps": 225, "total_steps": 595, "loss": 0.0098, "lr": 7.831022895511587e-05, "epoch": 1.8828451882845187, "percentage": 37.82, "elapsed_time": "1:00:32", "remaining_time": "1:39:33"}
{"current_steps": 225, "total_steps": 595, "eval_loss": 0.013838106766343117, "epoch": 1.8828451882845187, "percentage": 37.82, "elapsed_time": "1:00:40", "remaining_time": "1:39:46"}
{"current_steps": 226, "total_steps": 595, "loss": 0.0144, "lr": 7.80677325242051e-05, "epoch": 1.891213389121339, "percentage": 37.98, "elapsed_time": "1:00:55", "remaining_time": "1:39:28"}
{"current_steps": 227, "total_steps": 595, "loss": 0.0124, "lr": 7.782426826511564e-05, "epoch": 1.899581589958159, "percentage": 38.15, "elapsed_time": "1:01:10", "remaining_time": "1:39:10"}
{"current_steps": 228, "total_steps": 595, "loss": 0.0125, "lr": 7.757984457295284e-05, "epoch": 1.9079497907949792, "percentage": 38.32, "elapsed_time": "1:01:25", "remaining_time": "1:38:51"}
{"current_steps": 229, "total_steps": 595, "loss": 0.0115, "lr": 7.733446987590505e-05, "epoch": 1.9163179916317992, "percentage": 38.49, "elapsed_time": "1:01:39", "remaining_time": "1:38:32"}
{"current_steps": 230, "total_steps": 595, "loss": 0.0108, "lr": 7.708815263495308e-05, "epoch": 1.9246861924686192, "percentage": 38.66, "elapsed_time": "1:01:52", "remaining_time": "1:38:11"}
{"current_steps": 230, "total_steps": 595, "eval_loss": 0.014023682102560997, "epoch": 1.9246861924686192, "percentage": 38.66, "elapsed_time": "1:02:00", "remaining_time": "1:38:24"}
{"current_steps": 231, "total_steps": 595, "loss": 0.014, "lr": 7.684090134357839e-05, "epoch": 1.9330543933054394, "percentage": 38.82, "elapsed_time": "1:02:15", "remaining_time": "1:38:06"}
{"current_steps": 232, "total_steps": 595, "loss": 0.0102, "lr": 7.65927245274703e-05, "epoch": 1.9414225941422594, "percentage": 38.99, "elapsed_time": "1:02:28", "remaining_time": "1:37:45"}
{"current_steps": 233, "total_steps": 595, "loss": 0.0133, "lr": 7.634363074423199e-05, "epoch": 1.9497907949790796, "percentage": 39.16, "elapsed_time": "1:02:42", "remaining_time": "1:37:26"}
{"current_steps": 234, "total_steps": 595, "loss": 0.0139, "lr": 7.609362858308531e-05, "epoch": 1.9581589958158996, "percentage": 39.33, "elapsed_time": "1:02:57", "remaining_time": "1:37:07"}
{"current_steps": 235, "total_steps": 595, "loss": 0.0117, "lr": 7.58427266645747e-05, "epoch": 1.9665271966527196, "percentage": 39.5, "elapsed_time": "1:03:11", "remaining_time": "1:36:48"}
{"current_steps": 235, "total_steps": 595, "eval_loss": 0.014116828329861164, "epoch": 1.9665271966527196, "percentage": 39.5, "elapsed_time": "1:03:19", "remaining_time": "1:37:00"}
{"current_steps": 236, "total_steps": 595, "loss": 0.0141, "lr": 7.559093364027001e-05, "epoch": 1.9748953974895398, "percentage": 39.66, "elapsed_time": "1:03:33", "remaining_time": "1:36:40"}
{"current_steps": 237, "total_steps": 595, "loss": 0.0105, "lr": 7.5338258192468e-05, "epoch": 1.9832635983263598, "percentage": 39.83, "elapsed_time": "1:03:47", "remaining_time": "1:36:22"}
{"current_steps": 238, "total_steps": 595, "loss": 0.0138, "lr": 7.508470903389311e-05, "epoch": 1.99163179916318, "percentage": 40.0, "elapsed_time": "1:04:02", "remaining_time": "1:36:03"}
{"current_steps": 239, "total_steps": 595, "loss": 0.0166, "lr": 7.48302949073969e-05, "epoch": 2.0, "percentage": 40.17, "elapsed_time": "1:04:14", "remaining_time": "1:35:42"}
{"current_steps": 240, "total_steps": 595, "loss": 0.0109, "lr": 7.457502458565672e-05, "epoch": 2.00836820083682, "percentage": 40.34, "elapsed_time": "1:04:28", "remaining_time": "1:35:22"}
{"current_steps": 240, "total_steps": 595, "eval_loss": 0.013845333829522133, "epoch": 2.00836820083682, "percentage": 40.34, "elapsed_time": "1:04:36", "remaining_time": "1:35:34"}
{"current_steps": 241, "total_steps": 595, "loss": 0.0102, "lr": 7.431890687087313e-05, "epoch": 2.01673640167364, "percentage": 40.5, "elapsed_time": "1:04:49", "remaining_time": "1:35:13"}
{"current_steps": 242, "total_steps": 595, "loss": 0.0103, "lr": 7.406195059446636e-05, "epoch": 2.0251046025104604, "percentage": 40.67, "elapsed_time": "1:05:05", "remaining_time": "1:34:56"}
{"current_steps": 243, "total_steps": 595, "loss": 0.0119, "lr": 7.380416461677187e-05, "epoch": 2.0334728033472804, "percentage": 40.84, "elapsed_time": "1:05:19", "remaining_time": "1:34:37"}
{"current_steps": 244, "total_steps": 595, "loss": 0.0107, "lr": 7.354555782673473e-05, "epoch": 2.0418410041841004, "percentage": 41.01, "elapsed_time": "1:05:32", "remaining_time": "1:34:16"}
{"current_steps": 245, "total_steps": 595, "loss": 0.0093, "lr": 7.328613914160318e-05, "epoch": 2.0502092050209204, "percentage": 41.18, "elapsed_time": "1:05:46", "remaining_time": "1:33:57"}
{"current_steps": 245, "total_steps": 595, "eval_loss": 0.014546514488756657, "epoch": 2.0502092050209204, "percentage": 41.18, "elapsed_time": "1:05:54", "remaining_time": "1:34:09"}
{"current_steps": 246, "total_steps": 595, "loss": 0.0117, "lr": 7.302591750662116e-05, "epoch": 2.0585774058577404, "percentage": 41.34, "elapsed_time": "1:06:08", "remaining_time": "1:33:50"}
{"current_steps": 247, "total_steps": 595, "loss": 0.01, "lr": 7.276490189471977e-05, "epoch": 2.066945606694561, "percentage": 41.51, "elapsed_time": "1:06:21", "remaining_time": "1:33:29"}
{"current_steps": 248, "total_steps": 595, "loss": 0.0111, "lr": 7.250310130620799e-05, "epoch": 2.075313807531381, "percentage": 41.68, "elapsed_time": "1:06:35", "remaining_time": "1:33:10"}
{"current_steps": 249, "total_steps": 595, "loss": 0.0115, "lr": 7.224052476846222e-05, "epoch": 2.083682008368201, "percentage": 41.85, "elapsed_time": "1:06:47", "remaining_time": "1:32:49"}
{"current_steps": 250, "total_steps": 595, "loss": 0.0102, "lr": 7.197718133561508e-05, "epoch": 2.092050209205021, "percentage": 42.02, "elapsed_time": "1:07:02", "remaining_time": "1:32:31"}
{"current_steps": 250, "total_steps": 595, "eval_loss": 0.014336950145661831, "epoch": 2.092050209205021, "percentage": 42.02, "elapsed_time": "1:07:10", "remaining_time": "1:32:42"}
{"current_steps": 251, "total_steps": 595, "loss": 0.0105, "lr": 7.171308008824316e-05, "epoch": 2.100418410041841, "percentage": 42.18, "elapsed_time": "1:07:30", "remaining_time": "1:32:31"}
{"current_steps": 252, "total_steps": 595, "loss": 0.0085, "lr": 7.144823013305394e-05, "epoch": 2.1087866108786613, "percentage": 42.35, "elapsed_time": "1:07:44", "remaining_time": "1:32:12"}
{"current_steps": 253, "total_steps": 595, "loss": 0.0116, "lr": 7.118264060257169e-05, "epoch": 2.1171548117154813, "percentage": 42.52, "elapsed_time": "1:07:57", "remaining_time": "1:31:52"}
{"current_steps": 254, "total_steps": 595, "loss": 0.0115, "lr": 7.091632065482272e-05, "epoch": 2.1255230125523012, "percentage": 42.69, "elapsed_time": "1:08:10", "remaining_time": "1:31:31"}
{"current_steps": 255, "total_steps": 595, "loss": 0.0104, "lr": 7.064927947301943e-05, "epoch": 2.1338912133891212, "percentage": 42.86, "elapsed_time": "1:08:25", "remaining_time": "1:31:13"}
{"current_steps": 255, "total_steps": 595, "eval_loss": 0.014133421704173088, "epoch": 2.1338912133891212, "percentage": 42.86, "elapsed_time": "1:08:33", "remaining_time": "1:31:24"}
{"current_steps": 256, "total_steps": 595, "loss": 0.0097, "lr": 7.038152626524373e-05, "epoch": 2.1422594142259412, "percentage": 43.03, "elapsed_time": "1:08:49", "remaining_time": "1:31:08"}
{"current_steps": 257, "total_steps": 595, "loss": 0.0106, "lr": 7.011307026412958e-05, "epoch": 2.1506276150627617, "percentage": 43.19, "elapsed_time": "1:09:03", "remaining_time": "1:30:49"}
{"current_steps": 258, "total_steps": 595, "loss": 0.0105, "lr": 6.984392072654453e-05, "epoch": 2.1589958158995817, "percentage": 43.36, "elapsed_time": "1:09:17", "remaining_time": "1:30:30"}
{"current_steps": 259, "total_steps": 595, "loss": 0.0096, "lr": 6.957408693327055e-05, "epoch": 2.1673640167364017, "percentage": 43.53, "elapsed_time": "1:09:31", "remaining_time": "1:30:12"}
{"current_steps": 260, "total_steps": 595, "loss": 0.0108, "lr": 6.930357818868409e-05, "epoch": 2.1757322175732217, "percentage": 43.7, "elapsed_time": "1:09:46", "remaining_time": "1:29:54"}
{"current_steps": 260, "total_steps": 595, "eval_loss": 0.0147059615701437, "epoch": 2.1757322175732217, "percentage": 43.7, "elapsed_time": "1:09:55", "remaining_time": "1:30:05"}
{"current_steps": 261, "total_steps": 595, "loss": 0.011, "lr": 6.903240382043514e-05, "epoch": 2.1841004184100417, "percentage": 43.87, "elapsed_time": "1:10:09", "remaining_time": "1:29:46"}
{"current_steps": 262, "total_steps": 595, "loss": 0.0108, "lr": 6.876057317912569e-05, "epoch": 2.192468619246862, "percentage": 44.03, "elapsed_time": "1:10:23", "remaining_time": "1:29:28"}
{"current_steps": 263, "total_steps": 595, "loss": 0.0106, "lr": 6.848809563798721e-05, "epoch": 2.200836820083682, "percentage": 44.2, "elapsed_time": "1:10:37", "remaining_time": "1:29:09"}
{"current_steps": 264, "total_steps": 595, "loss": 0.0101, "lr": 6.821498059255752e-05, "epoch": 2.209205020920502, "percentage": 44.37, "elapsed_time": "1:10:52", "remaining_time": "1:28:52"}
{"current_steps": 265, "total_steps": 595, "loss": 0.0104, "lr": 6.79412374603568e-05, "epoch": 2.217573221757322, "percentage": 44.54, "elapsed_time": "1:11:08", "remaining_time": "1:28:35"}
{"current_steps": 265, "total_steps": 595, "eval_loss": 0.014249371364712715, "epoch": 2.217573221757322, "percentage": 44.54, "elapsed_time": "1:11:16", "remaining_time": "1:28:45"}
{"current_steps": 266, "total_steps": 595, "loss": 0.0093, "lr": 6.766687568056281e-05, "epoch": 2.225941422594142, "percentage": 44.71, "elapsed_time": "1:11:30", "remaining_time": "1:28:26"}
{"current_steps": 267, "total_steps": 595, "loss": 0.0099, "lr": 6.739190471368548e-05, "epoch": 2.2343096234309625, "percentage": 44.87, "elapsed_time": "1:11:44", "remaining_time": "1:28:07"}
{"current_steps": 268, "total_steps": 595, "loss": 0.0105, "lr": 6.711633404124062e-05, "epoch": 2.2426778242677825, "percentage": 45.04, "elapsed_time": "1:11:59", "remaining_time": "1:27:50"}
{"current_steps": 269, "total_steps": 595, "loss": 0.01, "lr": 6.684017316542302e-05, "epoch": 2.2510460251046025, "percentage": 45.21, "elapsed_time": "1:12:14", "remaining_time": "1:27:33"}
{"current_steps": 270, "total_steps": 595, "loss": 0.0103, "lr": 6.656343160877881e-05, "epoch": 2.2594142259414225, "percentage": 45.38, "elapsed_time": "1:12:28", "remaining_time": "1:27:14"}
{"current_steps": 270, "total_steps": 595, "eval_loss": 0.014431845396757126, "epoch": 2.2594142259414225, "percentage": 45.38, "elapsed_time": "1:12:36", "remaining_time": "1:27:24"}
{"current_steps": 271, "total_steps": 595, "loss": 0.0098, "lr": 6.628611891387706e-05, "epoch": 2.2677824267782425, "percentage": 45.55, "elapsed_time": "1:12:50", "remaining_time": "1:27:05"}
{"current_steps": 272, "total_steps": 595, "loss": 0.0103, "lr": 6.600824464298082e-05, "epoch": 2.276150627615063, "percentage": 45.71, "elapsed_time": "1:13:04", "remaining_time": "1:26:46"}
{"current_steps": 273, "total_steps": 595, "loss": 0.0106, "lr": 6.572981837771726e-05, "epoch": 2.284518828451883, "percentage": 45.88, "elapsed_time": "1:13:18", "remaining_time": "1:26:27"}
{"current_steps": 274, "total_steps": 595, "loss": 0.0105, "lr": 6.545084971874738e-05, "epoch": 2.292887029288703, "percentage": 46.05, "elapsed_time": "1:13:32", "remaining_time": "1:26:08"}
{"current_steps": 275, "total_steps": 595, "loss": 0.0107, "lr": 6.517134828543496e-05, "epoch": 2.301255230125523, "percentage": 46.22, "elapsed_time": "1:13:47", "remaining_time": "1:25:51"}
{"current_steps": 275, "total_steps": 595, "eval_loss": 0.01435365341603756, "epoch": 2.301255230125523, "percentage": 46.22, "elapsed_time": "1:13:55", "remaining_time": "1:26:01"}
{"current_steps": 276, "total_steps": 595, "loss": 0.0107, "lr": 6.489132371551482e-05, "epoch": 2.309623430962343, "percentage": 46.39, "elapsed_time": "1:14:07", "remaining_time": "1:25:40"}
{"current_steps": 277, "total_steps": 595, "loss": 0.0108, "lr": 6.461078566476054e-05, "epoch": 2.3179916317991633, "percentage": 46.55, "elapsed_time": "1:14:22", "remaining_time": "1:25:22"}
{"current_steps": 278, "total_steps": 595, "loss": 0.0115, "lr": 6.43297438066514e-05, "epoch": 2.3263598326359833, "percentage": 46.72, "elapsed_time": "1:14:36", "remaining_time": "1:25:04"}
{"current_steps": 279, "total_steps": 595, "loss": 0.0101, "lr": 6.404820783203901e-05, "epoch": 2.3347280334728033, "percentage": 46.89, "elapsed_time": "1:14:51", "remaining_time": "1:24:47"}
{"current_steps": 280, "total_steps": 595, "loss": 0.0104, "lr": 6.3766187448813e-05, "epoch": 2.3430962343096233, "percentage": 47.06, "elapsed_time": "1:15:04", "remaining_time": "1:24:27"}
{"current_steps": 280, "total_steps": 595, "eval_loss": 0.01405297126621008, "epoch": 2.3430962343096233, "percentage": 47.06, "elapsed_time": "1:15:13", "remaining_time": "1:24:37"}
{"current_steps": 281, "total_steps": 595, "loss": 0.0099, "lr": 6.348369238156631e-05, "epoch": 2.3514644351464433, "percentage": 47.23, "elapsed_time": "1:15:28", "remaining_time": "1:24:19"}
{"current_steps": 282, "total_steps": 595, "loss": 0.0094, "lr": 6.32007323712599e-05, "epoch": 2.3598326359832638, "percentage": 47.39, "elapsed_time": "1:15:42", "remaining_time": "1:24:01"}
{"current_steps": 283, "total_steps": 595, "loss": 0.0106, "lr": 6.29173171748868e-05, "epoch": 2.3682008368200838, "percentage": 47.56, "elapsed_time": "1:15:57", "remaining_time": "1:23:44"}
{"current_steps": 284, "total_steps": 595, "loss": 0.0096, "lr": 6.263345656513576e-05, "epoch": 2.3765690376569037, "percentage": 47.73, "elapsed_time": "1:16:13", "remaining_time": "1:23:28"}
{"current_steps": 285, "total_steps": 595, "loss": 0.0092, "lr": 6.234916033005421e-05, "epoch": 2.3849372384937237, "percentage": 47.9, "elapsed_time": "1:16:26", "remaining_time": "1:23:09"}
{"current_steps": 285, "total_steps": 595, "eval_loss": 0.014250432141125202, "epoch": 2.3849372384937237, "percentage": 47.9, "elapsed_time": "1:16:35", "remaining_time": "1:23:18"}
{"current_steps": 286, "total_steps": 595, "loss": 0.011, "lr": 6.206443827271073e-05, "epoch": 2.393305439330544, "percentage": 48.07, "elapsed_time": "1:16:50", "remaining_time": "1:23:01"}
{"current_steps": 287, "total_steps": 595, "loss": 0.0101, "lr": 6.17793002108571e-05, "epoch": 2.401673640167364, "percentage": 48.24, "elapsed_time": "1:17:05", "remaining_time": "1:22:44"}
{"current_steps": 288, "total_steps": 595, "loss": 0.0092, "lr": 6.149375597658967e-05, "epoch": 2.410041841004184, "percentage": 48.4, "elapsed_time": "1:17:19", "remaining_time": "1:22:25"}
{"current_steps": 289, "total_steps": 595, "loss": 0.0105, "lr": 6.12078154160104e-05, "epoch": 2.418410041841004, "percentage": 48.57, "elapsed_time": "1:17:34", "remaining_time": "1:22:08"}
{"current_steps": 290, "total_steps": 595, "loss": 0.0107, "lr": 6.092148838888732e-05, "epoch": 2.426778242677824, "percentage": 48.74, "elapsed_time": "1:17:49", "remaining_time": "1:21:50"}
{"current_steps": 290, "total_steps": 595, "eval_loss": 0.01402355171740055, "epoch": 2.426778242677824, "percentage": 48.74, "elapsed_time": "1:17:57", "remaining_time": "1:21:59"}
{"current_steps": 291, "total_steps": 595, "loss": 0.0107, "lr": 6.0634784768314564e-05, "epoch": 2.435146443514644, "percentage": 48.91, "elapsed_time": "1:18:12", "remaining_time": "1:21:41"}
{"current_steps": 292, "total_steps": 595, "loss": 0.0095, "lr": 6.0347714440371924e-05, "epoch": 2.4435146443514646, "percentage": 49.08, "elapsed_time": "1:18:26", "remaining_time": "1:21:23"}
{"current_steps": 293, "total_steps": 595, "loss": 0.011, "lr": 6.0060287303783924e-05, "epoch": 2.4518828451882846, "percentage": 49.24, "elapsed_time": "1:18:41", "remaining_time": "1:21:06"}
{"current_steps": 294, "total_steps": 595, "loss": 0.0099, "lr": 5.977251326957852e-05, "epoch": 2.4602510460251046, "percentage": 49.41, "elapsed_time": "1:18:53", "remaining_time": "1:20:46"}
{"current_steps": 295, "total_steps": 595, "loss": 0.0112, "lr": 5.9484402260745386e-05, "epoch": 2.4686192468619246, "percentage": 49.58, "elapsed_time": "1:19:08", "remaining_time": "1:20:29"}
{"current_steps": 295, "total_steps": 595, "eval_loss": 0.014348245225846767, "epoch": 2.4686192468619246, "percentage": 49.58, "elapsed_time": "1:19:16", "remaining_time": "1:20:37"}
{"current_steps": 296, "total_steps": 595, "loss": 0.0096, "lr": 5.919596421189368e-05, "epoch": 2.476987447698745, "percentage": 49.75, "elapsed_time": "1:19:32", "remaining_time": "1:20:20"}
{"current_steps": 297, "total_steps": 595, "loss": 0.0085, "lr": 5.8907209068909554e-05, "epoch": 2.485355648535565, "percentage": 49.92, "elapsed_time": "1:19:45", "remaining_time": "1:20:01"}
{"current_steps": 298, "total_steps": 595, "loss": 0.0101, "lr": 5.8618146788613105e-05, "epoch": 2.493723849372385, "percentage": 50.08, "elapsed_time": "1:19:59", "remaining_time": "1:19:43"}
{"current_steps": 299, "total_steps": 595, "loss": 0.0102, "lr": 5.832878733841513e-05, "epoch": 2.502092050209205, "percentage": 50.25, "elapsed_time": "1:20:13", "remaining_time": "1:19:25"}
{"current_steps": 300, "total_steps": 595, "loss": 0.01, "lr": 5.803914069597342e-05, "epoch": 2.510460251046025, "percentage": 50.42, "elapsed_time": "1:20:28", "remaining_time": "1:19:08"}
{"current_steps": 300, "total_steps": 595, "eval_loss": 0.014326265081763268, "epoch": 2.510460251046025, "percentage": 50.42, "elapsed_time": "1:20:36", "remaining_time": "1:19:16"}
{"current_steps": 301, "total_steps": 595, "loss": 0.0092, "lr": 5.7749216848848664e-05, "epoch": 2.518828451882845, "percentage": 50.59, "elapsed_time": "1:20:57", "remaining_time": "1:19:04"}
{"current_steps": 302, "total_steps": 595, "loss": 0.0109, "lr": 5.7459025794160136e-05, "epoch": 2.5271966527196654, "percentage": 50.76, "elapsed_time": "1:21:12", "remaining_time": "1:18:47"}
{"current_steps": 303, "total_steps": 595, "loss": 0.0089, "lr": 5.716857753824086e-05, "epoch": 2.5355648535564854, "percentage": 50.92, "elapsed_time": "1:21:26", "remaining_time": "1:18:29"}
{"current_steps": 304, "total_steps": 595, "loss": 0.0095, "lr": 5.6877882096292715e-05, "epoch": 2.5439330543933054, "percentage": 51.09, "elapsed_time": "1:21:41", "remaining_time": "1:18:11"}
{"current_steps": 305, "total_steps": 595, "loss": 0.0096, "lr": 5.6586949492040944e-05, "epoch": 2.5523012552301254, "percentage": 51.26, "elapsed_time": "1:21:55", "remaining_time": "1:17:53"}
{"current_steps": 305, "total_steps": 595, "eval_loss": 0.01382070779800415, "epoch": 2.5523012552301254, "percentage": 51.26, "elapsed_time": "1:22:03", "remaining_time": "1:18:01"}
{"current_steps": 306, "total_steps": 595, "loss": 0.0099, "lr": 5.629578975738865e-05, "epoch": 2.560669456066946, "percentage": 51.43, "elapsed_time": "1:22:17", "remaining_time": "1:17:43"}
{"current_steps": 307, "total_steps": 595, "loss": 0.0104, "lr": 5.6004412932070835e-05, "epoch": 2.569037656903766, "percentage": 51.6, "elapsed_time": "1:22:30", "remaining_time": "1:17:24"}
{"current_steps": 308, "total_steps": 595, "loss": 0.0096, "lr": 5.57128290633081e-05, "epoch": 2.577405857740586, "percentage": 51.76, "elapsed_time": "1:22:44", "remaining_time": "1:17:06"}
{"current_steps": 309, "total_steps": 595, "loss": 0.0095, "lr": 5.542104820546041e-05, "epoch": 2.585774058577406, "percentage": 51.93, "elapsed_time": "1:22:59", "remaining_time": "1:16:48"}
{"current_steps": 310, "total_steps": 595, "loss": 0.0096, "lr": 5.512908041968018e-05, "epoch": 2.594142259414226, "percentage": 52.1, "elapsed_time": "1:23:12", "remaining_time": "1:16:30"}
{"current_steps": 310, "total_steps": 595, "eval_loss": 0.013671735301613808, "epoch": 2.594142259414226, "percentage": 52.1, "elapsed_time": "1:23:20", "remaining_time": "1:16:37"}
{"current_steps": 311, "total_steps": 595, "loss": 0.01, "lr": 5.483693577356552e-05, "epoch": 2.602510460251046, "percentage": 52.27, "elapsed_time": "1:23:35", "remaining_time": "1:16:20"}
{"current_steps": 312, "total_steps": 595, "loss": 0.0099, "lr": 5.454462434081302e-05, "epoch": 2.6108786610878663, "percentage": 52.44, "elapsed_time": "1:23:50", "remaining_time": "1:16:03"}
{"current_steps": 313, "total_steps": 595, "loss": 0.0097, "lr": 5.425215620087033e-05, "epoch": 2.6192468619246863, "percentage": 52.61, "elapsed_time": "1:24:07", "remaining_time": "1:15:47"}
{"current_steps": 314, "total_steps": 595, "loss": 0.0108, "lr": 5.395954143858871e-05, "epoch": 2.6276150627615062, "percentage": 52.77, "elapsed_time": "1:24:22", "remaining_time": "1:15:30"}
{"current_steps": 315, "total_steps": 595, "loss": 0.0099, "lr": 5.36667901438752e-05, "epoch": 2.6359832635983262, "percentage": 52.94, "elapsed_time": "1:24:36", "remaining_time": "1:15:12"}
{"current_steps": 315, "total_steps": 595, "eval_loss": 0.013724744319915771, "epoch": 2.6359832635983262, "percentage": 52.94, "elapsed_time": "1:24:44", "remaining_time": "1:15:19"}
{"current_steps": 316, "total_steps": 595, "loss": 0.0104, "lr": 5.337391241134476e-05, "epoch": 2.6443514644351467, "percentage": 53.11, "elapsed_time": "1:24:58", "remaining_time": "1:15:01"}
{"current_steps": 317, "total_steps": 595, "loss": 0.0101, "lr": 5.3080918339972175e-05, "epoch": 2.6527196652719667, "percentage": 53.28, "elapsed_time": "1:25:11", "remaining_time": "1:14:42"}
{"current_steps": 318, "total_steps": 595, "loss": 0.0109, "lr": 5.278781803274375e-05, "epoch": 2.6610878661087867, "percentage": 53.45, "elapsed_time": "1:25:26", "remaining_time": "1:14:25"}
{"current_steps": 319, "total_steps": 595, "loss": 0.0105, "lr": 5.249462159630908e-05, "epoch": 2.6694560669456067, "percentage": 53.61, "elapsed_time": "1:25:39", "remaining_time": "1:14:06"}
{"current_steps": 320, "total_steps": 595, "loss": 0.009, "lr": 5.220133914063239e-05, "epoch": 2.6778242677824267, "percentage": 53.78, "elapsed_time": "1:25:53", "remaining_time": "1:13:48"}
{"current_steps": 320, "total_steps": 595, "eval_loss": 0.013836627826094627, "epoch": 2.6778242677824267, "percentage": 53.78, "elapsed_time": "1:26:01", "remaining_time": "1:13:55"}
{"current_steps": 321, "total_steps": 595, "loss": 0.0097, "lr": 5.1907980778644114e-05, "epoch": 2.6861924686192467, "percentage": 53.95, "elapsed_time": "1:26:15", "remaining_time": "1:13:38"}
{"current_steps": 322, "total_steps": 595, "loss": 0.0112, "lr": 5.161455662589201e-05, "epoch": 2.694560669456067, "percentage": 54.12, "elapsed_time": "1:26:28", "remaining_time": "1:13:19"}
{"current_steps": 323, "total_steps": 595, "loss": 0.0106, "lr": 5.132107680019241e-05, "epoch": 2.702928870292887, "percentage": 54.29, "elapsed_time": "1:26:41", "remaining_time": "1:13:00"}
{"current_steps": 324, "total_steps": 595, "loss": 0.0092, "lr": 5.102755142128143e-05, "epoch": 2.711297071129707, "percentage": 54.45, "elapsed_time": "1:26:57", "remaining_time": "1:12:43"}
{"current_steps": 325, "total_steps": 595, "loss": 0.0097, "lr": 5.073399061046583e-05, "epoch": 2.719665271966527, "percentage": 54.62, "elapsed_time": "1:27:12", "remaining_time": "1:12:26"}
{"current_steps": 325, "total_steps": 595, "eval_loss": 0.01370433159172535, "epoch": 2.719665271966527, "percentage": 54.62, "elapsed_time": "1:27:20", "remaining_time": "1:12:33"}
{"current_steps": 326, "total_steps": 595, "loss": 0.0091, "lr": 5.044040449027426e-05, "epoch": 2.7280334728033475, "percentage": 54.79, "elapsed_time": "1:27:33", "remaining_time": "1:12:15"}
{"current_steps": 327, "total_steps": 595, "loss": 0.0097, "lr": 5.0146803184108006e-05, "epoch": 2.7364016736401675, "percentage": 54.96, "elapsed_time": "1:27:48", "remaining_time": "1:11:57"}
{"current_steps": 328, "total_steps": 595, "loss": 0.0105, "lr": 4.9853196815892e-05, "epoch": 2.7447698744769875, "percentage": 55.13, "elapsed_time": "1:28:03", "remaining_time": "1:11:40"}
{"current_steps": 329, "total_steps": 595, "loss": 0.0091, "lr": 4.9559595509725744e-05, "epoch": 2.7531380753138075, "percentage": 55.29, "elapsed_time": "1:28:18", "remaining_time": "1:11:24"}
{"current_steps": 330, "total_steps": 595, "loss": 0.0097, "lr": 4.926600938953418e-05, "epoch": 2.7615062761506275, "percentage": 55.46, "elapsed_time": "1:28:30", "remaining_time": "1:11:04"}
{"current_steps": 330, "total_steps": 595, "eval_loss": 0.01360410638153553, "epoch": 2.7615062761506275, "percentage": 55.46, "elapsed_time": "1:28:38", "remaining_time": "1:11:10"}
{"current_steps": 331, "total_steps": 595, "loss": 0.0094, "lr": 4.89724485787186e-05, "epoch": 2.7698744769874475, "percentage": 55.63, "elapsed_time": "1:28:51", "remaining_time": "1:10:52"}
{"current_steps": 332, "total_steps": 595, "loss": 0.0092, "lr": 4.86789231998076e-05, "epoch": 2.778242677824268, "percentage": 55.8, "elapsed_time": "1:29:05", "remaining_time": "1:10:34"}
{"current_steps": 333, "total_steps": 595, "loss": 0.0093, "lr": 4.8385443374108e-05, "epoch": 2.786610878661088, "percentage": 55.97, "elapsed_time": "1:29:19", "remaining_time": "1:10:17"}
{"current_steps": 334, "total_steps": 595, "loss": 0.0116, "lr": 4.809201922135589e-05, "epoch": 2.794979079497908, "percentage": 56.13, "elapsed_time": "1:29:33", "remaining_time": "1:09:59"}
{"current_steps": 335, "total_steps": 595, "loss": 0.0108, "lr": 4.7798660859367615e-05, "epoch": 2.803347280334728, "percentage": 56.3, "elapsed_time": "1:29:49", "remaining_time": "1:09:42"}
{"current_steps": 335, "total_steps": 595, "eval_loss": 0.013578813523054123, "epoch": 2.803347280334728, "percentage": 56.3, "elapsed_time": "1:29:57", "remaining_time": "1:09:49"}
{"current_steps": 336, "total_steps": 595, "loss": 0.0097, "lr": 4.750537840369095e-05, "epoch": 2.8117154811715483, "percentage": 56.47, "elapsed_time": "1:30:10", "remaining_time": "1:09:30"}
{"current_steps": 337, "total_steps": 595, "loss": 0.0092, "lr": 4.721218196725627e-05, "epoch": 2.8200836820083683, "percentage": 56.64, "elapsed_time": "1:30:25", "remaining_time": "1:09:13"}
{"current_steps": 338, "total_steps": 595, "loss": 0.0114, "lr": 4.691908166002784e-05, "epoch": 2.8284518828451883, "percentage": 56.81, "elapsed_time": "1:30:40", "remaining_time": "1:08:56"}
{"current_steps": 339, "total_steps": 595, "loss": 0.0102, "lr": 4.662608758865524e-05, "epoch": 2.8368200836820083, "percentage": 56.97, "elapsed_time": "1:30:55", "remaining_time": "1:08:39"}
{"current_steps": 340, "total_steps": 595, "loss": 0.0092, "lr": 4.633320985612481e-05, "epoch": 2.8451882845188283, "percentage": 57.14, "elapsed_time": "1:31:10", "remaining_time": "1:08:22"}
{"current_steps": 340, "total_steps": 595, "eval_loss": 0.01316875871270895, "epoch": 2.8451882845188283, "percentage": 57.14, "elapsed_time": "1:31:18", "remaining_time": "1:08:29"}
{"current_steps": 341, "total_steps": 595, "loss": 0.0093, "lr": 4.60404585614113e-05, "epoch": 2.8535564853556483, "percentage": 57.31, "elapsed_time": "1:31:32", "remaining_time": "1:08:11"}
{"current_steps": 342, "total_steps": 595, "loss": 0.0101, "lr": 4.5747843799129684e-05, "epoch": 2.8619246861924688, "percentage": 57.48, "elapsed_time": "1:31:48", "remaining_time": "1:07:55"}
{"current_steps": 343, "total_steps": 595, "loss": 0.0098, "lr": 4.545537565918699e-05, "epoch": 2.8702928870292888, "percentage": 57.65, "elapsed_time": "1:32:03", "remaining_time": "1:07:38"}
{"current_steps": 344, "total_steps": 595, "loss": 0.009, "lr": 4.5163064226434475e-05, "epoch": 2.8786610878661087, "percentage": 57.82, "elapsed_time": "1:32:16", "remaining_time": "1:07:19"}
{"current_steps": 345, "total_steps": 595, "loss": 0.0092, "lr": 4.487091958031984e-05, "epoch": 2.8870292887029287, "percentage": 57.98, "elapsed_time": "1:32:30", "remaining_time": "1:07:02"}
{"current_steps": 345, "total_steps": 595, "eval_loss": 0.013155767694115639, "epoch": 2.8870292887029287, "percentage": 57.98, "elapsed_time": "1:32:38", "remaining_time": "1:07:08"}
{"current_steps": 346, "total_steps": 595, "loss": 0.0101, "lr": 4.457895179453961e-05, "epoch": 2.895397489539749, "percentage": 58.15, "elapsed_time": "1:32:53", "remaining_time": "1:06:51"}
{"current_steps": 347, "total_steps": 595, "loss": 0.0096, "lr": 4.42871709366919e-05, "epoch": 2.903765690376569, "percentage": 58.32, "elapsed_time": "1:33:08", "remaining_time": "1:06:34"}
{"current_steps": 348, "total_steps": 595, "loss": 0.0106, "lr": 4.3995587067929177e-05, "epoch": 2.912133891213389, "percentage": 58.49, "elapsed_time": "1:33:24", "remaining_time": "1:06:18"}
{"current_steps": 349, "total_steps": 595, "loss": 0.0105, "lr": 4.3704210242611346e-05, "epoch": 2.920502092050209, "percentage": 58.66, "elapsed_time": "1:33:38", "remaining_time": "1:06:00"}
{"current_steps": 350, "total_steps": 595, "loss": 0.0095, "lr": 4.341305050795907e-05, "epoch": 2.928870292887029, "percentage": 58.82, "elapsed_time": "1:33:54", "remaining_time": "1:05:44"}
{"current_steps": 350, "total_steps": 595, "eval_loss": 0.012959838844835758, "epoch": 2.928870292887029, "percentage": 58.82, "elapsed_time": "1:34:02", "remaining_time": "1:05:49"}
{"current_steps": 351, "total_steps": 595, "loss": 0.01, "lr": 4.31221179037073e-05, "epoch": 2.937238493723849, "percentage": 58.99, "elapsed_time": "1:34:24", "remaining_time": "1:05:37"}
{"current_steps": 352, "total_steps": 595, "loss": 0.0096, "lr": 4.283142246175915e-05, "epoch": 2.9456066945606696, "percentage": 59.16, "elapsed_time": "1:34:39", "remaining_time": "1:05:20"}
{"current_steps": 353, "total_steps": 595, "loss": 0.0094, "lr": 4.2540974205839876e-05, "epoch": 2.9539748953974896, "percentage": 59.33, "elapsed_time": "1:34:54", "remaining_time": "1:05:03"}
{"current_steps": 354, "total_steps": 595, "loss": 0.011, "lr": 4.2250783151151334e-05, "epoch": 2.9623430962343096, "percentage": 59.5, "elapsed_time": "1:35:08", "remaining_time": "1:04:46"}
{"current_steps": 355, "total_steps": 595, "loss": 0.0094, "lr": 4.1960859304026594e-05, "epoch": 2.9707112970711296, "percentage": 59.66, "elapsed_time": "1:35:23", "remaining_time": "1:04:29"}
{"current_steps": 355, "total_steps": 595, "eval_loss": 0.012675998732447624, "epoch": 2.9707112970711296, "percentage": 59.66, "elapsed_time": "1:35:32", "remaining_time": "1:04:35"}
{"current_steps": 356, "total_steps": 595, "loss": 0.0102, "lr": 4.167121266158488e-05, "epoch": 2.97907949790795, "percentage": 59.83, "elapsed_time": "1:35:45", "remaining_time": "1:04:17"}
{"current_steps": 357, "total_steps": 595, "loss": 0.0085, "lr": 4.1381853211386914e-05, "epoch": 2.98744769874477, "percentage": 60.0, "elapsed_time": "1:35:58", "remaining_time": "1:03:58"}
{"current_steps": 358, "total_steps": 595, "loss": 0.0098, "lr": 4.109279093109045e-05, "epoch": 2.99581589958159, "percentage": 60.17, "elapsed_time": "1:36:12", "remaining_time": "1:03:41"}
{"current_steps": 359, "total_steps": 595, "loss": 0.0133, "lr": 4.080403578810631e-05, "epoch": 3.00418410041841, "percentage": 60.34, "elapsed_time": "1:36:25", "remaining_time": "1:03:23"}
{"current_steps": 360, "total_steps": 595, "loss": 0.0088, "lr": 4.051559773925462e-05, "epoch": 3.01255230125523, "percentage": 60.5, "elapsed_time": "1:36:41", "remaining_time": "1:03:07"}
{"current_steps": 360, "total_steps": 595, "eval_loss": 0.012736815959215164, "epoch": 3.01255230125523, "percentage": 60.5, "elapsed_time": "1:36:49", "remaining_time": "1:03:12"}
{"current_steps": 361, "total_steps": 595, "loss": 0.0093, "lr": 4.022748673042149e-05, "epoch": 3.02092050209205, "percentage": 60.67, "elapsed_time": "1:37:04", "remaining_time": "1:02:55"}
{"current_steps": 362, "total_steps": 595, "loss": 0.007, "lr": 3.9939712696216094e-05, "epoch": 3.0292887029288704, "percentage": 60.84, "elapsed_time": "1:37:17", "remaining_time": "1:02:37"}
{"current_steps": 363, "total_steps": 595, "loss": 0.0082, "lr": 3.965228555962808e-05, "epoch": 3.0376569037656904, "percentage": 61.01, "elapsed_time": "1:37:31", "remaining_time": "1:02:20"}
{"current_steps": 364, "total_steps": 595, "loss": 0.0074, "lr": 3.9365215231685434e-05, "epoch": 3.0460251046025104, "percentage": 61.18, "elapsed_time": "1:37:46", "remaining_time": "1:02:03"}
{"current_steps": 365, "total_steps": 595, "loss": 0.0086, "lr": 3.907851161111269e-05, "epoch": 3.0543933054393304, "percentage": 61.34, "elapsed_time": "1:38:01", "remaining_time": "1:01:46"}
{"current_steps": 365, "total_steps": 595, "eval_loss": 0.013066377490758896, "epoch": 3.0543933054393304, "percentage": 61.34, "elapsed_time": "1:38:10", "remaining_time": "1:01:51"}
{"current_steps": 366, "total_steps": 595, "loss": 0.0095, "lr": 3.879218458398962e-05, "epoch": 3.062761506276151, "percentage": 61.51, "elapsed_time": "1:38:25", "remaining_time": "1:01:34"}
{"current_steps": 367, "total_steps": 595, "loss": 0.0076, "lr": 3.8506244023410345e-05, "epoch": 3.071129707112971, "percentage": 61.68, "elapsed_time": "1:38:39", "remaining_time": "1:01:17"}
{"current_steps": 368, "total_steps": 595, "loss": 0.0073, "lr": 3.82206997891429e-05, "epoch": 3.079497907949791, "percentage": 61.85, "elapsed_time": "1:38:53", "remaining_time": "1:01:00"}
{"current_steps": 369, "total_steps": 595, "loss": 0.0079, "lr": 3.7935561727289265e-05, "epoch": 3.087866108786611, "percentage": 62.02, "elapsed_time": "1:39:10", "remaining_time": "1:00:44"}
{"current_steps": 370, "total_steps": 595, "loss": 0.0094, "lr": 3.7650839669945804e-05, "epoch": 3.096234309623431, "percentage": 62.18, "elapsed_time": "1:39:25", "remaining_time": "1:00:27"}
{"current_steps": 370, "total_steps": 595, "eval_loss": 0.01338866539299488, "epoch": 3.096234309623431, "percentage": 62.18, "elapsed_time": "1:39:33", "remaining_time": "1:00:32"}
{"current_steps": 371, "total_steps": 595, "loss": 0.0069, "lr": 3.736654343486425e-05, "epoch": 3.104602510460251, "percentage": 62.35, "elapsed_time": "1:39:47", "remaining_time": "1:00:14"}
{"current_steps": 372, "total_steps": 595, "loss": 0.0075, "lr": 3.708268282511321e-05, "epoch": 3.1129707112970713, "percentage": 62.52, "elapsed_time": "1:40:01", "remaining_time": "0:59:57"}
{"current_steps": 373, "total_steps": 595, "loss": 0.0086, "lr": 3.679926762874012e-05, "epoch": 3.1213389121338913, "percentage": 62.69, "elapsed_time": "1:40:14", "remaining_time": "0:59:39"}
{"current_steps": 374, "total_steps": 595, "loss": 0.0088, "lr": 3.65163076184337e-05, "epoch": 3.1297071129707112, "percentage": 62.86, "elapsed_time": "1:40:27", "remaining_time": "0:59:21"}
{"current_steps": 375, "total_steps": 595, "loss": 0.0075, "lr": 3.623381255118702e-05, "epoch": 3.1380753138075312, "percentage": 63.03, "elapsed_time": "1:40:42", "remaining_time": "0:59:04"}
{"current_steps": 375, "total_steps": 595, "eval_loss": 0.013682931661605835, "epoch": 3.1380753138075312, "percentage": 63.03, "elapsed_time": "1:40:50", "remaining_time": "0:59:09"}
{"current_steps": 376, "total_steps": 595, "loss": 0.0075, "lr": 3.5951792167961e-05, "epoch": 3.1464435146443517, "percentage": 63.19, "elapsed_time": "1:41:04", "remaining_time": "0:58:52"}
{"current_steps": 377, "total_steps": 595, "loss": 0.0091, "lr": 3.567025619334861e-05, "epoch": 3.1548117154811717, "percentage": 63.36, "elapsed_time": "1:41:18", "remaining_time": "0:58:35"}
{"current_steps": 378, "total_steps": 595, "loss": 0.0062, "lr": 3.538921433523949e-05, "epoch": 3.1631799163179917, "percentage": 63.53, "elapsed_time": "1:41:34", "remaining_time": "0:58:18"}
{"current_steps": 379, "total_steps": 595, "loss": 0.0076, "lr": 3.5108676284485176e-05, "epoch": 3.1715481171548117, "percentage": 63.7, "elapsed_time": "1:41:50", "remaining_time": "0:58:02"}
{"current_steps": 380, "total_steps": 595, "loss": 0.0068, "lr": 3.482865171456505e-05, "epoch": 3.1799163179916317, "percentage": 63.87, "elapsed_time": "1:42:03", "remaining_time": "0:57:44"}
{"current_steps": 380, "total_steps": 595, "eval_loss": 0.013625282794237137, "epoch": 3.1799163179916317, "percentage": 63.87, "elapsed_time": "1:42:11", "remaining_time": "0:57:49"}
{"current_steps": 381, "total_steps": 595, "loss": 0.0098, "lr": 3.4549150281252636e-05, "epoch": 3.1882845188284517, "percentage": 64.03, "elapsed_time": "1:42:26", "remaining_time": "0:57:32"}
{"current_steps": 382, "total_steps": 595, "loss": 0.0079, "lr": 3.427018162228276e-05, "epoch": 3.196652719665272, "percentage": 64.2, "elapsed_time": "1:42:40", "remaining_time": "0:57:15"}
{"current_steps": 383, "total_steps": 595, "loss": 0.0082, "lr": 3.3991755357019196e-05, "epoch": 3.205020920502092, "percentage": 64.37, "elapsed_time": "1:42:55", "remaining_time": "0:56:58"}
{"current_steps": 384, "total_steps": 595, "loss": 0.0068, "lr": 3.371388108612293e-05, "epoch": 3.213389121338912, "percentage": 64.54, "elapsed_time": "1:43:09", "remaining_time": "0:56:41"}
{"current_steps": 385, "total_steps": 595, "loss": 0.0096, "lr": 3.343656839122121e-05, "epoch": 3.221757322175732, "percentage": 64.71, "elapsed_time": "1:43:25", "remaining_time": "0:56:24"}
{"current_steps": 385, "total_steps": 595, "eval_loss": 0.013560273684561253, "epoch": 3.221757322175732, "percentage": 64.71, "elapsed_time": "1:43:33", "remaining_time": "0:56:29"}
{"current_steps": 386, "total_steps": 595, "loss": 0.0059, "lr": 3.3159826834576994e-05, "epoch": 3.2301255230125525, "percentage": 64.87, "elapsed_time": "1:43:46", "remaining_time": "0:56:11"}
{"current_steps": 387, "total_steps": 595, "loss": 0.0082, "lr": 3.2883665958759394e-05, "epoch": 3.2384937238493725, "percentage": 65.04, "elapsed_time": "1:44:00", "remaining_time": "0:55:54"}
{"current_steps": 388, "total_steps": 595, "loss": 0.008, "lr": 3.260809528631452e-05, "epoch": 3.2468619246861925, "percentage": 65.21, "elapsed_time": "1:44:16", "remaining_time": "0:55:37"}
{"current_steps": 389, "total_steps": 595, "loss": 0.0067, "lr": 3.233312431943719e-05, "epoch": 3.2552301255230125, "percentage": 65.38, "elapsed_time": "1:44:29", "remaining_time": "0:55:19"}
{"current_steps": 390, "total_steps": 595, "loss": 0.0088, "lr": 3.205876253964321e-05, "epoch": 3.2635983263598325, "percentage": 65.55, "elapsed_time": "1:44:45", "remaining_time": "0:55:03"}
{"current_steps": 390, "total_steps": 595, "eval_loss": 0.013662769459187984, "epoch": 3.2635983263598325, "percentage": 65.55, "elapsed_time": "1:44:53", "remaining_time": "0:55:08"}
{"current_steps": 391, "total_steps": 595, "loss": 0.0066, "lr": 3.178501940744249e-05, "epoch": 3.2719665271966525, "percentage": 65.71, "elapsed_time": "1:45:07", "remaining_time": "0:54:51"}
{"current_steps": 392, "total_steps": 595, "loss": 0.0086, "lr": 3.1511904362012805e-05, "epoch": 3.280334728033473, "percentage": 65.88, "elapsed_time": "1:45:21", "remaining_time": "0:54:33"}
{"current_steps": 393, "total_steps": 595, "loss": 0.0066, "lr": 3.123942682087433e-05, "epoch": 3.288702928870293, "percentage": 66.05, "elapsed_time": "1:45:36", "remaining_time": "0:54:17"}
{"current_steps": 394, "total_steps": 595, "loss": 0.0082, "lr": 3.096759617956486e-05, "epoch": 3.297071129707113, "percentage": 66.22, "elapsed_time": "1:45:52", "remaining_time": "0:54:00"}
{"current_steps": 395, "total_steps": 595, "loss": 0.008, "lr": 3.069642181131592e-05, "epoch": 3.305439330543933, "percentage": 66.39, "elapsed_time": "1:46:07", "remaining_time": "0:53:44"}
{"current_steps": 395, "total_steps": 595, "eval_loss": 0.01378766167908907, "epoch": 3.305439330543933, "percentage": 66.39, "elapsed_time": "1:46:15", "remaining_time": "0:53:48"}
{"current_steps": 396, "total_steps": 595, "loss": 0.0089, "lr": 3.042591306672946e-05, "epoch": 3.3138075313807533, "percentage": 66.55, "elapsed_time": "1:46:28", "remaining_time": "0:53:30"}
{"current_steps": 397, "total_steps": 595, "loss": 0.0071, "lr": 3.0156079273455483e-05, "epoch": 3.3221757322175733, "percentage": 66.72, "elapsed_time": "1:46:42", "remaining_time": "0:53:13"}
{"current_steps": 398, "total_steps": 595, "loss": 0.0079, "lr": 2.9886929735870416e-05, "epoch": 3.3305439330543933, "percentage": 66.89, "elapsed_time": "1:46:56", "remaining_time": "0:52:55"}
{"current_steps": 399, "total_steps": 595, "loss": 0.0079, "lr": 2.9618473734756264e-05, "epoch": 3.3389121338912133, "percentage": 67.06, "elapsed_time": "1:47:10", "remaining_time": "0:52:38"}
{"current_steps": 400, "total_steps": 595, "loss": 0.0085, "lr": 2.935072052698059e-05, "epoch": 3.3472803347280333, "percentage": 67.23, "elapsed_time": "1:47:25", "remaining_time": "0:52:22"}
{"current_steps": 400, "total_steps": 595, "eval_loss": 0.013703197240829468, "epoch": 3.3472803347280333, "percentage": 67.23, "elapsed_time": "1:47:34", "remaining_time": "0:52:26"}
{"current_steps": 401, "total_steps": 595, "loss": 0.0079, "lr": 2.908367934517729e-05, "epoch": 3.3556485355648533, "percentage": 67.39, "elapsed_time": "1:47:54", "remaining_time": "0:52:12"}
{"current_steps": 402, "total_steps": 595, "loss": 0.0077, "lr": 2.881735939742831e-05, "epoch": 3.3640167364016738, "percentage": 67.56, "elapsed_time": "1:48:08", "remaining_time": "0:51:55"}
{"current_steps": 403, "total_steps": 595, "loss": 0.0075, "lr": 2.8551769866946077e-05, "epoch": 3.3723849372384938, "percentage": 67.73, "elapsed_time": "1:48:21", "remaining_time": "0:51:37"}
{"current_steps": 404, "total_steps": 595, "loss": 0.0079, "lr": 2.8286919911756836e-05, "epoch": 3.3807531380753137, "percentage": 67.9, "elapsed_time": "1:48:36", "remaining_time": "0:51:20"}
{"current_steps": 405, "total_steps": 595, "loss": 0.0091, "lr": 2.8022818664384944e-05, "epoch": 3.3891213389121337, "percentage": 68.07, "elapsed_time": "1:48:49", "remaining_time": "0:51:03"}
{"current_steps": 405, "total_steps": 595, "eval_loss": 0.013571958057582378, "epoch": 3.3891213389121337, "percentage": 68.07, "elapsed_time": "1:48:57", "remaining_time": "0:51:07"}
{"current_steps": 406, "total_steps": 595, "loss": 0.007, "lr": 2.77594752315378e-05, "epoch": 3.397489539748954, "percentage": 68.24, "elapsed_time": "1:49:11", "remaining_time": "0:50:49"}
{"current_steps": 407, "total_steps": 595, "loss": 0.0094, "lr": 2.7496898693792028e-05, "epoch": 3.405857740585774, "percentage": 68.4, "elapsed_time": "1:49:26", "remaining_time": "0:50:33"}
{"current_steps": 408, "total_steps": 595, "loss": 0.0079, "lr": 2.7235098105280243e-05, "epoch": 3.414225941422594, "percentage": 68.57, "elapsed_time": "1:49:40", "remaining_time": "0:50:16"}
{"current_steps": 409, "total_steps": 595, "loss": 0.0084, "lr": 2.697408249337886e-05, "epoch": 3.422594142259414, "percentage": 68.74, "elapsed_time": "1:49:56", "remaining_time": "0:49:59"}
{"current_steps": 410, "total_steps": 595, "loss": 0.0049, "lr": 2.671386085839682e-05, "epoch": 3.430962343096234, "percentage": 68.91, "elapsed_time": "1:50:08", "remaining_time": "0:49:41"}
{"current_steps": 410, "total_steps": 595, "eval_loss": 0.013367210514843464, "epoch": 3.430962343096234, "percentage": 68.91, "elapsed_time": "1:50:16", "remaining_time": "0:49:45"}
{"current_steps": 411, "total_steps": 595, "loss": 0.0089, "lr": 2.6454442173265282e-05, "epoch": 3.439330543933054, "percentage": 69.08, "elapsed_time": "1:50:32", "remaining_time": "0:49:29"}
{"current_steps": 412, "total_steps": 595, "loss": 0.0084, "lr": 2.6195835383228127e-05, "epoch": 3.4476987447698746, "percentage": 69.24, "elapsed_time": "1:50:46", "remaining_time": "0:49:12"}
{"current_steps": 413, "total_steps": 595, "loss": 0.0071, "lr": 2.5938049405533627e-05, "epoch": 3.4560669456066946, "percentage": 69.41, "elapsed_time": "1:51:00", "remaining_time": "0:48:55"}
{"current_steps": 414, "total_steps": 595, "loss": 0.0072, "lr": 2.5681093129126864e-05, "epoch": 3.4644351464435146, "percentage": 69.58, "elapsed_time": "1:51:14", "remaining_time": "0:48:37"}
{"current_steps": 415, "total_steps": 595, "loss": 0.0072, "lr": 2.542497541434329e-05, "epoch": 3.4728033472803346, "percentage": 69.75, "elapsed_time": "1:51:28", "remaining_time": "0:48:20"}
{"current_steps": 415, "total_steps": 595, "eval_loss": 0.013123424723744392, "epoch": 3.4728033472803346, "percentage": 69.75, "elapsed_time": "1:51:36", "remaining_time": "0:48:24"}
{"current_steps": 416, "total_steps": 595, "loss": 0.0082, "lr": 2.5169705092603125e-05, "epoch": 3.481171548117155, "percentage": 69.92, "elapsed_time": "1:51:50", "remaining_time": "0:48:07"}
{"current_steps": 417, "total_steps": 595, "loss": 0.0079, "lr": 2.491529096610692e-05, "epoch": 3.489539748953975, "percentage": 70.08, "elapsed_time": "1:52:04", "remaining_time": "0:47:50"}
{"current_steps": 418, "total_steps": 595, "loss": 0.0088, "lr": 2.4661741807532006e-05, "epoch": 3.497907949790795, "percentage": 70.25, "elapsed_time": "1:52:18", "remaining_time": "0:47:33"}
{"current_steps": 419, "total_steps": 595, "loss": 0.0089, "lr": 2.4409066359729997e-05, "epoch": 3.506276150627615, "percentage": 70.42, "elapsed_time": "1:52:33", "remaining_time": "0:47:16"}
{"current_steps": 420, "total_steps": 595, "loss": 0.0063, "lr": 2.4157273335425297e-05, "epoch": 3.514644351464435, "percentage": 70.59, "elapsed_time": "1:52:46", "remaining_time": "0:46:59"}
{"current_steps": 420, "total_steps": 595, "eval_loss": 0.013349597342312336, "epoch": 3.514644351464435, "percentage": 70.59, "elapsed_time": "1:52:54", "remaining_time": "0:47:02"}
{"current_steps": 421, "total_steps": 595, "loss": 0.0078, "lr": 2.390637141691471e-05, "epoch": 3.523012552301255, "percentage": 70.76, "elapsed_time": "1:53:08", "remaining_time": "0:46:45"}
{"current_steps": 422, "total_steps": 595, "loss": 0.0065, "lr": 2.3656369255768017e-05, "epoch": 3.5313807531380754, "percentage": 70.92, "elapsed_time": "1:53:23", "remaining_time": "0:46:29"}
{"current_steps": 423, "total_steps": 595, "loss": 0.0081, "lr": 2.340727547252969e-05, "epoch": 3.5397489539748954, "percentage": 71.09, "elapsed_time": "1:53:37", "remaining_time": "0:46:12"}
{"current_steps": 424, "total_steps": 595, "loss": 0.0092, "lr": 2.3159098656421614e-05, "epoch": 3.5481171548117154, "percentage": 71.26, "elapsed_time": "1:53:53", "remaining_time": "0:45:56"}
{"current_steps": 425, "total_steps": 595, "loss": 0.0076, "lr": 2.291184736504695e-05, "epoch": 3.5564853556485354, "percentage": 71.43, "elapsed_time": "1:54:09", "remaining_time": "0:45:39"}
{"current_steps": 425, "total_steps": 595, "eval_loss": 0.013108824379742146, "epoch": 3.5564853556485354, "percentage": 71.43, "elapsed_time": "1:54:17", "remaining_time": "0:45:43"}
{"current_steps": 426, "total_steps": 595, "loss": 0.0084, "lr": 2.2665530124094962e-05, "epoch": 3.564853556485356, "percentage": 71.6, "elapsed_time": "1:54:32", "remaining_time": "0:45:26"}
{"current_steps": 427, "total_steps": 595, "loss": 0.0086, "lr": 2.2420155427047167e-05, "epoch": 3.573221757322176, "percentage": 71.76, "elapsed_time": "1:54:47", "remaining_time": "0:45:09"}
{"current_steps": 428, "total_steps": 595, "loss": 0.0075, "lr": 2.2175731734884365e-05, "epoch": 3.581589958158996, "percentage": 71.93, "elapsed_time": "1:55:00", "remaining_time": "0:44:52"}
{"current_steps": 429, "total_steps": 595, "loss": 0.0071, "lr": 2.1932267475794917e-05, "epoch": 3.589958158995816, "percentage": 72.1, "elapsed_time": "1:55:14", "remaining_time": "0:44:35"}
{"current_steps": 430, "total_steps": 595, "loss": 0.0076, "lr": 2.1689771044884148e-05, "epoch": 3.598326359832636, "percentage": 72.27, "elapsed_time": "1:55:30", "remaining_time": "0:44:19"}
{"current_steps": 430, "total_steps": 595, "eval_loss": 0.012915154919028282, "epoch": 3.598326359832636, "percentage": 72.27, "elapsed_time": "1:55:38", "remaining_time": "0:44:22"}
{"current_steps": 431, "total_steps": 595, "loss": 0.0087, "lr": 2.1448250803884834e-05, "epoch": 3.606694560669456, "percentage": 72.44, "elapsed_time": "1:55:54", "remaining_time": "0:44:06"}
{"current_steps": 432, "total_steps": 595, "loss": 0.0066, "lr": 2.120771508086889e-05, "epoch": 3.6150627615062763, "percentage": 72.61, "elapsed_time": "1:56:07", "remaining_time": "0:43:49"}
{"current_steps": 433, "total_steps": 595, "loss": 0.0067, "lr": 2.0968172169960197e-05, "epoch": 3.6234309623430963, "percentage": 72.77, "elapsed_time": "1:56:22", "remaining_time": "0:43:32"}
{"current_steps": 434, "total_steps": 595, "loss": 0.0088, "lr": 2.0729630331048615e-05, "epoch": 3.6317991631799162, "percentage": 72.94, "elapsed_time": "1:56:37", "remaining_time": "0:43:15"}
{"current_steps": 435, "total_steps": 595, "loss": 0.0074, "lr": 2.0492097789505178e-05, "epoch": 3.6401673640167362, "percentage": 73.11, "elapsed_time": "1:56:52", "remaining_time": "0:42:59"}
{"current_steps": 435, "total_steps": 595, "eval_loss": 0.013006238266825676, "epoch": 3.6401673640167362, "percentage": 73.11, "elapsed_time": "1:57:01", "remaining_time": "0:43:02"}
{"current_steps": 436, "total_steps": 595, "loss": 0.0063, "lr": 2.0255582735898383e-05, "epoch": 3.6485355648535567, "percentage": 73.28, "elapsed_time": "1:57:15", "remaining_time": "0:42:45"}
{"current_steps": 437, "total_steps": 595, "loss": 0.0084, "lr": 2.0020093325711896e-05, "epoch": 3.6569037656903767, "percentage": 73.45, "elapsed_time": "1:57:29", "remaining_time": "0:42:28"}
{"current_steps": 438, "total_steps": 595, "loss": 0.0064, "lr": 1.9785637679063258e-05, "epoch": 3.6652719665271967, "percentage": 73.61, "elapsed_time": "1:57:42", "remaining_time": "0:42:11"}
{"current_steps": 439, "total_steps": 595, "loss": 0.0092, "lr": 1.9552223880423882e-05, "epoch": 3.6736401673640167, "percentage": 73.78, "elapsed_time": "1:57:58", "remaining_time": "0:41:55"}
{"current_steps": 440, "total_steps": 595, "loss": 0.0074, "lr": 1.931985997834031e-05, "epoch": 3.6820083682008367, "percentage": 73.95, "elapsed_time": "1:58:13", "remaining_time": "0:41:38"}
{"current_steps": 440, "total_steps": 595, "eval_loss": 0.01317664049565792, "epoch": 3.6820083682008367, "percentage": 73.95, "elapsed_time": "1:58:21", "remaining_time": "0:41:41"}
{"current_steps": 441, "total_steps": 595, "loss": 0.0079, "lr": 1.908855398515669e-05, "epoch": 3.6903765690376567, "percentage": 74.12, "elapsed_time": "1:58:33", "remaining_time": "0:41:24"}
{"current_steps": 442, "total_steps": 595, "loss": 0.0069, "lr": 1.8858313876738458e-05, "epoch": 3.698744769874477, "percentage": 74.29, "elapsed_time": "1:58:47", "remaining_time": "0:41:07"}
{"current_steps": 443, "total_steps": 595, "loss": 0.0083, "lr": 1.8629147592197372e-05, "epoch": 3.707112970711297, "percentage": 74.45, "elapsed_time": "1:59:01", "remaining_time": "0:40:50"}
{"current_steps": 444, "total_steps": 595, "loss": 0.0075, "lr": 1.840106303361771e-05, "epoch": 3.715481171548117, "percentage": 74.62, "elapsed_time": "1:59:15", "remaining_time": "0:40:33"}
{"current_steps": 445, "total_steps": 595, "loss": 0.0067, "lr": 1.8174068065783765e-05, "epoch": 3.723849372384937, "percentage": 74.79, "elapsed_time": "1:59:27", "remaining_time": "0:40:16"}
{"current_steps": 445, "total_steps": 595, "eval_loss": 0.013197257183492184, "epoch": 3.723849372384937, "percentage": 74.79, "elapsed_time": "1:59:36", "remaining_time": "0:40:18"}
{"current_steps": 446, "total_steps": 595, "loss": 0.0077, "lr": 1.7948170515908757e-05, "epoch": 3.7322175732217575, "percentage": 74.96, "elapsed_time": "1:59:51", "remaining_time": "0:40:02"}
{"current_steps": 447, "total_steps": 595, "loss": 0.0081, "lr": 1.7723378173364836e-05, "epoch": 3.7405857740585775, "percentage": 75.13, "elapsed_time": "2:00:06", "remaining_time": "0:39:45"}
{"current_steps": 448, "total_steps": 595, "loss": 0.0076, "lr": 1.7499698789414536e-05, "epoch": 3.7489539748953975, "percentage": 75.29, "elapsed_time": "2:00:20", "remaining_time": "0:39:29"}
{"current_steps": 449, "total_steps": 595, "loss": 0.0092, "lr": 1.727714007694348e-05, "epoch": 3.7573221757322175, "percentage": 75.46, "elapsed_time": "2:00:34", "remaining_time": "0:39:12"}
{"current_steps": 450, "total_steps": 595, "loss": 0.0064, "lr": 1.705570971019445e-05, "epoch": 3.7656903765690375, "percentage": 75.63, "elapsed_time": "2:00:47", "remaining_time": "0:38:55"}
{"current_steps": 450, "total_steps": 595, "eval_loss": 0.013023738749325275, "epoch": 3.7656903765690375, "percentage": 75.63, "elapsed_time": "2:00:56", "remaining_time": "0:38:58"}
{"current_steps": 451, "total_steps": 595, "loss": 0.0077, "lr": 1.683541532450272e-05, "epoch": 3.7740585774058575, "percentage": 75.8, "elapsed_time": "2:01:16", "remaining_time": "0:38:43"}
{"current_steps": 452, "total_steps": 595, "loss": 0.0083, "lr": 1.6616264516032807e-05, "epoch": 3.782426778242678, "percentage": 75.97, "elapsed_time": "2:01:30", "remaining_time": "0:38:26"}
{"current_steps": 453, "total_steps": 595, "loss": 0.0076, "lr": 1.6398264841516564e-05, "epoch": 3.790794979079498, "percentage": 76.13, "elapsed_time": "2:01:45", "remaining_time": "0:38:09"}
{"current_steps": 454, "total_steps": 595, "loss": 0.0069, "lr": 1.618142381799256e-05, "epoch": 3.799163179916318, "percentage": 76.3, "elapsed_time": "2:01:59", "remaining_time": "0:37:53"}
{"current_steps": 455, "total_steps": 595, "loss": 0.0091, "lr": 1.5965748922546876e-05, "epoch": 3.8075313807531384, "percentage": 76.47, "elapsed_time": "2:02:13", "remaining_time": "0:37:36"}
{"current_steps": 455, "total_steps": 595, "eval_loss": 0.013014528900384903, "epoch": 3.8075313807531384, "percentage": 76.47, "elapsed_time": "2:02:21", "remaining_time": "0:37:39"}
{"current_steps": 456, "total_steps": 595, "loss": 0.0069, "lr": 1.5751247592055333e-05, "epoch": 3.8158995815899583, "percentage": 76.64, "elapsed_time": "2:02:36", "remaining_time": "0:37:22"}
{"current_steps": 457, "total_steps": 595, "loss": 0.0086, "lr": 1.5537927222927047e-05, "epoch": 3.8242677824267783, "percentage": 76.81, "elapsed_time": "2:02:52", "remaining_time": "0:37:06"}
{"current_steps": 458, "total_steps": 595, "loss": 0.0068, "lr": 1.5325795170849315e-05, "epoch": 3.8326359832635983, "percentage": 76.97, "elapsed_time": "2:03:06", "remaining_time": "0:36:49"}
{"current_steps": 459, "total_steps": 595, "loss": 0.0078, "lr": 1.5114858750534067e-05, "epoch": 3.8410041841004183, "percentage": 77.14, "elapsed_time": "2:03:20", "remaining_time": "0:36:32"}
{"current_steps": 460, "total_steps": 595, "loss": 0.0074, "lr": 1.4905125235465589e-05, "epoch": 3.8493723849372383, "percentage": 77.31, "elapsed_time": "2:03:33", "remaining_time": "0:36:15"}
{"current_steps": 460, "total_steps": 595, "eval_loss": 0.013112700544297695, "epoch": 3.8493723849372383, "percentage": 77.31, "elapsed_time": "2:03:41", "remaining_time": "0:36:18"}
{"current_steps": 461, "total_steps": 595, "loss": 0.0075, "lr": 1.4696601857649738e-05, "epoch": 3.8577405857740583, "percentage": 77.48, "elapsed_time": "2:03:54", "remaining_time": "0:36:01"}
{"current_steps": 462, "total_steps": 595, "loss": 0.0082, "lr": 1.4489295807364556e-05, "epoch": 3.8661087866108788, "percentage": 77.65, "elapsed_time": "2:04:08", "remaining_time": "0:35:44"}
{"current_steps": 463, "total_steps": 595, "loss": 0.0073, "lr": 1.4283214232912345e-05, "epoch": 3.8744769874476988, "percentage": 77.82, "elapsed_time": "2:04:22", "remaining_time": "0:35:27"}
{"current_steps": 464, "total_steps": 595, "loss": 0.0063, "lr": 1.4078364240373192e-05, "epoch": 3.8828451882845187, "percentage": 77.98, "elapsed_time": "2:04:37", "remaining_time": "0:35:11"}
{"current_steps": 465, "total_steps": 595, "loss": 0.0076, "lr": 1.38747528933599e-05, "epoch": 3.891213389121339, "percentage": 78.15, "elapsed_time": "2:04:51", "remaining_time": "0:34:54"}
{"current_steps": 465, "total_steps": 595, "eval_loss": 0.01321639958769083, "epoch": 3.891213389121339, "percentage": 78.15, "elapsed_time": "2:04:59", "remaining_time": "0:34:56"}
{"current_steps": 466, "total_steps": 595, "loss": 0.0093, "lr": 1.3672387212774457e-05, "epoch": 3.899581589958159, "percentage": 78.32, "elapsed_time": "2:05:15", "remaining_time": "0:34:40"}
{"current_steps": 467, "total_steps": 595, "loss": 0.0068, "lr": 1.3471274176565935e-05, "epoch": 3.907949790794979, "percentage": 78.49, "elapsed_time": "2:05:30", "remaining_time": "0:34:24"}
{"current_steps": 468, "total_steps": 595, "loss": 0.0076, "lr": 1.327142071948988e-05, "epoch": 3.916317991631799, "percentage": 78.66, "elapsed_time": "2:05:45", "remaining_time": "0:34:07"}
{"current_steps": 469, "total_steps": 595, "loss": 0.0079, "lr": 1.3072833732869167e-05, "epoch": 3.924686192468619, "percentage": 78.82, "elapsed_time": "2:05:59", "remaining_time": "0:33:50"}
{"current_steps": 470, "total_steps": 595, "loss": 0.007, "lr": 1.28755200643564e-05, "epoch": 3.933054393305439, "percentage": 78.99, "elapsed_time": "2:06:13", "remaining_time": "0:33:34"}
{"current_steps": 470, "total_steps": 595, "eval_loss": 0.013240823522210121, "epoch": 3.933054393305439, "percentage": 78.99, "elapsed_time": "2:06:22", "remaining_time": "0:33:36"}
{"current_steps": 471, "total_steps": 595, "loss": 0.0082, "lr": 1.267948651769777e-05, "epoch": 3.941422594142259, "percentage": 79.16, "elapsed_time": "2:06:36", "remaining_time": "0:33:19"}
{"current_steps": 472, "total_steps": 595, "loss": 0.0067, "lr": 1.2484739852498467e-05, "epoch": 3.9497907949790796, "percentage": 79.33, "elapsed_time": "2:06:50", "remaining_time": "0:33:03"}
{"current_steps": 473, "total_steps": 595, "loss": 0.0083, "lr": 1.2291286783989597e-05, "epoch": 3.9581589958158996, "percentage": 79.5, "elapsed_time": "2:07:05", "remaining_time": "0:32:46"}
{"current_steps": 474, "total_steps": 595, "loss": 0.0083, "lr": 1.2099133982796612e-05, "epoch": 3.9665271966527196, "percentage": 79.66, "elapsed_time": "2:07:18", "remaining_time": "0:32:29"}
{"current_steps": 475, "total_steps": 595, "loss": 0.0082, "lr": 1.190828807470929e-05, "epoch": 3.97489539748954, "percentage": 79.83, "elapsed_time": "2:07:34", "remaining_time": "0:32:13"}
{"current_steps": 475, "total_steps": 595, "eval_loss": 0.013233880512416363, "epoch": 3.97489539748954, "percentage": 79.83, "elapsed_time": "2:07:42", "remaining_time": "0:32:15"}
{"current_steps": 476, "total_steps": 595, "loss": 0.0059, "lr": 1.1718755640453288e-05, "epoch": 3.98326359832636, "percentage": 80.0, "elapsed_time": "2:07:56", "remaining_time": "0:31:59"}
{"current_steps": 477, "total_steps": 595, "loss": 0.0085, "lr": 1.1530543215463235e-05, "epoch": 3.99163179916318, "percentage": 80.17, "elapsed_time": "2:08:10", "remaining_time": "0:31:42"}
{"current_steps": 478, "total_steps": 595, "loss": 0.0115, "lr": 1.1343657289657333e-05, "epoch": 4.0, "percentage": 80.34, "elapsed_time": "2:08:21", "remaining_time": "0:31:25"}
{"current_steps": 479, "total_steps": 595, "loss": 0.0066, "lr": 1.1158104307213612e-05, "epoch": 4.00836820083682, "percentage": 80.5, "elapsed_time": "2:08:35", "remaining_time": "0:31:08"}
{"current_steps": 480, "total_steps": 595, "loss": 0.0059, "lr": 1.0973890666347702e-05, "epoch": 4.01673640167364, "percentage": 80.67, "elapsed_time": "2:08:48", "remaining_time": "0:30:51"}
{"current_steps": 480, "total_steps": 595, "eval_loss": 0.013261526823043823, "epoch": 4.01673640167364, "percentage": 80.67, "elapsed_time": "2:08:57", "remaining_time": "0:30:53"}
{"current_steps": 481, "total_steps": 595, "loss": 0.0064, "lr": 1.0791022719092231e-05, "epoch": 4.02510460251046, "percentage": 80.84, "elapsed_time": "2:09:09", "remaining_time": "0:30:36"}
{"current_steps": 482, "total_steps": 595, "loss": 0.0067, "lr": 1.0609506771077765e-05, "epoch": 4.03347280334728, "percentage": 81.01, "elapsed_time": "2:09:23", "remaining_time": "0:30:19"}
{"current_steps": 483, "total_steps": 595, "loss": 0.0058, "lr": 1.0429349081315404e-05, "epoch": 4.0418410041841, "percentage": 81.18, "elapsed_time": "2:09:36", "remaining_time": "0:30:03"}
{"current_steps": 484, "total_steps": 595, "loss": 0.0064, "lr": 1.025055586198096e-05, "epoch": 4.050209205020921, "percentage": 81.34, "elapsed_time": "2:09:50", "remaining_time": "0:29:46"}
{"current_steps": 485, "total_steps": 595, "loss": 0.0066, "lr": 1.0073133278200703e-05, "epoch": 4.058577405857741, "percentage": 81.51, "elapsed_time": "2:10:05", "remaining_time": "0:29:30"}
{"current_steps": 485, "total_steps": 595, "eval_loss": 0.013517594896256924, "epoch": 4.058577405857741, "percentage": 81.51, "elapsed_time": "2:10:13", "remaining_time": "0:29:32"}
{"current_steps": 486, "total_steps": 595, "loss": 0.0068, "lr": 9.897087447838848e-06, "epoch": 4.066945606694561, "percentage": 81.68, "elapsed_time": "2:10:26", "remaining_time": "0:29:15"}
{"current_steps": 487, "total_steps": 595, "loss": 0.0068, "lr": 9.72242444128656e-06, "epoch": 4.075313807531381, "percentage": 81.85, "elapsed_time": "2:10:41", "remaining_time": "0:28:58"}
{"current_steps": 488, "total_steps": 595, "loss": 0.0059, "lr": 9.549150281252633e-06, "epoch": 4.083682008368201, "percentage": 82.02, "elapsed_time": "2:10:55", "remaining_time": "0:28:42"}
{"current_steps": 489, "total_steps": 595, "loss": 0.0065, "lr": 9.377270942555816e-06, "epoch": 4.092050209205021, "percentage": 82.18, "elapsed_time": "2:11:09", "remaining_time": "0:28:25"}
{"current_steps": 490, "total_steps": 595, "loss": 0.0063, "lr": 9.206792351918808e-06, "epoch": 4.100418410041841, "percentage": 82.35, "elapsed_time": "2:11:22", "remaining_time": "0:28:09"}
{"current_steps": 490, "total_steps": 595, "eval_loss": 0.013989124447107315, "epoch": 4.100418410041841, "percentage": 82.35, "elapsed_time": "2:11:31", "remaining_time": "0:28:10"}
{"current_steps": 491, "total_steps": 595, "loss": 0.0062, "lr": 9.037720387763877e-06, "epoch": 4.108786610878661, "percentage": 82.52, "elapsed_time": "2:11:43", "remaining_time": "0:27:54"}
{"current_steps": 492, "total_steps": 595, "loss": 0.0072, "lr": 8.870060880010161e-06, "epoch": 4.117154811715481, "percentage": 82.69, "elapsed_time": "2:11:58", "remaining_time": "0:27:37"}
{"current_steps": 493, "total_steps": 595, "loss": 0.0065, "lr": 8.703819609872655e-06, "epoch": 4.125523012552302, "percentage": 82.86, "elapsed_time": "2:12:14", "remaining_time": "0:27:21"}
{"current_steps": 494, "total_steps": 595, "loss": 0.0068, "lr": 8.539002309662863e-06, "epoch": 4.133891213389122, "percentage": 83.03, "elapsed_time": "2:12:28", "remaining_time": "0:27:05"}
{"current_steps": 495, "total_steps": 595, "loss": 0.0059, "lr": 8.375614662591098e-06, "epoch": 4.142259414225942, "percentage": 83.19, "elapsed_time": "2:12:44", "remaining_time": "0:26:48"}
{"current_steps": 495, "total_steps": 595, "eval_loss": 0.01436224952340126, "epoch": 4.142259414225942, "percentage": 83.19, "elapsed_time": "2:12:52", "remaining_time": "0:26:50"}
{"current_steps": 496, "total_steps": 595, "loss": 0.0072, "lr": 8.213662302570564e-06, "epoch": 4.150627615062762, "percentage": 83.36, "elapsed_time": "2:13:06", "remaining_time": "0:26:33"}
{"current_steps": 497, "total_steps": 595, "loss": 0.006, "lr": 8.053150814023075e-06, "epoch": 4.158995815899582, "percentage": 83.53, "elapsed_time": "2:13:20", "remaining_time": "0:26:17"}
{"current_steps": 498, "total_steps": 595, "loss": 0.0068, "lr": 7.894085731686484e-06, "epoch": 4.167364016736402, "percentage": 83.7, "elapsed_time": "2:13:34", "remaining_time": "0:26:01"}
{"current_steps": 499, "total_steps": 595, "loss": 0.0062, "lr": 7.736472540423839e-06, "epoch": 4.175732217573222, "percentage": 83.87, "elapsed_time": "2:13:47", "remaining_time": "0:25:44"}
{"current_steps": 500, "total_steps": 595, "loss": 0.0066, "lr": 7.5803166750342545e-06, "epoch": 4.184100418410042, "percentage": 84.03, "elapsed_time": "2:14:00", "remaining_time": "0:25:27"}
{"current_steps": 500, "total_steps": 595, "eval_loss": 0.014202076941728592, "epoch": 4.184100418410042, "percentage": 84.03, "elapsed_time": "2:14:09", "remaining_time": "0:25:29"}
{"current_steps": 501, "total_steps": 595, "loss": 0.0068, "lr": 7.425623520065506e-06, "epoch": 4.192468619246862, "percentage": 84.2, "elapsed_time": "2:14:30", "remaining_time": "0:25:14"}
{"current_steps": 502, "total_steps": 595, "loss": 0.0058, "lr": 7.272398409628362e-06, "epoch": 4.200836820083682, "percentage": 84.37, "elapsed_time": "2:14:44", "remaining_time": "0:24:57"}
{"current_steps": 503, "total_steps": 595, "loss": 0.0065, "lr": 7.120646627212668e-06, "epoch": 4.209205020920502, "percentage": 84.54, "elapsed_time": "2:14:59", "remaining_time": "0:24:41"}
{"current_steps": 504, "total_steps": 595, "loss": 0.0059, "lr": 6.970373405505149e-06, "epoch": 4.2175732217573225, "percentage": 84.71, "elapsed_time": "2:15:13", "remaining_time": "0:24:24"}
{"current_steps": 505, "total_steps": 595, "loss": 0.0055, "lr": 6.8215839262089465e-06, "epoch": 4.2259414225941425, "percentage": 84.87, "elapsed_time": "2:15:26", "remaining_time": "0:24:08"}
{"current_steps": 505, "total_steps": 595, "eval_loss": 0.01415976881980896, "epoch": 4.2259414225941425, "percentage": 84.87, "elapsed_time": "2:15:34", "remaining_time": "0:24:09"}
{"current_steps": 506, "total_steps": 595, "loss": 0.0065, "lr": 6.674283319865015e-06, "epoch": 4.2343096234309625, "percentage": 85.04, "elapsed_time": "2:15:50", "remaining_time": "0:23:53"}
{"current_steps": 507, "total_steps": 595, "loss": 0.0067, "lr": 6.5284766656751486e-06, "epoch": 4.2426778242677825, "percentage": 85.21, "elapsed_time": "2:16:05", "remaining_time": "0:23:37"}
{"current_steps": 508, "total_steps": 595, "loss": 0.0058, "lr": 6.384168991326872e-06, "epoch": 4.2510460251046025, "percentage": 85.38, "elapsed_time": "2:16:19", "remaining_time": "0:23:20"}
{"current_steps": 509, "total_steps": 595, "loss": 0.0065, "lr": 6.241365272820065e-06, "epoch": 4.2594142259414225, "percentage": 85.55, "elapsed_time": "2:16:33", "remaining_time": "0:23:04"}
{"current_steps": 510, "total_steps": 595, "loss": 0.0067, "lr": 6.100070434295379e-06, "epoch": 4.2677824267782425, "percentage": 85.71, "elapsed_time": "2:16:48", "remaining_time": "0:22:48"}
{"current_steps": 510, "total_steps": 595, "eval_loss": 0.014154573902487755, "epoch": 4.2677824267782425, "percentage": 85.71, "elapsed_time": "2:16:56", "remaining_time": "0:22:49"}
{"current_steps": 511, "total_steps": 595, "loss": 0.0057, "lr": 5.96028934786445e-06, "epoch": 4.2761506276150625, "percentage": 85.88, "elapsed_time": "2:17:11", "remaining_time": "0:22:33"}
{"current_steps": 512, "total_steps": 595, "loss": 0.0061, "lr": 5.822026833441901e-06, "epoch": 4.2845188284518825, "percentage": 86.05, "elapsed_time": "2:17:24", "remaining_time": "0:22:16"}
{"current_steps": 513, "total_steps": 595, "loss": 0.0067, "lr": 5.685287658579124e-06, "epoch": 4.292887029288703, "percentage": 86.22, "elapsed_time": "2:17:38", "remaining_time": "0:22:00"}
{"current_steps": 514, "total_steps": 595, "loss": 0.0064, "lr": 5.550076538299931e-06, "epoch": 4.301255230125523, "percentage": 86.39, "elapsed_time": "2:17:53", "remaining_time": "0:21:43"}
{"current_steps": 515, "total_steps": 595, "loss": 0.0065, "lr": 5.416398134937878e-06, "epoch": 4.309623430962343, "percentage": 86.55, "elapsed_time": "2:18:07", "remaining_time": "0:21:27"}
{"current_steps": 515, "total_steps": 595, "eval_loss": 0.014257834292948246, "epoch": 4.309623430962343, "percentage": 86.55, "elapsed_time": "2:18:15", "remaining_time": "0:21:28"}
{"current_steps": 516, "total_steps": 595, "loss": 0.0063, "lr": 5.284257057975628e-06, "epoch": 4.317991631799163, "percentage": 86.72, "elapsed_time": "2:18:29", "remaining_time": "0:21:12"}
{"current_steps": 517, "total_steps": 595, "loss": 0.0056, "lr": 5.153657863885902e-06, "epoch": 4.326359832635983, "percentage": 86.89, "elapsed_time": "2:18:42", "remaining_time": "0:20:55"}
{"current_steps": 518, "total_steps": 595, "loss": 0.0065, "lr": 5.024605055974408e-06, "epoch": 4.334728033472803, "percentage": 87.06, "elapsed_time": "2:18:57", "remaining_time": "0:20:39"}
{"current_steps": 519, "total_steps": 595, "loss": 0.0066, "lr": 4.8971030842245635e-06, "epoch": 4.343096234309623, "percentage": 87.23, "elapsed_time": "2:19:13", "remaining_time": "0:20:23"}
{"current_steps": 520, "total_steps": 595, "loss": 0.0062, "lr": 4.771156345144018e-06, "epoch": 4.351464435146443, "percentage": 87.39, "elapsed_time": "2:19:28", "remaining_time": "0:20:06"}
{"current_steps": 520, "total_steps": 595, "eval_loss": 0.014165216125547886, "epoch": 4.351464435146443, "percentage": 87.39, "elapsed_time": "2:19:36", "remaining_time": "0:20:08"}
{"current_steps": 521, "total_steps": 595, "loss": 0.0063, "lr": 4.646769181613098e-06, "epoch": 4.359832635983263, "percentage": 87.56, "elapsed_time": "2:19:49", "remaining_time": "0:19:51"}
{"current_steps": 522, "total_steps": 595, "loss": 0.0065, "lr": 4.52394588273502e-06, "epoch": 4.368200836820083, "percentage": 87.73, "elapsed_time": "2:20:04", "remaining_time": "0:19:35"}
{"current_steps": 523, "total_steps": 595, "loss": 0.0065, "lr": 4.40269068368801e-06, "epoch": 4.376569037656903, "percentage": 87.9, "elapsed_time": "2:20:18", "remaining_time": "0:19:18"}
{"current_steps": 524, "total_steps": 595, "loss": 0.0062, "lr": 4.283007765579267e-06, "epoch": 4.384937238493724, "percentage": 88.07, "elapsed_time": "2:20:33", "remaining_time": "0:19:02"}
{"current_steps": 525, "total_steps": 595, "loss": 0.0065, "lr": 4.164901255300779e-06, "epoch": 4.393305439330544, "percentage": 88.24, "elapsed_time": "2:20:48", "remaining_time": "0:18:46"}
{"current_steps": 525, "total_steps": 595, "eval_loss": 0.01406473945826292, "epoch": 4.393305439330544, "percentage": 88.24, "elapsed_time": "2:20:57", "remaining_time": "0:18:47"}
{"current_steps": 526, "total_steps": 595, "loss": 0.0057, "lr": 4.048375225387036e-06, "epoch": 4.401673640167364, "percentage": 88.4, "elapsed_time": "2:21:11", "remaining_time": "0:18:31"}
{"current_steps": 527, "total_steps": 595, "loss": 0.0059, "lr": 3.9334336938746e-06, "epoch": 4.410041841004184, "percentage": 88.57, "elapsed_time": "2:21:24", "remaining_time": "0:18:14"}
{"current_steps": 528, "total_steps": 595, "loss": 0.0064, "lr": 3.82008062416353e-06, "epoch": 4.418410041841004, "percentage": 88.74, "elapsed_time": "2:21:40", "remaining_time": "0:17:58"}
{"current_steps": 529, "total_steps": 595, "loss": 0.0058, "lr": 3.7083199248807656e-06, "epoch": 4.426778242677824, "percentage": 88.91, "elapsed_time": "2:21:53", "remaining_time": "0:17:42"}
{"current_steps": 530, "total_steps": 595, "loss": 0.007, "lr": 3.5981554497452884e-06, "epoch": 4.435146443514644, "percentage": 89.08, "elapsed_time": "2:22:07", "remaining_time": "0:17:25"}
{"current_steps": 530, "total_steps": 595, "eval_loss": 0.013939818367362022, "epoch": 4.435146443514644, "percentage": 89.08, "elapsed_time": "2:22:15", "remaining_time": "0:17:26"}
{"current_steps": 531, "total_steps": 595, "loss": 0.0066, "lr": 3.4895909974352935e-06, "epoch": 4.443514644351464, "percentage": 89.24, "elapsed_time": "2:22:28", "remaining_time": "0:17:10"}
{"current_steps": 532, "total_steps": 595, "loss": 0.007, "lr": 3.38263031145718e-06, "epoch": 4.451882845188284, "percentage": 89.41, "elapsed_time": "2:22:43", "remaining_time": "0:16:54"}
{"current_steps": 533, "total_steps": 595, "loss": 0.0055, "lr": 3.27727708001645e-06, "epoch": 4.460251046025105, "percentage": 89.58, "elapsed_time": "2:22:58", "remaining_time": "0:16:37"}
{"current_steps": 534, "total_steps": 595, "loss": 0.0058, "lr": 3.173534935890582e-06, "epoch": 4.468619246861925, "percentage": 89.75, "elapsed_time": "2:23:12", "remaining_time": "0:16:21"}
{"current_steps": 535, "total_steps": 595, "loss": 0.0058, "lr": 3.0714074563037044e-06, "epoch": 4.476987447698745, "percentage": 89.92, "elapsed_time": "2:23:26", "remaining_time": "0:16:05"}
{"current_steps": 535, "total_steps": 595, "eval_loss": 0.013857071287930012, "epoch": 4.476987447698745, "percentage": 89.92, "elapsed_time": "2:23:35", "remaining_time": "0:16:06"}
{"current_steps": 536, "total_steps": 595, "loss": 0.0062, "lr": 2.970898162803287e-06, "epoch": 4.485355648535565, "percentage": 90.08, "elapsed_time": "2:23:49", "remaining_time": "0:15:49"}
{"current_steps": 537, "total_steps": 595, "loss": 0.006, "lr": 2.8720105211387183e-06, "epoch": 4.493723849372385, "percentage": 90.25, "elapsed_time": "2:24:03", "remaining_time": "0:15:33"}
{"current_steps": 538, "total_steps": 595, "loss": 0.0065, "lr": 2.774747941141764e-06, "epoch": 4.502092050209205, "percentage": 90.42, "elapsed_time": "2:24:18", "remaining_time": "0:15:17"}
{"current_steps": 539, "total_steps": 595, "loss": 0.0068, "lr": 2.6791137766090157e-06, "epoch": 4.510460251046025, "percentage": 90.59, "elapsed_time": "2:24:32", "remaining_time": "0:15:01"}
{"current_steps": 540, "total_steps": 595, "loss": 0.0056, "lr": 2.5851113251862345e-06, "epoch": 4.518828451882845, "percentage": 90.76, "elapsed_time": "2:24:46", "remaining_time": "0:14:44"}
{"current_steps": 540, "total_steps": 595, "eval_loss": 0.01391106192022562, "epoch": 4.518828451882845, "percentage": 90.76, "elapsed_time": "2:24:54", "remaining_time": "0:14:45"}
{"current_steps": 541, "total_steps": 595, "loss": 0.0068, "lr": 2.4927438282546567e-06, "epoch": 4.527196652719665, "percentage": 90.92, "elapsed_time": "2:25:08", "remaining_time": "0:14:29"}
{"current_steps": 542, "total_steps": 595, "loss": 0.006, "lr": 2.4020144708192026e-06, "epoch": 4.535564853556485, "percentage": 91.09, "elapsed_time": "2:25:23", "remaining_time": "0:14:13"}
{"current_steps": 543, "total_steps": 595, "loss": 0.0062, "lr": 2.3129263813986724e-06, "epoch": 4.543933054393305, "percentage": 91.26, "elapsed_time": "2:25:39", "remaining_time": "0:13:56"}
{"current_steps": 544, "total_steps": 595, "loss": 0.0067, "lr": 2.225482631917847e-06, "epoch": 4.552301255230126, "percentage": 91.43, "elapsed_time": "2:25:52", "remaining_time": "0:13:40"}
{"current_steps": 545, "total_steps": 595, "loss": 0.0062, "lr": 2.1396862376015903e-06, "epoch": 4.560669456066946, "percentage": 91.6, "elapsed_time": "2:26:07", "remaining_time": "0:13:24"}
{"current_steps": 545, "total_steps": 595, "eval_loss": 0.013888537883758545, "epoch": 4.560669456066946, "percentage": 91.6, "elapsed_time": "2:26:15", "remaining_time": "0:13:25"}
{"current_steps": 546, "total_steps": 595, "loss": 0.0065, "lr": 2.0555401568708554e-06, "epoch": 4.569037656903766, "percentage": 91.76, "elapsed_time": "2:26:30", "remaining_time": "0:13:08"}
{"current_steps": 547, "total_steps": 595, "loss": 0.0071, "lr": 1.9730472912406816e-06, "epoch": 4.577405857740586, "percentage": 91.93, "elapsed_time": "2:26:44", "remaining_time": "0:12:52"}
{"current_steps": 548, "total_steps": 595, "loss": 0.0064, "lr": 1.8922104852201528e-06, "epoch": 4.585774058577406, "percentage": 92.1, "elapsed_time": "2:26:59", "remaining_time": "0:12:36"}
{"current_steps": 549, "total_steps": 595, "loss": 0.0066, "lr": 1.8130325262142755e-06, "epoch": 4.594142259414226, "percentage": 92.27, "elapsed_time": "2:27:12", "remaining_time": "0:12:20"}
{"current_steps": 550, "total_steps": 595, "loss": 0.0061, "lr": 1.7355161444279344e-06, "epoch": 4.602510460251046, "percentage": 92.44, "elapsed_time": "2:27:28", "remaining_time": "0:12:03"}
{"current_steps": 550, "total_steps": 595, "eval_loss": 0.013935999944806099, "epoch": 4.602510460251046, "percentage": 92.44, "elapsed_time": "2:27:37", "remaining_time": "0:12:04"}
{"current_steps": 551, "total_steps": 595, "loss": 0.0074, "lr": 1.6596640127716778e-06, "epoch": 4.610878661087866, "percentage": 92.61, "elapsed_time": "2:27:58", "remaining_time": "0:11:48"}
{"current_steps": 552, "total_steps": 595, "loss": 0.0066, "lr": 1.5854787467695975e-06, "epoch": 4.619246861924686, "percentage": 92.77, "elapsed_time": "2:28:10", "remaining_time": "0:11:32"}
{"current_steps": 553, "total_steps": 595, "loss": 0.0057, "lr": 1.512962904469112e-06, "epoch": 4.627615062761507, "percentage": 92.94, "elapsed_time": "2:28:25", "remaining_time": "0:11:16"}
{"current_steps": 554, "total_steps": 595, "loss": 0.0064, "lr": 1.442118986352775e-06, "epoch": 4.635983263598327, "percentage": 93.11, "elapsed_time": "2:28:39", "remaining_time": "0:11:00"}
{"current_steps": 555, "total_steps": 595, "loss": 0.0061, "lr": 1.3729494352520578e-06, "epoch": 4.644351464435147, "percentage": 93.28, "elapsed_time": "2:28:53", "remaining_time": "0:10:43"}
{"current_steps": 555, "total_steps": 595, "eval_loss": 0.013867921195924282, "epoch": 4.644351464435147, "percentage": 93.28, "elapsed_time": "2:29:01", "remaining_time": "0:10:44"}
{"current_steps": 556, "total_steps": 595, "loss": 0.0068, "lr": 1.3054566362631082e-06, "epoch": 4.652719665271967, "percentage": 93.45, "elapsed_time": "2:29:17", "remaining_time": "0:10:28"}
{"current_steps": 557, "total_steps": 595, "loss": 0.0064, "lr": 1.2396429166645073e-06, "epoch": 4.661087866108787, "percentage": 93.61, "elapsed_time": "2:29:32", "remaining_time": "0:10:12"}
{"current_steps": 558, "total_steps": 595, "loss": 0.0062, "lr": 1.175510545837022e-06, "epoch": 4.669456066945607, "percentage": 93.78, "elapsed_time": "2:29:47", "remaining_time": "0:09:55"}
{"current_steps": 559, "total_steps": 595, "loss": 0.0057, "lr": 1.1130617351853446e-06, "epoch": 4.677824267782427, "percentage": 93.95, "elapsed_time": "2:30:02", "remaining_time": "0:09:39"}
{"current_steps": 560, "total_steps": 595, "loss": 0.0068, "lr": 1.0522986380618605e-06, "epoch": 4.686192468619247, "percentage": 94.12, "elapsed_time": "2:30:16", "remaining_time": "0:09:23"}
{"current_steps": 560, "total_steps": 595, "eval_loss": 0.01384110189974308, "epoch": 4.686192468619247, "percentage": 94.12, "elapsed_time": "2:30:24", "remaining_time": "0:09:24"}
{"current_steps": 561, "total_steps": 595, "loss": 0.0063, "lr": 9.932233496923903e-07, "epoch": 4.694560669456067, "percentage": 94.29, "elapsed_time": "2:30:39", "remaining_time": "0:09:07"}
{"current_steps": 562, "total_steps": 595, "loss": 0.0069, "lr": 9.358379071039147e-07, "epoch": 4.702928870292887, "percentage": 94.45, "elapsed_time": "2:30:53", "remaining_time": "0:08:51"}
{"current_steps": 563, "total_steps": 595, "loss": 0.0057, "lr": 8.801442890543743e-07, "epoch": 4.711297071129707, "percentage": 94.62, "elapsed_time": "2:31:08", "remaining_time": "0:08:35"}
{"current_steps": 564, "total_steps": 595, "loss": 0.0059, "lr": 8.261444159644083e-07, "epoch": 4.7196652719665275, "percentage": 94.79, "elapsed_time": "2:31:24", "remaining_time": "0:08:19"}
{"current_steps": 565, "total_steps": 595, "loss": 0.0069, "lr": 7.738401498511405e-07, "epoch": 4.7280334728033475, "percentage": 94.96, "elapsed_time": "2:31:39", "remaining_time": "0:08:03"}
{"current_steps": 565, "total_steps": 595, "eval_loss": 0.013867964036762714, "epoch": 4.7280334728033475, "percentage": 94.96, "elapsed_time": "2:31:47", "remaining_time": "0:08:03"}
{"current_steps": 566, "total_steps": 595, "loss": 0.0066, "lr": 7.232332942639974e-07, "epoch": 4.7364016736401675, "percentage": 95.13, "elapsed_time": "2:32:01", "remaining_time": "0:07:47"}
{"current_steps": 567, "total_steps": 595, "loss": 0.0063, "lr": 6.743255942224913e-07, "epoch": 4.7447698744769875, "percentage": 95.29, "elapsed_time": "2:32:16", "remaining_time": "0:07:31"}
{"current_steps": 568, "total_steps": 595, "loss": 0.0063, "lr": 6.27118736156046e-07, "epoch": 4.7531380753138075, "percentage": 95.46, "elapsed_time": "2:32:31", "remaining_time": "0:07:15"}
{"current_steps": 569, "total_steps": 595, "loss": 0.0059, "lr": 5.816143478458714e-07, "epoch": 4.7615062761506275, "percentage": 95.63, "elapsed_time": "2:32:44", "remaining_time": "0:06:58"}
{"current_steps": 570, "total_steps": 595, "loss": 0.0063, "lr": 5.378139983688135e-07, "epoch": 4.7698744769874475, "percentage": 95.8, "elapsed_time": "2:32:57", "remaining_time": "0:06:42"}
{"current_steps": 570, "total_steps": 595, "eval_loss": 0.013921505771577358, "epoch": 4.7698744769874475, "percentage": 95.8, "elapsed_time": "2:33:06", "remaining_time": "0:06:42"}
{"current_steps": 571, "total_steps": 595, "loss": 0.0061, "lr": 4.957191980432541e-07, "epoch": 4.7782426778242675, "percentage": 95.97, "elapsed_time": "2:33:20", "remaining_time": "0:06:26"}
{"current_steps": 572, "total_steps": 595, "loss": 0.0065, "lr": 4.5533139837704574e-07, "epoch": 4.786610878661088, "percentage": 96.13, "elapsed_time": "2:33:34", "remaining_time": "0:06:10"}
{"current_steps": 573, "total_steps": 595, "loss": 0.0065, "lr": 4.1665199201744167e-07, "epoch": 4.794979079497908, "percentage": 96.3, "elapsed_time": "2:33:47", "remaining_time": "0:05:54"}
{"current_steps": 574, "total_steps": 595, "loss": 0.006, "lr": 3.7968231270307244e-07, "epoch": 4.803347280334728, "percentage": 96.47, "elapsed_time": "2:34:02", "remaining_time": "0:05:38"}
{"current_steps": 575, "total_steps": 595, "loss": 0.0065, "lr": 3.4442363521798304e-07, "epoch": 4.811715481171548, "percentage": 96.64, "elapsed_time": "2:34:16", "remaining_time": "0:05:21"}
{"current_steps": 575, "total_steps": 595, "eval_loss": 0.01387822162359953, "epoch": 4.811715481171548, "percentage": 96.64, "elapsed_time": "2:34:24", "remaining_time": "0:05:22"}
{"current_steps": 576, "total_steps": 595, "loss": 0.0065, "lr": 3.1087717534764584e-07, "epoch": 4.820083682008368, "percentage": 96.81, "elapsed_time": "2:34:39", "remaining_time": "0:05:06"}
{"current_steps": 577, "total_steps": 595, "loss": 0.0062, "lr": 2.7904408983706607e-07, "epoch": 4.828451882845188, "percentage": 96.97, "elapsed_time": "2:34:54", "remaining_time": "0:04:49"}
{"current_steps": 578, "total_steps": 595, "loss": 0.0063, "lr": 2.489254763508642e-07, "epoch": 4.836820083682008, "percentage": 97.14, "elapsed_time": "2:35:07", "remaining_time": "0:04:33"}
{"current_steps": 579, "total_steps": 595, "loss": 0.0058, "lr": 2.2052237343545e-07, "epoch": 4.845188284518828, "percentage": 97.31, "elapsed_time": "2:35:22", "remaining_time": "0:04:17"}
{"current_steps": 580, "total_steps": 595, "loss": 0.0064, "lr": 1.938357604832075e-07, "epoch": 4.853556485355648, "percentage": 97.48, "elapsed_time": "2:35:37", "remaining_time": "0:04:01"}
{"current_steps": 580, "total_steps": 595, "eval_loss": 0.013862421736121178, "epoch": 4.853556485355648, "percentage": 97.48, "elapsed_time": "2:35:46", "remaining_time": "0:04:01"}
{"current_steps": 581, "total_steps": 595, "loss": 0.0058, "lr": 1.6886655769871029e-07, "epoch": 4.861924686192468, "percentage": 97.65, "elapsed_time": "2:35:59", "remaining_time": "0:03:45"}
{"current_steps": 582, "total_steps": 595, "loss": 0.0062, "lr": 1.4561562606701385e-07, "epoch": 4.870292887029288, "percentage": 97.82, "elapsed_time": "2:36:14", "remaining_time": "0:03:29"}
{"current_steps": 583, "total_steps": 595, "loss": 0.0065, "lr": 1.240837673239459e-07, "epoch": 4.878661087866108, "percentage": 97.98, "elapsed_time": "2:36:29", "remaining_time": "0:03:13"}
{"current_steps": 584, "total_steps": 595, "loss": 0.0062, "lr": 1.0427172392847295e-07, "epoch": 4.887029288702929, "percentage": 98.15, "elapsed_time": "2:36:44", "remaining_time": "0:02:57"}
{"current_steps": 585, "total_steps": 595, "loss": 0.0062, "lr": 8.618017903708197e-08, "epoch": 4.895397489539749, "percentage": 98.32, "elapsed_time": "2:36:58", "remaining_time": "0:02:41"}
{"current_steps": 585, "total_steps": 595, "eval_loss": 0.013880819082260132, "epoch": 4.895397489539749, "percentage": 98.32, "elapsed_time": "2:37:06", "remaining_time": "0:02:41"}
{"current_steps": 586, "total_steps": 595, "loss": 0.0061, "lr": 6.980975648026578e-08, "epoch": 4.903765690376569, "percentage": 98.49, "elapsed_time": "2:37:21", "remaining_time": "0:02:25"}
{"current_steps": 587, "total_steps": 595, "loss": 0.0062, "lr": 5.516102074095697e-08, "epoch": 4.912133891213389, "percentage": 98.66, "elapsed_time": "2:37:36", "remaining_time": "0:02:08"}
{"current_steps": 588, "total_steps": 595, "loss": 0.0062, "lr": 4.2234476935099074e-08, "epoch": 4.920502092050209, "percentage": 98.82, "elapsed_time": "2:37:50", "remaining_time": "0:01:52"}
{"current_steps": 589, "total_steps": 595, "loss": 0.0057, "lr": 3.103057079422711e-08, "epoch": 4.928870292887029, "percentage": 98.99, "elapsed_time": "2:38:05", "remaining_time": "0:01:36"}
{"current_steps": 590, "total_steps": 595, "loss": 0.0065, "lr": 2.154968865007989e-08, "epoch": 4.937238493723849, "percentage": 99.16, "elapsed_time": "2:38:21", "remaining_time": "0:01:20"}
{"current_steps": 590, "total_steps": 595, "eval_loss": 0.013855883851647377, "epoch": 4.937238493723849, "percentage": 99.16, "elapsed_time": "2:38:29", "remaining_time": "0:01:20"}
{"current_steps": 591, "total_steps": 595, "loss": 0.006, "lr": 1.3792157421299579e-08, "epoch": 4.945606694560669, "percentage": 99.33, "elapsed_time": "2:38:42", "remaining_time": "0:01:04"}
{"current_steps": 592, "total_steps": 595, "loss": 0.0057, "lr": 7.758244602151799e-09, "epoch": 4.95397489539749, "percentage": 99.5, "elapsed_time": "2:38:56", "remaining_time": "0:00:48"}
{"current_steps": 593, "total_steps": 595, "loss": 0.0059, "lr": 3.448158253277489e-09, "epoch": 4.96234309623431, "percentage": 99.66, "elapsed_time": "2:39:10", "remaining_time": "0:00:32"}
{"current_steps": 594, "total_steps": 595, "loss": 0.0062, "lr": 8.620469945708198e-10, "epoch": 4.97071129707113, "percentage": 99.83, "elapsed_time": "2:39:25", "remaining_time": "0:00:16"}
{"current_steps": 595, "total_steps": 595, "loss": 0.0055, "lr": 0.0, "epoch": 4.97907949790795, "percentage": 100.0, "elapsed_time": "2:39:39", "remaining_time": "0:00:00"}
{"current_steps": 595, "total_steps": 595, "eval_loss": 0.01388928946107626, "epoch": 4.97907949790795, "percentage": 100.0, "elapsed_time": "2:39:47", "remaining_time": "0:00:00"}
{"current_steps": 595, "total_steps": 595, "epoch": 4.97907949790795, "percentage": 100.0, "elapsed_time": "2:39:54", "remaining_time": "0:00:00"}