chchen's picture
Training in progress, step 3270
af24440 verified
{"current_steps": 10, "total_steps": 3270, "loss": 1.7007, "lr": 3.0581039755351682e-06, "epoch": 0.015278838808250574, "percentage": 0.31, "elapsed_time": "0:01:34", "remaining_time": "8:33:07"}
{"current_steps": 20, "total_steps": 3270, "loss": 1.6546, "lr": 6.1162079510703365e-06, "epoch": 0.030557677616501147, "percentage": 0.61, "elapsed_time": "0:03:10", "remaining_time": "8:37:17"}
{"current_steps": 30, "total_steps": 3270, "loss": 1.5461, "lr": 9.174311926605506e-06, "epoch": 0.04583651642475172, "percentage": 0.92, "elapsed_time": "0:04:46", "remaining_time": "8:36:09"}
{"current_steps": 40, "total_steps": 3270, "loss": 1.3083, "lr": 1.2232415902140673e-05, "epoch": 0.061115355233002294, "percentage": 1.22, "elapsed_time": "0:06:23", "remaining_time": "8:35:36"}
{"current_steps": 50, "total_steps": 3270, "loss": 0.8412, "lr": 1.5290519877675842e-05, "epoch": 0.07639419404125286, "percentage": 1.53, "elapsed_time": "0:07:58", "remaining_time": "8:33:46"}
{"current_steps": 50, "total_steps": 3270, "eval_loss": 0.6190279722213745, "epoch": 0.07639419404125286, "percentage": 1.53, "elapsed_time": "0:11:38", "remaining_time": "12:29:12"}
{"current_steps": 60, "total_steps": 3270, "loss": 0.6464, "lr": 1.834862385321101e-05, "epoch": 0.09167303284950344, "percentage": 1.83, "elapsed_time": "0:13:16", "remaining_time": "11:50:35"}
{"current_steps": 70, "total_steps": 3270, "loss": 0.4868, "lr": 2.140672782874618e-05, "epoch": 0.10695187165775401, "percentage": 2.14, "elapsed_time": "0:14:52", "remaining_time": "11:20:06"}
{"current_steps": 80, "total_steps": 3270, "loss": 0.3051, "lr": 2.4464831804281346e-05, "epoch": 0.12223071046600459, "percentage": 2.45, "elapsed_time": "0:16:28", "remaining_time": "10:56:45"}
{"current_steps": 90, "total_steps": 3270, "loss": 0.1913, "lr": 2.7522935779816515e-05, "epoch": 0.13750954927425516, "percentage": 2.75, "elapsed_time": "0:18:03", "remaining_time": "10:38:10"}
{"current_steps": 100, "total_steps": 3270, "loss": 0.1455, "lr": 3.0581039755351684e-05, "epoch": 0.15278838808250572, "percentage": 3.06, "elapsed_time": "0:19:39", "remaining_time": "10:23:10"}
{"current_steps": 100, "total_steps": 3270, "eval_loss": 0.10693324357271194, "epoch": 0.15278838808250572, "percentage": 3.06, "elapsed_time": "0:23:18", "remaining_time": "12:18:57"}
{"current_steps": 110, "total_steps": 3270, "loss": 0.1072, "lr": 3.363914373088685e-05, "epoch": 0.16806722689075632, "percentage": 3.36, "elapsed_time": "0:24:57", "remaining_time": "11:56:53"}
{"current_steps": 120, "total_steps": 3270, "loss": 0.096, "lr": 3.669724770642202e-05, "epoch": 0.18334606569900688, "percentage": 3.67, "elapsed_time": "0:26:32", "remaining_time": "11:36:47"}
{"current_steps": 130, "total_steps": 3270, "loss": 0.0842, "lr": 3.9755351681957185e-05, "epoch": 0.19862490450725745, "percentage": 3.98, "elapsed_time": "0:28:08", "remaining_time": "11:19:37"}
{"current_steps": 140, "total_steps": 3270, "loss": 0.0834, "lr": 4.281345565749236e-05, "epoch": 0.21390374331550802, "percentage": 4.28, "elapsed_time": "0:29:43", "remaining_time": "11:04:38"}
{"current_steps": 150, "total_steps": 3270, "loss": 0.0861, "lr": 4.587155963302753e-05, "epoch": 0.22918258212375858, "percentage": 4.59, "elapsed_time": "0:31:19", "remaining_time": "10:51:43"}
{"current_steps": 150, "total_steps": 3270, "eval_loss": 0.06472994387149811, "epoch": 0.22918258212375858, "percentage": 4.59, "elapsed_time": "0:34:58", "remaining_time": "12:07:29"}
{"current_steps": 160, "total_steps": 3270, "loss": 0.0823, "lr": 4.892966360856269e-05, "epoch": 0.24446142093200918, "percentage": 4.89, "elapsed_time": "0:36:37", "remaining_time": "11:51:44"}
{"current_steps": 170, "total_steps": 3270, "loss": 0.0676, "lr": 5.1987767584097854e-05, "epoch": 0.2597402597402597, "percentage": 5.2, "elapsed_time": "0:38:12", "remaining_time": "11:36:49"}
{"current_steps": 180, "total_steps": 3270, "loss": 0.0731, "lr": 5.504587155963303e-05, "epoch": 0.2750190985485103, "percentage": 5.5, "elapsed_time": "0:39:48", "remaining_time": "11:23:22"}
{"current_steps": 190, "total_steps": 3270, "loss": 0.0799, "lr": 5.81039755351682e-05, "epoch": 0.2902979373567609, "percentage": 5.81, "elapsed_time": "0:41:23", "remaining_time": "11:11:04"}
{"current_steps": 200, "total_steps": 3270, "loss": 0.0575, "lr": 6.116207951070337e-05, "epoch": 0.30557677616501144, "percentage": 6.12, "elapsed_time": "0:42:59", "remaining_time": "10:59:51"}
{"current_steps": 200, "total_steps": 3270, "eval_loss": 0.05183817818760872, "epoch": 0.30557677616501144, "percentage": 6.12, "elapsed_time": "0:46:37", "remaining_time": "11:55:35"}
{"current_steps": 210, "total_steps": 3270, "loss": 0.0501, "lr": 6.422018348623854e-05, "epoch": 0.32085561497326204, "percentage": 6.42, "elapsed_time": "0:48:15", "remaining_time": "11:43:11"}
{"current_steps": 220, "total_steps": 3270, "loss": 0.0637, "lr": 6.72782874617737e-05, "epoch": 0.33613445378151263, "percentage": 6.73, "elapsed_time": "0:49:51", "remaining_time": "11:31:14"}
{"current_steps": 230, "total_steps": 3270, "loss": 0.057, "lr": 7.033639143730886e-05, "epoch": 0.35141329258976317, "percentage": 7.03, "elapsed_time": "0:51:27", "remaining_time": "11:20:05"}
{"current_steps": 240, "total_steps": 3270, "loss": 0.0494, "lr": 7.339449541284404e-05, "epoch": 0.36669213139801377, "percentage": 7.34, "elapsed_time": "0:53:02", "remaining_time": "11:09:41"}
{"current_steps": 250, "total_steps": 3270, "loss": 0.0643, "lr": 7.645259938837921e-05, "epoch": 0.3819709702062643, "percentage": 7.65, "elapsed_time": "0:54:38", "remaining_time": "11:00:01"}
{"current_steps": 250, "total_steps": 3270, "eval_loss": 0.04688103497028351, "epoch": 0.3819709702062643, "percentage": 7.65, "elapsed_time": "0:58:16", "remaining_time": "11:43:54"}
{"current_steps": 260, "total_steps": 3270, "loss": 0.0436, "lr": 7.951070336391437e-05, "epoch": 0.3972498090145149, "percentage": 7.95, "elapsed_time": "0:59:54", "remaining_time": "11:33:28"}
{"current_steps": 270, "total_steps": 3270, "loss": 0.0708, "lr": 8.256880733944955e-05, "epoch": 0.4125286478227655, "percentage": 8.26, "elapsed_time": "1:01:29", "remaining_time": "11:23:16"}
{"current_steps": 280, "total_steps": 3270, "loss": 0.0634, "lr": 8.562691131498472e-05, "epoch": 0.42780748663101603, "percentage": 8.56, "elapsed_time": "1:03:05", "remaining_time": "11:13:40"}
{"current_steps": 290, "total_steps": 3270, "loss": 0.0507, "lr": 8.868501529051988e-05, "epoch": 0.4430863254392666, "percentage": 8.87, "elapsed_time": "1:04:40", "remaining_time": "11:04:34"}
{"current_steps": 300, "total_steps": 3270, "loss": 0.0341, "lr": 9.174311926605506e-05, "epoch": 0.45836516424751717, "percentage": 9.17, "elapsed_time": "1:06:15", "remaining_time": "10:55:59"}
{"current_steps": 300, "total_steps": 3270, "eval_loss": 0.043478548526763916, "epoch": 0.45836516424751717, "percentage": 9.17, "elapsed_time": "1:09:54", "remaining_time": "11:32:03"}
{"current_steps": 310, "total_steps": 3270, "loss": 0.0361, "lr": 9.480122324159021e-05, "epoch": 0.47364400305576776, "percentage": 9.48, "elapsed_time": "1:11:33", "remaining_time": "11:23:13"}
{"current_steps": 320, "total_steps": 3270, "loss": 0.0466, "lr": 9.785932721712538e-05, "epoch": 0.48892284186401835, "percentage": 9.79, "elapsed_time": "1:13:08", "remaining_time": "11:14:14"}
{"current_steps": 330, "total_steps": 3270, "loss": 0.0556, "lr": 9.999974360983129e-05, "epoch": 0.5042016806722689, "percentage": 10.09, "elapsed_time": "1:14:44", "remaining_time": "11:05:51"}
{"current_steps": 340, "total_steps": 3270, "loss": 0.0652, "lr": 9.999518563553522e-05, "epoch": 0.5194805194805194, "percentage": 10.4, "elapsed_time": "1:16:20", "remaining_time": "10:57:49"}
{"current_steps": 350, "total_steps": 3270, "loss": 0.0641, "lr": 9.998493069976636e-05, "epoch": 0.5347593582887701, "percentage": 10.7, "elapsed_time": "1:17:55", "remaining_time": "10:50:08"}
{"current_steps": 350, "total_steps": 3270, "eval_loss": 0.041326772421598434, "epoch": 0.5347593582887701, "percentage": 10.7, "elapsed_time": "1:21:34", "remaining_time": "11:20:30"}
{"current_steps": 360, "total_steps": 3270, "loss": 0.0574, "lr": 9.99689799710767e-05, "epoch": 0.5500381970970206, "percentage": 11.01, "elapsed_time": "1:23:11", "remaining_time": "11:12:31"}
{"current_steps": 370, "total_steps": 3270, "loss": 0.0535, "lr": 9.994733526705501e-05, "epoch": 0.5653170359052712, "percentage": 11.31, "elapsed_time": "1:24:47", "remaining_time": "11:04:32"}
{"current_steps": 380, "total_steps": 3270, "loss": 0.0432, "lr": 9.991999905411966e-05, "epoch": 0.5805958747135218, "percentage": 11.62, "elapsed_time": "1:26:22", "remaining_time": "10:56:54"}
{"current_steps": 390, "total_steps": 3270, "loss": 0.0345, "lr": 9.988697444723762e-05, "epoch": 0.5958747135217723, "percentage": 11.93, "elapsed_time": "1:27:58", "remaining_time": "10:49:37"}
{"current_steps": 400, "total_steps": 3270, "loss": 0.0405, "lr": 9.984826520956949e-05, "epoch": 0.6111535523300229, "percentage": 12.23, "elapsed_time": "1:29:33", "remaining_time": "10:42:35"}
{"current_steps": 400, "total_steps": 3270, "eval_loss": 0.04191767796874046, "epoch": 0.6111535523300229, "percentage": 12.23, "elapsed_time": "1:33:12", "remaining_time": "11:08:43"}
{"current_steps": 410, "total_steps": 3270, "loss": 0.0363, "lr": 9.980387575204072e-05, "epoch": 0.6264323911382735, "percentage": 12.54, "elapsed_time": "1:34:50", "remaining_time": "11:01:35"}
{"current_steps": 420, "total_steps": 3270, "loss": 0.0346, "lr": 9.975381113283891e-05, "epoch": 0.6417112299465241, "percentage": 12.84, "elapsed_time": "1:36:25", "remaining_time": "10:54:21"}
{"current_steps": 430, "total_steps": 3270, "loss": 0.0441, "lr": 9.969807705683751e-05, "epoch": 0.6569900687547746, "percentage": 13.15, "elapsed_time": "1:38:01", "remaining_time": "10:47:25"}
{"current_steps": 440, "total_steps": 3270, "loss": 0.0301, "lr": 9.96366798749457e-05, "epoch": 0.6722689075630253, "percentage": 13.46, "elapsed_time": "1:39:37", "remaining_time": "10:40:45"}
{"current_steps": 450, "total_steps": 3270, "loss": 0.0531, "lr": 9.956962658338473e-05, "epoch": 0.6875477463712758, "percentage": 13.76, "elapsed_time": "1:41:12", "remaining_time": "10:34:15"}
{"current_steps": 450, "total_steps": 3270, "eval_loss": 0.03845739737153053, "epoch": 0.6875477463712758, "percentage": 13.76, "elapsed_time": "1:44:49", "remaining_time": "10:56:57"}
{"current_steps": 460, "total_steps": 3270, "loss": 0.0363, "lr": 9.94969248228907e-05, "epoch": 0.7028265851795263, "percentage": 14.07, "elapsed_time": "1:46:27", "remaining_time": "10:50:21"}
{"current_steps": 470, "total_steps": 3270, "loss": 0.0447, "lr": 9.941858287784383e-05, "epoch": 0.7181054239877769, "percentage": 14.37, "elapsed_time": "1:48:02", "remaining_time": "10:43:39"}
{"current_steps": 480, "total_steps": 3270, "loss": 0.043, "lr": 9.933460967532453e-05, "epoch": 0.7333842627960275, "percentage": 14.68, "elapsed_time": "1:49:36", "remaining_time": "10:37:07"}
{"current_steps": 490, "total_steps": 3270, "loss": 0.0468, "lr": 9.924501478409618e-05, "epoch": 0.7486631016042781, "percentage": 14.98, "elapsed_time": "1:51:10", "remaining_time": "10:30:47"}
{"current_steps": 500, "total_steps": 3270, "loss": 0.041, "lr": 9.914980841351465e-05, "epoch": 0.7639419404125286, "percentage": 15.29, "elapsed_time": "1:52:45", "remaining_time": "10:24:38"}
{"current_steps": 500, "total_steps": 3270, "eval_loss": 0.03724617511034012, "epoch": 0.7639419404125286, "percentage": 15.29, "elapsed_time": "1:56:18", "remaining_time": "10:44:22"}
{"current_steps": 510, "total_steps": 3270, "loss": 0.0254, "lr": 9.904900141236506e-05, "epoch": 0.7792207792207793, "percentage": 15.6, "elapsed_time": "1:57:55", "remaining_time": "10:38:11"}
{"current_steps": 520, "total_steps": 3270, "loss": 0.0495, "lr": 9.894260526762548e-05, "epoch": 0.7944996180290298, "percentage": 15.9, "elapsed_time": "1:59:29", "remaining_time": "10:31:55"}
{"current_steps": 530, "total_steps": 3270, "loss": 0.0556, "lr": 9.883063210315804e-05, "epoch": 0.8097784568372803, "percentage": 16.21, "elapsed_time": "2:01:02", "remaining_time": "10:25:44"}
{"current_steps": 540, "total_steps": 3270, "loss": 0.0381, "lr": 9.871309467832738e-05, "epoch": 0.825057295645531, "percentage": 16.51, "elapsed_time": "2:02:33", "remaining_time": "10:19:37"}
{"current_steps": 550, "total_steps": 3270, "loss": 0.0283, "lr": 9.859000638654674e-05, "epoch": 0.8403361344537815, "percentage": 16.82, "elapsed_time": "2:04:05", "remaining_time": "10:13:41"}
{"current_steps": 550, "total_steps": 3270, "eval_loss": 0.03525731340050697, "epoch": 0.8403361344537815, "percentage": 16.82, "elapsed_time": "2:07:34", "remaining_time": "10:30:55"}
{"current_steps": 560, "total_steps": 3270, "loss": 0.0501, "lr": 9.846138125375175e-05, "epoch": 0.8556149732620321, "percentage": 17.13, "elapsed_time": "2:09:08", "remaining_time": "10:24:58"}
{"current_steps": 570, "total_steps": 3270, "loss": 0.0298, "lr": 9.83272339368022e-05, "epoch": 0.8708938120702827, "percentage": 17.43, "elapsed_time": "2:10:39", "remaining_time": "10:18:56"}
{"current_steps": 580, "total_steps": 3270, "loss": 0.043, "lr": 9.818757972181191e-05, "epoch": 0.8861726508785333, "percentage": 17.74, "elapsed_time": "2:12:10", "remaining_time": "10:13:00"}
{"current_steps": 590, "total_steps": 3270, "loss": 0.0335, "lr": 9.804243452240675e-05, "epoch": 0.9014514896867838, "percentage": 18.04, "elapsed_time": "2:13:40", "remaining_time": "10:07:13"}
{"current_steps": 600, "total_steps": 3270, "loss": 0.041, "lr": 9.789181487791146e-05, "epoch": 0.9167303284950343, "percentage": 18.35, "elapsed_time": "2:15:11", "remaining_time": "10:01:36"}
{"current_steps": 600, "total_steps": 3270, "eval_loss": 0.03299807012081146, "epoch": 0.9167303284950343, "percentage": 18.35, "elapsed_time": "2:18:38", "remaining_time": "10:16:58"}
{"current_steps": 610, "total_steps": 3270, "loss": 0.044, "lr": 9.773573795146485e-05, "epoch": 0.932009167303285, "percentage": 18.65, "elapsed_time": "2:20:12", "remaining_time": "10:11:24"}
{"current_steps": 620, "total_steps": 3270, "loss": 0.0284, "lr": 9.757422152806415e-05, "epoch": 0.9472880061115355, "percentage": 18.96, "elapsed_time": "2:21:42", "remaining_time": "10:05:41"}
{"current_steps": 630, "total_steps": 3270, "loss": 0.0417, "lr": 9.74072840125383e-05, "epoch": 0.9625668449197861, "percentage": 19.27, "elapsed_time": "2:23:12", "remaining_time": "10:00:05"}
{"current_steps": 640, "total_steps": 3270, "loss": 0.0395, "lr": 9.723494442745085e-05, "epoch": 0.9778456837280367, "percentage": 19.57, "elapsed_time": "2:24:42", "remaining_time": "9:54:38"}
{"current_steps": 650, "total_steps": 3270, "loss": 0.0553, "lr": 9.705722241093223e-05, "epoch": 0.9931245225362872, "percentage": 19.88, "elapsed_time": "2:26:12", "remaining_time": "9:49:19"}
{"current_steps": 650, "total_steps": 3270, "eval_loss": 0.0362694077193737, "epoch": 0.9931245225362872, "percentage": 19.88, "elapsed_time": "2:29:38", "remaining_time": "10:03:09"}
{"current_steps": 660, "total_steps": 3270, "loss": 0.0376, "lr": 9.687413821444199e-05, "epoch": 1.0084033613445378, "percentage": 20.18, "elapsed_time": "2:31:11", "remaining_time": "9:57:53"}
{"current_steps": 670, "total_steps": 3270, "loss": 0.0351, "lr": 9.668571270046122e-05, "epoch": 1.0236822001527883, "percentage": 20.49, "elapsed_time": "2:32:41", "remaining_time": "9:52:30"}
{"current_steps": 680, "total_steps": 3270, "loss": 0.0288, "lr": 9.649196734011519e-05, "epoch": 1.0389610389610389, "percentage": 20.8, "elapsed_time": "2:34:11", "remaining_time": "9:47:15"}
{"current_steps": 690, "total_steps": 3270, "loss": 0.0295, "lr": 9.629292421072671e-05, "epoch": 1.0542398777692896, "percentage": 21.1, "elapsed_time": "2:35:41", "remaining_time": "9:42:07"}
{"current_steps": 700, "total_steps": 3270, "loss": 0.0314, "lr": 9.608860599330048e-05, "epoch": 1.0695187165775402, "percentage": 21.41, "elapsed_time": "2:37:10", "remaining_time": "9:37:04"}
{"current_steps": 700, "total_steps": 3270, "eval_loss": 0.03102213703095913, "epoch": 1.0695187165775402, "percentage": 21.41, "elapsed_time": "2:40:35", "remaining_time": "9:49:36"}
{"current_steps": 710, "total_steps": 3270, "loss": 0.0297, "lr": 9.587903596993854e-05, "epoch": 1.0847975553857907, "percentage": 21.71, "elapsed_time": "2:42:08", "remaining_time": "9:44:36"}
{"current_steps": 720, "total_steps": 3270, "loss": 0.0301, "lr": 9.566423802118724e-05, "epoch": 1.1000763941940412, "percentage": 22.02, "elapsed_time": "2:43:37", "remaining_time": "9:39:31"}
{"current_steps": 730, "total_steps": 3270, "loss": 0.0438, "lr": 9.544423662331612e-05, "epoch": 1.1153552330022918, "percentage": 22.32, "elapsed_time": "2:45:07", "remaining_time": "9:34:31"}
{"current_steps": 740, "total_steps": 3270, "loss": 0.0354, "lr": 9.521905684552877e-05, "epoch": 1.1306340718105423, "percentage": 22.63, "elapsed_time": "2:46:36", "remaining_time": "9:29:37"}
{"current_steps": 750, "total_steps": 3270, "loss": 0.0211, "lr": 9.498872434710623e-05, "epoch": 1.1459129106187929, "percentage": 22.94, "elapsed_time": "2:48:06", "remaining_time": "9:24:49"}
{"current_steps": 750, "total_steps": 3270, "eval_loss": 0.031196942552924156, "epoch": 1.1459129106187929, "percentage": 22.94, "elapsed_time": "2:51:30", "remaining_time": "9:36:15"}
{"current_steps": 760, "total_steps": 3270, "loss": 0.0285, "lr": 9.475326537448307e-05, "epoch": 1.1611917494270436, "percentage": 23.24, "elapsed_time": "2:53:02", "remaining_time": "9:31:31"}
{"current_steps": 770, "total_steps": 3270, "loss": 0.0287, "lr": 9.451270675825665e-05, "epoch": 1.1764705882352942, "percentage": 23.55, "elapsed_time": "2:54:32", "remaining_time": "9:26:41"}
{"current_steps": 780, "total_steps": 3270, "loss": 0.0261, "lr": 9.426707591012976e-05, "epoch": 1.1917494270435447, "percentage": 23.85, "elapsed_time": "2:56:01", "remaining_time": "9:21:56"}
{"current_steps": 790, "total_steps": 3270, "loss": 0.0404, "lr": 9.4016400819787e-05, "epoch": 1.2070282658517952, "percentage": 24.16, "elapsed_time": "2:57:31", "remaining_time": "9:17:16"}
{"current_steps": 800, "total_steps": 3270, "loss": 0.0314, "lr": 9.376071005170539e-05, "epoch": 1.2223071046600458, "percentage": 24.46, "elapsed_time": "2:59:00", "remaining_time": "9:12:42"}
{"current_steps": 800, "total_steps": 3270, "eval_loss": 0.03202859312295914, "epoch": 1.2223071046600458, "percentage": 24.46, "elapsed_time": "3:02:24", "remaining_time": "9:23:11"}
{"current_steps": 810, "total_steps": 3270, "loss": 0.0361, "lr": 9.350003274189949e-05, "epoch": 1.2375859434682965, "percentage": 24.77, "elapsed_time": "3:03:57", "remaining_time": "9:18:41"}
{"current_steps": 820, "total_steps": 3270, "loss": 0.0312, "lr": 9.323439859460122e-05, "epoch": 1.2528647822765469, "percentage": 25.08, "elapsed_time": "3:05:26", "remaining_time": "9:14:04"}
{"current_steps": 830, "total_steps": 3270, "loss": 0.0311, "lr": 9.296383787887519e-05, "epoch": 1.2681436210847976, "percentage": 25.38, "elapsed_time": "3:06:55", "remaining_time": "9:09:32"}
{"current_steps": 840, "total_steps": 3270, "loss": 0.0405, "lr": 9.268838142516943e-05, "epoch": 1.2834224598930482, "percentage": 25.69, "elapsed_time": "3:08:24", "remaining_time": "9:05:03"}
{"current_steps": 850, "total_steps": 3270, "loss": 0.0325, "lr": 9.240806062180234e-05, "epoch": 1.2987012987012987, "percentage": 25.99, "elapsed_time": "3:09:53", "remaining_time": "9:00:39"}
{"current_steps": 850, "total_steps": 3270, "eval_loss": 0.03146594762802124, "epoch": 1.2987012987012987, "percentage": 25.99, "elapsed_time": "3:13:17", "remaining_time": "9:10:18"}
{"current_steps": 860, "total_steps": 3270, "loss": 0.0172, "lr": 9.212290741138592e-05, "epoch": 1.3139801375095492, "percentage": 26.3, "elapsed_time": "3:14:50", "remaining_time": "9:05:59"}
{"current_steps": 870, "total_steps": 3270, "loss": 0.0285, "lr": 9.183295428718592e-05, "epoch": 1.3292589763177998, "percentage": 26.61, "elapsed_time": "3:16:19", "remaining_time": "9:01:33"}
{"current_steps": 880, "total_steps": 3270, "loss": 0.0395, "lr": 9.153823428941924e-05, "epoch": 1.3445378151260505, "percentage": 26.91, "elapsed_time": "3:17:48", "remaining_time": "8:57:12"}
{"current_steps": 890, "total_steps": 3270, "loss": 0.0276, "lr": 9.1238781001489e-05, "epoch": 1.359816653934301, "percentage": 27.22, "elapsed_time": "3:19:16", "remaining_time": "8:52:54"}
{"current_steps": 900, "total_steps": 3270, "loss": 0.0351, "lr": 9.093462854615766e-05, "epoch": 1.3750954927425516, "percentage": 27.52, "elapsed_time": "3:20:45", "remaining_time": "8:48:40"}
{"current_steps": 900, "total_steps": 3270, "eval_loss": 0.030502911657094955, "epoch": 1.3750954927425516, "percentage": 27.52, "elapsed_time": "3:24:08", "remaining_time": "8:57:35"}
{"current_steps": 910, "total_steps": 3270, "loss": 0.0323, "lr": 9.062581158165876e-05, "epoch": 1.3903743315508021, "percentage": 27.83, "elapsed_time": "3:25:41", "remaining_time": "8:53:25"}
{"current_steps": 920, "total_steps": 3270, "loss": 0.0222, "lr": 9.031236529774764e-05, "epoch": 1.4056531703590527, "percentage": 28.13, "elapsed_time": "3:27:09", "remaining_time": "8:49:10"}
{"current_steps": 930, "total_steps": 3270, "loss": 0.0273, "lr": 8.999432541169145e-05, "epoch": 1.4209320091673032, "percentage": 28.44, "elapsed_time": "3:28:38", "remaining_time": "8:44:58"}
{"current_steps": 940, "total_steps": 3270, "loss": 0.0274, "lr": 8.967172816419927e-05, "epoch": 1.4362108479755538, "percentage": 28.75, "elapsed_time": "3:30:07", "remaining_time": "8:40:49"}
{"current_steps": 950, "total_steps": 3270, "loss": 0.0402, "lr": 8.934461031529242e-05, "epoch": 1.4514896867838045, "percentage": 29.05, "elapsed_time": "3:31:36", "remaining_time": "8:36:45"}
{"current_steps": 950, "total_steps": 3270, "eval_loss": 0.03139554709196091, "epoch": 1.4514896867838045, "percentage": 29.05, "elapsed_time": "3:34:59", "remaining_time": "8:45:01"}
{"current_steps": 960, "total_steps": 3270, "loss": 0.0308, "lr": 8.901300914011569e-05, "epoch": 1.466768525592055, "percentage": 29.36, "elapsed_time": "3:36:31", "remaining_time": "8:41:01"}
{"current_steps": 970, "total_steps": 3270, "loss": 0.0228, "lr": 8.867696242468976e-05, "epoch": 1.4820473644003056, "percentage": 29.66, "elapsed_time": "3:38:00", "remaining_time": "8:36:56"}
{"current_steps": 980, "total_steps": 3270, "loss": 0.0321, "lr": 8.833650846160555e-05, "epoch": 1.4973262032085561, "percentage": 29.97, "elapsed_time": "3:39:30", "remaining_time": "8:32:54"}
{"current_steps": 990, "total_steps": 3270, "loss": 0.0269, "lr": 8.79916860456607e-05, "epoch": 1.5126050420168067, "percentage": 30.28, "elapsed_time": "3:40:58", "remaining_time": "8:28:54"}
{"current_steps": 1000, "total_steps": 3270, "loss": 0.0262, "lr": 8.7642534469439e-05, "epoch": 1.5278838808250574, "percentage": 30.58, "elapsed_time": "3:42:27", "remaining_time": "8:24:58"}
{"current_steps": 1000, "total_steps": 3270, "eval_loss": 0.029931625351309776, "epoch": 1.5278838808250574, "percentage": 30.58, "elapsed_time": "3:45:49", "remaining_time": "8:32:38"}
{"current_steps": 1010, "total_steps": 3270, "loss": 0.0295, "lr": 8.728909351883283e-05, "epoch": 1.5431627196333078, "percentage": 30.89, "elapsed_time": "3:47:21", "remaining_time": "8:28:45"}
{"current_steps": 1020, "total_steps": 3270, "loss": 0.0379, "lr": 8.693140346850975e-05, "epoch": 1.5584415584415585, "percentage": 31.19, "elapsed_time": "3:48:50", "remaining_time": "8:24:47"}
{"current_steps": 1030, "total_steps": 3270, "loss": 0.0247, "lr": 8.656950507732303e-05, "epoch": 1.573720397249809, "percentage": 31.5, "elapsed_time": "3:50:18", "remaining_time": "8:20:52"}
{"current_steps": 1040, "total_steps": 3270, "loss": 0.0284, "lr": 8.620343958366718e-05, "epoch": 1.5889992360580596, "percentage": 31.8, "elapsed_time": "3:51:47", "remaining_time": "8:17:01"}
{"current_steps": 1050, "total_steps": 3270, "loss": 0.026, "lr": 8.5833248700779e-05, "epoch": 1.6042780748663101, "percentage": 32.11, "elapsed_time": "3:53:16", "remaining_time": "8:13:13"}
{"current_steps": 1050, "total_steps": 3270, "eval_loss": 0.030233880504965782, "epoch": 1.6042780748663101, "percentage": 32.11, "elapsed_time": "3:56:39", "remaining_time": "8:20:20"}
{"current_steps": 1060, "total_steps": 3270, "loss": 0.0269, "lr": 8.545897461198413e-05, "epoch": 1.6195569136745607, "percentage": 32.42, "elapsed_time": "3:58:10", "remaining_time": "8:16:35"}
{"current_steps": 1070, "total_steps": 3270, "loss": 0.0295, "lr": 8.508065996589036e-05, "epoch": 1.6348357524828114, "percentage": 32.72, "elapsed_time": "3:59:39", "remaining_time": "8:12:45"}
{"current_steps": 1080, "total_steps": 3270, "loss": 0.0235, "lr": 8.469834787152783e-05, "epoch": 1.6501145912910617, "percentage": 33.03, "elapsed_time": "4:01:07", "remaining_time": "8:08:57"}
{"current_steps": 1090, "total_steps": 3270, "loss": 0.0267, "lr": 8.43120818934367e-05, "epoch": 1.6653934300993125, "percentage": 33.33, "elapsed_time": "4:02:36", "remaining_time": "8:05:12"}
{"current_steps": 1100, "total_steps": 3270, "loss": 0.024, "lr": 8.392190604670293e-05, "epoch": 1.680672268907563, "percentage": 33.64, "elapsed_time": "4:04:05", "remaining_time": "8:01:31"}
{"current_steps": 1100, "total_steps": 3270, "eval_loss": 0.031445007771253586, "epoch": 1.680672268907563, "percentage": 33.64, "elapsed_time": "4:07:26", "remaining_time": "8:08:09"}
{"current_steps": 1110, "total_steps": 3270, "loss": 0.0351, "lr": 8.352786479194288e-05, "epoch": 1.6959511077158136, "percentage": 33.94, "elapsed_time": "4:08:58", "remaining_time": "8:04:30"}
{"current_steps": 1120, "total_steps": 3270, "loss": 0.0245, "lr": 8.313000303023688e-05, "epoch": 1.7112299465240641, "percentage": 34.25, "elapsed_time": "4:10:27", "remaining_time": "8:00:47"}
{"current_steps": 1130, "total_steps": 3270, "loss": 0.0371, "lr": 8.27283660980128e-05, "epoch": 1.7265087853323147, "percentage": 34.56, "elapsed_time": "4:11:56", "remaining_time": "7:57:06"}
{"current_steps": 1140, "total_steps": 3270, "loss": 0.0334, "lr": 8.232299976187999e-05, "epoch": 1.7417876241405654, "percentage": 34.86, "elapsed_time": "4:13:24", "remaining_time": "7:53:28"}
{"current_steps": 1150, "total_steps": 3270, "loss": 0.0487, "lr": 8.191395021341408e-05, "epoch": 1.7570664629488157, "percentage": 35.17, "elapsed_time": "4:14:52", "remaining_time": "7:49:51"}
{"current_steps": 1150, "total_steps": 3270, "eval_loss": 0.03015304170548916, "epoch": 1.7570664629488157, "percentage": 35.17, "elapsed_time": "4:18:14", "remaining_time": "7:56:03"}
{"current_steps": 1160, "total_steps": 3270, "loss": 0.0299, "lr": 8.150126406389352e-05, "epoch": 1.7723453017570665, "percentage": 35.47, "elapsed_time": "4:19:46", "remaining_time": "7:52:30"}
{"current_steps": 1170, "total_steps": 3270, "loss": 0.0315, "lr": 8.108498833898815e-05, "epoch": 1.787624140565317, "percentage": 35.78, "elapsed_time": "4:21:15", "remaining_time": "7:48:54"}
{"current_steps": 1180, "total_steps": 3270, "loss": 0.0348, "lr": 8.066517047340066e-05, "epoch": 1.8029029793735676, "percentage": 36.09, "elapsed_time": "4:22:43", "remaining_time": "7:45:20"}
{"current_steps": 1190, "total_steps": 3270, "loss": 0.0213, "lr": 8.02418583054614e-05, "epoch": 1.8181818181818183, "percentage": 36.39, "elapsed_time": "4:24:12", "remaining_time": "7:41:48"}
{"current_steps": 1200, "total_steps": 3270, "loss": 0.0251, "lr": 7.981510007167719e-05, "epoch": 1.8334606569900687, "percentage": 36.7, "elapsed_time": "4:25:40", "remaining_time": "7:38:17"}
{"current_steps": 1200, "total_steps": 3270, "eval_loss": 0.030031004920601845, "epoch": 1.8334606569900687, "percentage": 36.7, "elapsed_time": "4:29:02", "remaining_time": "7:44:05"}
{"current_steps": 1210, "total_steps": 3270, "loss": 0.0295, "lr": 7.938494440123468e-05, "epoch": 1.8487394957983194, "percentage": 37.0, "elapsed_time": "4:30:34", "remaining_time": "7:40:38"}
{"current_steps": 1220, "total_steps": 3270, "loss": 0.0287, "lr": 7.895144031045918e-05, "epoch": 1.8640183346065697, "percentage": 37.31, "elapsed_time": "4:32:02", "remaining_time": "7:37:07"}
{"current_steps": 1230, "total_steps": 3270, "loss": 0.025, "lr": 7.851463719722913e-05, "epoch": 1.8792971734148205, "percentage": 37.61, "elapsed_time": "4:33:30", "remaining_time": "7:33:38"}
{"current_steps": 1240, "total_steps": 3270, "loss": 0.0294, "lr": 7.80745848353473e-05, "epoch": 1.894576012223071, "percentage": 37.92, "elapsed_time": "4:34:59", "remaining_time": "7:30:10"}
{"current_steps": 1250, "total_steps": 3270, "loss": 0.028, "lr": 7.763133336886892e-05, "epoch": 1.9098548510313216, "percentage": 38.23, "elapsed_time": "4:36:27", "remaining_time": "7:26:45"}
{"current_steps": 1250, "total_steps": 3270, "eval_loss": 0.031990259885787964, "epoch": 1.9098548510313216, "percentage": 38.23, "elapsed_time": "4:39:49", "remaining_time": "7:32:12"}
{"current_steps": 1260, "total_steps": 3270, "loss": 0.0205, "lr": 7.718493330638789e-05, "epoch": 1.9251336898395723, "percentage": 38.53, "elapsed_time": "4:41:21", "remaining_time": "7:28:50"}
{"current_steps": 1270, "total_steps": 3270, "loss": 0.0346, "lr": 7.673543551528122e-05, "epoch": 1.9404125286478227, "percentage": 38.84, "elapsed_time": "4:42:49", "remaining_time": "7:25:23"}
{"current_steps": 1280, "total_steps": 3270, "loss": 0.0314, "lr": 7.628289121591277e-05, "epoch": 1.9556913674560734, "percentage": 39.14, "elapsed_time": "4:44:18", "remaining_time": "7:21:59"}
{"current_steps": 1290, "total_steps": 3270, "loss": 0.0282, "lr": 7.582735197579656e-05, "epoch": 1.970970206264324, "percentage": 39.45, "elapsed_time": "4:45:46", "remaining_time": "7:18:37"}
{"current_steps": 1300, "total_steps": 3270, "loss": 0.0244, "lr": 7.536886970372078e-05, "epoch": 1.9862490450725745, "percentage": 39.76, "elapsed_time": "4:47:14", "remaining_time": "7:15:17"}
{"current_steps": 1300, "total_steps": 3270, "eval_loss": 0.029929550364613533, "epoch": 1.9862490450725745, "percentage": 39.76, "elapsed_time": "4:50:36", "remaining_time": "7:20:22"}
{"current_steps": 1310, "total_steps": 3270, "loss": 0.0372, "lr": 7.490749664383271e-05, "epoch": 2.0015278838808253, "percentage": 40.06, "elapsed_time": "4:52:08", "remaining_time": "7:17:05"}
{"current_steps": 1320, "total_steps": 3270, "loss": 0.0258, "lr": 7.444328536968538e-05, "epoch": 2.0168067226890756, "percentage": 40.37, "elapsed_time": "4:53:35", "remaining_time": "7:13:43"}
{"current_steps": 1330, "total_steps": 3270, "loss": 0.024, "lr": 7.397628877824701e-05, "epoch": 2.0320855614973263, "percentage": 40.67, "elapsed_time": "4:55:04", "remaining_time": "7:10:24"}
{"current_steps": 1340, "total_steps": 3270, "loss": 0.0192, "lr": 7.350656008387327e-05, "epoch": 2.0473644003055766, "percentage": 40.98, "elapsed_time": "4:56:32", "remaining_time": "7:07:06"}
{"current_steps": 1350, "total_steps": 3270, "loss": 0.0211, "lr": 7.303415281224346e-05, "epoch": 2.0626432391138274, "percentage": 41.28, "elapsed_time": "4:58:01", "remaining_time": "7:03:51"}
{"current_steps": 1350, "total_steps": 3270, "eval_loss": 0.0282374769449234, "epoch": 2.0626432391138274, "percentage": 41.28, "elapsed_time": "5:01:23", "remaining_time": "7:08:38"}
{"current_steps": 1360, "total_steps": 3270, "loss": 0.0155, "lr": 7.255912079426136e-05, "epoch": 2.0779220779220777, "percentage": 41.59, "elapsed_time": "5:02:55", "remaining_time": "7:05:25"}
{"current_steps": 1370, "total_steps": 3270, "loss": 0.0172, "lr": 7.208151815992107e-05, "epoch": 2.0932009167303285, "percentage": 41.9, "elapsed_time": "5:04:22", "remaining_time": "7:02:07"}
{"current_steps": 1380, "total_steps": 3270, "loss": 0.0254, "lr": 7.160139933213898e-05, "epoch": 2.1084797555385792, "percentage": 42.2, "elapsed_time": "5:05:51", "remaining_time": "6:58:53"}
{"current_steps": 1390, "total_steps": 3270, "loss": 0.0226, "lr": 7.111881902055223e-05, "epoch": 2.1237585943468296, "percentage": 42.51, "elapsed_time": "5:07:19", "remaining_time": "6:55:39"}
{"current_steps": 1400, "total_steps": 3270, "loss": 0.019, "lr": 7.06338322152845e-05, "epoch": 2.1390374331550803, "percentage": 42.81, "elapsed_time": "5:08:47", "remaining_time": "6:52:27"}
{"current_steps": 1400, "total_steps": 3270, "eval_loss": 0.02854863740503788, "epoch": 2.1390374331550803, "percentage": 42.81, "elapsed_time": "5:12:08", "remaining_time": "6:56:56"}
{"current_steps": 1410, "total_steps": 3270, "loss": 0.0176, "lr": 7.014649418067994e-05, "epoch": 2.1543162719633306, "percentage": 43.12, "elapsed_time": "5:13:40", "remaining_time": "6:53:46"}
{"current_steps": 1420, "total_steps": 3270, "loss": 0.0163, "lr": 6.965686044900577e-05, "epoch": 2.1695951107715814, "percentage": 43.43, "elapsed_time": "5:15:08", "remaining_time": "6:50:33"}
{"current_steps": 1430, "total_steps": 3270, "loss": 0.0154, "lr": 6.91649868141243e-05, "epoch": 2.184873949579832, "percentage": 43.73, "elapsed_time": "5:16:36", "remaining_time": "6:47:22"}
{"current_steps": 1440, "total_steps": 3270, "loss": 0.0142, "lr": 6.86709293251353e-05, "epoch": 2.2001527883880825, "percentage": 44.04, "elapsed_time": "5:18:04", "remaining_time": "6:44:13"}
{"current_steps": 1450, "total_steps": 3270, "loss": 0.012, "lr": 6.817474427998916e-05, "epoch": 2.2154316271963332, "percentage": 44.34, "elapsed_time": "5:19:32", "remaining_time": "6:41:04"}
{"current_steps": 1450, "total_steps": 3270, "eval_loss": 0.030223889276385307, "epoch": 2.2154316271963332, "percentage": 44.34, "elapsed_time": "5:22:53", "remaining_time": "6:45:17"}
{"current_steps": 1460, "total_steps": 3270, "loss": 0.0192, "lr": 6.767648821907172e-05, "epoch": 2.2307104660045836, "percentage": 44.65, "elapsed_time": "5:24:25", "remaining_time": "6:42:11"}
{"current_steps": 1470, "total_steps": 3270, "loss": 0.0302, "lr": 6.717621791876147e-05, "epoch": 2.2459893048128343, "percentage": 44.95, "elapsed_time": "5:25:53", "remaining_time": "6:39:03"}
{"current_steps": 1480, "total_steps": 3270, "loss": 0.0207, "lr": 6.667399038495986e-05, "epoch": 2.2612681436210846, "percentage": 45.26, "elapsed_time": "5:27:21", "remaining_time": "6:35:55"}
{"current_steps": 1490, "total_steps": 3270, "loss": 0.0247, "lr": 6.616986284659556e-05, "epoch": 2.2765469824293354, "percentage": 45.57, "elapsed_time": "5:28:49", "remaining_time": "6:32:49"}
{"current_steps": 1500, "total_steps": 3270, "loss": 0.0181, "lr": 6.566389274910309e-05, "epoch": 2.2918258212375857, "percentage": 45.87, "elapsed_time": "5:30:17", "remaining_time": "6:29:45"}
{"current_steps": 1500, "total_steps": 3270, "eval_loss": 0.02827996388077736, "epoch": 2.2918258212375857, "percentage": 45.87, "elapsed_time": "5:33:39", "remaining_time": "6:33:42"}
{"current_steps": 1510, "total_steps": 3270, "loss": 0.019, "lr": 6.515613774787697e-05, "epoch": 2.3071046600458365, "percentage": 46.18, "elapsed_time": "5:35:10", "remaining_time": "6:30:39"}
{"current_steps": 1520, "total_steps": 3270, "loss": 0.0215, "lr": 6.464665570170186e-05, "epoch": 2.3223834988540872, "percentage": 46.48, "elapsed_time": "5:36:38", "remaining_time": "6:27:35"}
{"current_steps": 1530, "total_steps": 3270, "loss": 0.017, "lr": 6.413550466615952e-05, "epoch": 2.3376623376623376, "percentage": 46.79, "elapsed_time": "5:38:06", "remaining_time": "6:24:31"}
{"current_steps": 1540, "total_steps": 3270, "loss": 0.0174, "lr": 6.362274288701342e-05, "epoch": 2.3529411764705883, "percentage": 47.09, "elapsed_time": "5:39:34", "remaining_time": "6:21:28"}
{"current_steps": 1550, "total_steps": 3270, "loss": 0.0176, "lr": 6.310842879357158e-05, "epoch": 2.3682200152788386, "percentage": 47.4, "elapsed_time": "5:41:02", "remaining_time": "6:18:27"}
{"current_steps": 1550, "total_steps": 3270, "eval_loss": 0.028811601921916008, "epoch": 2.3682200152788386, "percentage": 47.4, "elapsed_time": "5:44:24", "remaining_time": "6:22:10"}
{"current_steps": 1560, "total_steps": 3270, "loss": 0.0117, "lr": 6.25926209920285e-05, "epoch": 2.3834988540870894, "percentage": 47.71, "elapsed_time": "5:45:58", "remaining_time": "6:19:14"}
{"current_steps": 1570, "total_steps": 3270, "loss": 0.0165, "lr": 6.207537825878708e-05, "epoch": 2.39877769289534, "percentage": 48.01, "elapsed_time": "5:47:25", "remaining_time": "6:16:12"}
{"current_steps": 1580, "total_steps": 3270, "loss": 0.027, "lr": 6.155675953376095e-05, "epoch": 2.4140565317035905, "percentage": 48.32, "elapsed_time": "5:48:54", "remaining_time": "6:13:11"}
{"current_steps": 1590, "total_steps": 3270, "loss": 0.0185, "lr": 6.103682391365828e-05, "epoch": 2.4293353705118412, "percentage": 48.62, "elapsed_time": "5:50:22", "remaining_time": "6:10:12"}
{"current_steps": 1600, "total_steps": 3270, "loss": 0.0136, "lr": 6.05156306452477e-05, "epoch": 2.4446142093200915, "percentage": 48.93, "elapsed_time": "5:51:50", "remaining_time": "6:07:13"}
{"current_steps": 1600, "total_steps": 3270, "eval_loss": 0.027694666758179665, "epoch": 2.4446142093200915, "percentage": 48.93, "elapsed_time": "5:55:11", "remaining_time": "6:10:44"}
{"current_steps": 1610, "total_steps": 3270, "loss": 0.0251, "lr": 5.9993239118607124e-05, "epoch": 2.4598930481283423, "percentage": 49.24, "elapsed_time": "5:56:44", "remaining_time": "6:07:49"}
{"current_steps": 1620, "total_steps": 3270, "loss": 0.0207, "lr": 5.9469708860356246e-05, "epoch": 2.475171886936593, "percentage": 49.54, "elapsed_time": "5:58:12", "remaining_time": "6:04:50"}
{"current_steps": 1630, "total_steps": 3270, "loss": 0.0195, "lr": 5.89450995268734e-05, "epoch": 2.4904507257448434, "percentage": 49.85, "elapsed_time": "5:59:40", "remaining_time": "6:01:52"}
{"current_steps": 1640, "total_steps": 3270, "loss": 0.0251, "lr": 5.841947089749783e-05, "epoch": 2.5057295645530937, "percentage": 50.15, "elapsed_time": "6:01:08", "remaining_time": "5:58:56"}
{"current_steps": 1650, "total_steps": 3270, "loss": 0.0217, "lr": 5.78928828677177e-05, "epoch": 2.5210084033613445, "percentage": 50.46, "elapsed_time": "6:02:36", "remaining_time": "5:56:01"}
{"current_steps": 1650, "total_steps": 3270, "eval_loss": 0.028578663244843483, "epoch": 2.5210084033613445, "percentage": 50.46, "elapsed_time": "6:05:57", "remaining_time": "5:59:18"}
{"current_steps": 1660, "total_steps": 3270, "loss": 0.0143, "lr": 5.7365395442345085e-05, "epoch": 2.5362872421695952, "percentage": 50.76, "elapsed_time": "6:07:29", "remaining_time": "5:56:25"}
{"current_steps": 1670, "total_steps": 3270, "loss": 0.0149, "lr": 5.683706872867833e-05, "epoch": 2.5515660809778455, "percentage": 51.07, "elapsed_time": "6:08:57", "remaining_time": "5:53:29"}
{"current_steps": 1680, "total_steps": 3270, "loss": 0.0255, "lr": 5.630796292965288e-05, "epoch": 2.5668449197860963, "percentage": 51.38, "elapsed_time": "6:10:25", "remaining_time": "5:50:34"}
{"current_steps": 1690, "total_steps": 3270, "loss": 0.02, "lr": 5.57781383369811e-05, "epoch": 2.5821237585943466, "percentage": 51.68, "elapsed_time": "6:11:54", "remaining_time": "5:47:41"}
{"current_steps": 1700, "total_steps": 3270, "loss": 0.0156, "lr": 5.524765532428203e-05, "epoch": 2.5974025974025974, "percentage": 51.99, "elapsed_time": "6:13:22", "remaining_time": "5:44:49"}
{"current_steps": 1700, "total_steps": 3270, "eval_loss": 0.029410608112812042, "epoch": 2.5974025974025974, "percentage": 51.99, "elapsed_time": "6:16:43", "remaining_time": "5:47:54"}
{"current_steps": 1710, "total_steps": 3270, "loss": 0.0187, "lr": 5.471657434020182e-05, "epoch": 2.612681436210848, "percentage": 52.29, "elapsed_time": "6:18:16", "remaining_time": "5:45:05"}
{"current_steps": 1720, "total_steps": 3270, "loss": 0.0231, "lr": 5.418495590152557e-05, "epoch": 2.6279602750190985, "percentage": 52.6, "elapsed_time": "6:19:44", "remaining_time": "5:42:12"}
{"current_steps": 1730, "total_steps": 3270, "loss": 0.0212, "lr": 5.365286058628145e-05, "epoch": 2.643239113827349, "percentage": 52.91, "elapsed_time": "6:21:12", "remaining_time": "5:39:20"}
{"current_steps": 1740, "total_steps": 3270, "loss": 0.0268, "lr": 5.312034902683779e-05, "epoch": 2.6585179526355995, "percentage": 53.21, "elapsed_time": "6:22:40", "remaining_time": "5:36:29"}
{"current_steps": 1750, "total_steps": 3270, "loss": 0.0191, "lr": 5.258748190299404e-05, "epoch": 2.6737967914438503, "percentage": 53.52, "elapsed_time": "6:24:08", "remaining_time": "5:33:39"}
{"current_steps": 1750, "total_steps": 3270, "eval_loss": 0.028579337522387505, "epoch": 2.6737967914438503, "percentage": 53.52, "elapsed_time": "6:27:29", "remaining_time": "5:36:33"}
{"current_steps": 1760, "total_steps": 3270, "loss": 0.0217, "lr": 5.20543199350663e-05, "epoch": 2.689075630252101, "percentage": 53.82, "elapsed_time": "6:29:02", "remaining_time": "5:33:46"}
{"current_steps": 1770, "total_steps": 3270, "loss": 0.0215, "lr": 5.152092387696821e-05, "epoch": 2.7043544690603514, "percentage": 54.13, "elapsed_time": "6:30:30", "remaining_time": "5:30:55"}
{"current_steps": 1780, "total_steps": 3270, "loss": 0.0224, "lr": 5.0987354509287985e-05, "epoch": 2.719633307868602, "percentage": 54.43, "elapsed_time": "6:31:58", "remaining_time": "5:28:06"}
{"current_steps": 1790, "total_steps": 3270, "loss": 0.017, "lr": 5.045367263236257e-05, "epoch": 2.7349121466768525, "percentage": 54.74, "elapsed_time": "6:33:26", "remaining_time": "5:25:18"}
{"current_steps": 1800, "total_steps": 3270, "loss": 0.0249, "lr": 4.991993905934931e-05, "epoch": 2.750190985485103, "percentage": 55.05, "elapsed_time": "6:34:54", "remaining_time": "5:22:30"}
{"current_steps": 1800, "total_steps": 3270, "eval_loss": 0.027184655889868736, "epoch": 2.750190985485103, "percentage": 55.05, "elapsed_time": "6:38:15", "remaining_time": "5:25:14"}
{"current_steps": 1810, "total_steps": 3270, "loss": 0.0182, "lr": 4.938621460929639e-05, "epoch": 2.765469824293354, "percentage": 55.35, "elapsed_time": "6:39:46", "remaining_time": "5:22:28"}
{"current_steps": 1820, "total_steps": 3270, "loss": 0.0193, "lr": 4.885256010021233e-05, "epoch": 2.7807486631016043, "percentage": 55.66, "elapsed_time": "6:41:15", "remaining_time": "5:19:41"}
{"current_steps": 1830, "total_steps": 3270, "loss": 0.0199, "lr": 4.831903634213599e-05, "epoch": 2.7960275019098546, "percentage": 55.96, "elapsed_time": "6:42:43", "remaining_time": "5:16:53"}
{"current_steps": 1840, "total_steps": 3270, "loss": 0.0211, "lr": 4.778570413020702e-05, "epoch": 2.8113063407181054, "percentage": 56.27, "elapsed_time": "6:44:11", "remaining_time": "5:14:07"}
{"current_steps": 1850, "total_steps": 3270, "loss": 0.0237, "lr": 4.725262423773838e-05, "epoch": 2.826585179526356, "percentage": 56.57, "elapsed_time": "6:45:39", "remaining_time": "5:11:21"}
{"current_steps": 1850, "total_steps": 3270, "eval_loss": 0.02900101989507675, "epoch": 2.826585179526356, "percentage": 56.57, "elapsed_time": "6:49:00", "remaining_time": "5:13:56"}
{"current_steps": 1860, "total_steps": 3270, "loss": 0.0165, "lr": 4.671985740929123e-05, "epoch": 2.8418640183346064, "percentage": 56.88, "elapsed_time": "6:50:31", "remaining_time": "5:11:12"}
{"current_steps": 1870, "total_steps": 3270, "loss": 0.023, "lr": 4.618746435375295e-05, "epoch": 2.857142857142857, "percentage": 57.19, "elapsed_time": "6:51:59", "remaining_time": "5:08:26"}
{"current_steps": 1880, "total_steps": 3270, "loss": 0.0159, "lr": 4.565550573741942e-05, "epoch": 2.8724216959511075, "percentage": 57.49, "elapsed_time": "6:53:27", "remaining_time": "5:05:41"}
{"current_steps": 1890, "total_steps": 3270, "loss": 0.0227, "lr": 4.512404217708217e-05, "epoch": 2.8877005347593583, "percentage": 57.8, "elapsed_time": "6:54:55", "remaining_time": "5:02:57"}
{"current_steps": 1900, "total_steps": 3270, "loss": 0.021, "lr": 4.45931342331209e-05, "epoch": 2.902979373567609, "percentage": 58.1, "elapsed_time": "6:56:23", "remaining_time": "5:00:14"}
{"current_steps": 1900, "total_steps": 3270, "eval_loss": 0.02777683548629284, "epoch": 2.902979373567609, "percentage": 58.1, "elapsed_time": "6:59:44", "remaining_time": "5:02:39"}
{"current_steps": 1910, "total_steps": 3270, "loss": 0.023, "lr": 4.406284240260278e-05, "epoch": 2.9182582123758594, "percentage": 58.41, "elapsed_time": "7:01:15", "remaining_time": "4:59:57"}
{"current_steps": 1920, "total_steps": 3270, "loss": 0.0165, "lr": 4.3533227112388694e-05, "epoch": 2.93353705118411, "percentage": 58.72, "elapsed_time": "7:02:42", "remaining_time": "4:57:13"}
{"current_steps": 1930, "total_steps": 3270, "loss": 0.0234, "lr": 4.300434871224763e-05, "epoch": 2.9488158899923604, "percentage": 59.02, "elapsed_time": "7:04:10", "remaining_time": "4:54:30"}
{"current_steps": 1940, "total_steps": 3270, "loss": 0.0207, "lr": 4.247626746797983e-05, "epoch": 2.964094728800611, "percentage": 59.33, "elapsed_time": "7:05:38", "remaining_time": "4:51:48"}
{"current_steps": 1950, "total_steps": 3270, "loss": 0.0174, "lr": 4.1949043554549406e-05, "epoch": 2.979373567608862, "percentage": 59.63, "elapsed_time": "7:07:06", "remaining_time": "4:49:07"}
{"current_steps": 1950, "total_steps": 3270, "eval_loss": 0.028289297595620155, "epoch": 2.979373567608862, "percentage": 59.63, "elapsed_time": "7:10:27", "remaining_time": "4:51:23"}
{"current_steps": 1960, "total_steps": 3270, "loss": 0.0261, "lr": 4.14227370492275e-05, "epoch": 2.9946524064171123, "percentage": 59.94, "elapsed_time": "7:11:58", "remaining_time": "4:48:43"}
{"current_steps": 1970, "total_steps": 3270, "loss": 0.0172, "lr": 4.08974079247464e-05, "epoch": 3.009931245225363, "percentage": 60.24, "elapsed_time": "7:13:26", "remaining_time": "4:46:01"}
{"current_steps": 1980, "total_steps": 3270, "loss": 0.0115, "lr": 4.037311604246565e-05, "epoch": 3.0252100840336134, "percentage": 60.55, "elapsed_time": "7:14:54", "remaining_time": "4:43:21"}
{"current_steps": 1990, "total_steps": 3270, "loss": 0.0129, "lr": 3.9849921145550805e-05, "epoch": 3.040488922841864, "percentage": 60.86, "elapsed_time": "7:16:22", "remaining_time": "4:40:41"}
{"current_steps": 2000, "total_steps": 3270, "loss": 0.0122, "lr": 3.9327882852165795e-05, "epoch": 3.0557677616501144, "percentage": 61.16, "elapsed_time": "7:17:50", "remaining_time": "4:38:01"}
{"current_steps": 2000, "total_steps": 3270, "eval_loss": 0.028973255306482315, "epoch": 3.0557677616501144, "percentage": 61.16, "elapsed_time": "7:21:11", "remaining_time": "4:40:09"}
{"current_steps": 2010, "total_steps": 3270, "loss": 0.0125, "lr": 3.880706064867926e-05, "epoch": 3.071046600458365, "percentage": 61.47, "elapsed_time": "7:22:42", "remaining_time": "4:37:31"}
{"current_steps": 2020, "total_steps": 3270, "loss": 0.009, "lr": 3.8287513882886196e-05, "epoch": 3.0863254392666155, "percentage": 61.77, "elapsed_time": "7:24:10", "remaining_time": "4:34:51"}
{"current_steps": 2030, "total_steps": 3270, "loss": 0.011, "lr": 3.776930175724521e-05, "epoch": 3.1016042780748663, "percentage": 62.08, "elapsed_time": "7:25:37", "remaining_time": "4:32:12"}
{"current_steps": 2040, "total_steps": 3270, "loss": 0.0128, "lr": 3.7252483322132386e-05, "epoch": 3.116883116883117, "percentage": 62.39, "elapsed_time": "7:27:05", "remaining_time": "4:29:34"}
{"current_steps": 2050, "total_steps": 3270, "loss": 0.0137, "lr": 3.673711746911252e-05, "epoch": 3.1321619556913673, "percentage": 62.69, "elapsed_time": "7:28:34", "remaining_time": "4:26:57"}
{"current_steps": 2050, "total_steps": 3270, "eval_loss": 0.030082957819104195, "epoch": 3.1321619556913673, "percentage": 62.69, "elapsed_time": "7:31:54", "remaining_time": "4:28:56"}
{"current_steps": 2060, "total_steps": 3270, "loss": 0.0078, "lr": 3.6223262924228344e-05, "epoch": 3.147440794499618, "percentage": 63.0, "elapsed_time": "7:33:25", "remaining_time": "4:26:20"}
{"current_steps": 2070, "total_steps": 3270, "loss": 0.013, "lr": 3.5710978241308733e-05, "epoch": 3.1627196333078684, "percentage": 63.3, "elapsed_time": "7:34:54", "remaining_time": "4:23:42"}
{"current_steps": 2080, "total_steps": 3270, "loss": 0.0123, "lr": 3.520032179529652e-05, "epoch": 3.177998472116119, "percentage": 63.61, "elapsed_time": "7:36:21", "remaining_time": "4:21:05"}
{"current_steps": 2090, "total_steps": 3270, "loss": 0.0135, "lr": 3.4691351775596564e-05, "epoch": 3.19327731092437, "percentage": 63.91, "elapsed_time": "7:37:49", "remaining_time": "4:18:29"}
{"current_steps": 2100, "total_steps": 3270, "loss": 0.0086, "lr": 3.41841261794451e-05, "epoch": 3.2085561497326203, "percentage": 64.22, "elapsed_time": "7:39:17", "remaining_time": "4:15:53"}
{"current_steps": 2100, "total_steps": 3270, "eval_loss": 0.030945168808102608, "epoch": 3.2085561497326203, "percentage": 64.22, "elapsed_time": "7:42:38", "remaining_time": "4:17:45"}
{"current_steps": 2110, "total_steps": 3270, "loss": 0.0176, "lr": 3.367870280530101e-05, "epoch": 3.223834988540871, "percentage": 64.53, "elapsed_time": "7:44:09", "remaining_time": "4:15:10"}
{"current_steps": 2120, "total_steps": 3270, "loss": 0.0109, "lr": 3.3175139246259536e-05, "epoch": 3.2391138273491213, "percentage": 64.83, "elapsed_time": "7:45:36", "remaining_time": "4:12:34"}
{"current_steps": 2130, "total_steps": 3270, "loss": 0.0105, "lr": 3.2673492883489696e-05, "epoch": 3.254392666157372, "percentage": 65.14, "elapsed_time": "7:47:03", "remaining_time": "4:09:58"}
{"current_steps": 2140, "total_steps": 3270, "loss": 0.0166, "lr": 3.2173820879695535e-05, "epoch": 3.2696715049656224, "percentage": 65.44, "elapsed_time": "7:48:30", "remaining_time": "4:07:23"}
{"current_steps": 2150, "total_steps": 3270, "loss": 0.0136, "lr": 3.1676180172602525e-05, "epoch": 3.284950343773873, "percentage": 65.75, "elapsed_time": "7:49:55", "remaining_time": "4:04:47"}
{"current_steps": 2150, "total_steps": 3270, "eval_loss": 0.030590800568461418, "epoch": 3.284950343773873, "percentage": 65.75, "elapsed_time": "7:53:15", "remaining_time": "4:06:31"}
{"current_steps": 2160, "total_steps": 3270, "loss": 0.0115, "lr": 3.11806274684695e-05, "epoch": 3.300229182582124, "percentage": 66.06, "elapsed_time": "7:54:46", "remaining_time": "4:03:59"}
{"current_steps": 2170, "total_steps": 3270, "loss": 0.0076, "lr": 3.068721923562688e-05, "epoch": 3.3155080213903743, "percentage": 66.36, "elapsed_time": "7:56:14", "remaining_time": "4:01:24"}
{"current_steps": 2180, "total_steps": 3270, "loss": 0.0109, "lr": 3.019601169804216e-05, "epoch": 3.330786860198625, "percentage": 66.67, "elapsed_time": "7:57:42", "remaining_time": "3:58:51"}
{"current_steps": 2190, "total_steps": 3270, "loss": 0.0086, "lr": 2.9707060828913225e-05, "epoch": 3.3460656990068753, "percentage": 66.97, "elapsed_time": "7:59:09", "remaining_time": "3:56:17"}
{"current_steps": 2200, "total_steps": 3270, "loss": 0.0111, "lr": 2.9220422344290056e-05, "epoch": 3.361344537815126, "percentage": 67.28, "elapsed_time": "8:00:37", "remaining_time": "3:53:45"}
{"current_steps": 2200, "total_steps": 3270, "eval_loss": 0.03102887235581875, "epoch": 3.361344537815126, "percentage": 67.28, "elapsed_time": "8:03:57", "remaining_time": "3:55:23"}
{"current_steps": 2210, "total_steps": 3270, "loss": 0.0099, "lr": 2.873615169672601e-05, "epoch": 3.3766233766233764, "percentage": 67.58, "elapsed_time": "8:05:29", "remaining_time": "3:52:51"}
{"current_steps": 2220, "total_steps": 3270, "loss": 0.011, "lr": 2.8254304068958927e-05, "epoch": 3.391902215431627, "percentage": 67.89, "elapsed_time": "8:06:56", "remaining_time": "3:50:18"}
{"current_steps": 2230, "total_steps": 3270, "loss": 0.0159, "lr": 2.7774934367622996e-05, "epoch": 3.407181054239878, "percentage": 68.2, "elapsed_time": "8:08:24", "remaining_time": "3:47:46"}
{"current_steps": 2240, "total_steps": 3270, "loss": 0.0095, "lr": 2.7298097216992284e-05, "epoch": 3.4224598930481283, "percentage": 68.5, "elapsed_time": "8:09:52", "remaining_time": "3:45:15"}
{"current_steps": 2250, "total_steps": 3270, "loss": 0.0142, "lr": 2.6823846952756125e-05, "epoch": 3.437738731856379, "percentage": 68.81, "elapsed_time": "8:11:20", "remaining_time": "3:42:44"}
{"current_steps": 2250, "total_steps": 3270, "eval_loss": 0.03270566090941429, "epoch": 3.437738731856379, "percentage": 68.81, "elapsed_time": "8:14:41", "remaining_time": "3:44:15"}
{"current_steps": 2260, "total_steps": 3270, "loss": 0.0077, "lr": 2.6352237615827636e-05, "epoch": 3.4530175706646293, "percentage": 69.11, "elapsed_time": "8:16:12", "remaining_time": "3:41:45"}
{"current_steps": 2270, "total_steps": 3270, "loss": 0.0129, "lr": 2.5883322946185777e-05, "epoch": 3.46829640947288, "percentage": 69.42, "elapsed_time": "8:17:40", "remaining_time": "3:39:14"}
{"current_steps": 2280, "total_steps": 3270, "loss": 0.0124, "lr": 2.5417156376751562e-05, "epoch": 3.483575248281131, "percentage": 69.72, "elapsed_time": "8:19:08", "remaining_time": "3:36:43"}
{"current_steps": 2290, "total_steps": 3270, "loss": 0.008, "lr": 2.4953791027299506e-05, "epoch": 3.498854087089381, "percentage": 70.03, "elapsed_time": "8:20:36", "remaining_time": "3:34:14"}
{"current_steps": 2300, "total_steps": 3270, "loss": 0.0114, "lr": 2.4493279698404493e-05, "epoch": 3.514132925897632, "percentage": 70.34, "elapsed_time": "8:22:04", "remaining_time": "3:31:44"}
{"current_steps": 2300, "total_steps": 3270, "eval_loss": 0.031200075522065163, "epoch": 3.514132925897632, "percentage": 70.34, "elapsed_time": "8:25:25", "remaining_time": "3:33:09"}
{"current_steps": 2310, "total_steps": 3270, "loss": 0.0107, "lr": 2.403567486542518e-05, "epoch": 3.5294117647058822, "percentage": 70.64, "elapsed_time": "8:26:56", "remaining_time": "3:30:40"}
{"current_steps": 2320, "total_steps": 3270, "loss": 0.0111, "lr": 2.3581028672524485e-05, "epoch": 3.544690603514133, "percentage": 70.95, "elapsed_time": "8:28:24", "remaining_time": "3:28:10"}
{"current_steps": 2330, "total_steps": 3270, "loss": 0.0088, "lr": 2.312939292672765e-05, "epoch": 3.5599694423223838, "percentage": 71.25, "elapsed_time": "8:29:52", "remaining_time": "3:25:42"}
{"current_steps": 2340, "total_steps": 3270, "loss": 0.0087, "lr": 2.268081909201885e-05, "epoch": 3.575248281130634, "percentage": 71.56, "elapsed_time": "8:31:20", "remaining_time": "3:23:13"}
{"current_steps": 2350, "total_steps": 3270, "loss": 0.015, "lr": 2.2235358283476936e-05, "epoch": 3.5905271199388844, "percentage": 71.87, "elapsed_time": "8:32:48", "remaining_time": "3:20:45"}
{"current_steps": 2350, "total_steps": 3270, "eval_loss": 0.031868599355220795, "epoch": 3.5905271199388844, "percentage": 71.87, "elapsed_time": "8:36:08", "remaining_time": "3:22:03"}
{"current_steps": 2360, "total_steps": 3270, "loss": 0.0135, "lr": 2.179306126145075e-05, "epoch": 3.605805958747135, "percentage": 72.17, "elapsed_time": "8:37:39", "remaining_time": "3:19:36"}
{"current_steps": 2370, "total_steps": 3270, "loss": 0.0129, "lr": 2.1353978425775008e-05, "epoch": 3.621084797555386, "percentage": 72.48, "elapsed_time": "8:39:07", "remaining_time": "3:17:08"}
{"current_steps": 2380, "total_steps": 3270, "loss": 0.0101, "lr": 2.091815981002731e-05, "epoch": 3.6363636363636362, "percentage": 72.78, "elapsed_time": "8:40:35", "remaining_time": "3:14:40"}
{"current_steps": 2390, "total_steps": 3270, "loss": 0.0141, "lr": 2.0485655075826667e-05, "epoch": 3.651642475171887, "percentage": 73.09, "elapsed_time": "8:42:02", "remaining_time": "3:12:13"}
{"current_steps": 2400, "total_steps": 3270, "loss": 0.0088, "lr": 2.0056513507174685e-05, "epoch": 3.6669213139801373, "percentage": 73.39, "elapsed_time": "8:43:30", "remaining_time": "3:09:46"}
{"current_steps": 2400, "total_steps": 3270, "eval_loss": 0.030020447447896004, "epoch": 3.6669213139801373, "percentage": 73.39, "elapsed_time": "8:46:50", "remaining_time": "3:10:58"}
{"current_steps": 2410, "total_steps": 3270, "loss": 0.0111, "lr": 1.963078400483953e-05, "epoch": 3.682200152788388, "percentage": 73.7, "elapsed_time": "8:48:21", "remaining_time": "3:08:32"}
{"current_steps": 2420, "total_steps": 3270, "loss": 0.0087, "lr": 1.9208515080783723e-05, "epoch": 3.697478991596639, "percentage": 74.01, "elapsed_time": "8:49:49", "remaining_time": "3:06:05"}
{"current_steps": 2430, "total_steps": 3270, "loss": 0.0084, "lr": 1.8789754852636245e-05, "epoch": 3.712757830404889, "percentage": 74.31, "elapsed_time": "8:51:16", "remaining_time": "3:03:39"}
{"current_steps": 2440, "total_steps": 3270, "loss": 0.0173, "lr": 1.837455103820942e-05, "epoch": 3.72803666921314, "percentage": 74.62, "elapsed_time": "8:52:44", "remaining_time": "3:01:13"}
{"current_steps": 2450, "total_steps": 3270, "loss": 0.0068, "lr": 1.7962950950061502e-05, "epoch": 3.7433155080213902, "percentage": 74.92, "elapsed_time": "8:54:12", "remaining_time": "2:58:47"}
{"current_steps": 2450, "total_steps": 3270, "eval_loss": 0.03097730502486229, "epoch": 3.7433155080213902, "percentage": 74.92, "elapsed_time": "8:57:31", "remaining_time": "2:59:54"}
{"current_steps": 2460, "total_steps": 3270, "loss": 0.0103, "lr": 1.7555001490105488e-05, "epoch": 3.758594346829641, "percentage": 75.23, "elapsed_time": "8:59:01", "remaining_time": "2:57:29"}
{"current_steps": 2470, "total_steps": 3270, "loss": 0.0123, "lr": 1.7150749144264462e-05, "epoch": 3.7738731856378918, "percentage": 75.54, "elapsed_time": "9:00:29", "remaining_time": "2:55:03"}
{"current_steps": 2480, "total_steps": 3270, "loss": 0.0097, "lr": 1.6750239977174682e-05, "epoch": 3.789152024446142, "percentage": 75.84, "elapsed_time": "9:01:57", "remaining_time": "2:52:38"}
{"current_steps": 2490, "total_steps": 3270, "loss": 0.0145, "lr": 1.6353519626936397e-05, "epoch": 3.8044308632543924, "percentage": 76.15, "elapsed_time": "9:03:24", "remaining_time": "2:50:13"}
{"current_steps": 2500, "total_steps": 3270, "loss": 0.0098, "lr": 1.596063329991341e-05, "epoch": 3.819709702062643, "percentage": 76.45, "elapsed_time": "9:04:52", "remaining_time": "2:47:49"}
{"current_steps": 2500, "total_steps": 3270, "eval_loss": 0.02996741607785225, "epoch": 3.819709702062643, "percentage": 76.45, "elapsed_time": "9:08:11", "remaining_time": "2:48:50"}
{"current_steps": 2510, "total_steps": 3270, "loss": 0.0081, "lr": 1.5571625765581832e-05, "epoch": 3.834988540870894, "percentage": 76.76, "elapsed_time": "9:09:42", "remaining_time": "2:46:26"}
{"current_steps": 2520, "total_steps": 3270, "loss": 0.012, "lr": 1.5186541351428545e-05, "epoch": 3.8502673796791442, "percentage": 77.06, "elapsed_time": "9:11:09", "remaining_time": "2:44:02"}
{"current_steps": 2530, "total_steps": 3270, "loss": 0.0138, "lr": 1.4805423937900087e-05, "epoch": 3.865546218487395, "percentage": 77.37, "elapsed_time": "9:12:36", "remaining_time": "2:41:38"}
{"current_steps": 2540, "total_steps": 3270, "loss": 0.0095, "lr": 1.4428316953402526e-05, "epoch": 3.8808250572956453, "percentage": 77.68, "elapsed_time": "9:14:04", "remaining_time": "2:39:14"}
{"current_steps": 2550, "total_steps": 3270, "loss": 0.0088, "lr": 1.4055263369352672e-05, "epoch": 3.896103896103896, "percentage": 77.98, "elapsed_time": "9:15:31", "remaining_time": "2:36:51"}
{"current_steps": 2550, "total_steps": 3270, "eval_loss": 0.02977598085999489, "epoch": 3.896103896103896, "percentage": 77.98, "elapsed_time": "9:18:50", "remaining_time": "2:37:47"}
{"current_steps": 2560, "total_steps": 3270, "loss": 0.0111, "lr": 1.3686305695281559e-05, "epoch": 3.911382734912147, "percentage": 78.29, "elapsed_time": "9:20:21", "remaining_time": "2:35:24"}
{"current_steps": 2570, "total_steps": 3270, "loss": 0.0083, "lr": 1.3321485973990494e-05, "epoch": 3.926661573720397, "percentage": 78.59, "elapsed_time": "9:21:49", "remaining_time": "2:33:01"}
{"current_steps": 2580, "total_steps": 3270, "loss": 0.0164, "lr": 1.2960845776760156e-05, "epoch": 3.941940412528648, "percentage": 78.9, "elapsed_time": "9:23:17", "remaining_time": "2:30:38"}
{"current_steps": 2590, "total_steps": 3270, "loss": 0.0089, "lr": 1.2604426198613688e-05, "epoch": 3.9572192513368982, "percentage": 79.2, "elapsed_time": "9:24:44", "remaining_time": "2:28:16"}
{"current_steps": 2600, "total_steps": 3270, "loss": 0.0081, "lr": 1.2252267853633798e-05, "epoch": 3.972498090145149, "percentage": 79.51, "elapsed_time": "9:26:11", "remaining_time": "2:25:54"}
{"current_steps": 2600, "total_steps": 3270, "eval_loss": 0.030624018982052803, "epoch": 3.972498090145149, "percentage": 79.51, "elapsed_time": "9:29:31", "remaining_time": "2:26:45"}
{"current_steps": 2610, "total_steps": 3270, "loss": 0.0132, "lr": 1.1904410870334803e-05, "epoch": 3.9877769289533997, "percentage": 79.82, "elapsed_time": "9:31:02", "remaining_time": "2:24:23"}
{"current_steps": 2620, "total_steps": 3270, "loss": 0.011, "lr": 1.1560894887090052e-05, "epoch": 4.0030557677616505, "percentage": 80.12, "elapsed_time": "9:32:29", "remaining_time": "2:22:01"}
{"current_steps": 2630, "total_steps": 3270, "loss": 0.0084, "lr": 1.1221759047615004e-05, "epoch": 4.0183346065699, "percentage": 80.43, "elapsed_time": "9:33:56", "remaining_time": "2:19:40"}
{"current_steps": 2640, "total_steps": 3270, "loss": 0.0041, "lr": 1.0887041996506859e-05, "epoch": 4.033613445378151, "percentage": 80.73, "elapsed_time": "9:35:23", "remaining_time": "2:17:18"}
{"current_steps": 2650, "total_steps": 3270, "loss": 0.0052, "lr": 1.0556781874841027e-05, "epoch": 4.048892284186402, "percentage": 81.04, "elapsed_time": "9:36:51", "remaining_time": "2:14:57"}
{"current_steps": 2650, "total_steps": 3270, "eval_loss": 0.031373970210552216, "epoch": 4.048892284186402, "percentage": 81.04, "elapsed_time": "9:40:11", "remaining_time": "2:15:44"}
{"current_steps": 2660, "total_steps": 3270, "loss": 0.0042, "lr": 1.0231016315824875e-05, "epoch": 4.064171122994653, "percentage": 81.35, "elapsed_time": "9:41:41", "remaining_time": "2:13:23"}
{"current_steps": 2670, "total_steps": 3270, "loss": 0.0063, "lr": 9.909782440509491e-06, "epoch": 4.0794499618029025, "percentage": 81.65, "elapsed_time": "9:43:08", "remaining_time": "2:11:02"}
{"current_steps": 2680, "total_steps": 3270, "loss": 0.0076, "lr": 9.593116853559648e-06, "epoch": 4.094728800611153, "percentage": 81.96, "elapsed_time": "9:44:35", "remaining_time": "2:08:41"}
{"current_steps": 2690, "total_steps": 3270, "loss": 0.009, "lr": 9.281055639082747e-06, "epoch": 4.110007639419404, "percentage": 82.26, "elapsed_time": "9:46:03", "remaining_time": "2:06:21"}
{"current_steps": 2700, "total_steps": 3270, "loss": 0.0076, "lr": 8.973634356517063e-06, "epoch": 4.125286478227655, "percentage": 82.57, "elapsed_time": "9:47:31", "remaining_time": "2:04:01"}
{"current_steps": 2700, "total_steps": 3270, "eval_loss": 0.03259371221065521, "epoch": 4.125286478227655, "percentage": 82.57, "elapsed_time": "9:50:50", "remaining_time": "2:04:44"}
{"current_steps": 2710, "total_steps": 3270, "loss": 0.0056, "lr": 8.670888036579639e-06, "epoch": 4.140565317035906, "percentage": 82.87, "elapsed_time": "9:52:21", "remaining_time": "2:02:24"}
{"current_steps": 2720, "total_steps": 3270, "loss": 0.0064, "lr": 8.372851177274604e-06, "epoch": 4.1558441558441555, "percentage": 83.18, "elapsed_time": "9:53:48", "remaining_time": "2:00:04"}
{"current_steps": 2730, "total_steps": 3270, "loss": 0.0063, "lr": 8.079557739962128e-06, "epoch": 4.171122994652406, "percentage": 83.49, "elapsed_time": "9:55:16", "remaining_time": "1:57:44"}
{"current_steps": 2740, "total_steps": 3270, "loss": 0.0065, "lr": 7.791041145488454e-06, "epoch": 4.186401833460657, "percentage": 83.79, "elapsed_time": "9:56:44", "remaining_time": "1:55:25"}
{"current_steps": 2750, "total_steps": 3270, "loss": 0.0091, "lr": 7.507334270377619e-06, "epoch": 4.201680672268908, "percentage": 84.1, "elapsed_time": "9:58:12", "remaining_time": "1:53:06"}
{"current_steps": 2750, "total_steps": 3270, "eval_loss": 0.03307883441448212, "epoch": 4.201680672268908, "percentage": 84.1, "elapsed_time": "10:01:31", "remaining_time": "1:53:44"}
{"current_steps": 2760, "total_steps": 3270, "loss": 0.0072, "lr": 7.228469443085206e-06, "epoch": 4.2169595110771585, "percentage": 84.4, "elapsed_time": "10:03:01", "remaining_time": "1:51:25"}
{"current_steps": 2770, "total_steps": 3270, "loss": 0.0079, "lr": 6.954478440314427e-06, "epoch": 4.232238349885408, "percentage": 84.71, "elapsed_time": "10:04:29", "remaining_time": "1:49:06"}
{"current_steps": 2780, "total_steps": 3270, "loss": 0.0029, "lr": 6.685392483395259e-06, "epoch": 4.247517188693659, "percentage": 85.02, "elapsed_time": "10:05:56", "remaining_time": "1:46:48"}
{"current_steps": 2790, "total_steps": 3270, "loss": 0.0055, "lr": 6.421242234726682e-06, "epoch": 4.26279602750191, "percentage": 85.32, "elapsed_time": "10:07:24", "remaining_time": "1:44:30"}
{"current_steps": 2800, "total_steps": 3270, "loss": 0.0045, "lr": 6.1620577942827166e-06, "epoch": 4.278074866310161, "percentage": 85.63, "elapsed_time": "10:08:52", "remaining_time": "1:42:12"}
{"current_steps": 2800, "total_steps": 3270, "eval_loss": 0.0341590940952301, "epoch": 4.278074866310161, "percentage": 85.63, "elapsed_time": "10:12:11", "remaining_time": "1:42:45"}
{"current_steps": 2810, "total_steps": 3270, "loss": 0.0058, "lr": 5.907868696182584e-06, "epoch": 4.293353705118411, "percentage": 85.93, "elapsed_time": "10:13:42", "remaining_time": "1:40:27"}
{"current_steps": 2820, "total_steps": 3270, "loss": 0.0078, "lr": 5.658703905325186e-06, "epoch": 4.308632543926661, "percentage": 86.24, "elapsed_time": "10:15:10", "remaining_time": "1:38:09"}
{"current_steps": 2830, "total_steps": 3270, "loss": 0.0077, "lr": 5.414591814088627e-06, "epoch": 4.323911382734912, "percentage": 86.54, "elapsed_time": "10:16:37", "remaining_time": "1:35:52"}
{"current_steps": 2840, "total_steps": 3270, "loss": 0.0059, "lr": 5.17556023909489e-06, "epoch": 4.339190221543163, "percentage": 86.85, "elapsed_time": "10:18:04", "remaining_time": "1:33:34"}
{"current_steps": 2850, "total_steps": 3270, "loss": 0.0047, "lr": 4.941636418040058e-06, "epoch": 4.354469060351414, "percentage": 87.16, "elapsed_time": "10:19:32", "remaining_time": "1:31:18"}
{"current_steps": 2850, "total_steps": 3270, "eval_loss": 0.034740038216114044, "epoch": 4.354469060351414, "percentage": 87.16, "elapsed_time": "10:22:51", "remaining_time": "1:31:47"}
{"current_steps": 2860, "total_steps": 3270, "loss": 0.0041, "lr": 4.7128470065906925e-06, "epoch": 4.369747899159664, "percentage": 87.46, "elapsed_time": "10:24:22", "remaining_time": "1:29:30"}
{"current_steps": 2870, "total_steps": 3270, "loss": 0.0039, "lr": 4.4892180753462744e-06, "epoch": 4.385026737967914, "percentage": 87.77, "elapsed_time": "10:25:49", "remaining_time": "1:27:13"}
{"current_steps": 2880, "total_steps": 3270, "loss": 0.004, "lr": 4.270775106868586e-06, "epoch": 4.400305576776165, "percentage": 88.07, "elapsed_time": "10:27:16", "remaining_time": "1:24:56"}
{"current_steps": 2890, "total_steps": 3270, "loss": 0.0057, "lr": 4.057542992777868e-06, "epoch": 4.415584415584416, "percentage": 88.38, "elapsed_time": "10:28:44", "remaining_time": "1:22:40"}
{"current_steps": 2900, "total_steps": 3270, "loss": 0.0047, "lr": 3.849546030916473e-06, "epoch": 4.4308632543926665, "percentage": 88.69, "elapsed_time": "10:30:11", "remaining_time": "1:20:24"}
{"current_steps": 2900, "total_steps": 3270, "eval_loss": 0.03577398136258125, "epoch": 4.4308632543926665, "percentage": 88.69, "elapsed_time": "10:33:30", "remaining_time": "1:20:49"}
{"current_steps": 2910, "total_steps": 3270, "loss": 0.004, "lr": 3.646807922580098e-06, "epoch": 4.446142093200916, "percentage": 88.99, "elapsed_time": "10:35:01", "remaining_time": "1:18:33"}
{"current_steps": 2920, "total_steps": 3270, "loss": 0.0082, "lr": 3.4493517698170164e-06, "epoch": 4.461420932009167, "percentage": 89.3, "elapsed_time": "10:36:29", "remaining_time": "1:16:17"}
{"current_steps": 2930, "total_steps": 3270, "loss": 0.0058, "lr": 3.2572000727956186e-06, "epoch": 4.476699770817418, "percentage": 89.6, "elapsed_time": "10:37:56", "remaining_time": "1:14:01"}
{"current_steps": 2940, "total_steps": 3270, "loss": 0.0043, "lr": 3.070374727240466e-06, "epoch": 4.491978609625669, "percentage": 89.91, "elapsed_time": "10:39:23", "remaining_time": "1:11:46"}
{"current_steps": 2950, "total_steps": 3270, "loss": 0.005, "lr": 2.8888970219373314e-06, "epoch": 4.507257448433919, "percentage": 90.21, "elapsed_time": "10:40:50", "remaining_time": "1:09:30"}
{"current_steps": 2950, "total_steps": 3270, "eval_loss": 0.03592822700738907, "epoch": 4.507257448433919, "percentage": 90.21, "elapsed_time": "10:44:10", "remaining_time": "1:09:52"}
{"current_steps": 2960, "total_steps": 3270, "loss": 0.0031, "lr": 2.7127876363072736e-06, "epoch": 4.522536287242169, "percentage": 90.52, "elapsed_time": "10:45:40", "remaining_time": "1:07:37"}
{"current_steps": 2970, "total_steps": 3270, "loss": 0.0057, "lr": 2.54206663805025e-06, "epoch": 4.53781512605042, "percentage": 90.83, "elapsed_time": "10:47:08", "remaining_time": "1:05:22"}
{"current_steps": 2980, "total_steps": 3270, "loss": 0.0026, "lr": 2.3767534808584125e-06, "epoch": 4.553093964858671, "percentage": 91.13, "elapsed_time": "10:48:35", "remaining_time": "1:03:07"}
{"current_steps": 2990, "total_steps": 3270, "loss": 0.0078, "lr": 2.2168670021993075e-06, "epoch": 4.5683728036669216, "percentage": 91.44, "elapsed_time": "10:50:02", "remaining_time": "1:00:52"}
{"current_steps": 3000, "total_steps": 3270, "loss": 0.0049, "lr": 2.0624254211693894e-06, "epoch": 4.583651642475171, "percentage": 91.74, "elapsed_time": "10:51:30", "remaining_time": "0:58:38"}
{"current_steps": 3000, "total_steps": 3270, "eval_loss": 0.0363006666302681, "epoch": 4.583651642475171, "percentage": 91.74, "elapsed_time": "10:54:49", "remaining_time": "0:58:56"}
{"current_steps": 3010, "total_steps": 3270, "loss": 0.007, "lr": 1.9134463364179177e-06, "epoch": 4.598930481283422, "percentage": 92.05, "elapsed_time": "10:56:19", "remaining_time": "0:56:41"}
{"current_steps": 3020, "total_steps": 3270, "loss": 0.0073, "lr": 1.7699467241416024e-06, "epoch": 4.614209320091673, "percentage": 92.35, "elapsed_time": "10:57:46", "remaining_time": "0:54:27"}
{"current_steps": 3030, "total_steps": 3270, "loss": 0.0045, "lr": 1.6319429361501714e-06, "epoch": 4.629488158899924, "percentage": 92.66, "elapsed_time": "10:59:13", "remaining_time": "0:52:12"}
{"current_steps": 3040, "total_steps": 3270, "loss": 0.0019, "lr": 1.4994506980030577e-06, "epoch": 4.6447669977081745, "percentage": 92.97, "elapsed_time": "11:00:40", "remaining_time": "0:49:59"}
{"current_steps": 3050, "total_steps": 3270, "loss": 0.0039, "lr": 1.3724851072174917e-06, "epoch": 4.660045836516424, "percentage": 93.27, "elapsed_time": "11:02:07", "remaining_time": "0:47:45"}
{"current_steps": 3050, "total_steps": 3270, "eval_loss": 0.036286067217588425, "epoch": 4.660045836516424, "percentage": 93.27, "elapsed_time": "11:05:26", "remaining_time": "0:47:59"}
{"current_steps": 3060, "total_steps": 3270, "loss": 0.0107, "lr": 1.251060631548112e-06, "epoch": 4.675324675324675, "percentage": 93.58, "elapsed_time": "11:06:56", "remaining_time": "0:45:46"}
{"current_steps": 3070, "total_steps": 3270, "loss": 0.0029, "lr": 1.135191107338368e-06, "epoch": 4.690603514132926, "percentage": 93.88, "elapsed_time": "11:08:23", "remaining_time": "0:43:32"}
{"current_steps": 3080, "total_steps": 3270, "loss": 0.0054, "lr": 1.0248897379438904e-06, "epoch": 4.705882352941177, "percentage": 94.19, "elapsed_time": "11:09:50", "remaining_time": "0:41:19"}
{"current_steps": 3090, "total_steps": 3270, "loss": 0.0052, "lr": 9.201690922279405e-07, "epoch": 4.721161191749427, "percentage": 94.5, "elapsed_time": "11:11:17", "remaining_time": "0:39:06"}
{"current_steps": 3100, "total_steps": 3270, "loss": 0.0062, "lr": 8.210411031291776e-07, "epoch": 4.736440030557677, "percentage": 94.8, "elapsed_time": "11:12:45", "remaining_time": "0:36:53"}
{"current_steps": 3100, "total_steps": 3270, "eval_loss": 0.03661744296550751, "epoch": 4.736440030557677, "percentage": 94.8, "elapsed_time": "11:16:04", "remaining_time": "0:37:04"}
{"current_steps": 3110, "total_steps": 3270, "loss": 0.0061, "lr": 7.275170663019415e-07, "epoch": 4.751718869365928, "percentage": 95.11, "elapsed_time": "11:17:34", "remaining_time": "0:34:51"}
{"current_steps": 3120, "total_steps": 3270, "loss": 0.0043, "lr": 6.396076388290484e-07, "epoch": 4.766997708174179, "percentage": 95.41, "elapsed_time": "11:19:01", "remaining_time": "0:32:38"}
{"current_steps": 3130, "total_steps": 3270, "loss": 0.0054, "lr": 5.573228380074736e-07, "epoch": 4.7822765469824295, "percentage": 95.72, "elapsed_time": "11:20:29", "remaining_time": "0:30:26"}
{"current_steps": 3140, "total_steps": 3270, "loss": 0.0031, "lr": 4.806720402068477e-07, "epoch": 4.79755538579068, "percentage": 96.02, "elapsed_time": "11:21:56", "remaining_time": "0:28:13"}
{"current_steps": 3150, "total_steps": 3270, "loss": 0.0054, "lr": 4.0966397980100604e-07, "epoch": 4.81283422459893, "percentage": 96.33, "elapsed_time": "11:23:23", "remaining_time": "0:26:02"}
{"current_steps": 3150, "total_steps": 3270, "eval_loss": 0.03663839399814606, "epoch": 4.81283422459893, "percentage": 96.33, "elapsed_time": "11:26:42", "remaining_time": "0:26:09"}
{"current_steps": 3160, "total_steps": 3270, "loss": 0.0043, "lr": 3.4430674817274575e-07, "epoch": 4.828113063407181, "percentage": 96.64, "elapsed_time": "11:28:12", "remaining_time": "0:23:57"}
{"current_steps": 3170, "total_steps": 3270, "loss": 0.0071, "lr": 2.8460779279176896e-07, "epoch": 4.843391902215432, "percentage": 96.94, "elapsed_time": "11:29:39", "remaining_time": "0:21:45"}
{"current_steps": 3180, "total_steps": 3270, "loss": 0.0035, "lr": 2.3057391636606696e-07, "epoch": 4.8586707410236825, "percentage": 97.25, "elapsed_time": "11:31:06", "remaining_time": "0:19:33"}
{"current_steps": 3190, "total_steps": 3270, "loss": 0.0078, "lr": 1.8221127606674605e-07, "epoch": 4.873949579831933, "percentage": 97.55, "elapsed_time": "11:32:33", "remaining_time": "0:17:22"}
{"current_steps": 3200, "total_steps": 3270, "loss": 0.0041, "lr": 1.3952538282639982e-07, "epoch": 4.889228418640183, "percentage": 97.86, "elapsed_time": "11:34:00", "remaining_time": "0:15:10"}
{"current_steps": 3200, "total_steps": 3270, "eval_loss": 0.03660115599632263, "epoch": 4.889228418640183, "percentage": 97.86, "elapsed_time": "11:37:19", "remaining_time": "0:15:15"}
{"current_steps": 3210, "total_steps": 3270, "loss": 0.0048, "lr": 1.025211007111615e-07, "epoch": 4.904507257448434, "percentage": 98.17, "elapsed_time": "11:38:49", "remaining_time": "0:13:03"}
{"current_steps": 3220, "total_steps": 3270, "loss": 0.0023, "lr": 7.120264636643615e-08, "epoch": 4.919786096256685, "percentage": 98.47, "elapsed_time": "11:40:16", "remaining_time": "0:10:52"}
{"current_steps": 3230, "total_steps": 3270, "loss": 0.006, "lr": 4.5573588536407254e-08, "epoch": 4.935064935064935, "percentage": 98.78, "elapsed_time": "11:41:43", "remaining_time": "0:08:41"}
{"current_steps": 3240, "total_steps": 3270, "loss": 0.0094, "lr": 2.5636847657367623e-08, "epoch": 4.950343773873186, "percentage": 99.08, "elapsed_time": "11:43:10", "remaining_time": "0:06:30"}
{"current_steps": 3250, "total_steps": 3270, "loss": 0.0047, "lr": 1.1394695524963306e-08, "epoch": 4.965622612681436, "percentage": 99.39, "elapsed_time": "11:44:37", "remaining_time": "0:04:20"}
{"current_steps": 3250, "total_steps": 3270, "eval_loss": 0.03658132627606392, "epoch": 4.965622612681436, "percentage": 99.39, "elapsed_time": "11:47:56", "remaining_time": "0:04:21"}
{"current_steps": 3260, "total_steps": 3270, "loss": 0.0064, "lr": 2.8487550352951363e-09, "epoch": 4.980901451489687, "percentage": 99.69, "elapsed_time": "11:49:26", "remaining_time": "0:02:10"}
{"current_steps": 3270, "total_steps": 3270, "loss": 0.0078, "lr": 0.0, "epoch": 4.9961802902979375, "percentage": 100.0, "elapsed_time": "11:50:53", "remaining_time": "0:00:00"}
{"current_steps": 3270, "total_steps": 3270, "epoch": 4.9961802902979375, "percentage": 100.0, "elapsed_time": "11:50:56", "remaining_time": "0:00:00"}