{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8, "eval_steps": 500, "global_step": 80000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "loss_action": 1.4719703197479248, "loss_total": 1.4719703197479248, "step": 0 }, { "grad_norm": 0.4109882414340973, "learning_rate": 1.8e-07, "loss": 1.5018, "step": 10 }, { "loss_action": 1.5427956581115723, "loss_total": 1.5427956581115723, "step": 10 }, { "grad_norm": 0.39324623346328735, "learning_rate": 3.8e-07, "loss": 1.4963, "step": 20 }, { "loss_action": 1.504586935043335, "loss_total": 1.504586935043335, "step": 20 }, { "grad_norm": 0.4163825213909149, "learning_rate": 5.8e-07, "loss": 1.4966, "step": 30 }, { "loss_action": 1.4898337125778198, "loss_total": 1.4898337125778198, "step": 30 }, { "grad_norm": 0.4501744210720062, "learning_rate": 7.8e-07, "loss": 1.5105, "step": 40 }, { "loss_action": 1.532029628753662, "loss_total": 1.532029628753662, "step": 40 }, { "grad_norm": 0.43652552366256714, "learning_rate": 9.8e-07, "loss": 1.5015, "step": 50 }, { "loss_action": 1.5143605470657349, "loss_total": 1.5143605470657349, "step": 50 }, { "grad_norm": 0.5205863118171692, "learning_rate": 1.18e-06, "loss": 1.4794, "step": 60 }, { "loss_action": 1.4363876581192017, "loss_total": 1.4363876581192017, "step": 60 }, { "grad_norm": 1.1011013984680176, "learning_rate": 1.3800000000000001e-06, "loss": 1.4286, "step": 70 }, { "loss_action": 1.4478446245193481, "loss_total": 1.4478446245193481, "step": 70 }, { "grad_norm": 0.4099116325378418, "learning_rate": 1.5800000000000003e-06, "loss": 1.3922, "step": 80 }, { "loss_action": 1.356630563735962, "loss_total": 1.356630563735962, "step": 80 }, { "grad_norm": 0.43503081798553467, "learning_rate": 1.7800000000000001e-06, "loss": 1.3863, "step": 90 }, { "loss_action": 1.3819196224212646, "loss_total": 1.3819196224212646, "step": 90 }, { "grad_norm": 0.39009082317352295, "learning_rate": 1.98e-06, "loss": 1.3792, "step": 100 }, { "loss_action": 1.3160806894302368, "loss_total": 1.3160806894302368, "step": 100 }, { "grad_norm": 1.2284878492355347, "learning_rate": 2.1800000000000003e-06, "loss": 1.3792, "step": 110 }, { "loss_action": 1.4328564405441284, "loss_total": 1.4328564405441284, "step": 110 }, { "grad_norm": 0.6489635705947876, "learning_rate": 2.38e-06, "loss": 1.373, "step": 120 }, { "loss_action": 1.328627109527588, "loss_total": 1.328627109527588, "step": 120 }, { "grad_norm": 1.312942624092102, "learning_rate": 2.5800000000000003e-06, "loss": 1.3871, "step": 130 }, { "loss_action": 1.390194058418274, "loss_total": 1.390194058418274, "step": 130 }, { "grad_norm": 1.0520895719528198, "learning_rate": 2.78e-06, "loss": 1.3209, "step": 140 }, { "loss_action": 1.3274849653244019, "loss_total": 1.3274849653244019, "step": 140 }, { "grad_norm": 0.874740481376648, "learning_rate": 2.9800000000000003e-06, "loss": 1.3241, "step": 150 }, { "loss_action": 1.3819314241409302, "loss_total": 1.3819314241409302, "step": 150 }, { "grad_norm": 0.7428416609764099, "learning_rate": 3.1800000000000005e-06, "loss": 1.3038, "step": 160 }, { "loss_action": 1.3200007677078247, "loss_total": 1.3200007677078247, "step": 160 }, { "grad_norm": 1.614477276802063, "learning_rate": 3.38e-06, "loss": 1.3188, "step": 170 }, { "loss_action": 1.2817492485046387, "loss_total": 1.2817492485046387, "step": 170 }, { "grad_norm": 1.669776201248169, "learning_rate": 3.58e-06, "loss": 1.2603, "step": 180 }, { "loss_action": 1.2137112617492676, "loss_total": 1.2137112617492676, "step": 180 }, { "grad_norm": 2.380039691925049, "learning_rate": 3.7800000000000002e-06, "loss": 1.2456, "step": 190 }, { "loss_action": 1.2437924146652222, "loss_total": 1.2437924146652222, "step": 190 }, { "grad_norm": 2.3696460723876953, "learning_rate": 3.98e-06, "loss": 1.225, "step": 200 }, { "loss_action": 1.1890586614608765, "loss_total": 1.1890586614608765, "step": 200 }, { "grad_norm": 1.6676667928695679, "learning_rate": 4.18e-06, "loss": 1.1946, "step": 210 }, { "loss_action": 1.1782736778259277, "loss_total": 1.1782736778259277, "step": 210 }, { "grad_norm": 0.6343235969543457, "learning_rate": 4.38e-06, "loss": 1.1649, "step": 220 }, { "loss_action": 1.1531782150268555, "loss_total": 1.1531782150268555, "step": 220 }, { "grad_norm": 1.7340364456176758, "learning_rate": 4.58e-06, "loss": 1.1806, "step": 230 }, { "loss_action": 1.1499565839767456, "loss_total": 1.1499565839767456, "step": 230 }, { "grad_norm": 2.7202024459838867, "learning_rate": 4.780000000000001e-06, "loss": 1.1509, "step": 240 }, { "loss_action": 1.1503266096115112, "loss_total": 1.1503266096115112, "step": 240 }, { "grad_norm": 3.5487890243530273, "learning_rate": 4.98e-06, "loss": 1.1317, "step": 250 }, { "loss_action": 1.1529513597488403, "loss_total": 1.1529513597488403, "step": 250 }, { "grad_norm": 0.8592603206634521, "learning_rate": 5.18e-06, "loss": 1.1221, "step": 260 }, { "loss_action": 1.1342618465423584, "loss_total": 1.1342618465423584, "step": 260 }, { "grad_norm": 1.236278772354126, "learning_rate": 5.38e-06, "loss": 1.1195, "step": 270 }, { "loss_action": 1.1048569679260254, "loss_total": 1.1048569679260254, "step": 270 }, { "grad_norm": 1.9107675552368164, "learning_rate": 5.580000000000001e-06, "loss": 1.1043, "step": 280 }, { "loss_action": 1.1156140565872192, "loss_total": 1.1156140565872192, "step": 280 }, { "grad_norm": 2.4258151054382324, "learning_rate": 5.78e-06, "loss": 1.1062, "step": 290 }, { "loss_action": 1.0901376008987427, "loss_total": 1.0901376008987427, "step": 290 }, { "grad_norm": 5.3845038414001465, "learning_rate": 5.98e-06, "loss": 1.1057, "step": 300 }, { "loss_action": 1.107596516609192, "loss_total": 1.107596516609192, "step": 300 }, { "grad_norm": 1.4296518564224243, "learning_rate": 6.18e-06, "loss": 1.1026, "step": 310 }, { "loss_action": 1.1113231182098389, "loss_total": 1.1113231182098389, "step": 310 }, { "grad_norm": 3.8086071014404297, "learning_rate": 6.38e-06, "loss": 1.0896, "step": 320 }, { "loss_action": 1.085884690284729, "loss_total": 1.085884690284729, "step": 320 }, { "grad_norm": 2.531043767929077, "learning_rate": 6.58e-06, "loss": 1.1175, "step": 330 }, { "loss_action": 1.1307865381240845, "loss_total": 1.1307865381240845, "step": 330 }, { "grad_norm": 2.256495714187622, "learning_rate": 6.78e-06, "loss": 1.1089, "step": 340 }, { "loss_action": 1.2656317949295044, "loss_total": 1.2656317949295044, "step": 340 }, { "grad_norm": 2.333089828491211, "learning_rate": 6.98e-06, "loss": 1.1248, "step": 350 }, { "loss_action": 1.117535948753357, "loss_total": 1.117535948753357, "step": 350 }, { "grad_norm": 1.2974244356155396, "learning_rate": 7.180000000000001e-06, "loss": 1.0814, "step": 360 }, { "loss_action": 1.0744410753250122, "loss_total": 1.0744410753250122, "step": 360 }, { "grad_norm": 1.987302303314209, "learning_rate": 7.3800000000000005e-06, "loss": 1.0703, "step": 370 }, { "loss_action": 1.0704264640808105, "loss_total": 1.0704264640808105, "step": 370 }, { "grad_norm": 2.2571468353271484, "learning_rate": 7.580000000000001e-06, "loss": 1.0728, "step": 380 }, { "loss_action": 1.0590676069259644, "loss_total": 1.0590676069259644, "step": 380 }, { "grad_norm": 1.1306709051132202, "learning_rate": 7.78e-06, "loss": 1.0534, "step": 390 }, { "loss_action": 1.0367927551269531, "loss_total": 1.0367927551269531, "step": 390 }, { "grad_norm": 0.8710293769836426, "learning_rate": 7.98e-06, "loss": 1.0532, "step": 400 }, { "loss_action": 1.0346544981002808, "loss_total": 1.0346544981002808, "step": 400 }, { "grad_norm": 1.0157413482666016, "learning_rate": 8.18e-06, "loss": 1.0378, "step": 410 }, { "loss_action": 1.057373046875, "loss_total": 1.057373046875, "step": 410 }, { "grad_norm": 1.08717679977417, "learning_rate": 8.380000000000001e-06, "loss": 1.0408, "step": 420 }, { "loss_action": 1.0392578840255737, "loss_total": 1.0392578840255737, "step": 420 }, { "grad_norm": 1.9826409816741943, "learning_rate": 8.580000000000001e-06, "loss": 1.0432, "step": 430 }, { "loss_action": 1.0350645780563354, "loss_total": 1.0350645780563354, "step": 430 }, { "grad_norm": 0.6600489616394043, "learning_rate": 8.78e-06, "loss": 1.0295, "step": 440 }, { "loss_action": 1.0201817750930786, "loss_total": 1.0201817750930786, "step": 440 }, { "grad_norm": 0.8986703753471375, "learning_rate": 8.98e-06, "loss": 1.0233, "step": 450 }, { "loss_action": 1.0167165994644165, "loss_total": 1.0167165994644165, "step": 450 }, { "grad_norm": 0.9545632600784302, "learning_rate": 9.180000000000002e-06, "loss": 1.0232, "step": 460 }, { "loss_action": 1.0100070238113403, "loss_total": 1.0100070238113403, "step": 460 }, { "grad_norm": 0.6535515785217285, "learning_rate": 9.38e-06, "loss": 0.9996, "step": 470 }, { "loss_action": 0.9978578090667725, "loss_total": 0.9978578090667725, "step": 470 }, { "grad_norm": 0.6615709662437439, "learning_rate": 9.58e-06, "loss": 0.9871, "step": 480 }, { "loss_action": 0.9865769147872925, "loss_total": 0.9865769147872925, "step": 480 }, { "grad_norm": 0.8142436742782593, "learning_rate": 9.78e-06, "loss": 0.9687, "step": 490 }, { "loss_action": 0.9581699967384338, "loss_total": 0.9581699967384338, "step": 490 }, { "grad_norm": 1.1317726373672485, "learning_rate": 9.980000000000001e-06, "loss": 0.9583, "step": 500 }, { "loss_action": 0.9540553689002991, "loss_total": 0.9540553689002991, "step": 500 }, { "grad_norm": 0.9282472729682922, "learning_rate": 1.018e-05, "loss": 0.9366, "step": 510 }, { "loss_action": 0.9321423172950745, "loss_total": 0.9321423172950745, "step": 510 }, { "grad_norm": 0.7672775387763977, "learning_rate": 1.038e-05, "loss": 0.9152, "step": 520 }, { "loss_action": 0.9164221286773682, "loss_total": 0.9164221286773682, "step": 520 }, { "grad_norm": 2.4145050048828125, "learning_rate": 1.058e-05, "loss": 0.9048, "step": 530 }, { "loss_action": 0.9016859531402588, "loss_total": 0.9016859531402588, "step": 530 }, { "grad_norm": 1.2240113019943237, "learning_rate": 1.0780000000000002e-05, "loss": 0.8818, "step": 540 }, { "loss_action": 0.8510606288909912, "loss_total": 0.8510606288909912, "step": 540 }, { "grad_norm": 1.2735393047332764, "learning_rate": 1.098e-05, "loss": 0.8539, "step": 550 }, { "loss_action": 0.8284356594085693, "loss_total": 0.8284356594085693, "step": 550 }, { "grad_norm": 1.0217732191085815, "learning_rate": 1.118e-05, "loss": 0.8258, "step": 560 }, { "loss_action": 0.7989144325256348, "loss_total": 0.7989144325256348, "step": 560 }, { "grad_norm": 1.273232340812683, "learning_rate": 1.1380000000000001e-05, "loss": 0.7992, "step": 570 }, { "loss_action": 0.775649905204773, "loss_total": 0.775649905204773, "step": 570 }, { "grad_norm": 1.116767406463623, "learning_rate": 1.1580000000000001e-05, "loss": 0.784, "step": 580 }, { "loss_action": 0.7626177668571472, "loss_total": 0.7626177668571472, "step": 580 }, { "grad_norm": 1.1861213445663452, "learning_rate": 1.178e-05, "loss": 0.7579, "step": 590 }, { "loss_action": 0.7444540858268738, "loss_total": 0.7444540858268738, "step": 590 }, { "grad_norm": 1.3255103826522827, "learning_rate": 1.198e-05, "loss": 0.7363, "step": 600 }, { "loss_action": 0.7231761813163757, "loss_total": 0.7231761813163757, "step": 600 }, { "grad_norm": 1.5606333017349243, "learning_rate": 1.2180000000000002e-05, "loss": 0.7114, "step": 610 }, { "loss_action": 0.7117518782615662, "loss_total": 0.7117518782615662, "step": 610 }, { "grad_norm": 1.2315521240234375, "learning_rate": 1.238e-05, "loss": 0.7083, "step": 620 }, { "loss_action": 0.6777777075767517, "loss_total": 0.6777777075767517, "step": 620 }, { "grad_norm": 3.534264326095581, "learning_rate": 1.258e-05, "loss": 0.6834, "step": 630 }, { "loss_action": 0.6897846460342407, "loss_total": 0.6897846460342407, "step": 630 }, { "grad_norm": 1.0947914123535156, "learning_rate": 1.278e-05, "loss": 0.67, "step": 640 }, { "loss_action": 0.6453354358673096, "loss_total": 0.6453354358673096, "step": 640 }, { "grad_norm": 1.4565562009811401, "learning_rate": 1.2980000000000001e-05, "loss": 0.6448, "step": 650 }, { "loss_action": 0.6370096802711487, "loss_total": 0.6370096802711487, "step": 650 }, { "grad_norm": 1.6031367778778076, "learning_rate": 1.3180000000000001e-05, "loss": 0.6264, "step": 660 }, { "loss_action": 0.6282988786697388, "loss_total": 0.6282988786697388, "step": 660 }, { "grad_norm": 1.7804539203643799, "learning_rate": 1.338e-05, "loss": 0.6169, "step": 670 }, { "loss_action": 0.6210946440696716, "loss_total": 0.6210946440696716, "step": 670 }, { "grad_norm": 1.17171311378479, "learning_rate": 1.358e-05, "loss": 0.5955, "step": 680 }, { "loss_action": 0.5973937511444092, "loss_total": 0.5973937511444092, "step": 680 }, { "grad_norm": 1.5605578422546387, "learning_rate": 1.3780000000000002e-05, "loss": 0.57, "step": 690 }, { "loss_action": 0.5703452825546265, "loss_total": 0.5703452825546265, "step": 690 }, { "grad_norm": 1.9015531539916992, "learning_rate": 1.3980000000000002e-05, "loss": 0.5575, "step": 700 }, { "loss_action": 0.5451210737228394, "loss_total": 0.5451210737228394, "step": 700 }, { "grad_norm": 1.258121132850647, "learning_rate": 1.4180000000000001e-05, "loss": 0.5438, "step": 710 }, { "loss_action": 0.5201143622398376, "loss_total": 0.5201143622398376, "step": 710 }, { "grad_norm": 3.2380504608154297, "learning_rate": 1.4380000000000001e-05, "loss": 0.5259, "step": 720 }, { "loss_action": 0.5269573926925659, "loss_total": 0.5269573926925659, "step": 720 }, { "grad_norm": 1.90060293674469, "learning_rate": 1.4580000000000003e-05, "loss": 0.5278, "step": 730 }, { "loss_action": 0.5110713243484497, "loss_total": 0.5110713243484497, "step": 730 }, { "grad_norm": 1.787921667098999, "learning_rate": 1.4779999999999999e-05, "loss": 0.5006, "step": 740 }, { "loss_action": 0.5019059777259827, "loss_total": 0.5019059777259827, "step": 740 }, { "grad_norm": 1.50544273853302, "learning_rate": 1.4979999999999999e-05, "loss": 0.4875, "step": 750 }, { "loss_action": 0.508712649345398, "loss_total": 0.508712649345398, "step": 750 }, { "grad_norm": 2.237514019012451, "learning_rate": 1.518e-05, "loss": 0.4847, "step": 760 }, { "loss_action": 0.45760464668273926, "loss_total": 0.45760464668273926, "step": 760 }, { "grad_norm": 1.5537340641021729, "learning_rate": 1.538e-05, "loss": 0.4642, "step": 770 }, { "loss_action": 0.43948590755462646, "loss_total": 0.43948590755462646, "step": 770 }, { "grad_norm": 1.3379859924316406, "learning_rate": 1.558e-05, "loss": 0.4445, "step": 780 }, { "loss_action": 0.4218965172767639, "loss_total": 0.4218965172767639, "step": 780 }, { "grad_norm": 1.611452341079712, "learning_rate": 1.578e-05, "loss": 0.4355, "step": 790 }, { "loss_action": 0.41421395540237427, "loss_total": 0.41421395540237427, "step": 790 }, { "grad_norm": 1.4581588506698608, "learning_rate": 1.598e-05, "loss": 0.424, "step": 800 }, { "loss_action": 0.41843244433403015, "loss_total": 0.41843244433403015, "step": 800 }, { "grad_norm": 2.3191895484924316, "learning_rate": 1.618e-05, "loss": 0.4051, "step": 810 }, { "loss_action": 0.4028083086013794, "loss_total": 0.4028083086013794, "step": 810 }, { "grad_norm": 2.511782169342041, "learning_rate": 1.6380000000000002e-05, "loss": 0.4038, "step": 820 }, { "loss_action": 0.42594993114471436, "loss_total": 0.42594993114471436, "step": 820 }, { "grad_norm": 1.4664446115493774, "learning_rate": 1.658e-05, "loss": 0.3849, "step": 830 }, { "loss_action": 0.36868491768836975, "loss_total": 0.36868491768836975, "step": 830 }, { "grad_norm": 1.608067274093628, "learning_rate": 1.6780000000000002e-05, "loss": 0.3776, "step": 840 }, { "loss_action": 0.38852861523628235, "loss_total": 0.38852861523628235, "step": 840 }, { "grad_norm": 1.837788701057434, "learning_rate": 1.698e-05, "loss": 0.3805, "step": 850 }, { "loss_action": 0.43614742159843445, "loss_total": 0.43614742159843445, "step": 850 }, { "grad_norm": 2.9102394580841064, "learning_rate": 1.718e-05, "loss": 0.3866, "step": 860 }, { "loss_action": 0.35275882482528687, "loss_total": 0.35275882482528687, "step": 860 }, { "grad_norm": 1.7411389350891113, "learning_rate": 1.7380000000000003e-05, "loss": 0.3536, "step": 870 }, { "loss_action": 0.3498653173446655, "loss_total": 0.3498653173446655, "step": 870 }, { "grad_norm": 2.2242562770843506, "learning_rate": 1.758e-05, "loss": 0.3447, "step": 880 }, { "loss_action": 0.32884901762008667, "loss_total": 0.32884901762008667, "step": 880 }, { "grad_norm": 2.6692137718200684, "learning_rate": 1.7780000000000003e-05, "loss": 0.3373, "step": 890 }, { "loss_action": 0.3408646881580353, "loss_total": 0.3408646881580353, "step": 890 }, { "grad_norm": 1.5391954183578491, "learning_rate": 1.798e-05, "loss": 0.3304, "step": 900 }, { "loss_action": 0.31632518768310547, "loss_total": 0.31632518768310547, "step": 900 }, { "grad_norm": 1.6207280158996582, "learning_rate": 1.818e-05, "loss": 0.3232, "step": 910 }, { "loss_action": 0.2971653640270233, "loss_total": 0.2971653640270233, "step": 910 }, { "grad_norm": 1.5043786764144897, "learning_rate": 1.838e-05, "loss": 0.3115, "step": 920 }, { "loss_action": 0.33358287811279297, "loss_total": 0.33358287811279297, "step": 920 }, { "grad_norm": 2.000373125076294, "learning_rate": 1.858e-05, "loss": 0.308, "step": 930 }, { "loss_action": 0.3091801404953003, "loss_total": 0.3091801404953003, "step": 930 }, { "grad_norm": 1.5808124542236328, "learning_rate": 1.878e-05, "loss": 0.2997, "step": 940 }, { "loss_action": 0.3034047782421112, "loss_total": 0.3034047782421112, "step": 940 }, { "grad_norm": 1.7755664587020874, "learning_rate": 1.898e-05, "loss": 0.2908, "step": 950 }, { "loss_action": 0.2851598560810089, "loss_total": 0.2851598560810089, "step": 950 }, { "grad_norm": 1.5317206382751465, "learning_rate": 1.918e-05, "loss": 0.2829, "step": 960 }, { "loss_action": 0.270894318819046, "loss_total": 0.270894318819046, "step": 960 }, { "grad_norm": 1.7854950428009033, "learning_rate": 1.938e-05, "loss": 0.2707, "step": 970 }, { "loss_action": 0.26668688654899597, "loss_total": 0.26668688654899597, "step": 970 }, { "grad_norm": 2.309015989303589, "learning_rate": 1.9580000000000002e-05, "loss": 0.2654, "step": 980 }, { "loss_action": 0.26455748081207275, "loss_total": 0.26455748081207275, "step": 980 }, { "grad_norm": 1.7885935306549072, "learning_rate": 1.978e-05, "loss": 0.2651, "step": 990 }, { "loss_action": 0.24818451702594757, "loss_total": 0.24818451702594757, "step": 990 }, { "grad_norm": 2.546172857284546, "learning_rate": 1.9980000000000002e-05, "loss": 0.2499, "step": 1000 }, { "loss_action": 0.24546915292739868, "loss_total": 0.24546915292739868, "step": 1000 }, { "grad_norm": 2.3741843700408936, "learning_rate": 2.0180000000000003e-05, "loss": 0.2466, "step": 1010 }, { "loss_action": 0.22018903493881226, "loss_total": 0.22018903493881226, "step": 1010 }, { "grad_norm": 2.0495288372039795, "learning_rate": 2.038e-05, "loss": 0.2313, "step": 1020 }, { "loss_action": 0.22735407948493958, "loss_total": 0.22735407948493958, "step": 1020 }, { "grad_norm": 2.011207342147827, "learning_rate": 2.0580000000000003e-05, "loss": 0.2264, "step": 1030 }, { "loss_action": 0.21788913011550903, "loss_total": 0.21788913011550903, "step": 1030 }, { "grad_norm": 2.1970319747924805, "learning_rate": 2.078e-05, "loss": 0.2183, "step": 1040 }, { "loss_action": 0.22886840999126434, "loss_total": 0.22886840999126434, "step": 1040 }, { "grad_norm": 1.9502389430999756, "learning_rate": 2.098e-05, "loss": 0.2123, "step": 1050 }, { "loss_action": 0.19879814982414246, "loss_total": 0.19879814982414246, "step": 1050 }, { "grad_norm": 2.203538656234741, "learning_rate": 2.118e-05, "loss": 0.2059, "step": 1060 }, { "loss_action": 0.20823751389980316, "loss_total": 0.20823751389980316, "step": 1060 }, { "grad_norm": 1.7890255451202393, "learning_rate": 2.138e-05, "loss": 0.2063, "step": 1070 }, { "loss_action": 0.1751929372549057, "loss_total": 0.1751929372549057, "step": 1070 }, { "grad_norm": 2.0886547565460205, "learning_rate": 2.158e-05, "loss": 0.193, "step": 1080 }, { "loss_action": 0.19383983314037323, "loss_total": 0.19383983314037323, "step": 1080 }, { "grad_norm": 1.669100284576416, "learning_rate": 2.178e-05, "loss": 0.1935, "step": 1090 }, { "loss_action": 0.20844589173793793, "loss_total": 0.20844589173793793, "step": 1090 }, { "grad_norm": 1.7136542797088623, "learning_rate": 2.198e-05, "loss": 0.198, "step": 1100 }, { "loss_action": 0.21345442533493042, "loss_total": 0.21345442533493042, "step": 1100 }, { "grad_norm": 1.5116338729858398, "learning_rate": 2.218e-05, "loss": 0.1915, "step": 1110 }, { "loss_action": 0.16822317242622375, "loss_total": 0.16822317242622375, "step": 1110 }, { "grad_norm": 2.4104151725769043, "learning_rate": 2.2380000000000003e-05, "loss": 0.1731, "step": 1120 }, { "loss_action": 0.17216219007968903, "loss_total": 0.17216219007968903, "step": 1120 }, { "grad_norm": 1.780718445777893, "learning_rate": 2.258e-05, "loss": 0.1772, "step": 1130 }, { "loss_action": 0.17003236711025238, "loss_total": 0.17003236711025238, "step": 1130 }, { "grad_norm": 1.321094036102295, "learning_rate": 2.2780000000000002e-05, "loss": 0.1585, "step": 1140 }, { "loss_action": 0.1837119162082672, "loss_total": 0.1837119162082672, "step": 1140 }, { "grad_norm": 1.4576189517974854, "learning_rate": 2.298e-05, "loss": 0.1631, "step": 1150 }, { "loss_action": 0.1715218871831894, "loss_total": 0.1715218871831894, "step": 1150 }, { "grad_norm": 1.7784440517425537, "learning_rate": 2.318e-05, "loss": 0.1581, "step": 1160 }, { "loss_action": 0.13576266169548035, "loss_total": 0.13576266169548035, "step": 1160 }, { "grad_norm": 2.0827794075012207, "learning_rate": 2.3380000000000003e-05, "loss": 0.1477, "step": 1170 }, { "loss_action": 0.18969684839248657, "loss_total": 0.18969684839248657, "step": 1170 }, { "grad_norm": 1.9726378917694092, "learning_rate": 2.358e-05, "loss": 0.1538, "step": 1180 }, { "loss_action": 0.15483170747756958, "loss_total": 0.15483170747756958, "step": 1180 }, { "grad_norm": 1.9113836288452148, "learning_rate": 2.3780000000000003e-05, "loss": 0.1445, "step": 1190 }, { "loss_action": 0.15310989320278168, "loss_total": 0.15310989320278168, "step": 1190 }, { "grad_norm": 1.6347167491912842, "learning_rate": 2.398e-05, "loss": 0.1394, "step": 1200 }, { "loss_action": 0.12280192226171494, "loss_total": 0.12280192226171494, "step": 1200 }, { "grad_norm": 1.7024892568588257, "learning_rate": 2.418e-05, "loss": 0.1347, "step": 1210 }, { "loss_action": 0.1141812652349472, "loss_total": 0.1141812652349472, "step": 1210 }, { "grad_norm": 2.553508996963501, "learning_rate": 2.438e-05, "loss": 0.1249, "step": 1220 }, { "loss_action": 0.13326537609100342, "loss_total": 0.13326537609100342, "step": 1220 }, { "grad_norm": 2.1353883743286133, "learning_rate": 2.4580000000000002e-05, "loss": 0.1263, "step": 1230 }, { "loss_action": 0.12657365202903748, "loss_total": 0.12657365202903748, "step": 1230 }, { "grad_norm": 2.2635600566864014, "learning_rate": 2.478e-05, "loss": 0.1203, "step": 1240 }, { "loss_action": 0.13778534531593323, "loss_total": 0.13778534531593323, "step": 1240 }, { "grad_norm": 1.8107918500900269, "learning_rate": 2.498e-05, "loss": 0.1242, "step": 1250 }, { "loss_action": 0.10736624151468277, "loss_total": 0.10736624151468277, "step": 1250 }, { "grad_norm": 2.126692056655884, "learning_rate": 2.5180000000000003e-05, "loss": 0.1171, "step": 1260 }, { "loss_action": 0.11996821314096451, "loss_total": 0.11996821314096451, "step": 1260 }, { "grad_norm": 1.5106160640716553, "learning_rate": 2.5380000000000004e-05, "loss": 0.1164, "step": 1270 }, { "loss_action": 0.1183917373418808, "loss_total": 0.1183917373418808, "step": 1270 }, { "grad_norm": 1.7720829248428345, "learning_rate": 2.5580000000000002e-05, "loss": 0.1192, "step": 1280 }, { "loss_action": 0.11550354957580566, "loss_total": 0.11550354957580566, "step": 1280 }, { "grad_norm": 1.604983925819397, "learning_rate": 2.5779999999999997e-05, "loss": 0.1136, "step": 1290 }, { "loss_action": 0.09474963694810867, "loss_total": 0.09474963694810867, "step": 1290 }, { "grad_norm": 2.4011011123657227, "learning_rate": 2.598e-05, "loss": 0.1086, "step": 1300 }, { "loss_action": 0.10602141916751862, "loss_total": 0.10602141916751862, "step": 1300 }, { "grad_norm": 2.734215259552002, "learning_rate": 2.618e-05, "loss": 0.1243, "step": 1310 }, { "loss_action": 0.10672373324632645, "loss_total": 0.10672373324632645, "step": 1310 }, { "grad_norm": 2.102694272994995, "learning_rate": 2.6379999999999998e-05, "loss": 0.1135, "step": 1320 }, { "loss_action": 0.13017961382865906, "loss_total": 0.13017961382865906, "step": 1320 }, { "grad_norm": 2.325324058532715, "learning_rate": 2.658e-05, "loss": 0.1131, "step": 1330 }, { "loss_action": 0.11435531079769135, "loss_total": 0.11435531079769135, "step": 1330 }, { "grad_norm": 1.8963319063186646, "learning_rate": 2.678e-05, "loss": 0.1138, "step": 1340 }, { "loss_action": 0.11223219335079193, "loss_total": 0.11223219335079193, "step": 1340 }, { "grad_norm": 1.8990859985351562, "learning_rate": 2.698e-05, "loss": 0.1071, "step": 1350 }, { "loss_action": 0.11280202865600586, "loss_total": 0.11280202865600586, "step": 1350 }, { "grad_norm": 1.891511082649231, "learning_rate": 2.718e-05, "loss": 0.1046, "step": 1360 }, { "loss_action": 0.1018218994140625, "loss_total": 0.1018218994140625, "step": 1360 }, { "grad_norm": 2.2588627338409424, "learning_rate": 2.738e-05, "loss": 0.1084, "step": 1370 }, { "loss_action": 0.11343901604413986, "loss_total": 0.11343901604413986, "step": 1370 }, { "grad_norm": 1.9744237661361694, "learning_rate": 2.758e-05, "loss": 0.1097, "step": 1380 }, { "loss_action": 0.11561024934053421, "loss_total": 0.11561024934053421, "step": 1380 }, { "grad_norm": 1.8237768411636353, "learning_rate": 2.778e-05, "loss": 0.1054, "step": 1390 }, { "loss_action": 0.08786916732788086, "loss_total": 0.08786916732788086, "step": 1390 }, { "grad_norm": 2.3025288581848145, "learning_rate": 2.798e-05, "loss": 0.1151, "step": 1400 }, { "loss_action": 0.1250944435596466, "loss_total": 0.1250944435596466, "step": 1400 }, { "grad_norm": 1.640091896057129, "learning_rate": 2.818e-05, "loss": 0.1088, "step": 1410 }, { "loss_action": 0.0860084593296051, "loss_total": 0.0860084593296051, "step": 1410 }, { "grad_norm": 1.5633232593536377, "learning_rate": 2.8380000000000003e-05, "loss": 0.0983, "step": 1420 }, { "loss_action": 0.10509208589792252, "loss_total": 0.10509208589792252, "step": 1420 }, { "grad_norm": 1.5517141819000244, "learning_rate": 2.858e-05, "loss": 0.1076, "step": 1430 }, { "loss_action": 0.10510808974504471, "loss_total": 0.10510808974504471, "step": 1430 }, { "grad_norm": 1.7155530452728271, "learning_rate": 2.8780000000000002e-05, "loss": 0.1107, "step": 1440 }, { "loss_action": 0.12242737412452698, "loss_total": 0.12242737412452698, "step": 1440 }, { "grad_norm": 2.039205551147461, "learning_rate": 2.898e-05, "loss": 0.1036, "step": 1450 }, { "loss_action": 0.09044715762138367, "loss_total": 0.09044715762138367, "step": 1450 }, { "grad_norm": 1.913451910018921, "learning_rate": 2.9180000000000002e-05, "loss": 0.0972, "step": 1460 }, { "loss_action": 0.10182847082614899, "loss_total": 0.10182847082614899, "step": 1460 }, { "grad_norm": 1.9890110492706299, "learning_rate": 2.9380000000000003e-05, "loss": 0.103, "step": 1470 }, { "loss_action": 0.10082468390464783, "loss_total": 0.10082468390464783, "step": 1470 }, { "grad_norm": 1.7817939519882202, "learning_rate": 2.958e-05, "loss": 0.1031, "step": 1480 }, { "loss_action": 0.09396567195653915, "loss_total": 0.09396567195653915, "step": 1480 }, { "grad_norm": 1.8546509742736816, "learning_rate": 2.9780000000000003e-05, "loss": 0.0945, "step": 1490 }, { "loss_action": 0.07825460284948349, "loss_total": 0.07825460284948349, "step": 1490 }, { "grad_norm": 1.774600863456726, "learning_rate": 2.998e-05, "loss": 0.0937, "step": 1500 }, { "loss_action": 0.08502033352851868, "loss_total": 0.08502033352851868, "step": 1500 }, { "grad_norm": 1.7144558429718018, "learning_rate": 3.0180000000000002e-05, "loss": 0.0927, "step": 1510 }, { "loss_action": 0.08330810815095901, "loss_total": 0.08330810815095901, "step": 1510 }, { "grad_norm": 1.9999109506607056, "learning_rate": 3.0380000000000004e-05, "loss": 0.0884, "step": 1520 }, { "loss_action": 0.082108274102211, "loss_total": 0.082108274102211, "step": 1520 }, { "grad_norm": 2.6848928928375244, "learning_rate": 3.058e-05, "loss": 0.0882, "step": 1530 }, { "loss_action": 0.11180569231510162, "loss_total": 0.11180569231510162, "step": 1530 }, { "grad_norm": 1.3180707693099976, "learning_rate": 3.078e-05, "loss": 0.099, "step": 1540 }, { "loss_action": 0.09130052477121353, "loss_total": 0.09130052477121353, "step": 1540 }, { "grad_norm": 1.5988858938217163, "learning_rate": 3.0980000000000005e-05, "loss": 0.0988, "step": 1550 }, { "loss_action": 0.09105897694826126, "loss_total": 0.09105897694826126, "step": 1550 }, { "grad_norm": 1.783216953277588, "learning_rate": 3.118e-05, "loss": 0.0904, "step": 1560 }, { "loss_action": 0.09760374575853348, "loss_total": 0.09760374575853348, "step": 1560 }, { "grad_norm": 1.4032416343688965, "learning_rate": 3.138e-05, "loss": 0.0968, "step": 1570 }, { "loss_action": 0.09224730730056763, "loss_total": 0.09224730730056763, "step": 1570 }, { "grad_norm": 1.516771912574768, "learning_rate": 3.1580000000000006e-05, "loss": 0.0861, "step": 1580 }, { "loss_action": 0.09189189970493317, "loss_total": 0.09189189970493317, "step": 1580 }, { "grad_norm": 1.4260263442993164, "learning_rate": 3.1780000000000004e-05, "loss": 0.0858, "step": 1590 }, { "loss_action": 0.0960170105099678, "loss_total": 0.0960170105099678, "step": 1590 }, { "grad_norm": 1.800865650177002, "learning_rate": 3.198e-05, "loss": 0.0919, "step": 1600 }, { "loss_action": 0.10131175071001053, "loss_total": 0.10131175071001053, "step": 1600 }, { "grad_norm": 1.9816219806671143, "learning_rate": 3.218e-05, "loss": 0.0871, "step": 1610 }, { "loss_action": 0.07776249945163727, "loss_total": 0.07776249945163727, "step": 1610 }, { "grad_norm": 1.8734441995620728, "learning_rate": 3.238e-05, "loss": 0.0882, "step": 1620 }, { "loss_action": 0.07746737450361252, "loss_total": 0.07746737450361252, "step": 1620 }, { "grad_norm": 1.9167358875274658, "learning_rate": 3.2579999999999996e-05, "loss": 0.0849, "step": 1630 }, { "loss_action": 0.08029995858669281, "loss_total": 0.08029995858669281, "step": 1630 }, { "grad_norm": 1.9753614664077759, "learning_rate": 3.278e-05, "loss": 0.0854, "step": 1640 }, { "loss_action": 0.08936705440282822, "loss_total": 0.08936705440282822, "step": 1640 }, { "grad_norm": 2.1801023483276367, "learning_rate": 3.298e-05, "loss": 0.0912, "step": 1650 }, { "loss_action": 0.0980130285024643, "loss_total": 0.0980130285024643, "step": 1650 }, { "grad_norm": 1.6424908638000488, "learning_rate": 3.318e-05, "loss": 0.1006, "step": 1660 }, { "loss_action": 0.07598018646240234, "loss_total": 0.07598018646240234, "step": 1660 }, { "grad_norm": 1.8731170892715454, "learning_rate": 3.338e-05, "loss": 0.0851, "step": 1670 }, { "loss_action": 0.08240404725074768, "loss_total": 0.08240404725074768, "step": 1670 }, { "grad_norm": 1.359260082244873, "learning_rate": 3.358e-05, "loss": 0.084, "step": 1680 }, { "loss_action": 0.08208087831735611, "loss_total": 0.08208087831735611, "step": 1680 }, { "grad_norm": 1.7395377159118652, "learning_rate": 3.378e-05, "loss": 0.0838, "step": 1690 }, { "loss_action": 0.07235003262758255, "loss_total": 0.07235003262758255, "step": 1690 }, { "grad_norm": 1.6751054525375366, "learning_rate": 3.398e-05, "loss": 0.0816, "step": 1700 }, { "loss_action": 0.07380537688732147, "loss_total": 0.07380537688732147, "step": 1700 }, { "grad_norm": 2.4507389068603516, "learning_rate": 3.418e-05, "loss": 0.0793, "step": 1710 }, { "loss_action": 0.07605668902397156, "loss_total": 0.07605668902397156, "step": 1710 }, { "grad_norm": 1.4877090454101562, "learning_rate": 3.438e-05, "loss": 0.0856, "step": 1720 }, { "loss_action": 0.09286586195230484, "loss_total": 0.09286586195230484, "step": 1720 }, { "grad_norm": 1.8029582500457764, "learning_rate": 3.4580000000000004e-05, "loss": 0.0866, "step": 1730 }, { "loss_action": 0.08238176256418228, "loss_total": 0.08238176256418228, "step": 1730 }, { "grad_norm": 1.809967279434204, "learning_rate": 3.478e-05, "loss": 0.0864, "step": 1740 }, { "loss_action": 0.06287062913179398, "loss_total": 0.06287062913179398, "step": 1740 }, { "grad_norm": 1.6572991609573364, "learning_rate": 3.498e-05, "loss": 0.0807, "step": 1750 }, { "loss_action": 0.07744240760803223, "loss_total": 0.07744240760803223, "step": 1750 }, { "grad_norm": 2.001748561859131, "learning_rate": 3.518e-05, "loss": 0.0821, "step": 1760 }, { "loss_action": 0.08587680011987686, "loss_total": 0.08587680011987686, "step": 1760 }, { "grad_norm": 1.7491120100021362, "learning_rate": 3.5380000000000003e-05, "loss": 0.0851, "step": 1770 }, { "loss_action": 0.07507892698049545, "loss_total": 0.07507892698049545, "step": 1770 }, { "grad_norm": 1.4011751413345337, "learning_rate": 3.558e-05, "loss": 0.0777, "step": 1780 }, { "loss_action": 0.07439182698726654, "loss_total": 0.07439182698726654, "step": 1780 }, { "grad_norm": 1.6271735429763794, "learning_rate": 3.578e-05, "loss": 0.0781, "step": 1790 }, { "loss_action": 0.06798932701349258, "loss_total": 0.06798932701349258, "step": 1790 }, { "grad_norm": 1.5344369411468506, "learning_rate": 3.5980000000000004e-05, "loss": 0.0788, "step": 1800 }, { "loss_action": 0.07739000022411346, "loss_total": 0.07739000022411346, "step": 1800 }, { "grad_norm": 1.970399260520935, "learning_rate": 3.618e-05, "loss": 0.0779, "step": 1810 }, { "loss_action": 0.06566829234361649, "loss_total": 0.06566829234361649, "step": 1810 }, { "grad_norm": 1.3226141929626465, "learning_rate": 3.638e-05, "loss": 0.0725, "step": 1820 }, { "loss_action": 0.06573958694934845, "loss_total": 0.06573958694934845, "step": 1820 }, { "grad_norm": 1.6509647369384766, "learning_rate": 3.6580000000000006e-05, "loss": 0.0746, "step": 1830 }, { "loss_action": 0.082979217171669, "loss_total": 0.082979217171669, "step": 1830 }, { "grad_norm": 1.5838203430175781, "learning_rate": 3.6780000000000004e-05, "loss": 0.0808, "step": 1840 }, { "loss_action": 0.07066208124160767, "loss_total": 0.07066208124160767, "step": 1840 }, { "grad_norm": 1.7333940267562866, "learning_rate": 3.698e-05, "loss": 0.0745, "step": 1850 }, { "loss_action": 0.059823110699653625, "loss_total": 0.059823110699653625, "step": 1850 }, { "grad_norm": 1.5867079496383667, "learning_rate": 3.7180000000000007e-05, "loss": 0.0714, "step": 1860 }, { "loss_action": 0.07564558833837509, "loss_total": 0.07564558833837509, "step": 1860 }, { "grad_norm": 1.5666369199752808, "learning_rate": 3.7380000000000005e-05, "loss": 0.0796, "step": 1870 }, { "loss_action": 0.08366435766220093, "loss_total": 0.08366435766220093, "step": 1870 }, { "grad_norm": 1.8034987449645996, "learning_rate": 3.758e-05, "loss": 0.0763, "step": 1880 }, { "loss_action": 0.06637480854988098, "loss_total": 0.06637480854988098, "step": 1880 }, { "grad_norm": 1.865465760231018, "learning_rate": 3.778000000000001e-05, "loss": 0.0745, "step": 1890 }, { "loss_action": 0.07000473886728287, "loss_total": 0.07000473886728287, "step": 1890 }, { "grad_norm": 1.4413244724273682, "learning_rate": 3.7980000000000006e-05, "loss": 0.0761, "step": 1900 }, { "loss_action": 0.06372073292732239, "loss_total": 0.06372073292732239, "step": 1900 }, { "grad_norm": 1.411976933479309, "learning_rate": 3.818e-05, "loss": 0.0698, "step": 1910 }, { "loss_action": 0.08579737693071365, "loss_total": 0.08579737693071365, "step": 1910 }, { "grad_norm": 1.9353233575820923, "learning_rate": 3.838e-05, "loss": 0.0718, "step": 1920 }, { "loss_action": 0.07395662367343903, "loss_total": 0.07395662367343903, "step": 1920 }, { "grad_norm": 1.4549628496170044, "learning_rate": 3.858e-05, "loss": 0.0683, "step": 1930 }, { "loss_action": 0.07869701087474823, "loss_total": 0.07869701087474823, "step": 1930 }, { "grad_norm": 1.3357651233673096, "learning_rate": 3.878e-05, "loss": 0.0705, "step": 1940 }, { "loss_action": 0.06555836647748947, "loss_total": 0.06555836647748947, "step": 1940 }, { "grad_norm": 1.6844998598098755, "learning_rate": 3.898e-05, "loss": 0.0673, "step": 1950 }, { "loss_action": 0.0777442529797554, "loss_total": 0.0777442529797554, "step": 1950 }, { "grad_norm": 1.6498303413391113, "learning_rate": 3.918e-05, "loss": 0.0785, "step": 1960 }, { "loss_action": 0.07136394083499908, "loss_total": 0.07136394083499908, "step": 1960 }, { "grad_norm": 1.9323105812072754, "learning_rate": 3.938e-05, "loss": 0.0695, "step": 1970 }, { "loss_action": 0.07921566814184189, "loss_total": 0.07921566814184189, "step": 1970 }, { "grad_norm": 1.562604546546936, "learning_rate": 3.958e-05, "loss": 0.0728, "step": 1980 }, { "loss_action": 0.06909997016191483, "loss_total": 0.06909997016191483, "step": 1980 }, { "grad_norm": 1.4374141693115234, "learning_rate": 3.978e-05, "loss": 0.0769, "step": 1990 }, { "loss_action": 0.07110957056283951, "loss_total": 0.07110957056283951, "step": 1990 }, { "grad_norm": 1.3763998746871948, "learning_rate": 3.998e-05, "loss": 0.0694, "step": 2000 }, { "loss_action": 0.06735556572675705, "loss_total": 0.06735556572675705, "step": 2000 }, { "grad_norm": 1.4267973899841309, "learning_rate": 4.018e-05, "loss": 0.0669, "step": 2010 }, { "loss_action": 0.06693907827138901, "loss_total": 0.06693907827138901, "step": 2010 }, { "grad_norm": 1.6724779605865479, "learning_rate": 4.038e-05, "loss": 0.0673, "step": 2020 }, { "loss_action": 0.06359020620584488, "loss_total": 0.06359020620584488, "step": 2020 }, { "grad_norm": 1.7893812656402588, "learning_rate": 4.058e-05, "loss": 0.0705, "step": 2030 }, { "loss_action": 0.06221610680222511, "loss_total": 0.06221610680222511, "step": 2030 }, { "grad_norm": 1.7210962772369385, "learning_rate": 4.078e-05, "loss": 0.0741, "step": 2040 }, { "loss_action": 0.06409767270088196, "loss_total": 0.06409767270088196, "step": 2040 }, { "grad_norm": 1.4575811624526978, "learning_rate": 4.0980000000000004e-05, "loss": 0.0724, "step": 2050 }, { "loss_action": 0.06480720639228821, "loss_total": 0.06480720639228821, "step": 2050 }, { "grad_norm": 1.7262804508209229, "learning_rate": 4.118e-05, "loss": 0.0701, "step": 2060 }, { "loss_action": 0.06698770076036453, "loss_total": 0.06698770076036453, "step": 2060 }, { "grad_norm": 1.837482213973999, "learning_rate": 4.138e-05, "loss": 0.0712, "step": 2070 }, { "loss_action": 0.07867161184549332, "loss_total": 0.07867161184549332, "step": 2070 }, { "grad_norm": 1.2243237495422363, "learning_rate": 4.1580000000000005e-05, "loss": 0.0741, "step": 2080 }, { "loss_action": 0.061276692897081375, "loss_total": 0.061276692897081375, "step": 2080 }, { "grad_norm": 1.747591257095337, "learning_rate": 4.178e-05, "loss": 0.0677, "step": 2090 }, { "loss_action": 0.061822086572647095, "loss_total": 0.061822086572647095, "step": 2090 }, { "grad_norm": 1.4477041959762573, "learning_rate": 4.198e-05, "loss": 0.0656, "step": 2100 }, { "loss_action": 0.06594310700893402, "loss_total": 0.06594310700893402, "step": 2100 }, { "grad_norm": 1.2618168592453003, "learning_rate": 4.2180000000000006e-05, "loss": 0.0677, "step": 2110 }, { "loss_action": 0.06409618258476257, "loss_total": 0.06409618258476257, "step": 2110 }, { "grad_norm": 1.8238718509674072, "learning_rate": 4.2380000000000004e-05, "loss": 0.0655, "step": 2120 }, { "loss_action": 0.06117832288146019, "loss_total": 0.06117832288146019, "step": 2120 }, { "grad_norm": 1.6574797630310059, "learning_rate": 4.258e-05, "loss": 0.0656, "step": 2130 }, { "loss_action": 0.06789113581180573, "loss_total": 0.06789113581180573, "step": 2130 }, { "grad_norm": 1.851223111152649, "learning_rate": 4.278e-05, "loss": 0.0649, "step": 2140 }, { "loss_action": 0.06587785482406616, "loss_total": 0.06587785482406616, "step": 2140 }, { "grad_norm": 1.5932729244232178, "learning_rate": 4.2980000000000005e-05, "loss": 0.0672, "step": 2150 }, { "loss_action": 0.06413953006267548, "loss_total": 0.06413953006267548, "step": 2150 }, { "grad_norm": 1.5607280731201172, "learning_rate": 4.318e-05, "loss": 0.0644, "step": 2160 }, { "loss_action": 0.06628527492284775, "loss_total": 0.06628527492284775, "step": 2160 }, { "grad_norm": 1.9246593713760376, "learning_rate": 4.338e-05, "loss": 0.0682, "step": 2170 }, { "loss_action": 0.057603757828474045, "loss_total": 0.057603757828474045, "step": 2170 }, { "grad_norm": 1.5021806955337524, "learning_rate": 4.3580000000000006e-05, "loss": 0.0676, "step": 2180 }, { "loss_action": 0.08261279761791229, "loss_total": 0.08261279761791229, "step": 2180 }, { "grad_norm": 1.5388332605361938, "learning_rate": 4.3780000000000004e-05, "loss": 0.0677, "step": 2190 }, { "loss_action": 0.05748467147350311, "loss_total": 0.05748467147350311, "step": 2190 }, { "grad_norm": 1.5391428470611572, "learning_rate": 4.398e-05, "loss": 0.0711, "step": 2200 }, { "loss_action": 0.0815531387925148, "loss_total": 0.0815531387925148, "step": 2200 }, { "grad_norm": 1.393863558769226, "learning_rate": 4.418000000000001e-05, "loss": 0.0667, "step": 2210 }, { "loss_action": 0.0652352124452591, "loss_total": 0.0652352124452591, "step": 2210 }, { "grad_norm": 1.1977607011795044, "learning_rate": 4.438e-05, "loss": 0.0681, "step": 2220 }, { "loss_action": 0.05546818673610687, "loss_total": 0.05546818673610687, "step": 2220 }, { "grad_norm": 1.4241138696670532, "learning_rate": 4.458e-05, "loss": 0.0607, "step": 2230 }, { "loss_action": 0.05957566201686859, "loss_total": 0.05957566201686859, "step": 2230 }, { "grad_norm": 1.5580041408538818, "learning_rate": 4.478e-05, "loss": 0.0613, "step": 2240 }, { "loss_action": 0.055328670889139175, "loss_total": 0.055328670889139175, "step": 2240 }, { "grad_norm": 1.3573205471038818, "learning_rate": 4.498e-05, "loss": 0.0638, "step": 2250 }, { "loss_action": 0.0556834414601326, "loss_total": 0.0556834414601326, "step": 2250 }, { "grad_norm": 1.416259527206421, "learning_rate": 4.518e-05, "loss": 0.0613, "step": 2260 }, { "loss_action": 0.06769665330648422, "loss_total": 0.06769665330648422, "step": 2260 }, { "grad_norm": 1.3520737886428833, "learning_rate": 4.538e-05, "loss": 0.0644, "step": 2270 }, { "loss_action": 0.05909973755478859, "loss_total": 0.05909973755478859, "step": 2270 }, { "grad_norm": 1.5898507833480835, "learning_rate": 4.558e-05, "loss": 0.0642, "step": 2280 }, { "loss_action": 0.050332434475421906, "loss_total": 0.050332434475421906, "step": 2280 }, { "grad_norm": 1.8673903942108154, "learning_rate": 4.578e-05, "loss": 0.065, "step": 2290 }, { "loss_action": 0.05888838320970535, "loss_total": 0.05888838320970535, "step": 2290 }, { "grad_norm": 1.3730641603469849, "learning_rate": 4.5980000000000004e-05, "loss": 0.0639, "step": 2300 }, { "loss_action": 0.05827987194061279, "loss_total": 0.05827987194061279, "step": 2300 }, { "grad_norm": 1.2982990741729736, "learning_rate": 4.618e-05, "loss": 0.0718, "step": 2310 }, { "loss_action": 0.07140783965587616, "loss_total": 0.07140783965587616, "step": 2310 }, { "grad_norm": 1.3275941610336304, "learning_rate": 4.638e-05, "loss": 0.0631, "step": 2320 }, { "loss_action": 0.05679939314723015, "loss_total": 0.05679939314723015, "step": 2320 }, { "grad_norm": 1.8142551183700562, "learning_rate": 4.6580000000000005e-05, "loss": 0.0613, "step": 2330 }, { "loss_action": 0.06039111316204071, "loss_total": 0.06039111316204071, "step": 2330 }, { "grad_norm": 1.5932828187942505, "learning_rate": 4.678e-05, "loss": 0.0609, "step": 2340 }, { "loss_action": 0.07779514044523239, "loss_total": 0.07779514044523239, "step": 2340 }, { "grad_norm": 1.1236211061477661, "learning_rate": 4.698e-05, "loss": 0.0636, "step": 2350 }, { "loss_action": 0.05830252170562744, "loss_total": 0.05830252170562744, "step": 2350 }, { "grad_norm": 1.4411146640777588, "learning_rate": 4.718e-05, "loss": 0.0619, "step": 2360 }, { "loss_action": 0.058489490300416946, "loss_total": 0.058489490300416946, "step": 2360 }, { "grad_norm": 1.108262538909912, "learning_rate": 4.7380000000000004e-05, "loss": 0.0588, "step": 2370 }, { "loss_action": 0.05854383483529091, "loss_total": 0.05854383483529091, "step": 2370 }, { "grad_norm": 1.261234164237976, "learning_rate": 4.758e-05, "loss": 0.062, "step": 2380 }, { "loss_action": 0.05688927695155144, "loss_total": 0.05688927695155144, "step": 2380 }, { "grad_norm": 1.6834771633148193, "learning_rate": 4.778e-05, "loss": 0.0636, "step": 2390 }, { "loss_action": 0.05140908434987068, "loss_total": 0.05140908434987068, "step": 2390 }, { "grad_norm": 1.4964542388916016, "learning_rate": 4.7980000000000005e-05, "loss": 0.0603, "step": 2400 }, { "loss_action": 0.06645054370164871, "loss_total": 0.06645054370164871, "step": 2400 }, { "grad_norm": 1.6729530096054077, "learning_rate": 4.818e-05, "loss": 0.064, "step": 2410 }, { "loss_action": 0.0716886892914772, "loss_total": 0.0716886892914772, "step": 2410 }, { "grad_norm": 1.362006664276123, "learning_rate": 4.838e-05, "loss": 0.0628, "step": 2420 }, { "loss_action": 0.0513809509575367, "loss_total": 0.0513809509575367, "step": 2420 }, { "grad_norm": 1.1365247964859009, "learning_rate": 4.8580000000000006e-05, "loss": 0.0594, "step": 2430 }, { "loss_action": 0.054407790303230286, "loss_total": 0.054407790303230286, "step": 2430 }, { "grad_norm": 1.3733570575714111, "learning_rate": 4.8780000000000004e-05, "loss": 0.0559, "step": 2440 }, { "loss_action": 0.061942681670188904, "loss_total": 0.061942681670188904, "step": 2440 }, { "grad_norm": 1.258101463317871, "learning_rate": 4.898e-05, "loss": 0.0559, "step": 2450 }, { "loss_action": 0.06128488481044769, "loss_total": 0.06128488481044769, "step": 2450 }, { "grad_norm": 1.261559247970581, "learning_rate": 4.918000000000001e-05, "loss": 0.0566, "step": 2460 }, { "loss_action": 0.05535638704895973, "loss_total": 0.05535638704895973, "step": 2460 }, { "grad_norm": 1.3797554969787598, "learning_rate": 4.9380000000000005e-05, "loss": 0.0553, "step": 2470 }, { "loss_action": 0.04986531659960747, "loss_total": 0.04986531659960747, "step": 2470 }, { "grad_norm": 1.3043231964111328, "learning_rate": 4.958e-05, "loss": 0.0592, "step": 2480 }, { "loss_action": 0.044091057032346725, "loss_total": 0.044091057032346725, "step": 2480 }, { "grad_norm": 1.580985426902771, "learning_rate": 4.978e-05, "loss": 0.0578, "step": 2490 }, { "loss_action": 0.052405402064323425, "loss_total": 0.052405402064323425, "step": 2490 }, { "grad_norm": 1.2457356452941895, "learning_rate": 4.9980000000000006e-05, "loss": 0.0598, "step": 2500 }, { "loss_action": 0.06180170178413391, "loss_total": 0.06180170178413391, "step": 2500 }, { "grad_norm": 1.5441744327545166, "learning_rate": 5.0180000000000004e-05, "loss": 0.057, "step": 2510 }, { "loss_action": 0.05734488368034363, "loss_total": 0.05734488368034363, "step": 2510 }, { "grad_norm": 1.3683925867080688, "learning_rate": 5.038e-05, "loss": 0.0573, "step": 2520 }, { "loss_action": 0.05686265975236893, "loss_total": 0.05686265975236893, "step": 2520 }, { "grad_norm": 1.380780816078186, "learning_rate": 5.058000000000001e-05, "loss": 0.0545, "step": 2530 }, { "loss_action": 0.05961787328124046, "loss_total": 0.05961787328124046, "step": 2530 }, { "grad_norm": 1.317933440208435, "learning_rate": 5.0780000000000005e-05, "loss": 0.056, "step": 2540 }, { "loss_action": 0.056078750640153885, "loss_total": 0.056078750640153885, "step": 2540 }, { "grad_norm": 1.4021587371826172, "learning_rate": 5.098e-05, "loss": 0.0591, "step": 2550 }, { "loss_action": 0.07625774294137955, "loss_total": 0.07625774294137955, "step": 2550 }, { "grad_norm": 1.3749088048934937, "learning_rate": 5.118000000000001e-05, "loss": 0.0596, "step": 2560 }, { "loss_action": 0.06202111393213272, "loss_total": 0.06202111393213272, "step": 2560 }, { "grad_norm": 1.3928065299987793, "learning_rate": 5.1380000000000006e-05, "loss": 0.0566, "step": 2570 }, { "loss_action": 0.05354642868041992, "loss_total": 0.05354642868041992, "step": 2570 }, { "grad_norm": 1.1601066589355469, "learning_rate": 5.1580000000000004e-05, "loss": 0.0555, "step": 2580 }, { "loss_action": 0.053057484328746796, "loss_total": 0.053057484328746796, "step": 2580 }, { "grad_norm": 1.4052702188491821, "learning_rate": 5.178000000000001e-05, "loss": 0.0565, "step": 2590 }, { "loss_action": 0.05682957172393799, "loss_total": 0.05682957172393799, "step": 2590 }, { "grad_norm": 1.3287265300750732, "learning_rate": 5.198000000000001e-05, "loss": 0.057, "step": 2600 }, { "loss_action": 0.058233197778463364, "loss_total": 0.058233197778463364, "step": 2600 }, { "grad_norm": 1.1858521699905396, "learning_rate": 5.2180000000000005e-05, "loss": 0.0585, "step": 2610 }, { "loss_action": 0.05828292295336723, "loss_total": 0.05828292295336723, "step": 2610 }, { "grad_norm": 1.1679635047912598, "learning_rate": 5.238000000000001e-05, "loss": 0.0555, "step": 2620 }, { "loss_action": 0.044683728367090225, "loss_total": 0.044683728367090225, "step": 2620 }, { "grad_norm": 1.554461121559143, "learning_rate": 5.258000000000001e-05, "loss": 0.0569, "step": 2630 }, { "loss_action": 0.06348318606615067, "loss_total": 0.06348318606615067, "step": 2630 }, { "grad_norm": 1.248550534248352, "learning_rate": 5.2780000000000006e-05, "loss": 0.0568, "step": 2640 }, { "loss_action": 0.05288269743323326, "loss_total": 0.05288269743323326, "step": 2640 }, { "grad_norm": 1.2643455266952515, "learning_rate": 5.2980000000000004e-05, "loss": 0.0568, "step": 2650 }, { "loss_action": 0.047898486256599426, "loss_total": 0.047898486256599426, "step": 2650 }, { "grad_norm": 1.098006010055542, "learning_rate": 5.318000000000001e-05, "loss": 0.0521, "step": 2660 }, { "loss_action": 0.04552047327160835, "loss_total": 0.04552047327160835, "step": 2660 }, { "grad_norm": 1.182012677192688, "learning_rate": 5.338000000000001e-05, "loss": 0.0527, "step": 2670 }, { "loss_action": 0.044340118765830994, "loss_total": 0.044340118765830994, "step": 2670 }, { "grad_norm": 1.3922737836837769, "learning_rate": 5.3580000000000005e-05, "loss": 0.0524, "step": 2680 }, { "loss_action": 0.04975496232509613, "loss_total": 0.04975496232509613, "step": 2680 }, { "grad_norm": 1.5723977088928223, "learning_rate": 5.378e-05, "loss": 0.0528, "step": 2690 }, { "loss_action": 0.04674115777015686, "loss_total": 0.04674115777015686, "step": 2690 }, { "grad_norm": 1.5244803428649902, "learning_rate": 5.3979999999999995e-05, "loss": 0.0512, "step": 2700 }, { "loss_action": 0.0434361957013607, "loss_total": 0.0434361957013607, "step": 2700 }, { "grad_norm": 1.190733790397644, "learning_rate": 5.418e-05, "loss": 0.053, "step": 2710 }, { "loss_action": 0.06148817762732506, "loss_total": 0.06148817762732506, "step": 2710 }, { "grad_norm": 1.3483306169509888, "learning_rate": 5.438e-05, "loss": 0.0547, "step": 2720 }, { "loss_action": 0.052866969257593155, "loss_total": 0.052866969257593155, "step": 2720 }, { "grad_norm": 1.1637537479400635, "learning_rate": 5.4579999999999996e-05, "loss": 0.0507, "step": 2730 }, { "loss_action": 0.05549471825361252, "loss_total": 0.05549471825361252, "step": 2730 }, { "grad_norm": 1.4045825004577637, "learning_rate": 5.478e-05, "loss": 0.0562, "step": 2740 }, { "loss_action": 0.053489286452531815, "loss_total": 0.053489286452531815, "step": 2740 }, { "grad_norm": 1.3250538110733032, "learning_rate": 5.498e-05, "loss": 0.0571, "step": 2750 }, { "loss_action": 0.05768967419862747, "loss_total": 0.05768967419862747, "step": 2750 }, { "grad_norm": 1.3346456289291382, "learning_rate": 5.518e-05, "loss": 0.0524, "step": 2760 }, { "loss_action": 0.04285990819334984, "loss_total": 0.04285990819334984, "step": 2760 }, { "grad_norm": 1.4086995124816895, "learning_rate": 5.538e-05, "loss": 0.051, "step": 2770 }, { "loss_action": 0.05651700869202614, "loss_total": 0.05651700869202614, "step": 2770 }, { "grad_norm": 1.3783296346664429, "learning_rate": 5.558e-05, "loss": 0.0522, "step": 2780 }, { "loss_action": 0.04590579867362976, "loss_total": 0.04590579867362976, "step": 2780 }, { "grad_norm": 1.1774245500564575, "learning_rate": 5.578e-05, "loss": 0.0541, "step": 2790 }, { "loss_action": 0.04673144966363907, "loss_total": 0.04673144966363907, "step": 2790 }, { "grad_norm": 1.23768949508667, "learning_rate": 5.5979999999999996e-05, "loss": 0.0528, "step": 2800 }, { "loss_action": 0.05880303680896759, "loss_total": 0.05880303680896759, "step": 2800 }, { "grad_norm": 1.3712263107299805, "learning_rate": 5.618e-05, "loss": 0.0554, "step": 2810 }, { "loss_action": 0.05693726986646652, "loss_total": 0.05693726986646652, "step": 2810 }, { "grad_norm": 1.2623295783996582, "learning_rate": 5.638e-05, "loss": 0.0514, "step": 2820 }, { "loss_action": 0.05012288689613342, "loss_total": 0.05012288689613342, "step": 2820 }, { "grad_norm": 1.2424030303955078, "learning_rate": 5.658e-05, "loss": 0.0482, "step": 2830 }, { "loss_action": 0.05414658039808273, "loss_total": 0.05414658039808273, "step": 2830 }, { "grad_norm": 1.638231873512268, "learning_rate": 5.678e-05, "loss": 0.0546, "step": 2840 }, { "loss_action": 0.05674811825156212, "loss_total": 0.05674811825156212, "step": 2840 }, { "grad_norm": 1.2106937170028687, "learning_rate": 5.698e-05, "loss": 0.05, "step": 2850 }, { "loss_action": 0.0516153983771801, "loss_total": 0.0516153983771801, "step": 2850 }, { "grad_norm": 1.3184452056884766, "learning_rate": 5.718e-05, "loss": 0.0507, "step": 2860 }, { "loss_action": 0.047116439789533615, "loss_total": 0.047116439789533615, "step": 2860 }, { "grad_norm": 1.1747816801071167, "learning_rate": 5.738e-05, "loss": 0.0544, "step": 2870 }, { "loss_action": 0.05357819423079491, "loss_total": 0.05357819423079491, "step": 2870 }, { "grad_norm": 2.070795774459839, "learning_rate": 5.758e-05, "loss": 0.0565, "step": 2880 }, { "loss_action": 0.05274133384227753, "loss_total": 0.05274133384227753, "step": 2880 }, { "grad_norm": 1.5759369134902954, "learning_rate": 5.778e-05, "loss": 0.0574, "step": 2890 }, { "loss_action": 0.06340020149946213, "loss_total": 0.06340020149946213, "step": 2890 }, { "grad_norm": 1.533084750175476, "learning_rate": 5.7980000000000004e-05, "loss": 0.0527, "step": 2900 }, { "loss_action": 0.05398417264223099, "loss_total": 0.05398417264223099, "step": 2900 }, { "grad_norm": 1.3798346519470215, "learning_rate": 5.818e-05, "loss": 0.0527, "step": 2910 }, { "loss_action": 0.05896278843283653, "loss_total": 0.05896278843283653, "step": 2910 }, { "grad_norm": 1.2957497835159302, "learning_rate": 5.838e-05, "loss": 0.0544, "step": 2920 }, { "loss_action": 0.060649093240499496, "loss_total": 0.060649093240499496, "step": 2920 }, { "grad_norm": 1.2702749967575073, "learning_rate": 5.858e-05, "loss": 0.0527, "step": 2930 }, { "loss_action": 0.05355320870876312, "loss_total": 0.05355320870876312, "step": 2930 }, { "grad_norm": 1.3492944240570068, "learning_rate": 5.878e-05, "loss": 0.0537, "step": 2940 }, { "loss_action": 0.040663544088602066, "loss_total": 0.040663544088602066, "step": 2940 }, { "grad_norm": 1.3357480764389038, "learning_rate": 5.898e-05, "loss": 0.0496, "step": 2950 }, { "loss_action": 0.049415040761232376, "loss_total": 0.049415040761232376, "step": 2950 }, { "grad_norm": 1.283063530921936, "learning_rate": 5.918e-05, "loss": 0.0523, "step": 2960 }, { "loss_action": 0.048496343195438385, "loss_total": 0.048496343195438385, "step": 2960 }, { "grad_norm": 1.5952855348587036, "learning_rate": 5.9380000000000004e-05, "loss": 0.055, "step": 2970 }, { "loss_action": 0.05112611502408981, "loss_total": 0.05112611502408981, "step": 2970 }, { "grad_norm": 0.8211349248886108, "learning_rate": 5.958e-05, "loss": 0.0497, "step": 2980 }, { "loss_action": 0.048722535371780396, "loss_total": 0.048722535371780396, "step": 2980 }, { "grad_norm": 1.3120685815811157, "learning_rate": 5.978e-05, "loss": 0.0464, "step": 2990 }, { "loss_action": 0.06038803607225418, "loss_total": 0.06038803607225418, "step": 2990 }, { "grad_norm": 1.143944501876831, "learning_rate": 5.9980000000000005e-05, "loss": 0.0477, "step": 3000 }, { "loss_action": 0.05882890522480011, "loss_total": 0.05882890522480011, "step": 3000 }, { "grad_norm": 1.4320844411849976, "learning_rate": 6.018e-05, "loss": 0.0517, "step": 3010 }, { "loss_action": 0.047893162816762924, "loss_total": 0.047893162816762924, "step": 3010 }, { "grad_norm": 1.387548565864563, "learning_rate": 6.038e-05, "loss": 0.0505, "step": 3020 }, { "loss_action": 0.0371730737388134, "loss_total": 0.0371730737388134, "step": 3020 }, { "grad_norm": 1.3040847778320312, "learning_rate": 6.0580000000000006e-05, "loss": 0.0472, "step": 3030 }, { "loss_action": 0.045233435928821564, "loss_total": 0.045233435928821564, "step": 3030 }, { "grad_norm": 1.2813644409179688, "learning_rate": 6.0780000000000004e-05, "loss": 0.0512, "step": 3040 }, { "loss_action": 0.04326876997947693, "loss_total": 0.04326876997947693, "step": 3040 }, { "grad_norm": 1.1319472789764404, "learning_rate": 6.098e-05, "loss": 0.051, "step": 3050 }, { "loss_action": 0.04399822652339935, "loss_total": 0.04399822652339935, "step": 3050 }, { "grad_norm": 1.3394668102264404, "learning_rate": 6.118000000000001e-05, "loss": 0.0486, "step": 3060 }, { "loss_action": 0.057486023753881454, "loss_total": 0.057486023753881454, "step": 3060 }, { "grad_norm": 1.1155893802642822, "learning_rate": 6.138e-05, "loss": 0.0527, "step": 3070 }, { "loss_action": 0.04877787083387375, "loss_total": 0.04877787083387375, "step": 3070 }, { "grad_norm": 1.0794446468353271, "learning_rate": 6.158e-05, "loss": 0.0507, "step": 3080 }, { "loss_action": 0.040887314826250076, "loss_total": 0.040887314826250076, "step": 3080 }, { "grad_norm": 1.1161596775054932, "learning_rate": 6.178000000000001e-05, "loss": 0.0481, "step": 3090 }, { "loss_action": 0.04387206956744194, "loss_total": 0.04387206956744194, "step": 3090 }, { "grad_norm": 1.451738715171814, "learning_rate": 6.198e-05, "loss": 0.0495, "step": 3100 }, { "loss_action": 0.05355067923665047, "loss_total": 0.05355067923665047, "step": 3100 }, { "grad_norm": 1.075186014175415, "learning_rate": 6.218e-05, "loss": 0.0488, "step": 3110 }, { "loss_action": 0.039786674082279205, "loss_total": 0.039786674082279205, "step": 3110 }, { "grad_norm": 1.0155922174453735, "learning_rate": 6.238000000000001e-05, "loss": 0.045, "step": 3120 }, { "loss_action": 0.04742589592933655, "loss_total": 0.04742589592933655, "step": 3120 }, { "grad_norm": 1.2095022201538086, "learning_rate": 6.258e-05, "loss": 0.0448, "step": 3130 }, { "loss_action": 0.04756271466612816, "loss_total": 0.04756271466612816, "step": 3130 }, { "grad_norm": 1.1946606636047363, "learning_rate": 6.278e-05, "loss": 0.0508, "step": 3140 }, { "loss_action": 0.04634314030408859, "loss_total": 0.04634314030408859, "step": 3140 }, { "grad_norm": 1.1373172998428345, "learning_rate": 6.298000000000001e-05, "loss": 0.0506, "step": 3150 }, { "loss_action": 0.04449659213423729, "loss_total": 0.04449659213423729, "step": 3150 }, { "grad_norm": 1.1127740144729614, "learning_rate": 6.318e-05, "loss": 0.045, "step": 3160 }, { "loss_action": 0.04093267023563385, "loss_total": 0.04093267023563385, "step": 3160 }, { "grad_norm": 1.1585478782653809, "learning_rate": 6.338e-05, "loss": 0.0446, "step": 3170 }, { "loss_action": 0.05572154000401497, "loss_total": 0.05572154000401497, "step": 3170 }, { "grad_norm": 1.270904541015625, "learning_rate": 6.358000000000001e-05, "loss": 0.0487, "step": 3180 }, { "loss_action": 0.0397467166185379, "loss_total": 0.0397467166185379, "step": 3180 }, { "grad_norm": 1.0173591375350952, "learning_rate": 6.378e-05, "loss": 0.0473, "step": 3190 }, { "loss_action": 0.04635303467512131, "loss_total": 0.04635303467512131, "step": 3190 }, { "grad_norm": 0.8886622786521912, "learning_rate": 6.398000000000001e-05, "loss": 0.0469, "step": 3200 }, { "loss_action": 0.05705932155251503, "loss_total": 0.05705932155251503, "step": 3200 }, { "grad_norm": 0.9440981149673462, "learning_rate": 6.418000000000001e-05, "loss": 0.048, "step": 3210 }, { "loss_action": 0.04071546345949173, "loss_total": 0.04071546345949173, "step": 3210 }, { "grad_norm": 1.504152774810791, "learning_rate": 6.438e-05, "loss": 0.0513, "step": 3220 }, { "loss_action": 0.058343905955553055, "loss_total": 0.058343905955553055, "step": 3220 }, { "grad_norm": 2.3357815742492676, "learning_rate": 6.458000000000001e-05, "loss": 0.0798, "step": 3230 }, { "loss_action": 0.06938778609037399, "loss_total": 0.06938778609037399, "step": 3230 }, { "grad_norm": 1.3360378742218018, "learning_rate": 6.478000000000001e-05, "loss": 0.0813, "step": 3240 }, { "loss_action": 0.09129434078931808, "loss_total": 0.09129434078931808, "step": 3240 }, { "grad_norm": 1.291885256767273, "learning_rate": 6.498e-05, "loss": 0.0708, "step": 3250 }, { "loss_action": 0.07097684592008591, "loss_total": 0.07097684592008591, "step": 3250 }, { "grad_norm": 1.107508897781372, "learning_rate": 6.518000000000001e-05, "loss": 0.0612, "step": 3260 }, { "loss_action": 0.06097017973661423, "loss_total": 0.06097017973661423, "step": 3260 }, { "grad_norm": 0.9178004264831543, "learning_rate": 6.538000000000001e-05, "loss": 0.0576, "step": 3270 }, { "loss_action": 0.05889541655778885, "loss_total": 0.05889541655778885, "step": 3270 }, { "grad_norm": 1.1025047302246094, "learning_rate": 6.558e-05, "loss": 0.054, "step": 3280 }, { "loss_action": 0.06024333834648132, "loss_total": 0.06024333834648132, "step": 3280 }, { "grad_norm": 0.9439118504524231, "learning_rate": 6.578000000000001e-05, "loss": 0.0513, "step": 3290 }, { "loss_action": 0.054549507796764374, "loss_total": 0.054549507796764374, "step": 3290 }, { "grad_norm": 1.181992530822754, "learning_rate": 6.598e-05, "loss": 0.0767, "step": 3300 }, { "loss_action": 0.057641275227069855, "loss_total": 0.057641275227069855, "step": 3300 }, { "grad_norm": 1.0153528451919556, "learning_rate": 6.618e-05, "loss": 0.0616, "step": 3310 }, { "loss_action": 0.05985981598496437, "loss_total": 0.05985981598496437, "step": 3310 }, { "grad_norm": 1.1689457893371582, "learning_rate": 6.638e-05, "loss": 0.0592, "step": 3320 }, { "loss_action": 0.0477900430560112, "loss_total": 0.0477900430560112, "step": 3320 }, { "grad_norm": 1.2638918161392212, "learning_rate": 6.658e-05, "loss": 0.0517, "step": 3330 }, { "loss_action": 0.04419568553566933, "loss_total": 0.04419568553566933, "step": 3330 }, { "grad_norm": 1.1941804885864258, "learning_rate": 6.678e-05, "loss": 0.0483, "step": 3340 }, { "loss_action": 0.06179872155189514, "loss_total": 0.06179872155189514, "step": 3340 }, { "grad_norm": 1.1420730352401733, "learning_rate": 6.698e-05, "loss": 0.0524, "step": 3350 }, { "loss_action": 0.04497480392456055, "loss_total": 0.04497480392456055, "step": 3350 }, { "grad_norm": 0.9652194976806641, "learning_rate": 6.718e-05, "loss": 0.0561, "step": 3360 }, { "loss_action": 0.05564774572849274, "loss_total": 0.05564774572849274, "step": 3360 }, { "grad_norm": 1.192496418952942, "learning_rate": 6.738e-05, "loss": 0.0543, "step": 3370 }, { "loss_action": 0.06388581544160843, "loss_total": 0.06388581544160843, "step": 3370 }, { "grad_norm": 1.0206984281539917, "learning_rate": 6.758e-05, "loss": 0.0535, "step": 3380 }, { "loss_action": 0.05056721344590187, "loss_total": 0.05056721344590187, "step": 3380 }, { "grad_norm": 1.3853693008422852, "learning_rate": 6.778e-05, "loss": 0.0524, "step": 3390 }, { "loss_action": 0.04225834086537361, "loss_total": 0.04225834086537361, "step": 3390 }, { "grad_norm": 0.8586239218711853, "learning_rate": 6.798e-05, "loss": 0.0446, "step": 3400 }, { "loss_action": 0.05128650367259979, "loss_total": 0.05128650367259979, "step": 3400 }, { "grad_norm": 0.979119598865509, "learning_rate": 6.818e-05, "loss": 0.0488, "step": 3410 }, { "loss_action": 0.04104115813970566, "loss_total": 0.04104115813970566, "step": 3410 }, { "grad_norm": 1.017946720123291, "learning_rate": 6.838e-05, "loss": 0.049, "step": 3420 }, { "loss_action": 0.049309246242046356, "loss_total": 0.049309246242046356, "step": 3420 }, { "grad_norm": 1.1691383123397827, "learning_rate": 6.858e-05, "loss": 0.0493, "step": 3430 }, { "loss_action": 0.04158820956945419, "loss_total": 0.04158820956945419, "step": 3430 }, { "grad_norm": 1.0174580812454224, "learning_rate": 6.878e-05, "loss": 0.0472, "step": 3440 }, { "loss_action": 0.055100876837968826, "loss_total": 0.055100876837968826, "step": 3440 }, { "grad_norm": 1.116247534751892, "learning_rate": 6.898e-05, "loss": 0.0501, "step": 3450 }, { "loss_action": 0.059492532163858414, "loss_total": 0.059492532163858414, "step": 3450 }, { "grad_norm": 0.9501627087593079, "learning_rate": 6.918e-05, "loss": 0.048, "step": 3460 }, { "loss_action": 0.04587392508983612, "loss_total": 0.04587392508983612, "step": 3460 }, { "grad_norm": 1.1375137567520142, "learning_rate": 6.938e-05, "loss": 0.0473, "step": 3470 }, { "loss_action": 0.045865993946790695, "loss_total": 0.045865993946790695, "step": 3470 }, { "grad_norm": 0.882577121257782, "learning_rate": 6.958e-05, "loss": 0.0509, "step": 3480 }, { "loss_action": 0.05010788515210152, "loss_total": 0.05010788515210152, "step": 3480 }, { "grad_norm": 1.0051085948944092, "learning_rate": 6.978e-05, "loss": 0.0473, "step": 3490 }, { "loss_action": 0.04567313194274902, "loss_total": 0.04567313194274902, "step": 3490 }, { "grad_norm": 1.0361500978469849, "learning_rate": 6.998e-05, "loss": 0.0427, "step": 3500 }, { "loss_action": 0.04230278357863426, "loss_total": 0.04230278357863426, "step": 3500 }, { "grad_norm": 1.022584080696106, "learning_rate": 7.018e-05, "loss": 0.0445, "step": 3510 }, { "loss_action": 0.039147358387708664, "loss_total": 0.039147358387708664, "step": 3510 }, { "grad_norm": 1.099564790725708, "learning_rate": 7.038e-05, "loss": 0.0453, "step": 3520 }, { "loss_action": 0.03989114239811897, "loss_total": 0.03989114239811897, "step": 3520 }, { "grad_norm": 1.1489535570144653, "learning_rate": 7.058e-05, "loss": 0.048, "step": 3530 }, { "loss_action": 0.055263716727495193, "loss_total": 0.055263716727495193, "step": 3530 }, { "grad_norm": 0.8449605107307434, "learning_rate": 7.078e-05, "loss": 0.0477, "step": 3540 }, { "loss_action": 0.055269237607717514, "loss_total": 0.055269237607717514, "step": 3540 }, { "grad_norm": 1.0608875751495361, "learning_rate": 7.098e-05, "loss": 0.0448, "step": 3550 }, { "loss_action": 0.045746784657239914, "loss_total": 0.045746784657239914, "step": 3550 }, { "grad_norm": 1.0757969617843628, "learning_rate": 7.118e-05, "loss": 0.0445, "step": 3560 }, { "loss_action": 0.04664645716547966, "loss_total": 0.04664645716547966, "step": 3560 }, { "grad_norm": 1.1054890155792236, "learning_rate": 7.138e-05, "loss": 0.0445, "step": 3570 }, { "loss_action": 0.03715520352125168, "loss_total": 0.03715520352125168, "step": 3570 }, { "grad_norm": 1.016849160194397, "learning_rate": 7.158e-05, "loss": 0.0429, "step": 3580 }, { "loss_action": 0.04204292595386505, "loss_total": 0.04204292595386505, "step": 3580 }, { "grad_norm": 1.1718577146530151, "learning_rate": 7.178000000000001e-05, "loss": 0.0449, "step": 3590 }, { "loss_action": 0.05045174062252045, "loss_total": 0.05045174062252045, "step": 3590 }, { "grad_norm": 1.073835015296936, "learning_rate": 7.198e-05, "loss": 0.0484, "step": 3600 }, { "loss_action": 0.045567892491817474, "loss_total": 0.045567892491817474, "step": 3600 }, { "grad_norm": 0.9979596734046936, "learning_rate": 7.218e-05, "loss": 0.0434, "step": 3610 }, { "loss_action": 0.050986532121896744, "loss_total": 0.050986532121896744, "step": 3610 }, { "grad_norm": 0.9368095993995667, "learning_rate": 7.238000000000001e-05, "loss": 0.0489, "step": 3620 }, { "loss_action": 0.04610009491443634, "loss_total": 0.04610009491443634, "step": 3620 }, { "grad_norm": 1.2954505681991577, "learning_rate": 7.258e-05, "loss": 0.0438, "step": 3630 }, { "loss_action": 0.0574728287756443, "loss_total": 0.0574728287756443, "step": 3630 }, { "grad_norm": 0.8944570422172546, "learning_rate": 7.278e-05, "loss": 0.0476, "step": 3640 }, { "loss_action": 0.051436666399240494, "loss_total": 0.051436666399240494, "step": 3640 }, { "grad_norm": 0.9427154064178467, "learning_rate": 7.298000000000001e-05, "loss": 0.0432, "step": 3650 }, { "loss_action": 0.043551091104745865, "loss_total": 0.043551091104745865, "step": 3650 }, { "grad_norm": 1.121928095817566, "learning_rate": 7.318e-05, "loss": 0.0443, "step": 3660 }, { "loss_action": 0.053531136363744736, "loss_total": 0.053531136363744736, "step": 3660 }, { "grad_norm": 0.9556861519813538, "learning_rate": 7.338e-05, "loss": 0.0437, "step": 3670 }, { "loss_action": 0.03724793717265129, "loss_total": 0.03724793717265129, "step": 3670 }, { "grad_norm": 1.1412627696990967, "learning_rate": 7.358000000000001e-05, "loss": 0.0495, "step": 3680 }, { "loss_action": 0.07027160376310349, "loss_total": 0.07027160376310349, "step": 3680 }, { "grad_norm": 1.2996984720230103, "learning_rate": 7.378e-05, "loss": 0.0571, "step": 3690 }, { "loss_action": 0.05780141055583954, "loss_total": 0.05780141055583954, "step": 3690 }, { "grad_norm": 1.3298931121826172, "learning_rate": 7.398e-05, "loss": 0.0539, "step": 3700 }, { "loss_action": 0.05190359055995941, "loss_total": 0.05190359055995941, "step": 3700 }, { "grad_norm": 0.9224073886871338, "learning_rate": 7.418000000000001e-05, "loss": 0.0536, "step": 3710 }, { "loss_action": 0.04605992138385773, "loss_total": 0.04605992138385773, "step": 3710 }, { "grad_norm": 1.0323809385299683, "learning_rate": 7.438e-05, "loss": 0.0443, "step": 3720 }, { "loss_action": 0.05210709944367409, "loss_total": 0.05210709944367409, "step": 3720 }, { "grad_norm": 1.0605674982070923, "learning_rate": 7.458000000000001e-05, "loss": 0.048, "step": 3730 }, { "loss_action": 0.0405845008790493, "loss_total": 0.0405845008790493, "step": 3730 }, { "grad_norm": 1.1758863925933838, "learning_rate": 7.478e-05, "loss": 0.0448, "step": 3740 }, { "loss_action": 0.04331701621413231, "loss_total": 0.04331701621413231, "step": 3740 }, { "grad_norm": 0.933638870716095, "learning_rate": 7.498e-05, "loss": 0.0457, "step": 3750 }, { "loss_action": 0.04356436803936958, "loss_total": 0.04356436803936958, "step": 3750 }, { "grad_norm": 0.9689655303955078, "learning_rate": 7.518000000000001e-05, "loss": 0.0484, "step": 3760 }, { "loss_action": 0.05705331265926361, "loss_total": 0.05705331265926361, "step": 3760 }, { "grad_norm": 1.0438289642333984, "learning_rate": 7.538e-05, "loss": 0.0548, "step": 3770 }, { "loss_action": 0.04977917671203613, "loss_total": 0.04977917671203613, "step": 3770 }, { "grad_norm": 1.0783162117004395, "learning_rate": 7.558e-05, "loss": 0.0495, "step": 3780 }, { "loss_action": 0.048404596745967865, "loss_total": 0.048404596745967865, "step": 3780 }, { "grad_norm": 1.0043565034866333, "learning_rate": 7.578000000000001e-05, "loss": 0.049, "step": 3790 }, { "loss_action": 0.047656554728746414, "loss_total": 0.047656554728746414, "step": 3790 }, { "grad_norm": 0.945372998714447, "learning_rate": 7.598e-05, "loss": 0.0484, "step": 3800 }, { "loss_action": 0.04197985678911209, "loss_total": 0.04197985678911209, "step": 3800 }, { "grad_norm": 1.314452052116394, "learning_rate": 7.618e-05, "loss": 0.0505, "step": 3810 }, { "loss_action": 0.06589382141828537, "loss_total": 0.06589382141828537, "step": 3810 }, { "grad_norm": 1.4150222539901733, "learning_rate": 7.638000000000001e-05, "loss": 0.0585, "step": 3820 }, { "loss_action": 0.0582902692258358, "loss_total": 0.0582902692258358, "step": 3820 }, { "grad_norm": 0.6799286007881165, "learning_rate": 7.658e-05, "loss": 0.0528, "step": 3830 }, { "loss_action": 0.06108684837818146, "loss_total": 0.06108684837818146, "step": 3830 }, { "grad_norm": 0.9018051028251648, "learning_rate": 7.678000000000001e-05, "loss": 0.0495, "step": 3840 }, { "loss_action": 0.043385665863752365, "loss_total": 0.043385665863752365, "step": 3840 }, { "grad_norm": 1.002820372581482, "learning_rate": 7.698000000000001e-05, "loss": 0.0473, "step": 3850 }, { "loss_action": 0.04745766520500183, "loss_total": 0.04745766520500183, "step": 3850 }, { "grad_norm": 0.8426774740219116, "learning_rate": 7.718e-05, "loss": 0.0433, "step": 3860 }, { "loss_action": 0.05013229325413704, "loss_total": 0.05013229325413704, "step": 3860 }, { "grad_norm": 1.0984179973602295, "learning_rate": 7.738000000000001e-05, "loss": 0.0448, "step": 3870 }, { "loss_action": 0.04269425570964813, "loss_total": 0.04269425570964813, "step": 3870 }, { "grad_norm": 0.7947925329208374, "learning_rate": 7.758000000000001e-05, "loss": 0.0417, "step": 3880 }, { "loss_action": 0.059621863067150116, "loss_total": 0.059621863067150116, "step": 3880 }, { "grad_norm": 0.7511692643165588, "learning_rate": 7.778e-05, "loss": 0.0421, "step": 3890 }, { "loss_action": 0.04971357807517052, "loss_total": 0.04971357807517052, "step": 3890 }, { "grad_norm": 0.8251156210899353, "learning_rate": 7.798000000000001e-05, "loss": 0.0423, "step": 3900 }, { "loss_action": 0.04508983716368675, "loss_total": 0.04508983716368675, "step": 3900 }, { "grad_norm": 1.1494650840759277, "learning_rate": 7.818000000000001e-05, "loss": 0.046, "step": 3910 }, { "loss_action": 0.04070013016462326, "loss_total": 0.04070013016462326, "step": 3910 }, { "grad_norm": 1.2271144390106201, "learning_rate": 7.838e-05, "loss": 0.0489, "step": 3920 }, { "loss_action": 0.048708342015743256, "loss_total": 0.048708342015743256, "step": 3920 }, { "grad_norm": 1.1165823936462402, "learning_rate": 7.858000000000001e-05, "loss": 0.0466, "step": 3930 }, { "loss_action": 0.04439360275864601, "loss_total": 0.04439360275864601, "step": 3930 }, { "grad_norm": 0.9720523357391357, "learning_rate": 7.878e-05, "loss": 0.0417, "step": 3940 }, { "loss_action": 0.04643682762980461, "loss_total": 0.04643682762980461, "step": 3940 }, { "grad_norm": 1.321682095527649, "learning_rate": 7.897999999999999e-05, "loss": 0.0489, "step": 3950 }, { "loss_action": 0.048870332539081573, "loss_total": 0.048870332539081573, "step": 3950 }, { "grad_norm": 1.0869454145431519, "learning_rate": 7.918e-05, "loss": 0.0477, "step": 3960 }, { "loss_action": 0.055211279541254044, "loss_total": 0.055211279541254044, "step": 3960 }, { "grad_norm": 0.6722338199615479, "learning_rate": 7.938e-05, "loss": 0.043, "step": 3970 }, { "loss_action": 0.03831788897514343, "loss_total": 0.03831788897514343, "step": 3970 }, { "grad_norm": 0.9929181933403015, "learning_rate": 7.958e-05, "loss": 0.0404, "step": 3980 }, { "loss_action": 0.0551152229309082, "loss_total": 0.0551152229309082, "step": 3980 }, { "grad_norm": 0.9611337184906006, "learning_rate": 7.978e-05, "loss": 0.0432, "step": 3990 }, { "loss_action": 0.04119803383946419, "loss_total": 0.04119803383946419, "step": 3990 }, { "grad_norm": 0.8499287962913513, "learning_rate": 7.998e-05, "loss": 0.0375, "step": 4000 }, { "loss_action": 0.036461178213357925, "loss_total": 0.036461178213357925, "step": 4000 }, { "grad_norm": 0.9032295346260071, "learning_rate": 8.018e-05, "loss": 0.0354, "step": 4010 }, { "loss_action": 0.039443157613277435, "loss_total": 0.039443157613277435, "step": 4010 }, { "grad_norm": 0.8544635772705078, "learning_rate": 8.038e-05, "loss": 0.0396, "step": 4020 }, { "loss_action": 0.04078374803066254, "loss_total": 0.04078374803066254, "step": 4020 }, { "grad_norm": 1.0259153842926025, "learning_rate": 8.058e-05, "loss": 0.0414, "step": 4030 }, { "loss_action": 0.03739152103662491, "loss_total": 0.03739152103662491, "step": 4030 }, { "grad_norm": 0.9066490530967712, "learning_rate": 8.078e-05, "loss": 0.044, "step": 4040 }, { "loss_action": 0.03819442540407181, "loss_total": 0.03819442540407181, "step": 4040 }, { "grad_norm": 1.1795151233673096, "learning_rate": 8.098e-05, "loss": 0.0446, "step": 4050 }, { "loss_action": 0.04015308991074562, "loss_total": 0.04015308991074562, "step": 4050 }, { "grad_norm": 0.7802818417549133, "learning_rate": 8.118e-05, "loss": 0.0443, "step": 4060 }, { "loss_action": 0.04935809597373009, "loss_total": 0.04935809597373009, "step": 4060 }, { "grad_norm": 0.876537561416626, "learning_rate": 8.138e-05, "loss": 0.0435, "step": 4070 }, { "loss_action": 0.0539872981607914, "loss_total": 0.0539872981607914, "step": 4070 }, { "grad_norm": 0.8419002294540405, "learning_rate": 8.158e-05, "loss": 0.0439, "step": 4080 }, { "loss_action": 0.04847867414355278, "loss_total": 0.04847867414355278, "step": 4080 }, { "grad_norm": 1.289270281791687, "learning_rate": 8.178e-05, "loss": 0.0478, "step": 4090 }, { "loss_action": 0.04160299152135849, "loss_total": 0.04160299152135849, "step": 4090 }, { "grad_norm": 1.0522778034210205, "learning_rate": 8.198e-05, "loss": 0.0448, "step": 4100 }, { "loss_action": 0.041908860206604004, "loss_total": 0.041908860206604004, "step": 4100 }, { "grad_norm": 0.8856430649757385, "learning_rate": 8.218e-05, "loss": 0.0419, "step": 4110 }, { "loss_action": 0.04056835174560547, "loss_total": 0.04056835174560547, "step": 4110 }, { "grad_norm": 0.9677079916000366, "learning_rate": 8.238000000000001e-05, "loss": 0.0436, "step": 4120 }, { "loss_action": 0.03889242932200432, "loss_total": 0.03889242932200432, "step": 4120 }, { "grad_norm": 0.9178104996681213, "learning_rate": 8.258e-05, "loss": 0.0423, "step": 4130 }, { "loss_action": 0.04174230247735977, "loss_total": 0.04174230247735977, "step": 4130 }, { "grad_norm": 1.1241538524627686, "learning_rate": 8.278e-05, "loss": 0.0421, "step": 4140 }, { "loss_action": 0.04724230244755745, "loss_total": 0.04724230244755745, "step": 4140 }, { "grad_norm": 0.7922537922859192, "learning_rate": 8.298000000000001e-05, "loss": 0.0448, "step": 4150 }, { "loss_action": 0.04283718392252922, "loss_total": 0.04283718392252922, "step": 4150 }, { "grad_norm": 0.8788889646530151, "learning_rate": 8.318e-05, "loss": 0.0394, "step": 4160 }, { "loss_action": 0.03653073310852051, "loss_total": 0.03653073310852051, "step": 4160 }, { "grad_norm": 1.1295427083969116, "learning_rate": 8.338e-05, "loss": 0.038, "step": 4170 }, { "loss_action": 0.04369137063622475, "loss_total": 0.04369137063622475, "step": 4170 }, { "grad_norm": 1.0346871614456177, "learning_rate": 8.358e-05, "loss": 0.0424, "step": 4180 }, { "loss_action": 0.042922042310237885, "loss_total": 0.042922042310237885, "step": 4180 }, { "grad_norm": 0.6139446496963501, "learning_rate": 8.378e-05, "loss": 0.0351, "step": 4190 }, { "loss_action": 0.046601083129644394, "loss_total": 0.046601083129644394, "step": 4190 }, { "grad_norm": 0.8741772174835205, "learning_rate": 8.398e-05, "loss": 0.0356, "step": 4200 }, { "loss_action": 0.03899035230278969, "loss_total": 0.03899035230278969, "step": 4200 }, { "grad_norm": 0.8331954479217529, "learning_rate": 8.418e-05, "loss": 0.0358, "step": 4210 }, { "loss_action": 0.035592351108789444, "loss_total": 0.035592351108789444, "step": 4210 }, { "grad_norm": 1.1136059761047363, "learning_rate": 8.438e-05, "loss": 0.0378, "step": 4220 }, { "loss_action": 0.0469246432185173, "loss_total": 0.0469246432185173, "step": 4220 }, { "grad_norm": 0.8049380779266357, "learning_rate": 8.458e-05, "loss": 0.0423, "step": 4230 }, { "loss_action": 0.03150762990117073, "loss_total": 0.03150762990117073, "step": 4230 }, { "grad_norm": 0.9574014544487, "learning_rate": 8.478e-05, "loss": 0.0381, "step": 4240 }, { "loss_action": 0.04758472740650177, "loss_total": 0.04758472740650177, "step": 4240 }, { "grad_norm": 0.8596657514572144, "learning_rate": 8.498e-05, "loss": 0.042, "step": 4250 }, { "loss_action": 0.04014978185296059, "loss_total": 0.04014978185296059, "step": 4250 }, { "grad_norm": 1.3178608417510986, "learning_rate": 8.518000000000001e-05, "loss": 0.0403, "step": 4260 }, { "loss_action": 0.03919956460595131, "loss_total": 0.03919956460595131, "step": 4260 }, { "grad_norm": 0.9658582806587219, "learning_rate": 8.538e-05, "loss": 0.0394, "step": 4270 }, { "loss_action": 0.03281707689166069, "loss_total": 0.03281707689166069, "step": 4270 }, { "grad_norm": 1.184316873550415, "learning_rate": 8.558e-05, "loss": 0.0381, "step": 4280 }, { "loss_action": 0.04427772015333176, "loss_total": 0.04427772015333176, "step": 4280 }, { "grad_norm": 0.7410631775856018, "learning_rate": 8.578000000000001e-05, "loss": 0.0396, "step": 4290 }, { "loss_action": 0.032237403094768524, "loss_total": 0.032237403094768524, "step": 4290 }, { "grad_norm": 1.1259098052978516, "learning_rate": 8.598e-05, "loss": 0.0342, "step": 4300 }, { "loss_action": 0.04153436794877052, "loss_total": 0.04153436794877052, "step": 4300 }, { "grad_norm": 0.887586236000061, "learning_rate": 8.618e-05, "loss": 0.0428, "step": 4310 }, { "loss_action": 0.05578124150633812, "loss_total": 0.05578124150633812, "step": 4310 }, { "grad_norm": 0.6835507154464722, "learning_rate": 8.638000000000001e-05, "loss": 0.0425, "step": 4320 }, { "loss_action": 0.03947470709681511, "loss_total": 0.03947470709681511, "step": 4320 }, { "grad_norm": 0.6541295647621155, "learning_rate": 8.658e-05, "loss": 0.0406, "step": 4330 }, { "loss_action": 0.031924400478601456, "loss_total": 0.031924400478601456, "step": 4330 }, { "grad_norm": 0.9940209984779358, "learning_rate": 8.678e-05, "loss": 0.0394, "step": 4340 }, { "loss_action": 0.03560418635606766, "loss_total": 0.03560418635606766, "step": 4340 }, { "grad_norm": 0.6555806994438171, "learning_rate": 8.698000000000001e-05, "loss": 0.0359, "step": 4350 }, { "loss_action": 0.03643739968538284, "loss_total": 0.03643739968538284, "step": 4350 }, { "grad_norm": 0.8461087942123413, "learning_rate": 8.718e-05, "loss": 0.0365, "step": 4360 }, { "loss_action": 0.034566521644592285, "loss_total": 0.034566521644592285, "step": 4360 }, { "grad_norm": 0.8831172585487366, "learning_rate": 8.738000000000001e-05, "loss": 0.0357, "step": 4370 }, { "loss_action": 0.03605707362294197, "loss_total": 0.03605707362294197, "step": 4370 }, { "grad_norm": 0.7175894379615784, "learning_rate": 8.758000000000001e-05, "loss": 0.0336, "step": 4380 }, { "loss_action": 0.037020448595285416, "loss_total": 0.037020448595285416, "step": 4380 }, { "grad_norm": 0.9986705780029297, "learning_rate": 8.778e-05, "loss": 0.0424, "step": 4390 }, { "loss_action": 0.036156266927719116, "loss_total": 0.036156266927719116, "step": 4390 }, { "grad_norm": 0.7535983920097351, "learning_rate": 8.798000000000001e-05, "loss": 0.0381, "step": 4400 }, { "loss_action": 0.02978467009961605, "loss_total": 0.02978467009961605, "step": 4400 }, { "grad_norm": 0.8375895023345947, "learning_rate": 8.818000000000001e-05, "loss": 0.0383, "step": 4410 }, { "loss_action": 0.035162296146154404, "loss_total": 0.035162296146154404, "step": 4410 }, { "grad_norm": 1.0281662940979004, "learning_rate": 8.838e-05, "loss": 0.0377, "step": 4420 }, { "loss_action": 0.03300553932785988, "loss_total": 0.03300553932785988, "step": 4420 }, { "grad_norm": 1.0318933725357056, "learning_rate": 8.858000000000001e-05, "loss": 0.0406, "step": 4430 }, { "loss_action": 0.038457926362752914, "loss_total": 0.038457926362752914, "step": 4430 }, { "grad_norm": 0.8356506824493408, "learning_rate": 8.878000000000001e-05, "loss": 0.0395, "step": 4440 }, { "loss_action": 0.0485217310488224, "loss_total": 0.0485217310488224, "step": 4440 }, { "grad_norm": 0.6549805402755737, "learning_rate": 8.898e-05, "loss": 0.0374, "step": 4450 }, { "loss_action": 0.03748388588428497, "loss_total": 0.03748388588428497, "step": 4450 }, { "grad_norm": 1.0687202215194702, "learning_rate": 8.918000000000001e-05, "loss": 0.0369, "step": 4460 }, { "loss_action": 0.05345309153199196, "loss_total": 0.05345309153199196, "step": 4460 }, { "grad_norm": 0.8094319105148315, "learning_rate": 8.938e-05, "loss": 0.0384, "step": 4470 }, { "loss_action": 0.037022821605205536, "loss_total": 0.037022821605205536, "step": 4470 }, { "grad_norm": 1.0798550844192505, "learning_rate": 8.958e-05, "loss": 0.0393, "step": 4480 }, { "loss_action": 0.043276723474264145, "loss_total": 0.043276723474264145, "step": 4480 }, { "grad_norm": 0.6950423717498779, "learning_rate": 8.978000000000001e-05, "loss": 0.0425, "step": 4490 }, { "loss_action": 0.03946267068386078, "loss_total": 0.03946267068386078, "step": 4490 }, { "grad_norm": 0.7302269339561462, "learning_rate": 8.998e-05, "loss": 0.041, "step": 4500 }, { "loss_action": 0.04120643064379692, "loss_total": 0.04120643064379692, "step": 4500 }, { "grad_norm": 0.823352575302124, "learning_rate": 9.018000000000001e-05, "loss": 0.0406, "step": 4510 }, { "loss_action": 0.03678962588310242, "loss_total": 0.03678962588310242, "step": 4510 }, { "grad_norm": 1.012710690498352, "learning_rate": 9.038000000000001e-05, "loss": 0.0395, "step": 4520 }, { "loss_action": 0.04622800648212433, "loss_total": 0.04622800648212433, "step": 4520 }, { "grad_norm": 0.8594368100166321, "learning_rate": 9.058e-05, "loss": 0.0374, "step": 4530 }, { "loss_action": 0.0317169614136219, "loss_total": 0.0317169614136219, "step": 4530 }, { "grad_norm": 1.0729987621307373, "learning_rate": 9.078000000000001e-05, "loss": 0.0412, "step": 4540 }, { "loss_action": 0.02798634022474289, "loss_total": 0.02798634022474289, "step": 4540 }, { "grad_norm": 0.8086193799972534, "learning_rate": 9.098000000000001e-05, "loss": 0.0392, "step": 4550 }, { "loss_action": 0.033736325800418854, "loss_total": 0.033736325800418854, "step": 4550 }, { "grad_norm": 0.8837514519691467, "learning_rate": 9.118e-05, "loss": 0.0412, "step": 4560 }, { "loss_action": 0.04445977509021759, "loss_total": 0.04445977509021759, "step": 4560 }, { "grad_norm": 0.8987725377082825, "learning_rate": 9.138e-05, "loss": 0.0388, "step": 4570 }, { "loss_action": 0.04035666212439537, "loss_total": 0.04035666212439537, "step": 4570 }, { "grad_norm": 0.7573584914207458, "learning_rate": 9.158e-05, "loss": 0.0406, "step": 4580 }, { "loss_action": 0.03264801949262619, "loss_total": 0.03264801949262619, "step": 4580 }, { "grad_norm": 0.7342759966850281, "learning_rate": 9.178e-05, "loss": 0.0403, "step": 4590 }, { "loss_action": 0.03840506821870804, "loss_total": 0.03840506821870804, "step": 4590 }, { "grad_norm": 0.8667894005775452, "learning_rate": 9.198e-05, "loss": 0.0393, "step": 4600 }, { "loss_action": 0.04827697575092316, "loss_total": 0.04827697575092316, "step": 4600 }, { "grad_norm": 0.8827414512634277, "learning_rate": 9.218e-05, "loss": 0.043, "step": 4610 }, { "loss_action": 0.07526669651269913, "loss_total": 0.07526669651269913, "step": 4610 }, { "grad_norm": 0.9370957016944885, "learning_rate": 9.238e-05, "loss": 0.0492, "step": 4620 }, { "loss_action": 0.040155332535505295, "loss_total": 0.040155332535505295, "step": 4620 }, { "grad_norm": 0.8637730479240417, "learning_rate": 9.258e-05, "loss": 0.0461, "step": 4630 }, { "loss_action": 0.040229108184576035, "loss_total": 0.040229108184576035, "step": 4630 }, { "grad_norm": 0.8414173126220703, "learning_rate": 9.278e-05, "loss": 0.0501, "step": 4640 }, { "loss_action": 0.04991261288523674, "loss_total": 0.04991261288523674, "step": 4640 }, { "grad_norm": 0.8118918538093567, "learning_rate": 9.298e-05, "loss": 0.0476, "step": 4650 }, { "loss_action": 0.04022696241736412, "loss_total": 0.04022696241736412, "step": 4650 }, { "grad_norm": 0.9209198355674744, "learning_rate": 9.318e-05, "loss": 0.0427, "step": 4660 }, { "loss_action": 0.03527488559484482, "loss_total": 0.03527488559484482, "step": 4660 }, { "grad_norm": 0.8739047050476074, "learning_rate": 9.338e-05, "loss": 0.0418, "step": 4670 }, { "loss_action": 0.044289421290159225, "loss_total": 0.044289421290159225, "step": 4670 }, { "grad_norm": 0.9202687740325928, "learning_rate": 9.358e-05, "loss": 0.0426, "step": 4680 }, { "loss_action": 0.03743598237633705, "loss_total": 0.03743598237633705, "step": 4680 }, { "grad_norm": 0.912589430809021, "learning_rate": 9.378e-05, "loss": 0.0387, "step": 4690 }, { "loss_action": 0.03796648979187012, "loss_total": 0.03796648979187012, "step": 4690 }, { "grad_norm": 0.9216433167457581, "learning_rate": 9.398e-05, "loss": 0.0357, "step": 4700 }, { "loss_action": 0.041520699858665466, "loss_total": 0.041520699858665466, "step": 4700 }, { "grad_norm": 0.8619023561477661, "learning_rate": 9.418e-05, "loss": 0.0366, "step": 4710 }, { "loss_action": 0.04327170178294182, "loss_total": 0.04327170178294182, "step": 4710 }, { "grad_norm": 0.8668174147605896, "learning_rate": 9.438e-05, "loss": 0.0374, "step": 4720 }, { "loss_action": 0.036345306783914566, "loss_total": 0.036345306783914566, "step": 4720 }, { "grad_norm": 0.8221539258956909, "learning_rate": 9.458e-05, "loss": 0.041, "step": 4730 }, { "loss_action": 0.048884596675634384, "loss_total": 0.048884596675634384, "step": 4730 }, { "grad_norm": 0.8209794759750366, "learning_rate": 9.478e-05, "loss": 0.042, "step": 4740 }, { "loss_action": 0.036916334182024, "loss_total": 0.036916334182024, "step": 4740 }, { "grad_norm": 0.8358982801437378, "learning_rate": 9.498e-05, "loss": 0.0359, "step": 4750 }, { "loss_action": 0.034169625490903854, "loss_total": 0.034169625490903854, "step": 4750 }, { "grad_norm": 0.7622904777526855, "learning_rate": 9.518000000000001e-05, "loss": 0.0372, "step": 4760 }, { "loss_action": 0.03883681446313858, "loss_total": 0.03883681446313858, "step": 4760 }, { "grad_norm": 0.8430222868919373, "learning_rate": 9.538e-05, "loss": 0.0347, "step": 4770 }, { "loss_action": 0.03443753346800804, "loss_total": 0.03443753346800804, "step": 4770 }, { "grad_norm": 0.6836245059967041, "learning_rate": 9.558e-05, "loss": 0.0356, "step": 4780 }, { "loss_action": 0.0346650592982769, "loss_total": 0.0346650592982769, "step": 4780 }, { "grad_norm": 0.7150288224220276, "learning_rate": 9.578000000000001e-05, "loss": 0.0392, "step": 4790 }, { "loss_action": 0.04586884006857872, "loss_total": 0.04586884006857872, "step": 4790 }, { "grad_norm": 0.7228102087974548, "learning_rate": 9.598e-05, "loss": 0.0379, "step": 4800 }, { "loss_action": 0.043837543576955795, "loss_total": 0.043837543576955795, "step": 4800 }, { "grad_norm": 0.7924560308456421, "learning_rate": 9.618e-05, "loss": 0.0386, "step": 4810 }, { "loss_action": 0.030178003013134003, "loss_total": 0.030178003013134003, "step": 4810 }, { "grad_norm": 0.8252571225166321, "learning_rate": 9.638000000000001e-05, "loss": 0.0394, "step": 4820 }, { "loss_action": 0.04055141657590866, "loss_total": 0.04055141657590866, "step": 4820 }, { "grad_norm": 0.9937841296195984, "learning_rate": 9.658e-05, "loss": 0.0441, "step": 4830 }, { "loss_action": 0.029794128611683846, "loss_total": 0.029794128611683846, "step": 4830 }, { "grad_norm": 0.7966760396957397, "learning_rate": 9.678e-05, "loss": 0.0438, "step": 4840 }, { "loss_action": 0.03922927379608154, "loss_total": 0.03922927379608154, "step": 4840 }, { "grad_norm": 1.0271263122558594, "learning_rate": 9.698000000000001e-05, "loss": 0.0418, "step": 4850 }, { "loss_action": 0.04180862009525299, "loss_total": 0.04180862009525299, "step": 4850 }, { "grad_norm": 0.6731521487236023, "learning_rate": 9.718e-05, "loss": 0.0436, "step": 4860 }, { "loss_action": 0.051413100212812424, "loss_total": 0.051413100212812424, "step": 4860 }, { "grad_norm": 0.9160898923873901, "learning_rate": 9.738e-05, "loss": 0.0473, "step": 4870 }, { "loss_action": 0.05797279253602028, "loss_total": 0.05797279253602028, "step": 4870 }, { "grad_norm": 0.7061314582824707, "learning_rate": 9.758000000000001e-05, "loss": 0.0473, "step": 4880 }, { "loss_action": 0.051283564418554306, "loss_total": 0.051283564418554306, "step": 4880 }, { "grad_norm": 1.0426234006881714, "learning_rate": 9.778e-05, "loss": 0.0491, "step": 4890 }, { "loss_action": 0.04027697071433067, "loss_total": 0.04027697071433067, "step": 4890 }, { "grad_norm": 0.8046833276748657, "learning_rate": 9.798000000000001e-05, "loss": 0.0465, "step": 4900 }, { "loss_action": 0.045534126460552216, "loss_total": 0.045534126460552216, "step": 4900 }, { "grad_norm": 0.8856270909309387, "learning_rate": 9.818000000000001e-05, "loss": 0.0393, "step": 4910 }, { "loss_action": 0.036170538514852524, "loss_total": 0.036170538514852524, "step": 4910 }, { "grad_norm": 0.7203544974327087, "learning_rate": 9.838e-05, "loss": 0.038, "step": 4920 }, { "loss_action": 0.0320533849298954, "loss_total": 0.0320533849298954, "step": 4920 }, { "grad_norm": 0.7070646286010742, "learning_rate": 9.858000000000001e-05, "loss": 0.0375, "step": 4930 }, { "loss_action": 0.03457680717110634, "loss_total": 0.03457680717110634, "step": 4930 }, { "grad_norm": 0.9181399941444397, "learning_rate": 9.878e-05, "loss": 0.0388, "step": 4940 }, { "loss_action": 0.038213375955820084, "loss_total": 0.038213375955820084, "step": 4940 }, { "grad_norm": 0.6778244972229004, "learning_rate": 9.898e-05, "loss": 0.0357, "step": 4950 }, { "loss_action": 0.03682977333664894, "loss_total": 0.03682977333664894, "step": 4950 }, { "grad_norm": 0.6547965407371521, "learning_rate": 9.918000000000001e-05, "loss": 0.0391, "step": 4960 }, { "loss_action": 0.04633143171668053, "loss_total": 0.04633143171668053, "step": 4960 }, { "grad_norm": 0.9206891059875488, "learning_rate": 9.938e-05, "loss": 0.0408, "step": 4970 }, { "loss_action": 0.043055228888988495, "loss_total": 0.043055228888988495, "step": 4970 }, { "grad_norm": 0.9080333709716797, "learning_rate": 9.958e-05, "loss": 0.036, "step": 4980 }, { "loss_action": 0.02863914705812931, "loss_total": 0.02863914705812931, "step": 4980 }, { "grad_norm": 0.7721935510635376, "learning_rate": 9.978000000000001e-05, "loss": 0.035, "step": 4990 }, { "loss_action": 0.04695570468902588, "loss_total": 0.04695570468902588, "step": 4990 }, { "grad_norm": 0.7727968096733093, "learning_rate": 9.998e-05, "loss": 0.0365, "step": 5000 }, { "loss_action": 0.03644534572958946, "loss_total": 0.03644534572958946, "step": 5000 }, { "grad_norm": 0.6332436800003052, "learning_rate": 9.999999778549045e-05, "loss": 0.0345, "step": 5010 }, { "loss_action": 0.03304947540163994, "loss_total": 0.03304947540163994, "step": 5010 }, { "grad_norm": 0.9511208534240723, "learning_rate": 9.999999013039593e-05, "loss": 0.0372, "step": 5020 }, { "loss_action": 0.04163702204823494, "loss_total": 0.04163702204823494, "step": 5020 }, { "grad_norm": 0.7372180223464966, "learning_rate": 9.999997700737766e-05, "loss": 0.039, "step": 5030 }, { "loss_action": 0.030145490542054176, "loss_total": 0.030145490542054176, "step": 5030 }, { "grad_norm": 0.6826840043067932, "learning_rate": 9.999995841643709e-05, "loss": 0.0354, "step": 5040 }, { "loss_action": 0.03303868696093559, "loss_total": 0.03303868696093559, "step": 5040 }, { "grad_norm": 0.6930926442146301, "learning_rate": 9.999993435757623e-05, "loss": 0.0377, "step": 5050 }, { "loss_action": 0.042238060384988785, "loss_total": 0.042238060384988785, "step": 5050 }, { "grad_norm": 0.8291940689086914, "learning_rate": 9.999990483079773e-05, "loss": 0.037, "step": 5060 }, { "loss_action": 0.03341054171323776, "loss_total": 0.03341054171323776, "step": 5060 }, { "grad_norm": 0.8929299116134644, "learning_rate": 9.999986983610481e-05, "loss": 0.0413, "step": 5070 }, { "loss_action": 0.03668873384594917, "loss_total": 0.03668873384594917, "step": 5070 }, { "grad_norm": 1.0429493188858032, "learning_rate": 9.99998293735013e-05, "loss": 0.0412, "step": 5080 }, { "loss_action": 0.040405988693237305, "loss_total": 0.040405988693237305, "step": 5080 }, { "grad_norm": 1.2704325914382935, "learning_rate": 9.999978344299161e-05, "loss": 0.0466, "step": 5090 }, { "loss_action": 0.033743321895599365, "loss_total": 0.033743321895599365, "step": 5090 }, { "grad_norm": 0.8395931720733643, "learning_rate": 9.99997320445808e-05, "loss": 0.0395, "step": 5100 }, { "loss_action": 0.03749541938304901, "loss_total": 0.03749541938304901, "step": 5100 }, { "grad_norm": 1.9570826292037964, "learning_rate": 9.999967517827444e-05, "loss": 0.0566, "step": 5110 }, { "loss_action": 0.05960097163915634, "loss_total": 0.05960097163915634, "step": 5110 }, { "grad_norm": 1.0224103927612305, "learning_rate": 9.999961284407879e-05, "loss": 0.049, "step": 5120 }, { "loss_action": 0.051173314452171326, "loss_total": 0.051173314452171326, "step": 5120 }, { "grad_norm": 0.6592855453491211, "learning_rate": 9.999954504200067e-05, "loss": 0.041, "step": 5130 }, { "loss_action": 0.04862617701292038, "loss_total": 0.04862617701292038, "step": 5130 }, { "grad_norm": 0.7363248467445374, "learning_rate": 9.999947177204744e-05, "loss": 0.0374, "step": 5140 }, { "loss_action": 0.03487641364336014, "loss_total": 0.03487641364336014, "step": 5140 }, { "grad_norm": 0.7438303232192993, "learning_rate": 9.999939303422718e-05, "loss": 0.0372, "step": 5150 }, { "loss_action": 0.039597030729055405, "loss_total": 0.039597030729055405, "step": 5150 }, { "grad_norm": 0.689787745475769, "learning_rate": 9.999930882854847e-05, "loss": 0.0358, "step": 5160 }, { "loss_action": 0.03249470517039299, "loss_total": 0.03249470517039299, "step": 5160 }, { "grad_norm": 0.683773934841156, "learning_rate": 9.999921915502051e-05, "loss": 0.0394, "step": 5170 }, { "loss_action": 0.03477691859006882, "loss_total": 0.03477691859006882, "step": 5170 }, { "grad_norm": 1.0245661735534668, "learning_rate": 9.99991240136531e-05, "loss": 0.0422, "step": 5180 }, { "loss_action": 0.04528169706463814, "loss_total": 0.04528169706463814, "step": 5180 }, { "grad_norm": 0.735008955001831, "learning_rate": 9.999902340445668e-05, "loss": 0.0418, "step": 5190 }, { "loss_action": 0.046047527343034744, "loss_total": 0.046047527343034744, "step": 5190 }, { "grad_norm": 0.8983567953109741, "learning_rate": 9.999891732744224e-05, "loss": 0.0416, "step": 5200 }, { "loss_action": 0.03264724090695381, "loss_total": 0.03264724090695381, "step": 5200 }, { "grad_norm": 0.712909460067749, "learning_rate": 9.999880578262135e-05, "loss": 0.0365, "step": 5210 }, { "loss_action": 0.0402701161801815, "loss_total": 0.0402701161801815, "step": 5210 }, { "grad_norm": 0.9407169222831726, "learning_rate": 9.999868877000624e-05, "loss": 0.0539, "step": 5220 }, { "loss_action": 0.05272218957543373, "loss_total": 0.05272218957543373, "step": 5220 }, { "grad_norm": 0.6630451679229736, "learning_rate": 9.99985662896097e-05, "loss": 0.0512, "step": 5230 }, { "loss_action": 0.04700571671128273, "loss_total": 0.04700571671128273, "step": 5230 }, { "grad_norm": 1.5248723030090332, "learning_rate": 9.999843834144513e-05, "loss": 0.0436, "step": 5240 }, { "loss_action": 0.050846781581640244, "loss_total": 0.050846781581640244, "step": 5240 }, { "grad_norm": 0.9045064449310303, "learning_rate": 9.99983049255265e-05, "loss": 0.0502, "step": 5250 }, { "loss_action": 0.03917435184121132, "loss_total": 0.03917435184121132, "step": 5250 }, { "grad_norm": 0.6951999068260193, "learning_rate": 9.999816604186843e-05, "loss": 0.0403, "step": 5260 }, { "loss_action": 0.03741655498743057, "loss_total": 0.03741655498743057, "step": 5260 }, { "grad_norm": 0.7896528840065002, "learning_rate": 9.999802169048609e-05, "loss": 0.0413, "step": 5270 }, { "loss_action": 0.04291171580553055, "loss_total": 0.04291171580553055, "step": 5270 }, { "grad_norm": 1.13114333152771, "learning_rate": 9.999787187139527e-05, "loss": 0.0397, "step": 5280 }, { "loss_action": 0.03637994825839996, "loss_total": 0.03637994825839996, "step": 5280 }, { "grad_norm": 0.6310572028160095, "learning_rate": 9.999771658461234e-05, "loss": 0.0384, "step": 5290 }, { "loss_action": 0.034915003925561905, "loss_total": 0.034915003925561905, "step": 5290 }, { "grad_norm": 0.6830762624740601, "learning_rate": 9.999755583015431e-05, "loss": 0.0354, "step": 5300 }, { "loss_action": 0.03504515439271927, "loss_total": 0.03504515439271927, "step": 5300 }, { "grad_norm": 0.6878076195716858, "learning_rate": 9.999738960803874e-05, "loss": 0.038, "step": 5310 }, { "loss_action": 0.03766405209898949, "loss_total": 0.03766405209898949, "step": 5310 }, { "grad_norm": 0.6806914210319519, "learning_rate": 9.99972179182838e-05, "loss": 0.0353, "step": 5320 }, { "loss_action": 0.028444577008485794, "loss_total": 0.028444577008485794, "step": 5320 }, { "grad_norm": 0.7778635621070862, "learning_rate": 9.99970407609083e-05, "loss": 0.032, "step": 5330 }, { "loss_action": 0.03832486644387245, "loss_total": 0.03832486644387245, "step": 5330 }, { "grad_norm": 0.7056728601455688, "learning_rate": 9.999685813593159e-05, "loss": 0.0345, "step": 5340 }, { "loss_action": 0.03772836551070213, "loss_total": 0.03772836551070213, "step": 5340 }, { "grad_norm": 0.7544782161712646, "learning_rate": 9.999667004337362e-05, "loss": 0.035, "step": 5350 }, { "loss_action": 0.03074195235967636, "loss_total": 0.03074195235967636, "step": 5350 }, { "grad_norm": 0.6739373803138733, "learning_rate": 9.9996476483255e-05, "loss": 0.0339, "step": 5360 }, { "loss_action": 0.040115173906087875, "loss_total": 0.040115173906087875, "step": 5360 }, { "grad_norm": 0.7139842510223389, "learning_rate": 9.999627745559688e-05, "loss": 0.0333, "step": 5370 }, { "loss_action": 0.031971275806427, "loss_total": 0.031971275806427, "step": 5370 }, { "grad_norm": 0.7496257424354553, "learning_rate": 9.999607296042101e-05, "loss": 0.0322, "step": 5380 }, { "loss_action": 0.04326832666993141, "loss_total": 0.04326832666993141, "step": 5380 }, { "grad_norm": 0.5657700896263123, "learning_rate": 9.99958629977498e-05, "loss": 0.0328, "step": 5390 }, { "loss_action": 0.03117743879556656, "loss_total": 0.03117743879556656, "step": 5390 }, { "grad_norm": 0.7708244323730469, "learning_rate": 9.999564756760615e-05, "loss": 0.0337, "step": 5400 }, { "loss_action": 0.04130103066563606, "loss_total": 0.04130103066563606, "step": 5400 }, { "grad_norm": 0.8290607929229736, "learning_rate": 9.999542667001366e-05, "loss": 0.0371, "step": 5410 }, { "loss_action": 0.029454253613948822, "loss_total": 0.029454253613948822, "step": 5410 }, { "grad_norm": 1.1403416395187378, "learning_rate": 9.999520030499647e-05, "loss": 0.0403, "step": 5420 }, { "loss_action": 0.06097143515944481, "loss_total": 0.06097143515944481, "step": 5420 }, { "grad_norm": 1.143364429473877, "learning_rate": 9.999496847257936e-05, "loss": 0.0554, "step": 5430 }, { "loss_action": 0.04761327803134918, "loss_total": 0.04761327803134918, "step": 5430 }, { "grad_norm": 0.7959774732589722, "learning_rate": 9.999473117278764e-05, "loss": 0.0468, "step": 5440 }, { "loss_action": 0.04322116822004318, "loss_total": 0.04322116822004318, "step": 5440 }, { "grad_norm": 0.7282496094703674, "learning_rate": 9.999448840564731e-05, "loss": 0.0414, "step": 5450 }, { "loss_action": 0.03930022194981575, "loss_total": 0.03930022194981575, "step": 5450 }, { "grad_norm": 0.7054668664932251, "learning_rate": 9.999424017118488e-05, "loss": 0.0366, "step": 5460 }, { "loss_action": 0.03437850624322891, "loss_total": 0.03437850624322891, "step": 5460 }, { "grad_norm": 0.7151820063591003, "learning_rate": 9.999398646942751e-05, "loss": 0.036, "step": 5470 }, { "loss_action": 0.03816532343626022, "loss_total": 0.03816532343626022, "step": 5470 }, { "grad_norm": 0.8489328622817993, "learning_rate": 9.999372730040296e-05, "loss": 0.041, "step": 5480 }, { "loss_action": 0.03927626833319664, "loss_total": 0.03927626833319664, "step": 5480 }, { "grad_norm": 0.6976224184036255, "learning_rate": 9.999346266413953e-05, "loss": 0.044, "step": 5490 }, { "loss_action": 0.0352928563952446, "loss_total": 0.0352928563952446, "step": 5490 }, { "grad_norm": 0.7934830188751221, "learning_rate": 9.99931925606662e-05, "loss": 0.0386, "step": 5500 }, { "loss_action": 0.04520361125469208, "loss_total": 0.04520361125469208, "step": 5500 }, { "grad_norm": 0.7247717380523682, "learning_rate": 9.99929169900125e-05, "loss": 0.0418, "step": 5510 }, { "loss_action": 0.05275380238890648, "loss_total": 0.05275380238890648, "step": 5510 }, { "grad_norm": 0.8132012486457825, "learning_rate": 9.999263595220855e-05, "loss": 0.0379, "step": 5520 }, { "loss_action": 0.034034475684165955, "loss_total": 0.034034475684165955, "step": 5520 }, { "grad_norm": 0.7421391010284424, "learning_rate": 9.99923494472851e-05, "loss": 0.039, "step": 5530 }, { "loss_action": 0.0492190420627594, "loss_total": 0.0492190420627594, "step": 5530 }, { "grad_norm": 0.6388092637062073, "learning_rate": 9.999205747527348e-05, "loss": 0.0422, "step": 5540 }, { "loss_action": 0.03608241677284241, "loss_total": 0.03608241677284241, "step": 5540 }, { "grad_norm": 0.6766746640205383, "learning_rate": 9.999176003620561e-05, "loss": 0.0343, "step": 5550 }, { "loss_action": 0.03040517307817936, "loss_total": 0.03040517307817936, "step": 5550 }, { "grad_norm": 0.6847468614578247, "learning_rate": 9.999145713011405e-05, "loss": 0.0318, "step": 5560 }, { "loss_action": 0.03748917207121849, "loss_total": 0.03748917207121849, "step": 5560 }, { "grad_norm": 0.632010281085968, "learning_rate": 9.999114875703186e-05, "loss": 0.0319, "step": 5570 }, { "loss_action": 0.027955854311585426, "loss_total": 0.027955854311585426, "step": 5570 }, { "grad_norm": 0.7181161642074585, "learning_rate": 9.999083491699281e-05, "loss": 0.0319, "step": 5580 }, { "loss_action": 0.029909459874033928, "loss_total": 0.029909459874033928, "step": 5580 }, { "grad_norm": 0.7532554864883423, "learning_rate": 9.999051561003123e-05, "loss": 0.0336, "step": 5590 }, { "loss_action": 0.031069591641426086, "loss_total": 0.031069591641426086, "step": 5590 }, { "grad_norm": 0.6924834847450256, "learning_rate": 9.999019083618202e-05, "loss": 0.0386, "step": 5600 }, { "loss_action": 0.03586292266845703, "loss_total": 0.03586292266845703, "step": 5600 }, { "grad_norm": 0.5978168249130249, "learning_rate": 9.99898605954807e-05, "loss": 0.0374, "step": 5610 }, { "loss_action": 0.04879698529839516, "loss_total": 0.04879698529839516, "step": 5610 }, { "grad_norm": 0.7909366488456726, "learning_rate": 9.998952488796338e-05, "loss": 0.0379, "step": 5620 }, { "loss_action": 0.034397486597299576, "loss_total": 0.034397486597299576, "step": 5620 }, { "grad_norm": 0.7653017044067383, "learning_rate": 9.998918371366676e-05, "loss": 0.032, "step": 5630 }, { "loss_action": 0.03446580469608307, "loss_total": 0.03446580469608307, "step": 5630 }, { "grad_norm": 0.6281160116195679, "learning_rate": 9.99888370726282e-05, "loss": 0.0314, "step": 5640 }, { "loss_action": 0.03166228160262108, "loss_total": 0.03166228160262108, "step": 5640 }, { "grad_norm": 0.5475653409957886, "learning_rate": 9.998848496488556e-05, "loss": 0.0311, "step": 5650 }, { "loss_action": 0.02724548988044262, "loss_total": 0.02724548988044262, "step": 5650 }, { "grad_norm": 1.1226731538772583, "learning_rate": 9.998812739047736e-05, "loss": 0.0317, "step": 5660 }, { "loss_action": 0.0298174899071455, "loss_total": 0.0298174899071455, "step": 5660 }, { "grad_norm": 0.5889497399330139, "learning_rate": 9.99877643494427e-05, "loss": 0.0334, "step": 5670 }, { "loss_action": 0.028004862368106842, "loss_total": 0.028004862368106842, "step": 5670 }, { "grad_norm": 0.6111384630203247, "learning_rate": 9.998739584182128e-05, "loss": 0.0333, "step": 5680 }, { "loss_action": 0.0346306636929512, "loss_total": 0.0346306636929512, "step": 5680 }, { "grad_norm": 0.6349812150001526, "learning_rate": 9.998702186765342e-05, "loss": 0.0369, "step": 5690 }, { "loss_action": 0.04919159784913063, "loss_total": 0.04919159784913063, "step": 5690 }, { "grad_norm": 0.702704668045044, "learning_rate": 9.998664242698e-05, "loss": 0.0378, "step": 5700 }, { "loss_action": 0.034939855337142944, "loss_total": 0.034939855337142944, "step": 5700 }, { "grad_norm": 0.5756215453147888, "learning_rate": 9.998625751984251e-05, "loss": 0.0309, "step": 5710 }, { "loss_action": 0.029261531308293343, "loss_total": 0.029261531308293343, "step": 5710 }, { "grad_norm": 0.5613240599632263, "learning_rate": 9.998586714628307e-05, "loss": 0.0294, "step": 5720 }, { "loss_action": 0.028450647369027138, "loss_total": 0.028450647369027138, "step": 5720 }, { "grad_norm": 0.6618263721466064, "learning_rate": 9.998547130634432e-05, "loss": 0.0343, "step": 5730 }, { "loss_action": 0.02769138477742672, "loss_total": 0.02769138477742672, "step": 5730 }, { "grad_norm": 0.541637122631073, "learning_rate": 9.99850700000696e-05, "loss": 0.0295, "step": 5740 }, { "loss_action": 0.024669479578733444, "loss_total": 0.024669479578733444, "step": 5740 }, { "grad_norm": 0.9056773781776428, "learning_rate": 9.998466322750278e-05, "loss": 0.0306, "step": 5750 }, { "loss_action": 0.038102731108665466, "loss_total": 0.038102731108665466, "step": 5750 }, { "grad_norm": 0.6823132038116455, "learning_rate": 9.998425098868834e-05, "loss": 0.0345, "step": 5760 }, { "loss_action": 0.03925330191850662, "loss_total": 0.03925330191850662, "step": 5760 }, { "grad_norm": 0.5458261966705322, "learning_rate": 9.998383328367136e-05, "loss": 0.0343, "step": 5770 }, { "loss_action": 0.02331533655524254, "loss_total": 0.02331533655524254, "step": 5770 }, { "grad_norm": 0.7319838404655457, "learning_rate": 9.99834101124975e-05, "loss": 0.0318, "step": 5780 }, { "loss_action": 0.02499222755432129, "loss_total": 0.02499222755432129, "step": 5780 }, { "grad_norm": 0.7936741709709167, "learning_rate": 9.998298147521309e-05, "loss": 0.0324, "step": 5790 }, { "loss_action": 0.042470771819353104, "loss_total": 0.042470771819353104, "step": 5790 }, { "grad_norm": 0.8314389586448669, "learning_rate": 9.998254737186496e-05, "loss": 0.0325, "step": 5800 }, { "loss_action": 0.034613147377967834, "loss_total": 0.034613147377967834, "step": 5800 }, { "grad_norm": 0.6284705996513367, "learning_rate": 9.99821078025006e-05, "loss": 0.0361, "step": 5810 }, { "loss_action": 0.03801543638110161, "loss_total": 0.03801543638110161, "step": 5810 }, { "grad_norm": 0.6179669499397278, "learning_rate": 9.998166276716807e-05, "loss": 0.0347, "step": 5820 }, { "loss_action": 0.041895002126693726, "loss_total": 0.041895002126693726, "step": 5820 }, { "grad_norm": 0.7375308275222778, "learning_rate": 9.998121226591606e-05, "loss": 0.0347, "step": 5830 }, { "loss_action": 0.03649739921092987, "loss_total": 0.03649739921092987, "step": 5830 }, { "grad_norm": 0.604099452495575, "learning_rate": 9.998075629879382e-05, "loss": 0.0332, "step": 5840 }, { "loss_action": 0.035941436886787415, "loss_total": 0.035941436886787415, "step": 5840 }, { "grad_norm": 0.6557859182357788, "learning_rate": 9.99802948658512e-05, "loss": 0.0334, "step": 5850 }, { "loss_action": 0.03556601330637932, "loss_total": 0.03556601330637932, "step": 5850 }, { "grad_norm": 0.6922891736030579, "learning_rate": 9.99798279671387e-05, "loss": 0.0354, "step": 5860 }, { "loss_action": 0.04321720823645592, "loss_total": 0.04321720823645592, "step": 5860 }, { "grad_norm": 0.7330686450004578, "learning_rate": 9.997935560270734e-05, "loss": 0.0361, "step": 5870 }, { "loss_action": 0.028507908806204796, "loss_total": 0.028507908806204796, "step": 5870 }, { "grad_norm": 0.6483904123306274, "learning_rate": 9.997887777260879e-05, "loss": 0.0339, "step": 5880 }, { "loss_action": 0.029098736122250557, "loss_total": 0.029098736122250557, "step": 5880 }, { "grad_norm": 0.7559204697608948, "learning_rate": 9.997839447689532e-05, "loss": 0.0302, "step": 5890 }, { "loss_action": 0.04122989997267723, "loss_total": 0.04122989997267723, "step": 5890 }, { "grad_norm": 0.6513125896453857, "learning_rate": 9.997790571561978e-05, "loss": 0.0332, "step": 5900 }, { "loss_action": 0.027768395841121674, "loss_total": 0.027768395841121674, "step": 5900 }, { "grad_norm": 0.742597758769989, "learning_rate": 9.99774114888356e-05, "loss": 0.0344, "step": 5910 }, { "loss_action": 0.0261544156819582, "loss_total": 0.0261544156819582, "step": 5910 }, { "grad_norm": 0.5338680148124695, "learning_rate": 9.997691179659684e-05, "loss": 0.0328, "step": 5920 }, { "loss_action": 0.03570554405450821, "loss_total": 0.03570554405450821, "step": 5920 }, { "grad_norm": 0.6587647795677185, "learning_rate": 9.997640663895815e-05, "loss": 0.0316, "step": 5930 }, { "loss_action": 0.04616665095090866, "loss_total": 0.04616665095090866, "step": 5930 }, { "grad_norm": 0.7113649249076843, "learning_rate": 9.997589601597477e-05, "loss": 0.0322, "step": 5940 }, { "loss_action": 0.029807791113853455, "loss_total": 0.029807791113853455, "step": 5940 }, { "grad_norm": 0.7187195420265198, "learning_rate": 9.997537992770252e-05, "loss": 0.0298, "step": 5950 }, { "loss_action": 0.032498884946107864, "loss_total": 0.032498884946107864, "step": 5950 }, { "grad_norm": 0.6182377934455872, "learning_rate": 9.997485837419788e-05, "loss": 0.0321, "step": 5960 }, { "loss_action": 0.04417261481285095, "loss_total": 0.04417261481285095, "step": 5960 }, { "grad_norm": 0.7057471871376038, "learning_rate": 9.997433135551786e-05, "loss": 0.0376, "step": 5970 }, { "loss_action": 0.03529611602425575, "loss_total": 0.03529611602425575, "step": 5970 }, { "grad_norm": 0.5758468508720398, "learning_rate": 9.997379887172009e-05, "loss": 0.0346, "step": 5980 }, { "loss_action": 0.030164815485477448, "loss_total": 0.030164815485477448, "step": 5980 }, { "grad_norm": 0.5137056112289429, "learning_rate": 9.997326092286281e-05, "loss": 0.0304, "step": 5990 }, { "loss_action": 0.02948842942714691, "loss_total": 0.02948842942714691, "step": 5990 }, { "grad_norm": 0.5619415044784546, "learning_rate": 9.997271750900486e-05, "loss": 0.0326, "step": 6000 }, { "loss_action": 0.036794766783714294, "loss_total": 0.036794766783714294, "step": 6000 }, { "grad_norm": 0.5052590370178223, "learning_rate": 9.997216863020565e-05, "loss": 0.0311, "step": 6010 }, { "loss_action": 0.02873033471405506, "loss_total": 0.02873033471405506, "step": 6010 }, { "grad_norm": 0.6536321640014648, "learning_rate": 9.99716142865252e-05, "loss": 0.0284, "step": 6020 }, { "loss_action": 0.03931521624326706, "loss_total": 0.03931521624326706, "step": 6020 }, { "grad_norm": 0.7460179924964905, "learning_rate": 9.997105447802415e-05, "loss": 0.0304, "step": 6030 }, { "loss_action": 0.028590891510248184, "loss_total": 0.028590891510248184, "step": 6030 }, { "grad_norm": 0.6221199631690979, "learning_rate": 9.997048920476373e-05, "loss": 0.0306, "step": 6040 }, { "loss_action": 0.025404836982488632, "loss_total": 0.025404836982488632, "step": 6040 }, { "grad_norm": 0.6480293869972229, "learning_rate": 9.996991846680572e-05, "loss": 0.0302, "step": 6050 }, { "loss_action": 0.03324803337454796, "loss_total": 0.03324803337454796, "step": 6050 }, { "grad_norm": 0.6951015591621399, "learning_rate": 9.996934226421257e-05, "loss": 0.0314, "step": 6060 }, { "loss_action": 0.02793792262673378, "loss_total": 0.02793792262673378, "step": 6060 }, { "grad_norm": 0.5472599864006042, "learning_rate": 9.996876059704726e-05, "loss": 0.0298, "step": 6070 }, { "loss_action": 0.026272833347320557, "loss_total": 0.026272833347320557, "step": 6070 }, { "grad_norm": 0.6892925500869751, "learning_rate": 9.996817346537343e-05, "loss": 0.0303, "step": 6080 }, { "loss_action": 0.031700700521469116, "loss_total": 0.031700700521469116, "step": 6080 }, { "grad_norm": 0.6593720316886902, "learning_rate": 9.996758086925526e-05, "loss": 0.0336, "step": 6090 }, { "loss_action": 0.0295285452157259, "loss_total": 0.0295285452157259, "step": 6090 }, { "grad_norm": 0.6388488411903381, "learning_rate": 9.996698280875759e-05, "loss": 0.0313, "step": 6100 }, { "loss_action": 0.02949543297290802, "loss_total": 0.02949543297290802, "step": 6100 }, { "grad_norm": 0.6092357039451599, "learning_rate": 9.99663792839458e-05, "loss": 0.0303, "step": 6110 }, { "loss_action": 0.030102360993623734, "loss_total": 0.030102360993623734, "step": 6110 }, { "grad_norm": 0.6251684427261353, "learning_rate": 9.99657702948859e-05, "loss": 0.0309, "step": 6120 }, { "loss_action": 0.033643368631601334, "loss_total": 0.033643368631601334, "step": 6120 }, { "grad_norm": 0.6973860859870911, "learning_rate": 9.996515584164448e-05, "loss": 0.0287, "step": 6130 }, { "loss_action": 0.03327755630016327, "loss_total": 0.03327755630016327, "step": 6130 }, { "grad_norm": 0.6446822285652161, "learning_rate": 9.996453592428873e-05, "loss": 0.0289, "step": 6140 }, { "loss_action": 0.03130534291267395, "loss_total": 0.03130534291267395, "step": 6140 }, { "grad_norm": 0.8034268021583557, "learning_rate": 9.996391054288646e-05, "loss": 0.0312, "step": 6150 }, { "loss_action": 0.02437017671763897, "loss_total": 0.02437017671763897, "step": 6150 }, { "grad_norm": 0.6497493982315063, "learning_rate": 9.996327969750605e-05, "loss": 0.0293, "step": 6160 }, { "loss_action": 0.028659256175160408, "loss_total": 0.028659256175160408, "step": 6160 }, { "grad_norm": 0.614505410194397, "learning_rate": 9.996264338821649e-05, "loss": 0.0313, "step": 6170 }, { "loss_action": 0.039282750338315964, "loss_total": 0.039282750338315964, "step": 6170 }, { "grad_norm": 0.6190299987792969, "learning_rate": 9.996200161508735e-05, "loss": 0.0317, "step": 6180 }, { "loss_action": 0.03264731913805008, "loss_total": 0.03264731913805008, "step": 6180 }, { "grad_norm": 0.4779236614704132, "learning_rate": 9.996135437818885e-05, "loss": 0.0281, "step": 6190 }, { "loss_action": 0.02272465080022812, "loss_total": 0.02272465080022812, "step": 6190 }, { "grad_norm": 0.586380660533905, "learning_rate": 9.996070167759175e-05, "loss": 0.0284, "step": 6200 }, { "loss_action": 0.03453020751476288, "loss_total": 0.03453020751476288, "step": 6200 }, { "grad_norm": 0.5950153470039368, "learning_rate": 9.996004351336743e-05, "loss": 0.0299, "step": 6210 }, { "loss_action": 0.032259415835142136, "loss_total": 0.032259415835142136, "step": 6210 }, { "grad_norm": 0.7929839491844177, "learning_rate": 9.995937988558785e-05, "loss": 0.0303, "step": 6220 }, { "loss_action": 0.029418909922242165, "loss_total": 0.029418909922242165, "step": 6220 }, { "grad_norm": 0.6819549798965454, "learning_rate": 9.995871079432561e-05, "loss": 0.0274, "step": 6230 }, { "loss_action": 0.026176467537879944, "loss_total": 0.026176467537879944, "step": 6230 }, { "grad_norm": 0.5741655230522156, "learning_rate": 9.995803623965389e-05, "loss": 0.0279, "step": 6240 }, { "loss_action": 0.033445365726947784, "loss_total": 0.033445365726947784, "step": 6240 }, { "grad_norm": 0.5674813985824585, "learning_rate": 9.995735622164641e-05, "loss": 0.0311, "step": 6250 }, { "loss_action": 0.04206401854753494, "loss_total": 0.04206401854753494, "step": 6250 }, { "grad_norm": 0.5498164296150208, "learning_rate": 9.995667074037758e-05, "loss": 0.0286, "step": 6260 }, { "loss_action": 0.027684194967150688, "loss_total": 0.027684194967150688, "step": 6260 }, { "grad_norm": 0.7047069072723389, "learning_rate": 9.995597979592232e-05, "loss": 0.0297, "step": 6270 }, { "loss_action": 0.033982403576374054, "loss_total": 0.033982403576374054, "step": 6270 }, { "grad_norm": 0.4649812579154968, "learning_rate": 9.995528338835625e-05, "loss": 0.0318, "step": 6280 }, { "loss_action": 0.026971910148859024, "loss_total": 0.026971910148859024, "step": 6280 }, { "grad_norm": 0.5138411521911621, "learning_rate": 9.995458151775547e-05, "loss": 0.0303, "step": 6290 }, { "loss_action": 0.02677411027252674, "loss_total": 0.02677411027252674, "step": 6290 }, { "grad_norm": 0.6106396317481995, "learning_rate": 9.995387418419677e-05, "loss": 0.0263, "step": 6300 }, { "loss_action": 0.02533409185707569, "loss_total": 0.02533409185707569, "step": 6300 }, { "grad_norm": 0.7176235318183899, "learning_rate": 9.99531613877575e-05, "loss": 0.0263, "step": 6310 }, { "loss_action": 0.03570089116692543, "loss_total": 0.03570089116692543, "step": 6310 }, { "grad_norm": 0.5493943095207214, "learning_rate": 9.995244312851559e-05, "loss": 0.0288, "step": 6320 }, { "loss_action": 0.02459484525024891, "loss_total": 0.02459484525024891, "step": 6320 }, { "grad_norm": 0.6425183415412903, "learning_rate": 9.995171940654961e-05, "loss": 0.0279, "step": 6330 }, { "loss_action": 0.03383837267756462, "loss_total": 0.03383837267756462, "step": 6330 }, { "grad_norm": 0.5776748061180115, "learning_rate": 9.995099022193871e-05, "loss": 0.0316, "step": 6340 }, { "loss_action": 0.03173309192061424, "loss_total": 0.03173309192061424, "step": 6340 }, { "grad_norm": 0.7704550623893738, "learning_rate": 9.995025557476261e-05, "loss": 0.0325, "step": 6350 }, { "loss_action": 0.02371182292699814, "loss_total": 0.02371182292699814, "step": 6350 }, { "grad_norm": 0.6869314312934875, "learning_rate": 9.994951546510165e-05, "loss": 0.034, "step": 6360 }, { "loss_action": 0.038720399141311646, "loss_total": 0.038720399141311646, "step": 6360 }, { "grad_norm": 0.6815333962440491, "learning_rate": 9.994876989303679e-05, "loss": 0.0336, "step": 6370 }, { "loss_action": 0.02831832878291607, "loss_total": 0.02831832878291607, "step": 6370 }, { "grad_norm": 0.6208831667900085, "learning_rate": 9.994801885864955e-05, "loss": 0.0334, "step": 6380 }, { "loss_action": 0.03884328156709671, "loss_total": 0.03884328156709671, "step": 6380 }, { "grad_norm": 0.5702393054962158, "learning_rate": 9.994726236202205e-05, "loss": 0.0335, "step": 6390 }, { "loss_action": 0.03420191630721092, "loss_total": 0.03420191630721092, "step": 6390 }, { "grad_norm": 0.6778066158294678, "learning_rate": 9.994650040323704e-05, "loss": 0.029, "step": 6400 }, { "loss_action": 0.0348491407930851, "loss_total": 0.0348491407930851, "step": 6400 }, { "grad_norm": 0.5452660918235779, "learning_rate": 9.994573298237784e-05, "loss": 0.0272, "step": 6410 }, { "loss_action": 0.03186938166618347, "loss_total": 0.03186938166618347, "step": 6410 }, { "grad_norm": 0.552193284034729, "learning_rate": 9.994496009952837e-05, "loss": 0.0268, "step": 6420 }, { "loss_action": 0.024425283074378967, "loss_total": 0.024425283074378967, "step": 6420 }, { "grad_norm": 0.5582326650619507, "learning_rate": 9.994418175477316e-05, "loss": 0.028, "step": 6430 }, { "loss_action": 0.03471561148762703, "loss_total": 0.03471561148762703, "step": 6430 }, { "grad_norm": 0.43600910902023315, "learning_rate": 9.994339794819733e-05, "loss": 0.0287, "step": 6440 }, { "loss_action": 0.02701815776526928, "loss_total": 0.02701815776526928, "step": 6440 }, { "grad_norm": 0.5853634476661682, "learning_rate": 9.994260867988658e-05, "loss": 0.0281, "step": 6450 }, { "loss_action": 0.03042912855744362, "loss_total": 0.03042912855744362, "step": 6450 }, { "grad_norm": 0.7595946788787842, "learning_rate": 9.994181394992723e-05, "loss": 0.0278, "step": 6460 }, { "loss_action": 0.03650777041912079, "loss_total": 0.03650777041912079, "step": 6460 }, { "grad_norm": 0.5344882607460022, "learning_rate": 9.994101375840618e-05, "loss": 0.0298, "step": 6470 }, { "loss_action": 0.03128041326999664, "loss_total": 0.03128041326999664, "step": 6470 }, { "grad_norm": 0.8068072199821472, "learning_rate": 9.994020810541098e-05, "loss": 0.0285, "step": 6480 }, { "loss_action": 0.028097935020923615, "loss_total": 0.028097935020923615, "step": 6480 }, { "grad_norm": 0.5182907581329346, "learning_rate": 9.99393969910297e-05, "loss": 0.028, "step": 6490 }, { "loss_action": 0.030529174953699112, "loss_total": 0.030529174953699112, "step": 6490 }, { "grad_norm": 0.7385818362236023, "learning_rate": 9.993858041535104e-05, "loss": 0.0304, "step": 6500 }, { "loss_action": 0.023240791633725166, "loss_total": 0.023240791633725166, "step": 6500 }, { "grad_norm": 0.6719762086868286, "learning_rate": 9.99377583784643e-05, "loss": 0.0279, "step": 6510 }, { "loss_action": 0.02311215177178383, "loss_total": 0.02311215177178383, "step": 6510 }, { "grad_norm": 0.6492581367492676, "learning_rate": 9.993693088045939e-05, "loss": 0.0264, "step": 6520 }, { "loss_action": 0.02723698690533638, "loss_total": 0.02723698690533638, "step": 6520 }, { "grad_norm": 0.6195501685142517, "learning_rate": 9.99360979214268e-05, "loss": 0.0287, "step": 6530 }, { "loss_action": 0.0315103642642498, "loss_total": 0.0315103642642498, "step": 6530 }, { "grad_norm": 0.7944637537002563, "learning_rate": 9.99352595014576e-05, "loss": 0.0299, "step": 6540 }, { "loss_action": 0.03851178288459778, "loss_total": 0.03851178288459778, "step": 6540 }, { "grad_norm": 0.8563382029533386, "learning_rate": 9.993441562064354e-05, "loss": 0.0353, "step": 6550 }, { "loss_action": 0.036157507449388504, "loss_total": 0.036157507449388504, "step": 6550 }, { "grad_norm": 0.8205443620681763, "learning_rate": 9.993356627907685e-05, "loss": 0.0324, "step": 6560 }, { "loss_action": 0.03388122469186783, "loss_total": 0.03388122469186783, "step": 6560 }, { "grad_norm": 0.5593815445899963, "learning_rate": 9.99327114768504e-05, "loss": 0.0326, "step": 6570 }, { "loss_action": 0.03693322837352753, "loss_total": 0.03693322837352753, "step": 6570 }, { "grad_norm": 0.8370678424835205, "learning_rate": 9.99318512140577e-05, "loss": 0.0315, "step": 6580 }, { "loss_action": 0.029106806963682175, "loss_total": 0.029106806963682175, "step": 6580 }, { "grad_norm": 0.7928280830383301, "learning_rate": 9.993098549079284e-05, "loss": 0.0319, "step": 6590 }, { "loss_action": 0.02690390683710575, "loss_total": 0.02690390683710575, "step": 6590 }, { "grad_norm": 0.6550561785697937, "learning_rate": 9.993011430715047e-05, "loss": 0.0327, "step": 6600 }, { "loss_action": 0.030568087473511696, "loss_total": 0.030568087473511696, "step": 6600 }, { "grad_norm": 0.5492677092552185, "learning_rate": 9.992923766322586e-05, "loss": 0.0323, "step": 6610 }, { "loss_action": 0.032188985496759415, "loss_total": 0.032188985496759415, "step": 6610 }, { "grad_norm": 0.5661789774894714, "learning_rate": 9.99283555591149e-05, "loss": 0.0294, "step": 6620 }, { "loss_action": 0.02938850037753582, "loss_total": 0.02938850037753582, "step": 6620 }, { "grad_norm": 0.8122502565383911, "learning_rate": 9.992746799491404e-05, "loss": 0.0318, "step": 6630 }, { "loss_action": 0.024824604392051697, "loss_total": 0.024824604392051697, "step": 6630 }, { "grad_norm": 0.7469145655632019, "learning_rate": 9.992657497072033e-05, "loss": 0.0333, "step": 6640 }, { "loss_action": 0.03445282205939293, "loss_total": 0.03445282205939293, "step": 6640 }, { "grad_norm": 0.6033634543418884, "learning_rate": 9.992567648663147e-05, "loss": 0.0341, "step": 6650 }, { "loss_action": 0.03440769016742706, "loss_total": 0.03440769016742706, "step": 6650 }, { "grad_norm": 0.5037996768951416, "learning_rate": 9.992477254274568e-05, "loss": 0.0316, "step": 6660 }, { "loss_action": 0.03146560117602348, "loss_total": 0.03146560117602348, "step": 6660 }, { "grad_norm": 0.658931314945221, "learning_rate": 9.992386313916183e-05, "loss": 0.0316, "step": 6670 }, { "loss_action": 0.029878584668040276, "loss_total": 0.029878584668040276, "step": 6670 }, { "grad_norm": 0.6083654165267944, "learning_rate": 9.992294827597934e-05, "loss": 0.0303, "step": 6680 }, { "loss_action": 0.03421910107135773, "loss_total": 0.03421910107135773, "step": 6680 }, { "grad_norm": 0.708855926990509, "learning_rate": 9.992202795329831e-05, "loss": 0.0331, "step": 6690 }, { "loss_action": 0.03049412928521633, "loss_total": 0.03049412928521633, "step": 6690 }, { "grad_norm": 0.4710920453071594, "learning_rate": 9.992110217121936e-05, "loss": 0.0284, "step": 6700 }, { "loss_action": 0.040337905287742615, "loss_total": 0.040337905287742615, "step": 6700 }, { "grad_norm": 0.8607376217842102, "learning_rate": 9.992017092984372e-05, "loss": 0.0309, "step": 6710 }, { "loss_action": 0.031756360083818436, "loss_total": 0.031756360083818436, "step": 6710 }, { "grad_norm": 0.695537269115448, "learning_rate": 9.991923422927326e-05, "loss": 0.034, "step": 6720 }, { "loss_action": 0.035319920629262924, "loss_total": 0.035319920629262924, "step": 6720 }, { "grad_norm": 0.6742531657218933, "learning_rate": 9.991829206961037e-05, "loss": 0.0329, "step": 6730 }, { "loss_action": 0.02965688332915306, "loss_total": 0.02965688332915306, "step": 6730 }, { "grad_norm": 0.697074294090271, "learning_rate": 9.991734445095813e-05, "loss": 0.0328, "step": 6740 }, { "loss_action": 0.026575064286589622, "loss_total": 0.026575064286589622, "step": 6740 }, { "grad_norm": 0.7103519439697266, "learning_rate": 9.991639137342015e-05, "loss": 0.0279, "step": 6750 }, { "loss_action": 0.036731962114572525, "loss_total": 0.036731962114572525, "step": 6750 }, { "grad_norm": 0.6868784427642822, "learning_rate": 9.991543283710064e-05, "loss": 0.0293, "step": 6760 }, { "loss_action": 0.029692305251955986, "loss_total": 0.029692305251955986, "step": 6760 }, { "grad_norm": 0.6820548176765442, "learning_rate": 9.991446884210445e-05, "loss": 0.0298, "step": 6770 }, { "loss_action": 0.03323511779308319, "loss_total": 0.03323511779308319, "step": 6770 }, { "grad_norm": 0.5097008943557739, "learning_rate": 9.9913499388537e-05, "loss": 0.0304, "step": 6780 }, { "loss_action": 0.02918156422674656, "loss_total": 0.02918156422674656, "step": 6780 }, { "grad_norm": 0.7656968235969543, "learning_rate": 9.99125244765043e-05, "loss": 0.0296, "step": 6790 }, { "loss_action": 0.025016382336616516, "loss_total": 0.025016382336616516, "step": 6790 }, { "grad_norm": 0.6448904275894165, "learning_rate": 9.991154410611296e-05, "loss": 0.0288, "step": 6800 }, { "loss_action": 0.020572640001773834, "loss_total": 0.020572640001773834, "step": 6800 }, { "grad_norm": 0.5875858664512634, "learning_rate": 9.99105582774702e-05, "loss": 0.0258, "step": 6810 }, { "loss_action": 0.02741086296737194, "loss_total": 0.02741086296737194, "step": 6810 }, { "grad_norm": 0.5404052138328552, "learning_rate": 9.990956699068384e-05, "loss": 0.0289, "step": 6820 }, { "loss_action": 0.029726024717092514, "loss_total": 0.029726024717092514, "step": 6820 }, { "grad_norm": 0.7516732811927795, "learning_rate": 9.990857024586224e-05, "loss": 0.031, "step": 6830 }, { "loss_action": 0.02723299339413643, "loss_total": 0.02723299339413643, "step": 6830 }, { "grad_norm": 0.663167417049408, "learning_rate": 9.990756804311446e-05, "loss": 0.0369, "step": 6840 }, { "loss_action": 0.03876622021198273, "loss_total": 0.03876622021198273, "step": 6840 }, { "grad_norm": 0.678013026714325, "learning_rate": 9.990656038255006e-05, "loss": 0.0351, "step": 6850 }, { "loss_action": 0.03917663171887398, "loss_total": 0.03917663171887398, "step": 6850 }, { "grad_norm": 0.6891805529594421, "learning_rate": 9.990554726427926e-05, "loss": 0.0344, "step": 6860 }, { "loss_action": 0.030828161165118217, "loss_total": 0.030828161165118217, "step": 6860 }, { "grad_norm": 0.752985954284668, "learning_rate": 9.990452868841284e-05, "loss": 0.0346, "step": 6870 }, { "loss_action": 0.038129910826683044, "loss_total": 0.038129910826683044, "step": 6870 }, { "grad_norm": 0.853922963142395, "learning_rate": 9.99035046550622e-05, "loss": 0.0357, "step": 6880 }, { "loss_action": 0.028978144749999046, "loss_total": 0.028978144749999046, "step": 6880 }, { "grad_norm": 0.7495381832122803, "learning_rate": 9.99024751643393e-05, "loss": 0.0326, "step": 6890 }, { "loss_action": 0.032168418169021606, "loss_total": 0.032168418169021606, "step": 6890 }, { "grad_norm": 0.5994570255279541, "learning_rate": 9.990144021635677e-05, "loss": 0.03, "step": 6900 }, { "loss_action": 0.025458594784140587, "loss_total": 0.025458594784140587, "step": 6900 }, { "grad_norm": 0.6128695607185364, "learning_rate": 9.990039981122775e-05, "loss": 0.0291, "step": 6910 }, { "loss_action": 0.0306576918810606, "loss_total": 0.0306576918810606, "step": 6910 }, { "grad_norm": 0.6855647563934326, "learning_rate": 9.989935394906602e-05, "loss": 0.0327, "step": 6920 }, { "loss_action": 0.02373744733631611, "loss_total": 0.02373744733631611, "step": 6920 }, { "grad_norm": 0.6365651488304138, "learning_rate": 9.989830262998598e-05, "loss": 0.0276, "step": 6930 }, { "loss_action": 0.02652304247021675, "loss_total": 0.02652304247021675, "step": 6930 }, { "grad_norm": 0.6622269749641418, "learning_rate": 9.989724585410259e-05, "loss": 0.0309, "step": 6940 }, { "loss_action": 0.03262940049171448, "loss_total": 0.03262940049171448, "step": 6940 }, { "grad_norm": 0.5521926283836365, "learning_rate": 9.989618362153139e-05, "loss": 0.0294, "step": 6950 }, { "loss_action": 0.0318852961063385, "loss_total": 0.0318852961063385, "step": 6950 }, { "grad_norm": 0.42979690432548523, "learning_rate": 9.989511593238859e-05, "loss": 0.0285, "step": 6960 }, { "loss_action": 0.02747551165521145, "loss_total": 0.02747551165521145, "step": 6960 }, { "grad_norm": 0.656986653804779, "learning_rate": 9.98940427867909e-05, "loss": 0.0255, "step": 6970 }, { "loss_action": 0.030101750046014786, "loss_total": 0.030101750046014786, "step": 6970 }, { "grad_norm": 0.6412329077720642, "learning_rate": 9.989296418485573e-05, "loss": 0.0314, "step": 6980 }, { "loss_action": 0.03325210139155388, "loss_total": 0.03325210139155388, "step": 6980 }, { "grad_norm": 0.7936245799064636, "learning_rate": 9.989188012670101e-05, "loss": 0.0346, "step": 6990 }, { "loss_action": 0.03100660815834999, "loss_total": 0.03100660815834999, "step": 6990 }, { "grad_norm": 0.645041823387146, "learning_rate": 9.989079061244528e-05, "loss": 0.0325, "step": 7000 }, { "loss_action": 0.03399381786584854, "loss_total": 0.03399381786584854, "step": 7000 }, { "grad_norm": 0.7375674843788147, "learning_rate": 9.988969564220769e-05, "loss": 0.0332, "step": 7010 }, { "loss_action": 0.025690220296382904, "loss_total": 0.025690220296382904, "step": 7010 }, { "grad_norm": 0.641806423664093, "learning_rate": 9.988859521610801e-05, "loss": 0.0317, "step": 7020 }, { "loss_action": 0.03128490597009659, "loss_total": 0.03128490597009659, "step": 7020 }, { "grad_norm": 0.6593831777572632, "learning_rate": 9.988748933426656e-05, "loss": 0.0335, "step": 7030 }, { "loss_action": 0.029149077832698822, "loss_total": 0.029149077832698822, "step": 7030 }, { "grad_norm": 0.7527459859848022, "learning_rate": 9.988637799680428e-05, "loss": 0.0315, "step": 7040 }, { "loss_action": 0.03511437028646469, "loss_total": 0.03511437028646469, "step": 7040 }, { "grad_norm": 0.6321149468421936, "learning_rate": 9.98852612038427e-05, "loss": 0.0289, "step": 7050 }, { "loss_action": 0.04015488550066948, "loss_total": 0.04015488550066948, "step": 7050 }, { "grad_norm": 0.7533548474311829, "learning_rate": 9.988413895550397e-05, "loss": 0.0371, "step": 7060 }, { "loss_action": 0.04206867888569832, "loss_total": 0.04206867888569832, "step": 7060 }, { "grad_norm": 0.8612340688705444, "learning_rate": 9.98830112519108e-05, "loss": 0.0391, "step": 7070 }, { "loss_action": 0.02929750643670559, "loss_total": 0.02929750643670559, "step": 7070 }, { "grad_norm": 0.5708788633346558, "learning_rate": 9.98818780931865e-05, "loss": 0.0334, "step": 7080 }, { "loss_action": 0.03375751152634621, "loss_total": 0.03375751152634621, "step": 7080 }, { "grad_norm": 0.7799786925315857, "learning_rate": 9.988073947945502e-05, "loss": 0.0357, "step": 7090 }, { "loss_action": 0.03695131838321686, "loss_total": 0.03695131838321686, "step": 7090 }, { "grad_norm": 0.6763743162155151, "learning_rate": 9.987959541084087e-05, "loss": 0.0333, "step": 7100 }, { "loss_action": 0.029966792091727257, "loss_total": 0.029966792091727257, "step": 7100 }, { "grad_norm": 0.49191954731941223, "learning_rate": 9.987844588746915e-05, "loss": 0.0311, "step": 7110 }, { "loss_action": 0.031120551750063896, "loss_total": 0.031120551750063896, "step": 7110 }, { "grad_norm": 0.6394802331924438, "learning_rate": 9.987729090946558e-05, "loss": 0.0332, "step": 7120 }, { "loss_action": 0.03726120665669441, "loss_total": 0.03726120665669441, "step": 7120 }, { "grad_norm": 0.5306271910667419, "learning_rate": 9.987613047695647e-05, "loss": 0.0313, "step": 7130 }, { "loss_action": 0.041318513453006744, "loss_total": 0.041318513453006744, "step": 7130 }, { "grad_norm": 0.6315972805023193, "learning_rate": 9.987496459006871e-05, "loss": 0.0349, "step": 7140 }, { "loss_action": 0.03077113628387451, "loss_total": 0.03077113628387451, "step": 7140 }, { "grad_norm": 0.7797404527664185, "learning_rate": 9.987379324892982e-05, "loss": 0.0448, "step": 7150 }, { "loss_action": 0.04150325804948807, "loss_total": 0.04150325804948807, "step": 7150 }, { "grad_norm": 0.7567623257637024, "learning_rate": 9.987261645366788e-05, "loss": 0.0382, "step": 7160 }, { "loss_action": 0.02790139988064766, "loss_total": 0.02790139988064766, "step": 7160 }, { "grad_norm": 0.5466582775115967, "learning_rate": 9.987143420441158e-05, "loss": 0.0334, "step": 7170 }, { "loss_action": 0.03033418580889702, "loss_total": 0.03033418580889702, "step": 7170 }, { "grad_norm": 0.5841647982597351, "learning_rate": 9.987024650129022e-05, "loss": 0.0316, "step": 7180 }, { "loss_action": 0.03074110671877861, "loss_total": 0.03074110671877861, "step": 7180 }, { "grad_norm": 0.4566888213157654, "learning_rate": 9.986905334443368e-05, "loss": 0.0302, "step": 7190 }, { "loss_action": 0.03456781432032585, "loss_total": 0.03456781432032585, "step": 7190 }, { "grad_norm": 0.5194811820983887, "learning_rate": 9.986785473397245e-05, "loss": 0.0294, "step": 7200 }, { "loss_action": 0.036571793258190155, "loss_total": 0.036571793258190155, "step": 7200 }, { "grad_norm": 0.5579142570495605, "learning_rate": 9.98666506700376e-05, "loss": 0.0298, "step": 7210 }, { "loss_action": 0.02875303290784359, "loss_total": 0.02875303290784359, "step": 7210 }, { "grad_norm": 0.5396000146865845, "learning_rate": 9.986544115276081e-05, "loss": 0.0312, "step": 7220 }, { "loss_action": 0.024687930941581726, "loss_total": 0.024687930941581726, "step": 7220 }, { "grad_norm": 1.0031673908233643, "learning_rate": 9.986422618227433e-05, "loss": 0.0328, "step": 7230 }, { "loss_action": 0.04018067568540573, "loss_total": 0.04018067568540573, "step": 7230 }, { "grad_norm": 0.8054797053337097, "learning_rate": 9.986300575871106e-05, "loss": 0.0421, "step": 7240 }, { "loss_action": 0.04146218299865723, "loss_total": 0.04146218299865723, "step": 7240 }, { "grad_norm": 0.604465126991272, "learning_rate": 9.986177988220444e-05, "loss": 0.0405, "step": 7250 }, { "loss_action": 0.04651813581585884, "loss_total": 0.04651813581585884, "step": 7250 }, { "grad_norm": 0.6261517405509949, "learning_rate": 9.986054855288856e-05, "loss": 0.035, "step": 7260 }, { "loss_action": 0.0294379610568285, "loss_total": 0.0294379610568285, "step": 7260 }, { "grad_norm": 0.8468316793441772, "learning_rate": 9.985931177089802e-05, "loss": 0.0331, "step": 7270 }, { "loss_action": 0.04113589972257614, "loss_total": 0.04113589972257614, "step": 7270 }, { "grad_norm": 0.5754513144493103, "learning_rate": 9.985806953636814e-05, "loss": 0.0344, "step": 7280 }, { "loss_action": 0.034970637410879135, "loss_total": 0.034970637410879135, "step": 7280 }, { "grad_norm": 0.4411173164844513, "learning_rate": 9.985682184943471e-05, "loss": 0.0346, "step": 7290 }, { "loss_action": 0.02795432321727276, "loss_total": 0.02795432321727276, "step": 7290 }, { "grad_norm": 0.5785301923751831, "learning_rate": 9.98555687102342e-05, "loss": 0.0327, "step": 7300 }, { "loss_action": 0.02992738038301468, "loss_total": 0.02992738038301468, "step": 7300 }, { "grad_norm": 0.6396123766899109, "learning_rate": 9.985431011890367e-05, "loss": 0.0316, "step": 7310 }, { "loss_action": 0.026037875562906265, "loss_total": 0.026037875562906265, "step": 7310 }, { "grad_norm": 0.6521772742271423, "learning_rate": 9.985304607558075e-05, "loss": 0.0328, "step": 7320 }, { "loss_action": 0.03093196451663971, "loss_total": 0.03093196451663971, "step": 7320 }, { "grad_norm": 0.5478169322013855, "learning_rate": 9.985177658040364e-05, "loss": 0.0285, "step": 7330 }, { "loss_action": 0.042952485382556915, "loss_total": 0.042952485382556915, "step": 7330 }, { "grad_norm": 0.6586649417877197, "learning_rate": 9.985050163351119e-05, "loss": 0.0331, "step": 7340 }, { "loss_action": 0.025988813489675522, "loss_total": 0.025988813489675522, "step": 7340 }, { "grad_norm": 0.5594842433929443, "learning_rate": 9.984922123504286e-05, "loss": 0.0319, "step": 7350 }, { "loss_action": 0.03051820583641529, "loss_total": 0.03051820583641529, "step": 7350 }, { "grad_norm": 0.6039845943450928, "learning_rate": 9.984793538513862e-05, "loss": 0.0297, "step": 7360 }, { "loss_action": 0.026715006679296494, "loss_total": 0.026715006679296494, "step": 7360 }, { "grad_norm": 0.5232799053192139, "learning_rate": 9.984664408393912e-05, "loss": 0.0302, "step": 7370 }, { "loss_action": 0.02819468267261982, "loss_total": 0.02819468267261982, "step": 7370 }, { "grad_norm": 0.727291464805603, "learning_rate": 9.984534733158556e-05, "loss": 0.031, "step": 7380 }, { "loss_action": 0.03690467029809952, "loss_total": 0.03690467029809952, "step": 7380 }, { "grad_norm": 0.5643724203109741, "learning_rate": 9.984404512821977e-05, "loss": 0.0308, "step": 7390 }, { "loss_action": 0.028763948008418083, "loss_total": 0.028763948008418083, "step": 7390 }, { "grad_norm": 0.6433120965957642, "learning_rate": 9.984273747398411e-05, "loss": 0.0302, "step": 7400 }, { "loss_action": 0.0368766114115715, "loss_total": 0.0368766114115715, "step": 7400 }, { "grad_norm": 0.590260922908783, "learning_rate": 9.984142436902165e-05, "loss": 0.0288, "step": 7410 }, { "loss_action": 0.033829085528850555, "loss_total": 0.033829085528850555, "step": 7410 }, { "grad_norm": 0.49919813871383667, "learning_rate": 9.984010581347596e-05, "loss": 0.0297, "step": 7420 }, { "loss_action": 0.03453918918967247, "loss_total": 0.03453918918967247, "step": 7420 }, { "grad_norm": 0.5597841143608093, "learning_rate": 9.983878180749121e-05, "loss": 0.0283, "step": 7430 }, { "loss_action": 0.029899999499320984, "loss_total": 0.029899999499320984, "step": 7430 }, { "grad_norm": 0.5356578230857849, "learning_rate": 9.983745235121222e-05, "loss": 0.0304, "step": 7440 }, { "loss_action": 0.030777471140027046, "loss_total": 0.030777471140027046, "step": 7440 }, { "grad_norm": 0.5002740621566772, "learning_rate": 9.983611744478438e-05, "loss": 0.0271, "step": 7450 }, { "loss_action": 0.027042094618082047, "loss_total": 0.027042094618082047, "step": 7450 }, { "grad_norm": 0.5061171054840088, "learning_rate": 9.983477708835365e-05, "loss": 0.028, "step": 7460 }, { "loss_action": 0.02349899709224701, "loss_total": 0.02349899709224701, "step": 7460 }, { "grad_norm": 0.5276631116867065, "learning_rate": 9.983343128206664e-05, "loss": 0.0281, "step": 7470 }, { "loss_action": 0.018358899280428886, "loss_total": 0.018358899280428886, "step": 7470 }, { "grad_norm": 0.5164119005203247, "learning_rate": 9.983208002607049e-05, "loss": 0.0252, "step": 7480 }, { "loss_action": 0.027600739151239395, "loss_total": 0.027600739151239395, "step": 7480 }, { "grad_norm": 0.6765671968460083, "learning_rate": 9.9830723320513e-05, "loss": 0.027, "step": 7490 }, { "loss_action": 0.028985645622015, "loss_total": 0.028985645622015, "step": 7490 }, { "grad_norm": 0.5266484022140503, "learning_rate": 9.982936116554254e-05, "loss": 0.0278, "step": 7500 }, { "loss_action": 0.03559344261884689, "loss_total": 0.03559344261884689, "step": 7500 }, { "grad_norm": 0.6701818108558655, "learning_rate": 9.982799356130803e-05, "loss": 0.0304, "step": 7510 }, { "loss_action": 0.023943526670336723, "loss_total": 0.023943526670336723, "step": 7510 }, { "grad_norm": 0.48125743865966797, "learning_rate": 9.982662050795908e-05, "loss": 0.0274, "step": 7520 }, { "loss_action": 0.023982830345630646, "loss_total": 0.023982830345630646, "step": 7520 }, { "grad_norm": 0.5646202564239502, "learning_rate": 9.982524200564583e-05, "loss": 0.0268, "step": 7530 }, { "loss_action": 0.027311479672789574, "loss_total": 0.027311479672789574, "step": 7530 }, { "grad_norm": 0.6276676654815674, "learning_rate": 9.982385805451901e-05, "loss": 0.0306, "step": 7540 }, { "loss_action": 0.029920507222414017, "loss_total": 0.029920507222414017, "step": 7540 }, { "grad_norm": 0.46356815099716187, "learning_rate": 9.982246865472998e-05, "loss": 0.0278, "step": 7550 }, { "loss_action": 0.02465025521814823, "loss_total": 0.02465025521814823, "step": 7550 }, { "grad_norm": 0.5638503432273865, "learning_rate": 9.982107380643069e-05, "loss": 0.0279, "step": 7560 }, { "loss_action": 0.021285975351929665, "loss_total": 0.021285975351929665, "step": 7560 }, { "grad_norm": 0.5932214260101318, "learning_rate": 9.981967350977368e-05, "loss": 0.0252, "step": 7570 }, { "loss_action": 0.024451006203889847, "loss_total": 0.024451006203889847, "step": 7570 }, { "grad_norm": 0.7706928849220276, "learning_rate": 9.981826776491208e-05, "loss": 0.0277, "step": 7580 }, { "loss_action": 0.02370375767350197, "loss_total": 0.02370375767350197, "step": 7580 }, { "grad_norm": 0.7434324622154236, "learning_rate": 9.98168565719996e-05, "loss": 0.0295, "step": 7590 }, { "loss_action": 0.034188512712717056, "loss_total": 0.034188512712717056, "step": 7590 }, { "grad_norm": 0.4987758994102478, "learning_rate": 9.98154399311906e-05, "loss": 0.0266, "step": 7600 }, { "loss_action": 0.024634500965476036, "loss_total": 0.024634500965476036, "step": 7600 }, { "grad_norm": 0.7290545701980591, "learning_rate": 9.981401784263997e-05, "loss": 0.0264, "step": 7610 }, { "loss_action": 0.021731866523623466, "loss_total": 0.021731866523623466, "step": 7610 }, { "grad_norm": 0.6265918016433716, "learning_rate": 9.981259030650326e-05, "loss": 0.0269, "step": 7620 }, { "loss_action": 0.03416803851723671, "loss_total": 0.03416803851723671, "step": 7620 }, { "grad_norm": 0.6091070175170898, "learning_rate": 9.981115732293655e-05, "loss": 0.0281, "step": 7630 }, { "loss_action": 0.03814595192670822, "loss_total": 0.03814595192670822, "step": 7630 }, { "grad_norm": 0.5856614708900452, "learning_rate": 9.980971889209659e-05, "loss": 0.0357, "step": 7640 }, { "loss_action": 0.03665042296051979, "loss_total": 0.03665042296051979, "step": 7640 }, { "grad_norm": 1.1555728912353516, "learning_rate": 9.980827501414064e-05, "loss": 0.0383, "step": 7650 }, { "loss_action": 0.04158521443605423, "loss_total": 0.04158521443605423, "step": 7650 }, { "grad_norm": 0.8390804529190063, "learning_rate": 9.980682568922663e-05, "loss": 0.0413, "step": 7660 }, { "loss_action": 0.03871561959385872, "loss_total": 0.03871561959385872, "step": 7660 }, { "grad_norm": 0.7001910209655762, "learning_rate": 9.980537091751304e-05, "loss": 0.0362, "step": 7670 }, { "loss_action": 0.033003710210323334, "loss_total": 0.033003710210323334, "step": 7670 }, { "grad_norm": 0.5189226865768433, "learning_rate": 9.980391069915897e-05, "loss": 0.0347, "step": 7680 }, { "loss_action": 0.04051220789551735, "loss_total": 0.04051220789551735, "step": 7680 }, { "grad_norm": 0.5575160980224609, "learning_rate": 9.98024450343241e-05, "loss": 0.0337, "step": 7690 }, { "loss_action": 0.028635071590542793, "loss_total": 0.028635071590542793, "step": 7690 }, { "grad_norm": 0.4430355429649353, "learning_rate": 9.980097392316872e-05, "loss": 0.0326, "step": 7700 }, { "loss_action": 0.02804543823003769, "loss_total": 0.02804543823003769, "step": 7700 }, { "grad_norm": 0.6634790897369385, "learning_rate": 9.97994973658537e-05, "loss": 0.0282, "step": 7710 }, { "loss_action": 0.025099782273173332, "loss_total": 0.025099782273173332, "step": 7710 }, { "grad_norm": 0.5361230969429016, "learning_rate": 9.979801536254054e-05, "loss": 0.0314, "step": 7720 }, { "loss_action": 0.025608349591493607, "loss_total": 0.025608349591493607, "step": 7720 }, { "grad_norm": 0.9432501792907715, "learning_rate": 9.979652791339127e-05, "loss": 0.0415, "step": 7730 }, { "loss_action": 0.045468494296073914, "loss_total": 0.045468494296073914, "step": 7730 }, { "grad_norm": 0.6284369230270386, "learning_rate": 9.97950350185686e-05, "loss": 0.0375, "step": 7740 }, { "loss_action": 0.03204130753874779, "loss_total": 0.03204130753874779, "step": 7740 }, { "grad_norm": 0.6121285557746887, "learning_rate": 9.979353667823574e-05, "loss": 0.0348, "step": 7750 }, { "loss_action": 0.02820933796465397, "loss_total": 0.02820933796465397, "step": 7750 }, { "grad_norm": 0.5634433627128601, "learning_rate": 9.979203289255658e-05, "loss": 0.0324, "step": 7760 }, { "loss_action": 0.026311267167329788, "loss_total": 0.026311267167329788, "step": 7760 }, { "grad_norm": 0.5950087904930115, "learning_rate": 9.979052366169557e-05, "loss": 0.0322, "step": 7770 }, { "loss_action": 0.030978361144661903, "loss_total": 0.030978361144661903, "step": 7770 }, { "grad_norm": 0.6893101334571838, "learning_rate": 9.978900898581775e-05, "loss": 0.0334, "step": 7780 }, { "loss_action": 0.03917934000492096, "loss_total": 0.03917934000492096, "step": 7780 }, { "grad_norm": 0.807206392288208, "learning_rate": 9.978748886508875e-05, "loss": 0.0344, "step": 7790 }, { "loss_action": 0.027852116152644157, "loss_total": 0.027852116152644157, "step": 7790 }, { "grad_norm": 0.8085711598396301, "learning_rate": 9.978596329967484e-05, "loss": 0.0331, "step": 7800 }, { "loss_action": 0.033328551799058914, "loss_total": 0.033328551799058914, "step": 7800 }, { "grad_norm": 0.7048360705375671, "learning_rate": 9.978443228974284e-05, "loss": 0.0327, "step": 7810 }, { "loss_action": 0.02816351316869259, "loss_total": 0.02816351316869259, "step": 7810 }, { "grad_norm": 0.5435762405395508, "learning_rate": 9.978289583546015e-05, "loss": 0.0318, "step": 7820 }, { "loss_action": 0.027946321293711662, "loss_total": 0.027946321293711662, "step": 7820 }, { "grad_norm": 0.43660813570022583, "learning_rate": 9.978135393699484e-05, "loss": 0.0297, "step": 7830 }, { "loss_action": 0.02299468219280243, "loss_total": 0.02299468219280243, "step": 7830 }, { "grad_norm": 0.5528174638748169, "learning_rate": 9.977980659451548e-05, "loss": 0.0283, "step": 7840 }, { "loss_action": 0.02251278981566429, "loss_total": 0.02251278981566429, "step": 7840 }, { "grad_norm": 0.6012551188468933, "learning_rate": 9.977825380819135e-05, "loss": 0.0289, "step": 7850 }, { "loss_action": 0.0407174788415432, "loss_total": 0.0407174788415432, "step": 7850 }, { "grad_norm": 0.5943198800086975, "learning_rate": 9.97766955781922e-05, "loss": 0.0327, "step": 7860 }, { "loss_action": 0.03388185426592827, "loss_total": 0.03388185426592827, "step": 7860 }, { "grad_norm": 0.5817717909812927, "learning_rate": 9.977513190468848e-05, "loss": 0.0286, "step": 7870 }, { "loss_action": 0.026382602751255035, "loss_total": 0.026382602751255035, "step": 7870 }, { "grad_norm": 0.48456138372421265, "learning_rate": 9.977356278785116e-05, "loss": 0.0296, "step": 7880 }, { "loss_action": 0.030197862535715103, "loss_total": 0.030197862535715103, "step": 7880 }, { "grad_norm": 0.5145193338394165, "learning_rate": 9.977198822785184e-05, "loss": 0.028, "step": 7890 }, { "loss_action": 0.024643685668706894, "loss_total": 0.024643685668706894, "step": 7890 }, { "grad_norm": 0.5520408749580383, "learning_rate": 9.977040822486273e-05, "loss": 0.028, "step": 7900 }, { "loss_action": 0.02350868470966816, "loss_total": 0.02350868470966816, "step": 7900 }, { "grad_norm": 0.553868293762207, "learning_rate": 9.97688227790566e-05, "loss": 0.0276, "step": 7910 }, { "loss_action": 0.02732713706791401, "loss_total": 0.02732713706791401, "step": 7910 }, { "grad_norm": 0.4768139123916626, "learning_rate": 9.976723189060684e-05, "loss": 0.0285, "step": 7920 }, { "loss_action": 0.0417528860270977, "loss_total": 0.0417528860270977, "step": 7920 }, { "grad_norm": 0.631447434425354, "learning_rate": 9.976563555968742e-05, "loss": 0.0337, "step": 7930 }, { "loss_action": 0.02704782783985138, "loss_total": 0.02704782783985138, "step": 7930 }, { "grad_norm": 0.5834733247756958, "learning_rate": 9.976403378647292e-05, "loss": 0.0308, "step": 7940 }, { "loss_action": 0.02950136736035347, "loss_total": 0.02950136736035347, "step": 7940 }, { "grad_norm": 0.6757307648658752, "learning_rate": 9.97624265711385e-05, "loss": 0.0323, "step": 7950 }, { "loss_action": 0.03468457981944084, "loss_total": 0.03468457981944084, "step": 7950 }, { "grad_norm": 0.7443168759346008, "learning_rate": 9.976081391385993e-05, "loss": 0.0345, "step": 7960 }, { "loss_action": 0.04013609141111374, "loss_total": 0.04013609141111374, "step": 7960 }, { "grad_norm": 0.6646966934204102, "learning_rate": 9.975919581481356e-05, "loss": 0.0386, "step": 7970 }, { "loss_action": 0.04562614485621452, "loss_total": 0.04562614485621452, "step": 7970 }, { "grad_norm": 0.6614886522293091, "learning_rate": 9.975757227417634e-05, "loss": 0.0377, "step": 7980 }, { "loss_action": 0.025077806785702705, "loss_total": 0.025077806785702705, "step": 7980 }, { "grad_norm": 0.6371488571166992, "learning_rate": 9.975594329212586e-05, "loss": 0.0309, "step": 7990 }, { "loss_action": 0.030534788966178894, "loss_total": 0.030534788966178894, "step": 7990 }, { "grad_norm": 0.5800818800926208, "learning_rate": 9.97543088688402e-05, "loss": 0.0299, "step": 8000 }, { "loss_action": 0.028315283358097076, "loss_total": 0.028315283358097076, "step": 8000 }, { "grad_norm": 0.43615517020225525, "learning_rate": 9.975266900449814e-05, "loss": 0.0275, "step": 8010 }, { "loss_action": 0.02493136003613472, "loss_total": 0.02493136003613472, "step": 8010 }, { "grad_norm": 0.49082520604133606, "learning_rate": 9.975102369927898e-05, "loss": 0.0285, "step": 8020 }, { "loss_action": 0.029501697048544884, "loss_total": 0.029501697048544884, "step": 8020 }, { "grad_norm": 0.5012233257293701, "learning_rate": 9.974937295336269e-05, "loss": 0.0298, "step": 8030 }, { "loss_action": 0.026229694485664368, "loss_total": 0.026229694485664368, "step": 8030 }, { "grad_norm": 0.6034647822380066, "learning_rate": 9.974771676692975e-05, "loss": 0.0289, "step": 8040 }, { "loss_action": 0.035871803760528564, "loss_total": 0.035871803760528564, "step": 8040 }, { "grad_norm": 0.7020384073257446, "learning_rate": 9.974605514016131e-05, "loss": 0.0298, "step": 8050 }, { "loss_action": 0.03356941416859627, "loss_total": 0.03356941416859627, "step": 8050 }, { "grad_norm": 0.6802844405174255, "learning_rate": 9.974438807323907e-05, "loss": 0.0288, "step": 8060 }, { "loss_action": 0.037949878722429276, "loss_total": 0.037949878722429276, "step": 8060 }, { "grad_norm": 0.5634190440177917, "learning_rate": 9.974271556634535e-05, "loss": 0.0302, "step": 8070 }, { "loss_action": 0.030237721279263496, "loss_total": 0.030237721279263496, "step": 8070 }, { "grad_norm": 0.5462614893913269, "learning_rate": 9.974103761966302e-05, "loss": 0.0277, "step": 8080 }, { "loss_action": 0.02187730371952057, "loss_total": 0.02187730371952057, "step": 8080 }, { "grad_norm": 0.5907526016235352, "learning_rate": 9.973935423337563e-05, "loss": 0.0292, "step": 8090 }, { "loss_action": 0.02765721268951893, "loss_total": 0.02765721268951893, "step": 8090 }, { "grad_norm": 0.5717958807945251, "learning_rate": 9.973766540766722e-05, "loss": 0.0292, "step": 8100 }, { "loss_action": 0.02369190938770771, "loss_total": 0.02369190938770771, "step": 8100 }, { "grad_norm": 0.5476829409599304, "learning_rate": 9.97359711427225e-05, "loss": 0.0272, "step": 8110 }, { "loss_action": 0.023733016103506088, "loss_total": 0.023733016103506088, "step": 8110 }, { "grad_norm": 0.5607951283454895, "learning_rate": 9.973427143872677e-05, "loss": 0.0239, "step": 8120 }, { "loss_action": 0.03024076670408249, "loss_total": 0.03024076670408249, "step": 8120 }, { "grad_norm": 0.7097893357276917, "learning_rate": 9.973256629586589e-05, "loss": 0.0313, "step": 8130 }, { "loss_action": 0.024690469726920128, "loss_total": 0.024690469726920128, "step": 8130 }, { "grad_norm": 0.49289315938949585, "learning_rate": 9.973085571432632e-05, "loss": 0.0298, "step": 8140 }, { "loss_action": 0.029281072318553925, "loss_total": 0.029281072318553925, "step": 8140 }, { "grad_norm": 0.6361743211746216, "learning_rate": 9.972913969429513e-05, "loss": 0.0361, "step": 8150 }, { "loss_action": 0.02668610028922558, "loss_total": 0.02668610028922558, "step": 8150 }, { "grad_norm": 0.522165834903717, "learning_rate": 9.972741823596e-05, "loss": 0.0297, "step": 8160 }, { "loss_action": 0.043265312910079956, "loss_total": 0.043265312910079956, "step": 8160 }, { "grad_norm": 0.9116588234901428, "learning_rate": 9.972569133950917e-05, "loss": 0.0321, "step": 8170 }, { "loss_action": 0.024672862142324448, "loss_total": 0.024672862142324448, "step": 8170 }, { "grad_norm": 0.5786452293395996, "learning_rate": 9.972395900513151e-05, "loss": 0.0303, "step": 8180 }, { "loss_action": 0.02811267413198948, "loss_total": 0.02811267413198948, "step": 8180 }, { "grad_norm": 0.5873793363571167, "learning_rate": 9.972222123301645e-05, "loss": 0.0286, "step": 8190 }, { "loss_action": 0.02847336232662201, "loss_total": 0.02847336232662201, "step": 8190 }, { "grad_norm": 0.5557945370674133, "learning_rate": 9.972047802335403e-05, "loss": 0.0314, "step": 8200 }, { "loss_action": 0.0322597436606884, "loss_total": 0.0322597436606884, "step": 8200 }, { "grad_norm": 0.5715572237968445, "learning_rate": 9.971872937633488e-05, "loss": 0.0282, "step": 8210 }, { "loss_action": 0.03264341130852699, "loss_total": 0.03264341130852699, "step": 8210 }, { "grad_norm": 0.59347003698349, "learning_rate": 9.971697529215024e-05, "loss": 0.0291, "step": 8220 }, { "loss_action": 0.02736269123852253, "loss_total": 0.02736269123852253, "step": 8220 }, { "grad_norm": 0.6083841323852539, "learning_rate": 9.971521577099192e-05, "loss": 0.0286, "step": 8230 }, { "loss_action": 0.021880900487303734, "loss_total": 0.021880900487303734, "step": 8230 }, { "grad_norm": 0.4926452934741974, "learning_rate": 9.971345081305236e-05, "loss": 0.0265, "step": 8240 }, { "loss_action": 0.03014942817389965, "loss_total": 0.03014942817389965, "step": 8240 }, { "grad_norm": 0.5865480899810791, "learning_rate": 9.971168041852456e-05, "loss": 0.0255, "step": 8250 }, { "loss_action": 0.0228593610227108, "loss_total": 0.0228593610227108, "step": 8250 }, { "grad_norm": 0.39306163787841797, "learning_rate": 9.970990458760215e-05, "loss": 0.0269, "step": 8260 }, { "loss_action": 0.026714472100138664, "loss_total": 0.026714472100138664, "step": 8260 }, { "grad_norm": 0.6450402736663818, "learning_rate": 9.970812332047929e-05, "loss": 0.0239, "step": 8270 }, { "loss_action": 0.025380505248904228, "loss_total": 0.025380505248904228, "step": 8270 }, { "grad_norm": 0.5242564678192139, "learning_rate": 9.97063366173508e-05, "loss": 0.0255, "step": 8280 }, { "loss_action": 0.025963829830288887, "loss_total": 0.025963829830288887, "step": 8280 }, { "grad_norm": 0.5381988883018494, "learning_rate": 9.970454447841207e-05, "loss": 0.0267, "step": 8290 }, { "loss_action": 0.02702781744301319, "loss_total": 0.02702781744301319, "step": 8290 }, { "grad_norm": 0.4973326623439789, "learning_rate": 9.970274690385909e-05, "loss": 0.0268, "step": 8300 }, { "loss_action": 0.032999418675899506, "loss_total": 0.032999418675899506, "step": 8300 }, { "grad_norm": 0.5309027433395386, "learning_rate": 9.970094389388844e-05, "loss": 0.0261, "step": 8310 }, { "loss_action": 0.023562539368867874, "loss_total": 0.023562539368867874, "step": 8310 }, { "grad_norm": 0.8182329535484314, "learning_rate": 9.969913544869728e-05, "loss": 0.0284, "step": 8320 }, { "loss_action": 0.029393622651696205, "loss_total": 0.029393622651696205, "step": 8320 }, { "grad_norm": 0.6272286176681519, "learning_rate": 9.96973215684834e-05, "loss": 0.0268, "step": 8330 }, { "loss_action": 0.02726702392101288, "loss_total": 0.02726702392101288, "step": 8330 }, { "grad_norm": 0.599640429019928, "learning_rate": 9.969550225344513e-05, "loss": 0.0282, "step": 8340 }, { "loss_action": 0.02489321678876877, "loss_total": 0.02489321678876877, "step": 8340 }, { "grad_norm": 0.6588954925537109, "learning_rate": 9.969367750378147e-05, "loss": 0.0316, "step": 8350 }, { "loss_action": 0.03223991021513939, "loss_total": 0.03223991021513939, "step": 8350 }, { "grad_norm": 0.5620319247245789, "learning_rate": 9.969184731969194e-05, "loss": 0.0276, "step": 8360 }, { "loss_action": 0.02777712047100067, "loss_total": 0.02777712047100067, "step": 8360 }, { "grad_norm": 0.4958420693874359, "learning_rate": 9.96900117013767e-05, "loss": 0.0266, "step": 8370 }, { "loss_action": 0.02876279130578041, "loss_total": 0.02876279130578041, "step": 8370 }, { "grad_norm": 0.4434139132499695, "learning_rate": 9.96881706490365e-05, "loss": 0.0279, "step": 8380 }, { "loss_action": 0.024535560980439186, "loss_total": 0.024535560980439186, "step": 8380 }, { "grad_norm": 0.7220053672790527, "learning_rate": 9.968632416287265e-05, "loss": 0.0254, "step": 8390 }, { "loss_action": 0.022198831662535667, "loss_total": 0.022198831662535667, "step": 8390 }, { "grad_norm": 0.689732015132904, "learning_rate": 9.96844722430871e-05, "loss": 0.0277, "step": 8400 }, { "loss_action": 0.026308350265026093, "loss_total": 0.026308350265026093, "step": 8400 }, { "grad_norm": 0.5622034668922424, "learning_rate": 9.968261488988235e-05, "loss": 0.0293, "step": 8410 }, { "loss_action": 0.022996006533503532, "loss_total": 0.022996006533503532, "step": 8410 }, { "grad_norm": 0.6599277853965759, "learning_rate": 9.968075210346155e-05, "loss": 0.0276, "step": 8420 }, { "loss_action": 0.02963549643754959, "loss_total": 0.02963549643754959, "step": 8420 }, { "grad_norm": 0.6460793018341064, "learning_rate": 9.967888388402839e-05, "loss": 0.0307, "step": 8430 }, { "loss_action": 0.03047765977680683, "loss_total": 0.03047765977680683, "step": 8430 }, { "grad_norm": 0.4906521439552307, "learning_rate": 9.967701023178717e-05, "loss": 0.0308, "step": 8440 }, { "loss_action": 0.029644956812262535, "loss_total": 0.029644956812262535, "step": 8440 }, { "grad_norm": 0.6207212209701538, "learning_rate": 9.967513114694282e-05, "loss": 0.0321, "step": 8450 }, { "loss_action": 0.025475261732935905, "loss_total": 0.025475261732935905, "step": 8450 }, { "grad_norm": 0.4511338770389557, "learning_rate": 9.967324662970079e-05, "loss": 0.0268, "step": 8460 }, { "loss_action": 0.02621401846408844, "loss_total": 0.02621401846408844, "step": 8460 }, { "grad_norm": 0.5463948845863342, "learning_rate": 9.96713566802672e-05, "loss": 0.027, "step": 8470 }, { "loss_action": 0.025491703301668167, "loss_total": 0.025491703301668167, "step": 8470 }, { "grad_norm": 0.6069108843803406, "learning_rate": 9.966946129884873e-05, "loss": 0.0329, "step": 8480 }, { "loss_action": 0.027530498802661896, "loss_total": 0.027530498802661896, "step": 8480 }, { "grad_norm": 0.48305046558380127, "learning_rate": 9.966756048565265e-05, "loss": 0.028, "step": 8490 }, { "loss_action": 0.04384847357869148, "loss_total": 0.04384847357869148, "step": 8490 }, { "grad_norm": 0.5135709047317505, "learning_rate": 9.966565424088681e-05, "loss": 0.0287, "step": 8500 }, { "loss_action": 0.031669288873672485, "loss_total": 0.031669288873672485, "step": 8500 }, { "grad_norm": 0.4521924555301666, "learning_rate": 9.96637425647597e-05, "loss": 0.0291, "step": 8510 }, { "loss_action": 0.02702867053449154, "loss_total": 0.02702867053449154, "step": 8510 }, { "grad_norm": 0.5459510087966919, "learning_rate": 9.966182545748038e-05, "loss": 0.0261, "step": 8520 }, { "loss_action": 0.0230899378657341, "loss_total": 0.0230899378657341, "step": 8520 }, { "grad_norm": 0.4321083724498749, "learning_rate": 9.96599029192585e-05, "loss": 0.0269, "step": 8530 }, { "loss_action": 0.024546556174755096, "loss_total": 0.024546556174755096, "step": 8530 }, { "grad_norm": 0.5452591776847839, "learning_rate": 9.965797495030428e-05, "loss": 0.0246, "step": 8540 }, { "loss_action": 0.022799113765358925, "loss_total": 0.022799113765358925, "step": 8540 }, { "grad_norm": 0.5505461096763611, "learning_rate": 9.96560415508286e-05, "loss": 0.0237, "step": 8550 }, { "loss_action": 0.027006808668375015, "loss_total": 0.027006808668375015, "step": 8550 }, { "grad_norm": 0.4893888235092163, "learning_rate": 9.965410272104286e-05, "loss": 0.0255, "step": 8560 }, { "loss_action": 0.024053454399108887, "loss_total": 0.024053454399108887, "step": 8560 }, { "grad_norm": 0.5574366450309753, "learning_rate": 9.96521584611591e-05, "loss": 0.026, "step": 8570 }, { "loss_action": 0.027337705716490746, "loss_total": 0.027337705716490746, "step": 8570 }, { "grad_norm": 0.46669647097587585, "learning_rate": 9.965020877138994e-05, "loss": 0.0274, "step": 8580 }, { "loss_action": 0.02265196107327938, "loss_total": 0.02265196107327938, "step": 8580 }, { "grad_norm": 0.69167560338974, "learning_rate": 9.964825365194861e-05, "loss": 0.0275, "step": 8590 }, { "loss_action": 0.023767665028572083, "loss_total": 0.023767665028572083, "step": 8590 }, { "grad_norm": 0.48345398902893066, "learning_rate": 9.96462931030489e-05, "loss": 0.0286, "step": 8600 }, { "loss_action": 0.02109479531645775, "loss_total": 0.02109479531645775, "step": 8600 }, { "grad_norm": 0.5970656871795654, "learning_rate": 9.96443271249052e-05, "loss": 0.028, "step": 8610 }, { "loss_action": 0.022624125704169273, "loss_total": 0.022624125704169273, "step": 8610 }, { "grad_norm": 0.5504875779151917, "learning_rate": 9.964235571773255e-05, "loss": 0.0257, "step": 8620 }, { "loss_action": 0.018105050548911095, "loss_total": 0.018105050548911095, "step": 8620 }, { "grad_norm": 0.48361191153526306, "learning_rate": 9.96403788817465e-05, "loss": 0.0261, "step": 8630 }, { "loss_action": 0.021054863929748535, "loss_total": 0.021054863929748535, "step": 8630 }, { "grad_norm": 0.5248446464538574, "learning_rate": 9.963839661716325e-05, "loss": 0.0238, "step": 8640 }, { "loss_action": 0.029807161539793015, "loss_total": 0.029807161539793015, "step": 8640 }, { "grad_norm": 0.4505361020565033, "learning_rate": 9.963640892419958e-05, "loss": 0.0262, "step": 8650 }, { "loss_action": 0.025076493620872498, "loss_total": 0.025076493620872498, "step": 8650 }, { "grad_norm": 0.48497462272644043, "learning_rate": 9.963441580307286e-05, "loss": 0.0255, "step": 8660 }, { "loss_action": 0.024948954582214355, "loss_total": 0.024948954582214355, "step": 8660 }, { "grad_norm": 0.6067065000534058, "learning_rate": 9.963241725400104e-05, "loss": 0.0258, "step": 8670 }, { "loss_action": 0.025746187195181847, "loss_total": 0.025746187195181847, "step": 8670 }, { "grad_norm": 0.5473437309265137, "learning_rate": 9.963041327720271e-05, "loss": 0.0252, "step": 8680 }, { "loss_action": 0.019918473437428474, "loss_total": 0.019918473437428474, "step": 8680 }, { "grad_norm": 0.6440747380256653, "learning_rate": 9.962840387289697e-05, "loss": 0.0249, "step": 8690 }, { "loss_action": 0.023198140785098076, "loss_total": 0.023198140785098076, "step": 8690 }, { "grad_norm": 0.4959675967693329, "learning_rate": 9.962638904130363e-05, "loss": 0.0289, "step": 8700 }, { "loss_action": 0.0291557889431715, "loss_total": 0.0291557889431715, "step": 8700 }, { "grad_norm": 0.6147810220718384, "learning_rate": 9.962436878264298e-05, "loss": 0.028, "step": 8710 }, { "loss_action": 0.0223543643951416, "loss_total": 0.0223543643951416, "step": 8710 }, { "grad_norm": 0.4313387870788574, "learning_rate": 9.962234309713598e-05, "loss": 0.0254, "step": 8720 }, { "loss_action": 0.02728724665939808, "loss_total": 0.02728724665939808, "step": 8720 }, { "grad_norm": 0.5455144047737122, "learning_rate": 9.962031198500414e-05, "loss": 0.027, "step": 8730 }, { "loss_action": 0.029597623273730278, "loss_total": 0.029597623273730278, "step": 8730 }, { "grad_norm": 0.562289834022522, "learning_rate": 9.961827544646958e-05, "loss": 0.0253, "step": 8740 }, { "loss_action": 0.02727128192782402, "loss_total": 0.02727128192782402, "step": 8740 }, { "grad_norm": 0.5336057543754578, "learning_rate": 9.961623348175501e-05, "loss": 0.0271, "step": 8750 }, { "loss_action": 0.021834025159478188, "loss_total": 0.021834025159478188, "step": 8750 }, { "grad_norm": 0.6123400330543518, "learning_rate": 9.961418609108377e-05, "loss": 0.0282, "step": 8760 }, { "loss_action": 0.03437214717268944, "loss_total": 0.03437214717268944, "step": 8760 }, { "grad_norm": 0.5087407231330872, "learning_rate": 9.961213327467971e-05, "loss": 0.0282, "step": 8770 }, { "loss_action": 0.021947741508483887, "loss_total": 0.021947741508483887, "step": 8770 }, { "grad_norm": 0.6381390690803528, "learning_rate": 9.961007503276736e-05, "loss": 0.0269, "step": 8780 }, { "loss_action": 0.0297942403703928, "loss_total": 0.0297942403703928, "step": 8780 }, { "grad_norm": 0.5875042080879211, "learning_rate": 9.960801136557179e-05, "loss": 0.0271, "step": 8790 }, { "loss_action": 0.02921433001756668, "loss_total": 0.02921433001756668, "step": 8790 }, { "grad_norm": 0.5751448273658752, "learning_rate": 9.960594227331866e-05, "loss": 0.0261, "step": 8800 }, { "loss_action": 0.027927543967962265, "loss_total": 0.027927543967962265, "step": 8800 }, { "grad_norm": 0.5360561013221741, "learning_rate": 9.960386775623429e-05, "loss": 0.0244, "step": 8810 }, { "loss_action": 0.033449310809373856, "loss_total": 0.033449310809373856, "step": 8810 }, { "grad_norm": 0.5345072150230408, "learning_rate": 9.96017878145455e-05, "loss": 0.0269, "step": 8820 }, { "loss_action": 0.030954493209719658, "loss_total": 0.030954493209719658, "step": 8820 }, { "grad_norm": 0.3847109079360962, "learning_rate": 9.959970244847977e-05, "loss": 0.0276, "step": 8830 }, { "loss_action": 0.029628166928887367, "loss_total": 0.029628166928887367, "step": 8830 }, { "grad_norm": 0.4889768362045288, "learning_rate": 9.959761165826518e-05, "loss": 0.0253, "step": 8840 }, { "loss_action": 0.03558808192610741, "loss_total": 0.03558808192610741, "step": 8840 }, { "grad_norm": 0.4231654405593872, "learning_rate": 9.959551544413033e-05, "loss": 0.0283, "step": 8850 }, { "loss_action": 0.026041140779852867, "loss_total": 0.026041140779852867, "step": 8850 }, { "grad_norm": 0.4242435097694397, "learning_rate": 9.959341380630448e-05, "loss": 0.0263, "step": 8860 }, { "loss_action": 0.02491885796189308, "loss_total": 0.02491885796189308, "step": 8860 }, { "grad_norm": 0.6277284026145935, "learning_rate": 9.959130674501746e-05, "loss": 0.0261, "step": 8870 }, { "loss_action": 0.018847690895199776, "loss_total": 0.018847690895199776, "step": 8870 }, { "grad_norm": 0.554871141910553, "learning_rate": 9.958919426049968e-05, "loss": 0.0272, "step": 8880 }, { "loss_action": 0.03244530037045479, "loss_total": 0.03244530037045479, "step": 8880 }, { "grad_norm": 0.4505598247051239, "learning_rate": 9.958707635298219e-05, "loss": 0.0261, "step": 8890 }, { "loss_action": 0.024196699261665344, "loss_total": 0.024196699261665344, "step": 8890 }, { "grad_norm": 0.5065159201622009, "learning_rate": 9.958495302269657e-05, "loss": 0.0257, "step": 8900 }, { "loss_action": 0.026005733758211136, "loss_total": 0.026005733758211136, "step": 8900 }, { "grad_norm": 0.6336683630943298, "learning_rate": 9.958282426987503e-05, "loss": 0.0271, "step": 8910 }, { "loss_action": 0.03062870167195797, "loss_total": 0.03062870167195797, "step": 8910 }, { "grad_norm": 0.6845685839653015, "learning_rate": 9.95806900947504e-05, "loss": 0.028, "step": 8920 }, { "loss_action": 0.02818509005010128, "loss_total": 0.02818509005010128, "step": 8920 }, { "grad_norm": 0.5236548185348511, "learning_rate": 9.957855049755604e-05, "loss": 0.0259, "step": 8930 }, { "loss_action": 0.02525249868631363, "loss_total": 0.02525249868631363, "step": 8930 }, { "grad_norm": 0.5648311376571655, "learning_rate": 9.957640547852593e-05, "loss": 0.0254, "step": 8940 }, { "loss_action": 0.03014475293457508, "loss_total": 0.03014475293457508, "step": 8940 }, { "grad_norm": 0.6960701942443848, "learning_rate": 9.957425503789466e-05, "loss": 0.0263, "step": 8950 }, { "loss_action": 0.026951204985380173, "loss_total": 0.026951204985380173, "step": 8950 }, { "grad_norm": 0.467221736907959, "learning_rate": 9.957209917589738e-05, "loss": 0.0262, "step": 8960 }, { "loss_action": 0.02286064252257347, "loss_total": 0.02286064252257347, "step": 8960 }, { "grad_norm": 0.4297380745410919, "learning_rate": 9.956993789276987e-05, "loss": 0.0244, "step": 8970 }, { "loss_action": 0.02738061361014843, "loss_total": 0.02738061361014843, "step": 8970 }, { "grad_norm": 0.5040616393089294, "learning_rate": 9.956777118874847e-05, "loss": 0.0227, "step": 8980 }, { "loss_action": 0.027480866760015488, "loss_total": 0.027480866760015488, "step": 8980 }, { "grad_norm": 0.4140470325946808, "learning_rate": 9.956559906407016e-05, "loss": 0.0243, "step": 8990 }, { "loss_action": 0.019910039380192757, "loss_total": 0.019910039380192757, "step": 8990 }, { "grad_norm": 0.5623032450675964, "learning_rate": 9.956342151897245e-05, "loss": 0.0234, "step": 9000 }, { "loss_action": 0.023339342325925827, "loss_total": 0.023339342325925827, "step": 9000 }, { "grad_norm": 0.45271578431129456, "learning_rate": 9.956123855369346e-05, "loss": 0.0245, "step": 9010 }, { "loss_action": 0.022596325725317, "loss_total": 0.022596325725317, "step": 9010 }, { "grad_norm": 0.632264256477356, "learning_rate": 9.955905016847196e-05, "loss": 0.0261, "step": 9020 }, { "loss_action": 0.023843662813305855, "loss_total": 0.023843662813305855, "step": 9020 }, { "grad_norm": 0.4721885621547699, "learning_rate": 9.955685636354723e-05, "loss": 0.0258, "step": 9030 }, { "loss_action": 0.029328830540180206, "loss_total": 0.029328830540180206, "step": 9030 }, { "grad_norm": 0.7646363377571106, "learning_rate": 9.95546571391592e-05, "loss": 0.0262, "step": 9040 }, { "loss_action": 0.02817354165017605, "loss_total": 0.02817354165017605, "step": 9040 }, { "grad_norm": 0.45939362049102783, "learning_rate": 9.955245249554837e-05, "loss": 0.0265, "step": 9050 }, { "loss_action": 0.02577977627515793, "loss_total": 0.02577977627515793, "step": 9050 }, { "grad_norm": 0.590304434299469, "learning_rate": 9.955024243295582e-05, "loss": 0.0275, "step": 9060 }, { "loss_action": 0.025613002479076385, "loss_total": 0.025613002479076385, "step": 9060 }, { "grad_norm": 0.5791478753089905, "learning_rate": 9.954802695162328e-05, "loss": 0.0292, "step": 9070 }, { "loss_action": 0.023338042199611664, "loss_total": 0.023338042199611664, "step": 9070 }, { "grad_norm": 0.5730296969413757, "learning_rate": 9.954580605179302e-05, "loss": 0.0259, "step": 9080 }, { "loss_action": 0.03215567395091057, "loss_total": 0.03215567395091057, "step": 9080 }, { "grad_norm": 0.5830085277557373, "learning_rate": 9.954357973370788e-05, "loss": 0.0284, "step": 9090 }, { "loss_action": 0.02902287431061268, "loss_total": 0.02902287431061268, "step": 9090 }, { "grad_norm": 0.5084896683692932, "learning_rate": 9.954134799761135e-05, "loss": 0.0272, "step": 9100 }, { "loss_action": 0.025905927643179893, "loss_total": 0.025905927643179893, "step": 9100 }, { "grad_norm": 0.3665774166584015, "learning_rate": 9.953911084374748e-05, "loss": 0.0277, "step": 9110 }, { "loss_action": 0.037968993186950684, "loss_total": 0.037968993186950684, "step": 9110 }, { "grad_norm": 0.5161162614822388, "learning_rate": 9.953686827236093e-05, "loss": 0.0267, "step": 9120 }, { "loss_action": 0.025741007179021835, "loss_total": 0.025741007179021835, "step": 9120 }, { "grad_norm": 0.5470866560935974, "learning_rate": 9.953462028369695e-05, "loss": 0.024, "step": 9130 }, { "loss_action": 0.02665112167596817, "loss_total": 0.02665112167596817, "step": 9130 }, { "grad_norm": 0.5466944575309753, "learning_rate": 9.953236687800136e-05, "loss": 0.0281, "step": 9140 }, { "loss_action": 0.0335422158241272, "loss_total": 0.0335422158241272, "step": 9140 }, { "grad_norm": 0.608325719833374, "learning_rate": 9.95301080555206e-05, "loss": 0.029, "step": 9150 }, { "loss_action": 0.03095743991434574, "loss_total": 0.03095743991434574, "step": 9150 }, { "grad_norm": 0.5006709694862366, "learning_rate": 9.952784381650171e-05, "loss": 0.0283, "step": 9160 }, { "loss_action": 0.03543873131275177, "loss_total": 0.03543873131275177, "step": 9160 }, { "grad_norm": 0.4338286221027374, "learning_rate": 9.952557416119226e-05, "loss": 0.0299, "step": 9170 }, { "loss_action": 0.023612646386027336, "loss_total": 0.023612646386027336, "step": 9170 }, { "grad_norm": 0.4836024343967438, "learning_rate": 9.95232990898405e-05, "loss": 0.0244, "step": 9180 }, { "loss_action": 0.024022946134209633, "loss_total": 0.024022946134209633, "step": 9180 }, { "grad_norm": 0.515143632888794, "learning_rate": 9.95210186026952e-05, "loss": 0.0246, "step": 9190 }, { "loss_action": 0.03188472241163254, "loss_total": 0.03188472241163254, "step": 9190 }, { "grad_norm": 0.6562073826789856, "learning_rate": 9.951873270000576e-05, "loss": 0.0252, "step": 9200 }, { "loss_action": 0.02534463442862034, "loss_total": 0.02534463442862034, "step": 9200 }, { "grad_norm": 0.5055083632469177, "learning_rate": 9.951644138202216e-05, "loss": 0.0281, "step": 9210 }, { "loss_action": 0.023552466183900833, "loss_total": 0.023552466183900833, "step": 9210 }, { "grad_norm": 0.5246383547782898, "learning_rate": 9.951414464899498e-05, "loss": 0.0255, "step": 9220 }, { "loss_action": 0.020625581964850426, "loss_total": 0.020625581964850426, "step": 9220 }, { "grad_norm": 0.43443259596824646, "learning_rate": 9.951184250117538e-05, "loss": 0.0253, "step": 9230 }, { "loss_action": 0.032593052834272385, "loss_total": 0.032593052834272385, "step": 9230 }, { "grad_norm": 0.5338173508644104, "learning_rate": 9.950953493881513e-05, "loss": 0.0235, "step": 9240 }, { "loss_action": 0.02557460032403469, "loss_total": 0.02557460032403469, "step": 9240 }, { "grad_norm": 0.37833982706069946, "learning_rate": 9.950722196216658e-05, "loss": 0.0245, "step": 9250 }, { "loss_action": 0.02676638588309288, "loss_total": 0.02676638588309288, "step": 9250 }, { "grad_norm": 0.7106869220733643, "learning_rate": 9.950490357148265e-05, "loss": 0.0308, "step": 9260 }, { "loss_action": 0.03058777004480362, "loss_total": 0.03058777004480362, "step": 9260 }, { "grad_norm": 0.48801836371421814, "learning_rate": 9.950257976701692e-05, "loss": 0.0322, "step": 9270 }, { "loss_action": 0.03132788836956024, "loss_total": 0.03132788836956024, "step": 9270 }, { "grad_norm": 0.49205800890922546, "learning_rate": 9.950025054902348e-05, "loss": 0.0286, "step": 9280 }, { "loss_action": 0.02825333923101425, "loss_total": 0.02825333923101425, "step": 9280 }, { "grad_norm": 0.5110257863998413, "learning_rate": 9.949791591775706e-05, "loss": 0.0288, "step": 9290 }, { "loss_action": 0.029482774436473846, "loss_total": 0.029482774436473846, "step": 9290 }, { "grad_norm": 0.6966412663459778, "learning_rate": 9.949557587347298e-05, "loss": 0.0285, "step": 9300 }, { "loss_action": 0.034092649817466736, "loss_total": 0.034092649817466736, "step": 9300 }, { "grad_norm": 0.47103700041770935, "learning_rate": 9.949323041642713e-05, "loss": 0.0265, "step": 9310 }, { "loss_action": 0.028876055032014847, "loss_total": 0.028876055032014847, "step": 9310 }, { "grad_norm": 0.5792636275291443, "learning_rate": 9.949087954687602e-05, "loss": 0.0298, "step": 9320 }, { "loss_action": 0.02430073916912079, "loss_total": 0.02430073916912079, "step": 9320 }, { "grad_norm": 0.4024140238761902, "learning_rate": 9.948852326507672e-05, "loss": 0.0254, "step": 9330 }, { "loss_action": 0.020930131897330284, "loss_total": 0.020930131897330284, "step": 9330 }, { "grad_norm": 0.6824281215667725, "learning_rate": 9.948616157128694e-05, "loss": 0.023, "step": 9340 }, { "loss_action": 0.025652291253209114, "loss_total": 0.025652291253209114, "step": 9340 }, { "grad_norm": 0.486541748046875, "learning_rate": 9.948379446576493e-05, "loss": 0.0296, "step": 9350 }, { "loss_action": 0.029693705961108208, "loss_total": 0.029693705961108208, "step": 9350 }, { "grad_norm": 0.4959268271923065, "learning_rate": 9.948142194876952e-05, "loss": 0.029, "step": 9360 }, { "loss_action": 0.0244516059756279, "loss_total": 0.0244516059756279, "step": 9360 }, { "grad_norm": 0.4665455222129822, "learning_rate": 9.947904402056024e-05, "loss": 0.0272, "step": 9370 }, { "loss_action": 0.029487406834959984, "loss_total": 0.029487406834959984, "step": 9370 }, { "grad_norm": 0.5049009323120117, "learning_rate": 9.947666068139708e-05, "loss": 0.0261, "step": 9380 }, { "loss_action": 0.028108885511755943, "loss_total": 0.028108885511755943, "step": 9380 }, { "grad_norm": 0.5776688456535339, "learning_rate": 9.947427193154071e-05, "loss": 0.0274, "step": 9390 }, { "loss_action": 0.02102719247341156, "loss_total": 0.02102719247341156, "step": 9390 }, { "grad_norm": 0.4691135585308075, "learning_rate": 9.947187777125233e-05, "loss": 0.0235, "step": 9400 }, { "loss_action": 0.030233697965741158, "loss_total": 0.030233697965741158, "step": 9400 }, { "grad_norm": 0.7160501480102539, "learning_rate": 9.946947820079377e-05, "loss": 0.0277, "step": 9410 }, { "loss_action": 0.027180548757314682, "loss_total": 0.027180548757314682, "step": 9410 }, { "grad_norm": 0.561042070388794, "learning_rate": 9.946707322042747e-05, "loss": 0.031, "step": 9420 }, { "loss_action": 0.030202772468328476, "loss_total": 0.030202772468328476, "step": 9420 }, { "grad_norm": 0.52689528465271, "learning_rate": 9.94646628304164e-05, "loss": 0.0292, "step": 9430 }, { "loss_action": 0.023659374564886093, "loss_total": 0.023659374564886093, "step": 9430 }, { "grad_norm": 0.5457445383071899, "learning_rate": 9.946224703102418e-05, "loss": 0.0243, "step": 9440 }, { "loss_action": 0.024344120174646378, "loss_total": 0.024344120174646378, "step": 9440 }, { "grad_norm": 0.41894057393074036, "learning_rate": 9.945982582251498e-05, "loss": 0.0235, "step": 9450 }, { "loss_action": 0.018464399501681328, "loss_total": 0.018464399501681328, "step": 9450 }, { "grad_norm": 0.468914270401001, "learning_rate": 9.94573992051536e-05, "loss": 0.023, "step": 9460 }, { "loss_action": 0.02192322351038456, "loss_total": 0.02192322351038456, "step": 9460 }, { "grad_norm": 0.44148939847946167, "learning_rate": 9.94549671792054e-05, "loss": 0.0212, "step": 9470 }, { "loss_action": 0.024558091536164284, "loss_total": 0.024558091536164284, "step": 9470 }, { "grad_norm": 0.4595925509929657, "learning_rate": 9.945252974493635e-05, "loss": 0.0238, "step": 9480 }, { "loss_action": 0.03153339773416519, "loss_total": 0.03153339773416519, "step": 9480 }, { "grad_norm": 0.5018813610076904, "learning_rate": 9.9450086902613e-05, "loss": 0.0254, "step": 9490 }, { "loss_action": 0.0221591554582119, "loss_total": 0.0221591554582119, "step": 9490 }, { "grad_norm": 0.4731517732143402, "learning_rate": 9.944763865250248e-05, "loss": 0.026, "step": 9500 }, { "loss_action": 0.02162562496960163, "loss_total": 0.02162562496960163, "step": 9500 }, { "grad_norm": 0.5158859491348267, "learning_rate": 9.944518499487254e-05, "loss": 0.0239, "step": 9510 }, { "loss_action": 0.024991702288389206, "loss_total": 0.024991702288389206, "step": 9510 }, { "grad_norm": 0.5406782031059265, "learning_rate": 9.944272592999151e-05, "loss": 0.0258, "step": 9520 }, { "loss_action": 0.02063678205013275, "loss_total": 0.02063678205013275, "step": 9520 }, { "grad_norm": 0.6028642654418945, "learning_rate": 9.94402614581283e-05, "loss": 0.0262, "step": 9530 }, { "loss_action": 0.030831165611743927, "loss_total": 0.030831165611743927, "step": 9530 }, { "grad_norm": 0.4544227719306946, "learning_rate": 9.943779157955244e-05, "loss": 0.0272, "step": 9540 }, { "loss_action": 0.030489766970276833, "loss_total": 0.030489766970276833, "step": 9540 }, { "grad_norm": 0.8283273577690125, "learning_rate": 9.943531629453403e-05, "loss": 0.0269, "step": 9550 }, { "loss_action": 0.04137894883751869, "loss_total": 0.04137894883751869, "step": 9550 }, { "grad_norm": 0.5965924263000488, "learning_rate": 9.943283560334375e-05, "loss": 0.0345, "step": 9560 }, { "loss_action": 0.029108859598636627, "loss_total": 0.029108859598636627, "step": 9560 }, { "grad_norm": 0.7359400987625122, "learning_rate": 9.943034950625288e-05, "loss": 0.0353, "step": 9570 }, { "loss_action": 0.022256087511777878, "loss_total": 0.022256087511777878, "step": 9570 }, { "grad_norm": 0.5206573009490967, "learning_rate": 9.942785800353332e-05, "loss": 0.0323, "step": 9580 }, { "loss_action": 0.03352481871843338, "loss_total": 0.03352481871843338, "step": 9580 }, { "grad_norm": 0.4993250370025635, "learning_rate": 9.942536109545751e-05, "loss": 0.0287, "step": 9590 }, { "loss_action": 0.02407045103609562, "loss_total": 0.02407045103609562, "step": 9590 }, { "grad_norm": 0.4990997314453125, "learning_rate": 9.942285878229853e-05, "loss": 0.0277, "step": 9600 }, { "loss_action": 0.025380555540323257, "loss_total": 0.025380555540323257, "step": 9600 }, { "grad_norm": 0.4443775415420532, "learning_rate": 9.942035106433001e-05, "loss": 0.0281, "step": 9610 }, { "loss_action": 0.028191661462187767, "loss_total": 0.028191661462187767, "step": 9610 }, { "grad_norm": 0.5419775247573853, "learning_rate": 9.94178379418262e-05, "loss": 0.0267, "step": 9620 }, { "loss_action": 0.019547130912542343, "loss_total": 0.019547130912542343, "step": 9620 }, { "grad_norm": 0.4316558539867401, "learning_rate": 9.941531941506194e-05, "loss": 0.0245, "step": 9630 }, { "loss_action": 0.019714804366230965, "loss_total": 0.019714804366230965, "step": 9630 }, { "grad_norm": 0.5411370992660522, "learning_rate": 9.941279548431263e-05, "loss": 0.0288, "step": 9640 }, { "loss_action": 0.025347482413053513, "loss_total": 0.025347482413053513, "step": 9640 }, { "grad_norm": 0.6101707220077515, "learning_rate": 9.941026614985431e-05, "loss": 0.0264, "step": 9650 }, { "loss_action": 0.027344273403286934, "loss_total": 0.027344273403286934, "step": 9650 }, { "grad_norm": 0.5892508029937744, "learning_rate": 9.940773141196357e-05, "loss": 0.0315, "step": 9660 }, { "loss_action": 0.02901925891637802, "loss_total": 0.02901925891637802, "step": 9660 }, { "grad_norm": 0.4595535695552826, "learning_rate": 9.94051912709176e-05, "loss": 0.0276, "step": 9670 }, { "loss_action": 0.027084538713097572, "loss_total": 0.027084538713097572, "step": 9670 }, { "grad_norm": 0.6365921497344971, "learning_rate": 9.940264572699421e-05, "loss": 0.0295, "step": 9680 }, { "loss_action": 0.029763570055365562, "loss_total": 0.029763570055365562, "step": 9680 }, { "grad_norm": 0.6567317843437195, "learning_rate": 9.940009478047174e-05, "loss": 0.0302, "step": 9690 }, { "loss_action": 0.03161229193210602, "loss_total": 0.03161229193210602, "step": 9690 }, { "grad_norm": 0.5573370456695557, "learning_rate": 9.939753843162918e-05, "loss": 0.0285, "step": 9700 }, { "loss_action": 0.02610750123858452, "loss_total": 0.02610750123858452, "step": 9700 }, { "grad_norm": 0.5941888093948364, "learning_rate": 9.939497668074609e-05, "loss": 0.03, "step": 9710 }, { "loss_action": 0.02776760794222355, "loss_total": 0.02776760794222355, "step": 9710 }, { "grad_norm": 0.5510679483413696, "learning_rate": 9.93924095281026e-05, "loss": 0.028, "step": 9720 }, { "loss_action": 0.025231007486581802, "loss_total": 0.025231007486581802, "step": 9720 }, { "grad_norm": 0.6414505243301392, "learning_rate": 9.938983697397948e-05, "loss": 0.0299, "step": 9730 }, { "loss_action": 0.0330146849155426, "loss_total": 0.0330146849155426, "step": 9730 }, { "grad_norm": 1.0355709791183472, "learning_rate": 9.938725901865805e-05, "loss": 0.0391, "step": 9740 }, { "loss_action": 0.03255295380949974, "loss_total": 0.03255295380949974, "step": 9740 }, { "grad_norm": 0.8064544200897217, "learning_rate": 9.93846756624202e-05, "loss": 0.0401, "step": 9750 }, { "loss_action": 0.04356341063976288, "loss_total": 0.04356341063976288, "step": 9750 }, { "grad_norm": 0.9827566742897034, "learning_rate": 9.938208690554849e-05, "loss": 0.0466, "step": 9760 }, { "loss_action": 0.05139901861548424, "loss_total": 0.05139901861548424, "step": 9760 }, { "grad_norm": 1.3885964155197144, "learning_rate": 9.9379492748326e-05, "loss": 0.0492, "step": 9770 }, { "loss_action": 0.06894738972187042, "loss_total": 0.06894738972187042, "step": 9770 }, { "grad_norm": 1.2691208124160767, "learning_rate": 9.937689319103641e-05, "loss": 0.0625, "step": 9780 }, { "loss_action": 0.046372413635253906, "loss_total": 0.046372413635253906, "step": 9780 }, { "grad_norm": 0.8343265652656555, "learning_rate": 9.937428823396404e-05, "loss": 0.0434, "step": 9790 }, { "loss_action": 0.048467256128787994, "loss_total": 0.048467256128787994, "step": 9790 }, { "grad_norm": 0.6816955804824829, "learning_rate": 9.937167787739372e-05, "loss": 0.0484, "step": 9800 }, { "loss_action": 0.04253704100847244, "loss_total": 0.04253704100847244, "step": 9800 }, { "grad_norm": 0.7106035947799683, "learning_rate": 9.936906212161095e-05, "loss": 0.0408, "step": 9810 }, { "loss_action": 0.05341977998614311, "loss_total": 0.05341977998614311, "step": 9810 }, { "grad_norm": 0.513205349445343, "learning_rate": 9.936644096690176e-05, "loss": 0.0357, "step": 9820 }, { "loss_action": 0.03608231246471405, "loss_total": 0.03608231246471405, "step": 9820 }, { "grad_norm": 0.600601851940155, "learning_rate": 9.936381441355282e-05, "loss": 0.0384, "step": 9830 }, { "loss_action": 0.034045420587062836, "loss_total": 0.034045420587062836, "step": 9830 }, { "grad_norm": 0.620913565158844, "learning_rate": 9.936118246185136e-05, "loss": 0.0345, "step": 9840 }, { "loss_action": 0.02514280378818512, "loss_total": 0.02514280378818512, "step": 9840 }, { "grad_norm": 0.637148380279541, "learning_rate": 9.935854511208518e-05, "loss": 0.0332, "step": 9850 }, { "loss_action": 0.03864160552620888, "loss_total": 0.03864160552620888, "step": 9850 }, { "grad_norm": 0.5305306315422058, "learning_rate": 9.935590236454272e-05, "loss": 0.033, "step": 9860 }, { "loss_action": 0.02946372888982296, "loss_total": 0.02946372888982296, "step": 9860 }, { "grad_norm": 0.4401465058326721, "learning_rate": 9.935325421951298e-05, "loss": 0.0333, "step": 9870 }, { "loss_action": 0.02761385589838028, "loss_total": 0.02761385589838028, "step": 9870 }, { "grad_norm": 0.6084761023521423, "learning_rate": 9.935060067728557e-05, "loss": 0.033, "step": 9880 }, { "loss_action": 0.03621724247932434, "loss_total": 0.03621724247932434, "step": 9880 }, { "grad_norm": 0.458731472492218, "learning_rate": 9.934794173815067e-05, "loss": 0.0269, "step": 9890 }, { "loss_action": 0.02717430889606476, "loss_total": 0.02717430889606476, "step": 9890 }, { "grad_norm": 0.5589230060577393, "learning_rate": 9.934527740239906e-05, "loss": 0.0313, "step": 9900 }, { "loss_action": 0.026251988485455513, "loss_total": 0.026251988485455513, "step": 9900 }, { "grad_norm": 0.48372870683670044, "learning_rate": 9.934260767032209e-05, "loss": 0.0286, "step": 9910 }, { "loss_action": 0.022989865392446518, "loss_total": 0.022989865392446518, "step": 9910 }, { "grad_norm": 0.4366505742073059, "learning_rate": 9.933993254221172e-05, "loss": 0.0255, "step": 9920 }, { "loss_action": 0.025322958827018738, "loss_total": 0.025322958827018738, "step": 9920 }, { "grad_norm": 0.4716244041919708, "learning_rate": 9.933725201836053e-05, "loss": 0.0257, "step": 9930 }, { "loss_action": 0.023169485852122307, "loss_total": 0.023169485852122307, "step": 9930 }, { "grad_norm": 0.5888099670410156, "learning_rate": 9.933456609906162e-05, "loss": 0.0271, "step": 9940 }, { "loss_action": 0.026128049939870834, "loss_total": 0.026128049939870834, "step": 9940 }, { "grad_norm": 0.5151963233947754, "learning_rate": 9.933187478460875e-05, "loss": 0.0265, "step": 9950 }, { "loss_action": 0.024525359272956848, "loss_total": 0.024525359272956848, "step": 9950 }, { "grad_norm": 0.36658281087875366, "learning_rate": 9.93291780752962e-05, "loss": 0.0286, "step": 9960 }, { "loss_action": 0.025012806057929993, "loss_total": 0.025012806057929993, "step": 9960 }, { "grad_norm": 0.41628941893577576, "learning_rate": 9.932647597141893e-05, "loss": 0.0272, "step": 9970 }, { "loss_action": 0.027479181066155434, "loss_total": 0.027479181066155434, "step": 9970 }, { "grad_norm": 0.5746884346008301, "learning_rate": 9.932376847327239e-05, "loss": 0.0281, "step": 9980 }, { "loss_action": 0.028764799237251282, "loss_total": 0.028764799237251282, "step": 9980 }, { "grad_norm": 0.502919614315033, "learning_rate": 9.932105558115268e-05, "loss": 0.023, "step": 9990 }, { "loss_action": 0.026459304615855217, "loss_total": 0.026459304615855217, "step": 9990 }, { "grad_norm": 0.4708450138568878, "learning_rate": 9.931833729535651e-05, "loss": 0.0253, "step": 10000 }, { "loss_action": 0.021838082000613213, "loss_total": 0.021838082000613213, "step": 10000 }, { "grad_norm": 0.4461027681827545, "learning_rate": 9.931561361618111e-05, "loss": 0.0235, "step": 10010 }, { "loss_action": 0.0227997787296772, "loss_total": 0.0227997787296772, "step": 10010 }, { "grad_norm": 0.5078397989273071, "learning_rate": 9.931288454392435e-05, "loss": 0.0253, "step": 10020 }, { "loss_action": 0.02517792396247387, "loss_total": 0.02517792396247387, "step": 10020 }, { "grad_norm": 0.36296120285987854, "learning_rate": 9.931015007888467e-05, "loss": 0.0226, "step": 10030 }, { "loss_action": 0.0188495721668005, "loss_total": 0.0188495721668005, "step": 10030 }, { "grad_norm": 0.5815931558609009, "learning_rate": 9.930741022136112e-05, "loss": 0.0242, "step": 10040 }, { "loss_action": 0.02867412567138672, "loss_total": 0.02867412567138672, "step": 10040 }, { "grad_norm": 0.4469257593154907, "learning_rate": 9.930466497165333e-05, "loss": 0.0235, "step": 10050 }, { "loss_action": 0.02066337689757347, "loss_total": 0.02066337689757347, "step": 10050 }, { "grad_norm": 0.5568402409553528, "learning_rate": 9.93019143300615e-05, "loss": 0.0237, "step": 10060 }, { "loss_action": 0.030051784589886665, "loss_total": 0.030051784589886665, "step": 10060 }, { "grad_norm": 0.6223722100257874, "learning_rate": 9.929915829688644e-05, "loss": 0.0259, "step": 10070 }, { "loss_action": 0.01959202066063881, "loss_total": 0.01959202066063881, "step": 10070 }, { "grad_norm": 0.5837752223014832, "learning_rate": 9.929639687242955e-05, "loss": 0.0245, "step": 10080 }, { "loss_action": 0.020325882360339165, "loss_total": 0.020325882360339165, "step": 10080 }, { "grad_norm": 0.4255390167236328, "learning_rate": 9.929363005699281e-05, "loss": 0.0237, "step": 10090 }, { "loss_action": 0.021396387368440628, "loss_total": 0.021396387368440628, "step": 10090 }, { "grad_norm": 0.42503076791763306, "learning_rate": 9.92908578508788e-05, "loss": 0.0238, "step": 10100 }, { "loss_action": 0.022324951365590096, "loss_total": 0.022324951365590096, "step": 10100 }, { "grad_norm": 0.6419380903244019, "learning_rate": 9.928808025439069e-05, "loss": 0.0237, "step": 10110 }, { "loss_action": 0.02389625273644924, "loss_total": 0.02389625273644924, "step": 10110 }, { "grad_norm": 0.46999457478523254, "learning_rate": 9.928529726783223e-05, "loss": 0.0249, "step": 10120 }, { "loss_action": 0.027759239077568054, "loss_total": 0.027759239077568054, "step": 10120 }, { "grad_norm": 0.4669170379638672, "learning_rate": 9.928250889150774e-05, "loss": 0.0261, "step": 10130 }, { "loss_action": 0.02601132169365883, "loss_total": 0.02601132169365883, "step": 10130 }, { "grad_norm": 0.9535101652145386, "learning_rate": 9.92797151257222e-05, "loss": 0.0277, "step": 10140 }, { "loss_action": 0.028795309364795685, "loss_total": 0.028795309364795685, "step": 10140 }, { "grad_norm": 0.5331063270568848, "learning_rate": 9.927691597078108e-05, "loss": 0.0312, "step": 10150 }, { "loss_action": 0.031869854778051376, "loss_total": 0.031869854778051376, "step": 10150 }, { "grad_norm": 0.5147456526756287, "learning_rate": 9.927411142699053e-05, "loss": 0.0291, "step": 10160 }, { "loss_action": 0.024665066972374916, "loss_total": 0.024665066972374916, "step": 10160 }, { "grad_norm": 0.4532717168331146, "learning_rate": 9.927130149465725e-05, "loss": 0.0276, "step": 10170 }, { "loss_action": 0.025215134024620056, "loss_total": 0.025215134024620056, "step": 10170 }, { "grad_norm": 0.48334288597106934, "learning_rate": 9.92684861740885e-05, "loss": 0.0259, "step": 10180 }, { "loss_action": 0.0237518772482872, "loss_total": 0.0237518772482872, "step": 10180 }, { "grad_norm": 0.6008232831954956, "learning_rate": 9.926566546559217e-05, "loss": 0.0281, "step": 10190 }, { "loss_action": 0.02098117023706436, "loss_total": 0.02098117023706436, "step": 10190 }, { "grad_norm": 0.5563509464263916, "learning_rate": 9.926283936947673e-05, "loss": 0.0267, "step": 10200 }, { "loss_action": 0.026224136352539062, "loss_total": 0.026224136352539062, "step": 10200 }, { "grad_norm": 0.3871767222881317, "learning_rate": 9.926000788605126e-05, "loss": 0.0238, "step": 10210 }, { "loss_action": 0.02437319979071617, "loss_total": 0.02437319979071617, "step": 10210 }, { "grad_norm": 0.6551507711410522, "learning_rate": 9.92571710156254e-05, "loss": 0.0275, "step": 10220 }, { "loss_action": 0.02599351853132248, "loss_total": 0.02599351853132248, "step": 10220 }, { "grad_norm": 0.570025622844696, "learning_rate": 9.925432875850936e-05, "loss": 0.0253, "step": 10230 }, { "loss_action": 0.023155640810728073, "loss_total": 0.023155640810728073, "step": 10230 }, { "grad_norm": 0.6732288599014282, "learning_rate": 9.925148111501396e-05, "loss": 0.0317, "step": 10240 }, { "loss_action": 0.024055203422904015, "loss_total": 0.024055203422904015, "step": 10240 }, { "grad_norm": 0.5508769154548645, "learning_rate": 9.924862808545066e-05, "loss": 0.0255, "step": 10250 }, { "loss_action": 0.03328846022486687, "loss_total": 0.03328846022486687, "step": 10250 }, { "grad_norm": 0.5594253540039062, "learning_rate": 9.924576967013141e-05, "loss": 0.0271, "step": 10260 }, { "loss_action": 0.02951396442949772, "loss_total": 0.02951396442949772, "step": 10260 }, { "grad_norm": 0.6328586935997009, "learning_rate": 9.924290586936887e-05, "loss": 0.0263, "step": 10270 }, { "loss_action": 0.019474947825074196, "loss_total": 0.019474947825074196, "step": 10270 }, { "grad_norm": 0.5654677748680115, "learning_rate": 9.924003668347614e-05, "loss": 0.0269, "step": 10280 }, { "loss_action": 0.02846185304224491, "loss_total": 0.02846185304224491, "step": 10280 }, { "grad_norm": 0.672439694404602, "learning_rate": 9.923716211276704e-05, "loss": 0.0294, "step": 10290 }, { "loss_action": 0.024272724986076355, "loss_total": 0.024272724986076355, "step": 10290 }, { "grad_norm": 0.49229443073272705, "learning_rate": 9.923428215755594e-05, "loss": 0.0285, "step": 10300 }, { "loss_action": 0.030541658401489258, "loss_total": 0.030541658401489258, "step": 10300 }, { "grad_norm": 0.40706971287727356, "learning_rate": 9.923139681815775e-05, "loss": 0.0241, "step": 10310 }, { "loss_action": 0.02452898398041725, "loss_total": 0.02452898398041725, "step": 10310 }, { "grad_norm": 0.4422120451927185, "learning_rate": 9.922850609488801e-05, "loss": 0.0237, "step": 10320 }, { "loss_action": 0.019434761255979538, "loss_total": 0.019434761255979538, "step": 10320 }, { "grad_norm": 0.4009549021720886, "learning_rate": 9.922560998806287e-05, "loss": 0.0219, "step": 10330 }, { "loss_action": 0.024867305532097816, "loss_total": 0.024867305532097816, "step": 10330 }, { "grad_norm": 0.4209223985671997, "learning_rate": 9.922270849799905e-05, "loss": 0.0231, "step": 10340 }, { "loss_action": 0.022342363372445107, "loss_total": 0.022342363372445107, "step": 10340 }, { "grad_norm": 0.4996240437030792, "learning_rate": 9.92198016250138e-05, "loss": 0.0249, "step": 10350 }, { "loss_action": 0.029044345021247864, "loss_total": 0.029044345021247864, "step": 10350 }, { "grad_norm": 0.46839770674705505, "learning_rate": 9.921688936942506e-05, "loss": 0.0278, "step": 10360 }, { "loss_action": 0.02370983548462391, "loss_total": 0.02370983548462391, "step": 10360 }, { "grad_norm": 0.5221248865127563, "learning_rate": 9.921397173155129e-05, "loss": 0.0246, "step": 10370 }, { "loss_action": 0.026618124917149544, "loss_total": 0.026618124917149544, "step": 10370 }, { "grad_norm": 0.388830304145813, "learning_rate": 9.921104871171157e-05, "loss": 0.0223, "step": 10380 }, { "loss_action": 0.0299599077552557, "loss_total": 0.0299599077552557, "step": 10380 }, { "grad_norm": 0.43121832609176636, "learning_rate": 9.920812031022554e-05, "loss": 0.0235, "step": 10390 }, { "loss_action": 0.023271068930625916, "loss_total": 0.023271068930625916, "step": 10390 }, { "grad_norm": 0.4358574450016022, "learning_rate": 9.920518652741348e-05, "loss": 0.0238, "step": 10400 }, { "loss_action": 0.02673131413757801, "loss_total": 0.02673131413757801, "step": 10400 }, { "grad_norm": 0.7626355886459351, "learning_rate": 9.920224736359618e-05, "loss": 0.025, "step": 10410 }, { "loss_action": 0.031539201736450195, "loss_total": 0.031539201736450195, "step": 10410 }, { "grad_norm": 0.42068472504615784, "learning_rate": 9.91993028190951e-05, "loss": 0.0259, "step": 10420 }, { "loss_action": 0.02496296353638172, "loss_total": 0.02496296353638172, "step": 10420 }, { "grad_norm": 0.6563087105751038, "learning_rate": 9.919635289423222e-05, "loss": 0.0268, "step": 10430 }, { "loss_action": 0.03469715639948845, "loss_total": 0.03469715639948845, "step": 10430 }, { "grad_norm": 0.3912523090839386, "learning_rate": 9.919339758933015e-05, "loss": 0.0263, "step": 10440 }, { "loss_action": 0.025193454697728157, "loss_total": 0.025193454697728157, "step": 10440 }, { "grad_norm": 0.5513988733291626, "learning_rate": 9.919043690471209e-05, "loss": 0.0255, "step": 10450 }, { "loss_action": 0.026816394180059433, "loss_total": 0.026816394180059433, "step": 10450 }, { "grad_norm": 0.4901029169559479, "learning_rate": 9.91874708407018e-05, "loss": 0.0252, "step": 10460 }, { "loss_action": 0.022663196548819542, "loss_total": 0.022663196548819542, "step": 10460 }, { "grad_norm": 0.3824107050895691, "learning_rate": 9.918449939762367e-05, "loss": 0.025, "step": 10470 }, { "loss_action": 0.025952370837330818, "loss_total": 0.025952370837330818, "step": 10470 }, { "grad_norm": 0.4814654290676117, "learning_rate": 9.91815225758026e-05, "loss": 0.025, "step": 10480 }, { "loss_action": 0.030728185549378395, "loss_total": 0.030728185549378395, "step": 10480 }, { "grad_norm": 0.6307049989700317, "learning_rate": 9.917854037556419e-05, "loss": 0.0239, "step": 10490 }, { "loss_action": 0.02848723717033863, "loss_total": 0.02848723717033863, "step": 10490 }, { "grad_norm": 0.5210148692131042, "learning_rate": 9.917555279723454e-05, "loss": 0.027, "step": 10500 }, { "loss_action": 0.0212860107421875, "loss_total": 0.0212860107421875, "step": 10500 }, { "grad_norm": 0.49868810176849365, "learning_rate": 9.917255984114036e-05, "loss": 0.0231, "step": 10510 }, { "loss_action": 0.023287693038582802, "loss_total": 0.023287693038582802, "step": 10510 }, { "grad_norm": 0.4589836597442627, "learning_rate": 9.916956150760896e-05, "loss": 0.0246, "step": 10520 }, { "loss_action": 0.024490036070346832, "loss_total": 0.024490036070346832, "step": 10520 }, { "grad_norm": 0.5047275424003601, "learning_rate": 9.916655779696826e-05, "loss": 0.0257, "step": 10530 }, { "loss_action": 0.02488773874938488, "loss_total": 0.02488773874938488, "step": 10530 }, { "grad_norm": 0.5175179839134216, "learning_rate": 9.916354870954671e-05, "loss": 0.026, "step": 10540 }, { "loss_action": 0.023068038746714592, "loss_total": 0.023068038746714592, "step": 10540 }, { "grad_norm": 0.42411351203918457, "learning_rate": 9.91605342456734e-05, "loss": 0.0254, "step": 10550 }, { "loss_action": 0.025476155802607536, "loss_total": 0.025476155802607536, "step": 10550 }, { "grad_norm": 0.4267095923423767, "learning_rate": 9.915751440567795e-05, "loss": 0.0213, "step": 10560 }, { "loss_action": 0.02065443992614746, "loss_total": 0.02065443992614746, "step": 10560 }, { "grad_norm": 0.6157150864601135, "learning_rate": 9.915448918989066e-05, "loss": 0.0232, "step": 10570 }, { "loss_action": 0.030565906316041946, "loss_total": 0.030565906316041946, "step": 10570 }, { "grad_norm": 0.46746203303337097, "learning_rate": 9.915145859864232e-05, "loss": 0.0235, "step": 10580 }, { "loss_action": 0.01885927841067314, "loss_total": 0.01885927841067314, "step": 10580 }, { "grad_norm": 0.9474408626556396, "learning_rate": 9.914842263226437e-05, "loss": 0.0306, "step": 10590 }, { "loss_action": 0.02831742726266384, "loss_total": 0.02831742726266384, "step": 10590 }, { "grad_norm": 0.5485817193984985, "learning_rate": 9.914538129108882e-05, "loss": 0.0284, "step": 10600 }, { "loss_action": 0.024611257016658783, "loss_total": 0.024611257016658783, "step": 10600 }, { "grad_norm": 0.5316389203071594, "learning_rate": 9.914233457544825e-05, "loss": 0.0272, "step": 10610 }, { "loss_action": 0.023335149511694908, "loss_total": 0.023335149511694908, "step": 10610 }, { "grad_norm": 0.49234554171562195, "learning_rate": 9.913928248567586e-05, "loss": 0.0271, "step": 10620 }, { "loss_action": 0.023429516702890396, "loss_total": 0.023429516702890396, "step": 10620 }, { "grad_norm": 0.4688624143600464, "learning_rate": 9.913622502210542e-05, "loss": 0.0246, "step": 10630 }, { "loss_action": 0.028080198913812637, "loss_total": 0.028080198913812637, "step": 10630 }, { "grad_norm": 0.5364955067634583, "learning_rate": 9.913316218507128e-05, "loss": 0.0289, "step": 10640 }, { "loss_action": 0.0392894484102726, "loss_total": 0.0392894484102726, "step": 10640 }, { "grad_norm": 0.472924143075943, "learning_rate": 9.91300939749084e-05, "loss": 0.0267, "step": 10650 }, { "loss_action": 0.050291016697883606, "loss_total": 0.050291016697883606, "step": 10650 }, { "grad_norm": 0.47051435708999634, "learning_rate": 9.91270203919523e-05, "loss": 0.0262, "step": 10660 }, { "loss_action": 0.031565722078084946, "loss_total": 0.031565722078084946, "step": 10660 }, { "grad_norm": 0.5613824129104614, "learning_rate": 9.912394143653912e-05, "loss": 0.0265, "step": 10670 }, { "loss_action": 0.02338414639234543, "loss_total": 0.02338414639234543, "step": 10670 }, { "grad_norm": 0.5034571290016174, "learning_rate": 9.912085710900555e-05, "loss": 0.0257, "step": 10680 }, { "loss_action": 0.022959912195801735, "loss_total": 0.022959912195801735, "step": 10680 }, { "grad_norm": 0.46969500184059143, "learning_rate": 9.911776740968892e-05, "loss": 0.025, "step": 10690 }, { "loss_action": 0.020251356065273285, "loss_total": 0.020251356065273285, "step": 10690 }, { "grad_norm": 0.5011672973632812, "learning_rate": 9.911467233892709e-05, "loss": 0.0242, "step": 10700 }, { "loss_action": 0.019653337076306343, "loss_total": 0.019653337076306343, "step": 10700 }, { "grad_norm": 0.4925122559070587, "learning_rate": 9.911157189705853e-05, "loss": 0.0234, "step": 10710 }, { "loss_action": 0.023384345695376396, "loss_total": 0.023384345695376396, "step": 10710 }, { "grad_norm": 0.3900912404060364, "learning_rate": 9.910846608442229e-05, "loss": 0.0231, "step": 10720 }, { "loss_action": 0.027367817237973213, "loss_total": 0.027367817237973213, "step": 10720 }, { "grad_norm": 0.5693707466125488, "learning_rate": 9.910535490135805e-05, "loss": 0.0242, "step": 10730 }, { "loss_action": 0.021730277687311172, "loss_total": 0.021730277687311172, "step": 10730 }, { "grad_norm": 0.5511727333068848, "learning_rate": 9.910223834820603e-05, "loss": 0.0226, "step": 10740 }, { "loss_action": 0.023753013461828232, "loss_total": 0.023753013461828232, "step": 10740 }, { "grad_norm": 0.36062461137771606, "learning_rate": 9.909911642530703e-05, "loss": 0.0219, "step": 10750 }, { "loss_action": 0.026161110028624535, "loss_total": 0.026161110028624535, "step": 10750 }, { "grad_norm": 0.5680587291717529, "learning_rate": 9.909598913300249e-05, "loss": 0.0253, "step": 10760 }, { "loss_action": 0.018809013068675995, "loss_total": 0.018809013068675995, "step": 10760 }, { "grad_norm": 0.34879687428474426, "learning_rate": 9.909285647163438e-05, "loss": 0.0226, "step": 10770 }, { "loss_action": 0.0275313388556242, "loss_total": 0.0275313388556242, "step": 10770 }, { "grad_norm": 0.6799631714820862, "learning_rate": 9.908971844154531e-05, "loss": 0.0246, "step": 10780 }, { "loss_action": 0.020208826288580894, "loss_total": 0.020208826288580894, "step": 10780 }, { "grad_norm": 0.4973685145378113, "learning_rate": 9.908657504307843e-05, "loss": 0.024, "step": 10790 }, { "loss_action": 0.023714348673820496, "loss_total": 0.023714348673820496, "step": 10790 }, { "grad_norm": 0.5099071860313416, "learning_rate": 9.908342627657751e-05, "loss": 0.0224, "step": 10800 }, { "loss_action": 0.026697201654314995, "loss_total": 0.026697201654314995, "step": 10800 }, { "grad_norm": 0.5795334577560425, "learning_rate": 9.908027214238689e-05, "loss": 0.0255, "step": 10810 }, { "loss_action": 0.025282766669988632, "loss_total": 0.025282766669988632, "step": 10810 }, { "grad_norm": 0.5628902912139893, "learning_rate": 9.90771126408515e-05, "loss": 0.0251, "step": 10820 }, { "loss_action": 0.02645578607916832, "loss_total": 0.02645578607916832, "step": 10820 }, { "grad_norm": 0.5125296115875244, "learning_rate": 9.907394777231685e-05, "loss": 0.0215, "step": 10830 }, { "loss_action": 0.025205766782164574, "loss_total": 0.025205766782164574, "step": 10830 }, { "grad_norm": 0.759875476360321, "learning_rate": 9.907077753712905e-05, "loss": 0.0263, "step": 10840 }, { "loss_action": 0.025966450572013855, "loss_total": 0.025966450572013855, "step": 10840 }, { "grad_norm": 0.605378270149231, "learning_rate": 9.906760193563482e-05, "loss": 0.0282, "step": 10850 }, { "loss_action": 0.021295491605997086, "loss_total": 0.021295491605997086, "step": 10850 }, { "grad_norm": 0.5802412629127502, "learning_rate": 9.906442096818139e-05, "loss": 0.0297, "step": 10860 }, { "loss_action": 0.02821185439825058, "loss_total": 0.02821185439825058, "step": 10860 }, { "grad_norm": 0.35686540603637695, "learning_rate": 9.906123463511665e-05, "loss": 0.0276, "step": 10870 }, { "loss_action": 0.03126375377178192, "loss_total": 0.03126375377178192, "step": 10870 }, { "grad_norm": 1.0793169736862183, "learning_rate": 9.905804293678907e-05, "loss": 0.0328, "step": 10880 }, { "loss_action": 0.023904554545879364, "loss_total": 0.023904554545879364, "step": 10880 }, { "grad_norm": 0.4633610248565674, "learning_rate": 9.905484587354766e-05, "loss": 0.0301, "step": 10890 }, { "loss_action": 0.025399353355169296, "loss_total": 0.025399353355169296, "step": 10890 }, { "grad_norm": 0.7330312132835388, "learning_rate": 9.905164344574205e-05, "loss": 0.0356, "step": 10900 }, { "loss_action": 0.037836600095033646, "loss_total": 0.037836600095033646, "step": 10900 }, { "grad_norm": 0.7515223622322083, "learning_rate": 9.904843565372248e-05, "loss": 0.0365, "step": 10910 }, { "loss_action": 0.03910360485315323, "loss_total": 0.03910360485315323, "step": 10910 }, { "grad_norm": 0.5347037315368652, "learning_rate": 9.904522249783972e-05, "loss": 0.0313, "step": 10920 }, { "loss_action": 0.02740802802145481, "loss_total": 0.02740802802145481, "step": 10920 }, { "grad_norm": 0.6539056301116943, "learning_rate": 9.904200397844517e-05, "loss": 0.0303, "step": 10930 }, { "loss_action": 0.02986692637205124, "loss_total": 0.02986692637205124, "step": 10930 }, { "grad_norm": 0.7397406697273254, "learning_rate": 9.903878009589078e-05, "loss": 0.0303, "step": 10940 }, { "loss_action": 0.03395892679691315, "loss_total": 0.03395892679691315, "step": 10940 }, { "grad_norm": 0.5879645347595215, "learning_rate": 9.903555085052915e-05, "loss": 0.0339, "step": 10950 }, { "loss_action": 0.02704865112900734, "loss_total": 0.02704865112900734, "step": 10950 }, { "grad_norm": 0.9990863800048828, "learning_rate": 9.903231624271338e-05, "loss": 0.032, "step": 10960 }, { "loss_action": 0.03203430399298668, "loss_total": 0.03203430399298668, "step": 10960 }, { "grad_norm": 0.6016134023666382, "learning_rate": 9.902907627279724e-05, "loss": 0.034, "step": 10970 }, { "loss_action": 0.04415052756667137, "loss_total": 0.04415052756667137, "step": 10970 }, { "grad_norm": 0.5660319924354553, "learning_rate": 9.902583094113504e-05, "loss": 0.0303, "step": 10980 }, { "loss_action": 0.033234983682632446, "loss_total": 0.033234983682632446, "step": 10980 }, { "grad_norm": 1.569401741027832, "learning_rate": 9.902258024808168e-05, "loss": 0.0352, "step": 10990 }, { "loss_action": 0.02826549857854843, "loss_total": 0.02826549857854843, "step": 10990 }, { "grad_norm": 0.8040468096733093, "learning_rate": 9.901932419399264e-05, "loss": 0.0619, "step": 11000 }, { "loss_action": 0.0327298641204834, "loss_total": 0.0327298641204834, "step": 11000 }, { "grad_norm": 0.47157496213912964, "learning_rate": 9.9016062779224e-05, "loss": 0.0301, "step": 11010 }, { "loss_action": 0.02935805171728134, "loss_total": 0.02935805171728134, "step": 11010 }, { "grad_norm": 0.5028717517852783, "learning_rate": 9.901279600413242e-05, "loss": 0.0302, "step": 11020 }, { "loss_action": 0.027192139998078346, "loss_total": 0.027192139998078346, "step": 11020 }, { "grad_norm": 0.6902158856391907, "learning_rate": 9.900952386907518e-05, "loss": 0.0283, "step": 11030 }, { "loss_action": 0.04537297785282135, "loss_total": 0.04537297785282135, "step": 11030 }, { "grad_norm": 0.5470240712165833, "learning_rate": 9.90062463744101e-05, "loss": 0.0365, "step": 11040 }, { "loss_action": 0.035368770360946655, "loss_total": 0.035368770360946655, "step": 11040 }, { "grad_norm": 0.511635422706604, "learning_rate": 9.900296352049558e-05, "loss": 0.0301, "step": 11050 }, { "loss_action": 0.03078494407236576, "loss_total": 0.03078494407236576, "step": 11050 }, { "grad_norm": 0.4127490520477295, "learning_rate": 9.899967530769065e-05, "loss": 0.028, "step": 11060 }, { "loss_action": 0.024654153734445572, "loss_total": 0.024654153734445572, "step": 11060 }, { "grad_norm": 0.4652874171733856, "learning_rate": 9.899638173635489e-05, "loss": 0.0259, "step": 11070 }, { "loss_action": 0.024171365424990654, "loss_total": 0.024171365424990654, "step": 11070 }, { "grad_norm": 0.4408641457557678, "learning_rate": 9.899308280684849e-05, "loss": 0.0255, "step": 11080 }, { "loss_action": 0.027936097234487534, "loss_total": 0.027936097234487534, "step": 11080 }, { "grad_norm": 0.4390433132648468, "learning_rate": 9.898977851953222e-05, "loss": 0.025, "step": 11090 }, { "loss_action": 0.023115213960409164, "loss_total": 0.023115213960409164, "step": 11090 }, { "grad_norm": 0.4503920078277588, "learning_rate": 9.898646887476741e-05, "loss": 0.0246, "step": 11100 }, { "loss_action": 0.02315889485180378, "loss_total": 0.02315889485180378, "step": 11100 }, { "grad_norm": 0.41394346952438354, "learning_rate": 9.898315387291603e-05, "loss": 0.0253, "step": 11110 }, { "loss_action": 0.02874166890978813, "loss_total": 0.02874166890978813, "step": 11110 }, { "grad_norm": 0.5576856136322021, "learning_rate": 9.89798335143406e-05, "loss": 0.0245, "step": 11120 }, { "loss_action": 0.024704089388251305, "loss_total": 0.024704089388251305, "step": 11120 }, { "grad_norm": 0.4046788811683655, "learning_rate": 9.897650779940419e-05, "loss": 0.0234, "step": 11130 }, { "loss_action": 0.025209642946720123, "loss_total": 0.025209642946720123, "step": 11130 }, { "grad_norm": 0.41134199500083923, "learning_rate": 9.897317672847054e-05, "loss": 0.0229, "step": 11140 }, { "loss_action": 0.018204398453235626, "loss_total": 0.018204398453235626, "step": 11140 }, { "grad_norm": 0.5827271342277527, "learning_rate": 9.89698403019039e-05, "loss": 0.0263, "step": 11150 }, { "loss_action": 0.02598727121949196, "loss_total": 0.02598727121949196, "step": 11150 }, { "grad_norm": 0.4850311577320099, "learning_rate": 9.896649852006917e-05, "loss": 0.0253, "step": 11160 }, { "loss_action": 0.021871885284781456, "loss_total": 0.021871885284781456, "step": 11160 }, { "grad_norm": 0.43213868141174316, "learning_rate": 9.896315138333177e-05, "loss": 0.026, "step": 11170 }, { "loss_action": 0.01801033690571785, "loss_total": 0.01801033690571785, "step": 11170 }, { "grad_norm": 0.38341256976127625, "learning_rate": 9.895979889205774e-05, "loss": 0.022, "step": 11180 }, { "loss_action": 0.023831715807318687, "loss_total": 0.023831715807318687, "step": 11180 }, { "grad_norm": 0.455499529838562, "learning_rate": 9.895644104661372e-05, "loss": 0.0253, "step": 11190 }, { "loss_action": 0.02565866895020008, "loss_total": 0.02565866895020008, "step": 11190 }, { "grad_norm": 0.50380939245224, "learning_rate": 9.895307784736691e-05, "loss": 0.0271, "step": 11200 }, { "loss_action": 0.021692700684070587, "loss_total": 0.021692700684070587, "step": 11200 }, { "grad_norm": 0.5690737366676331, "learning_rate": 9.894970929468512e-05, "loss": 0.0291, "step": 11210 }, { "loss_action": 0.03280290216207504, "loss_total": 0.03280290216207504, "step": 11210 }, { "grad_norm": 0.4862152934074402, "learning_rate": 9.89463353889367e-05, "loss": 0.0285, "step": 11220 }, { "loss_action": 0.030522920191287994, "loss_total": 0.030522920191287994, "step": 11220 }, { "grad_norm": 0.4791412949562073, "learning_rate": 9.894295613049065e-05, "loss": 0.0275, "step": 11230 }, { "loss_action": 0.021524641662836075, "loss_total": 0.021524641662836075, "step": 11230 }, { "grad_norm": 0.40047988295555115, "learning_rate": 9.893957151971649e-05, "loss": 0.023, "step": 11240 }, { "loss_action": 0.019755592569708824, "loss_total": 0.019755592569708824, "step": 11240 }, { "grad_norm": 0.43119773268699646, "learning_rate": 9.893618155698436e-05, "loss": 0.0238, "step": 11250 }, { "loss_action": 0.01882171258330345, "loss_total": 0.01882171258330345, "step": 11250 }, { "grad_norm": 0.4224584996700287, "learning_rate": 9.8932786242665e-05, "loss": 0.0245, "step": 11260 }, { "loss_action": 0.02238508127629757, "loss_total": 0.02238508127629757, "step": 11260 }, { "grad_norm": 0.4667148292064667, "learning_rate": 9.89293855771297e-05, "loss": 0.0214, "step": 11270 }, { "loss_action": 0.022589819505810738, "loss_total": 0.022589819505810738, "step": 11270 }, { "grad_norm": 0.37544435262680054, "learning_rate": 9.892597956075036e-05, "loss": 0.0238, "step": 11280 }, { "loss_action": 0.026358695700764656, "loss_total": 0.026358695700764656, "step": 11280 }, { "grad_norm": 0.46868643164634705, "learning_rate": 9.892256819389947e-05, "loss": 0.0246, "step": 11290 }, { "loss_action": 0.02282247692346573, "loss_total": 0.02282247692346573, "step": 11290 }, { "grad_norm": 0.449503630399704, "learning_rate": 9.891915147695006e-05, "loss": 0.0254, "step": 11300 }, { "loss_action": 0.025331784039735794, "loss_total": 0.025331784039735794, "step": 11300 }, { "grad_norm": 0.6468259692192078, "learning_rate": 9.891572941027577e-05, "loss": 0.0283, "step": 11310 }, { "loss_action": 0.023215457797050476, "loss_total": 0.023215457797050476, "step": 11310 }, { "grad_norm": 0.6342492699623108, "learning_rate": 9.89123019942509e-05, "loss": 0.0289, "step": 11320 }, { "loss_action": 0.03077375516295433, "loss_total": 0.03077375516295433, "step": 11320 }, { "grad_norm": 0.41438478231430054, "learning_rate": 9.89088692292502e-05, "loss": 0.0278, "step": 11330 }, { "loss_action": 0.03495882451534271, "loss_total": 0.03495882451534271, "step": 11330 }, { "grad_norm": 0.4368046820163727, "learning_rate": 9.89054311156491e-05, "loss": 0.0261, "step": 11340 }, { "loss_action": 0.0250298660248518, "loss_total": 0.0250298660248518, "step": 11340 }, { "grad_norm": 0.4834425151348114, "learning_rate": 9.890198765382357e-05, "loss": 0.0266, "step": 11350 }, { "loss_action": 0.021716823801398277, "loss_total": 0.021716823801398277, "step": 11350 }, { "grad_norm": 0.5062768459320068, "learning_rate": 9.889853884415021e-05, "loss": 0.0254, "step": 11360 }, { "loss_action": 0.023511802777647972, "loss_total": 0.023511802777647972, "step": 11360 }, { "grad_norm": 0.4485001266002655, "learning_rate": 9.889508468700614e-05, "loss": 0.0262, "step": 11370 }, { "loss_action": 0.026179663836956024, "loss_total": 0.026179663836956024, "step": 11370 }, { "grad_norm": 0.4190422296524048, "learning_rate": 9.889162518276915e-05, "loss": 0.0242, "step": 11380 }, { "loss_action": 0.02407384105026722, "loss_total": 0.02407384105026722, "step": 11380 }, { "grad_norm": 0.43330979347229004, "learning_rate": 9.888816033181752e-05, "loss": 0.0239, "step": 11390 }, { "loss_action": 0.022309524938464165, "loss_total": 0.022309524938464165, "step": 11390 }, { "grad_norm": 0.39452028274536133, "learning_rate": 9.888469013453018e-05, "loss": 0.022, "step": 11400 }, { "loss_action": 0.026378223672509193, "loss_total": 0.026378223672509193, "step": 11400 }, { "grad_norm": 0.3783171474933624, "learning_rate": 9.888121459128663e-05, "loss": 0.0241, "step": 11410 }, { "loss_action": 0.019362056627869606, "loss_total": 0.019362056627869606, "step": 11410 }, { "grad_norm": 0.4139009416103363, "learning_rate": 9.887773370246693e-05, "loss": 0.0218, "step": 11420 }, { "loss_action": 0.024002280086278915, "loss_total": 0.024002280086278915, "step": 11420 }, { "grad_norm": 0.6608930230140686, "learning_rate": 9.887424746845177e-05, "loss": 0.0225, "step": 11430 }, { "loss_action": 0.022350478917360306, "loss_total": 0.022350478917360306, "step": 11430 }, { "grad_norm": 0.6486517786979675, "learning_rate": 9.887075588962239e-05, "loss": 0.0252, "step": 11440 }, { "loss_action": 0.01952737383544445, "loss_total": 0.01952737383544445, "step": 11440 }, { "grad_norm": 0.47911855578422546, "learning_rate": 9.88672589663606e-05, "loss": 0.0246, "step": 11450 }, { "loss_action": 0.022255491465330124, "loss_total": 0.022255491465330124, "step": 11450 }, { "grad_norm": 0.4792484939098358, "learning_rate": 9.886375669904886e-05, "loss": 0.0246, "step": 11460 }, { "loss_action": 0.024226920679211617, "loss_total": 0.024226920679211617, "step": 11460 }, { "grad_norm": 0.4221579134464264, "learning_rate": 9.886024908807014e-05, "loss": 0.025, "step": 11470 }, { "loss_action": 0.021045174449682236, "loss_total": 0.021045174449682236, "step": 11470 }, { "grad_norm": 0.547315239906311, "learning_rate": 9.885673613380806e-05, "loss": 0.0232, "step": 11480 }, { "loss_action": 0.020219357684254646, "loss_total": 0.020219357684254646, "step": 11480 }, { "grad_norm": 0.5207573175430298, "learning_rate": 9.885321783664676e-05, "loss": 0.025, "step": 11490 }, { "loss_action": 0.02382698841392994, "loss_total": 0.02382698841392994, "step": 11490 }, { "grad_norm": 0.49944210052490234, "learning_rate": 9.884969419697101e-05, "loss": 0.0234, "step": 11500 }, { "loss_action": 0.020944813266396523, "loss_total": 0.020944813266396523, "step": 11500 }, { "grad_norm": 0.4903418719768524, "learning_rate": 9.884616521516614e-05, "loss": 0.0229, "step": 11510 }, { "loss_action": 0.021950077265501022, "loss_total": 0.021950077265501022, "step": 11510 }, { "grad_norm": 0.42627763748168945, "learning_rate": 9.88426308916181e-05, "loss": 0.0241, "step": 11520 }, { "loss_action": 0.020803352817893028, "loss_total": 0.020803352817893028, "step": 11520 }, { "grad_norm": 0.42956021428108215, "learning_rate": 9.883909122671335e-05, "loss": 0.024, "step": 11530 }, { "loss_action": 0.017432453110814095, "loss_total": 0.017432453110814095, "step": 11530 }, { "grad_norm": 0.5138512253761292, "learning_rate": 9.883554622083904e-05, "loss": 0.0234, "step": 11540 }, { "loss_action": 0.03615420684218407, "loss_total": 0.03615420684218407, "step": 11540 }, { "grad_norm": 0.5928680300712585, "learning_rate": 9.88319958743828e-05, "loss": 0.0323, "step": 11550 }, { "loss_action": 0.03917977213859558, "loss_total": 0.03917977213859558, "step": 11550 }, { "grad_norm": 0.29529261589050293, "learning_rate": 9.882844018773291e-05, "loss": 0.0284, "step": 11560 }, { "loss_action": 0.027048734948039055, "loss_total": 0.027048734948039055, "step": 11560 }, { "grad_norm": 0.43105757236480713, "learning_rate": 9.882487916127823e-05, "loss": 0.0224, "step": 11570 }, { "loss_action": 0.02049202471971512, "loss_total": 0.02049202471971512, "step": 11570 }, { "grad_norm": 0.49890923500061035, "learning_rate": 9.882131279540815e-05, "loss": 0.0256, "step": 11580 }, { "loss_action": 0.022553440183401108, "loss_total": 0.022553440183401108, "step": 11580 }, { "grad_norm": 0.46489834785461426, "learning_rate": 9.881774109051271e-05, "loss": 0.0237, "step": 11590 }, { "loss_action": 0.01901848614215851, "loss_total": 0.01901848614215851, "step": 11590 }, { "grad_norm": 0.4578203856945038, "learning_rate": 9.881416404698252e-05, "loss": 0.0247, "step": 11600 }, { "loss_action": 0.021512266248464584, "loss_total": 0.021512266248464584, "step": 11600 }, { "grad_norm": 0.43599388003349304, "learning_rate": 9.881058166520873e-05, "loss": 0.0256, "step": 11610 }, { "loss_action": 0.024178791791200638, "loss_total": 0.024178791791200638, "step": 11610 }, { "grad_norm": 0.5851152539253235, "learning_rate": 9.880699394558311e-05, "loss": 0.0235, "step": 11620 }, { "loss_action": 0.02754870429635048, "loss_total": 0.02754870429635048, "step": 11620 }, { "grad_norm": 0.3524783253669739, "learning_rate": 9.880340088849801e-05, "loss": 0.0231, "step": 11630 }, { "loss_action": 0.02519330196082592, "loss_total": 0.02519330196082592, "step": 11630 }, { "grad_norm": 0.4771839678287506, "learning_rate": 9.879980249434637e-05, "loss": 0.0229, "step": 11640 }, { "loss_action": 0.021595783531665802, "loss_total": 0.021595783531665802, "step": 11640 }, { "grad_norm": 0.40818434953689575, "learning_rate": 9.879619876352168e-05, "loss": 0.0233, "step": 11650 }, { "loss_action": 0.02499391697347164, "loss_total": 0.02499391697347164, "step": 11650 }, { "grad_norm": 0.5184663534164429, "learning_rate": 9.879258969641809e-05, "loss": 0.0241, "step": 11660 }, { "loss_action": 0.022261332720518112, "loss_total": 0.022261332720518112, "step": 11660 }, { "grad_norm": 0.49126100540161133, "learning_rate": 9.878897529343023e-05, "loss": 0.0236, "step": 11670 }, { "loss_action": 0.020011596381664276, "loss_total": 0.020011596381664276, "step": 11670 }, { "grad_norm": 0.4695969521999359, "learning_rate": 9.878535555495338e-05, "loss": 0.0239, "step": 11680 }, { "loss_action": 0.03522063046693802, "loss_total": 0.03522063046693802, "step": 11680 }, { "grad_norm": 0.473501980304718, "learning_rate": 9.87817304813834e-05, "loss": 0.0272, "step": 11690 }, { "loss_action": 0.027213845402002335, "loss_total": 0.027213845402002335, "step": 11690 }, { "grad_norm": 0.4956561326980591, "learning_rate": 9.877810007311671e-05, "loss": 0.0247, "step": 11700 }, { "loss_action": 0.029571978375315666, "loss_total": 0.029571978375315666, "step": 11700 }, { "grad_norm": 0.46822041273117065, "learning_rate": 9.877446433055035e-05, "loss": 0.0293, "step": 11710 }, { "loss_action": 0.024794720113277435, "loss_total": 0.024794720113277435, "step": 11710 }, { "grad_norm": 0.5271965265274048, "learning_rate": 9.877082325408191e-05, "loss": 0.0246, "step": 11720 }, { "loss_action": 0.018840242177248, "loss_total": 0.018840242177248, "step": 11720 }, { "grad_norm": 0.38499578833580017, "learning_rate": 9.876717684410954e-05, "loss": 0.0234, "step": 11730 }, { "loss_action": 0.026861168444156647, "loss_total": 0.026861168444156647, "step": 11730 }, { "grad_norm": 0.5084483623504639, "learning_rate": 9.876352510103204e-05, "loss": 0.0268, "step": 11740 }, { "loss_action": 0.02353067323565483, "loss_total": 0.02353067323565483, "step": 11740 }, { "grad_norm": 0.39143916964530945, "learning_rate": 9.875986802524875e-05, "loss": 0.0239, "step": 11750 }, { "loss_action": 0.022771550342440605, "loss_total": 0.022771550342440605, "step": 11750 }, { "grad_norm": 0.4186536967754364, "learning_rate": 9.87562056171596e-05, "loss": 0.0225, "step": 11760 }, { "loss_action": 0.025087906047701836, "loss_total": 0.025087906047701836, "step": 11760 }, { "grad_norm": 0.4170265793800354, "learning_rate": 9.875253787716511e-05, "loss": 0.0245, "step": 11770 }, { "loss_action": 0.028588784858584404, "loss_total": 0.028588784858584404, "step": 11770 }, { "grad_norm": 0.4177100658416748, "learning_rate": 9.874886480566637e-05, "loss": 0.0238, "step": 11780 }, { "loss_action": 0.03441445529460907, "loss_total": 0.03441445529460907, "step": 11780 }, { "grad_norm": 0.5410010814666748, "learning_rate": 9.874518640306507e-05, "loss": 0.0245, "step": 11790 }, { "loss_action": 0.025760844349861145, "loss_total": 0.025760844349861145, "step": 11790 }, { "grad_norm": 0.4762079417705536, "learning_rate": 9.874150266976347e-05, "loss": 0.0252, "step": 11800 }, { "loss_action": 0.023392459377646446, "loss_total": 0.023392459377646446, "step": 11800 }, { "grad_norm": 0.37677517533302307, "learning_rate": 9.873781360616443e-05, "loss": 0.0227, "step": 11810 }, { "loss_action": 0.022044941782951355, "loss_total": 0.022044941782951355, "step": 11810 }, { "grad_norm": 0.3698958158493042, "learning_rate": 9.873411921267137e-05, "loss": 0.0223, "step": 11820 }, { "loss_action": 0.02025320567190647, "loss_total": 0.02025320567190647, "step": 11820 }, { "grad_norm": 0.5127937197685242, "learning_rate": 9.873041948968829e-05, "loss": 0.0245, "step": 11830 }, { "loss_action": 0.02909083664417267, "loss_total": 0.02909083664417267, "step": 11830 }, { "grad_norm": 0.42122024297714233, "learning_rate": 9.872671443761981e-05, "loss": 0.0221, "step": 11840 }, { "loss_action": 0.018621493130922318, "loss_total": 0.018621493130922318, "step": 11840 }, { "grad_norm": 0.5864685773849487, "learning_rate": 9.872300405687109e-05, "loss": 0.0235, "step": 11850 }, { "loss_action": 0.024312861263751984, "loss_total": 0.024312861263751984, "step": 11850 }, { "grad_norm": 0.5599654912948608, "learning_rate": 9.871928834784792e-05, "loss": 0.0274, "step": 11860 }, { "loss_action": 0.024030162021517754, "loss_total": 0.024030162021517754, "step": 11860 }, { "grad_norm": 0.46621525287628174, "learning_rate": 9.871556731095661e-05, "loss": 0.0272, "step": 11870 }, { "loss_action": 0.033717378973960876, "loss_total": 0.033717378973960876, "step": 11870 }, { "grad_norm": 0.6621512770652771, "learning_rate": 9.871184094660411e-05, "loss": 0.0298, "step": 11880 }, { "loss_action": 0.024781635031104088, "loss_total": 0.024781635031104088, "step": 11880 }, { "grad_norm": 0.5298628807067871, "learning_rate": 9.870810925519791e-05, "loss": 0.0278, "step": 11890 }, { "loss_action": 0.028923513367772102, "loss_total": 0.028923513367772102, "step": 11890 }, { "grad_norm": 0.44321081042289734, "learning_rate": 9.870437223714612e-05, "loss": 0.0285, "step": 11900 }, { "loss_action": 0.026767874136567116, "loss_total": 0.026767874136567116, "step": 11900 }, { "grad_norm": 0.4596162438392639, "learning_rate": 9.87006298928574e-05, "loss": 0.0256, "step": 11910 }, { "loss_action": 0.028967415913939476, "loss_total": 0.028967415913939476, "step": 11910 }, { "grad_norm": 0.6128920316696167, "learning_rate": 9.869688222274103e-05, "loss": 0.0255, "step": 11920 }, { "loss_action": 0.027446158230304718, "loss_total": 0.027446158230304718, "step": 11920 }, { "grad_norm": 0.52744460105896, "learning_rate": 9.869312922720681e-05, "loss": 0.0256, "step": 11930 }, { "loss_action": 0.02307123877108097, "loss_total": 0.02307123877108097, "step": 11930 }, { "grad_norm": 0.535965085029602, "learning_rate": 9.868937090666521e-05, "loss": 0.025, "step": 11940 }, { "loss_action": 0.02678210660815239, "loss_total": 0.02678210660815239, "step": 11940 }, { "grad_norm": 0.46904119849205017, "learning_rate": 9.86856072615272e-05, "loss": 0.0268, "step": 11950 }, { "loss_action": 0.042807552963495255, "loss_total": 0.042807552963495255, "step": 11950 }, { "grad_norm": 0.5447129011154175, "learning_rate": 9.868183829220438e-05, "loss": 0.0291, "step": 11960 }, { "loss_action": 0.031384892761707306, "loss_total": 0.031384892761707306, "step": 11960 }, { "grad_norm": 0.4572918713092804, "learning_rate": 9.867806399910893e-05, "loss": 0.0269, "step": 11970 }, { "loss_action": 0.01868593692779541, "loss_total": 0.01868593692779541, "step": 11970 }, { "grad_norm": 0.46401721239089966, "learning_rate": 9.867428438265356e-05, "loss": 0.0243, "step": 11980 }, { "loss_action": 0.02505910024046898, "loss_total": 0.02505910024046898, "step": 11980 }, { "grad_norm": 0.628086268901825, "learning_rate": 9.867049944325165e-05, "loss": 0.0269, "step": 11990 }, { "loss_action": 0.03690825402736664, "loss_total": 0.03690825402736664, "step": 11990 }, { "grad_norm": 0.6681606769561768, "learning_rate": 9.86667091813171e-05, "loss": 0.0286, "step": 12000 }, { "loss_action": 0.028466956689953804, "loss_total": 0.028466956689953804, "step": 12000 }, { "grad_norm": 0.4157109260559082, "learning_rate": 9.866291359726438e-05, "loss": 0.0238, "step": 12010 }, { "loss_action": 0.022917889058589935, "loss_total": 0.022917889058589935, "step": 12010 }, { "grad_norm": 0.35248687863349915, "learning_rate": 9.865911269150861e-05, "loss": 0.021, "step": 12020 }, { "loss_action": 0.02294318377971649, "loss_total": 0.02294318377971649, "step": 12020 }, { "grad_norm": 0.6013563871383667, "learning_rate": 9.865530646446544e-05, "loss": 0.0239, "step": 12030 }, { "loss_action": 0.02585780620574951, "loss_total": 0.02585780620574951, "step": 12030 }, { "grad_norm": 0.3936450779438019, "learning_rate": 9.86514949165511e-05, "loss": 0.0238, "step": 12040 }, { "loss_action": 0.01811767928302288, "loss_total": 0.01811767928302288, "step": 12040 }, { "grad_norm": 0.7331258654594421, "learning_rate": 9.864767804818243e-05, "loss": 0.0216, "step": 12050 }, { "loss_action": 0.016569294035434723, "loss_total": 0.016569294035434723, "step": 12050 }, { "grad_norm": 0.4283442199230194, "learning_rate": 9.86438558597768e-05, "loss": 0.0232, "step": 12060 }, { "loss_action": 0.020782219246029854, "loss_total": 0.020782219246029854, "step": 12060 }, { "grad_norm": 0.40704795718193054, "learning_rate": 9.864002835175225e-05, "loss": 0.0267, "step": 12070 }, { "loss_action": 0.02383791282773018, "loss_total": 0.02383791282773018, "step": 12070 }, { "grad_norm": 0.4346737563610077, "learning_rate": 9.863619552452734e-05, "loss": 0.026, "step": 12080 }, { "loss_action": 0.02406569942831993, "loss_total": 0.02406569942831993, "step": 12080 }, { "grad_norm": 0.5433782935142517, "learning_rate": 9.863235737852119e-05, "loss": 0.0281, "step": 12090 }, { "loss_action": 0.01976896822452545, "loss_total": 0.01976896822452545, "step": 12090 }, { "grad_norm": 0.4046230614185333, "learning_rate": 9.862851391415356e-05, "loss": 0.0268, "step": 12100 }, { "loss_action": 0.024450941011309624, "loss_total": 0.024450941011309624, "step": 12100 }, { "grad_norm": 0.5319803953170776, "learning_rate": 9.862466513184477e-05, "loss": 0.0243, "step": 12110 }, { "loss_action": 0.02723219245672226, "loss_total": 0.02723219245672226, "step": 12110 }, { "grad_norm": 0.43974241614341736, "learning_rate": 9.86208110320157e-05, "loss": 0.025, "step": 12120 }, { "loss_action": 0.03210756927728653, "loss_total": 0.03210756927728653, "step": 12120 }, { "grad_norm": 0.556281566619873, "learning_rate": 9.861695161508784e-05, "loss": 0.0251, "step": 12130 }, { "loss_action": 0.024472597986459732, "loss_total": 0.024472597986459732, "step": 12130 }, { "grad_norm": 0.4292493462562561, "learning_rate": 9.861308688148324e-05, "loss": 0.025, "step": 12140 }, { "loss_action": 0.02825651876628399, "loss_total": 0.02825651876628399, "step": 12140 }, { "grad_norm": 0.4578523635864258, "learning_rate": 9.860921683162455e-05, "loss": 0.0239, "step": 12150 }, { "loss_action": 0.02823408506810665, "loss_total": 0.02823408506810665, "step": 12150 }, { "grad_norm": 0.4580935537815094, "learning_rate": 9.860534146593499e-05, "loss": 0.0258, "step": 12160 }, { "loss_action": 0.029506143182516098, "loss_total": 0.029506143182516098, "step": 12160 }, { "grad_norm": 0.49167048931121826, "learning_rate": 9.860146078483836e-05, "loss": 0.0235, "step": 12170 }, { "loss_action": 0.02172454446554184, "loss_total": 0.02172454446554184, "step": 12170 }, { "grad_norm": 0.4996114671230316, "learning_rate": 9.859757478875905e-05, "loss": 0.0235, "step": 12180 }, { "loss_action": 0.0215859767049551, "loss_total": 0.0215859767049551, "step": 12180 }, { "grad_norm": 0.48474496603012085, "learning_rate": 9.859368347812204e-05, "loss": 0.0239, "step": 12190 }, { "loss_action": 0.025322092697024345, "loss_total": 0.025322092697024345, "step": 12190 }, { "grad_norm": 0.4375641345977783, "learning_rate": 9.858978685335285e-05, "loss": 0.0278, "step": 12200 }, { "loss_action": 0.03277909383177757, "loss_total": 0.03277909383177757, "step": 12200 }, { "grad_norm": 0.5888964533805847, "learning_rate": 9.858588491487763e-05, "loss": 0.025, "step": 12210 }, { "loss_action": 0.025691242888569832, "loss_total": 0.025691242888569832, "step": 12210 }, { "grad_norm": 0.49093472957611084, "learning_rate": 9.858197766312308e-05, "loss": 0.0252, "step": 12220 }, { "loss_action": 0.03146905452013016, "loss_total": 0.03146905452013016, "step": 12220 }, { "grad_norm": 0.533683180809021, "learning_rate": 9.857806509851649e-05, "loss": 0.0233, "step": 12230 }, { "loss_action": 0.02036276087164879, "loss_total": 0.02036276087164879, "step": 12230 }, { "grad_norm": 0.3520388603210449, "learning_rate": 9.857414722148574e-05, "loss": 0.0201, "step": 12240 }, { "loss_action": 0.017602521926164627, "loss_total": 0.017602521926164627, "step": 12240 }, { "grad_norm": 0.5004624128341675, "learning_rate": 9.857022403245928e-05, "loss": 0.0197, "step": 12250 }, { "loss_action": 0.020029911771416664, "loss_total": 0.020029911771416664, "step": 12250 }, { "grad_norm": 0.560977041721344, "learning_rate": 9.856629553186615e-05, "loss": 0.024, "step": 12260 }, { "loss_action": 0.018893763422966003, "loss_total": 0.018893763422966003, "step": 12260 }, { "grad_norm": 0.4625658392906189, "learning_rate": 9.856236172013595e-05, "loss": 0.0212, "step": 12270 }, { "loss_action": 0.02170703560113907, "loss_total": 0.02170703560113907, "step": 12270 }, { "grad_norm": 0.5246562957763672, "learning_rate": 9.85584225976989e-05, "loss": 0.0234, "step": 12280 }, { "loss_action": 0.02287919446825981, "loss_total": 0.02287919446825981, "step": 12280 }, { "grad_norm": 0.4694146513938904, "learning_rate": 9.855447816498575e-05, "loss": 0.025, "step": 12290 }, { "loss_action": 0.020681167021393776, "loss_total": 0.020681167021393776, "step": 12290 }, { "grad_norm": 0.4521155059337616, "learning_rate": 9.855052842242787e-05, "loss": 0.0202, "step": 12300 }, { "loss_action": 0.019630571827292442, "loss_total": 0.019630571827292442, "step": 12300 }, { "grad_norm": 0.4970076382160187, "learning_rate": 9.85465733704572e-05, "loss": 0.0223, "step": 12310 }, { "loss_action": 0.022860491648316383, "loss_total": 0.022860491648316383, "step": 12310 }, { "grad_norm": 0.40793362259864807, "learning_rate": 9.854261300950624e-05, "loss": 0.0201, "step": 12320 }, { "loss_action": 0.017869487404823303, "loss_total": 0.017869487404823303, "step": 12320 }, { "grad_norm": 0.45840704441070557, "learning_rate": 9.853864734000813e-05, "loss": 0.0225, "step": 12330 }, { "loss_action": 0.022658666595816612, "loss_total": 0.022658666595816612, "step": 12330 }, { "grad_norm": 0.7475795149803162, "learning_rate": 9.85346763623965e-05, "loss": 0.0207, "step": 12340 }, { "loss_action": 0.02418929524719715, "loss_total": 0.02418929524719715, "step": 12340 }, { "grad_norm": 0.42950204014778137, "learning_rate": 9.853070007710564e-05, "loss": 0.021, "step": 12350 }, { "loss_action": 0.021217482164502144, "loss_total": 0.021217482164502144, "step": 12350 }, { "grad_norm": 0.4190436005592346, "learning_rate": 9.85267184845704e-05, "loss": 0.0231, "step": 12360 }, { "loss_action": 0.01785578392446041, "loss_total": 0.01785578392446041, "step": 12360 }, { "grad_norm": 0.3929525315761566, "learning_rate": 9.852273158522616e-05, "loss": 0.0212, "step": 12370 }, { "loss_action": 0.03630215302109718, "loss_total": 0.03630215302109718, "step": 12370 }, { "grad_norm": 0.47517725825309753, "learning_rate": 9.851873937950896e-05, "loss": 0.0249, "step": 12380 }, { "loss_action": 0.02638936974108219, "loss_total": 0.02638936974108219, "step": 12380 }, { "grad_norm": 0.47365760803222656, "learning_rate": 9.851474186785537e-05, "loss": 0.0238, "step": 12390 }, { "loss_action": 0.023308172821998596, "loss_total": 0.023308172821998596, "step": 12390 }, { "grad_norm": 0.509955108165741, "learning_rate": 9.851073905070254e-05, "loss": 0.0238, "step": 12400 }, { "loss_action": 0.015204573050141335, "loss_total": 0.015204573050141335, "step": 12400 }, { "grad_norm": 0.4802766740322113, "learning_rate": 9.850673092848824e-05, "loss": 0.0232, "step": 12410 }, { "loss_action": 0.019561847671866417, "loss_total": 0.019561847671866417, "step": 12410 }, { "grad_norm": 0.5242267847061157, "learning_rate": 9.850271750165077e-05, "loss": 0.0226, "step": 12420 }, { "loss_action": 0.02707221359014511, "loss_total": 0.02707221359014511, "step": 12420 }, { "grad_norm": 0.464118093252182, "learning_rate": 9.849869877062902e-05, "loss": 0.0241, "step": 12430 }, { "loss_action": 0.018620287999510765, "loss_total": 0.018620287999510765, "step": 12430 }, { "grad_norm": 0.5515719652175903, "learning_rate": 9.849467473586252e-05, "loss": 0.0236, "step": 12440 }, { "loss_action": 0.02383306808769703, "loss_total": 0.02383306808769703, "step": 12440 }, { "grad_norm": 0.43073907494544983, "learning_rate": 9.849064539779127e-05, "loss": 0.0245, "step": 12450 }, { "loss_action": 0.023384712636470795, "loss_total": 0.023384712636470795, "step": 12450 }, { "grad_norm": 0.44084522128105164, "learning_rate": 9.848661075685594e-05, "loss": 0.0232, "step": 12460 }, { "loss_action": 0.02315368875861168, "loss_total": 0.02315368875861168, "step": 12460 }, { "grad_norm": 0.45406073331832886, "learning_rate": 9.848257081349778e-05, "loss": 0.0251, "step": 12470 }, { "loss_action": 0.03211436793208122, "loss_total": 0.03211436793208122, "step": 12470 }, { "grad_norm": 0.4552468955516815, "learning_rate": 9.847852556815856e-05, "loss": 0.0254, "step": 12480 }, { "loss_action": 0.022186139598488808, "loss_total": 0.022186139598488808, "step": 12480 }, { "grad_norm": 0.46624982357025146, "learning_rate": 9.847447502128067e-05, "loss": 0.0226, "step": 12490 }, { "loss_action": 0.027370722964406013, "loss_total": 0.027370722964406013, "step": 12490 }, { "grad_norm": 0.5356216430664062, "learning_rate": 9.847041917330708e-05, "loss": 0.025, "step": 12500 }, { "loss_action": 0.028043940663337708, "loss_total": 0.028043940663337708, "step": 12500 }, { "grad_norm": 0.3616615831851959, "learning_rate": 9.846635802468132e-05, "loss": 0.0215, "step": 12510 }, { "loss_action": 0.025112757459282875, "loss_total": 0.025112757459282875, "step": 12510 }, { "grad_norm": 0.4009825885295868, "learning_rate": 9.84622915758475e-05, "loss": 0.0235, "step": 12520 }, { "loss_action": 0.01896096020936966, "loss_total": 0.01896096020936966, "step": 12520 }, { "grad_norm": 0.41778507828712463, "learning_rate": 9.845821982725034e-05, "loss": 0.0215, "step": 12530 }, { "loss_action": 0.01724100485444069, "loss_total": 0.01724100485444069, "step": 12530 }, { "grad_norm": 0.3455198109149933, "learning_rate": 9.845414277933514e-05, "loss": 0.0216, "step": 12540 }, { "loss_action": 0.036064401268959045, "loss_total": 0.036064401268959045, "step": 12540 }, { "grad_norm": 0.49125462770462036, "learning_rate": 9.845006043254771e-05, "loss": 0.0232, "step": 12550 }, { "loss_action": 0.02299804985523224, "loss_total": 0.02299804985523224, "step": 12550 }, { "grad_norm": 0.41065651178359985, "learning_rate": 9.844597278733451e-05, "loss": 0.0212, "step": 12560 }, { "loss_action": 0.022924797609448433, "loss_total": 0.022924797609448433, "step": 12560 }, { "grad_norm": 0.44834402203559875, "learning_rate": 9.844187984414259e-05, "loss": 0.0217, "step": 12570 }, { "loss_action": 0.022079849615693092, "loss_total": 0.022079849615693092, "step": 12570 }, { "grad_norm": 0.41954490542411804, "learning_rate": 9.84377816034195e-05, "loss": 0.0216, "step": 12580 }, { "loss_action": 0.018191857263445854, "loss_total": 0.018191857263445854, "step": 12580 }, { "grad_norm": 0.3965964615345001, "learning_rate": 9.843367806561345e-05, "loss": 0.0218, "step": 12590 }, { "loss_action": 0.02476498857140541, "loss_total": 0.02476498857140541, "step": 12590 }, { "grad_norm": 0.3752588927745819, "learning_rate": 9.842956923117317e-05, "loss": 0.0217, "step": 12600 }, { "loss_action": 0.017582420259714127, "loss_total": 0.017582420259714127, "step": 12600 }, { "grad_norm": 0.42465636134147644, "learning_rate": 9.842545510054802e-05, "loss": 0.0218, "step": 12610 }, { "loss_action": 0.021522190421819687, "loss_total": 0.021522190421819687, "step": 12610 }, { "grad_norm": 0.3752915561199188, "learning_rate": 9.842133567418792e-05, "loss": 0.0213, "step": 12620 }, { "loss_action": 0.022367892786860466, "loss_total": 0.022367892786860466, "step": 12620 }, { "grad_norm": 0.4127381145954132, "learning_rate": 9.841721095254333e-05, "loss": 0.0215, "step": 12630 }, { "loss_action": 0.024268170818686485, "loss_total": 0.024268170818686485, "step": 12630 }, { "grad_norm": 0.4467020332813263, "learning_rate": 9.841308093606537e-05, "loss": 0.0209, "step": 12640 }, { "loss_action": 0.02552391029894352, "loss_total": 0.02552391029894352, "step": 12640 }, { "grad_norm": 0.38832974433898926, "learning_rate": 9.840894562520565e-05, "loss": 0.0227, "step": 12650 }, { "loss_action": 0.018792716786265373, "loss_total": 0.018792716786265373, "step": 12650 }, { "grad_norm": 0.5504615306854248, "learning_rate": 9.840480502041642e-05, "loss": 0.0225, "step": 12660 }, { "loss_action": 0.02343890257179737, "loss_total": 0.02343890257179737, "step": 12660 }, { "grad_norm": 0.6632758378982544, "learning_rate": 9.840065912215049e-05, "loss": 0.0271, "step": 12670 }, { "loss_action": 0.034433890134096146, "loss_total": 0.034433890134096146, "step": 12670 }, { "grad_norm": 0.5216776728630066, "learning_rate": 9.839650793086124e-05, "loss": 0.028, "step": 12680 }, { "loss_action": 0.023958798497915268, "loss_total": 0.023958798497915268, "step": 12680 }, { "grad_norm": 0.4373569190502167, "learning_rate": 9.839235144700265e-05, "loss": 0.027, "step": 12690 }, { "loss_action": 0.02926419861614704, "loss_total": 0.02926419861614704, "step": 12690 }, { "grad_norm": 0.4590449333190918, "learning_rate": 9.838818967102926e-05, "loss": 0.0262, "step": 12700 }, { "loss_action": 0.02693174220621586, "loss_total": 0.02693174220621586, "step": 12700 }, { "grad_norm": 0.5842565298080444, "learning_rate": 9.83840226033962e-05, "loss": 0.0267, "step": 12710 }, { "loss_action": 0.024433577433228493, "loss_total": 0.024433577433228493, "step": 12710 }, { "grad_norm": 0.35730084776878357, "learning_rate": 9.837985024455918e-05, "loss": 0.0237, "step": 12720 }, { "loss_action": 0.03310389071702957, "loss_total": 0.03310389071702957, "step": 12720 }, { "grad_norm": 0.41712719202041626, "learning_rate": 9.837567259497447e-05, "loss": 0.0247, "step": 12730 }, { "loss_action": 0.027788246050477028, "loss_total": 0.027788246050477028, "step": 12730 }, { "grad_norm": 0.5622174143791199, "learning_rate": 9.837148965509894e-05, "loss": 0.0248, "step": 12740 }, { "loss_action": 0.023428253829479218, "loss_total": 0.023428253829479218, "step": 12740 }, { "grad_norm": 0.7341890931129456, "learning_rate": 9.836730142539001e-05, "loss": 0.0303, "step": 12750 }, { "loss_action": 0.026266170665621758, "loss_total": 0.026266170665621758, "step": 12750 }, { "grad_norm": 0.46262800693511963, "learning_rate": 9.836310790630574e-05, "loss": 0.0271, "step": 12760 }, { "loss_action": 0.030053885653614998, "loss_total": 0.030053885653614998, "step": 12760 }, { "grad_norm": 0.5024277567863464, "learning_rate": 9.83589090983047e-05, "loss": 0.0279, "step": 12770 }, { "loss_action": 0.03100680373609066, "loss_total": 0.03100680373609066, "step": 12770 }, { "grad_norm": 0.4901413321495056, "learning_rate": 9.835470500184605e-05, "loss": 0.0276, "step": 12780 }, { "loss_action": 0.026335494592785835, "loss_total": 0.026335494592785835, "step": 12780 }, { "grad_norm": 0.4333399832248688, "learning_rate": 9.835049561738957e-05, "loss": 0.0242, "step": 12790 }, { "loss_action": 0.03214658051729202, "loss_total": 0.03214658051729202, "step": 12790 }, { "grad_norm": 0.47184449434280396, "learning_rate": 9.834628094539558e-05, "loss": 0.026, "step": 12800 }, { "loss_action": 0.017913831397891045, "loss_total": 0.017913831397891045, "step": 12800 }, { "grad_norm": 0.5042710900306702, "learning_rate": 9.834206098632499e-05, "loss": 0.0223, "step": 12810 }, { "loss_action": 0.02252896875143051, "loss_total": 0.02252896875143051, "step": 12810 }, { "grad_norm": 0.4343465566635132, "learning_rate": 9.833783574063931e-05, "loss": 0.0231, "step": 12820 }, { "loss_action": 0.026939401403069496, "loss_total": 0.026939401403069496, "step": 12820 }, { "grad_norm": 0.42828336358070374, "learning_rate": 9.833360520880058e-05, "loss": 0.0219, "step": 12830 }, { "loss_action": 0.020198535174131393, "loss_total": 0.020198535174131393, "step": 12830 }, { "grad_norm": 0.39871150255203247, "learning_rate": 9.832936939127144e-05, "loss": 0.0222, "step": 12840 }, { "loss_action": 0.021677078679203987, "loss_total": 0.021677078679203987, "step": 12840 }, { "grad_norm": 0.3954709470272064, "learning_rate": 9.832512828851515e-05, "loss": 0.021, "step": 12850 }, { "loss_action": 0.022270802408456802, "loss_total": 0.022270802408456802, "step": 12850 }, { "grad_norm": 0.43479064106941223, "learning_rate": 9.832088190099546e-05, "loss": 0.0232, "step": 12860 }, { "loss_action": 0.022818878293037415, "loss_total": 0.022818878293037415, "step": 12860 }, { "grad_norm": 0.3756899833679199, "learning_rate": 9.831663022917679e-05, "loss": 0.021, "step": 12870 }, { "loss_action": 0.021565189585089684, "loss_total": 0.021565189585089684, "step": 12870 }, { "grad_norm": 0.3381897807121277, "learning_rate": 9.831237327352407e-05, "loss": 0.0217, "step": 12880 }, { "loss_action": 0.024549519643187523, "loss_total": 0.024549519643187523, "step": 12880 }, { "grad_norm": 0.3972277343273163, "learning_rate": 9.830811103450286e-05, "loss": 0.0215, "step": 12890 }, { "loss_action": 0.02054191567003727, "loss_total": 0.02054191567003727, "step": 12890 }, { "grad_norm": 0.4584209620952606, "learning_rate": 9.830384351257924e-05, "loss": 0.0228, "step": 12900 }, { "loss_action": 0.020125923678278923, "loss_total": 0.020125923678278923, "step": 12900 }, { "grad_norm": 0.4852924346923828, "learning_rate": 9.829957070821993e-05, "loss": 0.022, "step": 12910 }, { "loss_action": 0.021142752841114998, "loss_total": 0.021142752841114998, "step": 12910 }, { "grad_norm": 0.44963574409484863, "learning_rate": 9.829529262189218e-05, "loss": 0.0205, "step": 12920 }, { "loss_action": 0.023168392479419708, "loss_total": 0.023168392479419708, "step": 12920 }, { "grad_norm": 0.5456331968307495, "learning_rate": 9.829100925406385e-05, "loss": 0.0209, "step": 12930 }, { "loss_action": 0.022618873044848442, "loss_total": 0.022618873044848442, "step": 12930 }, { "grad_norm": 0.5540628433227539, "learning_rate": 9.828672060520333e-05, "loss": 0.0242, "step": 12940 }, { "loss_action": 0.02439444325864315, "loss_total": 0.02439444325864315, "step": 12940 }, { "grad_norm": 0.4255629777908325, "learning_rate": 9.828242667577966e-05, "loss": 0.0242, "step": 12950 }, { "loss_action": 0.019879288971424103, "loss_total": 0.019879288971424103, "step": 12950 }, { "grad_norm": 0.4835645258426666, "learning_rate": 9.82781274662624e-05, "loss": 0.0226, "step": 12960 }, { "loss_action": 0.024498743936419487, "loss_total": 0.024498743936419487, "step": 12960 }, { "grad_norm": 0.487629234790802, "learning_rate": 9.82738229771217e-05, "loss": 0.0244, "step": 12970 }, { "loss_action": 0.02185290865600109, "loss_total": 0.02185290865600109, "step": 12970 }, { "grad_norm": 0.42400386929512024, "learning_rate": 9.826951320882829e-05, "loss": 0.0229, "step": 12980 }, { "loss_action": 0.018433276563882828, "loss_total": 0.018433276563882828, "step": 12980 }, { "grad_norm": 0.4593527019023895, "learning_rate": 9.826519816185351e-05, "loss": 0.0213, "step": 12990 }, { "loss_action": 0.02592497318983078, "loss_total": 0.02592497318983078, "step": 12990 }, { "grad_norm": 0.5347223281860352, "learning_rate": 9.826087783666921e-05, "loss": 0.0224, "step": 13000 }, { "loss_action": 0.017983851954340935, "loss_total": 0.017983851954340935, "step": 13000 }, { "grad_norm": 0.46109530329704285, "learning_rate": 9.825655223374787e-05, "loss": 0.0254, "step": 13010 }, { "loss_action": 0.02540040947496891, "loss_total": 0.02540040947496891, "step": 13010 }, { "grad_norm": 0.5707854628562927, "learning_rate": 9.825222135356253e-05, "loss": 0.0274, "step": 13020 }, { "loss_action": 0.024687543511390686, "loss_total": 0.024687543511390686, "step": 13020 }, { "grad_norm": 0.49358677864074707, "learning_rate": 9.82478851965868e-05, "loss": 0.0262, "step": 13030 }, { "loss_action": 0.027896547690033913, "loss_total": 0.027896547690033913, "step": 13030 }, { "grad_norm": 0.45621562004089355, "learning_rate": 9.82435437632949e-05, "loss": 0.0255, "step": 13040 }, { "loss_action": 0.022784633561968803, "loss_total": 0.022784633561968803, "step": 13040 }, { "grad_norm": 0.3726957440376282, "learning_rate": 9.823919705416158e-05, "loss": 0.0208, "step": 13050 }, { "loss_action": 0.026730366051197052, "loss_total": 0.026730366051197052, "step": 13050 }, { "grad_norm": 0.3997085392475128, "learning_rate": 9.82348450696622e-05, "loss": 0.0223, "step": 13060 }, { "loss_action": 0.021386774256825447, "loss_total": 0.021386774256825447, "step": 13060 }, { "grad_norm": 0.39218950271606445, "learning_rate": 9.823048781027268e-05, "loss": 0.0192, "step": 13070 }, { "loss_action": 0.016255399212241173, "loss_total": 0.016255399212241173, "step": 13070 }, { "grad_norm": 0.37425774335861206, "learning_rate": 9.822612527646953e-05, "loss": 0.0248, "step": 13080 }, { "loss_action": 0.018914418295025826, "loss_total": 0.018914418295025826, "step": 13080 }, { "grad_norm": 0.4596177339553833, "learning_rate": 9.822175746872984e-05, "loss": 0.0199, "step": 13090 }, { "loss_action": 0.02460598573088646, "loss_total": 0.02460598573088646, "step": 13090 }, { "grad_norm": 0.57521653175354, "learning_rate": 9.821738438753123e-05, "loss": 0.0227, "step": 13100 }, { "loss_action": 0.019511274993419647, "loss_total": 0.019511274993419647, "step": 13100 }, { "grad_norm": 0.5743119716644287, "learning_rate": 9.821300603335196e-05, "loss": 0.0233, "step": 13110 }, { "loss_action": 0.021312100812792778, "loss_total": 0.021312100812792778, "step": 13110 }, { "grad_norm": 0.4658430814743042, "learning_rate": 9.820862240667085e-05, "loss": 0.024, "step": 13120 }, { "loss_action": 0.016596997156739235, "loss_total": 0.016596997156739235, "step": 13120 }, { "grad_norm": 0.6382530927658081, "learning_rate": 9.820423350796726e-05, "loss": 0.0253, "step": 13130 }, { "loss_action": 0.02577926777303219, "loss_total": 0.02577926777303219, "step": 13130 }, { "grad_norm": 0.4492029845714569, "learning_rate": 9.819983933772118e-05, "loss": 0.023, "step": 13140 }, { "loss_action": 0.02587132900953293, "loss_total": 0.02587132900953293, "step": 13140 }, { "grad_norm": 0.44511404633522034, "learning_rate": 9.819543989641314e-05, "loss": 0.0232, "step": 13150 }, { "loss_action": 0.032902948558330536, "loss_total": 0.032902948558330536, "step": 13150 }, { "grad_norm": 0.46242982149124146, "learning_rate": 9.819103518452423e-05, "loss": 0.0291, "step": 13160 }, { "loss_action": 0.03153584524989128, "loss_total": 0.03153584524989128, "step": 13160 }, { "grad_norm": 0.5692634582519531, "learning_rate": 9.818662520253618e-05, "loss": 0.0313, "step": 13170 }, { "loss_action": 0.028072083368897438, "loss_total": 0.028072083368897438, "step": 13170 }, { "grad_norm": 0.4031219184398651, "learning_rate": 9.818220995093126e-05, "loss": 0.0242, "step": 13180 }, { "loss_action": 0.02736952155828476, "loss_total": 0.02736952155828476, "step": 13180 }, { "grad_norm": 0.44147589802742004, "learning_rate": 9.817778943019228e-05, "loss": 0.0253, "step": 13190 }, { "loss_action": 0.030201295390725136, "loss_total": 0.030201295390725136, "step": 13190 }, { "grad_norm": 0.5110307931900024, "learning_rate": 9.81733636408027e-05, "loss": 0.026, "step": 13200 }, { "loss_action": 0.02001703903079033, "loss_total": 0.02001703903079033, "step": 13200 }, { "grad_norm": 0.601945161819458, "learning_rate": 9.816893258324649e-05, "loss": 0.022, "step": 13210 }, { "loss_action": 0.022832738235592842, "loss_total": 0.022832738235592842, "step": 13210 }, { "grad_norm": 0.4848460853099823, "learning_rate": 9.816449625800823e-05, "loss": 0.0238, "step": 13220 }, { "loss_action": 0.02703690342605114, "loss_total": 0.02703690342605114, "step": 13220 }, { "grad_norm": 0.3826669752597809, "learning_rate": 9.816005466557308e-05, "loss": 0.0207, "step": 13230 }, { "loss_action": 0.019084881991147995, "loss_total": 0.019084881991147995, "step": 13230 }, { "grad_norm": 0.5750436782836914, "learning_rate": 9.815560780642674e-05, "loss": 0.0227, "step": 13240 }, { "loss_action": 0.020759891718626022, "loss_total": 0.020759891718626022, "step": 13240 }, { "grad_norm": 0.40186071395874023, "learning_rate": 9.815115568105555e-05, "loss": 0.0229, "step": 13250 }, { "loss_action": 0.03135072439908981, "loss_total": 0.03135072439908981, "step": 13250 }, { "grad_norm": 0.4229227304458618, "learning_rate": 9.814669828994638e-05, "loss": 0.0249, "step": 13260 }, { "loss_action": 0.0295772273093462, "loss_total": 0.0295772273093462, "step": 13260 }, { "grad_norm": 0.48787254095077515, "learning_rate": 9.814223563358665e-05, "loss": 0.0252, "step": 13270 }, { "loss_action": 0.023318562656641006, "loss_total": 0.023318562656641006, "step": 13270 }, { "grad_norm": 0.9341921210289001, "learning_rate": 9.813776771246443e-05, "loss": 0.0308, "step": 13280 }, { "loss_action": 0.02860708348453045, "loss_total": 0.02860708348453045, "step": 13280 }, { "grad_norm": 0.7263368964195251, "learning_rate": 9.813329452706829e-05, "loss": 0.0369, "step": 13290 }, { "loss_action": 0.032778505235910416, "loss_total": 0.032778505235910416, "step": 13290 }, { "grad_norm": 0.6324726343154907, "learning_rate": 9.812881607788744e-05, "loss": 0.0316, "step": 13300 }, { "loss_action": 0.03184537962079048, "loss_total": 0.03184537962079048, "step": 13300 }, { "grad_norm": 0.712081253528595, "learning_rate": 9.812433236541163e-05, "loss": 0.0357, "step": 13310 }, { "loss_action": 0.034176867455244064, "loss_total": 0.034176867455244064, "step": 13310 }, { "grad_norm": 0.7248399257659912, "learning_rate": 9.811984339013116e-05, "loss": 0.0345, "step": 13320 }, { "loss_action": 0.025752509012818336, "loss_total": 0.025752509012818336, "step": 13320 }, { "grad_norm": 0.4125731289386749, "learning_rate": 9.811534915253698e-05, "loss": 0.0258, "step": 13330 }, { "loss_action": 0.02459496259689331, "loss_total": 0.02459496259689331, "step": 13330 }, { "grad_norm": 0.4790169894695282, "learning_rate": 9.811084965312056e-05, "loss": 0.0256, "step": 13340 }, { "loss_action": 0.019345598295331, "loss_total": 0.019345598295331, "step": 13340 }, { "grad_norm": 0.43429863452911377, "learning_rate": 9.810634489237396e-05, "loss": 0.0222, "step": 13350 }, { "loss_action": 0.02229190617799759, "loss_total": 0.02229190617799759, "step": 13350 }, { "grad_norm": 0.48028111457824707, "learning_rate": 9.81018348707898e-05, "loss": 0.0222, "step": 13360 }, { "loss_action": 0.027318252250552177, "loss_total": 0.027318252250552177, "step": 13360 }, { "grad_norm": 0.42748206853866577, "learning_rate": 9.809731958886131e-05, "loss": 0.0227, "step": 13370 }, { "loss_action": 0.03574451431632042, "loss_total": 0.03574451431632042, "step": 13370 }, { "grad_norm": 0.3959430754184723, "learning_rate": 9.809279904708224e-05, "loss": 0.0236, "step": 13380 }, { "loss_action": 0.024363597854971886, "loss_total": 0.024363597854971886, "step": 13380 }, { "grad_norm": 0.45534196496009827, "learning_rate": 9.808827324594699e-05, "loss": 0.0223, "step": 13390 }, { "loss_action": 0.02283569611608982, "loss_total": 0.02283569611608982, "step": 13390 }, { "grad_norm": 0.44108083844184875, "learning_rate": 9.808374218595046e-05, "loss": 0.0237, "step": 13400 }, { "loss_action": 0.023585908114910126, "loss_total": 0.023585908114910126, "step": 13400 }, { "grad_norm": 0.5512653589248657, "learning_rate": 9.80792058675882e-05, "loss": 0.0245, "step": 13410 }, { "loss_action": 0.025226976722478867, "loss_total": 0.025226976722478867, "step": 13410 }, { "grad_norm": 0.44100239872932434, "learning_rate": 9.807466429135627e-05, "loss": 0.0254, "step": 13420 }, { "loss_action": 0.023736394941806793, "loss_total": 0.023736394941806793, "step": 13420 }, { "grad_norm": 0.5628853440284729, "learning_rate": 9.807011745775132e-05, "loss": 0.0257, "step": 13430 }, { "loss_action": 0.02351853810250759, "loss_total": 0.02351853810250759, "step": 13430 }, { "grad_norm": 0.6341291666030884, "learning_rate": 9.806556536727061e-05, "loss": 0.0252, "step": 13440 }, { "loss_action": 0.02619241364300251, "loss_total": 0.02619241364300251, "step": 13440 }, { "grad_norm": 0.4252946078777313, "learning_rate": 9.806100802041193e-05, "loss": 0.0271, "step": 13450 }, { "loss_action": 0.03549858555197716, "loss_total": 0.03549858555197716, "step": 13450 }, { "grad_norm": 0.42793595790863037, "learning_rate": 9.805644541767368e-05, "loss": 0.025, "step": 13460 }, { "loss_action": 0.024865224957466125, "loss_total": 0.024865224957466125, "step": 13460 }, { "grad_norm": 0.40262484550476074, "learning_rate": 9.805187755955478e-05, "loss": 0.0231, "step": 13470 }, { "loss_action": 0.022236671298742294, "loss_total": 0.022236671298742294, "step": 13470 }, { "grad_norm": 0.44629988074302673, "learning_rate": 9.804730444655483e-05, "loss": 0.0216, "step": 13480 }, { "loss_action": 0.020718572661280632, "loss_total": 0.020718572661280632, "step": 13480 }, { "grad_norm": 0.4373857080936432, "learning_rate": 9.804272607917388e-05, "loss": 0.0242, "step": 13490 }, { "loss_action": 0.01614578813314438, "loss_total": 0.01614578813314438, "step": 13490 }, { "grad_norm": 0.4632359743118286, "learning_rate": 9.803814245791265e-05, "loss": 0.0241, "step": 13500 }, { "loss_action": 0.024199072271585464, "loss_total": 0.024199072271585464, "step": 13500 }, { "grad_norm": 0.3743046522140503, "learning_rate": 9.803355358327239e-05, "loss": 0.0216, "step": 13510 }, { "loss_action": 0.01988055370748043, "loss_total": 0.01988055370748043, "step": 13510 }, { "grad_norm": 0.36227932572364807, "learning_rate": 9.802895945575492e-05, "loss": 0.0223, "step": 13520 }, { "loss_action": 0.023809274658560753, "loss_total": 0.023809274658560753, "step": 13520 }, { "grad_norm": 0.45648646354675293, "learning_rate": 9.802436007586266e-05, "loss": 0.0217, "step": 13530 }, { "loss_action": 0.020131442695856094, "loss_total": 0.020131442695856094, "step": 13530 }, { "grad_norm": 0.4437933564186096, "learning_rate": 9.801975544409858e-05, "loss": 0.0218, "step": 13540 }, { "loss_action": 0.02720808982849121, "loss_total": 0.02720808982849121, "step": 13540 }, { "grad_norm": 0.6002411246299744, "learning_rate": 9.801514556096625e-05, "loss": 0.025, "step": 13550 }, { "loss_action": 0.032977666705846786, "loss_total": 0.032977666705846786, "step": 13550 }, { "grad_norm": 0.4553982615470886, "learning_rate": 9.801053042696977e-05, "loss": 0.027, "step": 13560 }, { "loss_action": 0.027907848358154297, "loss_total": 0.027907848358154297, "step": 13560 }, { "grad_norm": 0.6930415630340576, "learning_rate": 9.800591004261388e-05, "loss": 0.0239, "step": 13570 }, { "loss_action": 0.023440049961209297, "loss_total": 0.023440049961209297, "step": 13570 }, { "grad_norm": 0.4643852114677429, "learning_rate": 9.800128440840385e-05, "loss": 0.0233, "step": 13580 }, { "loss_action": 0.020945334807038307, "loss_total": 0.020945334807038307, "step": 13580 }, { "grad_norm": 0.6693676114082336, "learning_rate": 9.799665352484552e-05, "loss": 0.0261, "step": 13590 }, { "loss_action": 0.028150293976068497, "loss_total": 0.028150293976068497, "step": 13590 }, { "grad_norm": 0.4355388879776001, "learning_rate": 9.799201739244532e-05, "loss": 0.0241, "step": 13600 }, { "loss_action": 0.030365772545337677, "loss_total": 0.030365772545337677, "step": 13600 }, { "grad_norm": 0.47645771503448486, "learning_rate": 9.798737601171025e-05, "loss": 0.0265, "step": 13610 }, { "loss_action": 0.019270673394203186, "loss_total": 0.019270673394203186, "step": 13610 }, { "grad_norm": 0.5458251237869263, "learning_rate": 9.79827293831479e-05, "loss": 0.0238, "step": 13620 }, { "loss_action": 0.03767714276909828, "loss_total": 0.03767714276909828, "step": 13620 }, { "grad_norm": 0.5093558430671692, "learning_rate": 9.797807750726638e-05, "loss": 0.0253, "step": 13630 }, { "loss_action": 0.02592189610004425, "loss_total": 0.02592189610004425, "step": 13630 }, { "grad_norm": 0.43508630990982056, "learning_rate": 9.797342038457446e-05, "loss": 0.0227, "step": 13640 }, { "loss_action": 0.019116731360554695, "loss_total": 0.019116731360554695, "step": 13640 }, { "grad_norm": 0.44096094369888306, "learning_rate": 9.796875801558141e-05, "loss": 0.0212, "step": 13650 }, { "loss_action": 0.01717345416545868, "loss_total": 0.01717345416545868, "step": 13650 }, { "grad_norm": 0.4849386513233185, "learning_rate": 9.79640904007971e-05, "loss": 0.0209, "step": 13660 }, { "loss_action": 0.022112298756837845, "loss_total": 0.022112298756837845, "step": 13660 }, { "grad_norm": 0.43325507640838623, "learning_rate": 9.795941754073199e-05, "loss": 0.0221, "step": 13670 }, { "loss_action": 0.03122364543378353, "loss_total": 0.03122364543378353, "step": 13670 }, { "grad_norm": 0.5416023135185242, "learning_rate": 9.795473943589705e-05, "loss": 0.0234, "step": 13680 }, { "loss_action": 0.027975859120488167, "loss_total": 0.027975859120488167, "step": 13680 }, { "grad_norm": 0.4133548438549042, "learning_rate": 9.795005608680394e-05, "loss": 0.0222, "step": 13690 }, { "loss_action": 0.018066687509417534, "loss_total": 0.018066687509417534, "step": 13690 }, { "grad_norm": 0.43201979994773865, "learning_rate": 9.794536749396477e-05, "loss": 0.0205, "step": 13700 }, { "loss_action": 0.020539917051792145, "loss_total": 0.020539917051792145, "step": 13700 }, { "grad_norm": 0.43695664405822754, "learning_rate": 9.79406736578923e-05, "loss": 0.0211, "step": 13710 }, { "loss_action": 0.017365779727697372, "loss_total": 0.017365779727697372, "step": 13710 }, { "grad_norm": 0.3917083442211151, "learning_rate": 9.793597457909984e-05, "loss": 0.0224, "step": 13720 }, { "loss_action": 0.029063642024993896, "loss_total": 0.029063642024993896, "step": 13720 }, { "grad_norm": 0.5047137141227722, "learning_rate": 9.793127025810127e-05, "loss": 0.0246, "step": 13730 }, { "loss_action": 0.026490606367588043, "loss_total": 0.026490606367588043, "step": 13730 }, { "grad_norm": 0.4642926752567291, "learning_rate": 9.792656069541104e-05, "loss": 0.0219, "step": 13740 }, { "loss_action": 0.022869162261486053, "loss_total": 0.022869162261486053, "step": 13740 }, { "grad_norm": 0.4314856231212616, "learning_rate": 9.79218458915442e-05, "loss": 0.0226, "step": 13750 }, { "loss_action": 0.026831166818737984, "loss_total": 0.026831166818737984, "step": 13750 }, { "grad_norm": 0.42539238929748535, "learning_rate": 9.791712584701634e-05, "loss": 0.0261, "step": 13760 }, { "loss_action": 0.038602203130722046, "loss_total": 0.038602203130722046, "step": 13760 }, { "grad_norm": 0.3971759080886841, "learning_rate": 9.791240056234364e-05, "loss": 0.0255, "step": 13770 }, { "loss_action": 0.023816369473934174, "loss_total": 0.023816369473934174, "step": 13770 }, { "grad_norm": 0.3985670804977417, "learning_rate": 9.790767003804283e-05, "loss": 0.0232, "step": 13780 }, { "loss_action": 0.015944864600896835, "loss_total": 0.015944864600896835, "step": 13780 }, { "grad_norm": 0.40872958302497864, "learning_rate": 9.790293427463126e-05, "loss": 0.0214, "step": 13790 }, { "loss_action": 0.027018960565328598, "loss_total": 0.027018960565328598, "step": 13790 }, { "grad_norm": 0.458766371011734, "learning_rate": 9.789819327262684e-05, "loss": 0.0247, "step": 13800 }, { "loss_action": 0.02726108580827713, "loss_total": 0.02726108580827713, "step": 13800 }, { "grad_norm": 0.4057052433490753, "learning_rate": 9.7893447032548e-05, "loss": 0.0242, "step": 13810 }, { "loss_action": 0.023240230977535248, "loss_total": 0.023240230977535248, "step": 13810 }, { "grad_norm": 0.39240404963493347, "learning_rate": 9.78886955549138e-05, "loss": 0.0219, "step": 13820 }, { "loss_action": 0.027450554072856903, "loss_total": 0.027450554072856903, "step": 13820 }, { "grad_norm": 0.400642454624176, "learning_rate": 9.788393884024387e-05, "loss": 0.0215, "step": 13830 }, { "loss_action": 0.022897226735949516, "loss_total": 0.022897226735949516, "step": 13830 }, { "grad_norm": 0.48469144105911255, "learning_rate": 9.787917688905836e-05, "loss": 0.0246, "step": 13840 }, { "loss_action": 0.037827204912900925, "loss_total": 0.037827204912900925, "step": 13840 }, { "grad_norm": 0.5171140432357788, "learning_rate": 9.787440970187807e-05, "loss": 0.0226, "step": 13850 }, { "loss_action": 0.018208494409918785, "loss_total": 0.018208494409918785, "step": 13850 }, { "grad_norm": 0.4151690602302551, "learning_rate": 9.786963727922429e-05, "loss": 0.0249, "step": 13860 }, { "loss_action": 0.020648518577218056, "loss_total": 0.020648518577218056, "step": 13860 }, { "grad_norm": 0.5476895570755005, "learning_rate": 9.786485962161897e-05, "loss": 0.0227, "step": 13870 }, { "loss_action": 0.018782511353492737, "loss_total": 0.018782511353492737, "step": 13870 }, { "grad_norm": 0.6269285082817078, "learning_rate": 9.786007672958455e-05, "loss": 0.026, "step": 13880 }, { "loss_action": 0.03093724325299263, "loss_total": 0.03093724325299263, "step": 13880 }, { "grad_norm": 0.4569578766822815, "learning_rate": 9.78552886036441e-05, "loss": 0.0259, "step": 13890 }, { "loss_action": 0.025227705016732216, "loss_total": 0.025227705016732216, "step": 13890 }, { "grad_norm": 0.4763573706150055, "learning_rate": 9.785049524432124e-05, "loss": 0.0266, "step": 13900 }, { "loss_action": 0.02064906433224678, "loss_total": 0.02064906433224678, "step": 13900 }, { "grad_norm": 0.4467840790748596, "learning_rate": 9.784569665214016e-05, "loss": 0.0251, "step": 13910 }, { "loss_action": 0.021949807181954384, "loss_total": 0.021949807181954384, "step": 13910 }, { "grad_norm": 0.36143213510513306, "learning_rate": 9.784089282762563e-05, "loss": 0.0217, "step": 13920 }, { "loss_action": 0.022904014214873314, "loss_total": 0.022904014214873314, "step": 13920 }, { "grad_norm": 0.4095518887042999, "learning_rate": 9.7836083771303e-05, "loss": 0.0221, "step": 13930 }, { "loss_action": 0.02282414212822914, "loss_total": 0.02282414212822914, "step": 13930 }, { "grad_norm": 0.3684748113155365, "learning_rate": 9.783126948369817e-05, "loss": 0.0215, "step": 13940 }, { "loss_action": 0.017738550901412964, "loss_total": 0.017738550901412964, "step": 13940 }, { "grad_norm": 0.35091716051101685, "learning_rate": 9.78264499653376e-05, "loss": 0.0217, "step": 13950 }, { "loss_action": 0.02139277383685112, "loss_total": 0.02139277383685112, "step": 13950 }, { "grad_norm": 0.4580954313278198, "learning_rate": 9.782162521674838e-05, "loss": 0.0228, "step": 13960 }, { "loss_action": 0.021954037249088287, "loss_total": 0.021954037249088287, "step": 13960 }, { "grad_norm": 0.4276031255722046, "learning_rate": 9.781679523845812e-05, "loss": 0.0198, "step": 13970 }, { "loss_action": 0.01872556284070015, "loss_total": 0.01872556284070015, "step": 13970 }, { "grad_norm": 0.49184292554855347, "learning_rate": 9.781196003099502e-05, "loss": 0.0209, "step": 13980 }, { "loss_action": 0.017540963366627693, "loss_total": 0.017540963366627693, "step": 13980 }, { "grad_norm": 0.3891392946243286, "learning_rate": 9.780711959488786e-05, "loss": 0.0186, "step": 13990 }, { "loss_action": 0.02085474319756031, "loss_total": 0.02085474319756031, "step": 13990 }, { "grad_norm": 0.39367741346359253, "learning_rate": 9.780227393066599e-05, "loss": 0.0214, "step": 14000 }, { "loss_action": 0.025159362703561783, "loss_total": 0.025159362703561783, "step": 14000 }, { "grad_norm": 0.38795581459999084, "learning_rate": 9.77974230388593e-05, "loss": 0.0221, "step": 14010 }, { "loss_action": 0.02847028709948063, "loss_total": 0.02847028709948063, "step": 14010 }, { "grad_norm": 0.4448249638080597, "learning_rate": 9.779256691999829e-05, "loss": 0.0223, "step": 14020 }, { "loss_action": 0.021664699539542198, "loss_total": 0.021664699539542198, "step": 14020 }, { "grad_norm": 0.4053540527820587, "learning_rate": 9.778770557461403e-05, "loss": 0.0221, "step": 14030 }, { "loss_action": 0.019597835838794708, "loss_total": 0.019597835838794708, "step": 14030 }, { "grad_norm": 0.4310302436351776, "learning_rate": 9.778283900323812e-05, "loss": 0.0189, "step": 14040 }, { "loss_action": 0.016881611198186874, "loss_total": 0.016881611198186874, "step": 14040 }, { "grad_norm": 0.4341784715652466, "learning_rate": 9.777796720640277e-05, "loss": 0.0193, "step": 14050 }, { "loss_action": 0.029249949380755424, "loss_total": 0.029249949380755424, "step": 14050 }, { "grad_norm": 0.5030357837677002, "learning_rate": 9.777309018464078e-05, "loss": 0.0208, "step": 14060 }, { "loss_action": 0.017901012673974037, "loss_total": 0.017901012673974037, "step": 14060 }, { "grad_norm": 0.4669129550457001, "learning_rate": 9.776820793848547e-05, "loss": 0.0212, "step": 14070 }, { "loss_action": 0.018738552927970886, "loss_total": 0.018738552927970886, "step": 14070 }, { "grad_norm": 0.36842814087867737, "learning_rate": 9.776332046847075e-05, "loss": 0.0209, "step": 14080 }, { "loss_action": 0.020849592983722687, "loss_total": 0.020849592983722687, "step": 14080 }, { "grad_norm": 0.34110501408576965, "learning_rate": 9.775842777513111e-05, "loss": 0.0212, "step": 14090 }, { "loss_action": 0.01977837085723877, "loss_total": 0.01977837085723877, "step": 14090 }, { "grad_norm": 0.379430890083313, "learning_rate": 9.775352985900163e-05, "loss": 0.0182, "step": 14100 }, { "loss_action": 0.01710950955748558, "loss_total": 0.01710950955748558, "step": 14100 }, { "grad_norm": 0.39408040046691895, "learning_rate": 9.774862672061791e-05, "loss": 0.0182, "step": 14110 }, { "loss_action": 0.01702296920120716, "loss_total": 0.01702296920120716, "step": 14110 }, { "grad_norm": 0.4995708167552948, "learning_rate": 9.774371836051616e-05, "loss": 0.0196, "step": 14120 }, { "loss_action": 0.02141387388110161, "loss_total": 0.02141387388110161, "step": 14120 }, { "grad_norm": 0.42859745025634766, "learning_rate": 9.773880477923315e-05, "loss": 0.0228, "step": 14130 }, { "loss_action": 0.02442276105284691, "loss_total": 0.02442276105284691, "step": 14130 }, { "grad_norm": 0.3688986301422119, "learning_rate": 9.773388597730623e-05, "loss": 0.0201, "step": 14140 }, { "loss_action": 0.02176247350871563, "loss_total": 0.02176247350871563, "step": 14140 }, { "grad_norm": 0.37441614270210266, "learning_rate": 9.77289619552733e-05, "loss": 0.0206, "step": 14150 }, { "loss_action": 0.02495446242392063, "loss_total": 0.02495446242392063, "step": 14150 }, { "grad_norm": 0.46192699670791626, "learning_rate": 9.772403271367285e-05, "loss": 0.0221, "step": 14160 }, { "loss_action": 0.018098030239343643, "loss_total": 0.018098030239343643, "step": 14160 }, { "grad_norm": 0.367205947637558, "learning_rate": 9.771909825304396e-05, "loss": 0.019, "step": 14170 }, { "loss_action": 0.017405487596988678, "loss_total": 0.017405487596988678, "step": 14170 }, { "grad_norm": 0.39019665122032166, "learning_rate": 9.771415857392619e-05, "loss": 0.0192, "step": 14180 }, { "loss_action": 0.01888044737279415, "loss_total": 0.01888044737279415, "step": 14180 }, { "grad_norm": 0.4149252772331238, "learning_rate": 9.770921367685978e-05, "loss": 0.0197, "step": 14190 }, { "loss_action": 0.026099219918251038, "loss_total": 0.026099219918251038, "step": 14190 }, { "grad_norm": 0.4521087408065796, "learning_rate": 9.770426356238551e-05, "loss": 0.023, "step": 14200 }, { "loss_action": 0.022137142717838287, "loss_total": 0.022137142717838287, "step": 14200 }, { "grad_norm": 0.522409975528717, "learning_rate": 9.769930823104469e-05, "loss": 0.0227, "step": 14210 }, { "loss_action": 0.027734875679016113, "loss_total": 0.027734875679016113, "step": 14210 }, { "grad_norm": 0.44783517718315125, "learning_rate": 9.769434768337926e-05, "loss": 0.0228, "step": 14220 }, { "loss_action": 0.024469712749123573, "loss_total": 0.024469712749123573, "step": 14220 }, { "grad_norm": 0.4265252649784088, "learning_rate": 9.768938191993164e-05, "loss": 0.0212, "step": 14230 }, { "loss_action": 0.026648370549082756, "loss_total": 0.026648370549082756, "step": 14230 }, { "grad_norm": 0.40620365738868713, "learning_rate": 9.768441094124494e-05, "loss": 0.0238, "step": 14240 }, { "loss_action": 0.021889997646212578, "loss_total": 0.021889997646212578, "step": 14240 }, { "grad_norm": 0.503960371017456, "learning_rate": 9.767943474786275e-05, "loss": 0.0227, "step": 14250 }, { "loss_action": 0.017954977229237556, "loss_total": 0.017954977229237556, "step": 14250 }, { "grad_norm": 0.31975850462913513, "learning_rate": 9.767445334032923e-05, "loss": 0.0216, "step": 14260 }, { "loss_action": 0.02327389270067215, "loss_total": 0.02327389270067215, "step": 14260 }, { "grad_norm": 0.42639148235321045, "learning_rate": 9.766946671918919e-05, "loss": 0.0212, "step": 14270 }, { "loss_action": 0.017278194427490234, "loss_total": 0.017278194427490234, "step": 14270 }, { "grad_norm": 0.34149760007858276, "learning_rate": 9.766447488498796e-05, "loss": 0.0199, "step": 14280 }, { "loss_action": 0.019193120300769806, "loss_total": 0.019193120300769806, "step": 14280 }, { "grad_norm": 0.47749146819114685, "learning_rate": 9.765947783827139e-05, "loss": 0.0221, "step": 14290 }, { "loss_action": 0.018056146800518036, "loss_total": 0.018056146800518036, "step": 14290 }, { "grad_norm": 0.4453625977039337, "learning_rate": 9.765447557958599e-05, "loss": 0.0211, "step": 14300 }, { "loss_action": 0.035207439213991165, "loss_total": 0.035207439213991165, "step": 14300 }, { "grad_norm": 0.420289546251297, "learning_rate": 9.764946810947879e-05, "loss": 0.0211, "step": 14310 }, { "loss_action": 0.029239866882562637, "loss_total": 0.029239866882562637, "step": 14310 }, { "grad_norm": 0.4710123836994171, "learning_rate": 9.764445542849738e-05, "loss": 0.0219, "step": 14320 }, { "loss_action": 0.021028099581599236, "loss_total": 0.021028099581599236, "step": 14320 }, { "grad_norm": 0.42131873965263367, "learning_rate": 9.763943753718998e-05, "loss": 0.0211, "step": 14330 }, { "loss_action": 0.019640428945422173, "loss_total": 0.019640428945422173, "step": 14330 }, { "grad_norm": 0.32982173562049866, "learning_rate": 9.76344144361053e-05, "loss": 0.0205, "step": 14340 }, { "loss_action": 0.02133985422551632, "loss_total": 0.02133985422551632, "step": 14340 }, { "grad_norm": 0.5274317860603333, "learning_rate": 9.762938612579269e-05, "loss": 0.02, "step": 14350 }, { "loss_action": 0.018497122451663017, "loss_total": 0.018497122451663017, "step": 14350 }, { "grad_norm": 0.5572977662086487, "learning_rate": 9.762435260680202e-05, "loss": 0.0197, "step": 14360 }, { "loss_action": 0.028139587491750717, "loss_total": 0.028139587491750717, "step": 14360 }, { "grad_norm": 0.5770529508590698, "learning_rate": 9.761931387968373e-05, "loss": 0.0241, "step": 14370 }, { "loss_action": 0.022497251629829407, "loss_total": 0.022497251629829407, "step": 14370 }, { "grad_norm": 0.41001567244529724, "learning_rate": 9.76142699449889e-05, "loss": 0.0235, "step": 14380 }, { "loss_action": 0.022960912436246872, "loss_total": 0.022960912436246872, "step": 14380 }, { "grad_norm": 0.5888426899909973, "learning_rate": 9.760922080326908e-05, "loss": 0.0246, "step": 14390 }, { "loss_action": 0.020482376217842102, "loss_total": 0.020482376217842102, "step": 14390 }, { "grad_norm": 0.37181413173675537, "learning_rate": 9.760416645507644e-05, "loss": 0.0222, "step": 14400 }, { "loss_action": 0.01712622493505478, "loss_total": 0.01712622493505478, "step": 14400 }, { "grad_norm": 0.587211549282074, "learning_rate": 9.759910690096375e-05, "loss": 0.0239, "step": 14410 }, { "loss_action": 0.026468336582183838, "loss_total": 0.026468336582183838, "step": 14410 }, { "grad_norm": 0.40317654609680176, "learning_rate": 9.759404214148429e-05, "loss": 0.0228, "step": 14420 }, { "loss_action": 0.030434289947152138, "loss_total": 0.030434289947152138, "step": 14420 }, { "grad_norm": 0.5336844325065613, "learning_rate": 9.758897217719191e-05, "loss": 0.0247, "step": 14430 }, { "loss_action": 0.019625253975391388, "loss_total": 0.019625253975391388, "step": 14430 }, { "grad_norm": 0.487296998500824, "learning_rate": 9.758389700864113e-05, "loss": 0.0253, "step": 14440 }, { "loss_action": 0.017423685640096664, "loss_total": 0.017423685640096664, "step": 14440 }, { "grad_norm": 0.49383798241615295, "learning_rate": 9.757881663638688e-05, "loss": 0.0216, "step": 14450 }, { "loss_action": 0.02181834727525711, "loss_total": 0.02181834727525711, "step": 14450 }, { "grad_norm": 0.4669358730316162, "learning_rate": 9.757373106098478e-05, "loss": 0.0214, "step": 14460 }, { "loss_action": 0.022126222029328346, "loss_total": 0.022126222029328346, "step": 14460 }, { "grad_norm": 0.5525434613227844, "learning_rate": 9.756864028299097e-05, "loss": 0.0235, "step": 14470 }, { "loss_action": 0.02754192240536213, "loss_total": 0.02754192240536213, "step": 14470 }, { "grad_norm": 0.5780898928642273, "learning_rate": 9.75635443029622e-05, "loss": 0.0247, "step": 14480 }, { "loss_action": 0.021244335919618607, "loss_total": 0.021244335919618607, "step": 14480 }, { "grad_norm": 0.38221004605293274, "learning_rate": 9.755844312145572e-05, "loss": 0.0223, "step": 14490 }, { "loss_action": 0.01884368620812893, "loss_total": 0.01884368620812893, "step": 14490 }, { "grad_norm": 0.33278822898864746, "learning_rate": 9.755333673902941e-05, "loss": 0.0192, "step": 14500 }, { "loss_action": 0.027072088792920113, "loss_total": 0.027072088792920113, "step": 14500 }, { "grad_norm": 0.577191174030304, "learning_rate": 9.75482251562417e-05, "loss": 0.021, "step": 14510 }, { "loss_action": 0.020774753764271736, "loss_total": 0.020774753764271736, "step": 14510 }, { "grad_norm": 0.4387766122817993, "learning_rate": 9.754310837365155e-05, "loss": 0.0224, "step": 14520 }, { "loss_action": 0.01936614140868187, "loss_total": 0.01936614140868187, "step": 14520 }, { "grad_norm": 0.5820471048355103, "learning_rate": 9.753798639181856e-05, "loss": 0.0229, "step": 14530 }, { "loss_action": 0.024929165840148926, "loss_total": 0.024929165840148926, "step": 14530 }, { "grad_norm": 0.3926602005958557, "learning_rate": 9.753285921130286e-05, "loss": 0.0247, "step": 14540 }, { "loss_action": 0.02092425338923931, "loss_total": 0.02092425338923931, "step": 14540 }, { "grad_norm": 0.4748275578022003, "learning_rate": 9.752772683266512e-05, "loss": 0.0232, "step": 14550 }, { "loss_action": 0.022893918678164482, "loss_total": 0.022893918678164482, "step": 14550 }, { "grad_norm": 0.3898440897464752, "learning_rate": 9.752258925646665e-05, "loss": 0.023, "step": 14560 }, { "loss_action": 0.018511321395635605, "loss_total": 0.018511321395635605, "step": 14560 }, { "grad_norm": 0.33422207832336426, "learning_rate": 9.751744648326926e-05, "loss": 0.0225, "step": 14570 }, { "loss_action": 0.021350916475057602, "loss_total": 0.021350916475057602, "step": 14570 }, { "grad_norm": 0.39367911219596863, "learning_rate": 9.751229851363536e-05, "loss": 0.0219, "step": 14580 }, { "loss_action": 0.026155754923820496, "loss_total": 0.026155754923820496, "step": 14580 }, { "grad_norm": 0.3751325309276581, "learning_rate": 9.750714534812793e-05, "loss": 0.0228, "step": 14590 }, { "loss_action": 0.020370276644825935, "loss_total": 0.020370276644825935, "step": 14590 }, { "grad_norm": 0.8458166718482971, "learning_rate": 9.750198698731053e-05, "loss": 0.0211, "step": 14600 }, { "loss_action": 0.020680533722043037, "loss_total": 0.020680533722043037, "step": 14600 }, { "grad_norm": 0.7541763782501221, "learning_rate": 9.749682343174722e-05, "loss": 0.0248, "step": 14610 }, { "loss_action": 0.021662000566720963, "loss_total": 0.021662000566720963, "step": 14610 }, { "grad_norm": 0.7943942546844482, "learning_rate": 9.749165468200272e-05, "loss": 0.0307, "step": 14620 }, { "loss_action": 0.027608798816800117, "loss_total": 0.027608798816800117, "step": 14620 }, { "grad_norm": 0.5221847295761108, "learning_rate": 9.748648073864229e-05, "loss": 0.0275, "step": 14630 }, { "loss_action": 0.02096298150718212, "loss_total": 0.02096298150718212, "step": 14630 }, { "grad_norm": 0.6069525480270386, "learning_rate": 9.748130160223168e-05, "loss": 0.0268, "step": 14640 }, { "loss_action": 0.027346089482307434, "loss_total": 0.027346089482307434, "step": 14640 }, { "grad_norm": 0.4083380103111267, "learning_rate": 9.747611727333734e-05, "loss": 0.0254, "step": 14650 }, { "loss_action": 0.0235887598246336, "loss_total": 0.0235887598246336, "step": 14650 }, { "grad_norm": 0.5254895091056824, "learning_rate": 9.74709277525262e-05, "loss": 0.0243, "step": 14660 }, { "loss_action": 0.017085950821638107, "loss_total": 0.017085950821638107, "step": 14660 }, { "grad_norm": 0.5079727172851562, "learning_rate": 9.746573304036576e-05, "loss": 0.023, "step": 14670 }, { "loss_action": 0.09974532574415207, "loss_total": 0.09974532574415207, "step": 14670 }, { "grad_norm": 0.6019580364227295, "learning_rate": 9.746053313742412e-05, "loss": 0.0458, "step": 14680 }, { "loss_action": 0.03248937800526619, "loss_total": 0.03248937800526619, "step": 14680 }, { "grad_norm": 0.5112210512161255, "learning_rate": 9.745532804426994e-05, "loss": 0.0295, "step": 14690 }, { "loss_action": 0.0281512513756752, "loss_total": 0.0281512513756752, "step": 14690 }, { "grad_norm": 0.6281360387802124, "learning_rate": 9.745011776147242e-05, "loss": 0.0298, "step": 14700 }, { "loss_action": 0.020969631150364876, "loss_total": 0.020969631150364876, "step": 14700 }, { "grad_norm": 0.6335200071334839, "learning_rate": 9.744490228960138e-05, "loss": 0.0293, "step": 14710 }, { "loss_action": 0.024226246401667595, "loss_total": 0.024226246401667595, "step": 14710 }, { "grad_norm": 0.4909115731716156, "learning_rate": 9.743968162922713e-05, "loss": 0.0284, "step": 14720 }, { "loss_action": 0.03397146239876747, "loss_total": 0.03397146239876747, "step": 14720 }, { "grad_norm": 0.47999390959739685, "learning_rate": 9.743445578092064e-05, "loss": 0.0297, "step": 14730 }, { "loss_action": 0.021591579541563988, "loss_total": 0.021591579541563988, "step": 14730 }, { "grad_norm": 0.5058773159980774, "learning_rate": 9.742922474525338e-05, "loss": 0.026, "step": 14740 }, { "loss_action": 0.02958529070019722, "loss_total": 0.02958529070019722, "step": 14740 }, { "grad_norm": 0.6021970510482788, "learning_rate": 9.742398852279741e-05, "loss": 0.0287, "step": 14750 }, { "loss_action": 0.025001130998134613, "loss_total": 0.025001130998134613, "step": 14750 }, { "grad_norm": 0.6160579323768616, "learning_rate": 9.741874711412535e-05, "loss": 0.0253, "step": 14760 }, { "loss_action": 0.02358825132250786, "loss_total": 0.02358825132250786, "step": 14760 }, { "grad_norm": 0.45095011591911316, "learning_rate": 9.741350051981042e-05, "loss": 0.0244, "step": 14770 }, { "loss_action": 0.022344421595335007, "loss_total": 0.022344421595335007, "step": 14770 }, { "grad_norm": 0.7735289335250854, "learning_rate": 9.740824874042633e-05, "loss": 0.0281, "step": 14780 }, { "loss_action": 0.034898653626441956, "loss_total": 0.034898653626441956, "step": 14780 }, { "grad_norm": 0.7122666239738464, "learning_rate": 9.740299177654746e-05, "loss": 0.0368, "step": 14790 }, { "loss_action": 0.046538084745407104, "loss_total": 0.046538084745407104, "step": 14790 }, { "grad_norm": 0.6121280789375305, "learning_rate": 9.739772962874867e-05, "loss": 0.0329, "step": 14800 }, { "loss_action": 0.03328041732311249, "loss_total": 0.03328041732311249, "step": 14800 }, { "grad_norm": 0.7440356612205505, "learning_rate": 9.739246229760541e-05, "loss": 0.0354, "step": 14810 }, { "loss_action": 0.026280011981725693, "loss_total": 0.026280011981725693, "step": 14810 }, { "grad_norm": 0.530851423740387, "learning_rate": 9.738718978369376e-05, "loss": 0.037, "step": 14820 }, { "loss_action": 0.036766618490219116, "loss_total": 0.036766618490219116, "step": 14820 }, { "grad_norm": 0.5844917297363281, "learning_rate": 9.738191208759025e-05, "loss": 0.0336, "step": 14830 }, { "loss_action": 0.027840590104460716, "loss_total": 0.027840590104460716, "step": 14830 }, { "grad_norm": 0.4525027573108673, "learning_rate": 9.73766292098721e-05, "loss": 0.0318, "step": 14840 }, { "loss_action": 0.02969806268811226, "loss_total": 0.02969806268811226, "step": 14840 }, { "grad_norm": 0.3272251784801483, "learning_rate": 9.737134115111699e-05, "loss": 0.0291, "step": 14850 }, { "loss_action": 0.026605192571878433, "loss_total": 0.026605192571878433, "step": 14850 }, { "grad_norm": 0.48073726892471313, "learning_rate": 9.736604791190323e-05, "loss": 0.0258, "step": 14860 }, { "loss_action": 0.02087360806763172, "loss_total": 0.02087360806763172, "step": 14860 }, { "grad_norm": 0.446402907371521, "learning_rate": 9.73607494928097e-05, "loss": 0.0261, "step": 14870 }, { "loss_action": 0.022581271827220917, "loss_total": 0.022581271827220917, "step": 14870 }, { "grad_norm": 0.3841385543346405, "learning_rate": 9.735544589441581e-05, "loss": 0.0236, "step": 14880 }, { "loss_action": 0.02414821833372116, "loss_total": 0.02414821833372116, "step": 14880 }, { "grad_norm": 0.37645384669303894, "learning_rate": 9.735013711730154e-05, "loss": 0.024, "step": 14890 }, { "loss_action": 0.022074852138757706, "loss_total": 0.022074852138757706, "step": 14890 }, { "grad_norm": 0.3817442059516907, "learning_rate": 9.734482316204747e-05, "loss": 0.0211, "step": 14900 }, { "loss_action": 0.02209147997200489, "loss_total": 0.02209147997200489, "step": 14900 }, { "grad_norm": 0.4346106946468353, "learning_rate": 9.733950402923473e-05, "loss": 0.0216, "step": 14910 }, { "loss_action": 0.02155478484928608, "loss_total": 0.02155478484928608, "step": 14910 }, { "grad_norm": 0.356016606092453, "learning_rate": 9.7334179719445e-05, "loss": 0.0225, "step": 14920 }, { "loss_action": 0.019896162673830986, "loss_total": 0.019896162673830986, "step": 14920 }, { "grad_norm": 0.43381467461586, "learning_rate": 9.732885023326053e-05, "loss": 0.0234, "step": 14930 }, { "loss_action": 0.02213357575237751, "loss_total": 0.02213357575237751, "step": 14930 }, { "grad_norm": 0.49767422676086426, "learning_rate": 9.732351557126418e-05, "loss": 0.0216, "step": 14940 }, { "loss_action": 0.021143829450011253, "loss_total": 0.021143829450011253, "step": 14940 }, { "grad_norm": 0.4790646433830261, "learning_rate": 9.731817573403929e-05, "loss": 0.0227, "step": 14950 }, { "loss_action": 0.023952461779117584, "loss_total": 0.023952461779117584, "step": 14950 }, { "grad_norm": 0.38257288932800293, "learning_rate": 9.731283072216985e-05, "loss": 0.0234, "step": 14960 }, { "loss_action": 0.02008587308228016, "loss_total": 0.02008587308228016, "step": 14960 }, { "grad_norm": 0.4344802796840668, "learning_rate": 9.730748053624039e-05, "loss": 0.0218, "step": 14970 }, { "loss_action": 0.023073481395840645, "loss_total": 0.023073481395840645, "step": 14970 }, { "grad_norm": 0.3706064820289612, "learning_rate": 9.730212517683598e-05, "loss": 0.0208, "step": 14980 }, { "loss_action": 0.018845880404114723, "loss_total": 0.018845880404114723, "step": 14980 }, { "grad_norm": 0.4074361026287079, "learning_rate": 9.729676464454228e-05, "loss": 0.0204, "step": 14990 }, { "loss_action": 0.017279546707868576, "loss_total": 0.017279546707868576, "step": 14990 }, { "grad_norm": 0.3802396059036255, "learning_rate": 9.72913989399455e-05, "loss": 0.0198, "step": 15000 }, { "loss_action": 0.01644599437713623, "loss_total": 0.01644599437713623, "step": 15000 }, { "grad_norm": 0.4075891673564911, "learning_rate": 9.728602806363242e-05, "loss": 0.0217, "step": 15010 }, { "loss_action": 0.02390667237341404, "loss_total": 0.02390667237341404, "step": 15010 }, { "grad_norm": 0.3906122148036957, "learning_rate": 9.728065201619043e-05, "loss": 0.0212, "step": 15020 }, { "loss_action": 0.021631812676787376, "loss_total": 0.021631812676787376, "step": 15020 }, { "grad_norm": 0.44879624247550964, "learning_rate": 9.727527079820742e-05, "loss": 0.0221, "step": 15030 }, { "loss_action": 0.021542169153690338, "loss_total": 0.021542169153690338, "step": 15030 }, { "grad_norm": 0.3360314965248108, "learning_rate": 9.726988441027186e-05, "loss": 0.0226, "step": 15040 }, { "loss_action": 0.01624358259141445, "loss_total": 0.01624358259141445, "step": 15040 }, { "grad_norm": 0.39565134048461914, "learning_rate": 9.726449285297281e-05, "loss": 0.023, "step": 15050 }, { "loss_action": 0.022065652534365654, "loss_total": 0.022065652534365654, "step": 15050 }, { "grad_norm": 0.3491409122943878, "learning_rate": 9.72590961268999e-05, "loss": 0.0205, "step": 15060 }, { "loss_action": 0.021198520436882973, "loss_total": 0.021198520436882973, "step": 15060 }, { "grad_norm": 0.41458097100257874, "learning_rate": 9.725369423264328e-05, "loss": 0.0231, "step": 15070 }, { "loss_action": 0.01815279945731163, "loss_total": 0.01815279945731163, "step": 15070 }, { "grad_norm": 0.3720431923866272, "learning_rate": 9.72482871707937e-05, "loss": 0.0217, "step": 15080 }, { "loss_action": 0.014719448983669281, "loss_total": 0.014719448983669281, "step": 15080 }, { "grad_norm": 0.4718678593635559, "learning_rate": 9.724287494194247e-05, "loss": 0.0211, "step": 15090 }, { "loss_action": 0.019959691911935806, "loss_total": 0.019959691911935806, "step": 15090 }, { "grad_norm": 0.4372991919517517, "learning_rate": 9.723745754668147e-05, "loss": 0.0212, "step": 15100 }, { "loss_action": 0.02055235393345356, "loss_total": 0.02055235393345356, "step": 15100 }, { "grad_norm": 0.45445817708969116, "learning_rate": 9.723203498560313e-05, "loss": 0.0214, "step": 15110 }, { "loss_action": 0.01567799225449562, "loss_total": 0.01567799225449562, "step": 15110 }, { "grad_norm": 0.4042796492576599, "learning_rate": 9.722660725930046e-05, "loss": 0.0211, "step": 15120 }, { "loss_action": 0.034690335392951965, "loss_total": 0.034690335392951965, "step": 15120 }, { "grad_norm": 0.42567214369773865, "learning_rate": 9.722117436836702e-05, "loss": 0.0233, "step": 15130 }, { "loss_action": 0.020193258300423622, "loss_total": 0.020193258300423622, "step": 15130 }, { "grad_norm": 0.3501254618167877, "learning_rate": 9.721573631339696e-05, "loss": 0.0216, "step": 15140 }, { "loss_action": 0.025394974276423454, "loss_total": 0.025394974276423454, "step": 15140 }, { "grad_norm": 0.4547770321369171, "learning_rate": 9.721029309498494e-05, "loss": 0.0226, "step": 15150 }, { "loss_action": 0.01718352921307087, "loss_total": 0.01718352921307087, "step": 15150 }, { "grad_norm": 0.4656416177749634, "learning_rate": 9.720484471372627e-05, "loss": 0.02, "step": 15160 }, { "loss_action": 0.025241589173674583, "loss_total": 0.025241589173674583, "step": 15160 }, { "grad_norm": 0.4090401232242584, "learning_rate": 9.719939117021673e-05, "loss": 0.0225, "step": 15170 }, { "loss_action": 0.03053000196814537, "loss_total": 0.03053000196814537, "step": 15170 }, { "grad_norm": 0.3484233319759369, "learning_rate": 9.719393246505275e-05, "loss": 0.0227, "step": 15180 }, { "loss_action": 0.015853414312005043, "loss_total": 0.015853414312005043, "step": 15180 }, { "grad_norm": 0.49383750557899475, "learning_rate": 9.718846859883128e-05, "loss": 0.0213, "step": 15190 }, { "loss_action": 0.02079601027071476, "loss_total": 0.02079601027071476, "step": 15190 }, { "grad_norm": 0.5291115641593933, "learning_rate": 9.718299957214982e-05, "loss": 0.0245, "step": 15200 }, { "loss_action": 0.034021928906440735, "loss_total": 0.034021928906440735, "step": 15200 }, { "grad_norm": 0.4114023447036743, "learning_rate": 9.717752538560646e-05, "loss": 0.026, "step": 15210 }, { "loss_action": 0.02103460766375065, "loss_total": 0.02103460766375065, "step": 15210 }, { "grad_norm": 0.38951539993286133, "learning_rate": 9.717204603979986e-05, "loss": 0.0216, "step": 15220 }, { "loss_action": 0.01818695291876793, "loss_total": 0.01818695291876793, "step": 15220 }, { "grad_norm": 0.47167661786079407, "learning_rate": 9.716656153532922e-05, "loss": 0.023, "step": 15230 }, { "loss_action": 0.025550803169608116, "loss_total": 0.025550803169608116, "step": 15230 }, { "grad_norm": 0.4030413031578064, "learning_rate": 9.716107187279434e-05, "loss": 0.022, "step": 15240 }, { "loss_action": 0.02804502658545971, "loss_total": 0.02804502658545971, "step": 15240 }, { "grad_norm": 0.4472792148590088, "learning_rate": 9.715557705279555e-05, "loss": 0.0204, "step": 15250 }, { "loss_action": 0.021743765100836754, "loss_total": 0.021743765100836754, "step": 15250 }, { "grad_norm": 0.4185429811477661, "learning_rate": 9.715007707593372e-05, "loss": 0.0197, "step": 15260 }, { "loss_action": 0.016577940434217453, "loss_total": 0.016577940434217453, "step": 15260 }, { "grad_norm": 0.48707473278045654, "learning_rate": 9.714457194281036e-05, "loss": 0.0241, "step": 15270 }, { "loss_action": 0.01799274981021881, "loss_total": 0.01799274981021881, "step": 15270 }, { "grad_norm": 0.4108876883983612, "learning_rate": 9.713906165402751e-05, "loss": 0.0218, "step": 15280 }, { "loss_action": 0.021256975829601288, "loss_total": 0.021256975829601288, "step": 15280 }, { "grad_norm": 0.438876748085022, "learning_rate": 9.713354621018774e-05, "loss": 0.0208, "step": 15290 }, { "loss_action": 0.019810009747743607, "loss_total": 0.019810009747743607, "step": 15290 }, { "grad_norm": 0.37813425064086914, "learning_rate": 9.712802561189422e-05, "loss": 0.0223, "step": 15300 }, { "loss_action": 0.023608265444636345, "loss_total": 0.023608265444636345, "step": 15300 }, { "grad_norm": 0.48437273502349854, "learning_rate": 9.712249985975069e-05, "loss": 0.0251, "step": 15310 }, { "loss_action": 0.020547237247228622, "loss_total": 0.020547237247228622, "step": 15310 }, { "grad_norm": 0.4314931333065033, "learning_rate": 9.71169689543614e-05, "loss": 0.0226, "step": 15320 }, { "loss_action": 0.021440474316477776, "loss_total": 0.021440474316477776, "step": 15320 }, { "grad_norm": 0.4727593660354614, "learning_rate": 9.711143289633123e-05, "loss": 0.0208, "step": 15330 }, { "loss_action": 0.03224319592118263, "loss_total": 0.03224319592118263, "step": 15330 }, { "grad_norm": 0.6843883395195007, "learning_rate": 9.710589168626561e-05, "loss": 0.0365, "step": 15340 }, { "loss_action": 0.03531485050916672, "loss_total": 0.03531485050916672, "step": 15340 }, { "grad_norm": 0.5257564187049866, "learning_rate": 9.710034532477048e-05, "loss": 0.0266, "step": 15350 }, { "loss_action": 0.02812681905925274, "loss_total": 0.02812681905925274, "step": 15350 }, { "grad_norm": 0.3946306109428406, "learning_rate": 9.709479381245239e-05, "loss": 0.0268, "step": 15360 }, { "loss_action": 0.027930982410907745, "loss_total": 0.027930982410907745, "step": 15360 }, { "grad_norm": 0.47766169905662537, "learning_rate": 9.708923714991847e-05, "loss": 0.0267, "step": 15370 }, { "loss_action": 0.03012087382376194, "loss_total": 0.03012087382376194, "step": 15370 }, { "grad_norm": 0.3775057792663574, "learning_rate": 9.708367533777638e-05, "loss": 0.0232, "step": 15380 }, { "loss_action": 0.017161371186375618, "loss_total": 0.017161371186375618, "step": 15380 }, { "grad_norm": 0.4363296627998352, "learning_rate": 9.707810837663431e-05, "loss": 0.0217, "step": 15390 }, { "loss_action": 0.02059301920235157, "loss_total": 0.02059301920235157, "step": 15390 }, { "grad_norm": 0.4310853183269501, "learning_rate": 9.707253626710113e-05, "loss": 0.0222, "step": 15400 }, { "loss_action": 0.018257394433021545, "loss_total": 0.018257394433021545, "step": 15400 }, { "grad_norm": 0.4326225519180298, "learning_rate": 9.706695900978613e-05, "loss": 0.0217, "step": 15410 }, { "loss_action": 0.021378587931394577, "loss_total": 0.021378587931394577, "step": 15410 }, { "grad_norm": 0.4373912811279297, "learning_rate": 9.706137660529926e-05, "loss": 0.0209, "step": 15420 }, { "loss_action": 0.023846643045544624, "loss_total": 0.023846643045544624, "step": 15420 }, { "grad_norm": 0.4673885405063629, "learning_rate": 9.705578905425101e-05, "loss": 0.0217, "step": 15430 }, { "loss_action": 0.018844978883862495, "loss_total": 0.018844978883862495, "step": 15430 }, { "grad_norm": 0.3576526939868927, "learning_rate": 9.705019635725241e-05, "loss": 0.022, "step": 15440 }, { "loss_action": 0.022225454449653625, "loss_total": 0.022225454449653625, "step": 15440 }, { "grad_norm": 0.44839006662368774, "learning_rate": 9.704459851491508e-05, "loss": 0.0227, "step": 15450 }, { "loss_action": 0.015239722095429897, "loss_total": 0.015239722095429897, "step": 15450 }, { "grad_norm": 0.4081316292285919, "learning_rate": 9.703899552785118e-05, "loss": 0.0193, "step": 15460 }, { "loss_action": 0.01671772450208664, "loss_total": 0.01671772450208664, "step": 15460 }, { "grad_norm": 0.4628622531890869, "learning_rate": 9.703338739667346e-05, "loss": 0.0228, "step": 15470 }, { "loss_action": 0.019638895988464355, "loss_total": 0.019638895988464355, "step": 15470 }, { "grad_norm": 0.5308589339256287, "learning_rate": 9.70277741219952e-05, "loss": 0.0242, "step": 15480 }, { "loss_action": 0.021630631759762764, "loss_total": 0.021630631759762764, "step": 15480 }, { "grad_norm": 0.43529415130615234, "learning_rate": 9.702215570443027e-05, "loss": 0.0207, "step": 15490 }, { "loss_action": 0.01898043416440487, "loss_total": 0.01898043416440487, "step": 15490 }, { "grad_norm": 0.3565845787525177, "learning_rate": 9.701653214459309e-05, "loss": 0.022, "step": 15500 }, { "loss_action": 0.024097517132759094, "loss_total": 0.024097517132759094, "step": 15500 }, { "grad_norm": 0.6391220092773438, "learning_rate": 9.701090344309865e-05, "loss": 0.0248, "step": 15510 }, { "loss_action": 0.022833701223134995, "loss_total": 0.022833701223134995, "step": 15510 }, { "grad_norm": 0.6125988960266113, "learning_rate": 9.700526960056247e-05, "loss": 0.0269, "step": 15520 }, { "loss_action": 0.026592852547764778, "loss_total": 0.026592852547764778, "step": 15520 }, { "grad_norm": 0.49439311027526855, "learning_rate": 9.699963061760068e-05, "loss": 0.0269, "step": 15530 }, { "loss_action": 0.024816283956170082, "loss_total": 0.024816283956170082, "step": 15530 }, { "grad_norm": 0.40900886058807373, "learning_rate": 9.699398649482997e-05, "loss": 0.0223, "step": 15540 }, { "loss_action": 0.02242385596036911, "loss_total": 0.02242385596036911, "step": 15540 }, { "grad_norm": 0.4861106276512146, "learning_rate": 9.698833723286753e-05, "loss": 0.0265, "step": 15550 }, { "loss_action": 0.03130759298801422, "loss_total": 0.03130759298801422, "step": 15550 }, { "grad_norm": 0.45387157797813416, "learning_rate": 9.698268283233118e-05, "loss": 0.0281, "step": 15560 }, { "loss_action": 0.01955563947558403, "loss_total": 0.01955563947558403, "step": 15560 }, { "grad_norm": 0.5356608033180237, "learning_rate": 9.697702329383929e-05, "loss": 0.0227, "step": 15570 }, { "loss_action": 0.02472134865820408, "loss_total": 0.02472134865820408, "step": 15570 }, { "grad_norm": 0.3664799630641937, "learning_rate": 9.697135861801074e-05, "loss": 0.0219, "step": 15580 }, { "loss_action": 0.029997754842042923, "loss_total": 0.029997754842042923, "step": 15580 }, { "grad_norm": 0.5381391644477844, "learning_rate": 9.696568880546505e-05, "loss": 0.0233, "step": 15590 }, { "loss_action": 0.025717778131365776, "loss_total": 0.025717778131365776, "step": 15590 }, { "grad_norm": 0.43079593777656555, "learning_rate": 9.696001385682223e-05, "loss": 0.0247, "step": 15600 }, { "loss_action": 0.030361458659172058, "loss_total": 0.030361458659172058, "step": 15600 }, { "grad_norm": 0.4141468405723572, "learning_rate": 9.695433377270291e-05, "loss": 0.0222, "step": 15610 }, { "loss_action": 0.019611844792962074, "loss_total": 0.019611844792962074, "step": 15610 }, { "grad_norm": 0.4251842796802521, "learning_rate": 9.694864855372824e-05, "loss": 0.0197, "step": 15620 }, { "loss_action": 0.025039920583367348, "loss_total": 0.025039920583367348, "step": 15620 }, { "grad_norm": 0.579330563545227, "learning_rate": 9.694295820051995e-05, "loss": 0.0232, "step": 15630 }, { "loss_action": 0.01906600408256054, "loss_total": 0.01906600408256054, "step": 15630 }, { "grad_norm": 0.37888431549072266, "learning_rate": 9.693726271370032e-05, "loss": 0.021, "step": 15640 }, { "loss_action": 0.023531951010227203, "loss_total": 0.023531951010227203, "step": 15640 }, { "grad_norm": 0.3664238154888153, "learning_rate": 9.693156209389221e-05, "loss": 0.0218, "step": 15650 }, { "loss_action": 0.01970175839960575, "loss_total": 0.01970175839960575, "step": 15650 }, { "grad_norm": 0.3464021682739258, "learning_rate": 9.692585634171905e-05, "loss": 0.0212, "step": 15660 }, { "loss_action": 0.029343392699956894, "loss_total": 0.029343392699956894, "step": 15660 }, { "grad_norm": 0.40595507621765137, "learning_rate": 9.692014545780476e-05, "loss": 0.0236, "step": 15670 }, { "loss_action": 0.022417103871703148, "loss_total": 0.022417103871703148, "step": 15670 }, { "grad_norm": 0.38020244240760803, "learning_rate": 9.691442944277393e-05, "loss": 0.0195, "step": 15680 }, { "loss_action": 0.020204221829771996, "loss_total": 0.020204221829771996, "step": 15680 }, { "grad_norm": 0.41325801610946655, "learning_rate": 9.690870829725162e-05, "loss": 0.0201, "step": 15690 }, { "loss_action": 0.023152701556682587, "loss_total": 0.023152701556682587, "step": 15690 }, { "grad_norm": 0.44553402066230774, "learning_rate": 9.69029820218635e-05, "loss": 0.0206, "step": 15700 }, { "loss_action": 0.016581427305936813, "loss_total": 0.016581427305936813, "step": 15700 }, { "grad_norm": 0.4816253185272217, "learning_rate": 9.689725061723579e-05, "loss": 0.0217, "step": 15710 }, { "loss_action": 0.01611758954823017, "loss_total": 0.01611758954823017, "step": 15710 }, { "grad_norm": 0.4112064838409424, "learning_rate": 9.689151408399527e-05, "loss": 0.0201, "step": 15720 }, { "loss_action": 0.02597937360405922, "loss_total": 0.02597937360405922, "step": 15720 }, { "grad_norm": 0.3951713442802429, "learning_rate": 9.688577242276924e-05, "loss": 0.0224, "step": 15730 }, { "loss_action": 0.01934453658759594, "loss_total": 0.01934453658759594, "step": 15730 }, { "grad_norm": 0.465340256690979, "learning_rate": 9.688002563418566e-05, "loss": 0.0205, "step": 15740 }, { "loss_action": 0.018538082018494606, "loss_total": 0.018538082018494606, "step": 15740 }, { "grad_norm": 0.31320106983184814, "learning_rate": 9.687427371887293e-05, "loss": 0.019, "step": 15750 }, { "loss_action": 0.022504938766360283, "loss_total": 0.022504938766360283, "step": 15750 }, { "grad_norm": 0.4914570450782776, "learning_rate": 9.686851667746012e-05, "loss": 0.0212, "step": 15760 }, { "loss_action": 0.028283869847655296, "loss_total": 0.028283869847655296, "step": 15760 }, { "grad_norm": 0.29885783791542053, "learning_rate": 9.686275451057677e-05, "loss": 0.022, "step": 15770 }, { "loss_action": 0.019164612516760826, "loss_total": 0.019164612516760826, "step": 15770 }, { "grad_norm": 0.5168570876121521, "learning_rate": 9.685698721885308e-05, "loss": 0.0213, "step": 15780 }, { "loss_action": 0.01764872297644615, "loss_total": 0.01764872297644615, "step": 15780 }, { "grad_norm": 0.36764273047447205, "learning_rate": 9.68512148029197e-05, "loss": 0.023, "step": 15790 }, { "loss_action": 0.026205237954854965, "loss_total": 0.026205237954854965, "step": 15790 }, { "grad_norm": 0.35314077138900757, "learning_rate": 9.684543726340791e-05, "loss": 0.0213, "step": 15800 }, { "loss_action": 0.023470990359783173, "loss_total": 0.023470990359783173, "step": 15800 }, { "grad_norm": 0.5823065638542175, "learning_rate": 9.683965460094952e-05, "loss": 0.023, "step": 15810 }, { "loss_action": 0.020629726350307465, "loss_total": 0.020629726350307465, "step": 15810 }, { "grad_norm": 0.4365219473838806, "learning_rate": 9.683386681617694e-05, "loss": 0.0228, "step": 15820 }, { "loss_action": 0.02527392841875553, "loss_total": 0.02527392841875553, "step": 15820 }, { "grad_norm": 0.47935158014297485, "learning_rate": 9.68280739097231e-05, "loss": 0.0227, "step": 15830 }, { "loss_action": 0.019457027316093445, "loss_total": 0.019457027316093445, "step": 15830 }, { "grad_norm": 0.5958249568939209, "learning_rate": 9.682227588222148e-05, "loss": 0.0219, "step": 15840 }, { "loss_action": 0.021541301161050797, "loss_total": 0.021541301161050797, "step": 15840 }, { "grad_norm": 0.4317986071109772, "learning_rate": 9.681647273430618e-05, "loss": 0.0216, "step": 15850 }, { "loss_action": 0.018942104652523994, "loss_total": 0.018942104652523994, "step": 15850 }, { "grad_norm": 0.46988505125045776, "learning_rate": 9.681066446661182e-05, "loss": 0.0248, "step": 15860 }, { "loss_action": 0.026737678796052933, "loss_total": 0.026737678796052933, "step": 15860 }, { "grad_norm": 0.4196644425392151, "learning_rate": 9.680485107977357e-05, "loss": 0.0222, "step": 15870 }, { "loss_action": 0.019596396014094353, "loss_total": 0.019596396014094353, "step": 15870 }, { "grad_norm": 0.5448759198188782, "learning_rate": 9.679903257442716e-05, "loss": 0.0253, "step": 15880 }, { "loss_action": 0.034736599773168564, "loss_total": 0.034736599773168564, "step": 15880 }, { "grad_norm": 0.5307050347328186, "learning_rate": 9.679320895120891e-05, "loss": 0.0274, "step": 15890 }, { "loss_action": 0.04432975873351097, "loss_total": 0.04432975873351097, "step": 15890 }, { "grad_norm": 0.46382957696914673, "learning_rate": 9.67873802107557e-05, "loss": 0.0261, "step": 15900 }, { "loss_action": 0.026606915518641472, "loss_total": 0.026606915518641472, "step": 15900 }, { "grad_norm": 0.4575636386871338, "learning_rate": 9.67815463537049e-05, "loss": 0.0251, "step": 15910 }, { "loss_action": 0.03224758803844452, "loss_total": 0.03224758803844452, "step": 15910 }, { "grad_norm": 0.4965561628341675, "learning_rate": 9.677570738069457e-05, "loss": 0.024, "step": 15920 }, { "loss_action": 0.019000288099050522, "loss_total": 0.019000288099050522, "step": 15920 }, { "grad_norm": 0.4366752505302429, "learning_rate": 9.676986329236318e-05, "loss": 0.0244, "step": 15930 }, { "loss_action": 0.02337830327451229, "loss_total": 0.02337830327451229, "step": 15930 }, { "grad_norm": 0.6962738037109375, "learning_rate": 9.676401408934987e-05, "loss": 0.0255, "step": 15940 }, { "loss_action": 0.023224305361509323, "loss_total": 0.023224305361509323, "step": 15940 }, { "grad_norm": 0.43919435143470764, "learning_rate": 9.675815977229428e-05, "loss": 0.0244, "step": 15950 }, { "loss_action": 0.024650296196341515, "loss_total": 0.024650296196341515, "step": 15950 }, { "grad_norm": 0.410463809967041, "learning_rate": 9.675230034183664e-05, "loss": 0.0221, "step": 15960 }, { "loss_action": 0.020836306735873222, "loss_total": 0.020836306735873222, "step": 15960 }, { "grad_norm": 0.39095407724380493, "learning_rate": 9.674643579861773e-05, "loss": 0.021, "step": 15970 }, { "loss_action": 0.02825055830180645, "loss_total": 0.02825055830180645, "step": 15970 }, { "grad_norm": 0.5445573925971985, "learning_rate": 9.674056614327886e-05, "loss": 0.0257, "step": 15980 }, { "loss_action": 0.02480052225291729, "loss_total": 0.02480052225291729, "step": 15980 }, { "grad_norm": 0.4749775826931, "learning_rate": 9.673469137646198e-05, "loss": 0.0242, "step": 15990 }, { "loss_action": 0.02399638667702675, "loss_total": 0.02399638667702675, "step": 15990 }, { "grad_norm": 0.5252386331558228, "learning_rate": 9.67288114988095e-05, "loss": 0.0288, "step": 16000 }, { "loss_action": 0.038116343319416046, "loss_total": 0.038116343319416046, "step": 16000 }, { "grad_norm": 0.4232783615589142, "learning_rate": 9.672292651096447e-05, "loss": 0.029, "step": 16010 }, { "loss_action": 0.03306956961750984, "loss_total": 0.03306956961750984, "step": 16010 }, { "grad_norm": 0.42663976550102234, "learning_rate": 9.671703641357042e-05, "loss": 0.0274, "step": 16020 }, { "loss_action": 0.027337074279785156, "loss_total": 0.027337074279785156, "step": 16020 }, { "grad_norm": 0.4793071448802948, "learning_rate": 9.67111412072715e-05, "loss": 0.0254, "step": 16030 }, { "loss_action": 0.019299594685435295, "loss_total": 0.019299594685435295, "step": 16030 }, { "grad_norm": 0.5235365629196167, "learning_rate": 9.670524089271242e-05, "loss": 0.0274, "step": 16040 }, { "loss_action": 0.021356554701924324, "loss_total": 0.021356554701924324, "step": 16040 }, { "grad_norm": 0.593926191329956, "learning_rate": 9.669933547053842e-05, "loss": 0.0275, "step": 16050 }, { "loss_action": 0.024493591859936714, "loss_total": 0.024493591859936714, "step": 16050 }, { "grad_norm": 0.515630304813385, "learning_rate": 9.669342494139531e-05, "loss": 0.0241, "step": 16060 }, { "loss_action": 0.02761176787316799, "loss_total": 0.02761176787316799, "step": 16060 }, { "grad_norm": 0.3815179765224457, "learning_rate": 9.668750930592943e-05, "loss": 0.0247, "step": 16070 }, { "loss_action": 0.025614453479647636, "loss_total": 0.025614453479647636, "step": 16070 }, { "grad_norm": 0.3459688127040863, "learning_rate": 9.668158856478775e-05, "loss": 0.0215, "step": 16080 }, { "loss_action": 0.022421764209866524, "loss_total": 0.022421764209866524, "step": 16080 }, { "grad_norm": 0.353511244058609, "learning_rate": 9.66756627186177e-05, "loss": 0.0213, "step": 16090 }, { "loss_action": 0.019132114946842194, "loss_total": 0.019132114946842194, "step": 16090 }, { "grad_norm": 0.46680888533592224, "learning_rate": 9.666973176806737e-05, "loss": 0.021, "step": 16100 }, { "loss_action": 0.02739301510155201, "loss_total": 0.02739301510155201, "step": 16100 }, { "grad_norm": 1.032976508140564, "learning_rate": 9.666379571378534e-05, "loss": 0.0266, "step": 16110 }, { "loss_action": 0.02310873195528984, "loss_total": 0.02310873195528984, "step": 16110 }, { "grad_norm": 0.5523651838302612, "learning_rate": 9.665785455642076e-05, "loss": 0.0273, "step": 16120 }, { "loss_action": 0.029667655006051064, "loss_total": 0.029667655006051064, "step": 16120 }, { "grad_norm": 0.4576947093009949, "learning_rate": 9.665190829662337e-05, "loss": 0.0245, "step": 16130 }, { "loss_action": 0.024543719366192818, "loss_total": 0.024543719366192818, "step": 16130 }, { "grad_norm": 0.6317174434661865, "learning_rate": 9.664595693504342e-05, "loss": 0.0249, "step": 16140 }, { "loss_action": 0.027122030034661293, "loss_total": 0.027122030034661293, "step": 16140 }, { "grad_norm": 0.3812780976295471, "learning_rate": 9.664000047233175e-05, "loss": 0.0234, "step": 16150 }, { "loss_action": 0.026806915178894997, "loss_total": 0.026806915178894997, "step": 16150 }, { "grad_norm": 0.4097231924533844, "learning_rate": 9.663403890913976e-05, "loss": 0.0228, "step": 16160 }, { "loss_action": 0.020145539194345474, "loss_total": 0.020145539194345474, "step": 16160 }, { "grad_norm": 0.3513205647468567, "learning_rate": 9.662807224611938e-05, "loss": 0.0208, "step": 16170 }, { "loss_action": 0.024842023849487305, "loss_total": 0.024842023849487305, "step": 16170 }, { "grad_norm": 0.5410149097442627, "learning_rate": 9.662210048392311e-05, "loss": 0.0218, "step": 16180 }, { "loss_action": 0.017499510198831558, "loss_total": 0.017499510198831558, "step": 16180 }, { "grad_norm": 0.43375489115715027, "learning_rate": 9.661612362320405e-05, "loss": 0.0199, "step": 16190 }, { "loss_action": 0.026366012170910835, "loss_total": 0.026366012170910835, "step": 16190 }, { "grad_norm": 0.419181764125824, "learning_rate": 9.661014166461579e-05, "loss": 0.0205, "step": 16200 }, { "loss_action": 0.025310900062322617, "loss_total": 0.025310900062322617, "step": 16200 }, { "grad_norm": 0.4277727007865906, "learning_rate": 9.66041546088125e-05, "loss": 0.0226, "step": 16210 }, { "loss_action": 0.021530894562602043, "loss_total": 0.021530894562602043, "step": 16210 }, { "grad_norm": 0.4563433825969696, "learning_rate": 9.659816245644895e-05, "loss": 0.0204, "step": 16220 }, { "loss_action": 0.022880470380187035, "loss_total": 0.022880470380187035, "step": 16220 }, { "grad_norm": 0.3568563759326935, "learning_rate": 9.65921652081804e-05, "loss": 0.0208, "step": 16230 }, { "loss_action": 0.01803518645465374, "loss_total": 0.01803518645465374, "step": 16230 }, { "grad_norm": 0.5004387497901917, "learning_rate": 9.658616286466271e-05, "loss": 0.0201, "step": 16240 }, { "loss_action": 0.020324893295764923, "loss_total": 0.020324893295764923, "step": 16240 }, { "grad_norm": 0.5354252457618713, "learning_rate": 9.65801554265523e-05, "loss": 0.0209, "step": 16250 }, { "loss_action": 0.01658753864467144, "loss_total": 0.01658753864467144, "step": 16250 }, { "grad_norm": 0.5436987280845642, "learning_rate": 9.657414289450612e-05, "loss": 0.0232, "step": 16260 }, { "loss_action": 0.02135523408651352, "loss_total": 0.02135523408651352, "step": 16260 }, { "grad_norm": 0.3585275411605835, "learning_rate": 9.656812526918171e-05, "loss": 0.0204, "step": 16270 }, { "loss_action": 0.020924469456076622, "loss_total": 0.020924469456076622, "step": 16270 }, { "grad_norm": 0.3961581289768219, "learning_rate": 9.656210255123712e-05, "loss": 0.0223, "step": 16280 }, { "loss_action": 0.021913917735219002, "loss_total": 0.021913917735219002, "step": 16280 }, { "grad_norm": 0.35605937242507935, "learning_rate": 9.6556074741331e-05, "loss": 0.0237, "step": 16290 }, { "loss_action": 0.0236749816685915, "loss_total": 0.0236749816685915, "step": 16290 }, { "grad_norm": 0.4024989604949951, "learning_rate": 9.655004184012256e-05, "loss": 0.0199, "step": 16300 }, { "loss_action": 0.02603473886847496, "loss_total": 0.02603473886847496, "step": 16300 }, { "grad_norm": 0.4133363962173462, "learning_rate": 9.654400384827152e-05, "loss": 0.0208, "step": 16310 }, { "loss_action": 0.016920583322644234, "loss_total": 0.016920583322644234, "step": 16310 }, { "grad_norm": 0.3924855887889862, "learning_rate": 9.653796076643818e-05, "loss": 0.0216, "step": 16320 }, { "loss_action": 0.018321970477700233, "loss_total": 0.018321970477700233, "step": 16320 }, { "grad_norm": 0.4450596570968628, "learning_rate": 9.653191259528344e-05, "loss": 0.0216, "step": 16330 }, { "loss_action": 0.0224379263818264, "loss_total": 0.0224379263818264, "step": 16330 }, { "grad_norm": 0.36152493953704834, "learning_rate": 9.65258593354687e-05, "loss": 0.0214, "step": 16340 }, { "loss_action": 0.019023356959223747, "loss_total": 0.019023356959223747, "step": 16340 }, { "grad_norm": 0.4948427677154541, "learning_rate": 9.651980098765591e-05, "loss": 0.0222, "step": 16350 }, { "loss_action": 0.01860234886407852, "loss_total": 0.01860234886407852, "step": 16350 }, { "grad_norm": 0.3838079571723938, "learning_rate": 9.651373755250765e-05, "loss": 0.0227, "step": 16360 }, { "loss_action": 0.020588040351867676, "loss_total": 0.020588040351867676, "step": 16360 }, { "grad_norm": 0.319437712430954, "learning_rate": 9.650766903068697e-05, "loss": 0.0216, "step": 16370 }, { "loss_action": 0.0206117182970047, "loss_total": 0.0206117182970047, "step": 16370 }, { "grad_norm": 0.4483385384082794, "learning_rate": 9.650159542285753e-05, "loss": 0.0203, "step": 16380 }, { "loss_action": 0.029851160943508148, "loss_total": 0.029851160943508148, "step": 16380 }, { "grad_norm": 0.37987297773361206, "learning_rate": 9.649551672968353e-05, "loss": 0.0214, "step": 16390 }, { "loss_action": 0.019665108993649483, "loss_total": 0.019665108993649483, "step": 16390 }, { "grad_norm": 0.4977622926235199, "learning_rate": 9.648943295182973e-05, "loss": 0.02, "step": 16400 }, { "loss_action": 0.024053893983364105, "loss_total": 0.024053893983364105, "step": 16400 }, { "grad_norm": 0.46796849370002747, "learning_rate": 9.648334408996144e-05, "loss": 0.0226, "step": 16410 }, { "loss_action": 0.017883773893117905, "loss_total": 0.017883773893117905, "step": 16410 }, { "grad_norm": 0.4557194709777832, "learning_rate": 9.647725014474452e-05, "loss": 0.0221, "step": 16420 }, { "loss_action": 0.024084262549877167, "loss_total": 0.024084262549877167, "step": 16420 }, { "grad_norm": 0.43387898802757263, "learning_rate": 9.64711511168454e-05, "loss": 0.0232, "step": 16430 }, { "loss_action": 0.020888280123472214, "loss_total": 0.020888280123472214, "step": 16430 }, { "grad_norm": 0.39284777641296387, "learning_rate": 9.646504700693108e-05, "loss": 0.0198, "step": 16440 }, { "loss_action": 0.015883581712841988, "loss_total": 0.015883581712841988, "step": 16440 }, { "grad_norm": 0.4467127323150635, "learning_rate": 9.645893781566907e-05, "loss": 0.0239, "step": 16450 }, { "loss_action": 0.02204718254506588, "loss_total": 0.02204718254506588, "step": 16450 }, { "grad_norm": 0.3948802351951599, "learning_rate": 9.645282354372744e-05, "loss": 0.0248, "step": 16460 }, { "loss_action": 0.031728778034448624, "loss_total": 0.031728778034448624, "step": 16460 }, { "grad_norm": 0.39605510234832764, "learning_rate": 9.644670419177491e-05, "loss": 0.0235, "step": 16470 }, { "loss_action": 0.024623382836580276, "loss_total": 0.024623382836580276, "step": 16470 }, { "grad_norm": 0.4722018837928772, "learning_rate": 9.644057976048062e-05, "loss": 0.0234, "step": 16480 }, { "loss_action": 0.023181991651654243, "loss_total": 0.023181991651654243, "step": 16480 }, { "grad_norm": 0.3838167190551758, "learning_rate": 9.643445025051435e-05, "loss": 0.0207, "step": 16490 }, { "loss_action": 0.030215701088309288, "loss_total": 0.030215701088309288, "step": 16490 }, { "grad_norm": 0.37154221534729004, "learning_rate": 9.642831566254641e-05, "loss": 0.0222, "step": 16500 }, { "loss_action": 0.01936645805835724, "loss_total": 0.01936645805835724, "step": 16500 }, { "grad_norm": 0.3729762136936188, "learning_rate": 9.642217599724769e-05, "loss": 0.0217, "step": 16510 }, { "loss_action": 0.019745301455259323, "loss_total": 0.019745301455259323, "step": 16510 }, { "grad_norm": 0.43881458044052124, "learning_rate": 9.64160312552896e-05, "loss": 0.0215, "step": 16520 }, { "loss_action": 0.026253845542669296, "loss_total": 0.026253845542669296, "step": 16520 }, { "grad_norm": 0.44869130849838257, "learning_rate": 9.64098814373441e-05, "loss": 0.0215, "step": 16530 }, { "loss_action": 0.018362052738666534, "loss_total": 0.018362052738666534, "step": 16530 }, { "grad_norm": 0.43366318941116333, "learning_rate": 9.640372654408374e-05, "loss": 0.0202, "step": 16540 }, { "loss_action": 0.018351299688220024, "loss_total": 0.018351299688220024, "step": 16540 }, { "grad_norm": 0.36694997549057007, "learning_rate": 9.639756657618162e-05, "loss": 0.0208, "step": 16550 }, { "loss_action": 0.016279326751828194, "loss_total": 0.016279326751828194, "step": 16550 }, { "grad_norm": 0.43290260434150696, "learning_rate": 9.639140153431138e-05, "loss": 0.0184, "step": 16560 }, { "loss_action": 0.021468641236424446, "loss_total": 0.021468641236424446, "step": 16560 }, { "grad_norm": 0.4294406771659851, "learning_rate": 9.638523141914721e-05, "loss": 0.0209, "step": 16570 }, { "loss_action": 0.01733512431383133, "loss_total": 0.01733512431383133, "step": 16570 }, { "grad_norm": 0.43004077672958374, "learning_rate": 9.637905623136388e-05, "loss": 0.0244, "step": 16580 }, { "loss_action": 0.018848072737455368, "loss_total": 0.018848072737455368, "step": 16580 }, { "grad_norm": 0.5068214535713196, "learning_rate": 9.637287597163669e-05, "loss": 0.0231, "step": 16590 }, { "loss_action": 0.02406497299671173, "loss_total": 0.02406497299671173, "step": 16590 }, { "grad_norm": 0.49924468994140625, "learning_rate": 9.63666906406415e-05, "loss": 0.0243, "step": 16600 }, { "loss_action": 0.038231875747442245, "loss_total": 0.038231875747442245, "step": 16600 }, { "grad_norm": 0.48213455080986023, "learning_rate": 9.636050023905473e-05, "loss": 0.0262, "step": 16610 }, { "loss_action": 0.025151344016194344, "loss_total": 0.025151344016194344, "step": 16610 }, { "grad_norm": 0.4039996266365051, "learning_rate": 9.635430476755336e-05, "loss": 0.022, "step": 16620 }, { "loss_action": 0.02629038505256176, "loss_total": 0.02629038505256176, "step": 16620 }, { "grad_norm": 0.4857546091079712, "learning_rate": 9.63481042268149e-05, "loss": 0.0219, "step": 16630 }, { "loss_action": 0.0227771308273077, "loss_total": 0.0227771308273077, "step": 16630 }, { "grad_norm": 0.3930032551288605, "learning_rate": 9.634189861751745e-05, "loss": 0.0212, "step": 16640 }, { "loss_action": 0.02286633290350437, "loss_total": 0.02286633290350437, "step": 16640 }, { "grad_norm": 0.48984211683273315, "learning_rate": 9.633568794033967e-05, "loss": 0.0227, "step": 16650 }, { "loss_action": 0.02122134156525135, "loss_total": 0.02122134156525135, "step": 16650 }, { "grad_norm": 0.29261043667793274, "learning_rate": 9.63294721959607e-05, "loss": 0.0227, "step": 16660 }, { "loss_action": 0.028851743787527084, "loss_total": 0.028851743787527084, "step": 16660 }, { "grad_norm": 0.5716524124145508, "learning_rate": 9.63232513850603e-05, "loss": 0.0226, "step": 16670 }, { "loss_action": 0.022812020033597946, "loss_total": 0.022812020033597946, "step": 16670 }, { "grad_norm": 0.4576886296272278, "learning_rate": 9.631702550831878e-05, "loss": 0.024, "step": 16680 }, { "loss_action": 0.03153868019580841, "loss_total": 0.03153868019580841, "step": 16680 }, { "grad_norm": 0.39313849806785583, "learning_rate": 9.631079456641698e-05, "loss": 0.0234, "step": 16690 }, { "loss_action": 0.021644186228513718, "loss_total": 0.021644186228513718, "step": 16690 }, { "grad_norm": 0.3637879192829132, "learning_rate": 9.630455856003632e-05, "loss": 0.0203, "step": 16700 }, { "loss_action": 0.024614183232188225, "loss_total": 0.024614183232188225, "step": 16700 }, { "grad_norm": 0.46098172664642334, "learning_rate": 9.629831748985876e-05, "loss": 0.0218, "step": 16710 }, { "loss_action": 0.02043011039495468, "loss_total": 0.02043011039495468, "step": 16710 }, { "grad_norm": 0.43472820520401, "learning_rate": 9.629207135656679e-05, "loss": 0.0232, "step": 16720 }, { "loss_action": 0.024766799062490463, "loss_total": 0.024766799062490463, "step": 16720 }, { "grad_norm": 0.39831578731536865, "learning_rate": 9.628582016084353e-05, "loss": 0.0223, "step": 16730 }, { "loss_action": 0.02440556325018406, "loss_total": 0.02440556325018406, "step": 16730 }, { "grad_norm": 0.37406429648399353, "learning_rate": 9.627956390337254e-05, "loss": 0.0223, "step": 16740 }, { "loss_action": 0.0249167513102293, "loss_total": 0.0249167513102293, "step": 16740 }, { "grad_norm": 0.4610691964626312, "learning_rate": 9.627330258483802e-05, "loss": 0.0219, "step": 16750 }, { "loss_action": 0.021266432479023933, "loss_total": 0.021266432479023933, "step": 16750 }, { "grad_norm": 0.46878546476364136, "learning_rate": 9.62670362059247e-05, "loss": 0.0216, "step": 16760 }, { "loss_action": 0.02142898179590702, "loss_total": 0.02142898179590702, "step": 16760 }, { "grad_norm": 0.36509189009666443, "learning_rate": 9.626076476731786e-05, "loss": 0.0197, "step": 16770 }, { "loss_action": 0.0166870579123497, "loss_total": 0.0166870579123497, "step": 16770 }, { "grad_norm": 0.34425920248031616, "learning_rate": 9.625448826970336e-05, "loss": 0.0204, "step": 16780 }, { "loss_action": 0.019846752285957336, "loss_total": 0.019846752285957336, "step": 16780 }, { "grad_norm": 0.4027855396270752, "learning_rate": 9.624820671376755e-05, "loss": 0.0203, "step": 16790 }, { "loss_action": 0.017582807689905167, "loss_total": 0.017582807689905167, "step": 16790 }, { "grad_norm": 0.4517572224140167, "learning_rate": 9.62419201001974e-05, "loss": 0.0191, "step": 16800 }, { "loss_action": 0.01907213032245636, "loss_total": 0.01907213032245636, "step": 16800 }, { "grad_norm": 0.3947001099586487, "learning_rate": 9.623562842968037e-05, "loss": 0.0192, "step": 16810 }, { "loss_action": 0.021501194685697556, "loss_total": 0.021501194685697556, "step": 16810 }, { "grad_norm": 0.46075138449668884, "learning_rate": 9.622933170290454e-05, "loss": 0.0209, "step": 16820 }, { "loss_action": 0.018497096374630928, "loss_total": 0.018497096374630928, "step": 16820 }, { "grad_norm": 0.3386080265045166, "learning_rate": 9.622302992055849e-05, "loss": 0.0205, "step": 16830 }, { "loss_action": 0.020180396735668182, "loss_total": 0.020180396735668182, "step": 16830 }, { "grad_norm": 0.2791122794151306, "learning_rate": 9.62167230833314e-05, "loss": 0.0187, "step": 16840 }, { "loss_action": 0.01701819710433483, "loss_total": 0.01701819710433483, "step": 16840 }, { "grad_norm": 0.3866255581378937, "learning_rate": 9.621041119191295e-05, "loss": 0.0208, "step": 16850 }, { "loss_action": 0.020857198163866997, "loss_total": 0.020857198163866997, "step": 16850 }, { "grad_norm": 0.3154882490634918, "learning_rate": 9.620409424699342e-05, "loss": 0.018, "step": 16860 }, { "loss_action": 0.016210094094276428, "loss_total": 0.016210094094276428, "step": 16860 }, { "grad_norm": 0.39699697494506836, "learning_rate": 9.619777224926359e-05, "loss": 0.0196, "step": 16870 }, { "loss_action": 0.02484428882598877, "loss_total": 0.02484428882598877, "step": 16870 }, { "grad_norm": 0.37100422382354736, "learning_rate": 9.619144519941485e-05, "loss": 0.0189, "step": 16880 }, { "loss_action": 0.022130941972136497, "loss_total": 0.022130941972136497, "step": 16880 }, { "grad_norm": 0.3257017433643341, "learning_rate": 9.618511309813912e-05, "loss": 0.0198, "step": 16890 }, { "loss_action": 0.02081923559308052, "loss_total": 0.02081923559308052, "step": 16890 }, { "grad_norm": 0.35806789994239807, "learning_rate": 9.617877594612886e-05, "loss": 0.0199, "step": 16900 }, { "loss_action": 0.024413108825683594, "loss_total": 0.024413108825683594, "step": 16900 }, { "grad_norm": 0.33185267448425293, "learning_rate": 9.617243374407707e-05, "loss": 0.0187, "step": 16910 }, { "loss_action": 0.021350979804992676, "loss_total": 0.021350979804992676, "step": 16910 }, { "grad_norm": 0.4379758834838867, "learning_rate": 9.616608649267736e-05, "loss": 0.0175, "step": 16920 }, { "loss_action": 0.02144082821905613, "loss_total": 0.02144082821905613, "step": 16920 }, { "grad_norm": 0.4627295732498169, "learning_rate": 9.615973419262385e-05, "loss": 0.0198, "step": 16930 }, { "loss_action": 0.022762687876820564, "loss_total": 0.022762687876820564, "step": 16930 }, { "grad_norm": 0.34381726384162903, "learning_rate": 9.615337684461119e-05, "loss": 0.0202, "step": 16940 }, { "loss_action": 0.02497834898531437, "loss_total": 0.02497834898531437, "step": 16940 }, { "grad_norm": 0.4150736629962921, "learning_rate": 9.614701444933465e-05, "loss": 0.0197, "step": 16950 }, { "loss_action": 0.027381490916013718, "loss_total": 0.027381490916013718, "step": 16950 }, { "grad_norm": 0.3819023668766022, "learning_rate": 9.614064700748997e-05, "loss": 0.0191, "step": 16960 }, { "loss_action": 0.021003732457756996, "loss_total": 0.021003732457756996, "step": 16960 }, { "grad_norm": 0.45155125856399536, "learning_rate": 9.613427451977352e-05, "loss": 0.0205, "step": 16970 }, { "loss_action": 0.02103206142783165, "loss_total": 0.02103206142783165, "step": 16970 }, { "grad_norm": 0.403709352016449, "learning_rate": 9.612789698688216e-05, "loss": 0.0199, "step": 16980 }, { "loss_action": 0.017754221335053444, "loss_total": 0.017754221335053444, "step": 16980 }, { "grad_norm": 0.48048967123031616, "learning_rate": 9.612151440951334e-05, "loss": 0.0204, "step": 16990 }, { "loss_action": 0.020022008568048477, "loss_total": 0.020022008568048477, "step": 16990 }, { "grad_norm": 0.4122697114944458, "learning_rate": 9.611512678836506e-05, "loss": 0.0183, "step": 17000 }, { "loss_action": 0.020827170461416245, "loss_total": 0.020827170461416245, "step": 17000 }, { "grad_norm": 0.4311755299568176, "learning_rate": 9.610873412413584e-05, "loss": 0.0204, "step": 17010 }, { "loss_action": 0.021039318293333054, "loss_total": 0.021039318293333054, "step": 17010 }, { "grad_norm": 0.4347343444824219, "learning_rate": 9.610233641752476e-05, "loss": 0.0218, "step": 17020 }, { "loss_action": 0.021388612687587738, "loss_total": 0.021388612687587738, "step": 17020 }, { "grad_norm": 0.46935179829597473, "learning_rate": 9.609593366923151e-05, "loss": 0.024, "step": 17030 }, { "loss_action": 0.020962700247764587, "loss_total": 0.020962700247764587, "step": 17030 }, { "grad_norm": 0.3266327977180481, "learning_rate": 9.608952587995625e-05, "loss": 0.0214, "step": 17040 }, { "loss_action": 0.02400670386850834, "loss_total": 0.02400670386850834, "step": 17040 }, { "grad_norm": 0.5574402809143066, "learning_rate": 9.608311305039972e-05, "loss": 0.0256, "step": 17050 }, { "loss_action": 0.029131026938557625, "loss_total": 0.029131026938557625, "step": 17050 }, { "grad_norm": 0.3703630268573761, "learning_rate": 9.607669518126326e-05, "loss": 0.0243, "step": 17060 }, { "loss_action": 0.018913937732577324, "loss_total": 0.018913937732577324, "step": 17060 }, { "grad_norm": 0.4900130033493042, "learning_rate": 9.607027227324866e-05, "loss": 0.0208, "step": 17070 }, { "loss_action": 0.021553803235292435, "loss_total": 0.021553803235292435, "step": 17070 }, { "grad_norm": 0.4364631175994873, "learning_rate": 9.606384432705837e-05, "loss": 0.0221, "step": 17080 }, { "loss_action": 0.020705683156847954, "loss_total": 0.020705683156847954, "step": 17080 }, { "grad_norm": 0.35487285256385803, "learning_rate": 9.60574113433953e-05, "loss": 0.0209, "step": 17090 }, { "loss_action": 0.022265395149588585, "loss_total": 0.022265395149588585, "step": 17090 }, { "grad_norm": 0.38373926281929016, "learning_rate": 9.6050973322963e-05, "loss": 0.0228, "step": 17100 }, { "loss_action": 0.023843690752983093, "loss_total": 0.023843690752983093, "step": 17100 }, { "grad_norm": 0.4968153238296509, "learning_rate": 9.604453026646547e-05, "loss": 0.0201, "step": 17110 }, { "loss_action": 0.017445476725697517, "loss_total": 0.017445476725697517, "step": 17110 }, { "grad_norm": 0.42714154720306396, "learning_rate": 9.603808217460735e-05, "loss": 0.0201, "step": 17120 }, { "loss_action": 0.02081773430109024, "loss_total": 0.02081773430109024, "step": 17120 }, { "grad_norm": 0.48088791966438293, "learning_rate": 9.603162904809377e-05, "loss": 0.0241, "step": 17130 }, { "loss_action": 0.020500583574175835, "loss_total": 0.020500583574175835, "step": 17130 }, { "grad_norm": 0.40041279792785645, "learning_rate": 9.602517088763045e-05, "loss": 0.0235, "step": 17140 }, { "loss_action": 0.016522452235221863, "loss_total": 0.016522452235221863, "step": 17140 }, { "grad_norm": 0.30622947216033936, "learning_rate": 9.601870769392365e-05, "loss": 0.0199, "step": 17150 }, { "loss_action": 0.025664255023002625, "loss_total": 0.025664255023002625, "step": 17150 }, { "grad_norm": 0.29381200671195984, "learning_rate": 9.601223946768017e-05, "loss": 0.0231, "step": 17160 }, { "loss_action": 0.021736714988946915, "loss_total": 0.021736714988946915, "step": 17160 }, { "grad_norm": 0.6336966753005981, "learning_rate": 9.600576620960734e-05, "loss": 0.0245, "step": 17170 }, { "loss_action": 0.02053297869861126, "loss_total": 0.02053297869861126, "step": 17170 }, { "grad_norm": 0.45860397815704346, "learning_rate": 9.599928792041308e-05, "loss": 0.0203, "step": 17180 }, { "loss_action": 0.019634652882814407, "loss_total": 0.019634652882814407, "step": 17180 }, { "grad_norm": 0.6595089435577393, "learning_rate": 9.599280460080587e-05, "loss": 0.0213, "step": 17190 }, { "loss_action": 0.022367732599377632, "loss_total": 0.022367732599377632, "step": 17190 }, { "grad_norm": 0.3925665616989136, "learning_rate": 9.59863162514947e-05, "loss": 0.022, "step": 17200 }, { "loss_action": 0.029926754534244537, "loss_total": 0.029926754534244537, "step": 17200 }, { "grad_norm": 0.3749101459980011, "learning_rate": 9.597982287318911e-05, "loss": 0.0216, "step": 17210 }, { "loss_action": 0.019895799458026886, "loss_total": 0.019895799458026886, "step": 17210 }, { "grad_norm": 0.5263941884040833, "learning_rate": 9.597332446659923e-05, "loss": 0.0221, "step": 17220 }, { "loss_action": 0.020299891009926796, "loss_total": 0.020299891009926796, "step": 17220 }, { "grad_norm": 0.42845532298088074, "learning_rate": 9.59668210324357e-05, "loss": 0.0204, "step": 17230 }, { "loss_action": 0.024238647893071175, "loss_total": 0.024238647893071175, "step": 17230 }, { "grad_norm": 0.4259422719478607, "learning_rate": 9.596031257140974e-05, "loss": 0.0221, "step": 17240 }, { "loss_action": 0.02252982370555401, "loss_total": 0.02252982370555401, "step": 17240 }, { "grad_norm": 0.36129289865493774, "learning_rate": 9.59537990842331e-05, "loss": 0.0205, "step": 17250 }, { "loss_action": 0.01924060471355915, "loss_total": 0.01924060471355915, "step": 17250 }, { "grad_norm": 0.3526536226272583, "learning_rate": 9.594728057161806e-05, "loss": 0.0189, "step": 17260 }, { "loss_action": 0.017293797805905342, "loss_total": 0.017293797805905342, "step": 17260 }, { "grad_norm": 0.39151570200920105, "learning_rate": 9.594075703427752e-05, "loss": 0.0202, "step": 17270 }, { "loss_action": 0.025664202868938446, "loss_total": 0.025664202868938446, "step": 17270 }, { "grad_norm": 0.35576513409614563, "learning_rate": 9.593422847292486e-05, "loss": 0.0206, "step": 17280 }, { "loss_action": 0.0182513277977705, "loss_total": 0.0182513277977705, "step": 17280 }, { "grad_norm": 0.3759811520576477, "learning_rate": 9.592769488827402e-05, "loss": 0.0184, "step": 17290 }, { "loss_action": 0.02559138648211956, "loss_total": 0.02559138648211956, "step": 17290 }, { "grad_norm": 0.3818780183792114, "learning_rate": 9.592115628103952e-05, "loss": 0.0216, "step": 17300 }, { "loss_action": 0.019388698041439056, "loss_total": 0.019388698041439056, "step": 17300 }, { "grad_norm": 0.4043816924095154, "learning_rate": 9.591461265193643e-05, "loss": 0.018, "step": 17310 }, { "loss_action": 0.013816773891448975, "loss_total": 0.013816773891448975, "step": 17310 }, { "grad_norm": 0.4030532240867615, "learning_rate": 9.590806400168032e-05, "loss": 0.0182, "step": 17320 }, { "loss_action": 0.016882045194506645, "loss_total": 0.016882045194506645, "step": 17320 }, { "grad_norm": 0.410252183675766, "learning_rate": 9.590151033098735e-05, "loss": 0.0185, "step": 17330 }, { "loss_action": 0.017713312059640884, "loss_total": 0.017713312059640884, "step": 17330 }, { "grad_norm": 0.35378479957580566, "learning_rate": 9.589495164057423e-05, "loss": 0.0195, "step": 17340 }, { "loss_action": 0.017719240859150887, "loss_total": 0.017719240859150887, "step": 17340 }, { "grad_norm": 0.45689696073532104, "learning_rate": 9.58883879311582e-05, "loss": 0.0175, "step": 17350 }, { "loss_action": 0.011808718554675579, "loss_total": 0.011808718554675579, "step": 17350 }, { "grad_norm": 0.38855651021003723, "learning_rate": 9.588181920345705e-05, "loss": 0.0184, "step": 17360 }, { "loss_action": 0.01836482249200344, "loss_total": 0.01836482249200344, "step": 17360 }, { "grad_norm": 0.408523291349411, "learning_rate": 9.587524545818913e-05, "loss": 0.0201, "step": 17370 }, { "loss_action": 0.02102038636803627, "loss_total": 0.02102038636803627, "step": 17370 }, { "grad_norm": 0.5723813772201538, "learning_rate": 9.586866669607335e-05, "loss": 0.0242, "step": 17380 }, { "loss_action": 0.018848339095711708, "loss_total": 0.018848339095711708, "step": 17380 }, { "grad_norm": 0.3814631700515747, "learning_rate": 9.586208291782915e-05, "loss": 0.022, "step": 17390 }, { "loss_action": 0.019997118040919304, "loss_total": 0.019997118040919304, "step": 17390 }, { "grad_norm": 0.40147244930267334, "learning_rate": 9.58554941241765e-05, "loss": 0.0213, "step": 17400 }, { "loss_action": 0.022241197526454926, "loss_total": 0.022241197526454926, "step": 17400 }, { "grad_norm": 0.3594387173652649, "learning_rate": 9.584890031583596e-05, "loss": 0.0209, "step": 17410 }, { "loss_action": 0.019899392500519753, "loss_total": 0.019899392500519753, "step": 17410 }, { "grad_norm": 0.3755505681037903, "learning_rate": 9.584230149352861e-05, "loss": 0.0193, "step": 17420 }, { "loss_action": 0.017834510654211044, "loss_total": 0.017834510654211044, "step": 17420 }, { "grad_norm": 0.28100621700286865, "learning_rate": 9.58356976579761e-05, "loss": 0.0195, "step": 17430 }, { "loss_action": 0.014514529146254063, "loss_total": 0.014514529146254063, "step": 17430 }, { "grad_norm": 0.44343259930610657, "learning_rate": 9.58290888099006e-05, "loss": 0.019, "step": 17440 }, { "loss_action": 0.018679218366742134, "loss_total": 0.018679218366742134, "step": 17440 }, { "grad_norm": 0.36619263887405396, "learning_rate": 9.582247495002486e-05, "loss": 0.0169, "step": 17450 }, { "loss_action": 0.018509836867451668, "loss_total": 0.018509836867451668, "step": 17450 }, { "grad_norm": 0.3702712655067444, "learning_rate": 9.581585607907214e-05, "loss": 0.0194, "step": 17460 }, { "loss_action": 0.022664083167910576, "loss_total": 0.022664083167910576, "step": 17460 }, { "grad_norm": 0.4313226044178009, "learning_rate": 9.580923219776628e-05, "loss": 0.0236, "step": 17470 }, { "loss_action": 0.020193541422486305, "loss_total": 0.020193541422486305, "step": 17470 }, { "grad_norm": 0.448528528213501, "learning_rate": 9.580260330683167e-05, "loss": 0.0211, "step": 17480 }, { "loss_action": 0.021623646840453148, "loss_total": 0.021623646840453148, "step": 17480 }, { "grad_norm": 0.4151114821434021, "learning_rate": 9.579596940699322e-05, "loss": 0.0209, "step": 17490 }, { "loss_action": 0.023467497900128365, "loss_total": 0.023467497900128365, "step": 17490 }, { "grad_norm": 0.2943626940250397, "learning_rate": 9.578933049897643e-05, "loss": 0.0203, "step": 17500 }, { "loss_action": 0.01653452031314373, "loss_total": 0.01653452031314373, "step": 17500 }, { "grad_norm": 0.3351759910583496, "learning_rate": 9.578268658350728e-05, "loss": 0.0201, "step": 17510 }, { "loss_action": 0.031092211604118347, "loss_total": 0.031092211604118347, "step": 17510 }, { "grad_norm": 0.37920838594436646, "learning_rate": 9.577603766131235e-05, "loss": 0.0204, "step": 17520 }, { "loss_action": 0.02802075631916523, "loss_total": 0.02802075631916523, "step": 17520 }, { "grad_norm": 0.5026921629905701, "learning_rate": 9.576938373311878e-05, "loss": 0.0221, "step": 17530 }, { "loss_action": 0.022245587781071663, "loss_total": 0.022245587781071663, "step": 17530 }, { "grad_norm": 0.3871678411960602, "learning_rate": 9.576272479965421e-05, "loss": 0.0185, "step": 17540 }, { "loss_action": 0.013705821707844734, "loss_total": 0.013705821707844734, "step": 17540 }, { "grad_norm": 0.46457600593566895, "learning_rate": 9.575606086164687e-05, "loss": 0.0209, "step": 17550 }, { "loss_action": 0.019154731184244156, "loss_total": 0.019154731184244156, "step": 17550 }, { "grad_norm": 0.3514218032360077, "learning_rate": 9.57493919198255e-05, "loss": 0.0202, "step": 17560 }, { "loss_action": 0.02052829973399639, "loss_total": 0.02052829973399639, "step": 17560 }, { "grad_norm": 0.6351121068000793, "learning_rate": 9.57427179749194e-05, "loss": 0.0196, "step": 17570 }, { "loss_action": 0.019612034782767296, "loss_total": 0.019612034782767296, "step": 17570 }, { "grad_norm": 0.3508150279521942, "learning_rate": 9.573603902765846e-05, "loss": 0.0193, "step": 17580 }, { "loss_action": 0.02101631462574005, "loss_total": 0.02101631462574005, "step": 17580 }, { "grad_norm": 0.4195057153701782, "learning_rate": 9.572935507877304e-05, "loss": 0.019, "step": 17590 }, { "loss_action": 0.016514752060174942, "loss_total": 0.016514752060174942, "step": 17590 }, { "grad_norm": 0.3931092321872711, "learning_rate": 9.57226661289941e-05, "loss": 0.0205, "step": 17600 }, { "loss_action": 0.0272347591817379, "loss_total": 0.0272347591817379, "step": 17600 }, { "grad_norm": 0.3575567305088043, "learning_rate": 9.571597217905315e-05, "loss": 0.0221, "step": 17610 }, { "loss_action": 0.020900193601846695, "loss_total": 0.020900193601846695, "step": 17610 }, { "grad_norm": 0.34234142303466797, "learning_rate": 9.57092732296822e-05, "loss": 0.0208, "step": 17620 }, { "loss_action": 0.015469128265976906, "loss_total": 0.015469128265976906, "step": 17620 }, { "grad_norm": 0.40860551595687866, "learning_rate": 9.570256928161385e-05, "loss": 0.0172, "step": 17630 }, { "loss_action": 0.02308960258960724, "loss_total": 0.02308960258960724, "step": 17630 }, { "grad_norm": 0.372704416513443, "learning_rate": 9.569586033558126e-05, "loss": 0.0196, "step": 17640 }, { "loss_action": 0.015256660059094429, "loss_total": 0.015256660059094429, "step": 17640 }, { "grad_norm": 0.600955069065094, "learning_rate": 9.568914639231807e-05, "loss": 0.0188, "step": 17650 }, { "loss_action": 0.014430408366024494, "loss_total": 0.014430408366024494, "step": 17650 }, { "grad_norm": 0.3895106017589569, "learning_rate": 9.568242745255852e-05, "loss": 0.0199, "step": 17660 }, { "loss_action": 0.027925046160817146, "loss_total": 0.027925046160817146, "step": 17660 }, { "grad_norm": 0.4378920793533325, "learning_rate": 9.567570351703739e-05, "loss": 0.0221, "step": 17670 }, { "loss_action": 0.02269820310175419, "loss_total": 0.02269820310175419, "step": 17670 }, { "grad_norm": 0.31493526697158813, "learning_rate": 9.566897458649001e-05, "loss": 0.0207, "step": 17680 }, { "loss_action": 0.02272946760058403, "loss_total": 0.02272946760058403, "step": 17680 }, { "grad_norm": 0.44497936964035034, "learning_rate": 9.566224066165221e-05, "loss": 0.0194, "step": 17690 }, { "loss_action": 0.012983624823391438, "loss_total": 0.012983624823391438, "step": 17690 }, { "grad_norm": 0.33907437324523926, "learning_rate": 9.565550174326043e-05, "loss": 0.0181, "step": 17700 }, { "loss_action": 0.03160861134529114, "loss_total": 0.03160861134529114, "step": 17700 }, { "grad_norm": 0.4296012222766876, "learning_rate": 9.564875783205162e-05, "loss": 0.0222, "step": 17710 }, { "loss_action": 0.022097313776612282, "loss_total": 0.022097313776612282, "step": 17710 }, { "grad_norm": 0.43560153245925903, "learning_rate": 9.564200892876328e-05, "loss": 0.021, "step": 17720 }, { "loss_action": 0.01684563048183918, "loss_total": 0.01684563048183918, "step": 17720 }, { "grad_norm": 0.36878085136413574, "learning_rate": 9.563525503413348e-05, "loss": 0.0175, "step": 17730 }, { "loss_action": 0.015637807548046112, "loss_total": 0.015637807548046112, "step": 17730 }, { "grad_norm": 0.44090884923934937, "learning_rate": 9.562849614890079e-05, "loss": 0.0178, "step": 17740 }, { "loss_action": 0.022291960194706917, "loss_total": 0.022291960194706917, "step": 17740 }, { "grad_norm": 0.3274255394935608, "learning_rate": 9.562173227380436e-05, "loss": 0.0203, "step": 17750 }, { "loss_action": 0.019221000373363495, "loss_total": 0.019221000373363495, "step": 17750 }, { "grad_norm": 0.485150009393692, "learning_rate": 9.561496340958389e-05, "loss": 0.0209, "step": 17760 }, { "loss_action": 0.018237922340631485, "loss_total": 0.018237922340631485, "step": 17760 }, { "grad_norm": 0.4543094038963318, "learning_rate": 9.560818955697959e-05, "loss": 0.0191, "step": 17770 }, { "loss_action": 0.022139716893434525, "loss_total": 0.022139716893434525, "step": 17770 }, { "grad_norm": 0.44135263562202454, "learning_rate": 9.560141071673228e-05, "loss": 0.0194, "step": 17780 }, { "loss_action": 0.01728142239153385, "loss_total": 0.01728142239153385, "step": 17780 }, { "grad_norm": 0.3483985960483551, "learning_rate": 9.559462688958323e-05, "loss": 0.0182, "step": 17790 }, { "loss_action": 0.01981414295732975, "loss_total": 0.01981414295732975, "step": 17790 }, { "grad_norm": 0.5031217336654663, "learning_rate": 9.558783807627434e-05, "loss": 0.0188, "step": 17800 }, { "loss_action": 0.022841954603791237, "loss_total": 0.022841954603791237, "step": 17800 }, { "grad_norm": 0.5874212980270386, "learning_rate": 9.558104427754801e-05, "loss": 0.0236, "step": 17810 }, { "loss_action": 0.017706744372844696, "loss_total": 0.017706744372844696, "step": 17810 }, { "grad_norm": 0.3886801302433014, "learning_rate": 9.557424549414722e-05, "loss": 0.0206, "step": 17820 }, { "loss_action": 0.02063145488500595, "loss_total": 0.02063145488500595, "step": 17820 }, { "grad_norm": 0.4448956251144409, "learning_rate": 9.556744172681546e-05, "loss": 0.0218, "step": 17830 }, { "loss_action": 0.021729208528995514, "loss_total": 0.021729208528995514, "step": 17830 }, { "grad_norm": 0.3809884190559387, "learning_rate": 9.556063297629677e-05, "loss": 0.02, "step": 17840 }, { "loss_action": 0.021337570622563362, "loss_total": 0.021337570622563362, "step": 17840 }, { "grad_norm": 0.3546198010444641, "learning_rate": 9.555381924333578e-05, "loss": 0.0185, "step": 17850 }, { "loss_action": 0.02041231468319893, "loss_total": 0.02041231468319893, "step": 17850 }, { "grad_norm": 0.4115365445613861, "learning_rate": 9.554700052867758e-05, "loss": 0.0215, "step": 17860 }, { "loss_action": 0.019987106323242188, "loss_total": 0.019987106323242188, "step": 17860 }, { "grad_norm": 0.4495297372341156, "learning_rate": 9.554017683306789e-05, "loss": 0.0192, "step": 17870 }, { "loss_action": 0.01700601913034916, "loss_total": 0.01700601913034916, "step": 17870 }, { "grad_norm": 0.3230677545070648, "learning_rate": 9.553334815725294e-05, "loss": 0.0189, "step": 17880 }, { "loss_action": 0.016863230615854263, "loss_total": 0.016863230615854263, "step": 17880 }, { "grad_norm": 0.3737710118293762, "learning_rate": 9.552651450197949e-05, "loss": 0.0188, "step": 17890 }, { "loss_action": 0.019682470709085464, "loss_total": 0.019682470709085464, "step": 17890 }, { "grad_norm": 0.4278692901134491, "learning_rate": 9.551967586799486e-05, "loss": 0.0191, "step": 17900 }, { "loss_action": 0.015725621953606606, "loss_total": 0.015725621953606606, "step": 17900 }, { "grad_norm": 0.4154641628265381, "learning_rate": 9.551283225604692e-05, "loss": 0.0208, "step": 17910 }, { "loss_action": 0.017194893211126328, "loss_total": 0.017194893211126328, "step": 17910 }, { "grad_norm": 0.4002613127231598, "learning_rate": 9.550598366688406e-05, "loss": 0.0191, "step": 17920 }, { "loss_action": 0.022161757573485374, "loss_total": 0.022161757573485374, "step": 17920 }, { "grad_norm": 0.4114663600921631, "learning_rate": 9.549913010125526e-05, "loss": 0.0194, "step": 17930 }, { "loss_action": 0.020825481042265892, "loss_total": 0.020825481042265892, "step": 17930 }, { "grad_norm": 0.40491801500320435, "learning_rate": 9.549227155990999e-05, "loss": 0.0199, "step": 17940 }, { "loss_action": 0.017699263989925385, "loss_total": 0.017699263989925385, "step": 17940 }, { "grad_norm": 0.3612508773803711, "learning_rate": 9.548540804359828e-05, "loss": 0.0193, "step": 17950 }, { "loss_action": 0.01801980845630169, "loss_total": 0.01801980845630169, "step": 17950 }, { "grad_norm": 0.41379666328430176, "learning_rate": 9.547853955307077e-05, "loss": 0.0224, "step": 17960 }, { "loss_action": 0.02652895078063011, "loss_total": 0.02652895078063011, "step": 17960 }, { "grad_norm": 0.3580079674720764, "learning_rate": 9.547166608907853e-05, "loss": 0.0199, "step": 17970 }, { "loss_action": 0.02163599245250225, "loss_total": 0.02163599245250225, "step": 17970 }, { "grad_norm": 0.33331766724586487, "learning_rate": 9.546478765237326e-05, "loss": 0.0213, "step": 17980 }, { "loss_action": 0.019268786534667015, "loss_total": 0.019268786534667015, "step": 17980 }, { "grad_norm": 0.48734110593795776, "learning_rate": 9.545790424370715e-05, "loss": 0.0214, "step": 17990 }, { "loss_action": 0.015318907797336578, "loss_total": 0.015318907797336578, "step": 17990 }, { "grad_norm": 0.4122755527496338, "learning_rate": 9.5451015863833e-05, "loss": 0.0196, "step": 18000 }, { "loss_action": 0.016221513971686363, "loss_total": 0.016221513971686363, "step": 18000 }, { "grad_norm": 0.5718512535095215, "learning_rate": 9.544412251350408e-05, "loss": 0.0179, "step": 18010 }, { "loss_action": 0.02346603013575077, "loss_total": 0.02346603013575077, "step": 18010 }, { "grad_norm": 0.29115843772888184, "learning_rate": 9.543722419347422e-05, "loss": 0.0187, "step": 18020 }, { "loss_action": 0.019323067739605904, "loss_total": 0.019323067739605904, "step": 18020 }, { "grad_norm": 0.2890162169933319, "learning_rate": 9.543032090449788e-05, "loss": 0.0195, "step": 18030 }, { "loss_action": 0.020662546157836914, "loss_total": 0.020662546157836914, "step": 18030 }, { "grad_norm": 0.4360666871070862, "learning_rate": 9.542341264732992e-05, "loss": 0.0202, "step": 18040 }, { "loss_action": 0.02246687561273575, "loss_total": 0.02246687561273575, "step": 18040 }, { "grad_norm": 0.3733310401439667, "learning_rate": 9.541649942272585e-05, "loss": 0.0202, "step": 18050 }, { "loss_action": 0.019983883947134018, "loss_total": 0.019983883947134018, "step": 18050 }, { "grad_norm": 0.5574062466621399, "learning_rate": 9.54095812314417e-05, "loss": 0.0194, "step": 18060 }, { "loss_action": 0.02115975320339203, "loss_total": 0.02115975320339203, "step": 18060 }, { "grad_norm": 0.33826494216918945, "learning_rate": 9.540265807423401e-05, "loss": 0.0199, "step": 18070 }, { "loss_action": 0.03062436170876026, "loss_total": 0.03062436170876026, "step": 18070 }, { "grad_norm": 0.4106364846229553, "learning_rate": 9.53957299518599e-05, "loss": 0.0214, "step": 18080 }, { "loss_action": 0.01634429581463337, "loss_total": 0.01634429581463337, "step": 18080 }, { "grad_norm": 0.38315996527671814, "learning_rate": 9.5388796865077e-05, "loss": 0.0202, "step": 18090 }, { "loss_action": 0.019892493262887, "loss_total": 0.019892493262887, "step": 18090 }, { "grad_norm": 0.354757696390152, "learning_rate": 9.538185881464353e-05, "loss": 0.0199, "step": 18100 }, { "loss_action": 0.031197523698210716, "loss_total": 0.031197523698210716, "step": 18100 }, { "grad_norm": 0.4691712558269501, "learning_rate": 9.537491580131821e-05, "loss": 0.024, "step": 18110 }, { "loss_action": 0.020441828295588493, "loss_total": 0.020441828295588493, "step": 18110 }, { "grad_norm": 0.4916171133518219, "learning_rate": 9.53679678258603e-05, "loss": 0.022, "step": 18120 }, { "loss_action": 0.02072429656982422, "loss_total": 0.02072429656982422, "step": 18120 }, { "grad_norm": 0.29866665601730347, "learning_rate": 9.536101488902966e-05, "loss": 0.0188, "step": 18130 }, { "loss_action": 0.018645266070961952, "loss_total": 0.018645266070961952, "step": 18130 }, { "grad_norm": 0.3977564573287964, "learning_rate": 9.535405699158663e-05, "loss": 0.0223, "step": 18140 }, { "loss_action": 0.018780943006277084, "loss_total": 0.018780943006277084, "step": 18140 }, { "grad_norm": 0.40629684925079346, "learning_rate": 9.53470941342921e-05, "loss": 0.0194, "step": 18150 }, { "loss_action": 0.02042400650680065, "loss_total": 0.02042400650680065, "step": 18150 }, { "grad_norm": 0.5176863074302673, "learning_rate": 9.534012631790756e-05, "loss": 0.0201, "step": 18160 }, { "loss_action": 0.017473021522164345, "loss_total": 0.017473021522164345, "step": 18160 }, { "grad_norm": 0.3875528573989868, "learning_rate": 9.533315354319494e-05, "loss": 0.0209, "step": 18170 }, { "loss_action": 0.025831297039985657, "loss_total": 0.025831297039985657, "step": 18170 }, { "grad_norm": 0.34083035588264465, "learning_rate": 9.532617581091682e-05, "loss": 0.0187, "step": 18180 }, { "loss_action": 0.018797144293785095, "loss_total": 0.018797144293785095, "step": 18180 }, { "grad_norm": 0.4493591785430908, "learning_rate": 9.531919312183629e-05, "loss": 0.0201, "step": 18190 }, { "loss_action": 0.016063163056969643, "loss_total": 0.016063163056969643, "step": 18190 }, { "grad_norm": 0.39289870858192444, "learning_rate": 9.531220547671688e-05, "loss": 0.0219, "step": 18200 }, { "loss_action": 0.017127059400081635, "loss_total": 0.017127059400081635, "step": 18200 }, { "grad_norm": 0.3421602249145508, "learning_rate": 9.530521287632285e-05, "loss": 0.0188, "step": 18210 }, { "loss_action": 0.016779381781816483, "loss_total": 0.016779381781816483, "step": 18210 }, { "grad_norm": 0.3827972412109375, "learning_rate": 9.529821532141884e-05, "loss": 0.0182, "step": 18220 }, { "loss_action": 0.01708221808075905, "loss_total": 0.01708221808075905, "step": 18220 }, { "grad_norm": 0.35904476046562195, "learning_rate": 9.52912128127701e-05, "loss": 0.0188, "step": 18230 }, { "loss_action": 0.022267362102866173, "loss_total": 0.022267362102866173, "step": 18230 }, { "grad_norm": 0.4137357473373413, "learning_rate": 9.528420535114244e-05, "loss": 0.0197, "step": 18240 }, { "loss_action": 0.0228654183447361, "loss_total": 0.0228654183447361, "step": 18240 }, { "grad_norm": 0.31226131319999695, "learning_rate": 9.527719293730215e-05, "loss": 0.0189, "step": 18250 }, { "loss_action": 0.021825328469276428, "loss_total": 0.021825328469276428, "step": 18250 }, { "grad_norm": 0.41839754581451416, "learning_rate": 9.527017557201611e-05, "loss": 0.0192, "step": 18260 }, { "loss_action": 0.021122600883245468, "loss_total": 0.021122600883245468, "step": 18260 }, { "grad_norm": 0.4029717445373535, "learning_rate": 9.526315325605176e-05, "loss": 0.0195, "step": 18270 }, { "loss_action": 0.01872517168521881, "loss_total": 0.01872517168521881, "step": 18270 }, { "grad_norm": 0.34944283962249756, "learning_rate": 9.525612599017699e-05, "loss": 0.0191, "step": 18280 }, { "loss_action": 0.022595493122935295, "loss_total": 0.022595493122935295, "step": 18280 }, { "grad_norm": 0.5601726174354553, "learning_rate": 9.524909377516033e-05, "loss": 0.0212, "step": 18290 }, { "loss_action": 0.02743983268737793, "loss_total": 0.02743983268737793, "step": 18290 }, { "grad_norm": 0.3938129246234894, "learning_rate": 9.524205661177081e-05, "loss": 0.0218, "step": 18300 }, { "loss_action": 0.016533011570572853, "loss_total": 0.016533011570572853, "step": 18300 }, { "grad_norm": 0.46767979860305786, "learning_rate": 9.523501450077801e-05, "loss": 0.0192, "step": 18310 }, { "loss_action": 0.015743831172585487, "loss_total": 0.015743831172585487, "step": 18310 }, { "grad_norm": 0.3627362549304962, "learning_rate": 9.522796744295202e-05, "loss": 0.0214, "step": 18320 }, { "loss_action": 0.021918075159192085, "loss_total": 0.021918075159192085, "step": 18320 }, { "grad_norm": 0.35735777020454407, "learning_rate": 9.522091543906352e-05, "loss": 0.0217, "step": 18330 }, { "loss_action": 0.02321247197687626, "loss_total": 0.02321247197687626, "step": 18330 }, { "grad_norm": 0.469490647315979, "learning_rate": 9.521385848988369e-05, "loss": 0.0196, "step": 18340 }, { "loss_action": 0.01497511938214302, "loss_total": 0.01497511938214302, "step": 18340 }, { "grad_norm": 0.37799474596977234, "learning_rate": 9.520679659618428e-05, "loss": 0.0186, "step": 18350 }, { "loss_action": 0.02065063640475273, "loss_total": 0.02065063640475273, "step": 18350 }, { "grad_norm": 0.4316207468509674, "learning_rate": 9.519972975873754e-05, "loss": 0.0184, "step": 18360 }, { "loss_action": 0.023753849789500237, "loss_total": 0.023753849789500237, "step": 18360 }, { "grad_norm": 0.45120251178741455, "learning_rate": 9.519265797831633e-05, "loss": 0.0209, "step": 18370 }, { "loss_action": 0.020023886114358902, "loss_total": 0.020023886114358902, "step": 18370 }, { "grad_norm": 0.3019842803478241, "learning_rate": 9.518558125569399e-05, "loss": 0.0184, "step": 18380 }, { "loss_action": 0.018674073740839958, "loss_total": 0.018674073740839958, "step": 18380 }, { "grad_norm": 0.35440218448638916, "learning_rate": 9.517849959164442e-05, "loss": 0.0207, "step": 18390 }, { "loss_action": 0.019881226122379303, "loss_total": 0.019881226122379303, "step": 18390 }, { "grad_norm": 0.4825984239578247, "learning_rate": 9.517141298694205e-05, "loss": 0.0214, "step": 18400 }, { "loss_action": 0.021903596818447113, "loss_total": 0.021903596818447113, "step": 18400 }, { "grad_norm": 0.4142850935459137, "learning_rate": 9.516432144236188e-05, "loss": 0.0247, "step": 18410 }, { "loss_action": 0.021869968622922897, "loss_total": 0.021869968622922897, "step": 18410 }, { "grad_norm": 0.4711124897003174, "learning_rate": 9.515722495867941e-05, "loss": 0.022, "step": 18420 }, { "loss_action": 0.022775782272219658, "loss_total": 0.022775782272219658, "step": 18420 }, { "grad_norm": 0.41223669052124023, "learning_rate": 9.515012353667072e-05, "loss": 0.022, "step": 18430 }, { "loss_action": 0.02201053872704506, "loss_total": 0.02201053872704506, "step": 18430 }, { "grad_norm": 0.4455000162124634, "learning_rate": 9.51430171771124e-05, "loss": 0.022, "step": 18440 }, { "loss_action": 0.02464118041098118, "loss_total": 0.02464118041098118, "step": 18440 }, { "grad_norm": 0.39330777525901794, "learning_rate": 9.513590588078159e-05, "loss": 0.0204, "step": 18450 }, { "loss_action": 0.021787989884614944, "loss_total": 0.021787989884614944, "step": 18450 }, { "grad_norm": 0.5121392607688904, "learning_rate": 9.512878964845597e-05, "loss": 0.0229, "step": 18460 }, { "loss_action": 0.027284083887934685, "loss_total": 0.027284083887934685, "step": 18460 }, { "grad_norm": 0.43683892488479614, "learning_rate": 9.512166848091377e-05, "loss": 0.0217, "step": 18470 }, { "loss_action": 0.02045433595776558, "loss_total": 0.02045433595776558, "step": 18470 }, { "grad_norm": 0.5218113660812378, "learning_rate": 9.511454237893376e-05, "loss": 0.0229, "step": 18480 }, { "loss_action": 0.032134104520082474, "loss_total": 0.032134104520082474, "step": 18480 }, { "grad_norm": 0.4651670455932617, "learning_rate": 9.51074113432952e-05, "loss": 0.0205, "step": 18490 }, { "loss_action": 0.01978217251598835, "loss_total": 0.01978217251598835, "step": 18490 }, { "grad_norm": 0.3291738033294678, "learning_rate": 9.510027537477797e-05, "loss": 0.0184, "step": 18500 }, { "loss_action": 0.017732806503772736, "loss_total": 0.017732806503772736, "step": 18500 }, { "grad_norm": 0.37438035011291504, "learning_rate": 9.509313447416242e-05, "loss": 0.0183, "step": 18510 }, { "loss_action": 0.018461063504219055, "loss_total": 0.018461063504219055, "step": 18510 }, { "grad_norm": 0.4106255769729614, "learning_rate": 9.508598864222949e-05, "loss": 0.0191, "step": 18520 }, { "loss_action": 0.020279621705412865, "loss_total": 0.020279621705412865, "step": 18520 }, { "grad_norm": 0.4685960114002228, "learning_rate": 9.507883787976062e-05, "loss": 0.0214, "step": 18530 }, { "loss_action": 0.023360826075077057, "loss_total": 0.023360826075077057, "step": 18530 }, { "grad_norm": 0.40308740735054016, "learning_rate": 9.507168218753781e-05, "loss": 0.0208, "step": 18540 }, { "loss_action": 0.02020319551229477, "loss_total": 0.02020319551229477, "step": 18540 }, { "grad_norm": 0.3768259584903717, "learning_rate": 9.506452156634362e-05, "loss": 0.0177, "step": 18550 }, { "loss_action": 0.01929238624870777, "loss_total": 0.01929238624870777, "step": 18550 }, { "grad_norm": 0.48520466685295105, "learning_rate": 9.505735601696109e-05, "loss": 0.0212, "step": 18560 }, { "loss_action": 0.03130421042442322, "loss_total": 0.03130421042442322, "step": 18560 }, { "grad_norm": 0.35337379574775696, "learning_rate": 9.505018554017385e-05, "loss": 0.0209, "step": 18570 }, { "loss_action": 0.02300463430583477, "loss_total": 0.02300463430583477, "step": 18570 }, { "grad_norm": 0.40620866417884827, "learning_rate": 9.504301013676604e-05, "loss": 0.0186, "step": 18580 }, { "loss_action": 0.02341303415596485, "loss_total": 0.02341303415596485, "step": 18580 }, { "grad_norm": 0.4385805130004883, "learning_rate": 9.503582980752238e-05, "loss": 0.0208, "step": 18590 }, { "loss_action": 0.0194175373762846, "loss_total": 0.0194175373762846, "step": 18590 }, { "grad_norm": 0.3893003761768341, "learning_rate": 9.502864455322809e-05, "loss": 0.0221, "step": 18600 }, { "loss_action": 0.019361305981874466, "loss_total": 0.019361305981874466, "step": 18600 }, { "grad_norm": 0.3758178949356079, "learning_rate": 9.502145437466891e-05, "loss": 0.0199, "step": 18610 }, { "loss_action": 0.024766214191913605, "loss_total": 0.024766214191913605, "step": 18610 }, { "grad_norm": 0.3958759307861328, "learning_rate": 9.501425927263116e-05, "loss": 0.0209, "step": 18620 }, { "loss_action": 0.02040276676416397, "loss_total": 0.02040276676416397, "step": 18620 }, { "grad_norm": 0.3369269371032715, "learning_rate": 9.500705924790172e-05, "loss": 0.0203, "step": 18630 }, { "loss_action": 0.015568964183330536, "loss_total": 0.015568964183330536, "step": 18630 }, { "grad_norm": 0.3305476903915405, "learning_rate": 9.499985430126794e-05, "loss": 0.0193, "step": 18640 }, { "loss_action": 0.01838240772485733, "loss_total": 0.01838240772485733, "step": 18640 }, { "grad_norm": 0.3963306248188019, "learning_rate": 9.499264443351775e-05, "loss": 0.0205, "step": 18650 }, { "loss_action": 0.016822699457406998, "loss_total": 0.016822699457406998, "step": 18650 }, { "grad_norm": 0.4724787175655365, "learning_rate": 9.498542964543961e-05, "loss": 0.0188, "step": 18660 }, { "loss_action": 0.014260808937251568, "loss_total": 0.014260808937251568, "step": 18660 }, { "grad_norm": 0.34035640954971313, "learning_rate": 9.497820993782252e-05, "loss": 0.0182, "step": 18670 }, { "loss_action": 0.015471670776605606, "loss_total": 0.015471670776605606, "step": 18670 }, { "grad_norm": 0.3749602437019348, "learning_rate": 9.497098531145601e-05, "loss": 0.0188, "step": 18680 }, { "loss_action": 0.01514608133584261, "loss_total": 0.01514608133584261, "step": 18680 }, { "grad_norm": 0.29680588841438293, "learning_rate": 9.496375576713017e-05, "loss": 0.0188, "step": 18690 }, { "loss_action": 0.021241173148155212, "loss_total": 0.021241173148155212, "step": 18690 }, { "grad_norm": 0.5332461595535278, "learning_rate": 9.49565213056356e-05, "loss": 0.0198, "step": 18700 }, { "loss_action": 0.017298666760325432, "loss_total": 0.017298666760325432, "step": 18700 }, { "grad_norm": 0.3961159586906433, "learning_rate": 9.494928192776342e-05, "loss": 0.0196, "step": 18710 }, { "loss_action": 0.01793624460697174, "loss_total": 0.01793624460697174, "step": 18710 }, { "grad_norm": 0.3793864846229553, "learning_rate": 9.494203763430538e-05, "loss": 0.018, "step": 18720 }, { "loss_action": 0.026854930445551872, "loss_total": 0.026854930445551872, "step": 18720 }, { "grad_norm": 0.3770659863948822, "learning_rate": 9.493478842605366e-05, "loss": 0.0195, "step": 18730 }, { "loss_action": 0.015817072242498398, "loss_total": 0.015817072242498398, "step": 18730 }, { "grad_norm": 0.4319503605365753, "learning_rate": 9.492753430380105e-05, "loss": 0.0199, "step": 18740 }, { "loss_action": 0.01684800535440445, "loss_total": 0.01684800535440445, "step": 18740 }, { "grad_norm": 0.35550227761268616, "learning_rate": 9.492027526834083e-05, "loss": 0.0187, "step": 18750 }, { "loss_action": 0.026595380157232285, "loss_total": 0.026595380157232285, "step": 18750 }, { "grad_norm": 0.5106109976768494, "learning_rate": 9.491301132046684e-05, "loss": 0.0234, "step": 18760 }, { "loss_action": 0.020458554849028587, "loss_total": 0.020458554849028587, "step": 18760 }, { "grad_norm": 0.4823012948036194, "learning_rate": 9.490574246097345e-05, "loss": 0.0216, "step": 18770 }, { "loss_action": 0.020705441012978554, "loss_total": 0.020705441012978554, "step": 18770 }, { "grad_norm": 0.42956843972206116, "learning_rate": 9.48984686906556e-05, "loss": 0.0212, "step": 18780 }, { "loss_action": 0.019952604547142982, "loss_total": 0.019952604547142982, "step": 18780 }, { "grad_norm": 0.3288342356681824, "learning_rate": 9.489119001030871e-05, "loss": 0.0201, "step": 18790 }, { "loss_action": 0.01946057192981243, "loss_total": 0.01946057192981243, "step": 18790 }, { "grad_norm": 0.4545287787914276, "learning_rate": 9.488390642072878e-05, "loss": 0.0241, "step": 18800 }, { "loss_action": 0.014754478819668293, "loss_total": 0.014754478819668293, "step": 18800 }, { "grad_norm": 0.60054612159729, "learning_rate": 9.48766179227123e-05, "loss": 0.0206, "step": 18810 }, { "loss_action": 0.025012612342834473, "loss_total": 0.025012612342834473, "step": 18810 }, { "grad_norm": 0.3519544303417206, "learning_rate": 9.486932451705636e-05, "loss": 0.0201, "step": 18820 }, { "loss_action": 0.020316850394010544, "loss_total": 0.020316850394010544, "step": 18820 }, { "grad_norm": 0.338455468416214, "learning_rate": 9.486202620455857e-05, "loss": 0.0174, "step": 18830 }, { "loss_action": 0.018156424164772034, "loss_total": 0.018156424164772034, "step": 18830 }, { "grad_norm": 0.4716924726963043, "learning_rate": 9.485472298601704e-05, "loss": 0.0201, "step": 18840 }, { "loss_action": 0.01819642446935177, "loss_total": 0.01819642446935177, "step": 18840 }, { "grad_norm": 0.588681697845459, "learning_rate": 9.484741486223043e-05, "loss": 0.023, "step": 18850 }, { "loss_action": 0.029930707067251205, "loss_total": 0.029930707067251205, "step": 18850 }, { "grad_norm": 0.3915490210056305, "learning_rate": 9.484010183399797e-05, "loss": 0.0239, "step": 18860 }, { "loss_action": 0.018922599032521248, "loss_total": 0.018922599032521248, "step": 18860 }, { "grad_norm": 0.4965856969356537, "learning_rate": 9.483278390211938e-05, "loss": 0.0225, "step": 18870 }, { "loss_action": 0.02598382532596588, "loss_total": 0.02598382532596588, "step": 18870 }, { "grad_norm": 0.34099701046943665, "learning_rate": 9.482546106739496e-05, "loss": 0.0218, "step": 18880 }, { "loss_action": 0.02499464340507984, "loss_total": 0.02499464340507984, "step": 18880 }, { "grad_norm": 0.4809565842151642, "learning_rate": 9.48181333306255e-05, "loss": 0.0195, "step": 18890 }, { "loss_action": 0.01799047365784645, "loss_total": 0.01799047365784645, "step": 18890 }, { "grad_norm": 0.3829515278339386, "learning_rate": 9.481080069261237e-05, "loss": 0.0188, "step": 18900 }, { "loss_action": 0.019837234169244766, "loss_total": 0.019837234169244766, "step": 18900 }, { "grad_norm": 0.3313194215297699, "learning_rate": 9.480346315415745e-05, "loss": 0.0185, "step": 18910 }, { "loss_action": 0.018269242718815804, "loss_total": 0.018269242718815804, "step": 18910 }, { "grad_norm": 0.37486422061920166, "learning_rate": 9.479612071606314e-05, "loss": 0.018, "step": 18920 }, { "loss_action": 0.02512311562895775, "loss_total": 0.02512311562895775, "step": 18920 }, { "grad_norm": 0.4575614929199219, "learning_rate": 9.478877337913244e-05, "loss": 0.0197, "step": 18930 }, { "loss_action": 0.015746919438242912, "loss_total": 0.015746919438242912, "step": 18930 }, { "grad_norm": 0.43732625246047974, "learning_rate": 9.478142114416881e-05, "loss": 0.0218, "step": 18940 }, { "loss_action": 0.023320727050304413, "loss_total": 0.023320727050304413, "step": 18940 }, { "grad_norm": 0.5451393127441406, "learning_rate": 9.47740640119763e-05, "loss": 0.0192, "step": 18950 }, { "loss_action": 0.013671394437551498, "loss_total": 0.013671394437551498, "step": 18950 }, { "grad_norm": 0.4125525951385498, "learning_rate": 9.476670198335947e-05, "loss": 0.0188, "step": 18960 }, { "loss_action": 0.022368382662534714, "loss_total": 0.022368382662534714, "step": 18960 }, { "grad_norm": 0.4540952146053314, "learning_rate": 9.47593350591234e-05, "loss": 0.0199, "step": 18970 }, { "loss_action": 0.01684737578034401, "loss_total": 0.01684737578034401, "step": 18970 }, { "grad_norm": 0.39076516032218933, "learning_rate": 9.475196324007376e-05, "loss": 0.0188, "step": 18980 }, { "loss_action": 0.01683969981968403, "loss_total": 0.01683969981968403, "step": 18980 }, { "grad_norm": 0.38144367933273315, "learning_rate": 9.474458652701669e-05, "loss": 0.0186, "step": 18990 }, { "loss_action": 0.0233761053532362, "loss_total": 0.0233761053532362, "step": 18990 }, { "grad_norm": 0.42236873507499695, "learning_rate": 9.473720492075892e-05, "loss": 0.0206, "step": 19000 }, { "loss_action": 0.019393976777791977, "loss_total": 0.019393976777791977, "step": 19000 }, { "grad_norm": 0.34281396865844727, "learning_rate": 9.472981842210768e-05, "loss": 0.0188, "step": 19010 }, { "loss_action": 0.017171330749988556, "loss_total": 0.017171330749988556, "step": 19010 }, { "grad_norm": 0.48168712854385376, "learning_rate": 9.472242703187074e-05, "loss": 0.0221, "step": 19020 }, { "loss_action": 0.023822160437703133, "loss_total": 0.023822160437703133, "step": 19020 }, { "grad_norm": 0.3616443872451782, "learning_rate": 9.471503075085643e-05, "loss": 0.0215, "step": 19030 }, { "loss_action": 0.01793411746621132, "loss_total": 0.01793411746621132, "step": 19030 }, { "grad_norm": 0.3404978811740875, "learning_rate": 9.470762957987359e-05, "loss": 0.0204, "step": 19040 }, { "loss_action": 0.025405509397387505, "loss_total": 0.025405509397387505, "step": 19040 }, { "grad_norm": 0.4163975119590759, "learning_rate": 9.470022351973158e-05, "loss": 0.0182, "step": 19050 }, { "loss_action": 0.018145916983485222, "loss_total": 0.018145916983485222, "step": 19050 }, { "grad_norm": 0.5372061133384705, "learning_rate": 9.469281257124034e-05, "loss": 0.0189, "step": 19060 }, { "loss_action": 0.028268564492464066, "loss_total": 0.028268564492464066, "step": 19060 }, { "grad_norm": 0.360598623752594, "learning_rate": 9.46853967352103e-05, "loss": 0.0193, "step": 19070 }, { "loss_action": 0.022620033472776413, "loss_total": 0.022620033472776413, "step": 19070 }, { "grad_norm": 0.433951199054718, "learning_rate": 9.467797601245246e-05, "loss": 0.0237, "step": 19080 }, { "loss_action": 0.021881403401494026, "loss_total": 0.021881403401494026, "step": 19080 }, { "grad_norm": 0.4146537780761719, "learning_rate": 9.467055040377834e-05, "loss": 0.0198, "step": 19090 }, { "loss_action": 0.02290131151676178, "loss_total": 0.02290131151676178, "step": 19090 }, { "grad_norm": 0.33987241983413696, "learning_rate": 9.466311990999999e-05, "loss": 0.0187, "step": 19100 }, { "loss_action": 0.023056771606206894, "loss_total": 0.023056771606206894, "step": 19100 }, { "grad_norm": 0.4130312502384186, "learning_rate": 9.465568453193e-05, "loss": 0.0191, "step": 19110 }, { "loss_action": 0.019823221489787102, "loss_total": 0.019823221489787102, "step": 19110 }, { "grad_norm": 0.4398992359638214, "learning_rate": 9.464824427038148e-05, "loss": 0.0194, "step": 19120 }, { "loss_action": 0.017394503578543663, "loss_total": 0.017394503578543663, "step": 19120 }, { "grad_norm": 0.42316436767578125, "learning_rate": 9.46407991261681e-05, "loss": 0.0213, "step": 19130 }, { "loss_action": 0.02098672464489937, "loss_total": 0.02098672464489937, "step": 19130 }, { "grad_norm": 0.4040409326553345, "learning_rate": 9.463334910010404e-05, "loss": 0.0207, "step": 19140 }, { "loss_action": 0.019981781020760536, "loss_total": 0.019981781020760536, "step": 19140 }, { "grad_norm": 0.3920595347881317, "learning_rate": 9.462589419300403e-05, "loss": 0.0214, "step": 19150 }, { "loss_action": 0.02336556650698185, "loss_total": 0.02336556650698185, "step": 19150 }, { "grad_norm": 0.3973274528980255, "learning_rate": 9.461843440568333e-05, "loss": 0.0234, "step": 19160 }, { "loss_action": 0.019939174875617027, "loss_total": 0.019939174875617027, "step": 19160 }, { "grad_norm": 0.41210007667541504, "learning_rate": 9.461096973895773e-05, "loss": 0.0224, "step": 19170 }, { "loss_action": 0.02070159837603569, "loss_total": 0.02070159837603569, "step": 19170 }, { "grad_norm": 0.37911492586135864, "learning_rate": 9.460350019364355e-05, "loss": 0.0193, "step": 19180 }, { "loss_action": 0.015930285677313805, "loss_total": 0.015930285677313805, "step": 19180 }, { "grad_norm": 0.4329805374145508, "learning_rate": 9.459602577055764e-05, "loss": 0.0174, "step": 19190 }, { "loss_action": 0.017668047919869423, "loss_total": 0.017668047919869423, "step": 19190 }, { "grad_norm": 0.46420615911483765, "learning_rate": 9.45885464705174e-05, "loss": 0.0193, "step": 19200 }, { "loss_action": 0.018184766173362732, "loss_total": 0.018184766173362732, "step": 19200 }, { "grad_norm": 0.3044608533382416, "learning_rate": 9.458106229434076e-05, "loss": 0.0199, "step": 19210 }, { "loss_action": 0.014859890565276146, "loss_total": 0.014859890565276146, "step": 19210 }, { "grad_norm": 0.36860331892967224, "learning_rate": 9.457357324284617e-05, "loss": 0.0204, "step": 19220 }, { "loss_action": 0.017226899042725563, "loss_total": 0.017226899042725563, "step": 19220 }, { "grad_norm": 0.3603009879589081, "learning_rate": 9.456607931685262e-05, "loss": 0.0202, "step": 19230 }, { "loss_action": 0.019192291423678398, "loss_total": 0.019192291423678398, "step": 19230 }, { "grad_norm": 0.4710966944694519, "learning_rate": 9.455858051717965e-05, "loss": 0.0194, "step": 19240 }, { "loss_action": 0.021445930004119873, "loss_total": 0.021445930004119873, "step": 19240 }, { "grad_norm": 0.3558383882045746, "learning_rate": 9.45510768446473e-05, "loss": 0.0208, "step": 19250 }, { "loss_action": 0.017345404252409935, "loss_total": 0.017345404252409935, "step": 19250 }, { "grad_norm": 0.3812706470489502, "learning_rate": 9.454356830007618e-05, "loss": 0.0202, "step": 19260 }, { "loss_action": 0.01694445312023163, "loss_total": 0.01694445312023163, "step": 19260 }, { "grad_norm": 0.4687477946281433, "learning_rate": 9.45360548842874e-05, "loss": 0.0202, "step": 19270 }, { "loss_action": 0.020341254770755768, "loss_total": 0.020341254770755768, "step": 19270 }, { "grad_norm": 0.4337519407272339, "learning_rate": 9.452853659810261e-05, "loss": 0.0197, "step": 19280 }, { "loss_action": 0.019809899851679802, "loss_total": 0.019809899851679802, "step": 19280 }, { "grad_norm": 0.39158111810684204, "learning_rate": 9.452101344234401e-05, "loss": 0.0199, "step": 19290 }, { "loss_action": 0.017088625580072403, "loss_total": 0.017088625580072403, "step": 19290 }, { "grad_norm": 0.3955777585506439, "learning_rate": 9.451348541783431e-05, "loss": 0.0197, "step": 19300 }, { "loss_action": 0.020210742950439453, "loss_total": 0.020210742950439453, "step": 19300 }, { "grad_norm": 0.44263893365859985, "learning_rate": 9.450595252539678e-05, "loss": 0.0177, "step": 19310 }, { "loss_action": 0.017845436930656433, "loss_total": 0.017845436930656433, "step": 19310 }, { "grad_norm": 0.42551589012145996, "learning_rate": 9.449841476585518e-05, "loss": 0.0174, "step": 19320 }, { "loss_action": 0.014635162428021431, "loss_total": 0.014635162428021431, "step": 19320 }, { "grad_norm": 0.33304381370544434, "learning_rate": 9.449087214003384e-05, "loss": 0.0181, "step": 19330 }, { "loss_action": 0.017638515681028366, "loss_total": 0.017638515681028366, "step": 19330 }, { "grad_norm": 0.4017049968242645, "learning_rate": 9.448332464875765e-05, "loss": 0.0183, "step": 19340 }, { "loss_action": 0.017564235255122185, "loss_total": 0.017564235255122185, "step": 19340 }, { "grad_norm": 0.41031795740127563, "learning_rate": 9.447577229285192e-05, "loss": 0.0175, "step": 19350 }, { "loss_action": 0.014890390448272228, "loss_total": 0.014890390448272228, "step": 19350 }, { "grad_norm": 0.3846381604671478, "learning_rate": 9.446821507314261e-05, "loss": 0.0149, "step": 19360 }, { "loss_action": 0.020351441577076912, "loss_total": 0.020351441577076912, "step": 19360 }, { "grad_norm": 0.35173505544662476, "learning_rate": 9.446065299045617e-05, "loss": 0.0185, "step": 19370 }, { "loss_action": 0.021027497947216034, "loss_total": 0.021027497947216034, "step": 19370 }, { "grad_norm": 0.3424343466758728, "learning_rate": 9.445308604561955e-05, "loss": 0.0198, "step": 19380 }, { "loss_action": 0.016809586435556412, "loss_total": 0.016809586435556412, "step": 19380 }, { "grad_norm": 0.33493107557296753, "learning_rate": 9.444551423946028e-05, "loss": 0.0172, "step": 19390 }, { "loss_action": 0.015017145313322544, "loss_total": 0.015017145313322544, "step": 19390 }, { "grad_norm": 0.42623817920684814, "learning_rate": 9.443793757280638e-05, "loss": 0.0162, "step": 19400 }, { "loss_action": 0.016993870958685875, "loss_total": 0.016993870958685875, "step": 19400 }, { "grad_norm": 0.4494871497154236, "learning_rate": 9.443035604648646e-05, "loss": 0.0185, "step": 19410 }, { "loss_action": 0.01636514812707901, "loss_total": 0.01636514812707901, "step": 19410 }, { "grad_norm": 0.35270625352859497, "learning_rate": 9.44227696613296e-05, "loss": 0.0187, "step": 19420 }, { "loss_action": 0.013951380737125874, "loss_total": 0.013951380737125874, "step": 19420 }, { "grad_norm": 0.3096461892127991, "learning_rate": 9.441517841816542e-05, "loss": 0.0171, "step": 19430 }, { "loss_action": 0.016825541853904724, "loss_total": 0.016825541853904724, "step": 19430 }, { "grad_norm": 0.32566672563552856, "learning_rate": 9.440758231782413e-05, "loss": 0.0188, "step": 19440 }, { "loss_action": 0.01741068810224533, "loss_total": 0.01741068810224533, "step": 19440 }, { "grad_norm": 0.4154587388038635, "learning_rate": 9.439998136113639e-05, "loss": 0.0177, "step": 19450 }, { "loss_action": 0.01842314936220646, "loss_total": 0.01842314936220646, "step": 19450 }, { "grad_norm": 0.3954126834869385, "learning_rate": 9.439237554893344e-05, "loss": 0.0164, "step": 19460 }, { "loss_action": 0.015625571832060814, "loss_total": 0.015625571832060814, "step": 19460 }, { "grad_norm": 0.3910936713218689, "learning_rate": 9.438476488204705e-05, "loss": 0.0177, "step": 19470 }, { "loss_action": 0.017660459503531456, "loss_total": 0.017660459503531456, "step": 19470 }, { "grad_norm": 0.3882119655609131, "learning_rate": 9.43771493613095e-05, "loss": 0.018, "step": 19480 }, { "loss_action": 0.01648116298019886, "loss_total": 0.01648116298019886, "step": 19480 }, { "grad_norm": 0.4190490245819092, "learning_rate": 9.436952898755362e-05, "loss": 0.0172, "step": 19490 }, { "loss_action": 0.019628338515758514, "loss_total": 0.019628338515758514, "step": 19490 }, { "grad_norm": 0.4095386266708374, "learning_rate": 9.436190376161276e-05, "loss": 0.0223, "step": 19500 }, { "loss_action": 0.018687058240175247, "loss_total": 0.018687058240175247, "step": 19500 }, { "grad_norm": 0.3078427314758301, "learning_rate": 9.43542736843208e-05, "loss": 0.0195, "step": 19510 }, { "loss_action": 0.01999572105705738, "loss_total": 0.01999572105705738, "step": 19510 }, { "grad_norm": 0.27837949991226196, "learning_rate": 9.434663875651216e-05, "loss": 0.0192, "step": 19520 }, { "loss_action": 0.017845800146460533, "loss_total": 0.017845800146460533, "step": 19520 }, { "grad_norm": 0.35918310284614563, "learning_rate": 9.433899897902177e-05, "loss": 0.0192, "step": 19530 }, { "loss_action": 0.02292320504784584, "loss_total": 0.02292320504784584, "step": 19530 }, { "grad_norm": 0.42652738094329834, "learning_rate": 9.433135435268511e-05, "loss": 0.0201, "step": 19540 }, { "loss_action": 0.02029973454773426, "loss_total": 0.02029973454773426, "step": 19540 }, { "grad_norm": 0.3873731791973114, "learning_rate": 9.432370487833819e-05, "loss": 0.0179, "step": 19550 }, { "loss_action": 0.018056971952319145, "loss_total": 0.018056971952319145, "step": 19550 }, { "grad_norm": 0.6661306023597717, "learning_rate": 9.431605055681756e-05, "loss": 0.0191, "step": 19560 }, { "loss_action": 0.016998663544654846, "loss_total": 0.016998663544654846, "step": 19560 }, { "grad_norm": 0.304913192987442, "learning_rate": 9.430839138896026e-05, "loss": 0.0188, "step": 19570 }, { "loss_action": 0.030910726636648178, "loss_total": 0.030910726636648178, "step": 19570 }, { "grad_norm": 0.584209144115448, "learning_rate": 9.43007273756039e-05, "loss": 0.0213, "step": 19580 }, { "loss_action": 0.022132260724902153, "loss_total": 0.022132260724902153, "step": 19580 }, { "grad_norm": 0.39769843220710754, "learning_rate": 9.429305851758658e-05, "loss": 0.0206, "step": 19590 }, { "loss_action": 0.023271014913916588, "loss_total": 0.023271014913916588, "step": 19590 }, { "grad_norm": 0.4422151744365692, "learning_rate": 9.428538481574699e-05, "loss": 0.0209, "step": 19600 }, { "loss_action": 0.024860450997948647, "loss_total": 0.024860450997948647, "step": 19600 }, { "grad_norm": 0.5562602281570435, "learning_rate": 9.42777062709243e-05, "loss": 0.0229, "step": 19610 }, { "loss_action": 0.023986922577023506, "loss_total": 0.023986922577023506, "step": 19610 }, { "grad_norm": 0.48650315403938293, "learning_rate": 9.427002288395821e-05, "loss": 0.0204, "step": 19620 }, { "loss_action": 0.02498508431017399, "loss_total": 0.02498508431017399, "step": 19620 }, { "grad_norm": 0.4340568780899048, "learning_rate": 9.426233465568898e-05, "loss": 0.023, "step": 19630 }, { "loss_action": 0.022042561322450638, "loss_total": 0.022042561322450638, "step": 19630 }, { "grad_norm": 0.36575382947921753, "learning_rate": 9.42546415869574e-05, "loss": 0.0187, "step": 19640 }, { "loss_action": 0.021832378581166267, "loss_total": 0.021832378581166267, "step": 19640 }, { "grad_norm": 0.4782475531101227, "learning_rate": 9.424694367860473e-05, "loss": 0.0167, "step": 19650 }, { "loss_action": 0.02530081197619438, "loss_total": 0.02530081197619438, "step": 19650 }, { "grad_norm": 0.31932997703552246, "learning_rate": 9.423924093147284e-05, "loss": 0.0205, "step": 19660 }, { "loss_action": 0.018671544268727303, "loss_total": 0.018671544268727303, "step": 19660 }, { "grad_norm": 0.4231862723827362, "learning_rate": 9.423153334640407e-05, "loss": 0.0194, "step": 19670 }, { "loss_action": 0.01696021854877472, "loss_total": 0.01696021854877472, "step": 19670 }, { "grad_norm": 0.504460871219635, "learning_rate": 9.42238209242413e-05, "loss": 0.0229, "step": 19680 }, { "loss_action": 0.02242226153612137, "loss_total": 0.02242226153612137, "step": 19680 }, { "grad_norm": 0.3478124439716339, "learning_rate": 9.421610366582798e-05, "loss": 0.0225, "step": 19690 }, { "loss_action": 0.019513342529535294, "loss_total": 0.019513342529535294, "step": 19690 }, { "grad_norm": 0.42629745602607727, "learning_rate": 9.420838157200803e-05, "loss": 0.019, "step": 19700 }, { "loss_action": 0.02033649943768978, "loss_total": 0.02033649943768978, "step": 19700 }, { "grad_norm": 0.39862629771232605, "learning_rate": 9.420065464362594e-05, "loss": 0.0221, "step": 19710 }, { "loss_action": 0.030444322153925896, "loss_total": 0.030444322153925896, "step": 19710 }, { "grad_norm": 0.5002968311309814, "learning_rate": 9.419292288152673e-05, "loss": 0.0223, "step": 19720 }, { "loss_action": 0.01986551657319069, "loss_total": 0.01986551657319069, "step": 19720 }, { "grad_norm": 0.6358091235160828, "learning_rate": 9.418518628655588e-05, "loss": 0.0234, "step": 19730 }, { "loss_action": 0.02108675055205822, "loss_total": 0.02108675055205822, "step": 19730 }, { "grad_norm": 0.5632873177528381, "learning_rate": 9.417744485955951e-05, "loss": 0.0217, "step": 19740 }, { "loss_action": 0.021160855889320374, "loss_total": 0.021160855889320374, "step": 19740 }, { "grad_norm": 0.38624027371406555, "learning_rate": 9.41696986013842e-05, "loss": 0.0223, "step": 19750 }, { "loss_action": 0.027741238474845886, "loss_total": 0.027741238474845886, "step": 19750 }, { "grad_norm": 0.5261684656143188, "learning_rate": 9.416194751287705e-05, "loss": 0.0225, "step": 19760 }, { "loss_action": 0.02860906533896923, "loss_total": 0.02860906533896923, "step": 19760 }, { "grad_norm": 0.5095387697219849, "learning_rate": 9.415419159488572e-05, "loss": 0.0232, "step": 19770 }, { "loss_action": 0.023886941373348236, "loss_total": 0.023886941373348236, "step": 19770 }, { "grad_norm": 0.3568301796913147, "learning_rate": 9.414643084825837e-05, "loss": 0.023, "step": 19780 }, { "loss_action": 0.019844917580485344, "loss_total": 0.019844917580485344, "step": 19780 }, { "grad_norm": 0.40133702754974365, "learning_rate": 9.413866527384372e-05, "loss": 0.0215, "step": 19790 }, { "loss_action": 0.019037870690226555, "loss_total": 0.019037870690226555, "step": 19790 }, { "grad_norm": 0.43965718150138855, "learning_rate": 9.4130894872491e-05, "loss": 0.0221, "step": 19800 }, { "loss_action": 0.02325199916958809, "loss_total": 0.02325199916958809, "step": 19800 }, { "grad_norm": 0.37084507942199707, "learning_rate": 9.412311964504998e-05, "loss": 0.0228, "step": 19810 }, { "loss_action": 0.019109616056084633, "loss_total": 0.019109616056084633, "step": 19810 }, { "grad_norm": 0.8712657690048218, "learning_rate": 9.411533959237091e-05, "loss": 0.0214, "step": 19820 }, { "loss_action": 0.027177510783076286, "loss_total": 0.027177510783076286, "step": 19820 }, { "grad_norm": 0.6303255558013916, "learning_rate": 9.410755471530464e-05, "loss": 0.0301, "step": 19830 }, { "loss_action": 0.03490159288048744, "loss_total": 0.03490159288048744, "step": 19830 }, { "grad_norm": 0.5539296865463257, "learning_rate": 9.40997650147025e-05, "loss": 0.0281, "step": 19840 }, { "loss_action": 0.03385695815086365, "loss_total": 0.03385695815086365, "step": 19840 }, { "grad_norm": 1.0128281116485596, "learning_rate": 9.409197049141637e-05, "loss": 0.0512, "step": 19850 }, { "loss_action": 0.04091639816761017, "loss_total": 0.04091639816761017, "step": 19850 }, { "grad_norm": 0.7815171480178833, "learning_rate": 9.408417114629863e-05, "loss": 0.0436, "step": 19860 }, { "loss_action": 0.03392903134226799, "loss_total": 0.03392903134226799, "step": 19860 }, { "grad_norm": 0.7182493805885315, "learning_rate": 9.40763669802022e-05, "loss": 0.0337, "step": 19870 }, { "loss_action": 0.03781108558177948, "loss_total": 0.03781108558177948, "step": 19870 }, { "grad_norm": 0.5673439502716064, "learning_rate": 9.406855799398056e-05, "loss": 0.0296, "step": 19880 }, { "loss_action": 0.022593382745981216, "loss_total": 0.022593382745981216, "step": 19880 }, { "grad_norm": 0.4351784586906433, "learning_rate": 9.406074418848767e-05, "loss": 0.0231, "step": 19890 }, { "loss_action": 0.024496719241142273, "loss_total": 0.024496719241142273, "step": 19890 }, { "grad_norm": 0.463603138923645, "learning_rate": 9.405292556457805e-05, "loss": 0.0263, "step": 19900 }, { "loss_action": 0.02756136655807495, "loss_total": 0.02756136655807495, "step": 19900 }, { "grad_norm": 0.40791597962379456, "learning_rate": 9.404510212310671e-05, "loss": 0.025, "step": 19910 }, { "loss_action": 0.019030513241887093, "loss_total": 0.019030513241887093, "step": 19910 }, { "grad_norm": 0.4386388659477234, "learning_rate": 9.403727386492924e-05, "loss": 0.0215, "step": 19920 }, { "loss_action": 0.021399816498160362, "loss_total": 0.021399816498160362, "step": 19920 }, { "grad_norm": 0.635786771774292, "learning_rate": 9.40294407909017e-05, "loss": 0.0224, "step": 19930 }, { "loss_action": 0.01663089729845524, "loss_total": 0.01663089729845524, "step": 19930 }, { "grad_norm": 0.37940773367881775, "learning_rate": 9.40216029018807e-05, "loss": 0.0228, "step": 19940 }, { "loss_action": 0.019958671182394028, "loss_total": 0.019958671182394028, "step": 19940 }, { "grad_norm": 0.4740702509880066, "learning_rate": 9.401376019872338e-05, "loss": 0.0198, "step": 19950 }, { "loss_action": 0.019172171130776405, "loss_total": 0.019172171130776405, "step": 19950 }, { "grad_norm": 0.5374277234077454, "learning_rate": 9.400591268228746e-05, "loss": 0.0201, "step": 19960 }, { "loss_action": 0.01758352294564247, "loss_total": 0.01758352294564247, "step": 19960 }, { "grad_norm": 0.36500993371009827, "learning_rate": 9.399806035343106e-05, "loss": 0.0208, "step": 19970 }, { "loss_action": 0.026071563363075256, "loss_total": 0.026071563363075256, "step": 19970 }, { "grad_norm": 0.4382055699825287, "learning_rate": 9.399020321301294e-05, "loss": 0.0213, "step": 19980 }, { "loss_action": 0.02350618690252304, "loss_total": 0.02350618690252304, "step": 19980 }, { "grad_norm": 0.37679946422576904, "learning_rate": 9.398234126189234e-05, "loss": 0.021, "step": 19990 }, { "loss_action": 0.018843960016965866, "loss_total": 0.018843960016965866, "step": 19990 }, { "grad_norm": 0.34131091833114624, "learning_rate": 9.397447450092902e-05, "loss": 0.0201, "step": 20000 }, { "loss_action": 0.016622992232441902, "loss_total": 0.016622992232441902, "step": 20000 }, { "grad_norm": 0.37347063422203064, "learning_rate": 9.39666029309833e-05, "loss": 0.0191, "step": 20010 }, { "loss_action": 0.022522829473018646, "loss_total": 0.022522829473018646, "step": 20010 }, { "grad_norm": 0.39576950669288635, "learning_rate": 9.395872655291596e-05, "loss": 0.0219, "step": 20020 }, { "loss_action": 0.02195587381720543, "loss_total": 0.02195587381720543, "step": 20020 }, { "grad_norm": 0.3593807518482208, "learning_rate": 9.395084536758838e-05, "loss": 0.0192, "step": 20030 }, { "loss_action": 0.02669544145464897, "loss_total": 0.02669544145464897, "step": 20030 }, { "grad_norm": 0.4214026629924774, "learning_rate": 9.394295937586243e-05, "loss": 0.0227, "step": 20040 }, { "loss_action": 0.021516485139727592, "loss_total": 0.021516485139727592, "step": 20040 }, { "grad_norm": 0.5278917551040649, "learning_rate": 9.393506857860052e-05, "loss": 0.0211, "step": 20050 }, { "loss_action": 0.02029327303171158, "loss_total": 0.02029327303171158, "step": 20050 }, { "grad_norm": 0.4264228343963623, "learning_rate": 9.392717297666555e-05, "loss": 0.0196, "step": 20060 }, { "loss_action": 0.020420683547854424, "loss_total": 0.020420683547854424, "step": 20060 }, { "grad_norm": 0.2704625129699707, "learning_rate": 9.391927257092101e-05, "loss": 0.0203, "step": 20070 }, { "loss_action": 0.01848152093589306, "loss_total": 0.01848152093589306, "step": 20070 }, { "grad_norm": 0.5342222452163696, "learning_rate": 9.391136736223085e-05, "loss": 0.0207, "step": 20080 }, { "loss_action": 0.014510748907923698, "loss_total": 0.014510748907923698, "step": 20080 }, { "grad_norm": 0.3145099878311157, "learning_rate": 9.390345735145956e-05, "loss": 0.0184, "step": 20090 }, { "loss_action": 0.024730157107114792, "loss_total": 0.024730157107114792, "step": 20090 }, { "grad_norm": 0.3795829713344574, "learning_rate": 9.389554253947219e-05, "loss": 0.0207, "step": 20100 }, { "loss_action": 0.019000019878149033, "loss_total": 0.019000019878149033, "step": 20100 }, { "grad_norm": 0.4672604203224182, "learning_rate": 9.388762292713428e-05, "loss": 0.0203, "step": 20110 }, { "loss_action": 0.02536805160343647, "loss_total": 0.02536805160343647, "step": 20110 }, { "grad_norm": 0.35444337129592896, "learning_rate": 9.38796985153119e-05, "loss": 0.02, "step": 20120 }, { "loss_action": 0.020189236849546432, "loss_total": 0.020189236849546432, "step": 20120 }, { "grad_norm": 0.4680442214012146, "learning_rate": 9.387176930487169e-05, "loss": 0.0211, "step": 20130 }, { "loss_action": 0.016419578343629837, "loss_total": 0.016419578343629837, "step": 20130 }, { "grad_norm": 0.5082448720932007, "learning_rate": 9.386383529668072e-05, "loss": 0.0192, "step": 20140 }, { "loss_action": 0.019588951021432877, "loss_total": 0.019588951021432877, "step": 20140 }, { "grad_norm": 0.34010472893714905, "learning_rate": 9.385589649160669e-05, "loss": 0.0224, "step": 20150 }, { "loss_action": 0.024474309757351875, "loss_total": 0.024474309757351875, "step": 20150 }, { "grad_norm": 0.4716677963733673, "learning_rate": 9.384795289051775e-05, "loss": 0.0269, "step": 20160 }, { "loss_action": 0.02142486162483692, "loss_total": 0.02142486162483692, "step": 20160 }, { "grad_norm": 0.42164796590805054, "learning_rate": 9.384000449428261e-05, "loss": 0.0204, "step": 20170 }, { "loss_action": 0.015071743167936802, "loss_total": 0.015071743167936802, "step": 20170 }, { "grad_norm": 0.445390522480011, "learning_rate": 9.383205130377048e-05, "loss": 0.0202, "step": 20180 }, { "loss_action": 0.02050548978149891, "loss_total": 0.02050548978149891, "step": 20180 }, { "grad_norm": 0.3698902428150177, "learning_rate": 9.382409331985114e-05, "loss": 0.023, "step": 20190 }, { "loss_action": 0.023265620693564415, "loss_total": 0.023265620693564415, "step": 20190 }, { "grad_norm": 0.49209073185920715, "learning_rate": 9.381613054339482e-05, "loss": 0.022, "step": 20200 }, { "loss_action": 0.02237292379140854, "loss_total": 0.02237292379140854, "step": 20200 }, { "grad_norm": 0.46461617946624756, "learning_rate": 9.380816297527235e-05, "loss": 0.0222, "step": 20210 }, { "loss_action": 0.025039585307240486, "loss_total": 0.025039585307240486, "step": 20210 }, { "grad_norm": 0.5910293459892273, "learning_rate": 9.380019061635506e-05, "loss": 0.024, "step": 20220 }, { "loss_action": 0.026099644601345062, "loss_total": 0.026099644601345062, "step": 20220 }, { "grad_norm": 0.38809090852737427, "learning_rate": 9.379221346751474e-05, "loss": 0.0234, "step": 20230 }, { "loss_action": 0.01682811975479126, "loss_total": 0.01682811975479126, "step": 20230 }, { "grad_norm": 0.5828864574432373, "learning_rate": 9.378423152962382e-05, "loss": 0.0248, "step": 20240 }, { "loss_action": 0.023643486201763153, "loss_total": 0.023643486201763153, "step": 20240 }, { "grad_norm": 0.3803243637084961, "learning_rate": 9.377624480355517e-05, "loss": 0.0208, "step": 20250 }, { "loss_action": 0.02321583405137062, "loss_total": 0.02321583405137062, "step": 20250 }, { "grad_norm": 0.3768640458583832, "learning_rate": 9.376825329018219e-05, "loss": 0.0231, "step": 20260 }, { "loss_action": 0.018981555476784706, "loss_total": 0.018981555476784706, "step": 20260 }, { "grad_norm": 0.4444495141506195, "learning_rate": 9.376025699037884e-05, "loss": 0.0208, "step": 20270 }, { "loss_action": 0.02233092673122883, "loss_total": 0.02233092673122883, "step": 20270 }, { "grad_norm": 0.39230677485466003, "learning_rate": 9.37522559050196e-05, "loss": 0.0188, "step": 20280 }, { "loss_action": 0.018832191824913025, "loss_total": 0.018832191824913025, "step": 20280 }, { "grad_norm": 0.36523276567459106, "learning_rate": 9.37442500349794e-05, "loss": 0.0198, "step": 20290 }, { "loss_action": 0.018210457637906075, "loss_total": 0.018210457637906075, "step": 20290 }, { "grad_norm": 0.41385775804519653, "learning_rate": 9.373623938113381e-05, "loss": 0.0205, "step": 20300 }, { "loss_action": 0.022818906232714653, "loss_total": 0.022818906232714653, "step": 20300 }, { "grad_norm": 0.46643105149269104, "learning_rate": 9.372822394435883e-05, "loss": 0.0229, "step": 20310 }, { "loss_action": 0.027340518310666084, "loss_total": 0.027340518310666084, "step": 20310 }, { "grad_norm": 0.3592108190059662, "learning_rate": 9.372020372553102e-05, "loss": 0.0198, "step": 20320 }, { "loss_action": 0.016643358394503593, "loss_total": 0.016643358394503593, "step": 20320 }, { "grad_norm": 0.4730866253376007, "learning_rate": 9.371217872552746e-05, "loss": 0.0201, "step": 20330 }, { "loss_action": 0.018538823351264, "loss_total": 0.018538823351264, "step": 20330 }, { "grad_norm": 0.34174370765686035, "learning_rate": 9.370414894522576e-05, "loss": 0.0191, "step": 20340 }, { "loss_action": 0.021207179874181747, "loss_total": 0.021207179874181747, "step": 20340 }, { "grad_norm": 0.3250425457954407, "learning_rate": 9.369611438550406e-05, "loss": 0.0199, "step": 20350 }, { "loss_action": 0.022580305114388466, "loss_total": 0.022580305114388466, "step": 20350 }, { "grad_norm": 0.334138959646225, "learning_rate": 9.368807504724095e-05, "loss": 0.0193, "step": 20360 }, { "loss_action": 0.018795115873217583, "loss_total": 0.018795115873217583, "step": 20360 }, { "grad_norm": 0.34445545077323914, "learning_rate": 9.368003093131565e-05, "loss": 0.0199, "step": 20370 }, { "loss_action": 0.023436060175299644, "loss_total": 0.023436060175299644, "step": 20370 }, { "grad_norm": 0.41961100697517395, "learning_rate": 9.367198203860785e-05, "loss": 0.021, "step": 20380 }, { "loss_action": 0.016999205574393272, "loss_total": 0.016999205574393272, "step": 20380 }, { "grad_norm": 0.3152775168418884, "learning_rate": 9.366392836999774e-05, "loss": 0.0189, "step": 20390 }, { "loss_action": 0.017321811988949776, "loss_total": 0.017321811988949776, "step": 20390 }, { "grad_norm": 0.36073142290115356, "learning_rate": 9.365586992636607e-05, "loss": 0.0174, "step": 20400 }, { "loss_action": 0.017751075327396393, "loss_total": 0.017751075327396393, "step": 20400 }, { "grad_norm": 0.39601829648017883, "learning_rate": 9.364780670859412e-05, "loss": 0.0184, "step": 20410 }, { "loss_action": 0.019370105117559433, "loss_total": 0.019370105117559433, "step": 20410 }, { "grad_norm": 0.35267072916030884, "learning_rate": 9.363973871756364e-05, "loss": 0.0195, "step": 20420 }, { "loss_action": 0.015437472611665726, "loss_total": 0.015437472611665726, "step": 20420 }, { "grad_norm": 0.38372865319252014, "learning_rate": 9.363166595415696e-05, "loss": 0.018, "step": 20430 }, { "loss_action": 0.019758708775043488, "loss_total": 0.019758708775043488, "step": 20430 }, { "grad_norm": 0.34893766045570374, "learning_rate": 9.362358841925686e-05, "loss": 0.0191, "step": 20440 }, { "loss_action": 0.0195136908441782, "loss_total": 0.0195136908441782, "step": 20440 }, { "grad_norm": 0.3733380138874054, "learning_rate": 9.361550611374674e-05, "loss": 0.0183, "step": 20450 }, { "loss_action": 0.021886751055717468, "loss_total": 0.021886751055717468, "step": 20450 }, { "grad_norm": 0.38088831305503845, "learning_rate": 9.360741903851043e-05, "loss": 0.0182, "step": 20460 }, { "loss_action": 0.020707862451672554, "loss_total": 0.020707862451672554, "step": 20460 }, { "grad_norm": 0.37499287724494934, "learning_rate": 9.359932719443236e-05, "loss": 0.0191, "step": 20470 }, { "loss_action": 0.02614053152501583, "loss_total": 0.02614053152501583, "step": 20470 }, { "grad_norm": 0.3903651833534241, "learning_rate": 9.35912305823974e-05, "loss": 0.021, "step": 20480 }, { "loss_action": 0.02166132628917694, "loss_total": 0.02166132628917694, "step": 20480 }, { "grad_norm": 0.3982967138290405, "learning_rate": 9.358312920329101e-05, "loss": 0.0209, "step": 20490 }, { "loss_action": 0.024998338893055916, "loss_total": 0.024998338893055916, "step": 20490 }, { "grad_norm": 0.37431132793426514, "learning_rate": 9.357502305799914e-05, "loss": 0.02, "step": 20500 }, { "loss_action": 0.01723463088274002, "loss_total": 0.01723463088274002, "step": 20500 }, { "grad_norm": 0.30476292967796326, "learning_rate": 9.356691214740824e-05, "loss": 0.0188, "step": 20510 }, { "loss_action": 0.029539285227656364, "loss_total": 0.029539285227656364, "step": 20510 }, { "grad_norm": 0.35745829343795776, "learning_rate": 9.355879647240535e-05, "loss": 0.0211, "step": 20520 }, { "loss_action": 0.021841419860720634, "loss_total": 0.021841419860720634, "step": 20520 }, { "grad_norm": 0.35007444024086, "learning_rate": 9.355067603387798e-05, "loss": 0.0198, "step": 20530 }, { "loss_action": 0.019456960260868073, "loss_total": 0.019456960260868073, "step": 20530 }, { "grad_norm": 0.28127583861351013, "learning_rate": 9.354255083271412e-05, "loss": 0.018, "step": 20540 }, { "loss_action": 0.017920777201652527, "loss_total": 0.017920777201652527, "step": 20540 }, { "grad_norm": 0.4596196115016937, "learning_rate": 9.353442086980239e-05, "loss": 0.0182, "step": 20550 }, { "loss_action": 0.02027522586286068, "loss_total": 0.02027522586286068, "step": 20550 }, { "grad_norm": 0.48604077100753784, "learning_rate": 9.352628614603185e-05, "loss": 0.0208, "step": 20560 }, { "loss_action": 0.02474428527057171, "loss_total": 0.02474428527057171, "step": 20560 }, { "grad_norm": 0.4363443851470947, "learning_rate": 9.351814666229209e-05, "loss": 0.0191, "step": 20570 }, { "loss_action": 0.0167809147387743, "loss_total": 0.0167809147387743, "step": 20570 }, { "grad_norm": 0.4331035614013672, "learning_rate": 9.351000241947324e-05, "loss": 0.0192, "step": 20580 }, { "loss_action": 0.0140750827267766, "loss_total": 0.0140750827267766, "step": 20580 }, { "grad_norm": 0.4154784381389618, "learning_rate": 9.350185341846594e-05, "loss": 0.0198, "step": 20590 }, { "loss_action": 0.016015734523534775, "loss_total": 0.016015734523534775, "step": 20590 }, { "grad_norm": 0.3578287661075592, "learning_rate": 9.349369966016134e-05, "loss": 0.0181, "step": 20600 }, { "loss_action": 0.016570422798395157, "loss_total": 0.016570422798395157, "step": 20600 }, { "grad_norm": 0.48064330220222473, "learning_rate": 9.348554114545117e-05, "loss": 0.0196, "step": 20610 }, { "loss_action": 0.018428592011332512, "loss_total": 0.018428592011332512, "step": 20610 }, { "grad_norm": 0.4017678499221802, "learning_rate": 9.347737787522758e-05, "loss": 0.0181, "step": 20620 }, { "loss_action": 0.017573418095707893, "loss_total": 0.017573418095707893, "step": 20620 }, { "grad_norm": 0.51425701379776, "learning_rate": 9.346920985038332e-05, "loss": 0.019, "step": 20630 }, { "loss_action": 0.01900392770767212, "loss_total": 0.01900392770767212, "step": 20630 }, { "grad_norm": 0.3286152184009552, "learning_rate": 9.346103707181162e-05, "loss": 0.0194, "step": 20640 }, { "loss_action": 0.019673200324177742, "loss_total": 0.019673200324177742, "step": 20640 }, { "grad_norm": 0.41119155287742615, "learning_rate": 9.345285954040626e-05, "loss": 0.0207, "step": 20650 }, { "loss_action": 0.020544104278087616, "loss_total": 0.020544104278087616, "step": 20650 }, { "grad_norm": 0.31709498167037964, "learning_rate": 9.34446772570615e-05, "loss": 0.0194, "step": 20660 }, { "loss_action": 0.024968162178993225, "loss_total": 0.024968162178993225, "step": 20660 }, { "grad_norm": 0.45134228467941284, "learning_rate": 9.343649022267214e-05, "loss": 0.0198, "step": 20670 }, { "loss_action": 0.012277740985155106, "loss_total": 0.012277740985155106, "step": 20670 }, { "grad_norm": 0.3908030390739441, "learning_rate": 9.342829843813353e-05, "loss": 0.0196, "step": 20680 }, { "loss_action": 0.01877216435968876, "loss_total": 0.01877216435968876, "step": 20680 }, { "grad_norm": 0.38889259099960327, "learning_rate": 9.342010190434149e-05, "loss": 0.0199, "step": 20690 }, { "loss_action": 0.030932016670703888, "loss_total": 0.030932016670703888, "step": 20690 }, { "grad_norm": 0.3651333749294281, "learning_rate": 9.34119006221924e-05, "loss": 0.0216, "step": 20700 }, { "loss_action": 0.016469232738018036, "loss_total": 0.016469232738018036, "step": 20700 }, { "grad_norm": 0.4289662837982178, "learning_rate": 9.340369459258313e-05, "loss": 0.0184, "step": 20710 }, { "loss_action": 0.018681375309824944, "loss_total": 0.018681375309824944, "step": 20710 }, { "grad_norm": 0.36169376969337463, "learning_rate": 9.339548381641106e-05, "loss": 0.0218, "step": 20720 }, { "loss_action": 0.03016503155231476, "loss_total": 0.03016503155231476, "step": 20720 }, { "grad_norm": 0.3683370351791382, "learning_rate": 9.338726829457413e-05, "loss": 0.0199, "step": 20730 }, { "loss_action": 0.030156059190630913, "loss_total": 0.030156059190630913, "step": 20730 }, { "grad_norm": 0.3383820056915283, "learning_rate": 9.337904802797078e-05, "loss": 0.0202, "step": 20740 }, { "loss_action": 0.017725521698594093, "loss_total": 0.017725521698594093, "step": 20740 }, { "grad_norm": 0.3339739441871643, "learning_rate": 9.337082301749993e-05, "loss": 0.017, "step": 20750 }, { "loss_action": 0.016555706039071083, "loss_total": 0.016555706039071083, "step": 20750 }, { "grad_norm": 0.43037694692611694, "learning_rate": 9.336259326406109e-05, "loss": 0.0186, "step": 20760 }, { "loss_action": 0.020162202417850494, "loss_total": 0.020162202417850494, "step": 20760 }, { "grad_norm": 0.3648868203163147, "learning_rate": 9.335435876855427e-05, "loss": 0.016, "step": 20770 }, { "loss_action": 0.013787181116640568, "loss_total": 0.013787181116640568, "step": 20770 }, { "grad_norm": 0.3195021152496338, "learning_rate": 9.334611953187994e-05, "loss": 0.0175, "step": 20780 }, { "loss_action": 0.019161880016326904, "loss_total": 0.019161880016326904, "step": 20780 }, { "grad_norm": 0.3055669963359833, "learning_rate": 9.333787555493914e-05, "loss": 0.0177, "step": 20790 }, { "loss_action": 0.016587242484092712, "loss_total": 0.016587242484092712, "step": 20790 }, { "grad_norm": 0.2843208611011505, "learning_rate": 9.332962683863345e-05, "loss": 0.0174, "step": 20800 }, { "loss_action": 0.02191738784313202, "loss_total": 0.02191738784313202, "step": 20800 }, { "grad_norm": 0.37032338976860046, "learning_rate": 9.332137338386489e-05, "loss": 0.0174, "step": 20810 }, { "loss_action": 0.024755017831921577, "loss_total": 0.024755017831921577, "step": 20810 }, { "grad_norm": 0.4047810435295105, "learning_rate": 9.33131151915361e-05, "loss": 0.0201, "step": 20820 }, { "loss_action": 0.014217420481145382, "loss_total": 0.014217420481145382, "step": 20820 }, { "grad_norm": 0.37656575441360474, "learning_rate": 9.330485226255012e-05, "loss": 0.0174, "step": 20830 }, { "loss_action": 0.012957443483173847, "loss_total": 0.012957443483173847, "step": 20830 }, { "grad_norm": 0.43441256880760193, "learning_rate": 9.329658459781061e-05, "loss": 0.0193, "step": 20840 }, { "loss_action": 0.01586555689573288, "loss_total": 0.01586555689573288, "step": 20840 }, { "grad_norm": 0.3984034061431885, "learning_rate": 9.328831219822172e-05, "loss": 0.0199, "step": 20850 }, { "loss_action": 0.014804988168179989, "loss_total": 0.014804988168179989, "step": 20850 }, { "grad_norm": 0.271588534116745, "learning_rate": 9.328003506468808e-05, "loss": 0.017, "step": 20860 }, { "loss_action": 0.029759012162685394, "loss_total": 0.029759012162685394, "step": 20860 }, { "grad_norm": 0.32449671626091003, "learning_rate": 9.327175319811488e-05, "loss": 0.0206, "step": 20870 }, { "loss_action": 0.018310096114873886, "loss_total": 0.018310096114873886, "step": 20870 }, { "grad_norm": 0.3105047345161438, "learning_rate": 9.326346659940781e-05, "loss": 0.0202, "step": 20880 }, { "loss_action": 0.013519992120563984, "loss_total": 0.013519992120563984, "step": 20880 }, { "grad_norm": 0.3755249083042145, "learning_rate": 9.325517526947308e-05, "loss": 0.0193, "step": 20890 }, { "loss_action": 0.01638014428317547, "loss_total": 0.01638014428317547, "step": 20890 }, { "grad_norm": 0.41090694069862366, "learning_rate": 9.32468792092174e-05, "loss": 0.0167, "step": 20900 }, { "loss_action": 0.026324598118662834, "loss_total": 0.026324598118662834, "step": 20900 }, { "grad_norm": 0.3726000487804413, "learning_rate": 9.323857841954803e-05, "loss": 0.0184, "step": 20910 }, { "loss_action": 0.02108483575284481, "loss_total": 0.02108483575284481, "step": 20910 }, { "grad_norm": 0.42166978120803833, "learning_rate": 9.323027290137276e-05, "loss": 0.022, "step": 20920 }, { "loss_action": 0.030298098921775818, "loss_total": 0.030298098921775818, "step": 20920 }, { "grad_norm": 0.47724246978759766, "learning_rate": 9.322196265559981e-05, "loss": 0.0198, "step": 20930 }, { "loss_action": 0.017611172050237656, "loss_total": 0.017611172050237656, "step": 20930 }, { "grad_norm": 0.41434887051582336, "learning_rate": 9.321364768313803e-05, "loss": 0.0187, "step": 20940 }, { "loss_action": 0.02708747237920761, "loss_total": 0.02708747237920761, "step": 20940 }, { "grad_norm": 0.46425455808639526, "learning_rate": 9.32053279848967e-05, "loss": 0.0201, "step": 20950 }, { "loss_action": 0.015907468274235725, "loss_total": 0.015907468274235725, "step": 20950 }, { "grad_norm": 0.31813594698905945, "learning_rate": 9.319700356178567e-05, "loss": 0.0184, "step": 20960 }, { "loss_action": 0.012491583824157715, "loss_total": 0.012491583824157715, "step": 20960 }, { "grad_norm": 0.3260173797607422, "learning_rate": 9.318867441471527e-05, "loss": 0.0175, "step": 20970 }, { "loss_action": 0.015623158775269985, "loss_total": 0.015623158775269985, "step": 20970 }, { "grad_norm": 0.38052788376808167, "learning_rate": 9.318034054459637e-05, "loss": 0.0193, "step": 20980 }, { "loss_action": 0.02107916586101055, "loss_total": 0.02107916586101055, "step": 20980 }, { "grad_norm": 0.31470751762390137, "learning_rate": 9.317200195234034e-05, "loss": 0.0191, "step": 20990 }, { "loss_action": 0.015465487726032734, "loss_total": 0.015465487726032734, "step": 20990 }, { "grad_norm": 0.3470635414123535, "learning_rate": 9.316365863885909e-05, "loss": 0.0178, "step": 21000 }, { "loss_action": 0.017099887132644653, "loss_total": 0.017099887132644653, "step": 21000 }, { "grad_norm": 0.30949679017066956, "learning_rate": 9.315531060506502e-05, "loss": 0.0175, "step": 21010 }, { "loss_action": 0.016931960359215736, "loss_total": 0.016931960359215736, "step": 21010 }, { "grad_norm": 0.364281564950943, "learning_rate": 9.314695785187108e-05, "loss": 0.0148, "step": 21020 }, { "loss_action": 0.014193732291460037, "loss_total": 0.014193732291460037, "step": 21020 }, { "grad_norm": 0.3628770112991333, "learning_rate": 9.313860038019069e-05, "loss": 0.0183, "step": 21030 }, { "loss_action": 0.02358684316277504, "loss_total": 0.02358684316277504, "step": 21030 }, { "grad_norm": 0.4734603464603424, "learning_rate": 9.313023819093782e-05, "loss": 0.024, "step": 21040 }, { "loss_action": 0.020644674077630043, "loss_total": 0.020644674077630043, "step": 21040 }, { "grad_norm": 0.5428906679153442, "learning_rate": 9.312187128502695e-05, "loss": 0.0202, "step": 21050 }, { "loss_action": 0.02527364157140255, "loss_total": 0.02527364157140255, "step": 21050 }, { "grad_norm": 0.6368829011917114, "learning_rate": 9.311349966337307e-05, "loss": 0.0227, "step": 21060 }, { "loss_action": 0.017704298719763756, "loss_total": 0.017704298719763756, "step": 21060 }, { "grad_norm": 0.3433030843734741, "learning_rate": 9.310512332689169e-05, "loss": 0.0193, "step": 21070 }, { "loss_action": 0.015329762361943722, "loss_total": 0.015329762361943722, "step": 21070 }, { "grad_norm": 0.4475559890270233, "learning_rate": 9.309674227649883e-05, "loss": 0.0211, "step": 21080 }, { "loss_action": 0.018348798155784607, "loss_total": 0.018348798155784607, "step": 21080 }, { "grad_norm": 0.3530745506286621, "learning_rate": 9.308835651311103e-05, "loss": 0.0209, "step": 21090 }, { "loss_action": 0.019602535292506218, "loss_total": 0.019602535292506218, "step": 21090 }, { "grad_norm": 0.4370492994785309, "learning_rate": 9.307996603764533e-05, "loss": 0.0184, "step": 21100 }, { "loss_action": 0.019224347546696663, "loss_total": 0.019224347546696663, "step": 21100 }, { "grad_norm": 0.28613367676734924, "learning_rate": 9.307157085101932e-05, "loss": 0.0173, "step": 21110 }, { "loss_action": 0.02602546289563179, "loss_total": 0.02602546289563179, "step": 21110 }, { "grad_norm": 0.37646326422691345, "learning_rate": 9.306317095415109e-05, "loss": 0.0191, "step": 21120 }, { "loss_action": 0.02048674039542675, "loss_total": 0.02048674039542675, "step": 21120 }, { "grad_norm": 0.43953782320022583, "learning_rate": 9.305476634795922e-05, "loss": 0.0191, "step": 21130 }, { "loss_action": 0.020134832710027695, "loss_total": 0.020134832710027695, "step": 21130 }, { "grad_norm": 0.4481091797351837, "learning_rate": 9.304635703336284e-05, "loss": 0.0182, "step": 21140 }, { "loss_action": 0.01843879371881485, "loss_total": 0.01843879371881485, "step": 21140 }, { "grad_norm": 0.342988520860672, "learning_rate": 9.303794301128157e-05, "loss": 0.0185, "step": 21150 }, { "loss_action": 0.01694355718791485, "loss_total": 0.01694355718791485, "step": 21150 }, { "grad_norm": 0.36428147554397583, "learning_rate": 9.302952428263555e-05, "loss": 0.0207, "step": 21160 }, { "loss_action": 0.018712151795625687, "loss_total": 0.018712151795625687, "step": 21160 }, { "grad_norm": 0.29333409667015076, "learning_rate": 9.302110084834545e-05, "loss": 0.0183, "step": 21170 }, { "loss_action": 0.01608363166451454, "loss_total": 0.01608363166451454, "step": 21170 }, { "grad_norm": 0.350776731967926, "learning_rate": 9.301267270933245e-05, "loss": 0.0198, "step": 21180 }, { "loss_action": 0.01883106678724289, "loss_total": 0.01883106678724289, "step": 21180 }, { "grad_norm": 0.4370870888233185, "learning_rate": 9.300423986651823e-05, "loss": 0.0198, "step": 21190 }, { "loss_action": 0.01554868370294571, "loss_total": 0.01554868370294571, "step": 21190 }, { "grad_norm": 0.3514333665370941, "learning_rate": 9.299580232082501e-05, "loss": 0.0185, "step": 21200 }, { "loss_action": 0.018420660868287086, "loss_total": 0.018420660868287086, "step": 21200 }, { "grad_norm": 0.4129759669303894, "learning_rate": 9.298736007317547e-05, "loss": 0.0174, "step": 21210 }, { "loss_action": 0.027217604219913483, "loss_total": 0.027217604219913483, "step": 21210 }, { "grad_norm": 0.35111379623413086, "learning_rate": 9.297891312449288e-05, "loss": 0.0191, "step": 21220 }, { "loss_action": 0.01435758825391531, "loss_total": 0.01435758825391531, "step": 21220 }, { "grad_norm": 0.4307391941547394, "learning_rate": 9.297046147570094e-05, "loss": 0.0167, "step": 21230 }, { "loss_action": 0.019272204488515854, "loss_total": 0.019272204488515854, "step": 21230 }, { "grad_norm": 0.337022602558136, "learning_rate": 9.296200512772396e-05, "loss": 0.0189, "step": 21240 }, { "loss_action": 0.01474799495190382, "loss_total": 0.01474799495190382, "step": 21240 }, { "grad_norm": 0.42560505867004395, "learning_rate": 9.295354408148668e-05, "loss": 0.0184, "step": 21250 }, { "loss_action": 0.0206094142049551, "loss_total": 0.0206094142049551, "step": 21250 }, { "grad_norm": 0.49605005979537964, "learning_rate": 9.294507833791441e-05, "loss": 0.0187, "step": 21260 }, { "loss_action": 0.0178990475833416, "loss_total": 0.0178990475833416, "step": 21260 }, { "grad_norm": 0.32907289266586304, "learning_rate": 9.293660789793295e-05, "loss": 0.0196, "step": 21270 }, { "loss_action": 0.020224522799253464, "loss_total": 0.020224522799253464, "step": 21270 }, { "grad_norm": 0.35961008071899414, "learning_rate": 9.292813276246858e-05, "loss": 0.0172, "step": 21280 }, { "loss_action": 0.013836591504514217, "loss_total": 0.013836591504514217, "step": 21280 }, { "grad_norm": 0.35345807671546936, "learning_rate": 9.291965293244816e-05, "loss": 0.018, "step": 21290 }, { "loss_action": 0.015889104455709457, "loss_total": 0.015889104455709457, "step": 21290 }, { "grad_norm": 0.3562120199203491, "learning_rate": 9.291116840879904e-05, "loss": 0.0168, "step": 21300 }, { "loss_action": 0.01749248243868351, "loss_total": 0.01749248243868351, "step": 21300 }, { "grad_norm": 0.4164496660232544, "learning_rate": 9.290267919244904e-05, "loss": 0.0165, "step": 21310 }, { "loss_action": 0.01917875185608864, "loss_total": 0.01917875185608864, "step": 21310 }, { "grad_norm": 0.35640475153923035, "learning_rate": 9.289418528432655e-05, "loss": 0.0189, "step": 21320 }, { "loss_action": 0.018321769312024117, "loss_total": 0.018321769312024117, "step": 21320 }, { "grad_norm": 0.38035696744918823, "learning_rate": 9.288568668536045e-05, "loss": 0.02, "step": 21330 }, { "loss_action": 0.02424238994717598, "loss_total": 0.02424238994717598, "step": 21330 }, { "grad_norm": 0.29212430119514465, "learning_rate": 9.287718339648013e-05, "loss": 0.0196, "step": 21340 }, { "loss_action": 0.018556153401732445, "loss_total": 0.018556153401732445, "step": 21340 }, { "grad_norm": 0.36555206775665283, "learning_rate": 9.28686754186155e-05, "loss": 0.0182, "step": 21350 }, { "loss_action": 0.02371501922607422, "loss_total": 0.02371501922607422, "step": 21350 }, { "grad_norm": 0.36114609241485596, "learning_rate": 9.286016275269698e-05, "loss": 0.0185, "step": 21360 }, { "loss_action": 0.0175970196723938, "loss_total": 0.0175970196723938, "step": 21360 }, { "grad_norm": 0.35129639506340027, "learning_rate": 9.285164539965551e-05, "loss": 0.0172, "step": 21370 }, { "loss_action": 0.0186130553483963, "loss_total": 0.0186130553483963, "step": 21370 }, { "grad_norm": 0.3589678406715393, "learning_rate": 9.284312336042251e-05, "loss": 0.0186, "step": 21380 }, { "loss_action": 0.017028190195560455, "loss_total": 0.017028190195560455, "step": 21380 }, { "grad_norm": 0.3767962157726288, "learning_rate": 9.283459663592996e-05, "loss": 0.0203, "step": 21390 }, { "loss_action": 0.02083749696612358, "loss_total": 0.02083749696612358, "step": 21390 }, { "grad_norm": 0.3079175055027008, "learning_rate": 9.282606522711033e-05, "loss": 0.0183, "step": 21400 }, { "loss_action": 0.017433123663067818, "loss_total": 0.017433123663067818, "step": 21400 }, { "grad_norm": 0.495320588350296, "learning_rate": 9.281752913489657e-05, "loss": 0.0196, "step": 21410 }, { "loss_action": 0.01692354865372181, "loss_total": 0.01692354865372181, "step": 21410 }, { "grad_norm": 0.5204752087593079, "learning_rate": 9.280898836022222e-05, "loss": 0.0185, "step": 21420 }, { "loss_action": 0.018989665433764458, "loss_total": 0.018989665433764458, "step": 21420 }, { "grad_norm": 0.2897728681564331, "learning_rate": 9.280044290402126e-05, "loss": 0.0194, "step": 21430 }, { "loss_action": 0.015578393824398518, "loss_total": 0.015578393824398518, "step": 21430 }, { "grad_norm": 0.3955315351486206, "learning_rate": 9.279189276722821e-05, "loss": 0.0188, "step": 21440 }, { "loss_action": 0.01644895039498806, "loss_total": 0.01644895039498806, "step": 21440 }, { "grad_norm": 0.3618307113647461, "learning_rate": 9.278333795077812e-05, "loss": 0.0196, "step": 21450 }, { "loss_action": 0.014551760628819466, "loss_total": 0.014551760628819466, "step": 21450 }, { "grad_norm": 0.3628210723400116, "learning_rate": 9.27747784556065e-05, "loss": 0.0198, "step": 21460 }, { "loss_action": 0.022183367982506752, "loss_total": 0.022183367982506752, "step": 21460 }, { "grad_norm": 0.37851956486701965, "learning_rate": 9.276621428264942e-05, "loss": 0.018, "step": 21470 }, { "loss_action": 0.01979893445968628, "loss_total": 0.01979893445968628, "step": 21470 }, { "grad_norm": 0.33045539259910583, "learning_rate": 9.275764543284345e-05, "loss": 0.0192, "step": 21480 }, { "loss_action": 0.028450656682252884, "loss_total": 0.028450656682252884, "step": 21480 }, { "grad_norm": 0.37115389108657837, "learning_rate": 9.274907190712566e-05, "loss": 0.0195, "step": 21490 }, { "loss_action": 0.01724902354180813, "loss_total": 0.01724902354180813, "step": 21490 }, { "grad_norm": 0.43530815839767456, "learning_rate": 9.274049370643363e-05, "loss": 0.0186, "step": 21500 }, { "loss_action": 0.017153510823845863, "loss_total": 0.017153510823845863, "step": 21500 }, { "grad_norm": 0.46131762862205505, "learning_rate": 9.273191083170547e-05, "loss": 0.0181, "step": 21510 }, { "loss_action": 0.016469698399305344, "loss_total": 0.016469698399305344, "step": 21510 }, { "grad_norm": 0.4563528597354889, "learning_rate": 9.27233232838798e-05, "loss": 0.0178, "step": 21520 }, { "loss_action": 0.016179002821445465, "loss_total": 0.016179002821445465, "step": 21520 }, { "grad_norm": 0.4611559808254242, "learning_rate": 9.27147310638957e-05, "loss": 0.0178, "step": 21530 }, { "loss_action": 0.018659815192222595, "loss_total": 0.018659815192222595, "step": 21530 }, { "grad_norm": 0.3735152781009674, "learning_rate": 9.270613417269286e-05, "loss": 0.0197, "step": 21540 }, { "loss_action": 0.021779092028737068, "loss_total": 0.021779092028737068, "step": 21540 }, { "grad_norm": 0.5248770713806152, "learning_rate": 9.269753261121138e-05, "loss": 0.0191, "step": 21550 }, { "loss_action": 0.017510734498500824, "loss_total": 0.017510734498500824, "step": 21550 }, { "grad_norm": 0.4158843755722046, "learning_rate": 9.268892638039194e-05, "loss": 0.0159, "step": 21560 }, { "loss_action": 0.015386849641799927, "loss_total": 0.015386849641799927, "step": 21560 }, { "grad_norm": 0.3378419876098633, "learning_rate": 9.268031548117569e-05, "loss": 0.0171, "step": 21570 }, { "loss_action": 0.015377636067569256, "loss_total": 0.015377636067569256, "step": 21570 }, { "grad_norm": 0.35767295956611633, "learning_rate": 9.26716999145043e-05, "loss": 0.0186, "step": 21580 }, { "loss_action": 0.0158647820353508, "loss_total": 0.0158647820353508, "step": 21580 }, { "grad_norm": 0.35239285230636597, "learning_rate": 9.266307968131998e-05, "loss": 0.0206, "step": 21590 }, { "loss_action": 0.01560045126825571, "loss_total": 0.01560045126825571, "step": 21590 }, { "grad_norm": 0.3398135304450989, "learning_rate": 9.26544547825654e-05, "loss": 0.018, "step": 21600 }, { "loss_action": 0.01797313243150711, "loss_total": 0.01797313243150711, "step": 21600 }, { "grad_norm": 0.46078941226005554, "learning_rate": 9.264582521918376e-05, "loss": 0.0205, "step": 21610 }, { "loss_action": 0.01668018288910389, "loss_total": 0.01668018288910389, "step": 21610 }, { "grad_norm": 0.3636689782142639, "learning_rate": 9.263719099211881e-05, "loss": 0.0196, "step": 21620 }, { "loss_action": 0.018629632890224457, "loss_total": 0.018629632890224457, "step": 21620 }, { "grad_norm": 0.3271297514438629, "learning_rate": 9.262855210231476e-05, "loss": 0.0194, "step": 21630 }, { "loss_action": 0.023350533097982407, "loss_total": 0.023350533097982407, "step": 21630 }, { "grad_norm": 0.42533543705940247, "learning_rate": 9.261990855071633e-05, "loss": 0.0212, "step": 21640 }, { "loss_action": 0.014088624157011509, "loss_total": 0.014088624157011509, "step": 21640 }, { "grad_norm": 0.44545885920524597, "learning_rate": 9.261126033826878e-05, "loss": 0.0181, "step": 21650 }, { "loss_action": 0.021210046485066414, "loss_total": 0.021210046485066414, "step": 21650 }, { "grad_norm": 0.3951915204524994, "learning_rate": 9.260260746591786e-05, "loss": 0.0192, "step": 21660 }, { "loss_action": 0.019001765176653862, "loss_total": 0.019001765176653862, "step": 21660 }, { "grad_norm": 0.34978026151657104, "learning_rate": 9.259394993460985e-05, "loss": 0.0181, "step": 21670 }, { "loss_action": 0.02254842035472393, "loss_total": 0.02254842035472393, "step": 21670 }, { "grad_norm": 0.360228031873703, "learning_rate": 9.258528774529151e-05, "loss": 0.0193, "step": 21680 }, { "loss_action": 0.021261950954794884, "loss_total": 0.021261950954794884, "step": 21680 }, { "grad_norm": 0.4704018831253052, "learning_rate": 9.257662089891013e-05, "loss": 0.0206, "step": 21690 }, { "loss_action": 0.016453886404633522, "loss_total": 0.016453886404633522, "step": 21690 }, { "grad_norm": 0.3845294415950775, "learning_rate": 9.25679493964135e-05, "loss": 0.0181, "step": 21700 }, { "loss_action": 0.0153042022138834, "loss_total": 0.0153042022138834, "step": 21700 }, { "grad_norm": 0.3613044023513794, "learning_rate": 9.255927323874994e-05, "loss": 0.0176, "step": 21710 }, { "loss_action": 0.01897687092423439, "loss_total": 0.01897687092423439, "step": 21710 }, { "grad_norm": 0.4549090564250946, "learning_rate": 9.255059242686822e-05, "loss": 0.0174, "step": 21720 }, { "loss_action": 0.020012281835079193, "loss_total": 0.020012281835079193, "step": 21720 }, { "grad_norm": 0.3330315053462982, "learning_rate": 9.254190696171769e-05, "loss": 0.0197, "step": 21730 }, { "loss_action": 0.018128879368305206, "loss_total": 0.018128879368305206, "step": 21730 }, { "grad_norm": 0.3162003457546234, "learning_rate": 9.25332168442482e-05, "loss": 0.0177, "step": 21740 }, { "loss_action": 0.012564968317747116, "loss_total": 0.012564968317747116, "step": 21740 }, { "grad_norm": 0.3288878798484802, "learning_rate": 9.252452207541004e-05, "loss": 0.0168, "step": 21750 }, { "loss_action": 0.024321164935827255, "loss_total": 0.024321164935827255, "step": 21750 }, { "grad_norm": 0.4225633144378662, "learning_rate": 9.251582265615409e-05, "loss": 0.0189, "step": 21760 }, { "loss_action": 0.01983857899904251, "loss_total": 0.01983857899904251, "step": 21760 }, { "grad_norm": 0.3501949608325958, "learning_rate": 9.250711858743169e-05, "loss": 0.0185, "step": 21770 }, { "loss_action": 0.020974526181817055, "loss_total": 0.020974526181817055, "step": 21770 }, { "grad_norm": 0.368201345205307, "learning_rate": 9.24984098701947e-05, "loss": 0.02, "step": 21780 }, { "loss_action": 0.02217906340956688, "loss_total": 0.02217906340956688, "step": 21780 }, { "grad_norm": 0.3870978057384491, "learning_rate": 9.248969650539552e-05, "loss": 0.0194, "step": 21790 }, { "loss_action": 0.025889519602060318, "loss_total": 0.025889519602060318, "step": 21790 }, { "grad_norm": 0.45403680205345154, "learning_rate": 9.2480978493987e-05, "loss": 0.0229, "step": 21800 }, { "loss_action": 0.02316318266093731, "loss_total": 0.02316318266093731, "step": 21800 }, { "grad_norm": 0.521742582321167, "learning_rate": 9.247225583692256e-05, "loss": 0.0233, "step": 21810 }, { "loss_action": 0.0238336231559515, "loss_total": 0.0238336231559515, "step": 21810 }, { "grad_norm": 0.37773290276527405, "learning_rate": 9.246352853515607e-05, "loss": 0.0225, "step": 21820 }, { "loss_action": 0.018376115709543228, "loss_total": 0.018376115709543228, "step": 21820 }, { "grad_norm": 0.49199703335762024, "learning_rate": 9.245479658964194e-05, "loss": 0.0218, "step": 21830 }, { "loss_action": 0.015565671026706696, "loss_total": 0.015565671026706696, "step": 21830 }, { "grad_norm": 0.3956824541091919, "learning_rate": 9.244606000133507e-05, "loss": 0.0212, "step": 21840 }, { "loss_action": 0.026746617630124092, "loss_total": 0.026746617630124092, "step": 21840 }, { "grad_norm": 0.42664167284965515, "learning_rate": 9.24373187711909e-05, "loss": 0.0218, "step": 21850 }, { "loss_action": 0.0236592385917902, "loss_total": 0.0236592385917902, "step": 21850 }, { "grad_norm": 0.33434557914733887, "learning_rate": 9.242857290016537e-05, "loss": 0.0201, "step": 21860 }, { "loss_action": 0.015666531398892403, "loss_total": 0.015666531398892403, "step": 21860 }, { "grad_norm": 0.3622773587703705, "learning_rate": 9.241982238921488e-05, "loss": 0.0182, "step": 21870 }, { "loss_action": 0.01953110471367836, "loss_total": 0.01953110471367836, "step": 21870 }, { "grad_norm": 0.31875887513160706, "learning_rate": 9.24110672392964e-05, "loss": 0.0194, "step": 21880 }, { "loss_action": 0.016689909622073174, "loss_total": 0.016689909622073174, "step": 21880 }, { "grad_norm": 0.3493584990501404, "learning_rate": 9.240230745136737e-05, "loss": 0.019, "step": 21890 }, { "loss_action": 0.01790883205831051, "loss_total": 0.01790883205831051, "step": 21890 }, { "grad_norm": 0.3875574469566345, "learning_rate": 9.239354302638575e-05, "loss": 0.0213, "step": 21900 }, { "loss_action": 0.021889211609959602, "loss_total": 0.021889211609959602, "step": 21900 }, { "grad_norm": 0.39233630895614624, "learning_rate": 9.238477396531e-05, "loss": 0.0229, "step": 21910 }, { "loss_action": 0.016248783096671104, "loss_total": 0.016248783096671104, "step": 21910 }, { "grad_norm": 0.43314704298973083, "learning_rate": 9.23760002690991e-05, "loss": 0.0204, "step": 21920 }, { "loss_action": 0.021383898332715034, "loss_total": 0.021383898332715034, "step": 21920 }, { "grad_norm": 0.4076824486255646, "learning_rate": 9.236722193871252e-05, "loss": 0.0203, "step": 21930 }, { "loss_action": 0.016636189073324203, "loss_total": 0.016636189073324203, "step": 21930 }, { "grad_norm": 0.33071011304855347, "learning_rate": 9.235843897511023e-05, "loss": 0.0215, "step": 21940 }, { "loss_action": 0.022056765854358673, "loss_total": 0.022056765854358673, "step": 21940 }, { "grad_norm": 0.7539774775505066, "learning_rate": 9.234965137925276e-05, "loss": 0.0213, "step": 21950 }, { "loss_action": 0.028855465352535248, "loss_total": 0.028855465352535248, "step": 21950 }, { "grad_norm": 0.46457475423812866, "learning_rate": 9.234085915210108e-05, "loss": 0.0248, "step": 21960 }, { "loss_action": 0.034546393901109695, "loss_total": 0.034546393901109695, "step": 21960 }, { "grad_norm": 0.6994200944900513, "learning_rate": 9.23320622946167e-05, "loss": 0.0256, "step": 21970 }, { "loss_action": 0.02557131089270115, "loss_total": 0.02557131089270115, "step": 21970 }, { "grad_norm": 0.5054978728294373, "learning_rate": 9.232326080776163e-05, "loss": 0.0241, "step": 21980 }, { "loss_action": 0.02398640662431717, "loss_total": 0.02398640662431717, "step": 21980 }, { "grad_norm": 0.39560508728027344, "learning_rate": 9.23144546924984e-05, "loss": 0.0256, "step": 21990 }, { "loss_action": 0.023378007113933563, "loss_total": 0.023378007113933563, "step": 21990 }, { "grad_norm": 0.4524804353713989, "learning_rate": 9.230564394979e-05, "loss": 0.0204, "step": 22000 }, { "loss_action": 0.01779547706246376, "loss_total": 0.01779547706246376, "step": 22000 }, { "grad_norm": 0.3569372594356537, "learning_rate": 9.22968285806e-05, "loss": 0.0188, "step": 22010 }, { "loss_action": 0.021670548245310783, "loss_total": 0.021670548245310783, "step": 22010 }, { "grad_norm": 0.3513014316558838, "learning_rate": 9.228800858589242e-05, "loss": 0.0192, "step": 22020 }, { "loss_action": 0.02329065464437008, "loss_total": 0.02329065464437008, "step": 22020 }, { "grad_norm": 0.3564842641353607, "learning_rate": 9.227918396663179e-05, "loss": 0.0191, "step": 22030 }, { "loss_action": 0.015638506039977074, "loss_total": 0.015638506039977074, "step": 22030 }, { "grad_norm": 0.6768895387649536, "learning_rate": 9.227035472378319e-05, "loss": 0.0206, "step": 22040 }, { "loss_action": 0.02451782301068306, "loss_total": 0.02451782301068306, "step": 22040 }, { "grad_norm": 0.6608781218528748, "learning_rate": 9.226152085831213e-05, "loss": 0.0242, "step": 22050 }, { "loss_action": 0.03053450956940651, "loss_total": 0.03053450956940651, "step": 22050 }, { "grad_norm": 0.4670763313770294, "learning_rate": 9.22526823711847e-05, "loss": 0.0261, "step": 22060 }, { "loss_action": 0.02876315824687481, "loss_total": 0.02876315824687481, "step": 22060 }, { "grad_norm": 0.49745190143585205, "learning_rate": 9.224383926336745e-05, "loss": 0.022, "step": 22070 }, { "loss_action": 0.028649810701608658, "loss_total": 0.028649810701608658, "step": 22070 }, { "grad_norm": 0.4184342920780182, "learning_rate": 9.223499153582744e-05, "loss": 0.0227, "step": 22080 }, { "loss_action": 0.02079795114696026, "loss_total": 0.02079795114696026, "step": 22080 }, { "grad_norm": 0.4244753122329712, "learning_rate": 9.222613918953226e-05, "loss": 0.0205, "step": 22090 }, { "loss_action": 0.017171887680888176, "loss_total": 0.017171887680888176, "step": 22090 }, { "grad_norm": 0.32970720529556274, "learning_rate": 9.221728222544999e-05, "loss": 0.0175, "step": 22100 }, { "loss_action": 0.01782367005944252, "loss_total": 0.01782367005944252, "step": 22100 }, { "grad_norm": 0.40663012862205505, "learning_rate": 9.22084206445492e-05, "loss": 0.0199, "step": 22110 }, { "loss_action": 0.019380247220396996, "loss_total": 0.019380247220396996, "step": 22110 }, { "grad_norm": 0.496046245098114, "learning_rate": 9.2199554447799e-05, "loss": 0.0207, "step": 22120 }, { "loss_action": 0.02393881417810917, "loss_total": 0.02393881417810917, "step": 22120 }, { "grad_norm": 0.439264178276062, "learning_rate": 9.219068363616897e-05, "loss": 0.0192, "step": 22130 }, { "loss_action": 0.01869359239935875, "loss_total": 0.01869359239935875, "step": 22130 }, { "grad_norm": 0.4833652675151825, "learning_rate": 9.218180821062919e-05, "loss": 0.0209, "step": 22140 }, { "loss_action": 0.0150382649153471, "loss_total": 0.0150382649153471, "step": 22140 }, { "grad_norm": 0.36042022705078125, "learning_rate": 9.21729281721503e-05, "loss": 0.0177, "step": 22150 }, { "loss_action": 0.015168770216405392, "loss_total": 0.015168770216405392, "step": 22150 }, { "grad_norm": 0.44717544317245483, "learning_rate": 9.216404352170339e-05, "loss": 0.0186, "step": 22160 }, { "loss_action": 0.01794816367328167, "loss_total": 0.01794816367328167, "step": 22160 }, { "grad_norm": 0.4113543629646301, "learning_rate": 9.215515426026007e-05, "loss": 0.0196, "step": 22170 }, { "loss_action": 0.01562572456896305, "loss_total": 0.01562572456896305, "step": 22170 }, { "grad_norm": 0.2902180552482605, "learning_rate": 9.214626038879246e-05, "loss": 0.0187, "step": 22180 }, { "loss_action": 0.018658164888620377, "loss_total": 0.018658164888620377, "step": 22180 }, { "grad_norm": 0.33106547594070435, "learning_rate": 9.21373619082732e-05, "loss": 0.0173, "step": 22190 }, { "loss_action": 0.013818918727338314, "loss_total": 0.013818918727338314, "step": 22190 }, { "grad_norm": 0.3894941806793213, "learning_rate": 9.212845881967535e-05, "loss": 0.0172, "step": 22200 }, { "loss_action": 0.019074320793151855, "loss_total": 0.019074320793151855, "step": 22200 }, { "grad_norm": 0.3498556315898895, "learning_rate": 9.211955112397262e-05, "loss": 0.0178, "step": 22210 }, { "loss_action": 0.022259831428527832, "loss_total": 0.022259831428527832, "step": 22210 }, { "grad_norm": 0.3872512876987457, "learning_rate": 9.211063882213909e-05, "loss": 0.0167, "step": 22220 }, { "loss_action": 0.019988801330327988, "loss_total": 0.019988801330327988, "step": 22220 }, { "grad_norm": 0.33904433250427246, "learning_rate": 9.210172191514942e-05, "loss": 0.0186, "step": 22230 }, { "loss_action": 0.018402837216854095, "loss_total": 0.018402837216854095, "step": 22230 }, { "grad_norm": 0.2959619164466858, "learning_rate": 9.209280040397874e-05, "loss": 0.0182, "step": 22240 }, { "loss_action": 0.018969068303704262, "loss_total": 0.018969068303704262, "step": 22240 }, { "grad_norm": 0.38612785935401917, "learning_rate": 9.208387428960268e-05, "loss": 0.0189, "step": 22250 }, { "loss_action": 0.01843503676354885, "loss_total": 0.01843503676354885, "step": 22250 }, { "grad_norm": 0.5639643669128418, "learning_rate": 9.20749435729974e-05, "loss": 0.0182, "step": 22260 }, { "loss_action": 0.01865011639893055, "loss_total": 0.01865011639893055, "step": 22260 }, { "grad_norm": 0.34598928689956665, "learning_rate": 9.206600825513957e-05, "loss": 0.0218, "step": 22270 }, { "loss_action": 0.021211396902799606, "loss_total": 0.021211396902799606, "step": 22270 }, { "grad_norm": 0.460813045501709, "learning_rate": 9.20570683370063e-05, "loss": 0.02, "step": 22280 }, { "loss_action": 0.022157780826091766, "loss_total": 0.022157780826091766, "step": 22280 }, { "grad_norm": 0.34713396430015564, "learning_rate": 9.204812381957528e-05, "loss": 0.0196, "step": 22290 }, { "loss_action": 0.01743498630821705, "loss_total": 0.01743498630821705, "step": 22290 }, { "grad_norm": 0.3734006881713867, "learning_rate": 9.203917470382465e-05, "loss": 0.0167, "step": 22300 }, { "loss_action": 0.0156903937458992, "loss_total": 0.0156903937458992, "step": 22300 }, { "grad_norm": 0.47523462772369385, "learning_rate": 9.203022099073309e-05, "loss": 0.0189, "step": 22310 }, { "loss_action": 0.016722043976187706, "loss_total": 0.016722043976187706, "step": 22310 }, { "grad_norm": 0.35250988602638245, "learning_rate": 9.202126268127976e-05, "loss": 0.0188, "step": 22320 }, { "loss_action": 0.024794558063149452, "loss_total": 0.024794558063149452, "step": 22320 }, { "grad_norm": 0.35603031516075134, "learning_rate": 9.20122997764443e-05, "loss": 0.0206, "step": 22330 }, { "loss_action": 0.017042245715856552, "loss_total": 0.017042245715856552, "step": 22330 }, { "grad_norm": 0.34439754486083984, "learning_rate": 9.200333227720692e-05, "loss": 0.0201, "step": 22340 }, { "loss_action": 0.026750771328806877, "loss_total": 0.026750771328806877, "step": 22340 }, { "grad_norm": 0.3330468535423279, "learning_rate": 9.199436018454826e-05, "loss": 0.0197, "step": 22350 }, { "loss_action": 0.01871359534561634, "loss_total": 0.01871359534561634, "step": 22350 }, { "grad_norm": 0.4171121418476105, "learning_rate": 9.198538349944952e-05, "loss": 0.0189, "step": 22360 }, { "loss_action": 0.02318108081817627, "loss_total": 0.02318108081817627, "step": 22360 }, { "grad_norm": 0.38145962357521057, "learning_rate": 9.197640222289234e-05, "loss": 0.0192, "step": 22370 }, { "loss_action": 0.016168031841516495, "loss_total": 0.016168031841516495, "step": 22370 }, { "grad_norm": 0.3884977400302887, "learning_rate": 9.196741635585895e-05, "loss": 0.02, "step": 22380 }, { "loss_action": 0.014919962733983994, "loss_total": 0.014919962733983994, "step": 22380 }, { "grad_norm": 0.4670552909374237, "learning_rate": 9.195842589933199e-05, "loss": 0.0201, "step": 22390 }, { "loss_action": 0.024159686639904976, "loss_total": 0.024159686639904976, "step": 22390 }, { "grad_norm": 0.43588849902153015, "learning_rate": 9.194943085429466e-05, "loss": 0.0213, "step": 22400 }, { "loss_action": 0.03782287612557411, "loss_total": 0.03782287612557411, "step": 22400 }, { "grad_norm": 0.41212746500968933, "learning_rate": 9.194043122173065e-05, "loss": 0.0241, "step": 22410 }, { "loss_action": 0.01770125888288021, "loss_total": 0.01770125888288021, "step": 22410 }, { "grad_norm": 0.33519792556762695, "learning_rate": 9.193142700262413e-05, "loss": 0.0189, "step": 22420 }, { "loss_action": 0.019422950223088264, "loss_total": 0.019422950223088264, "step": 22420 }, { "grad_norm": 0.2682434618473053, "learning_rate": 9.192241819795979e-05, "loss": 0.0168, "step": 22430 }, { "loss_action": 0.017694959416985512, "loss_total": 0.017694959416985512, "step": 22430 }, { "grad_norm": 0.36979398131370544, "learning_rate": 9.191340480872284e-05, "loss": 0.0179, "step": 22440 }, { "loss_action": 0.023310063406825066, "loss_total": 0.023310063406825066, "step": 22440 }, { "grad_norm": 0.38327255845069885, "learning_rate": 9.190438683589895e-05, "loss": 0.0205, "step": 22450 }, { "loss_action": 0.017054053023457527, "loss_total": 0.017054053023457527, "step": 22450 }, { "grad_norm": 0.4099646508693695, "learning_rate": 9.189536428047432e-05, "loss": 0.0215, "step": 22460 }, { "loss_action": 0.027509348466992378, "loss_total": 0.027509348466992378, "step": 22460 }, { "grad_norm": 0.40062057971954346, "learning_rate": 9.188633714343564e-05, "loss": 0.0205, "step": 22470 }, { "loss_action": 0.018895285204052925, "loss_total": 0.018895285204052925, "step": 22470 }, { "grad_norm": 0.4025045931339264, "learning_rate": 9.18773054257701e-05, "loss": 0.0204, "step": 22480 }, { "loss_action": 0.01769549399614334, "loss_total": 0.01769549399614334, "step": 22480 }, { "grad_norm": 0.44259679317474365, "learning_rate": 9.18682691284654e-05, "loss": 0.021, "step": 22490 }, { "loss_action": 0.02018515020608902, "loss_total": 0.02018515020608902, "step": 22490 }, { "grad_norm": 0.46057137846946716, "learning_rate": 9.185922825250974e-05, "loss": 0.0231, "step": 22500 }, { "loss_action": 0.023270510137081146, "loss_total": 0.023270510137081146, "step": 22500 }, { "grad_norm": 0.4348312020301819, "learning_rate": 9.185018279889181e-05, "loss": 0.0234, "step": 22510 }, { "loss_action": 0.01675155945122242, "loss_total": 0.01675155945122242, "step": 22510 }, { "grad_norm": 0.42046815156936646, "learning_rate": 9.184113276860082e-05, "loss": 0.0203, "step": 22520 }, { "loss_action": 0.028436006978154182, "loss_total": 0.028436006978154182, "step": 22520 }, { "grad_norm": 0.7356604933738708, "learning_rate": 9.183207816262645e-05, "loss": 0.0241, "step": 22530 }, { "loss_action": 0.021606437861919403, "loss_total": 0.021606437861919403, "step": 22530 }, { "grad_norm": 0.7965004444122314, "learning_rate": 9.182301898195891e-05, "loss": 0.0311, "step": 22540 }, { "loss_action": 0.03218810260295868, "loss_total": 0.03218810260295868, "step": 22540 }, { "grad_norm": 0.5820850133895874, "learning_rate": 9.181395522758889e-05, "loss": 0.0314, "step": 22550 }, { "loss_action": 0.02722233347594738, "loss_total": 0.02722233347594738, "step": 22550 }, { "grad_norm": 0.42165830731391907, "learning_rate": 9.180488690050759e-05, "loss": 0.024, "step": 22560 }, { "loss_action": 0.025352653115987778, "loss_total": 0.025352653115987778, "step": 22560 }, { "grad_norm": 0.34451034665107727, "learning_rate": 9.179581400170671e-05, "loss": 0.0233, "step": 22570 }, { "loss_action": 0.022505642846226692, "loss_total": 0.022505642846226692, "step": 22570 }, { "grad_norm": 0.375870943069458, "learning_rate": 9.178673653217845e-05, "loss": 0.0201, "step": 22580 }, { "loss_action": 0.02542026899755001, "loss_total": 0.02542026899755001, "step": 22580 }, { "grad_norm": 0.43418461084365845, "learning_rate": 9.177765449291551e-05, "loss": 0.0228, "step": 22590 }, { "loss_action": 0.020591983571648598, "loss_total": 0.020591983571648598, "step": 22590 }, { "grad_norm": 0.3704354465007782, "learning_rate": 9.176856788491109e-05, "loss": 0.0217, "step": 22600 }, { "loss_action": 0.02518118917942047, "loss_total": 0.02518118917942047, "step": 22600 }, { "grad_norm": 0.3963457942008972, "learning_rate": 9.175947670915887e-05, "loss": 0.0212, "step": 22610 }, { "loss_action": 0.017102746292948723, "loss_total": 0.017102746292948723, "step": 22610 }, { "grad_norm": 0.37347283959388733, "learning_rate": 9.175038096665309e-05, "loss": 0.0179, "step": 22620 }, { "loss_action": 0.019420340657234192, "loss_total": 0.019420340657234192, "step": 22620 }, { "grad_norm": 0.364840030670166, "learning_rate": 9.17412806583884e-05, "loss": 0.0184, "step": 22630 }, { "loss_action": 0.023205824196338654, "loss_total": 0.023205824196338654, "step": 22630 }, { "grad_norm": 0.4048491418361664, "learning_rate": 9.173217578536002e-05, "loss": 0.0208, "step": 22640 }, { "loss_action": 0.0179306548088789, "loss_total": 0.0179306548088789, "step": 22640 }, { "grad_norm": 0.3818768262863159, "learning_rate": 9.172306634856362e-05, "loss": 0.0192, "step": 22650 }, { "loss_action": 0.018071843311190605, "loss_total": 0.018071843311190605, "step": 22650 }, { "grad_norm": 0.4268866777420044, "learning_rate": 9.171395234899545e-05, "loss": 0.0229, "step": 22660 }, { "loss_action": 0.01865309290587902, "loss_total": 0.01865309290587902, "step": 22660 }, { "grad_norm": 0.37769556045532227, "learning_rate": 9.170483378765214e-05, "loss": 0.0191, "step": 22670 }, { "loss_action": 0.0193395484238863, "loss_total": 0.0193395484238863, "step": 22670 }, { "grad_norm": 0.30229270458221436, "learning_rate": 9.169571066553091e-05, "loss": 0.0179, "step": 22680 }, { "loss_action": 0.02401874028146267, "loss_total": 0.02401874028146267, "step": 22680 }, { "grad_norm": 0.4251458942890167, "learning_rate": 9.168658298362946e-05, "loss": 0.0199, "step": 22690 }, { "loss_action": 0.016650749370455742, "loss_total": 0.016650749370455742, "step": 22690 }, { "grad_norm": 0.34595176577568054, "learning_rate": 9.167745074294598e-05, "loss": 0.0192, "step": 22700 }, { "loss_action": 0.019955208525061607, "loss_total": 0.019955208525061607, "step": 22700 }, { "grad_norm": 0.3854880630970001, "learning_rate": 9.166831394447913e-05, "loss": 0.0199, "step": 22710 }, { "loss_action": 0.016288960352540016, "loss_total": 0.016288960352540016, "step": 22710 }, { "grad_norm": 0.3703548014163971, "learning_rate": 9.165917258922812e-05, "loss": 0.0195, "step": 22720 }, { "loss_action": 0.016098545864224434, "loss_total": 0.016098545864224434, "step": 22720 }, { "grad_norm": 0.4028412401676178, "learning_rate": 9.165002667819262e-05, "loss": 0.0186, "step": 22730 }, { "loss_action": 0.013671555556356907, "loss_total": 0.013671555556356907, "step": 22730 }, { "grad_norm": 0.3178273141384125, "learning_rate": 9.164087621237282e-05, "loss": 0.0198, "step": 22740 }, { "loss_action": 0.020297562703490257, "loss_total": 0.020297562703490257, "step": 22740 }, { "grad_norm": 0.29570069909095764, "learning_rate": 9.163172119276942e-05, "loss": 0.017, "step": 22750 }, { "loss_action": 0.016715683043003082, "loss_total": 0.016715683043003082, "step": 22750 }, { "grad_norm": 0.41507741808891296, "learning_rate": 9.162256162038358e-05, "loss": 0.0202, "step": 22760 }, { "loss_action": 0.02006567269563675, "loss_total": 0.02006567269563675, "step": 22760 }, { "grad_norm": 0.38759490847587585, "learning_rate": 9.161339749621698e-05, "loss": 0.0186, "step": 22770 }, { "loss_action": 0.018252065405249596, "loss_total": 0.018252065405249596, "step": 22770 }, { "grad_norm": 0.3530329465866089, "learning_rate": 9.160422882127177e-05, "loss": 0.0168, "step": 22780 }, { "loss_action": 0.015774931758642197, "loss_total": 0.015774931758642197, "step": 22780 }, { "grad_norm": 0.4014571011066437, "learning_rate": 9.159505559655069e-05, "loss": 0.0173, "step": 22790 }, { "loss_action": 0.020160602405667305, "loss_total": 0.020160602405667305, "step": 22790 }, { "grad_norm": 0.39711233973503113, "learning_rate": 9.158587782305684e-05, "loss": 0.0182, "step": 22800 }, { "loss_action": 0.01838958077132702, "loss_total": 0.01838958077132702, "step": 22800 }, { "grad_norm": 0.38752588629722595, "learning_rate": 9.157669550179391e-05, "loss": 0.0177, "step": 22810 }, { "loss_action": 0.01511662732809782, "loss_total": 0.01511662732809782, "step": 22810 }, { "grad_norm": 0.32505670189857483, "learning_rate": 9.156750863376609e-05, "loss": 0.0192, "step": 22820 }, { "loss_action": 0.01633249782025814, "loss_total": 0.01633249782025814, "step": 22820 }, { "grad_norm": 0.4112168848514557, "learning_rate": 9.155831721997801e-05, "loss": 0.0187, "step": 22830 }, { "loss_action": 0.016241667792201042, "loss_total": 0.016241667792201042, "step": 22830 }, { "grad_norm": 0.35570207238197327, "learning_rate": 9.154912126143484e-05, "loss": 0.0163, "step": 22840 }, { "loss_action": 0.012696086429059505, "loss_total": 0.012696086429059505, "step": 22840 }, { "grad_norm": 0.3204631507396698, "learning_rate": 9.153992075914224e-05, "loss": 0.0187, "step": 22850 }, { "loss_action": 0.023007668554782867, "loss_total": 0.023007668554782867, "step": 22850 }, { "grad_norm": 0.41492077708244324, "learning_rate": 9.153071571410635e-05, "loss": 0.0187, "step": 22860 }, { "loss_action": 0.014038017950952053, "loss_total": 0.014038017950952053, "step": 22860 }, { "grad_norm": 0.3666871190071106, "learning_rate": 9.152150612733384e-05, "loss": 0.0166, "step": 22870 }, { "loss_action": 0.015955165028572083, "loss_total": 0.015955165028572083, "step": 22870 }, { "grad_norm": 0.3739255666732788, "learning_rate": 9.151229199983184e-05, "loss": 0.0166, "step": 22880 }, { "loss_action": 0.013094080612063408, "loss_total": 0.013094080612063408, "step": 22880 }, { "grad_norm": 0.4073406457901001, "learning_rate": 9.150307333260802e-05, "loss": 0.0183, "step": 22890 }, { "loss_action": 0.020827487111091614, "loss_total": 0.020827487111091614, "step": 22890 }, { "grad_norm": 0.3172858953475952, "learning_rate": 9.149385012667048e-05, "loss": 0.0158, "step": 22900 }, { "loss_action": 0.016916446387767792, "loss_total": 0.016916446387767792, "step": 22900 }, { "grad_norm": 0.4084140360355377, "learning_rate": 9.148462238302788e-05, "loss": 0.0163, "step": 22910 }, { "loss_action": 0.014150994829833508, "loss_total": 0.014150994829833508, "step": 22910 }, { "grad_norm": 0.4605520963668823, "learning_rate": 9.147539010268936e-05, "loss": 0.0169, "step": 22920 }, { "loss_action": 0.02050246112048626, "loss_total": 0.02050246112048626, "step": 22920 }, { "grad_norm": 0.287957102060318, "learning_rate": 9.14661532866645e-05, "loss": 0.0151, "step": 22930 }, { "loss_action": 0.015492522157728672, "loss_total": 0.015492522157728672, "step": 22930 }, { "grad_norm": 0.37323907017707825, "learning_rate": 9.145691193596348e-05, "loss": 0.0165, "step": 22940 }, { "loss_action": 0.013631598092615604, "loss_total": 0.013631598092615604, "step": 22940 }, { "grad_norm": 0.29126331210136414, "learning_rate": 9.144766605159691e-05, "loss": 0.0156, "step": 22950 }, { "loss_action": 0.017513731494545937, "loss_total": 0.017513731494545937, "step": 22950 }, { "grad_norm": 0.3494178354740143, "learning_rate": 9.14384156345759e-05, "loss": 0.016, "step": 22960 }, { "loss_action": 0.01671147160232067, "loss_total": 0.01671147160232067, "step": 22960 }, { "grad_norm": 0.30830949544906616, "learning_rate": 9.142916068591204e-05, "loss": 0.0175, "step": 22970 }, { "loss_action": 0.01620721071958542, "loss_total": 0.01620721071958542, "step": 22970 }, { "grad_norm": 0.41113585233688354, "learning_rate": 9.141990120661746e-05, "loss": 0.0166, "step": 22980 }, { "loss_action": 0.014287191443145275, "loss_total": 0.014287191443145275, "step": 22980 }, { "grad_norm": 0.37481996417045593, "learning_rate": 9.141063719770475e-05, "loss": 0.0182, "step": 22990 }, { "loss_action": 0.01900690793991089, "loss_total": 0.01900690793991089, "step": 22990 }, { "grad_norm": 0.4096946716308594, "learning_rate": 9.140136866018704e-05, "loss": 0.0186, "step": 23000 }, { "loss_action": 0.01636049523949623, "loss_total": 0.01636049523949623, "step": 23000 }, { "grad_norm": 0.3987790644168854, "learning_rate": 9.139209559507788e-05, "loss": 0.0163, "step": 23010 }, { "loss_action": 0.01709648035466671, "loss_total": 0.01709648035466671, "step": 23010 }, { "grad_norm": 0.3712560534477234, "learning_rate": 9.13828180033914e-05, "loss": 0.0182, "step": 23020 }, { "loss_action": 0.016628436744213104, "loss_total": 0.016628436744213104, "step": 23020 }, { "grad_norm": 0.3359006643295288, "learning_rate": 9.137353588614212e-05, "loss": 0.018, "step": 23030 }, { "loss_action": 0.018417056649923325, "loss_total": 0.018417056649923325, "step": 23030 }, { "grad_norm": 0.3342662453651428, "learning_rate": 9.136424924434519e-05, "loss": 0.0173, "step": 23040 }, { "loss_action": 0.013851850293576717, "loss_total": 0.013851850293576717, "step": 23040 }, { "grad_norm": 0.3152027428150177, "learning_rate": 9.135495807901615e-05, "loss": 0.0159, "step": 23050 }, { "loss_action": 0.01877724751830101, "loss_total": 0.01877724751830101, "step": 23050 }, { "grad_norm": 0.43228474259376526, "learning_rate": 9.134566239117108e-05, "loss": 0.0158, "step": 23060 }, { "loss_action": 0.012915152125060558, "loss_total": 0.012915152125060558, "step": 23060 }, { "grad_norm": 0.3776502013206482, "learning_rate": 9.13363621818265e-05, "loss": 0.0152, "step": 23070 }, { "loss_action": 0.0168987438082695, "loss_total": 0.0168987438082695, "step": 23070 }, { "grad_norm": 0.3368525505065918, "learning_rate": 9.132705745199953e-05, "loss": 0.0184, "step": 23080 }, { "loss_action": 0.018949151039123535, "loss_total": 0.018949151039123535, "step": 23080 }, { "grad_norm": 0.40370991826057434, "learning_rate": 9.131774820270768e-05, "loss": 0.0195, "step": 23090 }, { "loss_action": 0.013821904547512531, "loss_total": 0.013821904547512531, "step": 23090 }, { "grad_norm": 0.4100028872489929, "learning_rate": 9.130843443496901e-05, "loss": 0.0157, "step": 23100 }, { "loss_action": 0.01444776076823473, "loss_total": 0.01444776076823473, "step": 23100 }, { "grad_norm": 0.3115615248680115, "learning_rate": 9.129911614980206e-05, "loss": 0.0157, "step": 23110 }, { "loss_action": 0.013373608700931072, "loss_total": 0.013373608700931072, "step": 23110 }, { "grad_norm": 0.314337819814682, "learning_rate": 9.128979334822584e-05, "loss": 0.0158, "step": 23120 }, { "loss_action": 0.012631612829864025, "loss_total": 0.012631612829864025, "step": 23120 }, { "grad_norm": 0.38713833689689636, "learning_rate": 9.128046603125992e-05, "loss": 0.0145, "step": 23130 }, { "loss_action": 0.014388986863195896, "loss_total": 0.014388986863195896, "step": 23130 }, { "grad_norm": 0.39624008536338806, "learning_rate": 9.12711341999243e-05, "loss": 0.0162, "step": 23140 }, { "loss_action": 0.018914902582764626, "loss_total": 0.018914902582764626, "step": 23140 }, { "grad_norm": 0.3181537687778473, "learning_rate": 9.12617978552395e-05, "loss": 0.0182, "step": 23150 }, { "loss_action": 0.019704198464751244, "loss_total": 0.019704198464751244, "step": 23150 }, { "grad_norm": 0.31343910098075867, "learning_rate": 9.12524569982265e-05, "loss": 0.0165, "step": 23160 }, { "loss_action": 0.010784788057208061, "loss_total": 0.010784788057208061, "step": 23160 }, { "grad_norm": 0.40799346566200256, "learning_rate": 9.124311162990684e-05, "loss": 0.0151, "step": 23170 }, { "loss_action": 0.018283069133758545, "loss_total": 0.018283069133758545, "step": 23170 }, { "grad_norm": 0.29312893748283386, "learning_rate": 9.12337617513025e-05, "loss": 0.016, "step": 23180 }, { "loss_action": 0.01219477690756321, "loss_total": 0.01219477690756321, "step": 23180 }, { "grad_norm": 0.38331303000450134, "learning_rate": 9.122440736343596e-05, "loss": 0.0157, "step": 23190 }, { "loss_action": 0.020184138789772987, "loss_total": 0.020184138789772987, "step": 23190 }, { "grad_norm": 0.4773837924003601, "learning_rate": 9.12150484673302e-05, "loss": 0.0182, "step": 23200 }, { "loss_action": 0.01803704723715782, "loss_total": 0.01803704723715782, "step": 23200 }, { "grad_norm": 0.3420684337615967, "learning_rate": 9.120568506400873e-05, "loss": 0.0174, "step": 23210 }, { "loss_action": 0.01830594800412655, "loss_total": 0.01830594800412655, "step": 23210 }, { "grad_norm": 0.33788591623306274, "learning_rate": 9.119631715449548e-05, "loss": 0.0187, "step": 23220 }, { "loss_action": 0.020263947546482086, "loss_total": 0.020263947546482086, "step": 23220 }, { "grad_norm": 0.3152185380458832, "learning_rate": 9.118694473981493e-05, "loss": 0.0189, "step": 23230 }, { "loss_action": 0.016003906726837158, "loss_total": 0.016003906726837158, "step": 23230 }, { "grad_norm": 0.49450215697288513, "learning_rate": 9.117756782099203e-05, "loss": 0.0208, "step": 23240 }, { "loss_action": 0.022613905370235443, "loss_total": 0.022613905370235443, "step": 23240 }, { "grad_norm": 0.3386179208755493, "learning_rate": 9.11681863990522e-05, "loss": 0.018, "step": 23250 }, { "loss_action": 0.018120212480425835, "loss_total": 0.018120212480425835, "step": 23250 }, { "grad_norm": 0.38445189595222473, "learning_rate": 9.115880047502142e-05, "loss": 0.0171, "step": 23260 }, { "loss_action": 0.023260291665792465, "loss_total": 0.023260291665792465, "step": 23260 }, { "grad_norm": 0.48304203152656555, "learning_rate": 9.114941004992609e-05, "loss": 0.0203, "step": 23270 }, { "loss_action": 0.023274894803762436, "loss_total": 0.023274894803762436, "step": 23270 }, { "grad_norm": 0.3952282965183258, "learning_rate": 9.114001512479317e-05, "loss": 0.0188, "step": 23280 }, { "loss_action": 0.018234731629490852, "loss_total": 0.018234731629490852, "step": 23280 }, { "grad_norm": 0.290574848651886, "learning_rate": 9.113061570065003e-05, "loss": 0.0159, "step": 23290 }, { "loss_action": 0.018521644175052643, "loss_total": 0.018521644175052643, "step": 23290 }, { "grad_norm": 0.4093751609325409, "learning_rate": 9.112121177852459e-05, "loss": 0.0194, "step": 23300 }, { "loss_action": 0.01400754414498806, "loss_total": 0.01400754414498806, "step": 23300 }, { "grad_norm": 0.5385950803756714, "learning_rate": 9.111180335944527e-05, "loss": 0.0177, "step": 23310 }, { "loss_action": 0.016509242355823517, "loss_total": 0.016509242355823517, "step": 23310 }, { "grad_norm": 0.4079763889312744, "learning_rate": 9.110239044444093e-05, "loss": 0.0194, "step": 23320 }, { "loss_action": 0.019812854006886482, "loss_total": 0.019812854006886482, "step": 23320 }, { "grad_norm": 0.36630767583847046, "learning_rate": 9.109297303454099e-05, "loss": 0.0193, "step": 23330 }, { "loss_action": 0.019770409911870956, "loss_total": 0.019770409911870956, "step": 23330 }, { "grad_norm": 0.4190574586391449, "learning_rate": 9.108355113077526e-05, "loss": 0.0209, "step": 23340 }, { "loss_action": 0.018975747749209404, "loss_total": 0.018975747749209404, "step": 23340 }, { "grad_norm": 0.38542482256889343, "learning_rate": 9.107412473417419e-05, "loss": 0.0193, "step": 23350 }, { "loss_action": 0.015350001864135265, "loss_total": 0.015350001864135265, "step": 23350 }, { "grad_norm": 0.39730966091156006, "learning_rate": 9.106469384576858e-05, "loss": 0.0199, "step": 23360 }, { "loss_action": 0.021759776398539543, "loss_total": 0.021759776398539543, "step": 23360 }, { "grad_norm": 0.3717609643936157, "learning_rate": 9.105525846658978e-05, "loss": 0.0177, "step": 23370 }, { "loss_action": 0.01416983176022768, "loss_total": 0.01416983176022768, "step": 23370 }, { "grad_norm": 0.3194398880004883, "learning_rate": 9.104581859766965e-05, "loss": 0.0193, "step": 23380 }, { "loss_action": 0.016537414863705635, "loss_total": 0.016537414863705635, "step": 23380 }, { "grad_norm": 0.3690350353717804, "learning_rate": 9.10363742400405e-05, "loss": 0.0207, "step": 23390 }, { "loss_action": 0.023925457149744034, "loss_total": 0.023925457149744034, "step": 23390 }, { "grad_norm": 0.3975667953491211, "learning_rate": 9.102692539473518e-05, "loss": 0.0206, "step": 23400 }, { "loss_action": 0.015855249017477036, "loss_total": 0.015855249017477036, "step": 23400 }, { "grad_norm": 0.39518263936042786, "learning_rate": 9.101747206278697e-05, "loss": 0.0182, "step": 23410 }, { "loss_action": 0.02653702162206173, "loss_total": 0.02653702162206173, "step": 23410 }, { "grad_norm": 0.38454458117485046, "learning_rate": 9.100801424522968e-05, "loss": 0.0174, "step": 23420 }, { "loss_action": 0.016700534150004387, "loss_total": 0.016700534150004387, "step": 23420 }, { "grad_norm": 0.4071703851222992, "learning_rate": 9.099855194309762e-05, "loss": 0.0189, "step": 23430 }, { "loss_action": 0.019671253859996796, "loss_total": 0.019671253859996796, "step": 23430 }, { "grad_norm": 0.365336537361145, "learning_rate": 9.098908515742554e-05, "loss": 0.0188, "step": 23440 }, { "loss_action": 0.02151087298989296, "loss_total": 0.02151087298989296, "step": 23440 }, { "grad_norm": 0.39195701479911804, "learning_rate": 9.097961388924873e-05, "loss": 0.0185, "step": 23450 }, { "loss_action": 0.01827051490545273, "loss_total": 0.01827051490545273, "step": 23450 }, { "grad_norm": 0.3809264600276947, "learning_rate": 9.097013813960298e-05, "loss": 0.0195, "step": 23460 }, { "loss_action": 0.014769826084375381, "loss_total": 0.014769826084375381, "step": 23460 }, { "grad_norm": 0.41245904564857483, "learning_rate": 9.09606579095245e-05, "loss": 0.0202, "step": 23470 }, { "loss_action": 0.019768688827753067, "loss_total": 0.019768688827753067, "step": 23470 }, { "grad_norm": 0.34805190563201904, "learning_rate": 9.095117320005008e-05, "loss": 0.0198, "step": 23480 }, { "loss_action": 0.016345808282494545, "loss_total": 0.016345808282494545, "step": 23480 }, { "grad_norm": 0.42608779668807983, "learning_rate": 9.094168401221691e-05, "loss": 0.0176, "step": 23490 }, { "loss_action": 0.017649544402956963, "loss_total": 0.017649544402956963, "step": 23490 }, { "grad_norm": 0.46842101216316223, "learning_rate": 9.093219034706273e-05, "loss": 0.0185, "step": 23500 }, { "loss_action": 0.017572594806551933, "loss_total": 0.017572594806551933, "step": 23500 }, { "grad_norm": 0.35956689715385437, "learning_rate": 9.092269220562577e-05, "loss": 0.0166, "step": 23510 }, { "loss_action": 0.019389033317565918, "loss_total": 0.019389033317565918, "step": 23510 }, { "grad_norm": 0.4497515857219696, "learning_rate": 9.09131895889447e-05, "loss": 0.0168, "step": 23520 }, { "loss_action": 0.01410170178860426, "loss_total": 0.01410170178860426, "step": 23520 }, { "grad_norm": 0.3479275703430176, "learning_rate": 9.090368249805873e-05, "loss": 0.0152, "step": 23530 }, { "loss_action": 0.01454042736440897, "loss_total": 0.01454042736440897, "step": 23530 }, { "grad_norm": 0.29519668221473694, "learning_rate": 9.089417093400754e-05, "loss": 0.0174, "step": 23540 }, { "loss_action": 0.020292939618229866, "loss_total": 0.020292939618229866, "step": 23540 }, { "grad_norm": 0.3431035280227661, "learning_rate": 9.088465489783131e-05, "loss": 0.0161, "step": 23550 }, { "loss_action": 0.014331535436213017, "loss_total": 0.014331535436213017, "step": 23550 }, { "grad_norm": 0.30487653613090515, "learning_rate": 9.087513439057068e-05, "loss": 0.0167, "step": 23560 }, { "loss_action": 0.014156593009829521, "loss_total": 0.014156593009829521, "step": 23560 }, { "grad_norm": 0.4193193316459656, "learning_rate": 9.08656094132668e-05, "loss": 0.0164, "step": 23570 }, { "loss_action": 0.0159261804074049, "loss_total": 0.0159261804074049, "step": 23570 }, { "grad_norm": 0.3430342376232147, "learning_rate": 9.085607996696134e-05, "loss": 0.0162, "step": 23580 }, { "loss_action": 0.02072683535516262, "loss_total": 0.02072683535516262, "step": 23580 }, { "grad_norm": 0.36721187829971313, "learning_rate": 9.084654605269639e-05, "loss": 0.0177, "step": 23590 }, { "loss_action": 0.014321208000183105, "loss_total": 0.014321208000183105, "step": 23590 }, { "grad_norm": 0.32916730642318726, "learning_rate": 9.083700767151457e-05, "loss": 0.0153, "step": 23600 }, { "loss_action": 0.02337913028895855, "loss_total": 0.02337913028895855, "step": 23600 }, { "grad_norm": 0.3526136577129364, "learning_rate": 9.082746482445898e-05, "loss": 0.019, "step": 23610 }, { "loss_action": 0.01711232401430607, "loss_total": 0.01711232401430607, "step": 23610 }, { "grad_norm": 0.42075395584106445, "learning_rate": 9.081791751257325e-05, "loss": 0.0171, "step": 23620 }, { "loss_action": 0.01679539680480957, "loss_total": 0.01679539680480957, "step": 23620 }, { "grad_norm": 0.36372295022010803, "learning_rate": 9.080836573690142e-05, "loss": 0.0174, "step": 23630 }, { "loss_action": 0.01799183152616024, "loss_total": 0.01799183152616024, "step": 23630 }, { "grad_norm": 0.39992064237594604, "learning_rate": 9.079880949848805e-05, "loss": 0.0195, "step": 23640 }, { "loss_action": 0.016708029434084892, "loss_total": 0.016708029434084892, "step": 23640 }, { "grad_norm": 0.3910161256790161, "learning_rate": 9.078924879837822e-05, "loss": 0.0186, "step": 23650 }, { "loss_action": 0.013932839967310429, "loss_total": 0.013932839967310429, "step": 23650 }, { "grad_norm": 0.5226508378982544, "learning_rate": 9.077968363761747e-05, "loss": 0.0225, "step": 23660 }, { "loss_action": 0.01933002658188343, "loss_total": 0.01933002658188343, "step": 23660 }, { "grad_norm": 0.5503295063972473, "learning_rate": 9.077011401725182e-05, "loss": 0.0211, "step": 23670 }, { "loss_action": 0.018594808876514435, "loss_total": 0.018594808876514435, "step": 23670 }, { "grad_norm": 0.43117955327033997, "learning_rate": 9.07605399383278e-05, "loss": 0.0196, "step": 23680 }, { "loss_action": 0.028575168922543526, "loss_total": 0.028575168922543526, "step": 23680 }, { "grad_norm": 0.3674146234989166, "learning_rate": 9.075096140189243e-05, "loss": 0.0209, "step": 23690 }, { "loss_action": 0.022158434614539146, "loss_total": 0.022158434614539146, "step": 23690 }, { "grad_norm": 0.35983192920684814, "learning_rate": 9.074137840899318e-05, "loss": 0.0225, "step": 23700 }, { "loss_action": 0.021324167028069496, "loss_total": 0.021324167028069496, "step": 23700 }, { "grad_norm": 0.5006429553031921, "learning_rate": 9.073179096067804e-05, "loss": 0.0256, "step": 23710 }, { "loss_action": 0.025845186784863472, "loss_total": 0.025845186784863472, "step": 23710 }, { "grad_norm": 0.5376666784286499, "learning_rate": 9.072219905799549e-05, "loss": 0.0228, "step": 23720 }, { "loss_action": 0.017027849331498146, "loss_total": 0.017027849331498146, "step": 23720 }, { "grad_norm": 0.34608903527259827, "learning_rate": 9.071260270199447e-05, "loss": 0.0205, "step": 23730 }, { "loss_action": 0.022143997251987457, "loss_total": 0.022143997251987457, "step": 23730 }, { "grad_norm": 0.4702318608760834, "learning_rate": 9.070300189372441e-05, "loss": 0.0199, "step": 23740 }, { "loss_action": 0.024673903360962868, "loss_total": 0.024673903360962868, "step": 23740 }, { "grad_norm": 0.40410882234573364, "learning_rate": 9.069339663423528e-05, "loss": 0.0211, "step": 23750 }, { "loss_action": 0.021749364212155342, "loss_total": 0.021749364212155342, "step": 23750 }, { "grad_norm": 0.3233899474143982, "learning_rate": 9.068378692457747e-05, "loss": 0.0212, "step": 23760 }, { "loss_action": 0.019728081300854683, "loss_total": 0.019728081300854683, "step": 23760 }, { "grad_norm": 0.33894678950309753, "learning_rate": 9.067417276580189e-05, "loss": 0.0183, "step": 23770 }, { "loss_action": 0.01842653937637806, "loss_total": 0.01842653937637806, "step": 23770 }, { "grad_norm": 0.42335039377212524, "learning_rate": 9.066455415895993e-05, "loss": 0.0195, "step": 23780 }, { "loss_action": 0.0156538188457489, "loss_total": 0.0156538188457489, "step": 23780 }, { "grad_norm": 0.36998292803764343, "learning_rate": 9.065493110510346e-05, "loss": 0.0196, "step": 23790 }, { "loss_action": 0.017796115949749947, "loss_total": 0.017796115949749947, "step": 23790 }, { "grad_norm": 0.3601650893688202, "learning_rate": 9.064530360528484e-05, "loss": 0.0185, "step": 23800 }, { "loss_action": 0.01669149287045002, "loss_total": 0.01669149287045002, "step": 23800 }, { "grad_norm": 0.3169836401939392, "learning_rate": 9.063567166055695e-05, "loss": 0.0181, "step": 23810 }, { "loss_action": 0.019230978563427925, "loss_total": 0.019230978563427925, "step": 23810 }, { "grad_norm": 0.3514235019683838, "learning_rate": 9.062603527197308e-05, "loss": 0.0192, "step": 23820 }, { "loss_action": 0.018629321828484535, "loss_total": 0.018629321828484535, "step": 23820 }, { "grad_norm": 0.38897764682769775, "learning_rate": 9.06163944405871e-05, "loss": 0.0166, "step": 23830 }, { "loss_action": 0.019978784024715424, "loss_total": 0.019978784024715424, "step": 23830 }, { "grad_norm": 0.45142143964767456, "learning_rate": 9.060674916745327e-05, "loss": 0.0171, "step": 23840 }, { "loss_action": 0.019236886873841286, "loss_total": 0.019236886873841286, "step": 23840 }, { "grad_norm": 0.28974518179893494, "learning_rate": 9.05970994536264e-05, "loss": 0.0167, "step": 23850 }, { "loss_action": 0.016574356704950333, "loss_total": 0.016574356704950333, "step": 23850 }, { "grad_norm": 0.3357028365135193, "learning_rate": 9.05874453001618e-05, "loss": 0.0175, "step": 23860 }, { "loss_action": 0.018849534913897514, "loss_total": 0.018849534913897514, "step": 23860 }, { "grad_norm": 0.2833753824234009, "learning_rate": 9.057778670811517e-05, "loss": 0.0181, "step": 23870 }, { "loss_action": 0.018329694867134094, "loss_total": 0.018329694867134094, "step": 23870 }, { "grad_norm": 0.36486127972602844, "learning_rate": 9.056812367854281e-05, "loss": 0.0168, "step": 23880 }, { "loss_action": 0.01917511597275734, "loss_total": 0.01917511597275734, "step": 23880 }, { "grad_norm": 0.4279521703720093, "learning_rate": 9.055845621250143e-05, "loss": 0.0175, "step": 23890 }, { "loss_action": 0.016956545412540436, "loss_total": 0.016956545412540436, "step": 23890 }, { "grad_norm": 0.3286714553833008, "learning_rate": 9.054878431104825e-05, "loss": 0.0153, "step": 23900 }, { "loss_action": 0.014598355628550053, "loss_total": 0.014598355628550053, "step": 23900 }, { "grad_norm": 0.444693922996521, "learning_rate": 9.0539107975241e-05, "loss": 0.0163, "step": 23910 }, { "loss_action": 0.014025699347257614, "loss_total": 0.014025699347257614, "step": 23910 }, { "grad_norm": 0.28475263714790344, "learning_rate": 9.052942720613784e-05, "loss": 0.0165, "step": 23920 }, { "loss_action": 0.015253710560500622, "loss_total": 0.015253710560500622, "step": 23920 }, { "grad_norm": 0.280222624540329, "learning_rate": 9.051974200479745e-05, "loss": 0.017, "step": 23930 }, { "loss_action": 0.015554280020296574, "loss_total": 0.015554280020296574, "step": 23930 }, { "grad_norm": 0.4327665865421295, "learning_rate": 9.051005237227901e-05, "loss": 0.0173, "step": 23940 }, { "loss_action": 0.015181725844740868, "loss_total": 0.015181725844740868, "step": 23940 }, { "grad_norm": 0.31630855798721313, "learning_rate": 9.050035830964215e-05, "loss": 0.0171, "step": 23950 }, { "loss_action": 0.016739459708333015, "loss_total": 0.016739459708333015, "step": 23950 }, { "grad_norm": 0.43030568957328796, "learning_rate": 9.049065981794698e-05, "loss": 0.0171, "step": 23960 }, { "loss_action": 0.0163322351872921, "loss_total": 0.0163322351872921, "step": 23960 }, { "grad_norm": 0.39596542716026306, "learning_rate": 9.048095689825414e-05, "loss": 0.0172, "step": 23970 }, { "loss_action": 0.01948506012558937, "loss_total": 0.01948506012558937, "step": 23970 }, { "grad_norm": 0.38081496953964233, "learning_rate": 9.047124955162472e-05, "loss": 0.0165, "step": 23980 }, { "loss_action": 0.01598617061972618, "loss_total": 0.01598617061972618, "step": 23980 }, { "grad_norm": 0.35759803652763367, "learning_rate": 9.046153777912028e-05, "loss": 0.0166, "step": 23990 }, { "loss_action": 0.01382711622864008, "loss_total": 0.01382711622864008, "step": 23990 }, { "grad_norm": 0.3586110770702362, "learning_rate": 9.045182158180292e-05, "loss": 0.0159, "step": 24000 }, { "loss_action": 0.014822213910520077, "loss_total": 0.014822213910520077, "step": 24000 }, { "grad_norm": 0.29276058077812195, "learning_rate": 9.044210096073516e-05, "loss": 0.0155, "step": 24010 }, { "loss_action": 0.013915927149355412, "loss_total": 0.013915927149355412, "step": 24010 }, { "grad_norm": 0.37952932715415955, "learning_rate": 9.043237591698004e-05, "loss": 0.0164, "step": 24020 }, { "loss_action": 0.015173138119280338, "loss_total": 0.015173138119280338, "step": 24020 }, { "grad_norm": 0.41685107350349426, "learning_rate": 9.04226464516011e-05, "loss": 0.0176, "step": 24030 }, { "loss_action": 0.015723073855042458, "loss_total": 0.015723073855042458, "step": 24030 }, { "grad_norm": 0.3302617073059082, "learning_rate": 9.041291256566229e-05, "loss": 0.0196, "step": 24040 }, { "loss_action": 0.014470217749476433, "loss_total": 0.014470217749476433, "step": 24040 }, { "grad_norm": 0.2795342803001404, "learning_rate": 9.040317426022814e-05, "loss": 0.0183, "step": 24050 }, { "loss_action": 0.01581672392785549, "loss_total": 0.01581672392785549, "step": 24050 }, { "grad_norm": 0.37585484981536865, "learning_rate": 9.03934315363636e-05, "loss": 0.0192, "step": 24060 }, { "loss_action": 0.017125722020864487, "loss_total": 0.017125722020864487, "step": 24060 }, { "grad_norm": 0.2841484546661377, "learning_rate": 9.038368439513409e-05, "loss": 0.0187, "step": 24070 }, { "loss_action": 0.017182065173983574, "loss_total": 0.017182065173983574, "step": 24070 }, { "grad_norm": 0.3073772192001343, "learning_rate": 9.03739328376056e-05, "loss": 0.016, "step": 24080 }, { "loss_action": 0.013926573097705841, "loss_total": 0.013926573097705841, "step": 24080 }, { "grad_norm": 0.30348360538482666, "learning_rate": 9.036417686484451e-05, "loss": 0.0168, "step": 24090 }, { "loss_action": 0.015162401832640171, "loss_total": 0.015162401832640171, "step": 24090 }, { "grad_norm": 0.3456784188747406, "learning_rate": 9.035441647791773e-05, "loss": 0.0153, "step": 24100 }, { "loss_action": 0.017382154241204262, "loss_total": 0.017382154241204262, "step": 24100 }, { "grad_norm": 0.32450196146965027, "learning_rate": 9.034465167789263e-05, "loss": 0.0154, "step": 24110 }, { "loss_action": 0.016951266676187515, "loss_total": 0.016951266676187515, "step": 24110 }, { "grad_norm": 0.3466868996620178, "learning_rate": 9.033488246583706e-05, "loss": 0.0164, "step": 24120 }, { "loss_action": 0.015812411904335022, "loss_total": 0.015812411904335022, "step": 24120 }, { "grad_norm": 0.32637321949005127, "learning_rate": 9.032510884281941e-05, "loss": 0.0164, "step": 24130 }, { "loss_action": 0.02030479535460472, "loss_total": 0.02030479535460472, "step": 24130 }, { "grad_norm": 0.42067286372184753, "learning_rate": 9.031533080990848e-05, "loss": 0.0158, "step": 24140 }, { "loss_action": 0.01377768162637949, "loss_total": 0.01377768162637949, "step": 24140 }, { "grad_norm": 0.5580178499221802, "learning_rate": 9.030554836817358e-05, "loss": 0.0188, "step": 24150 }, { "loss_action": 0.02629014663398266, "loss_total": 0.02629014663398266, "step": 24150 }, { "grad_norm": 0.35826098918914795, "learning_rate": 9.029576151868451e-05, "loss": 0.0192, "step": 24160 }, { "loss_action": 0.018498925492167473, "loss_total": 0.018498925492167473, "step": 24160 }, { "grad_norm": 0.35986247658729553, "learning_rate": 9.028597026251155e-05, "loss": 0.0165, "step": 24170 }, { "loss_action": 0.017490848898887634, "loss_total": 0.017490848898887634, "step": 24170 }, { "grad_norm": 0.3372955620288849, "learning_rate": 9.027617460072547e-05, "loss": 0.0172, "step": 24180 }, { "loss_action": 0.013751532882452011, "loss_total": 0.013751532882452011, "step": 24180 }, { "grad_norm": 0.3756779134273529, "learning_rate": 9.026637453439745e-05, "loss": 0.0161, "step": 24190 }, { "loss_action": 0.015912242233753204, "loss_total": 0.015912242233753204, "step": 24190 }, { "grad_norm": 0.4046923518180847, "learning_rate": 9.025657006459927e-05, "loss": 0.0154, "step": 24200 }, { "loss_action": 0.020016619935631752, "loss_total": 0.020016619935631752, "step": 24200 }, { "grad_norm": 0.2947053015232086, "learning_rate": 9.024676119240311e-05, "loss": 0.0182, "step": 24210 }, { "loss_action": 0.019718313589692116, "loss_total": 0.019718313589692116, "step": 24210 }, { "grad_norm": 0.30550649762153625, "learning_rate": 9.023694791888166e-05, "loss": 0.0168, "step": 24220 }, { "loss_action": 0.014854945242404938, "loss_total": 0.014854945242404938, "step": 24220 }, { "grad_norm": 0.33660170435905457, "learning_rate": 9.022713024510808e-05, "loss": 0.0158, "step": 24230 }, { "loss_action": 0.015472320839762688, "loss_total": 0.015472320839762688, "step": 24230 }, { "grad_norm": 0.43931061029434204, "learning_rate": 9.021730817215601e-05, "loss": 0.018, "step": 24240 }, { "loss_action": 0.016825422644615173, "loss_total": 0.016825422644615173, "step": 24240 }, { "grad_norm": 0.31268081068992615, "learning_rate": 9.02074817010996e-05, "loss": 0.0163, "step": 24250 }, { "loss_action": 0.027814868837594986, "loss_total": 0.027814868837594986, "step": 24250 }, { "grad_norm": 0.3553019165992737, "learning_rate": 9.019765083301342e-05, "loss": 0.0196, "step": 24260 }, { "loss_action": 0.020846998319029808, "loss_total": 0.020846998319029808, "step": 24260 }, { "grad_norm": 0.29608550667762756, "learning_rate": 9.01878155689726e-05, "loss": 0.016, "step": 24270 }, { "loss_action": 0.016244662925601006, "loss_total": 0.016244662925601006, "step": 24270 }, { "grad_norm": 0.3555634915828705, "learning_rate": 9.017797591005268e-05, "loss": 0.0174, "step": 24280 }, { "loss_action": 0.01225916389375925, "loss_total": 0.01225916389375925, "step": 24280 }, { "grad_norm": 0.40460172295570374, "learning_rate": 9.016813185732972e-05, "loss": 0.021, "step": 24290 }, { "loss_action": 0.01847240887582302, "loss_total": 0.01847240887582302, "step": 24290 }, { "grad_norm": 0.36998653411865234, "learning_rate": 9.015828341188027e-05, "loss": 0.0208, "step": 24300 }, { "loss_action": 0.024954035878181458, "loss_total": 0.024954035878181458, "step": 24300 }, { "grad_norm": 0.39160433411598206, "learning_rate": 9.01484305747813e-05, "loss": 0.0213, "step": 24310 }, { "loss_action": 0.022321520373225212, "loss_total": 0.022321520373225212, "step": 24310 }, { "grad_norm": 0.359591543674469, "learning_rate": 9.013857334711033e-05, "loss": 0.0217, "step": 24320 }, { "loss_action": 0.02714739926159382, "loss_total": 0.02714739926159382, "step": 24320 }, { "grad_norm": 0.39351028203964233, "learning_rate": 9.012871172994534e-05, "loss": 0.022, "step": 24330 }, { "loss_action": 0.016940273344516754, "loss_total": 0.016940273344516754, "step": 24330 }, { "grad_norm": 0.3706718683242798, "learning_rate": 9.011884572436476e-05, "loss": 0.0188, "step": 24340 }, { "loss_action": 0.017992785200476646, "loss_total": 0.017992785200476646, "step": 24340 }, { "grad_norm": 0.3845987021923065, "learning_rate": 9.010897533144754e-05, "loss": 0.0193, "step": 24350 }, { "loss_action": 0.019898833706974983, "loss_total": 0.019898833706974983, "step": 24350 }, { "grad_norm": 0.3807142674922943, "learning_rate": 9.009910055227306e-05, "loss": 0.0164, "step": 24360 }, { "loss_action": 0.021389422938227654, "loss_total": 0.021389422938227654, "step": 24360 }, { "grad_norm": 0.539955735206604, "learning_rate": 9.008922138792124e-05, "loss": 0.0183, "step": 24370 }, { "loss_action": 0.017102720215916634, "loss_total": 0.017102720215916634, "step": 24370 }, { "grad_norm": 0.3101697266101837, "learning_rate": 9.007933783947244e-05, "loss": 0.0177, "step": 24380 }, { "loss_action": 0.017441272735595703, "loss_total": 0.017441272735595703, "step": 24380 }, { "grad_norm": 0.3519006073474884, "learning_rate": 9.006944990800752e-05, "loss": 0.0203, "step": 24390 }, { "loss_action": 0.019982025027275085, "loss_total": 0.019982025027275085, "step": 24390 }, { "grad_norm": 0.3700776696205139, "learning_rate": 9.005955759460779e-05, "loss": 0.0212, "step": 24400 }, { "loss_action": 0.019185343757271767, "loss_total": 0.019185343757271767, "step": 24400 }, { "grad_norm": 0.3595418930053711, "learning_rate": 9.004966090035508e-05, "loss": 0.018, "step": 24410 }, { "loss_action": 0.017293069511651993, "loss_total": 0.017293069511651993, "step": 24410 }, { "grad_norm": 0.320582777261734, "learning_rate": 9.003975982633166e-05, "loss": 0.0176, "step": 24420 }, { "loss_action": 0.024552468210458755, "loss_total": 0.024552468210458755, "step": 24420 }, { "grad_norm": 0.381188303232193, "learning_rate": 9.00298543736203e-05, "loss": 0.0184, "step": 24430 }, { "loss_action": 0.01783987507224083, "loss_total": 0.01783987507224083, "step": 24430 }, { "grad_norm": 0.304200679063797, "learning_rate": 9.001994454330427e-05, "loss": 0.018, "step": 24440 }, { "loss_action": 0.021460162475705147, "loss_total": 0.021460162475705147, "step": 24440 }, { "grad_norm": 0.3042185306549072, "learning_rate": 9.001003033646727e-05, "loss": 0.0179, "step": 24450 }, { "loss_action": 0.016456881538033485, "loss_total": 0.016456881538033485, "step": 24450 }, { "grad_norm": 0.36930394172668457, "learning_rate": 9.00001117541935e-05, "loss": 0.0191, "step": 24460 }, { "loss_action": 0.024938268586993217, "loss_total": 0.024938268586993217, "step": 24460 }, { "grad_norm": 0.3908335268497467, "learning_rate": 8.999018879756764e-05, "loss": 0.018, "step": 24470 }, { "loss_action": 0.015580172650516033, "loss_total": 0.015580172650516033, "step": 24470 }, { "grad_norm": 0.3531721532344818, "learning_rate": 8.998026146767487e-05, "loss": 0.0176, "step": 24480 }, { "loss_action": 0.01911608874797821, "loss_total": 0.01911608874797821, "step": 24480 }, { "grad_norm": 0.3306063413619995, "learning_rate": 8.99703297656008e-05, "loss": 0.0182, "step": 24490 }, { "loss_action": 0.0254738200455904, "loss_total": 0.0254738200455904, "step": 24490 }, { "grad_norm": 0.40939295291900635, "learning_rate": 8.996039369243156e-05, "loss": 0.02, "step": 24500 }, { "loss_action": 0.02310277707874775, "loss_total": 0.02310277707874775, "step": 24500 }, { "grad_norm": 0.32513394951820374, "learning_rate": 8.995045324925378e-05, "loss": 0.021, "step": 24510 }, { "loss_action": 0.021863995119929314, "loss_total": 0.021863995119929314, "step": 24510 }, { "grad_norm": 0.29192960262298584, "learning_rate": 8.994050843715448e-05, "loss": 0.0172, "step": 24520 }, { "loss_action": 0.013738827779889107, "loss_total": 0.013738827779889107, "step": 24520 }, { "grad_norm": 0.40772441029548645, "learning_rate": 8.993055925722121e-05, "loss": 0.0212, "step": 24530 }, { "loss_action": 0.01950986683368683, "loss_total": 0.01950986683368683, "step": 24530 }, { "grad_norm": 0.4222416281700134, "learning_rate": 8.992060571054202e-05, "loss": 0.0185, "step": 24540 }, { "loss_action": 0.01730714924633503, "loss_total": 0.01730714924633503, "step": 24540 }, { "grad_norm": 0.40742000937461853, "learning_rate": 8.991064779820542e-05, "loss": 0.0174, "step": 24550 }, { "loss_action": 0.01795555278658867, "loss_total": 0.01795555278658867, "step": 24550 }, { "grad_norm": 0.4105241596698761, "learning_rate": 8.990068552130036e-05, "loss": 0.0189, "step": 24560 }, { "loss_action": 0.017702793702483177, "loss_total": 0.017702793702483177, "step": 24560 }, { "grad_norm": 0.3554246127605438, "learning_rate": 8.989071888091634e-05, "loss": 0.02, "step": 24570 }, { "loss_action": 0.023811789229512215, "loss_total": 0.023811789229512215, "step": 24570 }, { "grad_norm": 0.47738850116729736, "learning_rate": 8.988074787814329e-05, "loss": 0.0221, "step": 24580 }, { "loss_action": 0.02516845054924488, "loss_total": 0.02516845054924488, "step": 24580 }, { "grad_norm": 0.5325830578804016, "learning_rate": 8.987077251407158e-05, "loss": 0.0296, "step": 24590 }, { "loss_action": 0.028807690367102623, "loss_total": 0.028807690367102623, "step": 24590 }, { "grad_norm": 0.5937768220901489, "learning_rate": 8.986079278979216e-05, "loss": 0.0262, "step": 24600 }, { "loss_action": 0.020928917452692986, "loss_total": 0.020928917452692986, "step": 24600 }, { "grad_norm": 0.5726011991500854, "learning_rate": 8.985080870639635e-05, "loss": 0.0248, "step": 24610 }, { "loss_action": 0.024554185569286346, "loss_total": 0.024554185569286346, "step": 24610 }, { "grad_norm": 0.4909578263759613, "learning_rate": 8.984082026497603e-05, "loss": 0.0235, "step": 24620 }, { "loss_action": 0.020854581147432327, "loss_total": 0.020854581147432327, "step": 24620 }, { "grad_norm": 0.46454963088035583, "learning_rate": 8.98308274666235e-05, "loss": 0.0206, "step": 24630 }, { "loss_action": 0.02781878598034382, "loss_total": 0.02781878598034382, "step": 24630 }, { "grad_norm": 0.3700697124004364, "learning_rate": 8.982083031243155e-05, "loss": 0.0219, "step": 24640 }, { "loss_action": 0.025478465482592583, "loss_total": 0.025478465482592583, "step": 24640 }, { "grad_norm": 0.32595545053482056, "learning_rate": 8.98108288034935e-05, "loss": 0.0206, "step": 24650 }, { "loss_action": 0.014917762018740177, "loss_total": 0.014917762018740177, "step": 24650 }, { "grad_norm": 0.38482457399368286, "learning_rate": 8.980082294090305e-05, "loss": 0.0167, "step": 24660 }, { "loss_action": 0.012442252598702908, "loss_total": 0.012442252598702908, "step": 24660 }, { "grad_norm": 0.29336273670196533, "learning_rate": 8.979081272575443e-05, "loss": 0.0171, "step": 24670 }, { "loss_action": 0.018904734402894974, "loss_total": 0.018904734402894974, "step": 24670 }, { "grad_norm": 0.381399005651474, "learning_rate": 8.978079815914236e-05, "loss": 0.0181, "step": 24680 }, { "loss_action": 0.01785312034189701, "loss_total": 0.01785312034189701, "step": 24680 }, { "grad_norm": 0.346502423286438, "learning_rate": 8.977077924216202e-05, "loss": 0.0166, "step": 24690 }, { "loss_action": 0.025992855429649353, "loss_total": 0.025992855429649353, "step": 24690 }, { "grad_norm": 0.3760569095611572, "learning_rate": 8.976075597590905e-05, "loss": 0.0172, "step": 24700 }, { "loss_action": 0.019545642659068108, "loss_total": 0.019545642659068108, "step": 24700 }, { "grad_norm": 0.34982481598854065, "learning_rate": 8.975072836147958e-05, "loss": 0.0182, "step": 24710 }, { "loss_action": 0.016884908080101013, "loss_total": 0.016884908080101013, "step": 24710 }, { "grad_norm": 0.3153071403503418, "learning_rate": 8.974069639997025e-05, "loss": 0.0163, "step": 24720 }, { "loss_action": 0.017632458359003067, "loss_total": 0.017632458359003067, "step": 24720 }, { "grad_norm": 0.3337867856025696, "learning_rate": 8.973066009247808e-05, "loss": 0.0161, "step": 24730 }, { "loss_action": 0.018125543370842934, "loss_total": 0.018125543370842934, "step": 24730 }, { "grad_norm": 0.3025025725364685, "learning_rate": 8.972061944010066e-05, "loss": 0.0173, "step": 24740 }, { "loss_action": 0.02601771056652069, "loss_total": 0.02601771056652069, "step": 24740 }, { "grad_norm": 0.29073724150657654, "learning_rate": 8.971057444393603e-05, "loss": 0.0177, "step": 24750 }, { "loss_action": 0.012065098620951176, "loss_total": 0.012065098620951176, "step": 24750 }, { "grad_norm": 0.3460083603858948, "learning_rate": 8.970052510508268e-05, "loss": 0.0149, "step": 24760 }, { "loss_action": 0.015168488025665283, "loss_total": 0.015168488025665283, "step": 24760 }, { "grad_norm": 0.33015215396881104, "learning_rate": 8.969047142463959e-05, "loss": 0.0179, "step": 24770 }, { "loss_action": 0.01910768449306488, "loss_total": 0.01910768449306488, "step": 24770 }, { "grad_norm": 0.3696015477180481, "learning_rate": 8.968041340370621e-05, "loss": 0.0177, "step": 24780 }, { "loss_action": 0.02083447389304638, "loss_total": 0.02083447389304638, "step": 24780 }, { "grad_norm": 0.2884177267551422, "learning_rate": 8.96703510433825e-05, "loss": 0.0169, "step": 24790 }, { "loss_action": 0.01687086932361126, "loss_total": 0.01687086932361126, "step": 24790 }, { "grad_norm": 0.3271937072277069, "learning_rate": 8.966028434476883e-05, "loss": 0.018, "step": 24800 }, { "loss_action": 0.013797355815768242, "loss_total": 0.013797355815768242, "step": 24800 }, { "grad_norm": 0.30437153577804565, "learning_rate": 8.96502133089661e-05, "loss": 0.0167, "step": 24810 }, { "loss_action": 0.013612897135317326, "loss_total": 0.013612897135317326, "step": 24810 }, { "grad_norm": 0.3273780643939972, "learning_rate": 8.964013793707564e-05, "loss": 0.0183, "step": 24820 }, { "loss_action": 0.017364053055644035, "loss_total": 0.017364053055644035, "step": 24820 }, { "grad_norm": 0.3466290831565857, "learning_rate": 8.963005823019932e-05, "loss": 0.0166, "step": 24830 }, { "loss_action": 0.015877926722168922, "loss_total": 0.015877926722168922, "step": 24830 }, { "grad_norm": 0.3347439169883728, "learning_rate": 8.961997418943939e-05, "loss": 0.018, "step": 24840 }, { "loss_action": 0.01857668161392212, "loss_total": 0.01857668161392212, "step": 24840 }, { "grad_norm": 0.31323009729385376, "learning_rate": 8.960988581589865e-05, "loss": 0.0177, "step": 24850 }, { "loss_action": 0.014482553116977215, "loss_total": 0.014482553116977215, "step": 24850 }, { "grad_norm": 0.3602287769317627, "learning_rate": 8.959979311068037e-05, "loss": 0.016, "step": 24860 }, { "loss_action": 0.013024275191128254, "loss_total": 0.013024275191128254, "step": 24860 }, { "grad_norm": 0.3601519465446472, "learning_rate": 8.958969607488823e-05, "loss": 0.0162, "step": 24870 }, { "loss_action": 0.02658638171851635, "loss_total": 0.02658638171851635, "step": 24870 }, { "grad_norm": 0.36336201429367065, "learning_rate": 8.957959470962647e-05, "loss": 0.0169, "step": 24880 }, { "loss_action": 0.015192123129963875, "loss_total": 0.015192123129963875, "step": 24880 }, { "grad_norm": 0.42289453744888306, "learning_rate": 8.956948901599971e-05, "loss": 0.016, "step": 24890 }, { "loss_action": 0.01750950515270233, "loss_total": 0.01750950515270233, "step": 24890 }, { "grad_norm": 0.40430688858032227, "learning_rate": 8.955937899511315e-05, "loss": 0.0159, "step": 24900 }, { "loss_action": 0.011302206665277481, "loss_total": 0.011302206665277481, "step": 24900 }, { "grad_norm": 0.3826257586479187, "learning_rate": 8.954926464807238e-05, "loss": 0.0157, "step": 24910 }, { "loss_action": 0.02348341792821884, "loss_total": 0.02348341792821884, "step": 24910 }, { "grad_norm": 0.4387461841106415, "learning_rate": 8.953914597598347e-05, "loss": 0.0171, "step": 24920 }, { "loss_action": 0.01961413584649563, "loss_total": 0.01961413584649563, "step": 24920 }, { "grad_norm": 0.3919936418533325, "learning_rate": 8.952902297995303e-05, "loss": 0.0189, "step": 24930 }, { "loss_action": 0.023133981972932816, "loss_total": 0.023133981972932816, "step": 24930 }, { "grad_norm": 0.387612521648407, "learning_rate": 8.951889566108804e-05, "loss": 0.0193, "step": 24940 }, { "loss_action": 0.01657409779727459, "loss_total": 0.01657409779727459, "step": 24940 }, { "grad_norm": 0.3865419328212738, "learning_rate": 8.950876402049606e-05, "loss": 0.0179, "step": 24950 }, { "loss_action": 0.02233528345823288, "loss_total": 0.02233528345823288, "step": 24950 }, { "grad_norm": 0.40349382162094116, "learning_rate": 8.949862805928504e-05, "loss": 0.0215, "step": 24960 }, { "loss_action": 0.018171854317188263, "loss_total": 0.018171854317188263, "step": 24960 }, { "grad_norm": 0.48181015253067017, "learning_rate": 8.948848777856343e-05, "loss": 0.0195, "step": 24970 }, { "loss_action": 0.016760138794779778, "loss_total": 0.016760138794779778, "step": 24970 }, { "grad_norm": 0.332966685295105, "learning_rate": 8.947834317944017e-05, "loss": 0.0198, "step": 24980 }, { "loss_action": 0.021388880908489227, "loss_total": 0.021388880908489227, "step": 24980 }, { "grad_norm": 0.2992352247238159, "learning_rate": 8.946819426302466e-05, "loss": 0.0176, "step": 24990 }, { "loss_action": 0.018664443865418434, "loss_total": 0.018664443865418434, "step": 24990 }, { "grad_norm": 0.37336456775665283, "learning_rate": 8.945804103042676e-05, "loss": 0.0186, "step": 25000 }, { "loss_action": 0.016807550564408302, "loss_total": 0.016807550564408302, "step": 25000 }, { "grad_norm": 0.28097003698349, "learning_rate": 8.944788348275681e-05, "loss": 0.0157, "step": 25010 }, { "loss_action": 0.015700455754995346, "loss_total": 0.015700455754995346, "step": 25010 }, { "grad_norm": 0.33327189087867737, "learning_rate": 8.943772162112565e-05, "loss": 0.016, "step": 25020 }, { "loss_action": 0.013457008637487888, "loss_total": 0.013457008637487888, "step": 25020 }, { "grad_norm": 0.3125891089439392, "learning_rate": 8.942755544664454e-05, "loss": 0.0151, "step": 25030 }, { "loss_action": 0.018997028470039368, "loss_total": 0.018997028470039368, "step": 25030 }, { "grad_norm": 0.3595854640007019, "learning_rate": 8.941738496042525e-05, "loss": 0.0181, "step": 25040 }, { "loss_action": 0.013531655073165894, "loss_total": 0.013531655073165894, "step": 25040 }, { "grad_norm": 0.5145063996315002, "learning_rate": 8.940721016357999e-05, "loss": 0.0184, "step": 25050 }, { "loss_action": 0.014819102361798286, "loss_total": 0.014819102361798286, "step": 25050 }, { "grad_norm": 0.5855222344398499, "learning_rate": 8.939703105722148e-05, "loss": 0.0181, "step": 25060 }, { "loss_action": 0.01777747832238674, "loss_total": 0.01777747832238674, "step": 25060 }, { "grad_norm": 0.46655067801475525, "learning_rate": 8.93868476424629e-05, "loss": 0.0201, "step": 25070 }, { "loss_action": 0.01776287704706192, "loss_total": 0.01776287704706192, "step": 25070 }, { "grad_norm": 0.4410724341869354, "learning_rate": 8.937665992041786e-05, "loss": 0.0197, "step": 25080 }, { "loss_action": 0.02168705314397812, "loss_total": 0.02168705314397812, "step": 25080 }, { "grad_norm": 0.3709552586078644, "learning_rate": 8.93664678922005e-05, "loss": 0.0188, "step": 25090 }, { "loss_action": 0.018500862643122673, "loss_total": 0.018500862643122673, "step": 25090 }, { "grad_norm": 0.4066067934036255, "learning_rate": 8.93562715589254e-05, "loss": 0.02, "step": 25100 }, { "loss_action": 0.020531438291072845, "loss_total": 0.020531438291072845, "step": 25100 }, { "grad_norm": 0.3635675013065338, "learning_rate": 8.934607092170762e-05, "loss": 0.0182, "step": 25110 }, { "loss_action": 0.021694419905543327, "loss_total": 0.021694419905543327, "step": 25110 }, { "grad_norm": 0.39936262369155884, "learning_rate": 8.933586598166266e-05, "loss": 0.0171, "step": 25120 }, { "loss_action": 0.01625129021704197, "loss_total": 0.01625129021704197, "step": 25120 }, { "grad_norm": 0.35063591599464417, "learning_rate": 8.932565673990655e-05, "loss": 0.0186, "step": 25130 }, { "loss_action": 0.019226064905524254, "loss_total": 0.019226064905524254, "step": 25130 }, { "grad_norm": 0.39108529686927795, "learning_rate": 8.931544319755574e-05, "loss": 0.0187, "step": 25140 }, { "loss_action": 0.014485383406281471, "loss_total": 0.014485383406281471, "step": 25140 }, { "grad_norm": 0.41657543182373047, "learning_rate": 8.930522535572718e-05, "loss": 0.0168, "step": 25150 }, { "loss_action": 0.01292719691991806, "loss_total": 0.01292719691991806, "step": 25150 }, { "grad_norm": 0.36821886897087097, "learning_rate": 8.929500321553826e-05, "loss": 0.0157, "step": 25160 }, { "loss_action": 0.014751392416656017, "loss_total": 0.014751392416656017, "step": 25160 }, { "grad_norm": 0.37386101484298706, "learning_rate": 8.928477677810686e-05, "loss": 0.017, "step": 25170 }, { "loss_action": 0.02013690024614334, "loss_total": 0.02013690024614334, "step": 25170 }, { "grad_norm": 0.380758136510849, "learning_rate": 8.927454604455137e-05, "loss": 0.0175, "step": 25180 }, { "loss_action": 0.014937222003936768, "loss_total": 0.014937222003936768, "step": 25180 }, { "grad_norm": 0.4027135670185089, "learning_rate": 8.926431101599053e-05, "loss": 0.0177, "step": 25190 }, { "loss_action": 0.021646574139595032, "loss_total": 0.021646574139595032, "step": 25190 }, { "grad_norm": 0.4514179527759552, "learning_rate": 8.925407169354369e-05, "loss": 0.0179, "step": 25200 }, { "loss_action": 0.018416043370962143, "loss_total": 0.018416043370962143, "step": 25200 }, { "grad_norm": 0.4604983627796173, "learning_rate": 8.92438280783306e-05, "loss": 0.0183, "step": 25210 }, { "loss_action": 0.01595478504896164, "loss_total": 0.01595478504896164, "step": 25210 }, { "grad_norm": 0.3705143332481384, "learning_rate": 8.923358017147146e-05, "loss": 0.0176, "step": 25220 }, { "loss_action": 0.019189586862921715, "loss_total": 0.019189586862921715, "step": 25220 }, { "grad_norm": 0.4335452914237976, "learning_rate": 8.922332797408697e-05, "loss": 0.0194, "step": 25230 }, { "loss_action": 0.019656013697385788, "loss_total": 0.019656013697385788, "step": 25230 }, { "grad_norm": 0.3684535622596741, "learning_rate": 8.921307148729831e-05, "loss": 0.0203, "step": 25240 }, { "loss_action": 0.018716314807534218, "loss_total": 0.018716314807534218, "step": 25240 }, { "grad_norm": 0.4552674889564514, "learning_rate": 8.920281071222712e-05, "loss": 0.0165, "step": 25250 }, { "loss_action": 0.013606693595647812, "loss_total": 0.013606693595647812, "step": 25250 }, { "grad_norm": 0.35571688413619995, "learning_rate": 8.919254564999548e-05, "loss": 0.0193, "step": 25260 }, { "loss_action": 0.02254584990441799, "loss_total": 0.02254584990441799, "step": 25260 }, { "grad_norm": 0.475167453289032, "learning_rate": 8.918227630172598e-05, "loss": 0.0184, "step": 25270 }, { "loss_action": 0.021364489570260048, "loss_total": 0.021364489570260048, "step": 25270 }, { "grad_norm": 0.38706812262535095, "learning_rate": 8.917200266854165e-05, "loss": 0.0187, "step": 25280 }, { "loss_action": 0.017204632982611656, "loss_total": 0.017204632982611656, "step": 25280 }, { "grad_norm": 0.34610873460769653, "learning_rate": 8.9161724751566e-05, "loss": 0.0179, "step": 25290 }, { "loss_action": 0.017862048000097275, "loss_total": 0.017862048000097275, "step": 25290 }, { "grad_norm": 0.4010735750198364, "learning_rate": 8.915144255192302e-05, "loss": 0.017, "step": 25300 }, { "loss_action": 0.014752932824194431, "loss_total": 0.014752932824194431, "step": 25300 }, { "grad_norm": 0.3507208526134491, "learning_rate": 8.914115607073714e-05, "loss": 0.0196, "step": 25310 }, { "loss_action": 0.027880212292075157, "loss_total": 0.027880212292075157, "step": 25310 }, { "grad_norm": 0.9422773718833923, "learning_rate": 8.913086530913327e-05, "loss": 0.0206, "step": 25320 }, { "loss_action": 0.028330938890576363, "loss_total": 0.028330938890576363, "step": 25320 }, { "grad_norm": 0.5847474932670593, "learning_rate": 8.912057026823681e-05, "loss": 0.0257, "step": 25330 }, { "loss_action": 0.034093789756298065, "loss_total": 0.034093789756298065, "step": 25330 }, { "grad_norm": 0.36867624521255493, "learning_rate": 8.91102709491736e-05, "loss": 0.0236, "step": 25340 }, { "loss_action": 0.027711905539035797, "loss_total": 0.027711905539035797, "step": 25340 }, { "grad_norm": 0.4410370886325836, "learning_rate": 8.909996735306996e-05, "loss": 0.0235, "step": 25350 }, { "loss_action": 0.021495230495929718, "loss_total": 0.021495230495929718, "step": 25350 }, { "grad_norm": 0.3654576241970062, "learning_rate": 8.908965948105268e-05, "loss": 0.0209, "step": 25360 }, { "loss_action": 0.017815586179494858, "loss_total": 0.017815586179494858, "step": 25360 }, { "grad_norm": 0.5029045343399048, "learning_rate": 8.907934733424901e-05, "loss": 0.0221, "step": 25370 }, { "loss_action": 0.018621254712343216, "loss_total": 0.018621254712343216, "step": 25370 }, { "grad_norm": 0.6143746376037598, "learning_rate": 8.906903091378666e-05, "loss": 0.023, "step": 25380 }, { "loss_action": 0.02707052230834961, "loss_total": 0.02707052230834961, "step": 25380 }, { "grad_norm": 0.39368417859077454, "learning_rate": 8.905871022079384e-05, "loss": 0.0249, "step": 25390 }, { "loss_action": 0.01964653469622135, "loss_total": 0.01964653469622135, "step": 25390 }, { "grad_norm": 0.547938346862793, "learning_rate": 8.90483852563992e-05, "loss": 0.0212, "step": 25400 }, { "loss_action": 0.015295589342713356, "loss_total": 0.015295589342713356, "step": 25400 }, { "grad_norm": 0.43453970551490784, "learning_rate": 8.903805602173185e-05, "loss": 0.0201, "step": 25410 }, { "loss_action": 0.021195324137806892, "loss_total": 0.021195324137806892, "step": 25410 }, { "grad_norm": 0.4040135145187378, "learning_rate": 8.902772251792137e-05, "loss": 0.0199, "step": 25420 }, { "loss_action": 0.017008690163493156, "loss_total": 0.017008690163493156, "step": 25420 }, { "grad_norm": 0.34230682253837585, "learning_rate": 8.901738474609786e-05, "loss": 0.019, "step": 25430 }, { "loss_action": 0.015182930044829845, "loss_total": 0.015182930044829845, "step": 25430 }, { "grad_norm": 0.3848593235015869, "learning_rate": 8.900704270739179e-05, "loss": 0.0196, "step": 25440 }, { "loss_action": 0.01557675376534462, "loss_total": 0.01557675376534462, "step": 25440 }, { "grad_norm": 0.47455039620399475, "learning_rate": 8.89966964029342e-05, "loss": 0.0185, "step": 25450 }, { "loss_action": 0.017516015097498894, "loss_total": 0.017516015097498894, "step": 25450 }, { "grad_norm": 0.3645992577075958, "learning_rate": 8.898634583385652e-05, "loss": 0.0185, "step": 25460 }, { "loss_action": 0.02033681608736515, "loss_total": 0.02033681608736515, "step": 25460 }, { "grad_norm": 0.3786775767803192, "learning_rate": 8.897599100129065e-05, "loss": 0.0186, "step": 25470 }, { "loss_action": 0.02265620231628418, "loss_total": 0.02265620231628418, "step": 25470 }, { "grad_norm": 0.3217892646789551, "learning_rate": 8.896563190636903e-05, "loss": 0.0171, "step": 25480 }, { "loss_action": 0.01730397157371044, "loss_total": 0.01730397157371044, "step": 25480 }, { "grad_norm": 0.41938984394073486, "learning_rate": 8.895526855022448e-05, "loss": 0.0195, "step": 25490 }, { "loss_action": 0.019535506144165993, "loss_total": 0.019535506144165993, "step": 25490 }, { "grad_norm": 0.28100353479385376, "learning_rate": 8.894490093399033e-05, "loss": 0.0175, "step": 25500 }, { "loss_action": 0.013169948011636734, "loss_total": 0.013169948011636734, "step": 25500 }, { "grad_norm": 0.37679165601730347, "learning_rate": 8.893452905880035e-05, "loss": 0.0181, "step": 25510 }, { "loss_action": 0.018953606486320496, "loss_total": 0.018953606486320496, "step": 25510 }, { "grad_norm": 0.3986486792564392, "learning_rate": 8.892415292578883e-05, "loss": 0.021, "step": 25520 }, { "loss_action": 0.021999815478920937, "loss_total": 0.021999815478920937, "step": 25520 }, { "grad_norm": 0.38474541902542114, "learning_rate": 8.891377253609046e-05, "loss": 0.0182, "step": 25530 }, { "loss_action": 0.02126891352236271, "loss_total": 0.02126891352236271, "step": 25530 }, { "grad_norm": 0.2838522493839264, "learning_rate": 8.890338789084043e-05, "loss": 0.0154, "step": 25540 }, { "loss_action": 0.01793680526316166, "loss_total": 0.01793680526316166, "step": 25540 }, { "grad_norm": 0.40891948342323303, "learning_rate": 8.88929989911744e-05, "loss": 0.0186, "step": 25550 }, { "loss_action": 0.01620154082775116, "loss_total": 0.01620154082775116, "step": 25550 }, { "grad_norm": 0.3234703540802002, "learning_rate": 8.888260583822847e-05, "loss": 0.016, "step": 25560 }, { "loss_action": 0.02237262949347496, "loss_total": 0.02237262949347496, "step": 25560 }, { "grad_norm": 0.3413708508014679, "learning_rate": 8.887220843313921e-05, "loss": 0.0187, "step": 25570 }, { "loss_action": 0.01363346353173256, "loss_total": 0.01363346353173256, "step": 25570 }, { "grad_norm": 0.34046846628189087, "learning_rate": 8.88618067770437e-05, "loss": 0.0178, "step": 25580 }, { "loss_action": 0.02120581828057766, "loss_total": 0.02120581828057766, "step": 25580 }, { "grad_norm": 0.510921835899353, "learning_rate": 8.885140087107942e-05, "loss": 0.02, "step": 25590 }, { "loss_action": 0.01267918385565281, "loss_total": 0.01267918385565281, "step": 25590 }, { "grad_norm": 0.2849147319793701, "learning_rate": 8.884099071638436e-05, "loss": 0.0154, "step": 25600 }, { "loss_action": 0.01871279627084732, "loss_total": 0.01871279627084732, "step": 25600 }, { "grad_norm": 0.394037127494812, "learning_rate": 8.883057631409695e-05, "loss": 0.0194, "step": 25610 }, { "loss_action": 0.022102180868387222, "loss_total": 0.022102180868387222, "step": 25610 }, { "grad_norm": 0.4003327190876007, "learning_rate": 8.882015766535608e-05, "loss": 0.0177, "step": 25620 }, { "loss_action": 0.01653399132192135, "loss_total": 0.01653399132192135, "step": 25620 }, { "grad_norm": 0.4258764088153839, "learning_rate": 8.880973477130115e-05, "loss": 0.0168, "step": 25630 }, { "loss_action": 0.020043019205331802, "loss_total": 0.020043019205331802, "step": 25630 }, { "grad_norm": 0.3400992751121521, "learning_rate": 8.879930763307197e-05, "loss": 0.0164, "step": 25640 }, { "loss_action": 0.014858185313642025, "loss_total": 0.014858185313642025, "step": 25640 }, { "grad_norm": 0.32346653938293457, "learning_rate": 8.878887625180884e-05, "loss": 0.0185, "step": 25650 }, { "loss_action": 0.022895552217960358, "loss_total": 0.022895552217960358, "step": 25650 }, { "grad_norm": 0.3286743462085724, "learning_rate": 8.877844062865253e-05, "loss": 0.0166, "step": 25660 }, { "loss_action": 0.023528121411800385, "loss_total": 0.023528121411800385, "step": 25660 }, { "grad_norm": 0.3292672336101532, "learning_rate": 8.876800076474424e-05, "loss": 0.018, "step": 25670 }, { "loss_action": 0.015093494206666946, "loss_total": 0.015093494206666946, "step": 25670 }, { "grad_norm": 0.29980260133743286, "learning_rate": 8.875755666122568e-05, "loss": 0.0153, "step": 25680 }, { "loss_action": 0.012833107262849808, "loss_total": 0.012833107262849808, "step": 25680 }, { "grad_norm": 0.3245849907398224, "learning_rate": 8.8747108319239e-05, "loss": 0.0162, "step": 25690 }, { "loss_action": 0.016338730230927467, "loss_total": 0.016338730230927467, "step": 25690 }, { "grad_norm": 0.32821083068847656, "learning_rate": 8.87366557399268e-05, "loss": 0.0159, "step": 25700 }, { "loss_action": 0.011900508776307106, "loss_total": 0.011900508776307106, "step": 25700 }, { "grad_norm": 0.36141595244407654, "learning_rate": 8.872619892443217e-05, "loss": 0.0157, "step": 25710 }, { "loss_action": 0.016896270215511322, "loss_total": 0.016896270215511322, "step": 25710 }, { "grad_norm": 0.28213807940483093, "learning_rate": 8.871573787389865e-05, "loss": 0.0176, "step": 25720 }, { "loss_action": 0.01261082198470831, "loss_total": 0.01261082198470831, "step": 25720 }, { "grad_norm": 0.49863144755363464, "learning_rate": 8.870527258947024e-05, "loss": 0.0191, "step": 25730 }, { "loss_action": 0.015551621094346046, "loss_total": 0.015551621094346046, "step": 25730 }, { "grad_norm": 0.2963961660861969, "learning_rate": 8.869480307229143e-05, "loss": 0.0158, "step": 25740 }, { "loss_action": 0.020191991701722145, "loss_total": 0.020191991701722145, "step": 25740 }, { "grad_norm": 0.44835135340690613, "learning_rate": 8.868432932350712e-05, "loss": 0.0172, "step": 25750 }, { "loss_action": 0.02519856207072735, "loss_total": 0.02519856207072735, "step": 25750 }, { "grad_norm": 0.39927804470062256, "learning_rate": 8.867385134426272e-05, "loss": 0.0187, "step": 25760 }, { "loss_action": 0.01603536121547222, "loss_total": 0.01603536121547222, "step": 25760 }, { "grad_norm": 0.38775911927223206, "learning_rate": 8.866336913570407e-05, "loss": 0.0199, "step": 25770 }, { "loss_action": 0.023194728419184685, "loss_total": 0.023194728419184685, "step": 25770 }, { "grad_norm": 0.30379700660705566, "learning_rate": 8.865288269897751e-05, "loss": 0.0169, "step": 25780 }, { "loss_action": 0.015790948644280434, "loss_total": 0.015790948644280434, "step": 25780 }, { "grad_norm": 0.3320285677909851, "learning_rate": 8.864239203522981e-05, "loss": 0.0155, "step": 25790 }, { "loss_action": 0.01579459384083748, "loss_total": 0.01579459384083748, "step": 25790 }, { "grad_norm": 0.2519122362136841, "learning_rate": 8.863189714560822e-05, "loss": 0.0155, "step": 25800 }, { "loss_action": 0.012696127407252789, "loss_total": 0.012696127407252789, "step": 25800 }, { "grad_norm": 0.33345913887023926, "learning_rate": 8.862139803126043e-05, "loss": 0.0179, "step": 25810 }, { "loss_action": 0.026760080829262733, "loss_total": 0.026760080829262733, "step": 25810 }, { "grad_norm": 0.35478565096855164, "learning_rate": 8.861089469333463e-05, "loss": 0.0184, "step": 25820 }, { "loss_action": 0.01954355463385582, "loss_total": 0.01954355463385582, "step": 25820 }, { "grad_norm": 0.3728543817996979, "learning_rate": 8.860038713297944e-05, "loss": 0.0192, "step": 25830 }, { "loss_action": 0.01632806845009327, "loss_total": 0.01632806845009327, "step": 25830 }, { "grad_norm": 0.3608236014842987, "learning_rate": 8.858987535134394e-05, "loss": 0.0168, "step": 25840 }, { "loss_action": 0.014858009293675423, "loss_total": 0.014858009293675423, "step": 25840 }, { "grad_norm": 0.35281047224998474, "learning_rate": 8.857935934957769e-05, "loss": 0.0166, "step": 25850 }, { "loss_action": 0.014320636168122292, "loss_total": 0.014320636168122292, "step": 25850 }, { "grad_norm": 0.28606054186820984, "learning_rate": 8.856883912883071e-05, "loss": 0.0168, "step": 25860 }, { "loss_action": 0.0211289431899786, "loss_total": 0.0211289431899786, "step": 25860 }, { "grad_norm": 0.3560989499092102, "learning_rate": 8.855831469025346e-05, "loss": 0.0171, "step": 25870 }, { "loss_action": 0.014012278988957405, "loss_total": 0.014012278988957405, "step": 25870 }, { "grad_norm": 0.4990175664424896, "learning_rate": 8.854778603499689e-05, "loss": 0.0151, "step": 25880 }, { "loss_action": 0.016313469037413597, "loss_total": 0.016313469037413597, "step": 25880 }, { "grad_norm": 0.32219821214675903, "learning_rate": 8.85372531642124e-05, "loss": 0.0153, "step": 25890 }, { "loss_action": 0.0181343425065279, "loss_total": 0.0181343425065279, "step": 25890 }, { "grad_norm": 0.29784882068634033, "learning_rate": 8.852671607905185e-05, "loss": 0.0158, "step": 25900 }, { "loss_action": 0.010263297706842422, "loss_total": 0.010263297706842422, "step": 25900 }, { "grad_norm": 0.4189240634441376, "learning_rate": 8.851617478066754e-05, "loss": 0.0159, "step": 25910 }, { "loss_action": 0.022166326642036438, "loss_total": 0.022166326642036438, "step": 25910 }, { "grad_norm": 0.41208142042160034, "learning_rate": 8.850562927021227e-05, "loss": 0.0165, "step": 25920 }, { "loss_action": 0.01907571218907833, "loss_total": 0.01907571218907833, "step": 25920 }, { "grad_norm": 0.33245354890823364, "learning_rate": 8.849507954883928e-05, "loss": 0.017, "step": 25930 }, { "loss_action": 0.02795490063726902, "loss_total": 0.02795490063726902, "step": 25930 }, { "grad_norm": 0.4046262800693512, "learning_rate": 8.848452561770226e-05, "loss": 0.0192, "step": 25940 }, { "loss_action": 0.012514622882008553, "loss_total": 0.012514622882008553, "step": 25940 }, { "grad_norm": 0.3735654056072235, "learning_rate": 8.847396747795538e-05, "loss": 0.0159, "step": 25950 }, { "loss_action": 0.01619536802172661, "loss_total": 0.01619536802172661, "step": 25950 }, { "grad_norm": 0.27567631006240845, "learning_rate": 8.846340513075327e-05, "loss": 0.0141, "step": 25960 }, { "loss_action": 0.01758156530559063, "loss_total": 0.01758156530559063, "step": 25960 }, { "grad_norm": 0.3538205921649933, "learning_rate": 8.845283857725099e-05, "loss": 0.016, "step": 25970 }, { "loss_action": 0.014097400940954685, "loss_total": 0.014097400940954685, "step": 25970 }, { "grad_norm": 0.39271146059036255, "learning_rate": 8.844226781860409e-05, "loss": 0.0169, "step": 25980 }, { "loss_action": 0.020057478919625282, "loss_total": 0.020057478919625282, "step": 25980 }, { "grad_norm": 0.319225013256073, "learning_rate": 8.84316928559686e-05, "loss": 0.0171, "step": 25990 }, { "loss_action": 0.015058360993862152, "loss_total": 0.015058360993862152, "step": 25990 }, { "grad_norm": 0.391009122133255, "learning_rate": 8.842111369050094e-05, "loss": 0.016, "step": 26000 }, { "loss_action": 0.016243722289800644, "loss_total": 0.016243722289800644, "step": 26000 }, { "grad_norm": 0.3034309148788452, "learning_rate": 8.841053032335808e-05, "loss": 0.0162, "step": 26010 }, { "loss_action": 0.014631860889494419, "loss_total": 0.014631860889494419, "step": 26010 }, { "grad_norm": 0.3039648234844208, "learning_rate": 8.839994275569735e-05, "loss": 0.0163, "step": 26020 }, { "loss_action": 0.021838923916220665, "loss_total": 0.021838923916220665, "step": 26020 }, { "grad_norm": 0.39675280451774597, "learning_rate": 8.838935098867662e-05, "loss": 0.0164, "step": 26030 }, { "loss_action": 0.01842423900961876, "loss_total": 0.01842423900961876, "step": 26030 }, { "grad_norm": 0.32521873712539673, "learning_rate": 8.837875502345418e-05, "loss": 0.0159, "step": 26040 }, { "loss_action": 0.01380897220224142, "loss_total": 0.01380897220224142, "step": 26040 }, { "grad_norm": 0.3123091757297516, "learning_rate": 8.83681548611888e-05, "loss": 0.0169, "step": 26050 }, { "loss_action": 0.0156959630548954, "loss_total": 0.0156959630548954, "step": 26050 }, { "grad_norm": 0.3188401460647583, "learning_rate": 8.835755050303969e-05, "loss": 0.0176, "step": 26060 }, { "loss_action": 0.019138213247060776, "loss_total": 0.019138213247060776, "step": 26060 }, { "grad_norm": 0.3731963038444519, "learning_rate": 8.834694195016653e-05, "loss": 0.0167, "step": 26070 }, { "loss_action": 0.021656451746821404, "loss_total": 0.021656451746821404, "step": 26070 }, { "grad_norm": 0.28842002153396606, "learning_rate": 8.833632920372942e-05, "loss": 0.0158, "step": 26080 }, { "loss_action": 0.011099547147750854, "loss_total": 0.011099547147750854, "step": 26080 }, { "grad_norm": 0.31224894523620605, "learning_rate": 8.832571226488903e-05, "loss": 0.0156, "step": 26090 }, { "loss_action": 0.014475957490503788, "loss_total": 0.014475957490503788, "step": 26090 }, { "grad_norm": 0.3571968972682953, "learning_rate": 8.831509113480634e-05, "loss": 0.0169, "step": 26100 }, { "loss_action": 0.01258113980293274, "loss_total": 0.01258113980293274, "step": 26100 }, { "grad_norm": 0.35605406761169434, "learning_rate": 8.83044658146429e-05, "loss": 0.0162, "step": 26110 }, { "loss_action": 0.017640013247728348, "loss_total": 0.017640013247728348, "step": 26110 }, { "grad_norm": 0.3621278703212738, "learning_rate": 8.829383630556067e-05, "loss": 0.017, "step": 26120 }, { "loss_action": 0.018944628536701202, "loss_total": 0.018944628536701202, "step": 26120 }, { "grad_norm": 0.296826034784317, "learning_rate": 8.828320260872207e-05, "loss": 0.015, "step": 26130 }, { "loss_action": 0.014264073222875595, "loss_total": 0.014264073222875595, "step": 26130 }, { "grad_norm": 0.277765691280365, "learning_rate": 8.827256472529e-05, "loss": 0.014, "step": 26140 }, { "loss_action": 0.015711000189185143, "loss_total": 0.015711000189185143, "step": 26140 }, { "grad_norm": 0.35448333621025085, "learning_rate": 8.826192265642778e-05, "loss": 0.0156, "step": 26150 }, { "loss_action": 0.019698381423950195, "loss_total": 0.019698381423950195, "step": 26150 }, { "grad_norm": 0.3837564289569855, "learning_rate": 8.825127640329923e-05, "loss": 0.0177, "step": 26160 }, { "loss_action": 0.015261738561093807, "loss_total": 0.015261738561093807, "step": 26160 }, { "grad_norm": 0.2984965741634369, "learning_rate": 8.824062596706861e-05, "loss": 0.0154, "step": 26170 }, { "loss_action": 0.015105903148651123, "loss_total": 0.015105903148651123, "step": 26170 }, { "grad_norm": 0.4279292821884155, "learning_rate": 8.822997134890062e-05, "loss": 0.0143, "step": 26180 }, { "loss_action": 0.01621697098016739, "loss_total": 0.01621697098016739, "step": 26180 }, { "grad_norm": 0.3704100549221039, "learning_rate": 8.821931254996044e-05, "loss": 0.0153, "step": 26190 }, { "loss_action": 0.015406616032123566, "loss_total": 0.015406616032123566, "step": 26190 }, { "grad_norm": 0.3828905522823334, "learning_rate": 8.82086495714137e-05, "loss": 0.0168, "step": 26200 }, { "loss_action": 0.014234199188649654, "loss_total": 0.014234199188649654, "step": 26200 }, { "grad_norm": 0.37109512090682983, "learning_rate": 8.81979824144265e-05, "loss": 0.0176, "step": 26210 }, { "loss_action": 0.014550480991601944, "loss_total": 0.014550480991601944, "step": 26210 }, { "grad_norm": 0.35015586018562317, "learning_rate": 8.818731108016536e-05, "loss": 0.0155, "step": 26220 }, { "loss_action": 0.01608898490667343, "loss_total": 0.01608898490667343, "step": 26220 }, { "grad_norm": 0.3155072033405304, "learning_rate": 8.81766355697973e-05, "loss": 0.0165, "step": 26230 }, { "loss_action": 0.01643778569996357, "loss_total": 0.01643778569996357, "step": 26230 }, { "grad_norm": 0.339740514755249, "learning_rate": 8.816595588448977e-05, "loss": 0.0152, "step": 26240 }, { "loss_action": 0.01369335874915123, "loss_total": 0.01369335874915123, "step": 26240 }, { "grad_norm": 0.2918504476547241, "learning_rate": 8.81552720254107e-05, "loss": 0.0157, "step": 26250 }, { "loss_action": 0.01113544125109911, "loss_total": 0.01113544125109911, "step": 26250 }, { "grad_norm": 0.4131706953048706, "learning_rate": 8.814458399372842e-05, "loss": 0.0156, "step": 26260 }, { "loss_action": 0.012037551961839199, "loss_total": 0.012037551961839199, "step": 26260 }, { "grad_norm": 0.24817082285881042, "learning_rate": 8.813389179061181e-05, "loss": 0.0156, "step": 26270 }, { "loss_action": 0.015192723833024502, "loss_total": 0.015192723833024502, "step": 26270 }, { "grad_norm": 0.3371269404888153, "learning_rate": 8.812319541723012e-05, "loss": 0.016, "step": 26280 }, { "loss_action": 0.016735395416617393, "loss_total": 0.016735395416617393, "step": 26280 }, { "grad_norm": 0.31544235348701477, "learning_rate": 8.811249487475309e-05, "loss": 0.0155, "step": 26290 }, { "loss_action": 0.012882817536592484, "loss_total": 0.012882817536592484, "step": 26290 }, { "grad_norm": 0.2554325461387634, "learning_rate": 8.810179016435092e-05, "loss": 0.016, "step": 26300 }, { "loss_action": 0.014580728486180305, "loss_total": 0.014580728486180305, "step": 26300 }, { "grad_norm": 0.38795796036720276, "learning_rate": 8.809108128719428e-05, "loss": 0.0165, "step": 26310 }, { "loss_action": 0.015349860303103924, "loss_total": 0.015349860303103924, "step": 26310 }, { "grad_norm": 0.3154042959213257, "learning_rate": 8.808036824445424e-05, "loss": 0.0168, "step": 26320 }, { "loss_action": 0.015420801006257534, "loss_total": 0.015420801006257534, "step": 26320 }, { "grad_norm": 0.412386953830719, "learning_rate": 8.806965103730238e-05, "loss": 0.0169, "step": 26330 }, { "loss_action": 0.029179047793149948, "loss_total": 0.029179047793149948, "step": 26330 }, { "grad_norm": 0.40346401929855347, "learning_rate": 8.805892966691074e-05, "loss": 0.0193, "step": 26340 }, { "loss_action": 0.011921565048396587, "loss_total": 0.011921565048396587, "step": 26340 }, { "grad_norm": 0.35563769936561584, "learning_rate": 8.804820413445175e-05, "loss": 0.0169, "step": 26350 }, { "loss_action": 0.012217436917126179, "loss_total": 0.012217436917126179, "step": 26350 }, { "grad_norm": 0.46064233779907227, "learning_rate": 8.803747444109837e-05, "loss": 0.0168, "step": 26360 }, { "loss_action": 0.013596375472843647, "loss_total": 0.013596375472843647, "step": 26360 }, { "grad_norm": 0.3896539509296417, "learning_rate": 8.802674058802399e-05, "loss": 0.016, "step": 26370 }, { "loss_action": 0.01720607653260231, "loss_total": 0.01720607653260231, "step": 26370 }, { "grad_norm": 0.39089033007621765, "learning_rate": 8.801600257640241e-05, "loss": 0.0172, "step": 26380 }, { "loss_action": 0.016133490949869156, "loss_total": 0.016133490949869156, "step": 26380 }, { "grad_norm": 0.3912644386291504, "learning_rate": 8.800526040740795e-05, "loss": 0.019, "step": 26390 }, { "loss_action": 0.017835935577750206, "loss_total": 0.017835935577750206, "step": 26390 }, { "grad_norm": 0.4521223306655884, "learning_rate": 8.799451408221535e-05, "loss": 0.0179, "step": 26400 }, { "loss_action": 0.016503501683473587, "loss_total": 0.016503501683473587, "step": 26400 }, { "grad_norm": 0.38130077719688416, "learning_rate": 8.798376360199982e-05, "loss": 0.0194, "step": 26410 }, { "loss_action": 0.021163523197174072, "loss_total": 0.021163523197174072, "step": 26410 }, { "grad_norm": 0.4089582562446594, "learning_rate": 8.797300896793701e-05, "loss": 0.018, "step": 26420 }, { "loss_action": 0.020858677104115486, "loss_total": 0.020858677104115486, "step": 26420 }, { "grad_norm": 0.41500523686408997, "learning_rate": 8.796225018120302e-05, "loss": 0.0172, "step": 26430 }, { "loss_action": 0.014748998917639256, "loss_total": 0.014748998917639256, "step": 26430 }, { "grad_norm": 0.3967306613922119, "learning_rate": 8.795148724297444e-05, "loss": 0.017, "step": 26440 }, { "loss_action": 0.014322523958981037, "loss_total": 0.014322523958981037, "step": 26440 }, { "grad_norm": 0.3608822822570801, "learning_rate": 8.794072015442825e-05, "loss": 0.0168, "step": 26450 }, { "loss_action": 0.01528343465179205, "loss_total": 0.01528343465179205, "step": 26450 }, { "grad_norm": 0.298205703496933, "learning_rate": 8.792994891674198e-05, "loss": 0.0155, "step": 26460 }, { "loss_action": 0.013121610507369041, "loss_total": 0.013121610507369041, "step": 26460 }, { "grad_norm": 0.3260101079940796, "learning_rate": 8.79191735310935e-05, "loss": 0.0171, "step": 26470 }, { "loss_action": 0.018305271863937378, "loss_total": 0.018305271863937378, "step": 26470 }, { "grad_norm": 0.4740689694881439, "learning_rate": 8.790839399866122e-05, "loss": 0.016, "step": 26480 }, { "loss_action": 0.013049697503447533, "loss_total": 0.013049697503447533, "step": 26480 }, { "grad_norm": 0.3364157974720001, "learning_rate": 8.789761032062397e-05, "loss": 0.0144, "step": 26490 }, { "loss_action": 0.015078483149409294, "loss_total": 0.015078483149409294, "step": 26490 }, { "grad_norm": 0.306864470243454, "learning_rate": 8.788682249816103e-05, "loss": 0.0154, "step": 26500 }, { "loss_action": 0.010917121544480324, "loss_total": 0.010917121544480324, "step": 26500 }, { "grad_norm": 0.37155213952064514, "learning_rate": 8.787603053245215e-05, "loss": 0.0153, "step": 26510 }, { "loss_action": 0.015788104385137558, "loss_total": 0.015788104385137558, "step": 26510 }, { "grad_norm": 0.3994826376438141, "learning_rate": 8.78652344246775e-05, "loss": 0.0175, "step": 26520 }, { "loss_action": 0.015046689659357071, "loss_total": 0.015046689659357071, "step": 26520 }, { "grad_norm": 0.2908969223499298, "learning_rate": 8.785443417601776e-05, "loss": 0.0168, "step": 26530 }, { "loss_action": 0.01442018523812294, "loss_total": 0.01442018523812294, "step": 26530 }, { "grad_norm": 0.26807186007499695, "learning_rate": 8.784362978765401e-05, "loss": 0.0174, "step": 26540 }, { "loss_action": 0.016962777823209763, "loss_total": 0.016962777823209763, "step": 26540 }, { "grad_norm": 0.4479905366897583, "learning_rate": 8.783282126076779e-05, "loss": 0.0172, "step": 26550 }, { "loss_action": 0.011410623788833618, "loss_total": 0.011410623788833618, "step": 26550 }, { "grad_norm": 0.33530744910240173, "learning_rate": 8.782200859654112e-05, "loss": 0.0155, "step": 26560 }, { "loss_action": 0.01538345031440258, "loss_total": 0.01538345031440258, "step": 26560 }, { "grad_norm": 0.3293416202068329, "learning_rate": 8.781119179615646e-05, "loss": 0.0153, "step": 26570 }, { "loss_action": 0.016332432627677917, "loss_total": 0.016332432627677917, "step": 26570 }, { "grad_norm": 0.39873501658439636, "learning_rate": 8.780037086079674e-05, "loss": 0.0145, "step": 26580 }, { "loss_action": 0.018353160470724106, "loss_total": 0.018353160470724106, "step": 26580 }, { "grad_norm": 0.36129194498062134, "learning_rate": 8.778954579164527e-05, "loss": 0.016, "step": 26590 }, { "loss_action": 0.017767881974577904, "loss_total": 0.017767881974577904, "step": 26590 }, { "grad_norm": 0.2652473747730255, "learning_rate": 8.777871658988588e-05, "loss": 0.017, "step": 26600 }, { "loss_action": 0.013460546731948853, "loss_total": 0.013460546731948853, "step": 26600 }, { "grad_norm": 0.31251928210258484, "learning_rate": 8.776788325670285e-05, "loss": 0.0144, "step": 26610 }, { "loss_action": 0.019524838775396347, "loss_total": 0.019524838775396347, "step": 26610 }, { "grad_norm": 0.46355924010276794, "learning_rate": 8.775704579328089e-05, "loss": 0.0185, "step": 26620 }, { "loss_action": 0.015009747818112373, "loss_total": 0.015009747818112373, "step": 26620 }, { "grad_norm": 0.35590803623199463, "learning_rate": 8.774620420080517e-05, "loss": 0.0186, "step": 26630 }, { "loss_action": 0.016147350892424583, "loss_total": 0.016147350892424583, "step": 26630 }, { "grad_norm": 0.37492844462394714, "learning_rate": 8.773535848046131e-05, "loss": 0.0174, "step": 26640 }, { "loss_action": 0.013811212033033371, "loss_total": 0.013811212033033371, "step": 26640 }, { "grad_norm": 0.36128363013267517, "learning_rate": 8.772450863343538e-05, "loss": 0.0175, "step": 26650 }, { "loss_action": 0.01468373741954565, "loss_total": 0.01468373741954565, "step": 26650 }, { "grad_norm": 0.4119687080383301, "learning_rate": 8.77136546609139e-05, "loss": 0.0198, "step": 26660 }, { "loss_action": 0.012080810032784939, "loss_total": 0.012080810032784939, "step": 26660 }, { "grad_norm": 0.37333744764328003, "learning_rate": 8.770279656408385e-05, "loss": 0.0163, "step": 26670 }, { "loss_action": 0.01392286829650402, "loss_total": 0.01392286829650402, "step": 26670 }, { "grad_norm": 0.3487511873245239, "learning_rate": 8.769193434413265e-05, "loss": 0.0208, "step": 26680 }, { "loss_action": 0.01775018684566021, "loss_total": 0.01775018684566021, "step": 26680 }, { "grad_norm": 0.4294360876083374, "learning_rate": 8.76810680022482e-05, "loss": 0.0173, "step": 26690 }, { "loss_action": 0.017658095806837082, "loss_total": 0.017658095806837082, "step": 26690 }, { "grad_norm": 0.38544461131095886, "learning_rate": 8.767019753961878e-05, "loss": 0.0173, "step": 26700 }, { "loss_action": 0.012982278130948544, "loss_total": 0.012982278130948544, "step": 26700 }, { "grad_norm": 0.33232933282852173, "learning_rate": 8.765932295743321e-05, "loss": 0.0178, "step": 26710 }, { "loss_action": 0.012756513431668282, "loss_total": 0.012756513431668282, "step": 26710 }, { "grad_norm": 0.3204755485057831, "learning_rate": 8.764844425688068e-05, "loss": 0.0177, "step": 26720 }, { "loss_action": 0.021331699565052986, "loss_total": 0.021331699565052986, "step": 26720 }, { "grad_norm": 0.3272598385810852, "learning_rate": 8.763756143915092e-05, "loss": 0.0175, "step": 26730 }, { "loss_action": 0.018497226759791374, "loss_total": 0.018497226759791374, "step": 26730 }, { "grad_norm": 0.28104737401008606, "learning_rate": 8.7626674505434e-05, "loss": 0.0157, "step": 26740 }, { "loss_action": 0.017572999000549316, "loss_total": 0.017572999000549316, "step": 26740 }, { "grad_norm": 0.32370662689208984, "learning_rate": 8.761578345692053e-05, "loss": 0.0165, "step": 26750 }, { "loss_action": 0.01682799682021141, "loss_total": 0.01682799682021141, "step": 26750 }, { "grad_norm": 0.42872709035873413, "learning_rate": 8.760488829480156e-05, "loss": 0.0175, "step": 26760 }, { "loss_action": 0.013654510490596294, "loss_total": 0.013654510490596294, "step": 26760 }, { "grad_norm": 0.3831826150417328, "learning_rate": 8.759398902026854e-05, "loss": 0.0166, "step": 26770 }, { "loss_action": 0.016375694423913956, "loss_total": 0.016375694423913956, "step": 26770 }, { "grad_norm": 0.4097406268119812, "learning_rate": 8.758308563451339e-05, "loss": 0.0184, "step": 26780 }, { "loss_action": 0.015945162624120712, "loss_total": 0.015945162624120712, "step": 26780 }, { "grad_norm": 0.4115446209907532, "learning_rate": 8.75721781387285e-05, "loss": 0.0175, "step": 26790 }, { "loss_action": 0.024840012192726135, "loss_total": 0.024840012192726135, "step": 26790 }, { "grad_norm": 0.44386428594589233, "learning_rate": 8.75612665341067e-05, "loss": 0.0183, "step": 26800 }, { "loss_action": 0.01847178488969803, "loss_total": 0.01847178488969803, "step": 26800 }, { "grad_norm": 0.4413873553276062, "learning_rate": 8.755035082184126e-05, "loss": 0.0181, "step": 26810 }, { "loss_action": 0.01460492517799139, "loss_total": 0.01460492517799139, "step": 26810 }, { "grad_norm": 0.3774048388004303, "learning_rate": 8.753943100312592e-05, "loss": 0.0172, "step": 26820 }, { "loss_action": 0.015903063118457794, "loss_total": 0.015903063118457794, "step": 26820 }, { "grad_norm": 0.4123542308807373, "learning_rate": 8.752850707915484e-05, "loss": 0.017, "step": 26830 }, { "loss_action": 0.01681591384112835, "loss_total": 0.01681591384112835, "step": 26830 }, { "grad_norm": 0.32750487327575684, "learning_rate": 8.751757905112264e-05, "loss": 0.017, "step": 26840 }, { "loss_action": 0.015687452629208565, "loss_total": 0.015687452629208565, "step": 26840 }, { "grad_norm": 0.33021804690361023, "learning_rate": 8.75066469202244e-05, "loss": 0.0154, "step": 26850 }, { "loss_action": 0.020690808072686195, "loss_total": 0.020690808072686195, "step": 26850 }, { "grad_norm": 0.3386443853378296, "learning_rate": 8.749571068765567e-05, "loss": 0.0161, "step": 26860 }, { "loss_action": 0.012574802152812481, "loss_total": 0.012574802152812481, "step": 26860 }, { "grad_norm": 0.3163202404975891, "learning_rate": 8.748477035461238e-05, "loss": 0.0175, "step": 26870 }, { "loss_action": 0.02072256989777088, "loss_total": 0.02072256989777088, "step": 26870 }, { "grad_norm": 0.41629162430763245, "learning_rate": 8.747382592229095e-05, "loss": 0.0205, "step": 26880 }, { "loss_action": 0.020400574430823326, "loss_total": 0.020400574430823326, "step": 26880 }, { "grad_norm": 0.2828785479068756, "learning_rate": 8.746287739188828e-05, "loss": 0.0189, "step": 26890 }, { "loss_action": 0.018711593002080917, "loss_total": 0.018711593002080917, "step": 26890 }, { "grad_norm": 0.42348048090934753, "learning_rate": 8.745192476460165e-05, "loss": 0.02, "step": 26900 }, { "loss_action": 0.020947089418768883, "loss_total": 0.020947089418768883, "step": 26900 }, { "grad_norm": 0.4325505197048187, "learning_rate": 8.744096804162882e-05, "loss": 0.018, "step": 26910 }, { "loss_action": 0.017771953716874123, "loss_total": 0.017771953716874123, "step": 26910 }, { "grad_norm": 0.2989935576915741, "learning_rate": 8.743000722416804e-05, "loss": 0.0196, "step": 26920 }, { "loss_action": 0.021458934992551804, "loss_total": 0.021458934992551804, "step": 26920 }, { "grad_norm": 0.35711145401000977, "learning_rate": 8.741904231341793e-05, "loss": 0.018, "step": 26930 }, { "loss_action": 0.022648515179753304, "loss_total": 0.022648515179753304, "step": 26930 }, { "grad_norm": 0.31966760754585266, "learning_rate": 8.740807331057762e-05, "loss": 0.0183, "step": 26940 }, { "loss_action": 0.01767932064831257, "loss_total": 0.01767932064831257, "step": 26940 }, { "grad_norm": 0.26485341787338257, "learning_rate": 8.739710021684667e-05, "loss": 0.0181, "step": 26950 }, { "loss_action": 0.014668755233287811, "loss_total": 0.014668755233287811, "step": 26950 }, { "grad_norm": 0.47235944867134094, "learning_rate": 8.738612303342503e-05, "loss": 0.0174, "step": 26960 }, { "loss_action": 0.018194200471043587, "loss_total": 0.018194200471043587, "step": 26960 }, { "grad_norm": 0.35582655668258667, "learning_rate": 8.73751417615132e-05, "loss": 0.0177, "step": 26970 }, { "loss_action": 0.015180276706814766, "loss_total": 0.015180276706814766, "step": 26970 }, { "grad_norm": 0.32551607489585876, "learning_rate": 8.736415640231208e-05, "loss": 0.0172, "step": 26980 }, { "loss_action": 0.01480028871446848, "loss_total": 0.01480028871446848, "step": 26980 }, { "grad_norm": 0.3119613826274872, "learning_rate": 8.735316695702297e-05, "loss": 0.0192, "step": 26990 }, { "loss_action": 0.014732933603227139, "loss_total": 0.014732933603227139, "step": 26990 }, { "grad_norm": 0.34218859672546387, "learning_rate": 8.734217342684769e-05, "loss": 0.0175, "step": 27000 }, { "loss_action": 0.01843518204987049, "loss_total": 0.01843518204987049, "step": 27000 }, { "grad_norm": 0.31900742650032043, "learning_rate": 8.733117581298847e-05, "loss": 0.0185, "step": 27010 }, { "loss_action": 0.015071723610162735, "loss_total": 0.015071723610162735, "step": 27010 }, { "grad_norm": 0.3367525339126587, "learning_rate": 8.732017411664796e-05, "loss": 0.0181, "step": 27020 }, { "loss_action": 0.023144086822867393, "loss_total": 0.023144086822867393, "step": 27020 }, { "grad_norm": 0.3665659427642822, "learning_rate": 8.730916833902936e-05, "loss": 0.0189, "step": 27030 }, { "loss_action": 0.015645572915673256, "loss_total": 0.015645572915673256, "step": 27030 }, { "grad_norm": 0.37036439776420593, "learning_rate": 8.729815848133618e-05, "loss": 0.0176, "step": 27040 }, { "loss_action": 0.022796234115958214, "loss_total": 0.022796234115958214, "step": 27040 }, { "grad_norm": 0.2950803339481354, "learning_rate": 8.728714454477247e-05, "loss": 0.0171, "step": 27050 }, { "loss_action": 0.02419518679380417, "loss_total": 0.02419518679380417, "step": 27050 }, { "grad_norm": 0.38257986307144165, "learning_rate": 8.727612653054269e-05, "loss": 0.0174, "step": 27060 }, { "loss_action": 0.017015982419252396, "loss_total": 0.017015982419252396, "step": 27060 }, { "grad_norm": 0.2348126918077469, "learning_rate": 8.726510443985176e-05, "loss": 0.0147, "step": 27070 }, { "loss_action": 0.0246003158390522, "loss_total": 0.0246003158390522, "step": 27070 }, { "grad_norm": 0.418163001537323, "learning_rate": 8.725407827390503e-05, "loss": 0.0182, "step": 27080 }, { "loss_action": 0.02080322988331318, "loss_total": 0.02080322988331318, "step": 27080 }, { "grad_norm": 0.402817040681839, "learning_rate": 8.724304803390833e-05, "loss": 0.0173, "step": 27090 }, { "loss_action": 0.018398640677332878, "loss_total": 0.018398640677332878, "step": 27090 }, { "grad_norm": 0.3343700170516968, "learning_rate": 8.723201372106788e-05, "loss": 0.0188, "step": 27100 }, { "loss_action": 0.014885030686855316, "loss_total": 0.014885030686855316, "step": 27100 }, { "grad_norm": 0.2950733006000519, "learning_rate": 8.722097533659038e-05, "loss": 0.0178, "step": 27110 }, { "loss_action": 0.020762624219059944, "loss_total": 0.020762624219059944, "step": 27110 }, { "grad_norm": 0.35935288667678833, "learning_rate": 8.720993288168299e-05, "loss": 0.0168, "step": 27120 }, { "loss_action": 0.01924472115933895, "loss_total": 0.01924472115933895, "step": 27120 }, { "grad_norm": 0.3020951747894287, "learning_rate": 8.719888635755327e-05, "loss": 0.016, "step": 27130 }, { "loss_action": 0.02340853214263916, "loss_total": 0.02340853214263916, "step": 27130 }, { "grad_norm": 0.30488869547843933, "learning_rate": 8.718783576540928e-05, "loss": 0.0167, "step": 27140 }, { "loss_action": 0.018646040931344032, "loss_total": 0.018646040931344032, "step": 27140 }, { "grad_norm": 0.324167937040329, "learning_rate": 8.717678110645948e-05, "loss": 0.0167, "step": 27150 }, { "loss_action": 0.01311528030782938, "loss_total": 0.01311528030782938, "step": 27150 }, { "grad_norm": 0.32677024602890015, "learning_rate": 8.716572238191279e-05, "loss": 0.0164, "step": 27160 }, { "loss_action": 0.015946729108691216, "loss_total": 0.015946729108691216, "step": 27160 }, { "grad_norm": 0.2688997983932495, "learning_rate": 8.715465959297857e-05, "loss": 0.0161, "step": 27170 }, { "loss_action": 0.014425738714635372, "loss_total": 0.014425738714635372, "step": 27170 }, { "grad_norm": 0.38793203234672546, "learning_rate": 8.714359274086665e-05, "loss": 0.0168, "step": 27180 }, { "loss_action": 0.015853093937039375, "loss_total": 0.015853093937039375, "step": 27180 }, { "grad_norm": 0.339938223361969, "learning_rate": 8.713252182678726e-05, "loss": 0.0145, "step": 27190 }, { "loss_action": 0.019651087000966072, "loss_total": 0.019651087000966072, "step": 27190 }, { "grad_norm": 0.3291744887828827, "learning_rate": 8.712144685195112e-05, "loss": 0.0156, "step": 27200 }, { "loss_action": 0.019046591594815254, "loss_total": 0.019046591594815254, "step": 27200 }, { "grad_norm": 0.46028512716293335, "learning_rate": 8.711036781756936e-05, "loss": 0.0176, "step": 27210 }, { "loss_action": 0.019388070330023766, "loss_total": 0.019388070330023766, "step": 27210 }, { "grad_norm": 0.3618774712085724, "learning_rate": 8.709928472485357e-05, "loss": 0.0162, "step": 27220 }, { "loss_action": 0.019111359491944313, "loss_total": 0.019111359491944313, "step": 27220 }, { "grad_norm": 0.5375019907951355, "learning_rate": 8.708819757501579e-05, "loss": 0.0195, "step": 27230 }, { "loss_action": 0.015454357489943504, "loss_total": 0.015454357489943504, "step": 27230 }, { "grad_norm": 0.3118968605995178, "learning_rate": 8.707710636926846e-05, "loss": 0.0186, "step": 27240 }, { "loss_action": 0.016985801979899406, "loss_total": 0.016985801979899406, "step": 27240 }, { "grad_norm": 0.3519870936870575, "learning_rate": 8.706601110882455e-05, "loss": 0.0157, "step": 27250 }, { "loss_action": 0.012021182104945183, "loss_total": 0.012021182104945183, "step": 27250 }, { "grad_norm": 0.3857283592224121, "learning_rate": 8.705491179489738e-05, "loss": 0.0159, "step": 27260 }, { "loss_action": 0.014769443310797215, "loss_total": 0.014769443310797215, "step": 27260 }, { "grad_norm": 0.4091812074184418, "learning_rate": 8.704380842870077e-05, "loss": 0.0163, "step": 27270 }, { "loss_action": 0.014052140526473522, "loss_total": 0.014052140526473522, "step": 27270 }, { "grad_norm": 0.3255501389503479, "learning_rate": 8.703270101144895e-05, "loss": 0.0165, "step": 27280 }, { "loss_action": 0.01523620542138815, "loss_total": 0.01523620542138815, "step": 27280 }, { "grad_norm": 0.417359322309494, "learning_rate": 8.702158954435664e-05, "loss": 0.0163, "step": 27290 }, { "loss_action": 0.012123280204832554, "loss_total": 0.012123280204832554, "step": 27290 }, { "grad_norm": 0.3695726692676544, "learning_rate": 8.701047402863896e-05, "loss": 0.0161, "step": 27300 }, { "loss_action": 0.01769177056849003, "loss_total": 0.01769177056849003, "step": 27300 }, { "grad_norm": 0.3022089898586273, "learning_rate": 8.699935446551148e-05, "loss": 0.0184, "step": 27310 }, { "loss_action": 0.019759168848395348, "loss_total": 0.019759168848395348, "step": 27310 }, { "grad_norm": 0.3436112105846405, "learning_rate": 8.698823085619022e-05, "loss": 0.0177, "step": 27320 }, { "loss_action": 0.018147381022572517, "loss_total": 0.018147381022572517, "step": 27320 }, { "grad_norm": 0.41759127378463745, "learning_rate": 8.697710320189166e-05, "loss": 0.0174, "step": 27330 }, { "loss_action": 0.014773598872125149, "loss_total": 0.014773598872125149, "step": 27330 }, { "grad_norm": 0.36062854528427124, "learning_rate": 8.696597150383268e-05, "loss": 0.0189, "step": 27340 }, { "loss_action": 0.020006230100989342, "loss_total": 0.020006230100989342, "step": 27340 }, { "grad_norm": 0.27686232328414917, "learning_rate": 8.695483576323063e-05, "loss": 0.0162, "step": 27350 }, { "loss_action": 0.019936498254537582, "loss_total": 0.019936498254537582, "step": 27350 }, { "grad_norm": 0.24430911242961884, "learning_rate": 8.69436959813033e-05, "loss": 0.0171, "step": 27360 }, { "loss_action": 0.02004002220928669, "loss_total": 0.02004002220928669, "step": 27360 }, { "grad_norm": 0.39748531579971313, "learning_rate": 8.693255215926892e-05, "loss": 0.0164, "step": 27370 }, { "loss_action": 0.026624241843819618, "loss_total": 0.026624241843819618, "step": 27370 }, { "grad_norm": 0.3470018208026886, "learning_rate": 8.692140429834617e-05, "loss": 0.0163, "step": 27380 }, { "loss_action": 0.016718754544854164, "loss_total": 0.016718754544854164, "step": 27380 }, { "grad_norm": 0.30507493019104004, "learning_rate": 8.691025239975415e-05, "loss": 0.0145, "step": 27390 }, { "loss_action": 0.015449405647814274, "loss_total": 0.015449405647814274, "step": 27390 }, { "grad_norm": 0.34279951453208923, "learning_rate": 8.689909646471243e-05, "loss": 0.0139, "step": 27400 }, { "loss_action": 0.014492622576653957, "loss_total": 0.014492622576653957, "step": 27400 }, { "grad_norm": 0.36477014422416687, "learning_rate": 8.688793649444099e-05, "loss": 0.0156, "step": 27410 }, { "loss_action": 0.014576427638530731, "loss_total": 0.014576427638530731, "step": 27410 }, { "grad_norm": 0.5538641214370728, "learning_rate": 8.687677249016029e-05, "loss": 0.018, "step": 27420 }, { "loss_action": 0.014667193405330181, "loss_total": 0.014667193405330181, "step": 27420 }, { "grad_norm": 0.3921438157558441, "learning_rate": 8.686560445309118e-05, "loss": 0.0182, "step": 27430 }, { "loss_action": 0.01303433533757925, "loss_total": 0.01303433533757925, "step": 27430 }, { "grad_norm": 0.5099961161613464, "learning_rate": 8.685443238445499e-05, "loss": 0.0183, "step": 27440 }, { "loss_action": 0.022784557193517685, "loss_total": 0.022784557193517685, "step": 27440 }, { "grad_norm": 0.63029944896698, "learning_rate": 8.68432562854735e-05, "loss": 0.0181, "step": 27450 }, { "loss_action": 0.016588672995567322, "loss_total": 0.016588672995567322, "step": 27450 }, { "grad_norm": 0.45563846826553345, "learning_rate": 8.683207615736887e-05, "loss": 0.0161, "step": 27460 }, { "loss_action": 0.015850165858864784, "loss_total": 0.015850165858864784, "step": 27460 }, { "grad_norm": 0.35068413615226746, "learning_rate": 8.682089200136379e-05, "loss": 0.0165, "step": 27470 }, { "loss_action": 0.018496133387088776, "loss_total": 0.018496133387088776, "step": 27470 }, { "grad_norm": 0.2883397042751312, "learning_rate": 8.680970381868132e-05, "loss": 0.018, "step": 27480 }, { "loss_action": 0.011944735422730446, "loss_total": 0.011944735422730446, "step": 27480 }, { "grad_norm": 0.43510571122169495, "learning_rate": 8.679851161054498e-05, "loss": 0.0161, "step": 27490 }, { "loss_action": 0.013161187060177326, "loss_total": 0.013161187060177326, "step": 27490 }, { "grad_norm": 0.34569257497787476, "learning_rate": 8.678731537817873e-05, "loss": 0.0168, "step": 27500 }, { "loss_action": 0.01827860251069069, "loss_total": 0.01827860251069069, "step": 27500 }, { "grad_norm": 0.3300607204437256, "learning_rate": 8.677611512280697e-05, "loss": 0.0163, "step": 27510 }, { "loss_action": 0.017376944422721863, "loss_total": 0.017376944422721863, "step": 27510 }, { "grad_norm": 0.3520268201828003, "learning_rate": 8.676491084565457e-05, "loss": 0.017, "step": 27520 }, { "loss_action": 0.015783589333295822, "loss_total": 0.015783589333295822, "step": 27520 }, { "grad_norm": 0.37860944867134094, "learning_rate": 8.675370254794678e-05, "loss": 0.017, "step": 27530 }, { "loss_action": 0.023036066442728043, "loss_total": 0.023036066442728043, "step": 27530 }, { "grad_norm": 0.3713065981864929, "learning_rate": 8.674249023090935e-05, "loss": 0.0177, "step": 27540 }, { "loss_action": 0.016798779368400574, "loss_total": 0.016798779368400574, "step": 27540 }, { "grad_norm": 0.30982068181037903, "learning_rate": 8.673127389576843e-05, "loss": 0.0163, "step": 27550 }, { "loss_action": 0.015556792728602886, "loss_total": 0.015556792728602886, "step": 27550 }, { "grad_norm": 0.3486631512641907, "learning_rate": 8.67200535437506e-05, "loss": 0.0177, "step": 27560 }, { "loss_action": 0.015370285138487816, "loss_total": 0.015370285138487816, "step": 27560 }, { "grad_norm": 0.27249160408973694, "learning_rate": 8.670882917608296e-05, "loss": 0.0146, "step": 27570 }, { "loss_action": 0.01215625274926424, "loss_total": 0.01215625274926424, "step": 27570 }, { "grad_norm": 0.34395837783813477, "learning_rate": 8.669760079399292e-05, "loss": 0.016, "step": 27580 }, { "loss_action": 0.01760290004312992, "loss_total": 0.01760290004312992, "step": 27580 }, { "grad_norm": 0.2812764644622803, "learning_rate": 8.668636839870845e-05, "loss": 0.0157, "step": 27590 }, { "loss_action": 0.014698891900479794, "loss_total": 0.014698891900479794, "step": 27590 }, { "grad_norm": 0.46534985303878784, "learning_rate": 8.667513199145789e-05, "loss": 0.0172, "step": 27600 }, { "loss_action": 0.013300299644470215, "loss_total": 0.013300299644470215, "step": 27600 }, { "grad_norm": 0.2951815724372864, "learning_rate": 8.666389157347002e-05, "loss": 0.0162, "step": 27610 }, { "loss_action": 0.01812209002673626, "loss_total": 0.01812209002673626, "step": 27610 }, { "grad_norm": 0.32518526911735535, "learning_rate": 8.66526471459741e-05, "loss": 0.0149, "step": 27620 }, { "loss_action": 0.013408420607447624, "loss_total": 0.013408420607447624, "step": 27620 }, { "grad_norm": 0.31064745783805847, "learning_rate": 8.66413987101998e-05, "loss": 0.0166, "step": 27630 }, { "loss_action": 0.010295309126377106, "loss_total": 0.010295309126377106, "step": 27630 }, { "grad_norm": 0.34999942779541016, "learning_rate": 8.663014626737723e-05, "loss": 0.0142, "step": 27640 }, { "loss_action": 0.015245799906551838, "loss_total": 0.015245799906551838, "step": 27640 }, { "grad_norm": 0.41674262285232544, "learning_rate": 8.661888981873691e-05, "loss": 0.0158, "step": 27650 }, { "loss_action": 0.023436952382326126, "loss_total": 0.023436952382326126, "step": 27650 }, { "grad_norm": 0.3795093894004822, "learning_rate": 8.660762936550988e-05, "loss": 0.0189, "step": 27660 }, { "loss_action": 0.01627415604889393, "loss_total": 0.01627415604889393, "step": 27660 }, { "grad_norm": 0.518028736114502, "learning_rate": 8.659636490892753e-05, "loss": 0.0179, "step": 27670 }, { "loss_action": 0.019845418632030487, "loss_total": 0.019845418632030487, "step": 27670 }, { "grad_norm": 0.336593359708786, "learning_rate": 8.658509645022174e-05, "loss": 0.0179, "step": 27680 }, { "loss_action": 0.014751299284398556, "loss_total": 0.014751299284398556, "step": 27680 }, { "grad_norm": 0.3594421446323395, "learning_rate": 8.657382399062481e-05, "loss": 0.0165, "step": 27690 }, { "loss_action": 0.01667470671236515, "loss_total": 0.01667470671236515, "step": 27690 }, { "grad_norm": 0.39704370498657227, "learning_rate": 8.656254753136946e-05, "loss": 0.0174, "step": 27700 }, { "loss_action": 0.013390392996370792, "loss_total": 0.013390392996370792, "step": 27700 }, { "grad_norm": 0.367821604013443, "learning_rate": 8.655126707368891e-05, "loss": 0.0167, "step": 27710 }, { "loss_action": 0.013430033810436726, "loss_total": 0.013430033810436726, "step": 27710 }, { "grad_norm": 0.4112197160720825, "learning_rate": 8.653998261881672e-05, "loss": 0.0159, "step": 27720 }, { "loss_action": 0.020392170175909996, "loss_total": 0.020392170175909996, "step": 27720 }, { "grad_norm": 0.3294500410556793, "learning_rate": 8.652869416798699e-05, "loss": 0.0164, "step": 27730 }, { "loss_action": 0.01320220809429884, "loss_total": 0.01320220809429884, "step": 27730 }, { "grad_norm": 0.31577497720718384, "learning_rate": 8.651740172243417e-05, "loss": 0.0158, "step": 27740 }, { "loss_action": 0.01781223900616169, "loss_total": 0.01781223900616169, "step": 27740 }, { "grad_norm": 0.3906724750995636, "learning_rate": 8.65061052833932e-05, "loss": 0.017, "step": 27750 }, { "loss_action": 0.018413828685879707, "loss_total": 0.018413828685879707, "step": 27750 }, { "grad_norm": 0.31423574686050415, "learning_rate": 8.649480485209945e-05, "loss": 0.0149, "step": 27760 }, { "loss_action": 0.012858147732913494, "loss_total": 0.012858147732913494, "step": 27760 }, { "grad_norm": 0.266385018825531, "learning_rate": 8.64835004297887e-05, "loss": 0.0154, "step": 27770 }, { "loss_action": 0.012270297855138779, "loss_total": 0.012270297855138779, "step": 27770 }, { "grad_norm": 0.2649848759174347, "learning_rate": 8.64721920176972e-05, "loss": 0.0143, "step": 27780 }, { "loss_action": 0.02088000997900963, "loss_total": 0.02088000997900963, "step": 27780 }, { "grad_norm": 0.31374379992485046, "learning_rate": 8.646087961706164e-05, "loss": 0.0154, "step": 27790 }, { "loss_action": 0.016215940937399864, "loss_total": 0.016215940937399864, "step": 27790 }, { "grad_norm": 0.33963194489479065, "learning_rate": 8.644956322911908e-05, "loss": 0.0179, "step": 27800 }, { "loss_action": 0.023492343723773956, "loss_total": 0.023492343723773956, "step": 27800 }, { "grad_norm": 0.38075095415115356, "learning_rate": 8.643824285510709e-05, "loss": 0.0173, "step": 27810 }, { "loss_action": 0.01570700667798519, "loss_total": 0.01570700667798519, "step": 27810 }, { "grad_norm": 0.3359532654285431, "learning_rate": 8.642691849626364e-05, "loss": 0.0157, "step": 27820 }, { "loss_action": 0.015411273576319218, "loss_total": 0.015411273576319218, "step": 27820 }, { "grad_norm": 0.2682575583457947, "learning_rate": 8.641559015382717e-05, "loss": 0.0153, "step": 27830 }, { "loss_action": 0.011999525129795074, "loss_total": 0.011999525129795074, "step": 27830 }, { "grad_norm": 0.543522834777832, "learning_rate": 8.640425782903649e-05, "loss": 0.0179, "step": 27840 }, { "loss_action": 0.015736207365989685, "loss_total": 0.015736207365989685, "step": 27840 }, { "grad_norm": 0.399349182844162, "learning_rate": 8.639292152313091e-05, "loss": 0.017, "step": 27850 }, { "loss_action": 0.016694938763976097, "loss_total": 0.016694938763976097, "step": 27850 }, { "grad_norm": 0.3356302082538605, "learning_rate": 8.638158123735015e-05, "loss": 0.0169, "step": 27860 }, { "loss_action": 0.01662514917552471, "loss_total": 0.01662514917552471, "step": 27860 }, { "grad_norm": 0.356090784072876, "learning_rate": 8.637023697293436e-05, "loss": 0.017, "step": 27870 }, { "loss_action": 0.0156854297965765, "loss_total": 0.0156854297965765, "step": 27870 }, { "grad_norm": 0.3143090605735779, "learning_rate": 8.635888873112414e-05, "loss": 0.0167, "step": 27880 }, { "loss_action": 0.017626885324716568, "loss_total": 0.017626885324716568, "step": 27880 }, { "grad_norm": 0.5465176105499268, "learning_rate": 8.634753651316052e-05, "loss": 0.0166, "step": 27890 }, { "loss_action": 0.012199421413242817, "loss_total": 0.012199421413242817, "step": 27890 }, { "grad_norm": 0.3363819420337677, "learning_rate": 8.633618032028496e-05, "loss": 0.0165, "step": 27900 }, { "loss_action": 0.017692508175969124, "loss_total": 0.017692508175969124, "step": 27900 }, { "grad_norm": 0.2816074788570404, "learning_rate": 8.632482015373934e-05, "loss": 0.0172, "step": 27910 }, { "loss_action": 0.01772104948759079, "loss_total": 0.01772104948759079, "step": 27910 }, { "grad_norm": 0.2840513288974762, "learning_rate": 8.6313456014766e-05, "loss": 0.0167, "step": 27920 }, { "loss_action": 0.015737654641270638, "loss_total": 0.015737654641270638, "step": 27920 }, { "grad_norm": 0.3672436773777008, "learning_rate": 8.630208790460771e-05, "loss": 0.017, "step": 27930 }, { "loss_action": 0.023227080702781677, "loss_total": 0.023227080702781677, "step": 27930 }, { "grad_norm": 0.3330013155937195, "learning_rate": 8.629071582450768e-05, "loss": 0.0156, "step": 27940 }, { "loss_action": 0.02249731309711933, "loss_total": 0.02249731309711933, "step": 27940 }, { "grad_norm": 0.4422016143798828, "learning_rate": 8.62793397757095e-05, "loss": 0.0165, "step": 27950 }, { "loss_action": 0.0164131298661232, "loss_total": 0.0164131298661232, "step": 27950 }, { "grad_norm": 0.297369122505188, "learning_rate": 8.626795975945729e-05, "loss": 0.0164, "step": 27960 }, { "loss_action": 0.013665863312780857, "loss_total": 0.013665863312780857, "step": 27960 }, { "grad_norm": 0.3832245469093323, "learning_rate": 8.625657577699551e-05, "loss": 0.0162, "step": 27970 }, { "loss_action": 0.01886002905666828, "loss_total": 0.01886002905666828, "step": 27970 }, { "grad_norm": 0.3708648383617401, "learning_rate": 8.624518782956914e-05, "loss": 0.0154, "step": 27980 }, { "loss_action": 0.012464344501495361, "loss_total": 0.012464344501495361, "step": 27980 }, { "grad_norm": 0.3149389326572418, "learning_rate": 8.62337959184235e-05, "loss": 0.0156, "step": 27990 }, { "loss_action": 0.014347775839269161, "loss_total": 0.014347775839269161, "step": 27990 }, { "grad_norm": 0.3388867676258087, "learning_rate": 8.622240004480441e-05, "loss": 0.0153, "step": 28000 }, { "loss_action": 0.015598193742334843, "loss_total": 0.015598193742334843, "step": 28000 }, { "grad_norm": 0.35941246151924133, "learning_rate": 8.621100020995814e-05, "loss": 0.0151, "step": 28010 }, { "loss_action": 0.011847661808133125, "loss_total": 0.011847661808133125, "step": 28010 }, { "grad_norm": 0.3235757350921631, "learning_rate": 8.619959641513132e-05, "loss": 0.0164, "step": 28020 }, { "loss_action": 0.013910875655710697, "loss_total": 0.013910875655710697, "step": 28020 }, { "grad_norm": 0.35337790846824646, "learning_rate": 8.618818866157105e-05, "loss": 0.0163, "step": 28030 }, { "loss_action": 0.021314598619937897, "loss_total": 0.021314598619937897, "step": 28030 }, { "grad_norm": 0.33852607011795044, "learning_rate": 8.617677695052487e-05, "loss": 0.0163, "step": 28040 }, { "loss_action": 0.011043868027627468, "loss_total": 0.011043868027627468, "step": 28040 }, { "grad_norm": 0.42693185806274414, "learning_rate": 8.616536128324078e-05, "loss": 0.0182, "step": 28050 }, { "loss_action": 0.01555168442428112, "loss_total": 0.01555168442428112, "step": 28050 }, { "grad_norm": 0.3715907633304596, "learning_rate": 8.615394166096712e-05, "loss": 0.0157, "step": 28060 }, { "loss_action": 0.012226885184645653, "loss_total": 0.012226885184645653, "step": 28060 }, { "grad_norm": 0.341061532497406, "learning_rate": 8.614251808495279e-05, "loss": 0.0161, "step": 28070 }, { "loss_action": 0.018214454874396324, "loss_total": 0.018214454874396324, "step": 28070 }, { "grad_norm": 0.3089175820350647, "learning_rate": 8.6131090556447e-05, "loss": 0.0169, "step": 28080 }, { "loss_action": 0.013228116557002068, "loss_total": 0.013228116557002068, "step": 28080 }, { "grad_norm": 0.4360799789428711, "learning_rate": 8.611965907669947e-05, "loss": 0.0153, "step": 28090 }, { "loss_action": 0.012841496616601944, "loss_total": 0.012841496616601944, "step": 28090 }, { "grad_norm": 0.3146975338459015, "learning_rate": 8.610822364696034e-05, "loss": 0.0153, "step": 28100 }, { "loss_action": 0.019815387204289436, "loss_total": 0.019815387204289436, "step": 28100 }, { "grad_norm": 0.4321945607662201, "learning_rate": 8.609678426848015e-05, "loss": 0.0194, "step": 28110 }, { "loss_action": 0.014741281978785992, "loss_total": 0.014741281978785992, "step": 28110 }, { "grad_norm": 0.2967885136604309, "learning_rate": 8.60853409425099e-05, "loss": 0.0159, "step": 28120 }, { "loss_action": 0.012044403702020645, "loss_total": 0.012044403702020645, "step": 28120 }, { "grad_norm": 0.4670880436897278, "learning_rate": 8.607389367030104e-05, "loss": 0.017, "step": 28130 }, { "loss_action": 0.015118070878088474, "loss_total": 0.015118070878088474, "step": 28130 }, { "grad_norm": 0.3260689079761505, "learning_rate": 8.606244245310538e-05, "loss": 0.0178, "step": 28140 }, { "loss_action": 0.0176016204059124, "loss_total": 0.0176016204059124, "step": 28140 }, { "grad_norm": 0.3303065299987793, "learning_rate": 8.605098729217525e-05, "loss": 0.0162, "step": 28150 }, { "loss_action": 0.013970313593745232, "loss_total": 0.013970313593745232, "step": 28150 }, { "grad_norm": 0.34291401505470276, "learning_rate": 8.603952818876335e-05, "loss": 0.0189, "step": 28160 }, { "loss_action": 0.020186150446534157, "loss_total": 0.020186150446534157, "step": 28160 }, { "grad_norm": 0.3677690625190735, "learning_rate": 8.602806514412281e-05, "loss": 0.0178, "step": 28170 }, { "loss_action": 0.018536880612373352, "loss_total": 0.018536880612373352, "step": 28170 }, { "grad_norm": 0.45296376943588257, "learning_rate": 8.601659815950726e-05, "loss": 0.0197, "step": 28180 }, { "loss_action": 0.018359584733843803, "loss_total": 0.018359584733843803, "step": 28180 }, { "grad_norm": 0.4447725713253021, "learning_rate": 8.600512723617067e-05, "loss": 0.0169, "step": 28190 }, { "loss_action": 0.020174119621515274, "loss_total": 0.020174119621515274, "step": 28190 }, { "grad_norm": 0.31957095861434937, "learning_rate": 8.59936523753675e-05, "loss": 0.0177, "step": 28200 }, { "loss_action": 0.014321851544082165, "loss_total": 0.014321851544082165, "step": 28200 }, { "grad_norm": 0.32720914483070374, "learning_rate": 8.598217357835264e-05, "loss": 0.0161, "step": 28210 }, { "loss_action": 0.01522925402969122, "loss_total": 0.01522925402969122, "step": 28210 }, { "grad_norm": 0.3445667624473572, "learning_rate": 8.597069084638135e-05, "loss": 0.0174, "step": 28220 }, { "loss_action": 0.01952201873064041, "loss_total": 0.01952201873064041, "step": 28220 }, { "grad_norm": 0.32272788882255554, "learning_rate": 8.595920418070939e-05, "loss": 0.0154, "step": 28230 }, { "loss_action": 0.012424572370946407, "loss_total": 0.012424572370946407, "step": 28230 }, { "grad_norm": 0.30131691694259644, "learning_rate": 8.594771358259295e-05, "loss": 0.0155, "step": 28240 }, { "loss_action": 0.015181678347289562, "loss_total": 0.015181678347289562, "step": 28240 }, { "grad_norm": 0.354682058095932, "learning_rate": 8.593621905328858e-05, "loss": 0.0159, "step": 28250 }, { "loss_action": 0.019294247031211853, "loss_total": 0.019294247031211853, "step": 28250 }, { "grad_norm": 0.3331168293952942, "learning_rate": 8.592472059405333e-05, "loss": 0.0164, "step": 28260 }, { "loss_action": 0.017688151448965073, "loss_total": 0.017688151448965073, "step": 28260 }, { "grad_norm": 0.4678003489971161, "learning_rate": 8.591321820614464e-05, "loss": 0.0174, "step": 28270 }, { "loss_action": 0.018729697912931442, "loss_total": 0.018729697912931442, "step": 28270 }, { "grad_norm": 0.34666907787323, "learning_rate": 8.590171189082041e-05, "loss": 0.0155, "step": 28280 }, { "loss_action": 0.017521841451525688, "loss_total": 0.017521841451525688, "step": 28280 }, { "grad_norm": 0.29229432344436646, "learning_rate": 8.589020164933894e-05, "loss": 0.0146, "step": 28290 }, { "loss_action": 0.018310949206352234, "loss_total": 0.018310949206352234, "step": 28290 }, { "grad_norm": 0.31296446919441223, "learning_rate": 8.587868748295898e-05, "loss": 0.0153, "step": 28300 }, { "loss_action": 0.014362974092364311, "loss_total": 0.014362974092364311, "step": 28300 }, { "grad_norm": 0.5607311725616455, "learning_rate": 8.586716939293971e-05, "loss": 0.0164, "step": 28310 }, { "loss_action": 0.010891561396420002, "loss_total": 0.010891561396420002, "step": 28310 }, { "grad_norm": 0.3142973780632019, "learning_rate": 8.58556473805407e-05, "loss": 0.0167, "step": 28320 }, { "loss_action": 0.019983330741524696, "loss_total": 0.019983330741524696, "step": 28320 }, { "grad_norm": 0.31876450777053833, "learning_rate": 8.584412144702202e-05, "loss": 0.0176, "step": 28330 }, { "loss_action": 0.0200569536536932, "loss_total": 0.0200569536536932, "step": 28330 }, { "grad_norm": 0.31483495235443115, "learning_rate": 8.58325915936441e-05, "loss": 0.017, "step": 28340 }, { "loss_action": 0.012748919427394867, "loss_total": 0.012748919427394867, "step": 28340 }, { "grad_norm": 0.3269931972026825, "learning_rate": 8.582105782166783e-05, "loss": 0.0163, "step": 28350 }, { "loss_action": 0.02864309586584568, "loss_total": 0.02864309586584568, "step": 28350 }, { "grad_norm": 0.34015411138534546, "learning_rate": 8.580952013235455e-05, "loss": 0.0186, "step": 28360 }, { "loss_action": 0.014586184173822403, "loss_total": 0.014586184173822403, "step": 28360 }, { "grad_norm": 0.275875985622406, "learning_rate": 8.579797852696596e-05, "loss": 0.017, "step": 28370 }, { "loss_action": 0.016634788364171982, "loss_total": 0.016634788364171982, "step": 28370 }, { "grad_norm": 0.48388466238975525, "learning_rate": 8.578643300676428e-05, "loss": 0.0162, "step": 28380 }, { "loss_action": 0.021189812570810318, "loss_total": 0.021189812570810318, "step": 28380 }, { "grad_norm": 0.3925398588180542, "learning_rate": 8.577488357301209e-05, "loss": 0.0167, "step": 28390 }, { "loss_action": 0.02040412276983261, "loss_total": 0.02040412276983261, "step": 28390 }, { "grad_norm": 0.38758212327957153, "learning_rate": 8.576333022697242e-05, "loss": 0.0191, "step": 28400 }, { "loss_action": 0.01578277163207531, "loss_total": 0.01578277163207531, "step": 28400 }, { "grad_norm": 0.5207008123397827, "learning_rate": 8.575177296990873e-05, "loss": 0.0183, "step": 28410 }, { "loss_action": 0.015614908188581467, "loss_total": 0.015614908188581467, "step": 28410 }, { "grad_norm": 0.45405831933021545, "learning_rate": 8.574021180308489e-05, "loss": 0.0189, "step": 28420 }, { "loss_action": 0.019017670303583145, "loss_total": 0.019017670303583145, "step": 28420 }, { "grad_norm": 0.38652750849723816, "learning_rate": 8.572864672776523e-05, "loss": 0.0171, "step": 28430 }, { "loss_action": 0.01339149009436369, "loss_total": 0.01339149009436369, "step": 28430 }, { "grad_norm": 0.33829569816589355, "learning_rate": 8.571707774521447e-05, "loss": 0.016, "step": 28440 }, { "loss_action": 0.012637889944016933, "loss_total": 0.012637889944016933, "step": 28440 }, { "grad_norm": 0.31656041741371155, "learning_rate": 8.57055048566978e-05, "loss": 0.0146, "step": 28450 }, { "loss_action": 0.014128128997981548, "loss_total": 0.014128128997981548, "step": 28450 }, { "grad_norm": 0.31702038645744324, "learning_rate": 8.569392806348078e-05, "loss": 0.0149, "step": 28460 }, { "loss_action": 0.012428647838532925, "loss_total": 0.012428647838532925, "step": 28460 }, { "grad_norm": 0.35096096992492676, "learning_rate": 8.568234736682947e-05, "loss": 0.0152, "step": 28470 }, { "loss_action": 0.019182754680514336, "loss_total": 0.019182754680514336, "step": 28470 }, { "grad_norm": 0.3207610845565796, "learning_rate": 8.567076276801029e-05, "loss": 0.0164, "step": 28480 }, { "loss_action": 0.016566168516874313, "loss_total": 0.016566168516874313, "step": 28480 }, { "grad_norm": 0.3533709645271301, "learning_rate": 8.565917426829013e-05, "loss": 0.0157, "step": 28490 }, { "loss_action": 0.014760990627110004, "loss_total": 0.014760990627110004, "step": 28490 }, { "grad_norm": 0.40046191215515137, "learning_rate": 8.564758186893628e-05, "loss": 0.0167, "step": 28500 }, { "loss_action": 0.020049449056386948, "loss_total": 0.020049449056386948, "step": 28500 }, { "grad_norm": 0.39239805936813354, "learning_rate": 8.563598557121649e-05, "loss": 0.0163, "step": 28510 }, { "loss_action": 0.018893834203481674, "loss_total": 0.018893834203481674, "step": 28510 }, { "grad_norm": 0.27727004885673523, "learning_rate": 8.562438537639888e-05, "loss": 0.017, "step": 28520 }, { "loss_action": 0.020678922533988953, "loss_total": 0.020678922533988953, "step": 28520 }, { "grad_norm": 0.41707319021224976, "learning_rate": 8.561278128575206e-05, "loss": 0.0166, "step": 28530 }, { "loss_action": 0.01877574622631073, "loss_total": 0.01877574622631073, "step": 28530 }, { "grad_norm": 0.326932430267334, "learning_rate": 8.5601173300545e-05, "loss": 0.0159, "step": 28540 }, { "loss_action": 0.020235786214470863, "loss_total": 0.020235786214470863, "step": 28540 }, { "grad_norm": 0.34136804938316345, "learning_rate": 8.558956142204717e-05, "loss": 0.0176, "step": 28550 }, { "loss_action": 0.015812262892723083, "loss_total": 0.015812262892723083, "step": 28550 }, { "grad_norm": 0.3240182101726532, "learning_rate": 8.55779456515284e-05, "loss": 0.0159, "step": 28560 }, { "loss_action": 0.015691157430410385, "loss_total": 0.015691157430410385, "step": 28560 }, { "grad_norm": 0.37669622898101807, "learning_rate": 8.556632599025898e-05, "loss": 0.0153, "step": 28570 }, { "loss_action": 0.011961132287979126, "loss_total": 0.011961132287979126, "step": 28570 }, { "grad_norm": 0.32973334193229675, "learning_rate": 8.555470243950964e-05, "loss": 0.0164, "step": 28580 }, { "loss_action": 0.0126970699056983, "loss_total": 0.0126970699056983, "step": 28580 }, { "grad_norm": 0.30904272198677063, "learning_rate": 8.554307500055148e-05, "loss": 0.015, "step": 28590 }, { "loss_action": 0.02004673331975937, "loss_total": 0.02004673331975937, "step": 28590 }, { "grad_norm": 0.39214232563972473, "learning_rate": 8.553144367465609e-05, "loss": 0.0166, "step": 28600 }, { "loss_action": 0.012026699259877205, "loss_total": 0.012026699259877205, "step": 28600 }, { "grad_norm": 0.34785327315330505, "learning_rate": 8.551980846309544e-05, "loss": 0.0165, "step": 28610 }, { "loss_action": 0.019779158756136894, "loss_total": 0.019779158756136894, "step": 28610 }, { "grad_norm": 0.287820428609848, "learning_rate": 8.550816936714193e-05, "loss": 0.016, "step": 28620 }, { "loss_action": 0.014457100071012974, "loss_total": 0.014457100071012974, "step": 28620 }, { "grad_norm": 0.3278636038303375, "learning_rate": 8.549652638806841e-05, "loss": 0.0155, "step": 28630 }, { "loss_action": 0.015259255655109882, "loss_total": 0.015259255655109882, "step": 28630 }, { "grad_norm": 0.3105117082595825, "learning_rate": 8.548487952714812e-05, "loss": 0.0162, "step": 28640 }, { "loss_action": 0.015185839496552944, "loss_total": 0.015185839496552944, "step": 28640 }, { "grad_norm": 0.3479853570461273, "learning_rate": 8.547322878565478e-05, "loss": 0.015, "step": 28650 }, { "loss_action": 0.015749376267194748, "loss_total": 0.015749376267194748, "step": 28650 }, { "grad_norm": 0.4488523006439209, "learning_rate": 8.546157416486245e-05, "loss": 0.0164, "step": 28660 }, { "loss_action": 0.01183102373033762, "loss_total": 0.01183102373033762, "step": 28660 }, { "grad_norm": 0.3172065019607544, "learning_rate": 8.54499156660457e-05, "loss": 0.0162, "step": 28670 }, { "loss_action": 0.020318767055869102, "loss_total": 0.020318767055869102, "step": 28670 }, { "grad_norm": 0.3516276180744171, "learning_rate": 8.543825329047947e-05, "loss": 0.0169, "step": 28680 }, { "loss_action": 0.020425472408533096, "loss_total": 0.020425472408533096, "step": 28680 }, { "grad_norm": 0.33296850323677063, "learning_rate": 8.542658703943913e-05, "loss": 0.0187, "step": 28690 }, { "loss_action": 0.026208268478512764, "loss_total": 0.026208268478512764, "step": 28690 }, { "grad_norm": 0.293835312128067, "learning_rate": 8.541491691420051e-05, "loss": 0.0178, "step": 28700 }, { "loss_action": 0.013474492356181145, "loss_total": 0.013474492356181145, "step": 28700 }, { "grad_norm": 0.5065968632698059, "learning_rate": 8.54032429160398e-05, "loss": 0.0165, "step": 28710 }, { "loss_action": 0.015329791232943535, "loss_total": 0.015329791232943535, "step": 28710 }, { "grad_norm": 0.30484727025032043, "learning_rate": 8.539156504623369e-05, "loss": 0.0161, "step": 28720 }, { "loss_action": 0.017026903107762337, "loss_total": 0.017026903107762337, "step": 28720 }, { "grad_norm": 0.3239796757698059, "learning_rate": 8.537988330605923e-05, "loss": 0.0154, "step": 28730 }, { "loss_action": 0.012278794310986996, "loss_total": 0.012278794310986996, "step": 28730 }, { "grad_norm": 0.2678232192993164, "learning_rate": 8.536819769679393e-05, "loss": 0.0147, "step": 28740 }, { "loss_action": 0.012314393185079098, "loss_total": 0.012314393185079098, "step": 28740 }, { "grad_norm": 0.2925010323524475, "learning_rate": 8.53565082197157e-05, "loss": 0.014, "step": 28750 }, { "loss_action": 0.015792597085237503, "loss_total": 0.015792597085237503, "step": 28750 }, { "grad_norm": 0.38398462533950806, "learning_rate": 8.534481487610289e-05, "loss": 0.017, "step": 28760 }, { "loss_action": 0.019622137770056725, "loss_total": 0.019622137770056725, "step": 28760 }, { "grad_norm": 0.37262439727783203, "learning_rate": 8.533311766723428e-05, "loss": 0.016, "step": 28770 }, { "loss_action": 0.018526222556829453, "loss_total": 0.018526222556829453, "step": 28770 }, { "grad_norm": 0.3264584243297577, "learning_rate": 8.532141659438901e-05, "loss": 0.0164, "step": 28780 }, { "loss_action": 0.012968174181878567, "loss_total": 0.012968174181878567, "step": 28780 }, { "grad_norm": 0.33118242025375366, "learning_rate": 8.530971165884675e-05, "loss": 0.0156, "step": 28790 }, { "loss_action": 0.01949581317603588, "loss_total": 0.01949581317603588, "step": 28790 }, { "grad_norm": 0.3746507465839386, "learning_rate": 8.529800286188752e-05, "loss": 0.0165, "step": 28800 }, { "loss_action": 0.01632656529545784, "loss_total": 0.01632656529545784, "step": 28800 }, { "grad_norm": 0.3311171233654022, "learning_rate": 8.528629020479175e-05, "loss": 0.0154, "step": 28810 }, { "loss_action": 0.012902485206723213, "loss_total": 0.012902485206723213, "step": 28810 }, { "grad_norm": 0.3084712028503418, "learning_rate": 8.527457368884033e-05, "loss": 0.015, "step": 28820 }, { "loss_action": 0.018561985343694687, "loss_total": 0.018561985343694687, "step": 28820 }, { "grad_norm": 0.38318830728530884, "learning_rate": 8.526285331531458e-05, "loss": 0.0147, "step": 28830 }, { "loss_action": 0.014540310017764568, "loss_total": 0.014540310017764568, "step": 28830 }, { "grad_norm": 0.33168306946754456, "learning_rate": 8.525112908549621e-05, "loss": 0.0182, "step": 28840 }, { "loss_action": 0.013758999295532703, "loss_total": 0.013758999295532703, "step": 28840 }, { "grad_norm": 0.30639418959617615, "learning_rate": 8.523940100066735e-05, "loss": 0.0169, "step": 28850 }, { "loss_action": 0.013682740740478039, "loss_total": 0.013682740740478039, "step": 28850 }, { "grad_norm": 0.37614238262176514, "learning_rate": 8.52276690621106e-05, "loss": 0.0157, "step": 28860 }, { "loss_action": 0.016823599115014076, "loss_total": 0.016823599115014076, "step": 28860 }, { "grad_norm": 0.505231499671936, "learning_rate": 8.521593327110889e-05, "loss": 0.0183, "step": 28870 }, { "loss_action": 0.013683997094631195, "loss_total": 0.013683997094631195, "step": 28870 }, { "grad_norm": 0.49781888723373413, "learning_rate": 8.520419362894569e-05, "loss": 0.018, "step": 28880 }, { "loss_action": 0.01311643235385418, "loss_total": 0.01311643235385418, "step": 28880 }, { "grad_norm": 0.3432750999927521, "learning_rate": 8.51924501369048e-05, "loss": 0.017, "step": 28890 }, { "loss_action": 0.015433468855917454, "loss_total": 0.015433468855917454, "step": 28890 }, { "grad_norm": 0.41193559765815735, "learning_rate": 8.518070279627047e-05, "loss": 0.0178, "step": 28900 }, { "loss_action": 0.012430691160261631, "loss_total": 0.012430691160261631, "step": 28900 }, { "grad_norm": 0.3386845886707306, "learning_rate": 8.516895160832737e-05, "loss": 0.0161, "step": 28910 }, { "loss_action": 0.01854775659739971, "loss_total": 0.01854775659739971, "step": 28910 }, { "grad_norm": 0.34489667415618896, "learning_rate": 8.515719657436061e-05, "loss": 0.0147, "step": 28920 }, { "loss_action": 0.020814847201108932, "loss_total": 0.020814847201108932, "step": 28920 }, { "grad_norm": 0.36151963472366333, "learning_rate": 8.514543769565568e-05, "loss": 0.0154, "step": 28930 }, { "loss_action": 0.018113110214471817, "loss_total": 0.018113110214471817, "step": 28930 }, { "grad_norm": 0.41427648067474365, "learning_rate": 8.513367497349853e-05, "loss": 0.0142, "step": 28940 }, { "loss_action": 0.012944106943905354, "loss_total": 0.012944106943905354, "step": 28940 }, { "grad_norm": 0.4345109462738037, "learning_rate": 8.51219084091755e-05, "loss": 0.0165, "step": 28950 }, { "loss_action": 0.014009757898747921, "loss_total": 0.014009757898747921, "step": 28950 }, { "grad_norm": 0.504228949546814, "learning_rate": 8.511013800397338e-05, "loss": 0.0167, "step": 28960 }, { "loss_action": 0.019125206395983696, "loss_total": 0.019125206395983696, "step": 28960 }, { "grad_norm": 0.2811633050441742, "learning_rate": 8.509836375917937e-05, "loss": 0.0158, "step": 28970 }, { "loss_action": 0.020777812227606773, "loss_total": 0.020777812227606773, "step": 28970 }, { "grad_norm": 0.48035499453544617, "learning_rate": 8.508658567608104e-05, "loss": 0.0174, "step": 28980 }, { "loss_action": 0.015295182354748249, "loss_total": 0.015295182354748249, "step": 28980 }, { "grad_norm": 0.36392951011657715, "learning_rate": 8.507480375596647e-05, "loss": 0.0167, "step": 28990 }, { "loss_action": 0.018907925114035606, "loss_total": 0.018907925114035606, "step": 28990 }, { "grad_norm": 0.3657821714878082, "learning_rate": 8.506301800012408e-05, "loss": 0.0185, "step": 29000 }, { "loss_action": 0.01334400661289692, "loss_total": 0.01334400661289692, "step": 29000 }, { "grad_norm": 0.4597454369068146, "learning_rate": 8.505122840984278e-05, "loss": 0.0174, "step": 29010 }, { "loss_action": 0.018604671582579613, "loss_total": 0.018604671582579613, "step": 29010 }, { "grad_norm": 0.4214174747467041, "learning_rate": 8.503943498641182e-05, "loss": 0.0192, "step": 29020 }, { "loss_action": 0.01991160213947296, "loss_total": 0.01991160213947296, "step": 29020 }, { "grad_norm": 0.40266484022140503, "learning_rate": 8.502763773112095e-05, "loss": 0.0196, "step": 29030 }, { "loss_action": 0.02542664296925068, "loss_total": 0.02542664296925068, "step": 29030 }, { "grad_norm": 0.36437276005744934, "learning_rate": 8.501583664526026e-05, "loss": 0.0184, "step": 29040 }, { "loss_action": 0.015816984698176384, "loss_total": 0.015816984698176384, "step": 29040 }, { "grad_norm": 0.3752037286758423, "learning_rate": 8.500403173012032e-05, "loss": 0.0187, "step": 29050 }, { "loss_action": 0.02386527508497238, "loss_total": 0.02386527508497238, "step": 29050 }, { "grad_norm": 0.3237144947052002, "learning_rate": 8.499222298699211e-05, "loss": 0.0182, "step": 29060 }, { "loss_action": 0.02161845751106739, "loss_total": 0.02161845751106739, "step": 29060 }, { "grad_norm": 0.3529587984085083, "learning_rate": 8.498041041716701e-05, "loss": 0.016, "step": 29070 }, { "loss_action": 0.01366276666522026, "loss_total": 0.01366276666522026, "step": 29070 }, { "grad_norm": 0.32403865456581116, "learning_rate": 8.496859402193681e-05, "loss": 0.0162, "step": 29080 }, { "loss_action": 0.0166292916983366, "loss_total": 0.0166292916983366, "step": 29080 }, { "grad_norm": 0.3111485540866852, "learning_rate": 8.495677380259374e-05, "loss": 0.0164, "step": 29090 }, { "loss_action": 0.020748483017086983, "loss_total": 0.020748483017086983, "step": 29090 }, { "grad_norm": 0.3125210702419281, "learning_rate": 8.494494976043045e-05, "loss": 0.0178, "step": 29100 }, { "loss_action": 0.019263824447989464, "loss_total": 0.019263824447989464, "step": 29100 }, { "grad_norm": 0.2738015949726105, "learning_rate": 8.493312189673998e-05, "loss": 0.0177, "step": 29110 }, { "loss_action": 0.01659368723630905, "loss_total": 0.01659368723630905, "step": 29110 }, { "grad_norm": 0.4198225438594818, "learning_rate": 8.492129021281584e-05, "loss": 0.0159, "step": 29120 }, { "loss_action": 0.019964121282100677, "loss_total": 0.019964121282100677, "step": 29120 }, { "grad_norm": 0.3452708125114441, "learning_rate": 8.490945470995188e-05, "loss": 0.0175, "step": 29130 }, { "loss_action": 0.012854321859776974, "loss_total": 0.012854321859776974, "step": 29130 }, { "grad_norm": 0.5581620931625366, "learning_rate": 8.489761538944247e-05, "loss": 0.0148, "step": 29140 }, { "loss_action": 0.012248712591826916, "loss_total": 0.012248712591826916, "step": 29140 }, { "grad_norm": 0.3764880895614624, "learning_rate": 8.48857722525823e-05, "loss": 0.0181, "step": 29150 }, { "loss_action": 0.01847701333463192, "loss_total": 0.01847701333463192, "step": 29150 }, { "grad_norm": 0.47104156017303467, "learning_rate": 8.487392530066652e-05, "loss": 0.0177, "step": 29160 }, { "loss_action": 0.017890548333525658, "loss_total": 0.017890548333525658, "step": 29160 }, { "grad_norm": 0.46777093410491943, "learning_rate": 8.486207453499069e-05, "loss": 0.0164, "step": 29170 }, { "loss_action": 0.02215968631207943, "loss_total": 0.02215968631207943, "step": 29170 }, { "grad_norm": 0.3335549235343933, "learning_rate": 8.485021995685082e-05, "loss": 0.0172, "step": 29180 }, { "loss_action": 0.01750674471259117, "loss_total": 0.01750674471259117, "step": 29180 }, { "grad_norm": 0.3963470160961151, "learning_rate": 8.483836156754328e-05, "loss": 0.0172, "step": 29190 }, { "loss_action": 0.019394394010305405, "loss_total": 0.019394394010305405, "step": 29190 }, { "grad_norm": 0.2948947250843048, "learning_rate": 8.482649936836491e-05, "loss": 0.0172, "step": 29200 }, { "loss_action": 0.01470516249537468, "loss_total": 0.01470516249537468, "step": 29200 }, { "grad_norm": 0.3288860619068146, "learning_rate": 8.481463336061293e-05, "loss": 0.0186, "step": 29210 }, { "loss_action": 0.022519996389746666, "loss_total": 0.022519996389746666, "step": 29210 }, { "grad_norm": 0.29087164998054504, "learning_rate": 8.480276354558496e-05, "loss": 0.0186, "step": 29220 }, { "loss_action": 0.01983652263879776, "loss_total": 0.01983652263879776, "step": 29220 }, { "grad_norm": 0.35504573583602905, "learning_rate": 8.479088992457913e-05, "loss": 0.0188, "step": 29230 }, { "loss_action": 0.016767172142863274, "loss_total": 0.016767172142863274, "step": 29230 }, { "grad_norm": 0.28821659088134766, "learning_rate": 8.477901249889387e-05, "loss": 0.0172, "step": 29240 }, { "loss_action": 0.014109589159488678, "loss_total": 0.014109589159488678, "step": 29240 }, { "grad_norm": 0.361508309841156, "learning_rate": 8.47671312698281e-05, "loss": 0.0157, "step": 29250 }, { "loss_action": 0.014139405451714993, "loss_total": 0.014139405451714993, "step": 29250 }, { "grad_norm": 0.3000122010707855, "learning_rate": 8.475524623868112e-05, "loss": 0.0181, "step": 29260 }, { "loss_action": 0.015941496938467026, "loss_total": 0.015941496938467026, "step": 29260 }, { "grad_norm": 0.36030784249305725, "learning_rate": 8.474335740675266e-05, "loss": 0.0187, "step": 29270 }, { "loss_action": 0.020819485187530518, "loss_total": 0.020819485187530518, "step": 29270 }, { "grad_norm": 0.40717872977256775, "learning_rate": 8.473146477534289e-05, "loss": 0.0187, "step": 29280 }, { "loss_action": 0.023209592327475548, "loss_total": 0.023209592327475548, "step": 29280 }, { "grad_norm": 0.31623902916908264, "learning_rate": 8.471956834575232e-05, "loss": 0.0169, "step": 29290 }, { "loss_action": 0.02353614568710327, "loss_total": 0.02353614568710327, "step": 29290 }, { "grad_norm": 0.241840660572052, "learning_rate": 8.470766811928197e-05, "loss": 0.0165, "step": 29300 }, { "loss_action": 0.014244635589420795, "loss_total": 0.014244635589420795, "step": 29300 }, { "grad_norm": 0.26108065247535706, "learning_rate": 8.469576409723323e-05, "loss": 0.0146, "step": 29310 }, { "loss_action": 0.01850350759923458, "loss_total": 0.01850350759923458, "step": 29310 }, { "grad_norm": 0.30119913816452026, "learning_rate": 8.468385628090788e-05, "loss": 0.0165, "step": 29320 }, { "loss_action": 0.013180313631892204, "loss_total": 0.013180313631892204, "step": 29320 }, { "grad_norm": 0.22489608824253082, "learning_rate": 8.467194467160815e-05, "loss": 0.0153, "step": 29330 }, { "loss_action": 0.012709255330264568, "loss_total": 0.012709255330264568, "step": 29330 }, { "grad_norm": 0.3933242857456207, "learning_rate": 8.466002927063667e-05, "loss": 0.0181, "step": 29340 }, { "loss_action": 0.013431123457849026, "loss_total": 0.013431123457849026, "step": 29340 }, { "grad_norm": 0.5364819765090942, "learning_rate": 8.464811007929651e-05, "loss": 0.016, "step": 29350 }, { "loss_action": 0.013033942319452763, "loss_total": 0.013033942319452763, "step": 29350 }, { "grad_norm": 0.3000909686088562, "learning_rate": 8.463618709889114e-05, "loss": 0.0149, "step": 29360 }, { "loss_action": 0.013880944810807705, "loss_total": 0.013880944810807705, "step": 29360 }, { "grad_norm": 0.3459092080593109, "learning_rate": 8.462426033072442e-05, "loss": 0.0152, "step": 29370 }, { "loss_action": 0.015751339495182037, "loss_total": 0.015751339495182037, "step": 29370 }, { "grad_norm": 0.3182050883769989, "learning_rate": 8.461232977610061e-05, "loss": 0.0162, "step": 29380 }, { "loss_action": 0.015353167429566383, "loss_total": 0.015353167429566383, "step": 29380 }, { "grad_norm": 0.3433654010295868, "learning_rate": 8.46003954363245e-05, "loss": 0.0153, "step": 29390 }, { "loss_action": 0.017409661784768105, "loss_total": 0.017409661784768105, "step": 29390 }, { "grad_norm": 0.28596964478492737, "learning_rate": 8.458845731270115e-05, "loss": 0.0156, "step": 29400 }, { "loss_action": 0.012386679649353027, "loss_total": 0.012386679649353027, "step": 29400 }, { "grad_norm": 0.35117796063423157, "learning_rate": 8.45765154065361e-05, "loss": 0.0147, "step": 29410 }, { "loss_action": 0.011104314588010311, "loss_total": 0.011104314588010311, "step": 29410 }, { "grad_norm": 0.31089311838150024, "learning_rate": 8.456456971913532e-05, "loss": 0.0161, "step": 29420 }, { "loss_action": 0.014962555840611458, "loss_total": 0.014962555840611458, "step": 29420 }, { "grad_norm": 0.2948758006095886, "learning_rate": 8.455262025180517e-05, "loss": 0.0146, "step": 29430 }, { "loss_action": 0.014148990623652935, "loss_total": 0.014148990623652935, "step": 29430 }, { "grad_norm": 0.3327721357345581, "learning_rate": 8.454066700585242e-05, "loss": 0.0146, "step": 29440 }, { "loss_action": 0.0181715227663517, "loss_total": 0.0181715227663517, "step": 29440 }, { "grad_norm": 0.4500386118888855, "learning_rate": 8.452870998258423e-05, "loss": 0.0174, "step": 29450 }, { "loss_action": 0.015515611506998539, "loss_total": 0.015515611506998539, "step": 29450 }, { "grad_norm": 0.27114859223365784, "learning_rate": 8.451674918330825e-05, "loss": 0.016, "step": 29460 }, { "loss_action": 0.012041288428008556, "loss_total": 0.012041288428008556, "step": 29460 }, { "grad_norm": 0.3649594783782959, "learning_rate": 8.450478460933246e-05, "loss": 0.0174, "step": 29470 }, { "loss_action": 0.018525663763284683, "loss_total": 0.018525663763284683, "step": 29470 }, { "grad_norm": 0.3130607604980469, "learning_rate": 8.449281626196532e-05, "loss": 0.0166, "step": 29480 }, { "loss_action": 0.011414472945034504, "loss_total": 0.011414472945034504, "step": 29480 }, { "grad_norm": 0.29599806666374207, "learning_rate": 8.448084414251564e-05, "loss": 0.015, "step": 29490 }, { "loss_action": 0.016614394262433052, "loss_total": 0.016614394262433052, "step": 29490 }, { "grad_norm": 0.2900804281234741, "learning_rate": 8.446886825229271e-05, "loss": 0.0152, "step": 29500 }, { "loss_action": 0.01901102438569069, "loss_total": 0.01901102438569069, "step": 29500 }, { "grad_norm": 0.3734614849090576, "learning_rate": 8.445688859260615e-05, "loss": 0.0169, "step": 29510 }, { "loss_action": 0.013691985979676247, "loss_total": 0.013691985979676247, "step": 29510 }, { "grad_norm": 0.3860190510749817, "learning_rate": 8.444490516476606e-05, "loss": 0.0168, "step": 29520 }, { "loss_action": 0.01565956324338913, "loss_total": 0.01565956324338913, "step": 29520 }, { "grad_norm": 0.3422110974788666, "learning_rate": 8.443291797008293e-05, "loss": 0.0149, "step": 29530 }, { "loss_action": 0.020089121535420418, "loss_total": 0.020089121535420418, "step": 29530 }, { "grad_norm": 0.3213975727558136, "learning_rate": 8.442092700986765e-05, "loss": 0.0158, "step": 29540 }, { "loss_action": 0.01250925287604332, "loss_total": 0.01250925287604332, "step": 29540 }, { "grad_norm": 0.3173467516899109, "learning_rate": 8.440893228543156e-05, "loss": 0.0147, "step": 29550 }, { "loss_action": 0.015864957123994827, "loss_total": 0.015864957123994827, "step": 29550 }, { "grad_norm": 0.255574107170105, "learning_rate": 8.439693379808638e-05, "loss": 0.0158, "step": 29560 }, { "loss_action": 0.01619536615908146, "loss_total": 0.01619536615908146, "step": 29560 }, { "grad_norm": 0.35220375657081604, "learning_rate": 8.43849315491442e-05, "loss": 0.0148, "step": 29570 }, { "loss_action": 0.01536940224468708, "loss_total": 0.01536940224468708, "step": 29570 }, { "grad_norm": 0.30013349652290344, "learning_rate": 8.437292553991763e-05, "loss": 0.0131, "step": 29580 }, { "loss_action": 0.015540963970124722, "loss_total": 0.015540963970124722, "step": 29580 }, { "grad_norm": 0.367498517036438, "learning_rate": 8.436091577171959e-05, "loss": 0.0155, "step": 29590 }, { "loss_action": 0.014061592519283295, "loss_total": 0.014061592519283295, "step": 29590 }, { "grad_norm": 0.3545980453491211, "learning_rate": 8.434890224586347e-05, "loss": 0.0169, "step": 29600 }, { "loss_action": 0.019031044095754623, "loss_total": 0.019031044095754623, "step": 29600 }, { "grad_norm": 0.3052017390727997, "learning_rate": 8.433688496366303e-05, "loss": 0.0156, "step": 29610 }, { "loss_action": 0.014887213706970215, "loss_total": 0.014887213706970215, "step": 29610 }, { "grad_norm": 0.30982705950737, "learning_rate": 8.432486392643248e-05, "loss": 0.0146, "step": 29620 }, { "loss_action": 0.011879729107022285, "loss_total": 0.011879729107022285, "step": 29620 }, { "grad_norm": 0.3557073771953583, "learning_rate": 8.431283913548643e-05, "loss": 0.0146, "step": 29630 }, { "loss_action": 0.012479527853429317, "loss_total": 0.012479527853429317, "step": 29630 }, { "grad_norm": 0.35646384954452515, "learning_rate": 8.430081059213985e-05, "loss": 0.017, "step": 29640 }, { "loss_action": 0.016446975991129875, "loss_total": 0.016446975991129875, "step": 29640 }, { "grad_norm": 0.29334747791290283, "learning_rate": 8.428877829770823e-05, "loss": 0.0174, "step": 29650 }, { "loss_action": 0.0181183610111475, "loss_total": 0.0181183610111475, "step": 29650 }, { "grad_norm": 0.3481857180595398, "learning_rate": 8.427674225350735e-05, "loss": 0.017, "step": 29660 }, { "loss_action": 0.014546175487339497, "loss_total": 0.014546175487339497, "step": 29660 }, { "grad_norm": 0.3150389790534973, "learning_rate": 8.426470246085347e-05, "loss": 0.0161, "step": 29670 }, { "loss_action": 0.01587304286658764, "loss_total": 0.01587304286658764, "step": 29670 }, { "grad_norm": 0.4009445309638977, "learning_rate": 8.425265892106324e-05, "loss": 0.0177, "step": 29680 }, { "loss_action": 0.015965985134243965, "loss_total": 0.015965985134243965, "step": 29680 }, { "grad_norm": 0.370207816362381, "learning_rate": 8.424061163545374e-05, "loss": 0.0151, "step": 29690 }, { "loss_action": 0.013667453080415726, "loss_total": 0.013667453080415726, "step": 29690 }, { "grad_norm": 0.3669029772281647, "learning_rate": 8.422856060534243e-05, "loss": 0.0156, "step": 29700 }, { "loss_action": 0.013664232566952705, "loss_total": 0.013664232566952705, "step": 29700 }, { "grad_norm": 0.4048710763454437, "learning_rate": 8.421650583204718e-05, "loss": 0.0165, "step": 29710 }, { "loss_action": 0.0197699423879385, "loss_total": 0.0197699423879385, "step": 29710 }, { "grad_norm": 0.36876818537712097, "learning_rate": 8.420444731688633e-05, "loss": 0.0163, "step": 29720 }, { "loss_action": 0.01621863804757595, "loss_total": 0.01621863804757595, "step": 29720 }, { "grad_norm": 0.40051716566085815, "learning_rate": 8.419238506117852e-05, "loss": 0.0151, "step": 29730 }, { "loss_action": 0.022856000810861588, "loss_total": 0.022856000810861588, "step": 29730 }, { "grad_norm": 0.30515003204345703, "learning_rate": 8.418031906624289e-05, "loss": 0.018, "step": 29740 }, { "loss_action": 0.020244548097252846, "loss_total": 0.020244548097252846, "step": 29740 }, { "grad_norm": 0.3358171880245209, "learning_rate": 8.416824933339898e-05, "loss": 0.0171, "step": 29750 }, { "loss_action": 0.017978403717279434, "loss_total": 0.017978403717279434, "step": 29750 }, { "grad_norm": 0.3980855643749237, "learning_rate": 8.415617586396667e-05, "loss": 0.0163, "step": 29760 }, { "loss_action": 0.016361724585294724, "loss_total": 0.016361724585294724, "step": 29760 }, { "grad_norm": 0.295048326253891, "learning_rate": 8.414409865926632e-05, "loss": 0.0174, "step": 29770 }, { "loss_action": 0.012515791691839695, "loss_total": 0.012515791691839695, "step": 29770 }, { "grad_norm": 0.2990947365760803, "learning_rate": 8.413201772061867e-05, "loss": 0.0165, "step": 29780 }, { "loss_action": 0.014882240444421768, "loss_total": 0.014882240444421768, "step": 29780 }, { "grad_norm": 0.3437850773334503, "learning_rate": 8.411993304934488e-05, "loss": 0.0163, "step": 29790 }, { "loss_action": 0.015765024349093437, "loss_total": 0.015765024349093437, "step": 29790 }, { "grad_norm": 0.37305501103401184, "learning_rate": 8.410784464676654e-05, "loss": 0.0154, "step": 29800 }, { "loss_action": 0.015053658746182919, "loss_total": 0.015053658746182919, "step": 29800 }, { "grad_norm": 0.3214077651500702, "learning_rate": 8.409575251420556e-05, "loss": 0.0142, "step": 29810 }, { "loss_action": 0.014870090410113335, "loss_total": 0.014870090410113335, "step": 29810 }, { "grad_norm": 0.37277689576148987, "learning_rate": 8.408365665298435e-05, "loss": 0.0148, "step": 29820 }, { "loss_action": 0.019395586103200912, "loss_total": 0.019395586103200912, "step": 29820 }, { "grad_norm": 0.2994837760925293, "learning_rate": 8.40715570644257e-05, "loss": 0.0155, "step": 29830 }, { "loss_action": 0.015295675955712795, "loss_total": 0.015295675955712795, "step": 29830 }, { "grad_norm": 0.3359377384185791, "learning_rate": 8.40594537498528e-05, "loss": 0.0156, "step": 29840 }, { "loss_action": 0.015235893428325653, "loss_total": 0.015235893428325653, "step": 29840 }, { "grad_norm": 0.3385041058063507, "learning_rate": 8.404734671058924e-05, "loss": 0.0145, "step": 29850 }, { "loss_action": 0.01393580436706543, "loss_total": 0.01393580436706543, "step": 29850 }, { "grad_norm": 0.34010499715805054, "learning_rate": 8.403523594795902e-05, "loss": 0.0152, "step": 29860 }, { "loss_action": 0.01439716201275587, "loss_total": 0.01439716201275587, "step": 29860 }, { "grad_norm": 0.33773329854011536, "learning_rate": 8.402312146328659e-05, "loss": 0.0138, "step": 29870 }, { "loss_action": 0.011317416094243526, "loss_total": 0.011317416094243526, "step": 29870 }, { "grad_norm": 0.276163250207901, "learning_rate": 8.401100325789675e-05, "loss": 0.0145, "step": 29880 }, { "loss_action": 0.014962442219257355, "loss_total": 0.014962442219257355, "step": 29880 }, { "grad_norm": 0.32499992847442627, "learning_rate": 8.399888133311472e-05, "loss": 0.0151, "step": 29890 }, { "loss_action": 0.017813511192798615, "loss_total": 0.017813511192798615, "step": 29890 }, { "grad_norm": 0.27620744705200195, "learning_rate": 8.398675569026613e-05, "loss": 0.0137, "step": 29900 }, { "loss_action": 0.015762154012918472, "loss_total": 0.015762154012918472, "step": 29900 }, { "grad_norm": 0.35584819316864014, "learning_rate": 8.397462633067705e-05, "loss": 0.015, "step": 29910 }, { "loss_action": 0.020508933812379837, "loss_total": 0.020508933812379837, "step": 29910 }, { "grad_norm": 0.3407289385795593, "learning_rate": 8.396249325567392e-05, "loss": 0.0154, "step": 29920 }, { "loss_action": 0.01123744249343872, "loss_total": 0.01123744249343872, "step": 29920 }, { "grad_norm": 0.2525979280471802, "learning_rate": 8.395035646658357e-05, "loss": 0.0139, "step": 29930 }, { "loss_action": 0.012023203074932098, "loss_total": 0.012023203074932098, "step": 29930 }, { "grad_norm": 0.3215073347091675, "learning_rate": 8.39382159647333e-05, "loss": 0.0133, "step": 29940 }, { "loss_action": 0.01099952682852745, "loss_total": 0.01099952682852745, "step": 29940 }, { "grad_norm": 0.3833073377609253, "learning_rate": 8.392607175145075e-05, "loss": 0.0145, "step": 29950 }, { "loss_action": 0.013462461531162262, "loss_total": 0.013462461531162262, "step": 29950 }, { "grad_norm": 0.33015942573547363, "learning_rate": 8.3913923828064e-05, "loss": 0.0143, "step": 29960 }, { "loss_action": 0.014865593984723091, "loss_total": 0.014865593984723091, "step": 29960 }, { "grad_norm": 0.34768253564834595, "learning_rate": 8.390177219590152e-05, "loss": 0.0143, "step": 29970 }, { "loss_action": 0.011942512355744839, "loss_total": 0.011942512355744839, "step": 29970 }, { "grad_norm": 0.36901748180389404, "learning_rate": 8.388961685629222e-05, "loss": 0.0145, "step": 29980 }, { "loss_action": 0.021601486951112747, "loss_total": 0.021601486951112747, "step": 29980 }, { "grad_norm": 0.3140096366405487, "learning_rate": 8.387745781056536e-05, "loss": 0.0168, "step": 29990 }, { "loss_action": 0.01406561303883791, "loss_total": 0.01406561303883791, "step": 29990 }, { "grad_norm": 0.31683751940727234, "learning_rate": 8.386529506005065e-05, "loss": 0.0162, "step": 30000 }, { "loss_action": 0.015779653564095497, "loss_total": 0.015779653564095497, "step": 30000 }, { "grad_norm": 0.3124195635318756, "learning_rate": 8.38531286060782e-05, "loss": 0.0148, "step": 30010 }, { "loss_action": 0.018380215391516685, "loss_total": 0.018380215391516685, "step": 30010 }, { "grad_norm": 0.34801986813545227, "learning_rate": 8.384095844997849e-05, "loss": 0.0148, "step": 30020 }, { "loss_action": 0.017251433804631233, "loss_total": 0.017251433804631233, "step": 30020 }, { "grad_norm": 0.322404682636261, "learning_rate": 8.382878459308245e-05, "loss": 0.0141, "step": 30030 }, { "loss_action": 0.020558087155222893, "loss_total": 0.020558087155222893, "step": 30030 }, { "grad_norm": 0.40745484828948975, "learning_rate": 8.381660703672138e-05, "loss": 0.0166, "step": 30040 }, { "loss_action": 0.011657814495265484, "loss_total": 0.011657814495265484, "step": 30040 }, { "grad_norm": 0.31794339418411255, "learning_rate": 8.380442578222702e-05, "loss": 0.0134, "step": 30050 }, { "loss_action": 0.01722819358110428, "loss_total": 0.01722819358110428, "step": 30050 }, { "grad_norm": 0.34226658940315247, "learning_rate": 8.379224083093146e-05, "loss": 0.0146, "step": 30060 }, { "loss_action": 0.02040310762822628, "loss_total": 0.02040310762822628, "step": 30060 }, { "grad_norm": 0.4094950556755066, "learning_rate": 8.378005218416727e-05, "loss": 0.0153, "step": 30070 }, { "loss_action": 0.013323639519512653, "loss_total": 0.013323639519512653, "step": 30070 }, { "grad_norm": 0.33508601784706116, "learning_rate": 8.376785984326735e-05, "loss": 0.0153, "step": 30080 }, { "loss_action": 0.01600116863846779, "loss_total": 0.01600116863846779, "step": 30080 }, { "grad_norm": 0.6925395727157593, "learning_rate": 8.375566380956506e-05, "loss": 0.0174, "step": 30090 }, { "loss_action": 0.021067330613732338, "loss_total": 0.021067330613732338, "step": 30090 }, { "grad_norm": 0.7674288153648376, "learning_rate": 8.374346408439411e-05, "loss": 0.024, "step": 30100 }, { "loss_action": 0.028559323400259018, "loss_total": 0.028559323400259018, "step": 30100 }, { "grad_norm": 0.49653443694114685, "learning_rate": 8.373126066908868e-05, "loss": 0.029, "step": 30110 }, { "loss_action": 0.05739786848425865, "loss_total": 0.05739786848425865, "step": 30110 }, { "grad_norm": 0.4794243574142456, "learning_rate": 8.371905356498326e-05, "loss": 0.0271, "step": 30120 }, { "loss_action": 0.02519957907497883, "loss_total": 0.02519957907497883, "step": 30120 }, { "grad_norm": 0.3360801637172699, "learning_rate": 8.370684277341288e-05, "loss": 0.0221, "step": 30130 }, { "loss_action": 0.01640263944864273, "loss_total": 0.01640263944864273, "step": 30130 }, { "grad_norm": 0.30797863006591797, "learning_rate": 8.369462829571282e-05, "loss": 0.0166, "step": 30140 }, { "loss_action": 0.018751272931694984, "loss_total": 0.018751272931694984, "step": 30140 }, { "grad_norm": 0.4098825752735138, "learning_rate": 8.36824101332189e-05, "loss": 0.0161, "step": 30150 }, { "loss_action": 0.020214032381772995, "loss_total": 0.020214032381772995, "step": 30150 }, { "grad_norm": 0.3642691373825073, "learning_rate": 8.367018828726721e-05, "loss": 0.0181, "step": 30160 }, { "loss_action": 0.046675920486450195, "loss_total": 0.046675920486450195, "step": 30160 }, { "grad_norm": 0.5615362524986267, "learning_rate": 8.365796275919438e-05, "loss": 0.0259, "step": 30170 }, { "loss_action": 0.018431520089507103, "loss_total": 0.018431520089507103, "step": 30170 }, { "grad_norm": 0.4344547986984253, "learning_rate": 8.364573355033734e-05, "loss": 0.0205, "step": 30180 }, { "loss_action": 0.01809813641011715, "loss_total": 0.01809813641011715, "step": 30180 }, { "grad_norm": 0.4574221670627594, "learning_rate": 8.363350066203346e-05, "loss": 0.0246, "step": 30190 }, { "loss_action": 0.0231464970856905, "loss_total": 0.0231464970856905, "step": 30190 }, { "grad_norm": 0.47861751914024353, "learning_rate": 8.362126409562053e-05, "loss": 0.0241, "step": 30200 }, { "loss_action": 0.02228119596838951, "loss_total": 0.02228119596838951, "step": 30200 }, { "grad_norm": 0.5762732028961182, "learning_rate": 8.360902385243667e-05, "loss": 0.0201, "step": 30210 }, { "loss_action": 0.020915910601615906, "loss_total": 0.020915910601615906, "step": 30210 }, { "grad_norm": 0.3522303104400635, "learning_rate": 8.359677993382052e-05, "loss": 0.0235, "step": 30220 }, { "loss_action": 0.01803329959511757, "loss_total": 0.01803329959511757, "step": 30220 }, { "grad_norm": 0.4106220602989197, "learning_rate": 8.358453234111103e-05, "loss": 0.0189, "step": 30230 }, { "loss_action": 0.021512044593691826, "loss_total": 0.021512044593691826, "step": 30230 }, { "grad_norm": 0.38793236017227173, "learning_rate": 8.357228107564756e-05, "loss": 0.0179, "step": 30240 }, { "loss_action": 0.014349186792969704, "loss_total": 0.014349186792969704, "step": 30240 }, { "grad_norm": 0.3365361988544464, "learning_rate": 8.356002613876993e-05, "loss": 0.0191, "step": 30250 }, { "loss_action": 0.015765521675348282, "loss_total": 0.015765521675348282, "step": 30250 }, { "grad_norm": 0.301272451877594, "learning_rate": 8.35477675318183e-05, "loss": 0.0197, "step": 30260 }, { "loss_action": 0.018324576318264008, "loss_total": 0.018324576318264008, "step": 30260 }, { "grad_norm": 0.3487185537815094, "learning_rate": 8.353550525613323e-05, "loss": 0.0168, "step": 30270 }, { "loss_action": 0.012741999700665474, "loss_total": 0.012741999700665474, "step": 30270 }, { "grad_norm": 0.2623201608657837, "learning_rate": 8.352323931305572e-05, "loss": 0.015, "step": 30280 }, { "loss_action": 0.017178796231746674, "loss_total": 0.017178796231746674, "step": 30280 }, { "grad_norm": 0.2790846526622772, "learning_rate": 8.351096970392717e-05, "loss": 0.0176, "step": 30290 }, { "loss_action": 0.012036846950650215, "loss_total": 0.012036846950650215, "step": 30290 }, { "grad_norm": 0.292806476354599, "learning_rate": 8.349869643008937e-05, "loss": 0.0151, "step": 30300 }, { "loss_action": 0.014875613152980804, "loss_total": 0.014875613152980804, "step": 30300 }, { "grad_norm": 0.3283425569534302, "learning_rate": 8.348641949288449e-05, "loss": 0.017, "step": 30310 }, { "loss_action": 0.02007340081036091, "loss_total": 0.02007340081036091, "step": 30310 }, { "grad_norm": 0.36888328194618225, "learning_rate": 8.34741388936551e-05, "loss": 0.0175, "step": 30320 }, { "loss_action": 0.016420040279626846, "loss_total": 0.016420040279626846, "step": 30320 }, { "grad_norm": 0.28370535373687744, "learning_rate": 8.346185463374423e-05, "loss": 0.0165, "step": 30330 }, { "loss_action": 0.022847304120659828, "loss_total": 0.022847304120659828, "step": 30330 }, { "grad_norm": 0.28114053606987, "learning_rate": 8.344956671449524e-05, "loss": 0.0149, "step": 30340 }, { "loss_action": 0.01401115208864212, "loss_total": 0.01401115208864212, "step": 30340 }, { "grad_norm": 0.31411442160606384, "learning_rate": 8.343727513725192e-05, "loss": 0.0146, "step": 30350 }, { "loss_action": 0.016832813620567322, "loss_total": 0.016832813620567322, "step": 30350 }, { "grad_norm": 0.391236275434494, "learning_rate": 8.342497990335847e-05, "loss": 0.016, "step": 30360 }, { "loss_action": 0.015282399021089077, "loss_total": 0.015282399021089077, "step": 30360 }, { "grad_norm": 0.35368451476097107, "learning_rate": 8.341268101415946e-05, "loss": 0.0175, "step": 30370 }, { "loss_action": 0.016383623704314232, "loss_total": 0.016383623704314232, "step": 30370 }, { "grad_norm": 0.2986299991607666, "learning_rate": 8.34003784709999e-05, "loss": 0.0188, "step": 30380 }, { "loss_action": 0.015710020437836647, "loss_total": 0.015710020437836647, "step": 30380 }, { "grad_norm": 0.3168107271194458, "learning_rate": 8.338807227522516e-05, "loss": 0.0167, "step": 30390 }, { "loss_action": 0.015429329127073288, "loss_total": 0.015429329127073288, "step": 30390 }, { "grad_norm": 0.3771785795688629, "learning_rate": 8.337576242818103e-05, "loss": 0.017, "step": 30400 }, { "loss_action": 0.015003629960119724, "loss_total": 0.015003629960119724, "step": 30400 }, { "grad_norm": 0.25566503405570984, "learning_rate": 8.336344893121372e-05, "loss": 0.0155, "step": 30410 }, { "loss_action": 0.01440051756799221, "loss_total": 0.01440051756799221, "step": 30410 }, { "grad_norm": 0.3281134068965912, "learning_rate": 8.335113178566977e-05, "loss": 0.0146, "step": 30420 }, { "loss_action": 0.014128466136753559, "loss_total": 0.014128466136753559, "step": 30420 }, { "grad_norm": 0.2714206278324127, "learning_rate": 8.33388109928962e-05, "loss": 0.0155, "step": 30430 }, { "loss_action": 0.017384883016347885, "loss_total": 0.017384883016347885, "step": 30430 }, { "grad_norm": 0.3169732689857483, "learning_rate": 8.33264865542404e-05, "loss": 0.0137, "step": 30440 }, { "loss_action": 0.01363939419388771, "loss_total": 0.01363939419388771, "step": 30440 }, { "grad_norm": 0.3242238163948059, "learning_rate": 8.331415847105013e-05, "loss": 0.0145, "step": 30450 }, { "loss_action": 0.009953523054718971, "loss_total": 0.009953523054718971, "step": 30450 }, { "grad_norm": 0.3203352391719818, "learning_rate": 8.330182674467357e-05, "loss": 0.0144, "step": 30460 }, { "loss_action": 0.012456183321774006, "loss_total": 0.012456183321774006, "step": 30460 }, { "grad_norm": 0.2947641611099243, "learning_rate": 8.32894913764593e-05, "loss": 0.0143, "step": 30470 }, { "loss_action": 0.015701310709118843, "loss_total": 0.015701310709118843, "step": 30470 }, { "grad_norm": 0.4424325227737427, "learning_rate": 8.327715236775633e-05, "loss": 0.0162, "step": 30480 }, { "loss_action": 0.012571080587804317, "loss_total": 0.012571080587804317, "step": 30480 }, { "grad_norm": 0.5096340179443359, "learning_rate": 8.326480971991398e-05, "loss": 0.0171, "step": 30490 }, { "loss_action": 0.014352144673466682, "loss_total": 0.014352144673466682, "step": 30490 }, { "grad_norm": 0.4681883752346039, "learning_rate": 8.325246343428206e-05, "loss": 0.0166, "step": 30500 }, { "loss_action": 0.020791521295905113, "loss_total": 0.020791521295905113, "step": 30500 }, { "grad_norm": 0.31737735867500305, "learning_rate": 8.324011351221072e-05, "loss": 0.0164, "step": 30510 }, { "loss_action": 0.019191071391105652, "loss_total": 0.019191071391105652, "step": 30510 }, { "grad_norm": 0.2852948009967804, "learning_rate": 8.322775995505057e-05, "loss": 0.0165, "step": 30520 }, { "loss_action": 0.018540894612669945, "loss_total": 0.018540894612669945, "step": 30520 }, { "grad_norm": 0.2933722734451294, "learning_rate": 8.321540276415254e-05, "loss": 0.017, "step": 30530 }, { "loss_action": 0.01606069691479206, "loss_total": 0.01606069691479206, "step": 30530 }, { "grad_norm": 0.3692035377025604, "learning_rate": 8.320304194086798e-05, "loss": 0.0181, "step": 30540 }, { "loss_action": 0.015024487860500813, "loss_total": 0.015024487860500813, "step": 30540 }, { "grad_norm": 0.44592776894569397, "learning_rate": 8.31906774865487e-05, "loss": 0.0162, "step": 30550 }, { "loss_action": 0.013373684138059616, "loss_total": 0.013373684138059616, "step": 30550 }, { "grad_norm": 0.30851441621780396, "learning_rate": 8.317830940254682e-05, "loss": 0.0148, "step": 30560 }, { "loss_action": 0.011863432824611664, "loss_total": 0.011863432824611664, "step": 30560 }, { "grad_norm": 0.2857586145401001, "learning_rate": 8.316593769021491e-05, "loss": 0.0151, "step": 30570 }, { "loss_action": 0.0157182440161705, "loss_total": 0.0157182440161705, "step": 30570 }, { "grad_norm": 0.3111587464809418, "learning_rate": 8.315356235090592e-05, "loss": 0.0164, "step": 30580 }, { "loss_action": 0.01124342530965805, "loss_total": 0.01124342530965805, "step": 30580 }, { "grad_norm": 0.34559202194213867, "learning_rate": 8.314118338597319e-05, "loss": 0.0166, "step": 30590 }, { "loss_action": 0.01163505855947733, "loss_total": 0.01163505855947733, "step": 30590 }, { "grad_norm": 0.27672144770622253, "learning_rate": 8.312880079677048e-05, "loss": 0.0146, "step": 30600 }, { "loss_action": 0.014248525723814964, "loss_total": 0.014248525723814964, "step": 30600 }, { "grad_norm": 0.43783119320869446, "learning_rate": 8.311641458465191e-05, "loss": 0.0166, "step": 30610 }, { "loss_action": 0.02180579863488674, "loss_total": 0.02180579863488674, "step": 30610 }, { "grad_norm": 0.3579154312610626, "learning_rate": 8.310402475097205e-05, "loss": 0.0161, "step": 30620 }, { "loss_action": 0.016219237819314003, "loss_total": 0.016219237819314003, "step": 30620 }, { "grad_norm": 0.31864985823631287, "learning_rate": 8.309163129708581e-05, "loss": 0.0151, "step": 30630 }, { "loss_action": 0.010726386681199074, "loss_total": 0.010726386681199074, "step": 30630 }, { "grad_norm": 0.28885266184806824, "learning_rate": 8.307923422434852e-05, "loss": 0.0155, "step": 30640 }, { "loss_action": 0.013743232935667038, "loss_total": 0.013743232935667038, "step": 30640 }, { "grad_norm": 0.4139470160007477, "learning_rate": 8.30668335341159e-05, "loss": 0.0159, "step": 30650 }, { "loss_action": 0.018739735707640648, "loss_total": 0.018739735707640648, "step": 30650 }, { "grad_norm": 0.3242165446281433, "learning_rate": 8.305442922774408e-05, "loss": 0.0143, "step": 30660 }, { "loss_action": 0.018541796132922173, "loss_total": 0.018541796132922173, "step": 30660 }, { "grad_norm": 0.41181907057762146, "learning_rate": 8.304202130658959e-05, "loss": 0.0157, "step": 30670 }, { "loss_action": 0.017641959711909294, "loss_total": 0.017641959711909294, "step": 30670 }, { "grad_norm": 0.28929826617240906, "learning_rate": 8.302960977200931e-05, "loss": 0.0145, "step": 30680 }, { "loss_action": 0.011112777516245842, "loss_total": 0.011112777516245842, "step": 30680 }, { "grad_norm": 0.375216007232666, "learning_rate": 8.301719462536058e-05, "loss": 0.0141, "step": 30690 }, { "loss_action": 0.017717374488711357, "loss_total": 0.017717374488711357, "step": 30690 }, { "grad_norm": 0.2661598026752472, "learning_rate": 8.300477586800108e-05, "loss": 0.0159, "step": 30700 }, { "loss_action": 0.014029999263584614, "loss_total": 0.014029999263584614, "step": 30700 }, { "grad_norm": 0.27847182750701904, "learning_rate": 8.299235350128892e-05, "loss": 0.0136, "step": 30710 }, { "loss_action": 0.01225935947149992, "loss_total": 0.01225935947149992, "step": 30710 }, { "grad_norm": 0.27210700511932373, "learning_rate": 8.297992752658258e-05, "loss": 0.014, "step": 30720 }, { "loss_action": 0.02006973884999752, "loss_total": 0.02006973884999752, "step": 30720 }, { "grad_norm": 0.3010196089744568, "learning_rate": 8.296749794524094e-05, "loss": 0.0155, "step": 30730 }, { "loss_action": 0.018036704510450363, "loss_total": 0.018036704510450363, "step": 30730 }, { "grad_norm": 0.31916922330856323, "learning_rate": 8.295506475862332e-05, "loss": 0.0153, "step": 30740 }, { "loss_action": 0.013926097191870213, "loss_total": 0.013926097191870213, "step": 30740 }, { "grad_norm": 0.3752061426639557, "learning_rate": 8.294262796808933e-05, "loss": 0.0158, "step": 30750 }, { "loss_action": 0.0127866230905056, "loss_total": 0.0127866230905056, "step": 30750 }, { "grad_norm": 0.2950478196144104, "learning_rate": 8.293018757499909e-05, "loss": 0.0135, "step": 30760 }, { "loss_action": 0.019023939967155457, "loss_total": 0.019023939967155457, "step": 30760 }, { "grad_norm": 0.3822861909866333, "learning_rate": 8.291774358071305e-05, "loss": 0.016, "step": 30770 }, { "loss_action": 0.013486983254551888, "loss_total": 0.013486983254551888, "step": 30770 }, { "grad_norm": 0.24750570952892303, "learning_rate": 8.290529598659205e-05, "loss": 0.015, "step": 30780 }, { "loss_action": 0.013273320160806179, "loss_total": 0.013273320160806179, "step": 30780 }, { "grad_norm": 0.3698121905326843, "learning_rate": 8.289284479399738e-05, "loss": 0.0166, "step": 30790 }, { "loss_action": 0.013426811434328556, "loss_total": 0.013426811434328556, "step": 30790 }, { "grad_norm": 0.2960949242115021, "learning_rate": 8.288039000429064e-05, "loss": 0.0162, "step": 30800 }, { "loss_action": 0.015365507453680038, "loss_total": 0.015365507453680038, "step": 30800 }, { "grad_norm": 0.33871105313301086, "learning_rate": 8.286793161883388e-05, "loss": 0.0155, "step": 30810 }, { "loss_action": 0.02483646757900715, "loss_total": 0.02483646757900715, "step": 30810 }, { "grad_norm": 0.40913331508636475, "learning_rate": 8.285546963898954e-05, "loss": 0.0163, "step": 30820 }, { "loss_action": 0.01198255829513073, "loss_total": 0.01198255829513073, "step": 30820 }, { "grad_norm": 0.328365683555603, "learning_rate": 8.284300406612044e-05, "loss": 0.0156, "step": 30830 }, { "loss_action": 0.01916545443236828, "loss_total": 0.01916545443236828, "step": 30830 }, { "grad_norm": 0.284805566072464, "learning_rate": 8.283053490158978e-05, "loss": 0.0178, "step": 30840 }, { "loss_action": 0.013474631123244762, "loss_total": 0.013474631123244762, "step": 30840 }, { "grad_norm": 0.3485012650489807, "learning_rate": 8.28180621467612e-05, "loss": 0.014, "step": 30850 }, { "loss_action": 0.011885501444339752, "loss_total": 0.011885501444339752, "step": 30850 }, { "grad_norm": 0.2698841094970703, "learning_rate": 8.280558580299867e-05, "loss": 0.014, "step": 30860 }, { "loss_action": 0.019888509064912796, "loss_total": 0.019888509064912796, "step": 30860 }, { "grad_norm": 0.29712268710136414, "learning_rate": 8.279310587166661e-05, "loss": 0.015, "step": 30870 }, { "loss_action": 0.018397456035017967, "loss_total": 0.018397456035017967, "step": 30870 }, { "grad_norm": 0.30817773938179016, "learning_rate": 8.278062235412978e-05, "loss": 0.0174, "step": 30880 }, { "loss_action": 0.014220093376934528, "loss_total": 0.014220093376934528, "step": 30880 }, { "grad_norm": 0.33405616879463196, "learning_rate": 8.276813525175339e-05, "loss": 0.0153, "step": 30890 }, { "loss_action": 0.020032314583659172, "loss_total": 0.020032314583659172, "step": 30890 }, { "grad_norm": 0.33801594376564026, "learning_rate": 8.2755644565903e-05, "loss": 0.0148, "step": 30900 }, { "loss_action": 0.014683139510452747, "loss_total": 0.014683139510452747, "step": 30900 }, { "grad_norm": 0.35754069685935974, "learning_rate": 8.274315029794454e-05, "loss": 0.0159, "step": 30910 }, { "loss_action": 0.016193769872188568, "loss_total": 0.016193769872188568, "step": 30910 }, { "grad_norm": 0.2889944314956665, "learning_rate": 8.273065244924443e-05, "loss": 0.0155, "step": 30920 }, { "loss_action": 0.012235190719366074, "loss_total": 0.012235190719366074, "step": 30920 }, { "grad_norm": 0.33396992087364197, "learning_rate": 8.271815102116936e-05, "loss": 0.0136, "step": 30930 }, { "loss_action": 0.015422387979924679, "loss_total": 0.015422387979924679, "step": 30930 }, { "grad_norm": 0.3430304229259491, "learning_rate": 8.270564601508648e-05, "loss": 0.0156, "step": 30940 }, { "loss_action": 0.010740606114268303, "loss_total": 0.010740606114268303, "step": 30940 }, { "grad_norm": 0.3157012164592743, "learning_rate": 8.269313743236333e-05, "loss": 0.0132, "step": 30950 }, { "loss_action": 0.017408668994903564, "loss_total": 0.017408668994903564, "step": 30950 }, { "grad_norm": 0.33405473828315735, "learning_rate": 8.268062527436783e-05, "loss": 0.0128, "step": 30960 }, { "loss_action": 0.01026806328445673, "loss_total": 0.01026806328445673, "step": 30960 }, { "grad_norm": 0.31306570768356323, "learning_rate": 8.266810954246828e-05, "loss": 0.0153, "step": 30970 }, { "loss_action": 0.015223417431116104, "loss_total": 0.015223417431116104, "step": 30970 }, { "grad_norm": 0.3180846571922302, "learning_rate": 8.265559023803338e-05, "loss": 0.0142, "step": 30980 }, { "loss_action": 0.011343326419591904, "loss_total": 0.011343326419591904, "step": 30980 }, { "grad_norm": 0.33825525641441345, "learning_rate": 8.264306736243223e-05, "loss": 0.0146, "step": 30990 }, { "loss_action": 0.019159726798534393, "loss_total": 0.019159726798534393, "step": 30990 }, { "grad_norm": 0.3200575113296509, "learning_rate": 8.263054091703432e-05, "loss": 0.0159, "step": 31000 }, { "loss_action": 0.015711335465312004, "loss_total": 0.015711335465312004, "step": 31000 }, { "grad_norm": 0.25967350602149963, "learning_rate": 8.26180109032095e-05, "loss": 0.0156, "step": 31010 }, { "loss_action": 0.01543413195759058, "loss_total": 0.01543413195759058, "step": 31010 }, { "grad_norm": 0.33607766032218933, "learning_rate": 8.260547732232807e-05, "loss": 0.014, "step": 31020 }, { "loss_action": 0.011536013334989548, "loss_total": 0.011536013334989548, "step": 31020 }, { "grad_norm": 0.4643840789794922, "learning_rate": 8.259294017576063e-05, "loss": 0.0159, "step": 31030 }, { "loss_action": 0.015537864528596401, "loss_total": 0.015537864528596401, "step": 31030 }, { "grad_norm": 0.3353413939476013, "learning_rate": 8.258039946487828e-05, "loss": 0.0162, "step": 31040 }, { "loss_action": 0.021389110013842583, "loss_total": 0.021389110013842583, "step": 31040 }, { "grad_norm": 0.2819330394268036, "learning_rate": 8.256785519105241e-05, "loss": 0.0154, "step": 31050 }, { "loss_action": 0.011104486882686615, "loss_total": 0.011104486882686615, "step": 31050 }, { "grad_norm": 0.32177773118019104, "learning_rate": 8.255530735565488e-05, "loss": 0.0156, "step": 31060 }, { "loss_action": 0.014705929905176163, "loss_total": 0.014705929905176163, "step": 31060 }, { "grad_norm": 0.32531389594078064, "learning_rate": 8.254275596005787e-05, "loss": 0.0164, "step": 31070 }, { "loss_action": 0.014825732447206974, "loss_total": 0.014825732447206974, "step": 31070 }, { "grad_norm": 0.28239408135414124, "learning_rate": 8.2530201005634e-05, "loss": 0.0149, "step": 31080 }, { "loss_action": 0.02192465215921402, "loss_total": 0.02192465215921402, "step": 31080 }, { "grad_norm": 0.41779789328575134, "learning_rate": 8.251764249375626e-05, "loss": 0.0172, "step": 31090 }, { "loss_action": 0.022787759080529213, "loss_total": 0.022787759080529213, "step": 31090 }, { "grad_norm": 0.3763357400894165, "learning_rate": 8.250508042579803e-05, "loss": 0.0173, "step": 31100 }, { "loss_action": 0.015150272287428379, "loss_total": 0.015150272287428379, "step": 31100 }, { "grad_norm": 0.47431492805480957, "learning_rate": 8.249251480313307e-05, "loss": 0.0179, "step": 31110 }, { "loss_action": 0.028917260468006134, "loss_total": 0.028917260468006134, "step": 31110 }, { "grad_norm": 0.38001883029937744, "learning_rate": 8.247994562713555e-05, "loss": 0.0182, "step": 31120 }, { "loss_action": 0.014053605496883392, "loss_total": 0.014053605496883392, "step": 31120 }, { "grad_norm": 0.3425339162349701, "learning_rate": 8.246737289917998e-05, "loss": 0.0156, "step": 31130 }, { "loss_action": 0.013750584796071053, "loss_total": 0.013750584796071053, "step": 31130 }, { "grad_norm": 0.3104117810726166, "learning_rate": 8.245479662064135e-05, "loss": 0.0169, "step": 31140 }, { "loss_action": 0.016747236251831055, "loss_total": 0.016747236251831055, "step": 31140 }, { "grad_norm": 0.42505884170532227, "learning_rate": 8.244221679289496e-05, "loss": 0.0154, "step": 31150 }, { "loss_action": 0.013525839895009995, "loss_total": 0.013525839895009995, "step": 31150 }, { "grad_norm": 0.33794134855270386, "learning_rate": 8.242963341731652e-05, "loss": 0.0161, "step": 31160 }, { "loss_action": 0.022416608408093452, "loss_total": 0.022416608408093452, "step": 31160 }, { "grad_norm": 0.30194130539894104, "learning_rate": 8.24170464952821e-05, "loss": 0.0169, "step": 31170 }, { "loss_action": 0.01580824889242649, "loss_total": 0.01580824889242649, "step": 31170 }, { "grad_norm": 0.35543450713157654, "learning_rate": 8.240445602816824e-05, "loss": 0.0166, "step": 31180 }, { "loss_action": 0.01334673073142767, "loss_total": 0.01334673073142767, "step": 31180 }, { "grad_norm": 0.31180790066719055, "learning_rate": 8.239186201735179e-05, "loss": 0.0158, "step": 31190 }, { "loss_action": 0.012430868111550808, "loss_total": 0.012430868111550808, "step": 31190 }, { "grad_norm": 0.441794753074646, "learning_rate": 8.237926446420998e-05, "loss": 0.0165, "step": 31200 }, { "loss_action": 0.010977347381412983, "loss_total": 0.010977347381412983, "step": 31200 }, { "grad_norm": 0.249381422996521, "learning_rate": 8.236666337012052e-05, "loss": 0.0149, "step": 31210 }, { "loss_action": 0.017090942710638046, "loss_total": 0.017090942710638046, "step": 31210 }, { "grad_norm": 0.3609163761138916, "learning_rate": 8.23540587364614e-05, "loss": 0.0175, "step": 31220 }, { "loss_action": 0.021854864433407784, "loss_total": 0.021854864433407784, "step": 31220 }, { "grad_norm": 0.379578560590744, "learning_rate": 8.234145056461107e-05, "loss": 0.0167, "step": 31230 }, { "loss_action": 0.017182376235723495, "loss_total": 0.017182376235723495, "step": 31230 }, { "grad_norm": 0.3174736797809601, "learning_rate": 8.232883885594832e-05, "loss": 0.0136, "step": 31240 }, { "loss_action": 0.015972835943102837, "loss_total": 0.015972835943102837, "step": 31240 }, { "grad_norm": 0.31024372577667236, "learning_rate": 8.231622361185236e-05, "loss": 0.0163, "step": 31250 }, { "loss_action": 0.015288222581148148, "loss_total": 0.015288222581148148, "step": 31250 }, { "grad_norm": 0.23956520855426788, "learning_rate": 8.230360483370278e-05, "loss": 0.0149, "step": 31260 }, { "loss_action": 0.021055420860648155, "loss_total": 0.021055420860648155, "step": 31260 }, { "grad_norm": 0.32049575448036194, "learning_rate": 8.229098252287953e-05, "loss": 0.0151, "step": 31270 }, { "loss_action": 0.011910157278180122, "loss_total": 0.011910157278180122, "step": 31270 }, { "grad_norm": 0.37857529520988464, "learning_rate": 8.2278356680763e-05, "loss": 0.0157, "step": 31280 }, { "loss_action": 0.01452652458101511, "loss_total": 0.01452652458101511, "step": 31280 }, { "grad_norm": 0.2555035352706909, "learning_rate": 8.22657273087339e-05, "loss": 0.0132, "step": 31290 }, { "loss_action": 0.011085867881774902, "loss_total": 0.011085867881774902, "step": 31290 }, { "grad_norm": 0.2855583131313324, "learning_rate": 8.225309440817336e-05, "loss": 0.0143, "step": 31300 }, { "loss_action": 0.023846546187996864, "loss_total": 0.023846546187996864, "step": 31300 }, { "grad_norm": 0.3180033564567566, "learning_rate": 8.224045798046293e-05, "loss": 0.0159, "step": 31310 }, { "loss_action": 0.012923927046358585, "loss_total": 0.012923927046358585, "step": 31310 }, { "grad_norm": 0.3000625967979431, "learning_rate": 8.22278180269845e-05, "loss": 0.0146, "step": 31320 }, { "loss_action": 0.018157700076699257, "loss_total": 0.018157700076699257, "step": 31320 }, { "grad_norm": 0.34701812267303467, "learning_rate": 8.221517454912031e-05, "loss": 0.0142, "step": 31330 }, { "loss_action": 0.020233403891324997, "loss_total": 0.020233403891324997, "step": 31330 }, { "grad_norm": 0.4247168302536011, "learning_rate": 8.220252754825308e-05, "loss": 0.0158, "step": 31340 }, { "loss_action": 0.01914077252149582, "loss_total": 0.01914077252149582, "step": 31340 }, { "grad_norm": 0.2594624161720276, "learning_rate": 8.218987702576586e-05, "loss": 0.0152, "step": 31350 }, { "loss_action": 0.019533874467015266, "loss_total": 0.019533874467015266, "step": 31350 }, { "grad_norm": 0.36265143752098083, "learning_rate": 8.217722298304207e-05, "loss": 0.0173, "step": 31360 }, { "loss_action": 0.014251243323087692, "loss_total": 0.014251243323087692, "step": 31360 }, { "grad_norm": 0.3085576295852661, "learning_rate": 8.216456542146557e-05, "loss": 0.0138, "step": 31370 }, { "loss_action": 0.01992456056177616, "loss_total": 0.01992456056177616, "step": 31370 }, { "grad_norm": 0.39602041244506836, "learning_rate": 8.215190434242055e-05, "loss": 0.0182, "step": 31380 }, { "loss_action": 0.011937006376683712, "loss_total": 0.011937006376683712, "step": 31380 }, { "grad_norm": 0.4482070803642273, "learning_rate": 8.213923974729161e-05, "loss": 0.0164, "step": 31390 }, { "loss_action": 0.016692090779542923, "loss_total": 0.016692090779542923, "step": 31390 }, { "grad_norm": 0.3316895365715027, "learning_rate": 8.212657163746373e-05, "loss": 0.0155, "step": 31400 }, { "loss_action": 0.01132148876786232, "loss_total": 0.01132148876786232, "step": 31400 }, { "grad_norm": 0.3287264406681061, "learning_rate": 8.211390001432227e-05, "loss": 0.0145, "step": 31410 }, { "loss_action": 0.01843520998954773, "loss_total": 0.01843520998954773, "step": 31410 }, { "grad_norm": 0.3602040708065033, "learning_rate": 8.210122487925297e-05, "loss": 0.0148, "step": 31420 }, { "loss_action": 0.013405186124145985, "loss_total": 0.013405186124145985, "step": 31420 }, { "grad_norm": 0.37890639901161194, "learning_rate": 8.208854623364202e-05, "loss": 0.015, "step": 31430 }, { "loss_action": 0.01216971781104803, "loss_total": 0.01216971781104803, "step": 31430 }, { "grad_norm": 0.37582457065582275, "learning_rate": 8.207586407887589e-05, "loss": 0.0144, "step": 31440 }, { "loss_action": 0.013354535214602947, "loss_total": 0.013354535214602947, "step": 31440 }, { "grad_norm": 0.290890097618103, "learning_rate": 8.206317841634148e-05, "loss": 0.015, "step": 31450 }, { "loss_action": 0.013803267851471901, "loss_total": 0.013803267851471901, "step": 31450 }, { "grad_norm": 0.4290977418422699, "learning_rate": 8.205048924742609e-05, "loss": 0.0176, "step": 31460 }, { "loss_action": 0.014857707545161247, "loss_total": 0.014857707545161247, "step": 31460 }, { "grad_norm": 0.3183302581310272, "learning_rate": 8.203779657351738e-05, "loss": 0.0163, "step": 31470 }, { "loss_action": 0.01838514767587185, "loss_total": 0.01838514767587185, "step": 31470 }, { "grad_norm": 0.39744246006011963, "learning_rate": 8.20251003960034e-05, "loss": 0.0182, "step": 31480 }, { "loss_action": 0.015574702061712742, "loss_total": 0.015574702061712742, "step": 31480 }, { "grad_norm": 0.32082659006118774, "learning_rate": 8.201240071627258e-05, "loss": 0.0156, "step": 31490 }, { "loss_action": 0.013980792835354805, "loss_total": 0.013980792835354805, "step": 31490 }, { "grad_norm": 0.2913929522037506, "learning_rate": 8.199969753571377e-05, "loss": 0.017, "step": 31500 }, { "loss_action": 0.015262115746736526, "loss_total": 0.015262115746736526, "step": 31500 }, { "grad_norm": 0.26348286867141724, "learning_rate": 8.198699085571615e-05, "loss": 0.0158, "step": 31510 }, { "loss_action": 0.014634478837251663, "loss_total": 0.014634478837251663, "step": 31510 }, { "grad_norm": 0.4115264117717743, "learning_rate": 8.197428067766928e-05, "loss": 0.0165, "step": 31520 }, { "loss_action": 0.018723463639616966, "loss_total": 0.018723463639616966, "step": 31520 }, { "grad_norm": 0.3996098041534424, "learning_rate": 8.196156700296316e-05, "loss": 0.0153, "step": 31530 }, { "loss_action": 0.01317286305129528, "loss_total": 0.01317286305129528, "step": 31530 }, { "grad_norm": 0.45429718494415283, "learning_rate": 8.194884983298814e-05, "loss": 0.0138, "step": 31540 }, { "loss_action": 0.015270224772393703, "loss_total": 0.015270224772393703, "step": 31540 }, { "grad_norm": 0.3725566267967224, "learning_rate": 8.193612916913491e-05, "loss": 0.0151, "step": 31550 }, { "loss_action": 0.01229169499129057, "loss_total": 0.01229169499129057, "step": 31550 }, { "grad_norm": 0.4228571951389313, "learning_rate": 8.192340501279463e-05, "loss": 0.0142, "step": 31560 }, { "loss_action": 0.01591491512954235, "loss_total": 0.01591491512954235, "step": 31560 }, { "grad_norm": 0.352702260017395, "learning_rate": 8.191067736535876e-05, "loss": 0.016, "step": 31570 }, { "loss_action": 0.016291292384266853, "loss_total": 0.016291292384266853, "step": 31570 }, { "grad_norm": 0.26479867100715637, "learning_rate": 8.18979462282192e-05, "loss": 0.0159, "step": 31580 }, { "loss_action": 0.012833750806748867, "loss_total": 0.012833750806748867, "step": 31580 }, { "grad_norm": 0.32031404972076416, "learning_rate": 8.188521160276819e-05, "loss": 0.0155, "step": 31590 }, { "loss_action": 0.014418949373066425, "loss_total": 0.014418949373066425, "step": 31590 }, { "grad_norm": 0.3453679382801056, "learning_rate": 8.187247349039837e-05, "loss": 0.0141, "step": 31600 }, { "loss_action": 0.014266387559473515, "loss_total": 0.014266387559473515, "step": 31600 }, { "grad_norm": 0.40375828742980957, "learning_rate": 8.185973189250278e-05, "loss": 0.0163, "step": 31610 }, { "loss_action": 0.016146937385201454, "loss_total": 0.016146937385201454, "step": 31610 }, { "grad_norm": 0.46595537662506104, "learning_rate": 8.184698681047482e-05, "loss": 0.0181, "step": 31620 }, { "loss_action": 0.013139947317540646, "loss_total": 0.013139947317540646, "step": 31620 }, { "grad_norm": 0.30872392654418945, "learning_rate": 8.183423824570827e-05, "loss": 0.0149, "step": 31630 }, { "loss_action": 0.013011574745178223, "loss_total": 0.013011574745178223, "step": 31630 }, { "grad_norm": 0.2588799297809601, "learning_rate": 8.182148619959725e-05, "loss": 0.0145, "step": 31640 }, { "loss_action": 0.01926826499402523, "loss_total": 0.01926826499402523, "step": 31640 }, { "grad_norm": 0.28094929456710815, "learning_rate": 8.180873067353636e-05, "loss": 0.0145, "step": 31650 }, { "loss_action": 0.016373760998249054, "loss_total": 0.016373760998249054, "step": 31650 }, { "grad_norm": 0.30102771520614624, "learning_rate": 8.179597166892052e-05, "loss": 0.0138, "step": 31660 }, { "loss_action": 0.01250838115811348, "loss_total": 0.01250838115811348, "step": 31660 }, { "grad_norm": 0.3375367224216461, "learning_rate": 8.178320918714501e-05, "loss": 0.0125, "step": 31670 }, { "loss_action": 0.01368831004947424, "loss_total": 0.01368831004947424, "step": 31670 }, { "grad_norm": 0.3139190375804901, "learning_rate": 8.177044322960554e-05, "loss": 0.0147, "step": 31680 }, { "loss_action": 0.014573957771062851, "loss_total": 0.014573957771062851, "step": 31680 }, { "grad_norm": 0.3282058537006378, "learning_rate": 8.175767379769816e-05, "loss": 0.015, "step": 31690 }, { "loss_action": 0.0134651530534029, "loss_total": 0.0134651530534029, "step": 31690 }, { "grad_norm": 0.4406949579715729, "learning_rate": 8.174490089281932e-05, "loss": 0.0166, "step": 31700 }, { "loss_action": 0.01665286161005497, "loss_total": 0.01665286161005497, "step": 31700 }, { "grad_norm": 0.35022494196891785, "learning_rate": 8.173212451636584e-05, "loss": 0.0131, "step": 31710 }, { "loss_action": 0.015529180876910686, "loss_total": 0.015529180876910686, "step": 31710 }, { "grad_norm": 0.2498732954263687, "learning_rate": 8.171934466973493e-05, "loss": 0.0143, "step": 31720 }, { "loss_action": 0.014945381321012974, "loss_total": 0.014945381321012974, "step": 31720 }, { "grad_norm": 0.33159103989601135, "learning_rate": 8.170656135432418e-05, "loss": 0.015, "step": 31730 }, { "loss_action": 0.012047626078128815, "loss_total": 0.012047626078128815, "step": 31730 }, { "grad_norm": 0.3884093761444092, "learning_rate": 8.169377457153155e-05, "loss": 0.0135, "step": 31740 }, { "loss_action": 0.015429298393428326, "loss_total": 0.015429298393428326, "step": 31740 }, { "grad_norm": 0.37863317131996155, "learning_rate": 8.168098432275539e-05, "loss": 0.0143, "step": 31750 }, { "loss_action": 0.012184644117951393, "loss_total": 0.012184644117951393, "step": 31750 }, { "grad_norm": 0.23715531826019287, "learning_rate": 8.166819060939442e-05, "loss": 0.0129, "step": 31760 }, { "loss_action": 0.022602036595344543, "loss_total": 0.022602036595344543, "step": 31760 }, { "grad_norm": 0.3555161952972412, "learning_rate": 8.165539343284772e-05, "loss": 0.0156, "step": 31770 }, { "loss_action": 0.018376143649220467, "loss_total": 0.018376143649220467, "step": 31770 }, { "grad_norm": 0.36461371183395386, "learning_rate": 8.16425927945148e-05, "loss": 0.0149, "step": 31780 }, { "loss_action": 0.010535852052271366, "loss_total": 0.010535852052271366, "step": 31780 }, { "grad_norm": 0.35253238677978516, "learning_rate": 8.162978869579551e-05, "loss": 0.0153, "step": 31790 }, { "loss_action": 0.012767924927175045, "loss_total": 0.012767924927175045, "step": 31790 }, { "grad_norm": 0.3314904272556305, "learning_rate": 8.161698113809007e-05, "loss": 0.0153, "step": 31800 }, { "loss_action": 0.01644163392484188, "loss_total": 0.01644163392484188, "step": 31800 }, { "grad_norm": 0.32927337288856506, "learning_rate": 8.160417012279911e-05, "loss": 0.0152, "step": 31810 }, { "loss_action": 0.01184062846004963, "loss_total": 0.01184062846004963, "step": 31810 }, { "grad_norm": 0.28045570850372314, "learning_rate": 8.159135565132363e-05, "loss": 0.0154, "step": 31820 }, { "loss_action": 0.014577817171812057, "loss_total": 0.014577817171812057, "step": 31820 }, { "grad_norm": 0.39207544922828674, "learning_rate": 8.157853772506498e-05, "loss": 0.0148, "step": 31830 }, { "loss_action": 0.012291358783841133, "loss_total": 0.012291358783841133, "step": 31830 }, { "grad_norm": 0.33767375349998474, "learning_rate": 8.156571634542494e-05, "loss": 0.0135, "step": 31840 }, { "loss_action": 0.012580187059938908, "loss_total": 0.012580187059938908, "step": 31840 }, { "grad_norm": 0.3326406180858612, "learning_rate": 8.15528915138056e-05, "loss": 0.0163, "step": 31850 }, { "loss_action": 0.016293136402964592, "loss_total": 0.016293136402964592, "step": 31850 }, { "grad_norm": 0.2952468991279602, "learning_rate": 8.154006323160949e-05, "loss": 0.0156, "step": 31860 }, { "loss_action": 0.013525792397558689, "loss_total": 0.013525792397558689, "step": 31860 }, { "grad_norm": 0.3569748103618622, "learning_rate": 8.152723150023949e-05, "loss": 0.0176, "step": 31870 }, { "loss_action": 0.024631690233945847, "loss_total": 0.024631690233945847, "step": 31870 }, { "grad_norm": 0.2663556635379791, "learning_rate": 8.151439632109886e-05, "loss": 0.0154, "step": 31880 }, { "loss_action": 0.01665516011416912, "loss_total": 0.01665516011416912, "step": 31880 }, { "grad_norm": 0.30662205815315247, "learning_rate": 8.150155769559122e-05, "loss": 0.014, "step": 31890 }, { "loss_action": 0.010367472656071186, "loss_total": 0.010367472656071186, "step": 31890 }, { "grad_norm": 0.24807246029376984, "learning_rate": 8.148871562512058e-05, "loss": 0.0129, "step": 31900 }, { "loss_action": 0.01719669997692108, "loss_total": 0.01719669997692108, "step": 31900 }, { "grad_norm": 0.33449745178222656, "learning_rate": 8.147587011109136e-05, "loss": 0.0149, "step": 31910 }, { "loss_action": 0.013085856102406979, "loss_total": 0.013085856102406979, "step": 31910 }, { "grad_norm": 0.35602912306785583, "learning_rate": 8.14630211549083e-05, "loss": 0.0133, "step": 31920 }, { "loss_action": 0.019246406853199005, "loss_total": 0.019246406853199005, "step": 31920 }, { "grad_norm": 0.4689089059829712, "learning_rate": 8.145016875797655e-05, "loss": 0.0163, "step": 31930 }, { "loss_action": 0.011820746585726738, "loss_total": 0.011820746585726738, "step": 31930 }, { "grad_norm": 0.32194989919662476, "learning_rate": 8.143731292170164e-05, "loss": 0.0181, "step": 31940 }, { "loss_action": 0.013045983389019966, "loss_total": 0.013045983389019966, "step": 31940 }, { "grad_norm": 0.3224126398563385, "learning_rate": 8.142445364748944e-05, "loss": 0.0172, "step": 31950 }, { "loss_action": 0.015842273831367493, "loss_total": 0.015842273831367493, "step": 31950 }, { "grad_norm": 0.2917723059654236, "learning_rate": 8.141159093674624e-05, "loss": 0.0169, "step": 31960 }, { "loss_action": 0.012764536775648594, "loss_total": 0.012764536775648594, "step": 31960 }, { "grad_norm": 0.2779313325881958, "learning_rate": 8.139872479087869e-05, "loss": 0.0142, "step": 31970 }, { "loss_action": 0.016560127958655357, "loss_total": 0.016560127958655357, "step": 31970 }, { "grad_norm": 0.34190723299980164, "learning_rate": 8.13858552112938e-05, "loss": 0.0141, "step": 31980 }, { "loss_action": 0.011894242838025093, "loss_total": 0.011894242838025093, "step": 31980 }, { "grad_norm": 0.31871241331100464, "learning_rate": 8.137298219939895e-05, "loss": 0.0137, "step": 31990 }, { "loss_action": 0.01026911661028862, "loss_total": 0.01026911661028862, "step": 31990 }, { "grad_norm": 0.3139753043651581, "learning_rate": 8.136010575660196e-05, "loss": 0.0159, "step": 32000 }, { "loss_action": 0.021773435175418854, "loss_total": 0.021773435175418854, "step": 32000 }, { "grad_norm": 0.3095356225967407, "learning_rate": 8.134722588431095e-05, "loss": 0.0166, "step": 32010 }, { "loss_action": 0.014588119462132454, "loss_total": 0.014588119462132454, "step": 32010 }, { "grad_norm": 0.3225923180580139, "learning_rate": 8.133434258393444e-05, "loss": 0.0151, "step": 32020 }, { "loss_action": 0.011558085680007935, "loss_total": 0.011558085680007935, "step": 32020 }, { "grad_norm": 0.2497115135192871, "learning_rate": 8.132145585688134e-05, "loss": 0.014, "step": 32030 }, { "loss_action": 0.02106204256415367, "loss_total": 0.02106204256415367, "step": 32030 }, { "grad_norm": 0.403339684009552, "learning_rate": 8.130856570456093e-05, "loss": 0.0155, "step": 32040 }, { "loss_action": 0.014681780710816383, "loss_total": 0.014681780710816383, "step": 32040 }, { "grad_norm": 0.3145672678947449, "learning_rate": 8.129567212838283e-05, "loss": 0.0151, "step": 32050 }, { "loss_action": 0.015872636809945107, "loss_total": 0.015872636809945107, "step": 32050 }, { "grad_norm": 0.3246113359928131, "learning_rate": 8.128277512975708e-05, "loss": 0.0151, "step": 32060 }, { "loss_action": 0.014811298809945583, "loss_total": 0.014811298809945583, "step": 32060 }, { "grad_norm": 0.3127690851688385, "learning_rate": 8.126987471009408e-05, "loss": 0.0142, "step": 32070 }, { "loss_action": 0.013939183205366135, "loss_total": 0.013939183205366135, "step": 32070 }, { "grad_norm": 0.29522091150283813, "learning_rate": 8.125697087080459e-05, "loss": 0.0156, "step": 32080 }, { "loss_action": 0.014209159649908543, "loss_total": 0.014209159649908543, "step": 32080 }, { "grad_norm": 0.3096640110015869, "learning_rate": 8.124406361329976e-05, "loss": 0.0142, "step": 32090 }, { "loss_action": 0.011340482160449028, "loss_total": 0.011340482160449028, "step": 32090 }, { "grad_norm": 0.36711397767066956, "learning_rate": 8.123115293899111e-05, "loss": 0.0137, "step": 32100 }, { "loss_action": 0.014323598705232143, "loss_total": 0.014323598705232143, "step": 32100 }, { "grad_norm": 0.25084519386291504, "learning_rate": 8.121823884929055e-05, "loss": 0.013, "step": 32110 }, { "loss_action": 0.009166442789137363, "loss_total": 0.009166442789137363, "step": 32110 }, { "grad_norm": 0.3592456877231598, "learning_rate": 8.12053213456103e-05, "loss": 0.0138, "step": 32120 }, { "loss_action": 0.012464286759495735, "loss_total": 0.012464286759495735, "step": 32120 }, { "grad_norm": 0.3402372896671295, "learning_rate": 8.119240042936303e-05, "loss": 0.0139, "step": 32130 }, { "loss_action": 0.012954791076481342, "loss_total": 0.012954791076481342, "step": 32130 }, { "grad_norm": 0.34936708211898804, "learning_rate": 8.117947610196175e-05, "loss": 0.0131, "step": 32140 }, { "loss_action": 0.013088672421872616, "loss_total": 0.013088672421872616, "step": 32140 }, { "grad_norm": 0.46560394763946533, "learning_rate": 8.116654836481982e-05, "loss": 0.0138, "step": 32150 }, { "loss_action": 0.014600753784179688, "loss_total": 0.014600753784179688, "step": 32150 }, { "grad_norm": 0.4279055893421173, "learning_rate": 8.115361721935106e-05, "loss": 0.0165, "step": 32160 }, { "loss_action": 0.015311232767999172, "loss_total": 0.015311232767999172, "step": 32160 }, { "grad_norm": 0.35520288348197937, "learning_rate": 8.114068266696953e-05, "loss": 0.0162, "step": 32170 }, { "loss_action": 0.015118824318051338, "loss_total": 0.015118824318051338, "step": 32170 }, { "grad_norm": 0.3606310188770294, "learning_rate": 8.112774470908978e-05, "loss": 0.015, "step": 32180 }, { "loss_action": 0.022817425429821014, "loss_total": 0.022817425429821014, "step": 32180 }, { "grad_norm": 0.3309885561466217, "learning_rate": 8.111480334712665e-05, "loss": 0.0169, "step": 32190 }, { "loss_action": 0.016760975122451782, "loss_total": 0.016760975122451782, "step": 32190 }, { "grad_norm": 0.33583536744117737, "learning_rate": 8.110185858249542e-05, "loss": 0.015, "step": 32200 }, { "loss_action": 0.013614172115921974, "loss_total": 0.013614172115921974, "step": 32200 }, { "grad_norm": 0.4059239625930786, "learning_rate": 8.108891041661168e-05, "loss": 0.0165, "step": 32210 }, { "loss_action": 0.015554527752101421, "loss_total": 0.015554527752101421, "step": 32210 }, { "grad_norm": 0.347219318151474, "learning_rate": 8.107595885089146e-05, "loss": 0.0158, "step": 32220 }, { "loss_action": 0.012903785333037376, "loss_total": 0.012903785333037376, "step": 32220 }, { "grad_norm": 0.37959080934524536, "learning_rate": 8.106300388675108e-05, "loss": 0.0158, "step": 32230 }, { "loss_action": 0.014750814065337181, "loss_total": 0.014750814065337181, "step": 32230 }, { "grad_norm": 0.38312122225761414, "learning_rate": 8.105004552560731e-05, "loss": 0.0148, "step": 32240 }, { "loss_action": 0.020877888426184654, "loss_total": 0.020877888426184654, "step": 32240 }, { "grad_norm": 0.29693475365638733, "learning_rate": 8.103708376887724e-05, "loss": 0.0148, "step": 32250 }, { "loss_action": 0.013297496363520622, "loss_total": 0.013297496363520622, "step": 32250 }, { "grad_norm": 0.3048916757106781, "learning_rate": 8.102411861797836e-05, "loss": 0.0139, "step": 32260 }, { "loss_action": 0.014074081555008888, "loss_total": 0.014074081555008888, "step": 32260 }, { "grad_norm": 0.30400794744491577, "learning_rate": 8.101115007432851e-05, "loss": 0.015, "step": 32270 }, { "loss_action": 0.011342143639922142, "loss_total": 0.011342143639922142, "step": 32270 }, { "grad_norm": 0.3892802596092224, "learning_rate": 8.09981781393459e-05, "loss": 0.0156, "step": 32280 }, { "loss_action": 0.011364390142261982, "loss_total": 0.011364390142261982, "step": 32280 }, { "grad_norm": 0.3338025212287903, "learning_rate": 8.098520281444915e-05, "loss": 0.014, "step": 32290 }, { "loss_action": 0.01360150333493948, "loss_total": 0.01360150333493948, "step": 32290 }, { "grad_norm": 0.3139481246471405, "learning_rate": 8.09722241010572e-05, "loss": 0.0152, "step": 32300 }, { "loss_action": 0.01580492965877056, "loss_total": 0.01580492965877056, "step": 32300 }, { "grad_norm": 0.31442004442214966, "learning_rate": 8.095924200058939e-05, "loss": 0.0148, "step": 32310 }, { "loss_action": 0.011279797181487083, "loss_total": 0.011279797181487083, "step": 32310 }, { "grad_norm": 0.42125067114830017, "learning_rate": 8.094625651446541e-05, "loss": 0.0146, "step": 32320 }, { "loss_action": 0.012294705025851727, "loss_total": 0.012294705025851727, "step": 32320 }, { "grad_norm": 0.2928808033466339, "learning_rate": 8.093326764410536e-05, "loss": 0.0149, "step": 32330 }, { "loss_action": 0.014986146241426468, "loss_total": 0.014986146241426468, "step": 32330 }, { "grad_norm": 0.33266228437423706, "learning_rate": 8.092027539092966e-05, "loss": 0.0159, "step": 32340 }, { "loss_action": 0.014030626974999905, "loss_total": 0.014030626974999905, "step": 32340 }, { "grad_norm": 0.29760223627090454, "learning_rate": 8.090727975635913e-05, "loss": 0.0134, "step": 32350 }, { "loss_action": 0.015743324533104897, "loss_total": 0.015743324533104897, "step": 32350 }, { "grad_norm": 0.40814149379730225, "learning_rate": 8.089428074181497e-05, "loss": 0.0142, "step": 32360 }, { "loss_action": 0.01631125621497631, "loss_total": 0.01631125621497631, "step": 32360 }, { "grad_norm": 0.3880797028541565, "learning_rate": 8.088127834871871e-05, "loss": 0.0161, "step": 32370 }, { "loss_action": 0.012686621397733688, "loss_total": 0.012686621397733688, "step": 32370 }, { "grad_norm": 0.3983041048049927, "learning_rate": 8.086827257849226e-05, "loss": 0.0148, "step": 32380 }, { "loss_action": 0.0140010891482234, "loss_total": 0.0140010891482234, "step": 32380 }, { "grad_norm": 0.25310784578323364, "learning_rate": 8.085526343255795e-05, "loss": 0.0153, "step": 32390 }, { "loss_action": 0.011340619064867496, "loss_total": 0.011340619064867496, "step": 32390 }, { "grad_norm": 0.44778069853782654, "learning_rate": 8.084225091233842e-05, "loss": 0.0162, "step": 32400 }, { "loss_action": 0.014123832806944847, "loss_total": 0.014123832806944847, "step": 32400 }, { "grad_norm": 0.28138628602027893, "learning_rate": 8.082923501925668e-05, "loss": 0.0133, "step": 32410 }, { "loss_action": 0.014846445061266422, "loss_total": 0.014846445061266422, "step": 32410 }, { "grad_norm": 0.4296042025089264, "learning_rate": 8.081621575473617e-05, "loss": 0.0152, "step": 32420 }, { "loss_action": 0.012098489329218864, "loss_total": 0.012098489329218864, "step": 32420 }, { "grad_norm": 0.29936209321022034, "learning_rate": 8.080319312020064e-05, "loss": 0.0151, "step": 32430 }, { "loss_action": 0.016263071447610855, "loss_total": 0.016263071447610855, "step": 32430 }, { "grad_norm": 0.35743433237075806, "learning_rate": 8.079016711707421e-05, "loss": 0.0155, "step": 32440 }, { "loss_action": 0.012939627282321453, "loss_total": 0.012939627282321453, "step": 32440 }, { "grad_norm": 0.2861289083957672, "learning_rate": 8.077713774678139e-05, "loss": 0.0133, "step": 32450 }, { "loss_action": 0.01650567166507244, "loss_total": 0.01650567166507244, "step": 32450 }, { "grad_norm": 0.30454638600349426, "learning_rate": 8.076410501074707e-05, "loss": 0.014, "step": 32460 }, { "loss_action": 0.012419594451785088, "loss_total": 0.012419594451785088, "step": 32460 }, { "grad_norm": 0.29587844014167786, "learning_rate": 8.075106891039647e-05, "loss": 0.0138, "step": 32470 }, { "loss_action": 0.013292423449456692, "loss_total": 0.013292423449456692, "step": 32470 }, { "grad_norm": 0.24655519425868988, "learning_rate": 8.073802944715523e-05, "loss": 0.0133, "step": 32480 }, { "loss_action": 0.01338080782443285, "loss_total": 0.01338080782443285, "step": 32480 }, { "grad_norm": 0.33273258805274963, "learning_rate": 8.072498662244929e-05, "loss": 0.0143, "step": 32490 }, { "loss_action": 0.021476201713085175, "loss_total": 0.021476201713085175, "step": 32490 }, { "grad_norm": 0.31280896067619324, "learning_rate": 8.0711940437705e-05, "loss": 0.0161, "step": 32500 }, { "loss_action": 0.014742398634552956, "loss_total": 0.014742398634552956, "step": 32500 }, { "grad_norm": 0.28856050968170166, "learning_rate": 8.06988908943491e-05, "loss": 0.0142, "step": 32510 }, { "loss_action": 0.013477586209774017, "loss_total": 0.013477586209774017, "step": 32510 }, { "grad_norm": 0.263670414686203, "learning_rate": 8.068583799380863e-05, "loss": 0.0159, "step": 32520 }, { "loss_action": 0.01795363798737526, "loss_total": 0.01795363798737526, "step": 32520 }, { "grad_norm": 0.2923962473869324, "learning_rate": 8.067278173751104e-05, "loss": 0.0141, "step": 32530 }, { "loss_action": 0.01835070550441742, "loss_total": 0.01835070550441742, "step": 32530 }, { "grad_norm": 0.39465272426605225, "learning_rate": 8.065972212688417e-05, "loss": 0.0139, "step": 32540 }, { "loss_action": 0.013721358962357044, "loss_total": 0.013721358962357044, "step": 32540 }, { "grad_norm": 0.34635865688323975, "learning_rate": 8.064665916335618e-05, "loss": 0.0152, "step": 32550 }, { "loss_action": 0.013531137257814407, "loss_total": 0.013531137257814407, "step": 32550 }, { "grad_norm": 0.3425268828868866, "learning_rate": 8.063359284835564e-05, "loss": 0.0135, "step": 32560 }, { "loss_action": 0.016659578308463097, "loss_total": 0.016659578308463097, "step": 32560 }, { "grad_norm": 0.3136252164840698, "learning_rate": 8.062052318331142e-05, "loss": 0.0143, "step": 32570 }, { "loss_action": 0.01602708362042904, "loss_total": 0.01602708362042904, "step": 32570 }, { "grad_norm": 0.3321446180343628, "learning_rate": 8.060745016965283e-05, "loss": 0.0148, "step": 32580 }, { "loss_action": 0.011971847154200077, "loss_total": 0.011971847154200077, "step": 32580 }, { "grad_norm": 0.6312456130981445, "learning_rate": 8.059437380880952e-05, "loss": 0.0152, "step": 32590 }, { "loss_action": 0.022669734433293343, "loss_total": 0.022669734433293343, "step": 32590 }, { "grad_norm": 0.33703163266181946, "learning_rate": 8.058129410221146e-05, "loss": 0.0177, "step": 32600 }, { "loss_action": 0.019081830978393555, "loss_total": 0.019081830978393555, "step": 32600 }, { "grad_norm": 0.35749414563179016, "learning_rate": 8.056821105128908e-05, "loss": 0.0161, "step": 32610 }, { "loss_action": 0.0161640252918005, "loss_total": 0.0161640252918005, "step": 32610 }, { "grad_norm": 0.3634117841720581, "learning_rate": 8.05551246574731e-05, "loss": 0.0146, "step": 32620 }, { "loss_action": 0.012488728389143944, "loss_total": 0.012488728389143944, "step": 32620 }, { "grad_norm": 0.42820340394973755, "learning_rate": 8.05420349221946e-05, "loss": 0.0169, "step": 32630 }, { "loss_action": 0.013471730053424835, "loss_total": 0.013471730053424835, "step": 32630 }, { "grad_norm": 0.29696112871170044, "learning_rate": 8.05289418468851e-05, "loss": 0.0146, "step": 32640 }, { "loss_action": 0.01881774328649044, "loss_total": 0.01881774328649044, "step": 32640 }, { "grad_norm": 0.2948686182498932, "learning_rate": 8.051584543297642e-05, "loss": 0.0162, "step": 32650 }, { "loss_action": 0.013765175826847553, "loss_total": 0.013765175826847553, "step": 32650 }, { "grad_norm": 0.356424480676651, "learning_rate": 8.050274568190074e-05, "loss": 0.0152, "step": 32660 }, { "loss_action": 0.011869574896991253, "loss_total": 0.011869574896991253, "step": 32660 }, { "grad_norm": 0.38258785009384155, "learning_rate": 8.048964259509067e-05, "loss": 0.0149, "step": 32670 }, { "loss_action": 0.015605216845870018, "loss_total": 0.015605216845870018, "step": 32670 }, { "grad_norm": 0.30523478984832764, "learning_rate": 8.047653617397914e-05, "loss": 0.0153, "step": 32680 }, { "loss_action": 0.014378298074007034, "loss_total": 0.014378298074007034, "step": 32680 }, { "grad_norm": 0.30665114521980286, "learning_rate": 8.046342641999941e-05, "loss": 0.015, "step": 32690 }, { "loss_action": 0.019934825599193573, "loss_total": 0.019934825599193573, "step": 32690 }, { "grad_norm": 0.3488386571407318, "learning_rate": 8.045031333458517e-05, "loss": 0.0173, "step": 32700 }, { "loss_action": 0.01694139651954174, "loss_total": 0.01694139651954174, "step": 32700 }, { "grad_norm": 0.410539835691452, "learning_rate": 8.043719691917047e-05, "loss": 0.0149, "step": 32710 }, { "loss_action": 0.014423138462007046, "loss_total": 0.014423138462007046, "step": 32710 }, { "grad_norm": 0.27454623579978943, "learning_rate": 8.042407717518966e-05, "loss": 0.0133, "step": 32720 }, { "loss_action": 0.011820715852081776, "loss_total": 0.011820715852081776, "step": 32720 }, { "grad_norm": 0.27779462933540344, "learning_rate": 8.041095410407751e-05, "loss": 0.0136, "step": 32730 }, { "loss_action": 0.020509609952569008, "loss_total": 0.020509609952569008, "step": 32730 }, { "grad_norm": 0.30881190299987793, "learning_rate": 8.039782770726913e-05, "loss": 0.016, "step": 32740 }, { "loss_action": 0.018564455211162567, "loss_total": 0.018564455211162567, "step": 32740 }, { "grad_norm": 0.37793922424316406, "learning_rate": 8.038469798620004e-05, "loss": 0.0158, "step": 32750 }, { "loss_action": 0.013615435920655727, "loss_total": 0.013615435920655727, "step": 32750 }, { "grad_norm": 0.3252323865890503, "learning_rate": 8.037156494230604e-05, "loss": 0.015, "step": 32760 }, { "loss_action": 0.012978451326489449, "loss_total": 0.012978451326489449, "step": 32760 }, { "grad_norm": 0.3525349497795105, "learning_rate": 8.035842857702338e-05, "loss": 0.0143, "step": 32770 }, { "loss_action": 0.012689527124166489, "loss_total": 0.012689527124166489, "step": 32770 }, { "grad_norm": 0.3573794960975647, "learning_rate": 8.03452888917886e-05, "loss": 0.014, "step": 32780 }, { "loss_action": 0.013906741514801979, "loss_total": 0.013906741514801979, "step": 32780 }, { "grad_norm": 0.370004802942276, "learning_rate": 8.033214588803866e-05, "loss": 0.0135, "step": 32790 }, { "loss_action": 0.016830073669552803, "loss_total": 0.016830073669552803, "step": 32790 }, { "grad_norm": 0.2435920685529709, "learning_rate": 8.031899956721083e-05, "loss": 0.0129, "step": 32800 }, { "loss_action": 0.013583715073764324, "loss_total": 0.013583715073764324, "step": 32800 }, { "grad_norm": 0.46131017804145813, "learning_rate": 8.030584993074282e-05, "loss": 0.0129, "step": 32810 }, { "loss_action": 0.02008615806698799, "loss_total": 0.02008615806698799, "step": 32810 }, { "grad_norm": 0.3222810626029968, "learning_rate": 8.02926969800726e-05, "loss": 0.0155, "step": 32820 }, { "loss_action": 0.016047552227973938, "loss_total": 0.016047552227973938, "step": 32820 }, { "grad_norm": 0.3370330333709717, "learning_rate": 8.027954071663859e-05, "loss": 0.0141, "step": 32830 }, { "loss_action": 0.016195552423596382, "loss_total": 0.016195552423596382, "step": 32830 }, { "grad_norm": 0.29979392886161804, "learning_rate": 8.026638114187954e-05, "loss": 0.0168, "step": 32840 }, { "loss_action": 0.018225837498903275, "loss_total": 0.018225837498903275, "step": 32840 }, { "grad_norm": 0.3119872808456421, "learning_rate": 8.025321825723456e-05, "loss": 0.0152, "step": 32850 }, { "loss_action": 0.01612785831093788, "loss_total": 0.01612785831093788, "step": 32850 }, { "grad_norm": 0.35592809319496155, "learning_rate": 8.02400520641431e-05, "loss": 0.015, "step": 32860 }, { "loss_action": 0.01335274800658226, "loss_total": 0.01335274800658226, "step": 32860 }, { "grad_norm": 0.3362559676170349, "learning_rate": 8.022688256404501e-05, "loss": 0.0124, "step": 32870 }, { "loss_action": 0.017969423905014992, "loss_total": 0.017969423905014992, "step": 32870 }, { "grad_norm": 0.4228047728538513, "learning_rate": 8.02137097583805e-05, "loss": 0.0157, "step": 32880 }, { "loss_action": 0.017658913508057594, "loss_total": 0.017658913508057594, "step": 32880 }, { "grad_norm": 0.4752417206764221, "learning_rate": 8.02005336485901e-05, "loss": 0.0193, "step": 32890 }, { "loss_action": 0.01837320439517498, "loss_total": 0.01837320439517498, "step": 32890 }, { "grad_norm": 0.35367870330810547, "learning_rate": 8.018735423611476e-05, "loss": 0.017, "step": 32900 }, { "loss_action": 0.01688956469297409, "loss_total": 0.01688956469297409, "step": 32900 }, { "grad_norm": 0.38349348306655884, "learning_rate": 8.017417152239574e-05, "loss": 0.0164, "step": 32910 }, { "loss_action": 0.014535772614181042, "loss_total": 0.014535772614181042, "step": 32910 }, { "grad_norm": 0.38834619522094727, "learning_rate": 8.01609855088747e-05, "loss": 0.0165, "step": 32920 }, { "loss_action": 0.01298375055193901, "loss_total": 0.01298375055193901, "step": 32920 }, { "grad_norm": 0.39910539984703064, "learning_rate": 8.014779619699362e-05, "loss": 0.0154, "step": 32930 }, { "loss_action": 0.012890791520476341, "loss_total": 0.012890791520476341, "step": 32930 }, { "grad_norm": 0.30393290519714355, "learning_rate": 8.013460358819489e-05, "loss": 0.0165, "step": 32940 }, { "loss_action": 0.013715752400457859, "loss_total": 0.013715752400457859, "step": 32940 }, { "grad_norm": 0.3554856479167938, "learning_rate": 8.01214076839212e-05, "loss": 0.0152, "step": 32950 }, { "loss_action": 0.0122451763600111, "loss_total": 0.0122451763600111, "step": 32950 }, { "grad_norm": 0.3643186688423157, "learning_rate": 8.010820848561565e-05, "loss": 0.0147, "step": 32960 }, { "loss_action": 0.01762349344789982, "loss_total": 0.01762349344789982, "step": 32960 }, { "grad_norm": 0.3380812406539917, "learning_rate": 8.009500599472171e-05, "loss": 0.0177, "step": 32970 }, { "loss_action": 0.018208090215921402, "loss_total": 0.018208090215921402, "step": 32970 }, { "grad_norm": 0.35231122374534607, "learning_rate": 8.008180021268314e-05, "loss": 0.0157, "step": 32980 }, { "loss_action": 0.016226021572947502, "loss_total": 0.016226021572947502, "step": 32980 }, { "grad_norm": 0.3729858696460724, "learning_rate": 8.006859114094414e-05, "loss": 0.0178, "step": 32990 }, { "loss_action": 0.01185856107622385, "loss_total": 0.01185856107622385, "step": 32990 }, { "grad_norm": 0.36364084482192993, "learning_rate": 8.005537878094921e-05, "loss": 0.0161, "step": 33000 }, { "loss_action": 0.015501595102250576, "loss_total": 0.015501595102250576, "step": 33000 }, { "grad_norm": 0.25632017850875854, "learning_rate": 8.004216313414323e-05, "loss": 0.0151, "step": 33010 }, { "loss_action": 0.0191157478839159, "loss_total": 0.0191157478839159, "step": 33010 }, { "grad_norm": 0.3806668221950531, "learning_rate": 8.002894420197149e-05, "loss": 0.0172, "step": 33020 }, { "loss_action": 0.01698380894958973, "loss_total": 0.01698380894958973, "step": 33020 }, { "grad_norm": 0.33946412801742554, "learning_rate": 8.001572198587954e-05, "loss": 0.0175, "step": 33030 }, { "loss_action": 0.014520957134664059, "loss_total": 0.014520957134664059, "step": 33030 }, { "grad_norm": 0.24154318869113922, "learning_rate": 8.000249648731338e-05, "loss": 0.016, "step": 33040 }, { "loss_action": 0.013985749334096909, "loss_total": 0.013985749334096909, "step": 33040 }, { "grad_norm": 0.2961362898349762, "learning_rate": 7.998926770771928e-05, "loss": 0.0156, "step": 33050 }, { "loss_action": 0.01520615816116333, "loss_total": 0.01520615816116333, "step": 33050 }, { "grad_norm": 0.6349141001701355, "learning_rate": 7.997603564854397e-05, "loss": 0.0152, "step": 33060 }, { "loss_action": 0.013763761147856712, "loss_total": 0.013763761147856712, "step": 33060 }, { "grad_norm": 0.42295780777931213, "learning_rate": 7.996280031123448e-05, "loss": 0.0165, "step": 33070 }, { "loss_action": 0.017347954213619232, "loss_total": 0.017347954213619232, "step": 33070 }, { "grad_norm": 0.3527883291244507, "learning_rate": 7.994956169723818e-05, "loss": 0.0177, "step": 33080 }, { "loss_action": 0.01765427365899086, "loss_total": 0.01765427365899086, "step": 33080 }, { "grad_norm": 0.3261989951133728, "learning_rate": 7.993631980800285e-05, "loss": 0.0157, "step": 33090 }, { "loss_action": 0.012951195240020752, "loss_total": 0.012951195240020752, "step": 33090 }, { "grad_norm": 0.4163246750831604, "learning_rate": 7.992307464497659e-05, "loss": 0.0162, "step": 33100 }, { "loss_action": 0.013940548524260521, "loss_total": 0.013940548524260521, "step": 33100 }, { "grad_norm": 0.35485389828681946, "learning_rate": 7.990982620960787e-05, "loss": 0.015, "step": 33110 }, { "loss_action": 0.01587035320699215, "loss_total": 0.01587035320699215, "step": 33110 }, { "grad_norm": 0.48422855138778687, "learning_rate": 7.989657450334554e-05, "loss": 0.0159, "step": 33120 }, { "loss_action": 0.0177652295678854, "loss_total": 0.0177652295678854, "step": 33120 }, { "grad_norm": 0.48002541065216064, "learning_rate": 7.988331952763877e-05, "loss": 0.019, "step": 33130 }, { "loss_action": 0.015229958109557629, "loss_total": 0.015229958109557629, "step": 33130 }, { "grad_norm": 0.3925517797470093, "learning_rate": 7.987006128393709e-05, "loss": 0.0224, "step": 33140 }, { "loss_action": 0.02332104742527008, "loss_total": 0.02332104742527008, "step": 33140 }, { "grad_norm": 0.4167289733886719, "learning_rate": 7.985679977369043e-05, "loss": 0.0193, "step": 33150 }, { "loss_action": 0.01933198980987072, "loss_total": 0.01933198980987072, "step": 33150 }, { "grad_norm": 0.33450374007225037, "learning_rate": 7.984353499834902e-05, "loss": 0.0182, "step": 33160 }, { "loss_action": 0.017332620918750763, "loss_total": 0.017332620918750763, "step": 33160 }, { "grad_norm": 0.33155789971351624, "learning_rate": 7.983026695936351e-05, "loss": 0.0184, "step": 33170 }, { "loss_action": 0.01754741743206978, "loss_total": 0.01754741743206978, "step": 33170 }, { "grad_norm": 0.3113197982311249, "learning_rate": 7.981699565818486e-05, "loss": 0.0163, "step": 33180 }, { "loss_action": 0.01409956719726324, "loss_total": 0.01409956719726324, "step": 33180 }, { "grad_norm": 0.3133094906806946, "learning_rate": 7.980372109626437e-05, "loss": 0.0143, "step": 33190 }, { "loss_action": 0.017136314883828163, "loss_total": 0.017136314883828163, "step": 33190 }, { "grad_norm": 0.32063400745391846, "learning_rate": 7.979044327505375e-05, "loss": 0.0148, "step": 33200 }, { "loss_action": 0.014237185008823872, "loss_total": 0.014237185008823872, "step": 33200 }, { "grad_norm": 0.35213756561279297, "learning_rate": 7.977716219600506e-05, "loss": 0.0129, "step": 33210 }, { "loss_action": 0.013489965349435806, "loss_total": 0.013489965349435806, "step": 33210 }, { "grad_norm": 0.278320848941803, "learning_rate": 7.97638778605707e-05, "loss": 0.0148, "step": 33220 }, { "loss_action": 0.015641434118151665, "loss_total": 0.015641434118151665, "step": 33220 }, { "grad_norm": 0.30066603422164917, "learning_rate": 7.975059027020338e-05, "loss": 0.013, "step": 33230 }, { "loss_action": 0.015407877042889595, "loss_total": 0.015407877042889595, "step": 33230 }, { "grad_norm": 0.32410427927970886, "learning_rate": 7.973729942635623e-05, "loss": 0.0137, "step": 33240 }, { "loss_action": 0.024162761867046356, "loss_total": 0.024162761867046356, "step": 33240 }, { "grad_norm": 0.3576151430606842, "learning_rate": 7.972400533048273e-05, "loss": 0.0163, "step": 33250 }, { "loss_action": 0.012548188678920269, "loss_total": 0.012548188678920269, "step": 33250 }, { "grad_norm": 0.2706642746925354, "learning_rate": 7.97107079840367e-05, "loss": 0.0154, "step": 33260 }, { "loss_action": 0.018864668905735016, "loss_total": 0.018864668905735016, "step": 33260 }, { "grad_norm": 0.3387805223464966, "learning_rate": 7.969740738847231e-05, "loss": 0.0163, "step": 33270 }, { "loss_action": 0.014421189203858376, "loss_total": 0.014421189203858376, "step": 33270 }, { "grad_norm": 0.2980855107307434, "learning_rate": 7.968410354524411e-05, "loss": 0.0146, "step": 33280 }, { "loss_action": 0.011449352838099003, "loss_total": 0.011449352838099003, "step": 33280 }, { "grad_norm": 0.33108454942703247, "learning_rate": 7.967079645580697e-05, "loss": 0.014, "step": 33290 }, { "loss_action": 0.013135748915374279, "loss_total": 0.013135748915374279, "step": 33290 }, { "grad_norm": 0.3677687644958496, "learning_rate": 7.965748612161612e-05, "loss": 0.0152, "step": 33300 }, { "loss_action": 0.019742537289857864, "loss_total": 0.019742537289857864, "step": 33300 }, { "grad_norm": 0.25606435537338257, "learning_rate": 7.96441725441272e-05, "loss": 0.0149, "step": 33310 }, { "loss_action": 0.014913142658770084, "loss_total": 0.014913142658770084, "step": 33310 }, { "grad_norm": 0.5133190155029297, "learning_rate": 7.963085572479614e-05, "loss": 0.015, "step": 33320 }, { "loss_action": 0.019457710906863213, "loss_total": 0.019457710906863213, "step": 33320 }, { "grad_norm": 0.6316227912902832, "learning_rate": 7.961753566507924e-05, "loss": 0.0191, "step": 33330 }, { "loss_action": 0.0130792036652565, "loss_total": 0.0130792036652565, "step": 33330 }, { "grad_norm": 0.29492995142936707, "learning_rate": 7.960421236643316e-05, "loss": 0.0146, "step": 33340 }, { "loss_action": 0.011846380308270454, "loss_total": 0.011846380308270454, "step": 33340 }, { "grad_norm": 0.27628055214881897, "learning_rate": 7.959088583031496e-05, "loss": 0.0155, "step": 33350 }, { "loss_action": 0.012025892734527588, "loss_total": 0.012025892734527588, "step": 33350 }, { "grad_norm": 0.3024212419986725, "learning_rate": 7.957755605818194e-05, "loss": 0.014, "step": 33360 }, { "loss_action": 0.013509823009371758, "loss_total": 0.013509823009371758, "step": 33360 }, { "grad_norm": 0.31828221678733826, "learning_rate": 7.956422305149185e-05, "loss": 0.014, "step": 33370 }, { "loss_action": 0.021842166781425476, "loss_total": 0.021842166781425476, "step": 33370 }, { "grad_norm": 0.2929702401161194, "learning_rate": 7.95508868117028e-05, "loss": 0.014, "step": 33380 }, { "loss_action": 0.016496695578098297, "loss_total": 0.016496695578098297, "step": 33380 }, { "grad_norm": 0.2962276041507721, "learning_rate": 7.953754734027318e-05, "loss": 0.0138, "step": 33390 }, { "loss_action": 0.01584072969853878, "loss_total": 0.01584072969853878, "step": 33390 }, { "grad_norm": 0.3313053846359253, "learning_rate": 7.952420463866182e-05, "loss": 0.0144, "step": 33400 }, { "loss_action": 0.020060552284121513, "loss_total": 0.020060552284121513, "step": 33400 }, { "grad_norm": 0.2719596028327942, "learning_rate": 7.951085870832782e-05, "loss": 0.0147, "step": 33410 }, { "loss_action": 0.011072516441345215, "loss_total": 0.011072516441345215, "step": 33410 }, { "grad_norm": 0.33595189452171326, "learning_rate": 7.949750955073067e-05, "loss": 0.0144, "step": 33420 }, { "loss_action": 0.011453279294073582, "loss_total": 0.011453279294073582, "step": 33420 }, { "grad_norm": 0.31592756509780884, "learning_rate": 7.948415716733022e-05, "loss": 0.0137, "step": 33430 }, { "loss_action": 0.01779756136238575, "loss_total": 0.01779756136238575, "step": 33430 }, { "grad_norm": 0.316925585269928, "learning_rate": 7.947080155958669e-05, "loss": 0.0141, "step": 33440 }, { "loss_action": 0.013322120532393456, "loss_total": 0.013322120532393456, "step": 33440 }, { "grad_norm": 0.22298984229564667, "learning_rate": 7.94574427289606e-05, "loss": 0.0136, "step": 33450 }, { "loss_action": 0.020553894340991974, "loss_total": 0.020553894340991974, "step": 33450 }, { "grad_norm": 0.2567172050476074, "learning_rate": 7.944408067691284e-05, "loss": 0.0143, "step": 33460 }, { "loss_action": 0.015038443729281425, "loss_total": 0.015038443729281425, "step": 33460 }, { "grad_norm": 0.3827536106109619, "learning_rate": 7.943071540490473e-05, "loss": 0.0143, "step": 33470 }, { "loss_action": 0.010780292563140392, "loss_total": 0.010780292563140392, "step": 33470 }, { "grad_norm": 0.33095958828926086, "learning_rate": 7.94173469143978e-05, "loss": 0.0128, "step": 33480 }, { "loss_action": 0.012217031791806221, "loss_total": 0.012217031791806221, "step": 33480 }, { "grad_norm": 0.3294290006160736, "learning_rate": 7.940397520685406e-05, "loss": 0.0135, "step": 33490 }, { "loss_action": 0.01234358362853527, "loss_total": 0.01234358362853527, "step": 33490 }, { "grad_norm": 0.2989943027496338, "learning_rate": 7.939060028373577e-05, "loss": 0.0146, "step": 33500 }, { "loss_action": 0.015544251538813114, "loss_total": 0.015544251538813114, "step": 33500 }, { "grad_norm": 0.3650375008583069, "learning_rate": 7.937722214650565e-05, "loss": 0.0132, "step": 33510 }, { "loss_action": 0.015465343371033669, "loss_total": 0.015465343371033669, "step": 33510 }, { "grad_norm": 0.3185453414916992, "learning_rate": 7.936384079662666e-05, "loss": 0.0137, "step": 33520 }, { "loss_action": 0.013660728000104427, "loss_total": 0.013660728000104427, "step": 33520 }, { "grad_norm": 0.39267587661743164, "learning_rate": 7.93504562355622e-05, "loss": 0.0133, "step": 33530 }, { "loss_action": 0.012963064946234226, "loss_total": 0.012963064946234226, "step": 33530 }, { "grad_norm": 0.26815065741539, "learning_rate": 7.933706846477599e-05, "loss": 0.0141, "step": 33540 }, { "loss_action": 0.01705140247941017, "loss_total": 0.01705140247941017, "step": 33540 }, { "grad_norm": 0.24071666598320007, "learning_rate": 7.932367748573206e-05, "loss": 0.0135, "step": 33550 }, { "loss_action": 0.014736699871718884, "loss_total": 0.014736699871718884, "step": 33550 }, { "grad_norm": 0.32078713178634644, "learning_rate": 7.931028329989485e-05, "loss": 0.0145, "step": 33560 }, { "loss_action": 0.011705772951245308, "loss_total": 0.011705772951245308, "step": 33560 }, { "grad_norm": 0.3284096419811249, "learning_rate": 7.929688590872913e-05, "loss": 0.013, "step": 33570 }, { "loss_action": 0.013133091852068901, "loss_total": 0.013133091852068901, "step": 33570 }, { "grad_norm": 0.292502760887146, "learning_rate": 7.928348531370003e-05, "loss": 0.0127, "step": 33580 }, { "loss_action": 0.013076664879918098, "loss_total": 0.013076664879918098, "step": 33580 }, { "grad_norm": 0.2681015133857727, "learning_rate": 7.927008151627297e-05, "loss": 0.0136, "step": 33590 }, { "loss_action": 0.015032099559903145, "loss_total": 0.015032099559903145, "step": 33590 }, { "grad_norm": 0.3060396611690521, "learning_rate": 7.925667451791383e-05, "loss": 0.0131, "step": 33600 }, { "loss_action": 0.011964201927185059, "loss_total": 0.011964201927185059, "step": 33600 }, { "grad_norm": 0.364033043384552, "learning_rate": 7.924326432008874e-05, "loss": 0.0143, "step": 33610 }, { "loss_action": 0.018945761024951935, "loss_total": 0.018945761024951935, "step": 33610 }, { "grad_norm": 0.44108787178993225, "learning_rate": 7.922985092426422e-05, "loss": 0.0155, "step": 33620 }, { "loss_action": 0.015871724113821983, "loss_total": 0.015871724113821983, "step": 33620 }, { "grad_norm": 0.38701561093330383, "learning_rate": 7.921643433190717e-05, "loss": 0.0166, "step": 33630 }, { "loss_action": 0.013621152378618717, "loss_total": 0.013621152378618717, "step": 33630 }, { "grad_norm": 0.3571307063102722, "learning_rate": 7.920301454448478e-05, "loss": 0.0154, "step": 33640 }, { "loss_action": 0.021967872977256775, "loss_total": 0.021967872977256775, "step": 33640 }, { "grad_norm": 0.39909031987190247, "learning_rate": 7.918959156346461e-05, "loss": 0.0171, "step": 33650 }, { "loss_action": 0.02264503948390484, "loss_total": 0.02264503948390484, "step": 33650 }, { "grad_norm": 0.4951630234718323, "learning_rate": 7.91761653903146e-05, "loss": 0.0238, "step": 33660 }, { "loss_action": 0.02346639335155487, "loss_total": 0.02346639335155487, "step": 33660 }, { "grad_norm": 0.39250531792640686, "learning_rate": 7.916273602650302e-05, "loss": 0.0215, "step": 33670 }, { "loss_action": 0.023218831047415733, "loss_total": 0.023218831047415733, "step": 33670 }, { "grad_norm": 0.30607765913009644, "learning_rate": 7.914930347349847e-05, "loss": 0.0194, "step": 33680 }, { "loss_action": 0.018470535054802895, "loss_total": 0.018470535054802895, "step": 33680 }, { "grad_norm": 0.42841607332229614, "learning_rate": 7.913586773276992e-05, "loss": 0.018, "step": 33690 }, { "loss_action": 0.023269198834896088, "loss_total": 0.023269198834896088, "step": 33690 }, { "grad_norm": 0.2763206958770752, "learning_rate": 7.912242880578667e-05, "loss": 0.0173, "step": 33700 }, { "loss_action": 0.01564633473753929, "loss_total": 0.01564633473753929, "step": 33700 }, { "grad_norm": 0.35721370577812195, "learning_rate": 7.910898669401839e-05, "loss": 0.0179, "step": 33710 }, { "loss_action": 0.014206130057573318, "loss_total": 0.014206130057573318, "step": 33710 }, { "grad_norm": 0.45226964354515076, "learning_rate": 7.909554139893511e-05, "loss": 0.0167, "step": 33720 }, { "loss_action": 0.013152720406651497, "loss_total": 0.013152720406651497, "step": 33720 }, { "grad_norm": 0.34417128562927246, "learning_rate": 7.908209292200715e-05, "loss": 0.016, "step": 33730 }, { "loss_action": 0.01961648091673851, "loss_total": 0.01961648091673851, "step": 33730 }, { "grad_norm": 0.4390123188495636, "learning_rate": 7.906864126470523e-05, "loss": 0.0162, "step": 33740 }, { "loss_action": 0.015026875771582127, "loss_total": 0.015026875771582127, "step": 33740 }, { "grad_norm": 0.42515870928764343, "learning_rate": 7.905518642850041e-05, "loss": 0.0162, "step": 33750 }, { "loss_action": 0.01542470883578062, "loss_total": 0.01542470883578062, "step": 33750 }, { "grad_norm": 0.38068827986717224, "learning_rate": 7.904172841486409e-05, "loss": 0.0169, "step": 33760 }, { "loss_action": 0.019877253100275993, "loss_total": 0.019877253100275993, "step": 33760 }, { "grad_norm": 0.32922056317329407, "learning_rate": 7.902826722526801e-05, "loss": 0.0165, "step": 33770 }, { "loss_action": 0.01567000336945057, "loss_total": 0.01567000336945057, "step": 33770 }, { "grad_norm": 0.33298930525779724, "learning_rate": 7.901480286118427e-05, "loss": 0.0158, "step": 33780 }, { "loss_action": 0.015219432301819324, "loss_total": 0.015219432301819324, "step": 33780 }, { "grad_norm": 0.4803207814693451, "learning_rate": 7.900133532408531e-05, "loss": 0.0178, "step": 33790 }, { "loss_action": 0.017270781099796295, "loss_total": 0.017270781099796295, "step": 33790 }, { "grad_norm": 0.3002844452857971, "learning_rate": 7.898786461544395e-05, "loss": 0.0151, "step": 33800 }, { "loss_action": 0.016986330971121788, "loss_total": 0.016986330971121788, "step": 33800 }, { "grad_norm": 0.38557168841362, "learning_rate": 7.897439073673325e-05, "loss": 0.0181, "step": 33810 }, { "loss_action": 0.015203005634248257, "loss_total": 0.015203005634248257, "step": 33810 }, { "grad_norm": 0.2925843596458435, "learning_rate": 7.896091368942677e-05, "loss": 0.0156, "step": 33820 }, { "loss_action": 0.017953399568796158, "loss_total": 0.017953399568796158, "step": 33820 }, { "grad_norm": 0.33953186869621277, "learning_rate": 7.894743347499832e-05, "loss": 0.0164, "step": 33830 }, { "loss_action": 0.01116262748837471, "loss_total": 0.01116262748837471, "step": 33830 }, { "grad_norm": 0.4360548257827759, "learning_rate": 7.893395009492203e-05, "loss": 0.0171, "step": 33840 }, { "loss_action": 0.014655300416052341, "loss_total": 0.014655300416052341, "step": 33840 }, { "grad_norm": 0.4773542582988739, "learning_rate": 7.892046355067248e-05, "loss": 0.0152, "step": 33850 }, { "loss_action": 0.017763644456863403, "loss_total": 0.017763644456863403, "step": 33850 }, { "grad_norm": 0.3365478217601776, "learning_rate": 7.890697384372451e-05, "loss": 0.0172, "step": 33860 }, { "loss_action": 0.01822241209447384, "loss_total": 0.01822241209447384, "step": 33860 }, { "grad_norm": 0.3032027781009674, "learning_rate": 7.889348097555336e-05, "loss": 0.0166, "step": 33870 }, { "loss_action": 0.012757162563502789, "loss_total": 0.012757162563502789, "step": 33870 }, { "grad_norm": 0.30771687626838684, "learning_rate": 7.887998494763455e-05, "loss": 0.0145, "step": 33880 }, { "loss_action": 0.013357598334550858, "loss_total": 0.013357598334550858, "step": 33880 }, { "grad_norm": 0.3475659191608429, "learning_rate": 7.886648576144404e-05, "loss": 0.0153, "step": 33890 }, { "loss_action": 0.014673045836389065, "loss_total": 0.014673045836389065, "step": 33890 }, { "grad_norm": 0.30746737122535706, "learning_rate": 7.885298341845802e-05, "loss": 0.0149, "step": 33900 }, { "loss_action": 0.013204296119511127, "loss_total": 0.013204296119511127, "step": 33900 }, { "grad_norm": 0.3748128116130829, "learning_rate": 7.883947792015311e-05, "loss": 0.0159, "step": 33910 }, { "loss_action": 0.014026080258190632, "loss_total": 0.014026080258190632, "step": 33910 }, { "grad_norm": 0.36641383171081543, "learning_rate": 7.882596926800628e-05, "loss": 0.0158, "step": 33920 }, { "loss_action": 0.010626903735101223, "loss_total": 0.010626903735101223, "step": 33920 }, { "grad_norm": 0.2563241124153137, "learning_rate": 7.881245746349477e-05, "loss": 0.0123, "step": 33930 }, { "loss_action": 0.015072643756866455, "loss_total": 0.015072643756866455, "step": 33930 }, { "grad_norm": 0.3238678574562073, "learning_rate": 7.879894250809623e-05, "loss": 0.0144, "step": 33940 }, { "loss_action": 0.019395267590880394, "loss_total": 0.019395267590880394, "step": 33940 }, { "grad_norm": 0.3880998194217682, "learning_rate": 7.878542440328865e-05, "loss": 0.0155, "step": 33950 }, { "loss_action": 0.016165252774953842, "loss_total": 0.016165252774953842, "step": 33950 }, { "grad_norm": 0.297699898481369, "learning_rate": 7.877190315055031e-05, "loss": 0.0149, "step": 33960 }, { "loss_action": 0.022382298484444618, "loss_total": 0.022382298484444618, "step": 33960 }, { "grad_norm": 0.35170915722846985, "learning_rate": 7.875837875135991e-05, "loss": 0.0154, "step": 33970 }, { "loss_action": 0.014065640047192574, "loss_total": 0.014065640047192574, "step": 33970 }, { "grad_norm": 0.2940627336502075, "learning_rate": 7.874485120719646e-05, "loss": 0.0138, "step": 33980 }, { "loss_action": 0.010116969235241413, "loss_total": 0.010116969235241413, "step": 33980 }, { "grad_norm": 0.28521299362182617, "learning_rate": 7.873132051953928e-05, "loss": 0.0132, "step": 33990 }, { "loss_action": 0.010886047035455704, "loss_total": 0.010886047035455704, "step": 33990 }, { "grad_norm": 0.26654303073883057, "learning_rate": 7.87177866898681e-05, "loss": 0.0156, "step": 34000 }, { "loss_action": 0.01489601656794548, "loss_total": 0.01489601656794548, "step": 34000 }, { "grad_norm": 0.3108956217765808, "learning_rate": 7.870424971966294e-05, "loss": 0.0151, "step": 34010 }, { "loss_action": 0.013964204117655754, "loss_total": 0.013964204117655754, "step": 34010 }, { "grad_norm": 0.260498970746994, "learning_rate": 7.869070961040419e-05, "loss": 0.0136, "step": 34020 }, { "loss_action": 0.014719627797603607, "loss_total": 0.014719627797603607, "step": 34020 }, { "grad_norm": 0.41792693734169006, "learning_rate": 7.867716636357257e-05, "loss": 0.0147, "step": 34030 }, { "loss_action": 0.012404315173625946, "loss_total": 0.012404315173625946, "step": 34030 }, { "grad_norm": 0.31496667861938477, "learning_rate": 7.866361998064915e-05, "loss": 0.013, "step": 34040 }, { "loss_action": 0.01539499033242464, "loss_total": 0.01539499033242464, "step": 34040 }, { "grad_norm": 0.31784671545028687, "learning_rate": 7.865007046311534e-05, "loss": 0.0147, "step": 34050 }, { "loss_action": 0.015971994027495384, "loss_total": 0.015971994027495384, "step": 34050 }, { "grad_norm": 0.3034810423851013, "learning_rate": 7.86365178124529e-05, "loss": 0.0148, "step": 34060 }, { "loss_action": 0.015545125119388103, "loss_total": 0.015545125119388103, "step": 34060 }, { "grad_norm": 0.2693823575973511, "learning_rate": 7.862296203014394e-05, "loss": 0.0143, "step": 34070 }, { "loss_action": 0.012480352073907852, "loss_total": 0.012480352073907852, "step": 34070 }, { "grad_norm": 0.2966235876083374, "learning_rate": 7.860940311767088e-05, "loss": 0.0145, "step": 34080 }, { "loss_action": 0.011468561366200447, "loss_total": 0.011468561366200447, "step": 34080 }, { "grad_norm": 0.4010178744792938, "learning_rate": 7.85958410765165e-05, "loss": 0.0156, "step": 34090 }, { "loss_action": 0.016163749620318413, "loss_total": 0.016163749620318413, "step": 34090 }, { "grad_norm": 0.3165563642978668, "learning_rate": 7.858227590816394e-05, "loss": 0.0162, "step": 34100 }, { "loss_action": 0.0148418378084898, "loss_total": 0.0148418378084898, "step": 34100 }, { "grad_norm": 0.2875734269618988, "learning_rate": 7.856870761409664e-05, "loss": 0.0149, "step": 34110 }, { "loss_action": 0.022674497216939926, "loss_total": 0.022674497216939926, "step": 34110 }, { "grad_norm": 0.3343266248703003, "learning_rate": 7.855513619579846e-05, "loss": 0.0146, "step": 34120 }, { "loss_action": 0.017493490129709244, "loss_total": 0.017493490129709244, "step": 34120 }, { "grad_norm": 0.3266727924346924, "learning_rate": 7.85415616547535e-05, "loss": 0.014, "step": 34130 }, { "loss_action": 0.018988141790032387, "loss_total": 0.018988141790032387, "step": 34130 }, { "grad_norm": 0.2723531126976013, "learning_rate": 7.852798399244627e-05, "loss": 0.0151, "step": 34140 }, { "loss_action": 0.01075524091720581, "loss_total": 0.01075524091720581, "step": 34140 }, { "grad_norm": 0.32598283886909485, "learning_rate": 7.851440321036161e-05, "loss": 0.0152, "step": 34150 }, { "loss_action": 0.014787910506129265, "loss_total": 0.014787910506129265, "step": 34150 }, { "grad_norm": 0.3416428565979004, "learning_rate": 7.850081930998468e-05, "loss": 0.0148, "step": 34160 }, { "loss_action": 0.017373206093907356, "loss_total": 0.017373206093907356, "step": 34160 }, { "grad_norm": 0.35331881046295166, "learning_rate": 7.8487232292801e-05, "loss": 0.015, "step": 34170 }, { "loss_action": 0.01325293816626072, "loss_total": 0.01325293816626072, "step": 34170 }, { "grad_norm": 0.32160046696662903, "learning_rate": 7.847364216029642e-05, "loss": 0.0126, "step": 34180 }, { "loss_action": 0.010433503426611423, "loss_total": 0.010433503426611423, "step": 34180 }, { "grad_norm": 0.3191069960594177, "learning_rate": 7.846004891395716e-05, "loss": 0.0134, "step": 34190 }, { "loss_action": 0.015422794967889786, "loss_total": 0.015422794967889786, "step": 34190 }, { "grad_norm": 0.2546231150627136, "learning_rate": 7.844645255526972e-05, "loss": 0.0131, "step": 34200 }, { "loss_action": 0.013620687648653984, "loss_total": 0.013620687648653984, "step": 34200 }, { "grad_norm": 0.3224157989025116, "learning_rate": 7.843285308572101e-05, "loss": 0.0144, "step": 34210 }, { "loss_action": 0.012198514305055141, "loss_total": 0.012198514305055141, "step": 34210 }, { "grad_norm": 0.29259440302848816, "learning_rate": 7.841925050679823e-05, "loss": 0.0154, "step": 34220 }, { "loss_action": 0.012790611945092678, "loss_total": 0.012790611945092678, "step": 34220 }, { "grad_norm": 0.31733444333076477, "learning_rate": 7.840564481998895e-05, "loss": 0.0139, "step": 34230 }, { "loss_action": 0.013183938339352608, "loss_total": 0.013183938339352608, "step": 34230 }, { "grad_norm": 0.3441707193851471, "learning_rate": 7.839203602678105e-05, "loss": 0.0135, "step": 34240 }, { "loss_action": 0.019342215731739998, "loss_total": 0.019342215731739998, "step": 34240 }, { "grad_norm": 0.27155622839927673, "learning_rate": 7.837842412866279e-05, "loss": 0.0142, "step": 34250 }, { "loss_action": 0.013373615220189095, "loss_total": 0.013373615220189095, "step": 34250 }, { "grad_norm": 0.3286876678466797, "learning_rate": 7.836480912712272e-05, "loss": 0.0121, "step": 34260 }, { "loss_action": 0.017276644706726074, "loss_total": 0.017276644706726074, "step": 34260 }, { "grad_norm": 0.2847248911857605, "learning_rate": 7.835119102364976e-05, "loss": 0.0123, "step": 34270 }, { "loss_action": 0.012035609222948551, "loss_total": 0.012035609222948551, "step": 34270 }, { "grad_norm": 0.2967492341995239, "learning_rate": 7.83375698197332e-05, "loss": 0.0113, "step": 34280 }, { "loss_action": 0.008926832117140293, "loss_total": 0.008926832117140293, "step": 34280 }, { "grad_norm": 0.2789551913738251, "learning_rate": 7.83239455168626e-05, "loss": 0.013, "step": 34290 }, { "loss_action": 0.010290684178471565, "loss_total": 0.010290684178471565, "step": 34290 }, { "grad_norm": 0.2942720651626587, "learning_rate": 7.83103181165279e-05, "loss": 0.0144, "step": 34300 }, { "loss_action": 0.011362886056303978, "loss_total": 0.011362886056303978, "step": 34300 }, { "grad_norm": 0.3575449585914612, "learning_rate": 7.829668762021937e-05, "loss": 0.0158, "step": 34310 }, { "loss_action": 0.012550647370517254, "loss_total": 0.012550647370517254, "step": 34310 }, { "grad_norm": 0.32761070132255554, "learning_rate": 7.828305402942764e-05, "loss": 0.0166, "step": 34320 }, { "loss_action": 0.02324148453772068, "loss_total": 0.02324148453772068, "step": 34320 }, { "grad_norm": 0.35173413157463074, "learning_rate": 7.826941734564363e-05, "loss": 0.0148, "step": 34330 }, { "loss_action": 0.01388657744973898, "loss_total": 0.01388657744973898, "step": 34330 }, { "grad_norm": 0.357852041721344, "learning_rate": 7.825577757035865e-05, "loss": 0.0134, "step": 34340 }, { "loss_action": 0.018129637464880943, "loss_total": 0.018129637464880943, "step": 34340 }, { "grad_norm": 0.2914963662624359, "learning_rate": 7.824213470506431e-05, "loss": 0.0128, "step": 34350 }, { "loss_action": 0.010693247430026531, "loss_total": 0.010693247430026531, "step": 34350 }, { "grad_norm": 0.29535895586013794, "learning_rate": 7.822848875125257e-05, "loss": 0.0133, "step": 34360 }, { "loss_action": 0.024227164685726166, "loss_total": 0.024227164685726166, "step": 34360 }, { "grad_norm": 0.738956093788147, "learning_rate": 7.821483971041576e-05, "loss": 0.0154, "step": 34370 }, { "loss_action": 0.014912049286067486, "loss_total": 0.014912049286067486, "step": 34370 }, { "grad_norm": 0.313503235578537, "learning_rate": 7.820118758404649e-05, "loss": 0.0152, "step": 34380 }, { "loss_action": 0.01345710176974535, "loss_total": 0.01345710176974535, "step": 34380 }, { "grad_norm": 0.3118746280670166, "learning_rate": 7.818753237363776e-05, "loss": 0.0145, "step": 34390 }, { "loss_action": 0.017911188304424286, "loss_total": 0.017911188304424286, "step": 34390 }, { "grad_norm": 0.2851537764072418, "learning_rate": 7.817387408068286e-05, "loss": 0.0166, "step": 34400 }, { "loss_action": 0.019750669598579407, "loss_total": 0.019750669598579407, "step": 34400 }, { "grad_norm": 0.40090832114219666, "learning_rate": 7.816021270667544e-05, "loss": 0.0162, "step": 34410 }, { "loss_action": 0.01435789279639721, "loss_total": 0.01435789279639721, "step": 34410 }, { "grad_norm": 0.3330269753932953, "learning_rate": 7.81465482531095e-05, "loss": 0.0144, "step": 34420 }, { "loss_action": 0.015838131308555603, "loss_total": 0.015838131308555603, "step": 34420 }, { "grad_norm": 0.32788845896720886, "learning_rate": 7.813288072147938e-05, "loss": 0.0149, "step": 34430 }, { "loss_action": 0.016162320971488953, "loss_total": 0.016162320971488953, "step": 34430 }, { "grad_norm": 0.2809116542339325, "learning_rate": 7.811921011327972e-05, "loss": 0.0147, "step": 34440 }, { "loss_action": 0.01589774712920189, "loss_total": 0.01589774712920189, "step": 34440 }, { "grad_norm": 0.2900853753089905, "learning_rate": 7.810553643000549e-05, "loss": 0.0146, "step": 34450 }, { "loss_action": 0.013200070708990097, "loss_total": 0.013200070708990097, "step": 34450 }, { "grad_norm": 0.2827116549015045, "learning_rate": 7.809185967315206e-05, "loss": 0.0129, "step": 34460 }, { "loss_action": 0.012616490013897419, "loss_total": 0.012616490013897419, "step": 34460 }, { "grad_norm": 0.4405372142791748, "learning_rate": 7.80781798442151e-05, "loss": 0.0146, "step": 34470 }, { "loss_action": 0.011766762472689152, "loss_total": 0.011766762472689152, "step": 34470 }, { "grad_norm": 0.36764079332351685, "learning_rate": 7.806449694469061e-05, "loss": 0.0166, "step": 34480 }, { "loss_action": 0.012562896125018597, "loss_total": 0.012562896125018597, "step": 34480 }, { "grad_norm": 0.32417938113212585, "learning_rate": 7.805081097607492e-05, "loss": 0.0152, "step": 34490 }, { "loss_action": 0.019607415422797203, "loss_total": 0.019607415422797203, "step": 34490 }, { "grad_norm": 0.43106332421302795, "learning_rate": 7.803712193986474e-05, "loss": 0.0169, "step": 34500 }, { "loss_action": 0.013109956867992878, "loss_total": 0.013109956867992878, "step": 34500 }, { "grad_norm": 0.3958006799221039, "learning_rate": 7.802342983755702e-05, "loss": 0.0147, "step": 34510 }, { "loss_action": 0.012846478261053562, "loss_total": 0.012846478261053562, "step": 34510 }, { "grad_norm": 0.2657395303249359, "learning_rate": 7.800973467064918e-05, "loss": 0.0154, "step": 34520 }, { "loss_action": 0.015226668678224087, "loss_total": 0.015226668678224087, "step": 34520 }, { "grad_norm": 0.3399055600166321, "learning_rate": 7.799603644063884e-05, "loss": 0.0154, "step": 34530 }, { "loss_action": 0.014854010194540024, "loss_total": 0.014854010194540024, "step": 34530 }, { "grad_norm": 0.29516351222991943, "learning_rate": 7.798233514902405e-05, "loss": 0.0124, "step": 34540 }, { "loss_action": 0.013467659242451191, "loss_total": 0.013467659242451191, "step": 34540 }, { "grad_norm": 0.28115102648735046, "learning_rate": 7.796863079730318e-05, "loss": 0.0136, "step": 34550 }, { "loss_action": 0.010883929207921028, "loss_total": 0.010883929207921028, "step": 34550 }, { "grad_norm": 0.3286896049976349, "learning_rate": 7.795492338697488e-05, "loss": 0.0122, "step": 34560 }, { "loss_action": 0.014393003657460213, "loss_total": 0.014393003657460213, "step": 34560 }, { "grad_norm": 0.36107906699180603, "learning_rate": 7.794121291953819e-05, "loss": 0.0152, "step": 34570 }, { "loss_action": 0.010403509251773357, "loss_total": 0.010403509251773357, "step": 34570 }, { "grad_norm": 0.32683295011520386, "learning_rate": 7.792749939649246e-05, "loss": 0.0155, "step": 34580 }, { "loss_action": 0.015540601685643196, "loss_total": 0.015540601685643196, "step": 34580 }, { "grad_norm": 0.343580961227417, "learning_rate": 7.79137828193374e-05, "loss": 0.0164, "step": 34590 }, { "loss_action": 0.011040360666811466, "loss_total": 0.011040360666811466, "step": 34590 }, { "grad_norm": 0.33652254939079285, "learning_rate": 7.790006318957301e-05, "loss": 0.014, "step": 34600 }, { "loss_action": 0.01387512031942606, "loss_total": 0.01387512031942606, "step": 34600 }, { "grad_norm": 0.3056218922138214, "learning_rate": 7.788634050869965e-05, "loss": 0.0148, "step": 34610 }, { "loss_action": 0.01852048560976982, "loss_total": 0.01852048560976982, "step": 34610 }, { "grad_norm": 0.38325023651123047, "learning_rate": 7.787261477821803e-05, "loss": 0.0146, "step": 34620 }, { "loss_action": 0.016185753047466278, "loss_total": 0.016185753047466278, "step": 34620 }, { "grad_norm": 0.35789257287979126, "learning_rate": 7.785888599962916e-05, "loss": 0.0168, "step": 34630 }, { "loss_action": 0.014539899304509163, "loss_total": 0.014539899304509163, "step": 34630 }, { "grad_norm": 0.2990185022354126, "learning_rate": 7.784515417443439e-05, "loss": 0.0136, "step": 34640 }, { "loss_action": 0.011162563227117062, "loss_total": 0.011162563227117062, "step": 34640 }, { "grad_norm": 0.2851574420928955, "learning_rate": 7.783141930413545e-05, "loss": 0.0142, "step": 34650 }, { "loss_action": 0.014465242624282837, "loss_total": 0.014465242624282837, "step": 34650 }, { "grad_norm": 0.28382638096809387, "learning_rate": 7.78176813902343e-05, "loss": 0.0143, "step": 34660 }, { "loss_action": 0.01423222478479147, "loss_total": 0.01423222478479147, "step": 34660 }, { "grad_norm": 0.3521953821182251, "learning_rate": 7.780394043423336e-05, "loss": 0.0161, "step": 34670 }, { "loss_action": 0.0209643617272377, "loss_total": 0.0209643617272377, "step": 34670 }, { "grad_norm": 0.22697143256664276, "learning_rate": 7.77901964376353e-05, "loss": 0.0148, "step": 34680 }, { "loss_action": 0.014602785930037498, "loss_total": 0.014602785930037498, "step": 34680 }, { "grad_norm": 0.35195454955101013, "learning_rate": 7.777644940194316e-05, "loss": 0.0162, "step": 34690 }, { "loss_action": 0.027646303176879883, "loss_total": 0.027646303176879883, "step": 34690 }, { "grad_norm": 0.5234081149101257, "learning_rate": 7.776269932866023e-05, "loss": 0.0206, "step": 34700 }, { "loss_action": 0.028139542788267136, "loss_total": 0.028139542788267136, "step": 34700 }, { "grad_norm": 0.38715529441833496, "learning_rate": 7.774894621929026e-05, "loss": 0.0205, "step": 34710 }, { "loss_action": 0.019547903910279274, "loss_total": 0.019547903910279274, "step": 34710 }, { "grad_norm": 0.8015984296798706, "learning_rate": 7.773519007533725e-05, "loss": 0.0253, "step": 34720 }, { "loss_action": 0.01803264580667019, "loss_total": 0.01803264580667019, "step": 34720 }, { "grad_norm": 0.3854617774486542, "learning_rate": 7.772143089830556e-05, "loss": 0.0216, "step": 34730 }, { "loss_action": 0.01645362749695778, "loss_total": 0.01645362749695778, "step": 34730 }, { "grad_norm": 0.3719809949398041, "learning_rate": 7.770766868969985e-05, "loss": 0.0164, "step": 34740 }, { "loss_action": 0.017944226041436195, "loss_total": 0.017944226041436195, "step": 34740 }, { "grad_norm": 0.3712570369243622, "learning_rate": 7.769390345102518e-05, "loss": 0.0163, "step": 34750 }, { "loss_action": 0.0123286172747612, "loss_total": 0.0123286172747612, "step": 34750 }, { "grad_norm": 0.3441106677055359, "learning_rate": 7.768013518378683e-05, "loss": 0.016, "step": 34760 }, { "loss_action": 0.015826251357793808, "loss_total": 0.015826251357793808, "step": 34760 }, { "grad_norm": 0.40600746870040894, "learning_rate": 7.766636388949053e-05, "loss": 0.0151, "step": 34770 }, { "loss_action": 0.015966566279530525, "loss_total": 0.015966566279530525, "step": 34770 }, { "grad_norm": 0.28402575850486755, "learning_rate": 7.765258956964229e-05, "loss": 0.0146, "step": 34780 }, { "loss_action": 0.01727653294801712, "loss_total": 0.01727653294801712, "step": 34780 }, { "grad_norm": 0.313281774520874, "learning_rate": 7.76388122257484e-05, "loss": 0.0151, "step": 34790 }, { "loss_action": 0.011682468466460705, "loss_total": 0.011682468466460705, "step": 34790 }, { "grad_norm": 0.36569374799728394, "learning_rate": 7.762503185931558e-05, "loss": 0.014, "step": 34800 }, { "loss_action": 0.014192499220371246, "loss_total": 0.014192499220371246, "step": 34800 }, { "grad_norm": 0.3166244924068451, "learning_rate": 7.76112484718508e-05, "loss": 0.0154, "step": 34810 }, { "loss_action": 0.017746340483427048, "loss_total": 0.017746340483427048, "step": 34810 }, { "grad_norm": 0.37298405170440674, "learning_rate": 7.75974620648614e-05, "loss": 0.0146, "step": 34820 }, { "loss_action": 0.014595510438084602, "loss_total": 0.014595510438084602, "step": 34820 }, { "grad_norm": 0.3068394958972931, "learning_rate": 7.758367263985503e-05, "loss": 0.0141, "step": 34830 }, { "loss_action": 0.012601439841091633, "loss_total": 0.012601439841091633, "step": 34830 }, { "grad_norm": 0.2743276357650757, "learning_rate": 7.75698801983397e-05, "loss": 0.014, "step": 34840 }, { "loss_action": 0.015717603266239166, "loss_total": 0.015717603266239166, "step": 34840 }, { "grad_norm": 0.32755985856056213, "learning_rate": 7.755608474182372e-05, "loss": 0.0143, "step": 34850 }, { "loss_action": 0.014715212397277355, "loss_total": 0.014715212397277355, "step": 34850 }, { "grad_norm": 0.3479190170764923, "learning_rate": 7.754228627181574e-05, "loss": 0.0141, "step": 34860 }, { "loss_action": 0.011517130769789219, "loss_total": 0.011517130769789219, "step": 34860 }, { "grad_norm": 0.31176555156707764, "learning_rate": 7.752848478982476e-05, "loss": 0.014, "step": 34870 }, { "loss_action": 0.013771654106676579, "loss_total": 0.013771654106676579, "step": 34870 }, { "grad_norm": 0.3075753450393677, "learning_rate": 7.751468029736006e-05, "loss": 0.014, "step": 34880 }, { "loss_action": 0.012075523845851421, "loss_total": 0.012075523845851421, "step": 34880 }, { "grad_norm": 0.2320300042629242, "learning_rate": 7.750087279593129e-05, "loss": 0.0123, "step": 34890 }, { "loss_action": 0.013399009592831135, "loss_total": 0.013399009592831135, "step": 34890 }, { "grad_norm": 0.26044079661369324, "learning_rate": 7.748706228704843e-05, "loss": 0.0145, "step": 34900 }, { "loss_action": 0.009057417511940002, "loss_total": 0.009057417511940002, "step": 34900 }, { "grad_norm": 0.33429890871047974, "learning_rate": 7.747324877222176e-05, "loss": 0.0127, "step": 34910 }, { "loss_action": 0.0177448857575655, "loss_total": 0.0177448857575655, "step": 34910 }, { "grad_norm": 0.307381272315979, "learning_rate": 7.745943225296188e-05, "loss": 0.0144, "step": 34920 }, { "loss_action": 0.012601620517671108, "loss_total": 0.012601620517671108, "step": 34920 }, { "grad_norm": 0.2338121384382248, "learning_rate": 7.744561273077981e-05, "loss": 0.0124, "step": 34930 }, { "loss_action": 0.013313458301126957, "loss_total": 0.013313458301126957, "step": 34930 }, { "grad_norm": 0.30868661403656006, "learning_rate": 7.743179020718678e-05, "loss": 0.0141, "step": 34940 }, { "loss_action": 0.013539642095565796, "loss_total": 0.013539642095565796, "step": 34940 }, { "grad_norm": 0.30518651008605957, "learning_rate": 7.741796468369443e-05, "loss": 0.0136, "step": 34950 }, { "loss_action": 0.009803559631109238, "loss_total": 0.009803559631109238, "step": 34950 }, { "grad_norm": 0.24816448986530304, "learning_rate": 7.740413616181466e-05, "loss": 0.0127, "step": 34960 }, { "loss_action": 0.014254027977585793, "loss_total": 0.014254027977585793, "step": 34960 }, { "grad_norm": 0.37274909019470215, "learning_rate": 7.739030464305978e-05, "loss": 0.0151, "step": 34970 }, { "loss_action": 0.02183355949819088, "loss_total": 0.02183355949819088, "step": 34970 }, { "grad_norm": 0.3260689377784729, "learning_rate": 7.737647012894235e-05, "loss": 0.017, "step": 34980 }, { "loss_action": 0.014135690405964851, "loss_total": 0.014135690405964851, "step": 34980 }, { "grad_norm": 0.33882102370262146, "learning_rate": 7.736263262097532e-05, "loss": 0.0161, "step": 34990 }, { "loss_action": 0.019077317789196968, "loss_total": 0.019077317789196968, "step": 34990 }, { "grad_norm": 0.2616267204284668, "learning_rate": 7.734879212067192e-05, "loss": 0.0159, "step": 35000 }, { "loss_action": 0.01316993311047554, "loss_total": 0.01316993311047554, "step": 35000 }, { "grad_norm": 0.28472089767456055, "learning_rate": 7.733494862954573e-05, "loss": 0.0138, "step": 35010 }, { "loss_action": 0.014013593085110188, "loss_total": 0.014013593085110188, "step": 35010 }, { "grad_norm": 0.3039710819721222, "learning_rate": 7.732110214911066e-05, "loss": 0.0152, "step": 35020 }, { "loss_action": 0.01220452319830656, "loss_total": 0.01220452319830656, "step": 35020 }, { "grad_norm": 0.24126411974430084, "learning_rate": 7.730725268088094e-05, "loss": 0.0131, "step": 35030 }, { "loss_action": 0.032002005726099014, "loss_total": 0.032002005726099014, "step": 35030 }, { "grad_norm": 0.26890328526496887, "learning_rate": 7.729340022637112e-05, "loss": 0.0165, "step": 35040 }, { "loss_action": 0.013720883056521416, "loss_total": 0.013720883056521416, "step": 35040 }, { "grad_norm": 0.43019217252731323, "learning_rate": 7.727954478709607e-05, "loss": 0.0145, "step": 35050 }, { "loss_action": 0.011181814596056938, "loss_total": 0.011181814596056938, "step": 35050 }, { "grad_norm": 0.2970139682292938, "learning_rate": 7.726568636457103e-05, "loss": 0.0138, "step": 35060 }, { "loss_action": 0.014113188721239567, "loss_total": 0.014113188721239567, "step": 35060 }, { "grad_norm": 0.3090175986289978, "learning_rate": 7.725182496031153e-05, "loss": 0.0127, "step": 35070 }, { "loss_action": 0.016599157825112343, "loss_total": 0.016599157825112343, "step": 35070 }, { "grad_norm": 0.24044525623321533, "learning_rate": 7.723796057583341e-05, "loss": 0.0148, "step": 35080 }, { "loss_action": 0.009943312965333462, "loss_total": 0.009943312965333462, "step": 35080 }, { "grad_norm": 0.29906603693962097, "learning_rate": 7.722409321265287e-05, "loss": 0.0138, "step": 35090 }, { "loss_action": 0.013389812782406807, "loss_total": 0.013389812782406807, "step": 35090 }, { "grad_norm": 0.2929072976112366, "learning_rate": 7.721022287228645e-05, "loss": 0.0131, "step": 35100 }, { "loss_action": 0.013325567357242107, "loss_total": 0.013325567357242107, "step": 35100 }, { "grad_norm": 0.3573541045188904, "learning_rate": 7.719634955625094e-05, "loss": 0.0142, "step": 35110 }, { "loss_action": 0.011541451327502728, "loss_total": 0.011541451327502728, "step": 35110 }, { "grad_norm": 0.3068520724773407, "learning_rate": 7.718247326606355e-05, "loss": 0.0153, "step": 35120 }, { "loss_action": 0.0106198126450181, "loss_total": 0.0106198126450181, "step": 35120 }, { "grad_norm": 0.28100332617759705, "learning_rate": 7.716859400324175e-05, "loss": 0.0118, "step": 35130 }, { "loss_action": 0.019403042271733284, "loss_total": 0.019403042271733284, "step": 35130 }, { "grad_norm": 0.3112962543964386, "learning_rate": 7.715471176930335e-05, "loss": 0.0158, "step": 35140 }, { "loss_action": 0.012473433278501034, "loss_total": 0.012473433278501034, "step": 35140 }, { "grad_norm": 0.2341562956571579, "learning_rate": 7.714082656576651e-05, "loss": 0.0144, "step": 35150 }, { "loss_action": 0.02003437466919422, "loss_total": 0.02003437466919422, "step": 35150 }, { "grad_norm": 0.31735605001449585, "learning_rate": 7.712693839414968e-05, "loss": 0.0137, "step": 35160 }, { "loss_action": 0.014169680885970592, "loss_total": 0.014169680885970592, "step": 35160 }, { "grad_norm": 0.3117997646331787, "learning_rate": 7.711304725597164e-05, "loss": 0.0142, "step": 35170 }, { "loss_action": 0.016443148255348206, "loss_total": 0.016443148255348206, "step": 35170 }, { "grad_norm": 0.3182893693447113, "learning_rate": 7.709915315275151e-05, "loss": 0.014, "step": 35180 }, { "loss_action": 0.011591892689466476, "loss_total": 0.011591892689466476, "step": 35180 }, { "grad_norm": 0.3606560230255127, "learning_rate": 7.708525608600876e-05, "loss": 0.0122, "step": 35190 }, { "loss_action": 0.011782546527683735, "loss_total": 0.011782546527683735, "step": 35190 }, { "grad_norm": 0.29436108469963074, "learning_rate": 7.707135605726311e-05, "loss": 0.0134, "step": 35200 }, { "loss_action": 0.01036605890840292, "loss_total": 0.01036605890840292, "step": 35200 }, { "grad_norm": 0.32946622371673584, "learning_rate": 7.705745306803466e-05, "loss": 0.0131, "step": 35210 }, { "loss_action": 0.014562700875103474, "loss_total": 0.014562700875103474, "step": 35210 }, { "grad_norm": 0.2507821321487427, "learning_rate": 7.704354711984383e-05, "loss": 0.016, "step": 35220 }, { "loss_action": 0.017866501584649086, "loss_total": 0.017866501584649086, "step": 35220 }, { "grad_norm": 0.32327285408973694, "learning_rate": 7.702963821421133e-05, "loss": 0.0146, "step": 35230 }, { "loss_action": 0.010830848477780819, "loss_total": 0.010830848477780819, "step": 35230 }, { "grad_norm": 0.29588162899017334, "learning_rate": 7.701572635265826e-05, "loss": 0.0139, "step": 35240 }, { "loss_action": 0.00913659855723381, "loss_total": 0.00913659855723381, "step": 35240 }, { "grad_norm": 0.27492833137512207, "learning_rate": 7.700181153670596e-05, "loss": 0.0129, "step": 35250 }, { "loss_action": 0.011610341258347034, "loss_total": 0.011610341258347034, "step": 35250 }, { "grad_norm": 0.31114277243614197, "learning_rate": 7.698789376787616e-05, "loss": 0.0132, "step": 35260 }, { "loss_action": 0.011738521046936512, "loss_total": 0.011738521046936512, "step": 35260 }, { "grad_norm": 0.34422290325164795, "learning_rate": 7.697397304769085e-05, "loss": 0.0142, "step": 35270 }, { "loss_action": 0.014021574519574642, "loss_total": 0.014021574519574642, "step": 35270 }, { "grad_norm": 0.35903462767601013, "learning_rate": 7.696004937767241e-05, "loss": 0.013, "step": 35280 }, { "loss_action": 0.010701464489102364, "loss_total": 0.010701464489102364, "step": 35280 }, { "grad_norm": 0.33350956439971924, "learning_rate": 7.694612275934352e-05, "loss": 0.0128, "step": 35290 }, { "loss_action": 0.011794935911893845, "loss_total": 0.011794935911893845, "step": 35290 }, { "grad_norm": 0.31458207964897156, "learning_rate": 7.693219319422714e-05, "loss": 0.0142, "step": 35300 }, { "loss_action": 0.011999065056443214, "loss_total": 0.011999065056443214, "step": 35300 }, { "grad_norm": 0.306320458650589, "learning_rate": 7.69182606838466e-05, "loss": 0.0138, "step": 35310 }, { "loss_action": 0.014599868096411228, "loss_total": 0.014599868096411228, "step": 35310 }, { "grad_norm": 0.2798555791378021, "learning_rate": 7.690432522972558e-05, "loss": 0.0138, "step": 35320 }, { "loss_action": 0.015159154310822487, "loss_total": 0.015159154310822487, "step": 35320 }, { "grad_norm": 0.29308250546455383, "learning_rate": 7.689038683338796e-05, "loss": 0.0127, "step": 35330 }, { "loss_action": 0.012930594384670258, "loss_total": 0.012930594384670258, "step": 35330 }, { "grad_norm": 0.30815330147743225, "learning_rate": 7.687644549635808e-05, "loss": 0.0122, "step": 35340 }, { "loss_action": 0.014206255786120892, "loss_total": 0.014206255786120892, "step": 35340 }, { "grad_norm": 0.30878978967666626, "learning_rate": 7.686250122016053e-05, "loss": 0.0118, "step": 35350 }, { "loss_action": 0.010425927117466927, "loss_total": 0.010425927117466927, "step": 35350 }, { "grad_norm": 0.34208330512046814, "learning_rate": 7.684855400632022e-05, "loss": 0.0139, "step": 35360 }, { "loss_action": 0.011011146940290928, "loss_total": 0.011011146940290928, "step": 35360 }, { "grad_norm": 0.4161965548992157, "learning_rate": 7.683460385636243e-05, "loss": 0.0141, "step": 35370 }, { "loss_action": 0.012819976545870304, "loss_total": 0.012819976545870304, "step": 35370 }, { "grad_norm": 0.31878772377967834, "learning_rate": 7.68206507718127e-05, "loss": 0.0134, "step": 35380 }, { "loss_action": 0.012187928892672062, "loss_total": 0.012187928892672062, "step": 35380 }, { "grad_norm": 0.34240779280662537, "learning_rate": 7.680669475419693e-05, "loss": 0.0153, "step": 35390 }, { "loss_action": 0.01304621808230877, "loss_total": 0.01304621808230877, "step": 35390 }, { "grad_norm": 0.3706434667110443, "learning_rate": 7.679273580504132e-05, "loss": 0.0139, "step": 35400 }, { "loss_action": 0.013930601067841053, "loss_total": 0.013930601067841053, "step": 35400 }, { "grad_norm": 0.28957006335258484, "learning_rate": 7.67787739258724e-05, "loss": 0.0134, "step": 35410 }, { "loss_action": 0.010498744435608387, "loss_total": 0.010498744435608387, "step": 35410 }, { "grad_norm": 0.34890177845954895, "learning_rate": 7.676480911821705e-05, "loss": 0.0139, "step": 35420 }, { "loss_action": 0.011664938181638718, "loss_total": 0.011664938181638718, "step": 35420 }, { "grad_norm": 0.2389683574438095, "learning_rate": 7.675084138360238e-05, "loss": 0.0128, "step": 35430 }, { "loss_action": 0.010975558310747147, "loss_total": 0.010975558310747147, "step": 35430 }, { "grad_norm": 0.3066349923610687, "learning_rate": 7.673687072355592e-05, "loss": 0.0147, "step": 35440 }, { "loss_action": 0.014373553916811943, "loss_total": 0.014373553916811943, "step": 35440 }, { "grad_norm": 0.27454131841659546, "learning_rate": 7.67228971396055e-05, "loss": 0.012, "step": 35450 }, { "loss_action": 0.009765921160578728, "loss_total": 0.009765921160578728, "step": 35450 }, { "grad_norm": 0.2759109139442444, "learning_rate": 7.670892063327922e-05, "loss": 0.013, "step": 35460 }, { "loss_action": 0.013347129337489605, "loss_total": 0.013347129337489605, "step": 35460 }, { "grad_norm": 0.29616835713386536, "learning_rate": 7.669494120610552e-05, "loss": 0.0119, "step": 35470 }, { "loss_action": 0.013026267290115356, "loss_total": 0.013026267290115356, "step": 35470 }, { "grad_norm": 0.2714422047138214, "learning_rate": 7.66809588596132e-05, "loss": 0.0143, "step": 35480 }, { "loss_action": 0.014139704406261444, "loss_total": 0.014139704406261444, "step": 35480 }, { "grad_norm": 0.34630531072616577, "learning_rate": 7.666697359533132e-05, "loss": 0.0154, "step": 35490 }, { "loss_action": 0.014666164293885231, "loss_total": 0.014666164293885231, "step": 35490 }, { "grad_norm": 0.34803321957588196, "learning_rate": 7.665298541478932e-05, "loss": 0.015, "step": 35500 }, { "loss_action": 0.014612012542784214, "loss_total": 0.014612012542784214, "step": 35500 }, { "grad_norm": 0.3435748517513275, "learning_rate": 7.66389943195169e-05, "loss": 0.0144, "step": 35510 }, { "loss_action": 0.01351973507553339, "loss_total": 0.01351973507553339, "step": 35510 }, { "grad_norm": 0.32472410798072815, "learning_rate": 7.66250003110441e-05, "loss": 0.014, "step": 35520 }, { "loss_action": 0.011079073883593082, "loss_total": 0.011079073883593082, "step": 35520 }, { "grad_norm": 0.2797205448150635, "learning_rate": 7.66110033909013e-05, "loss": 0.0132, "step": 35530 }, { "loss_action": 0.009545234963297844, "loss_total": 0.009545234963297844, "step": 35530 }, { "grad_norm": 0.43656834959983826, "learning_rate": 7.659700356061918e-05, "loss": 0.0144, "step": 35540 }, { "loss_action": 0.016799746081233025, "loss_total": 0.016799746081233025, "step": 35540 }, { "grad_norm": 0.31872907280921936, "learning_rate": 7.658300082172875e-05, "loss": 0.0155, "step": 35550 }, { "loss_action": 0.014550972729921341, "loss_total": 0.014550972729921341, "step": 35550 }, { "grad_norm": 0.32656329870224, "learning_rate": 7.65689951757613e-05, "loss": 0.0138, "step": 35560 }, { "loss_action": 0.015102108009159565, "loss_total": 0.015102108009159565, "step": 35560 }, { "grad_norm": 0.3677712082862854, "learning_rate": 7.655498662424849e-05, "loss": 0.0155, "step": 35570 }, { "loss_action": 0.018548550084233284, "loss_total": 0.018548550084233284, "step": 35570 }, { "grad_norm": 0.3182155191898346, "learning_rate": 7.654097516872227e-05, "loss": 0.0142, "step": 35580 }, { "loss_action": 0.014358090236783028, "loss_total": 0.014358090236783028, "step": 35580 }, { "grad_norm": 0.31663578748703003, "learning_rate": 7.65269608107149e-05, "loss": 0.0164, "step": 35590 }, { "loss_action": 0.011177767999470234, "loss_total": 0.011177767999470234, "step": 35590 }, { "grad_norm": 0.28331229090690613, "learning_rate": 7.6512943551759e-05, "loss": 0.0133, "step": 35600 }, { "loss_action": 0.011920803226530552, "loss_total": 0.011920803226530552, "step": 35600 }, { "grad_norm": 0.2552497684955597, "learning_rate": 7.649892339338743e-05, "loss": 0.0152, "step": 35610 }, { "loss_action": 0.01364879496395588, "loss_total": 0.01364879496395588, "step": 35610 }, { "grad_norm": 0.2905745804309845, "learning_rate": 7.648490033713344e-05, "loss": 0.015, "step": 35620 }, { "loss_action": 0.014755679294466972, "loss_total": 0.014755679294466972, "step": 35620 }, { "grad_norm": 0.2831789553165436, "learning_rate": 7.647087438453058e-05, "loss": 0.0138, "step": 35630 }, { "loss_action": 0.01297050155699253, "loss_total": 0.01297050155699253, "step": 35630 }, { "grad_norm": 0.2552388310432434, "learning_rate": 7.64568455371127e-05, "loss": 0.0148, "step": 35640 }, { "loss_action": 0.010985864326357841, "loss_total": 0.010985864326357841, "step": 35640 }, { "grad_norm": 0.37614905834198, "learning_rate": 7.644281379641396e-05, "loss": 0.0141, "step": 35650 }, { "loss_action": 0.01477724127471447, "loss_total": 0.01477724127471447, "step": 35650 }, { "grad_norm": 0.3158816695213318, "learning_rate": 7.642877916396887e-05, "loss": 0.0133, "step": 35660 }, { "loss_action": 0.010793198831379414, "loss_total": 0.010793198831379414, "step": 35660 }, { "grad_norm": 0.26136094331741333, "learning_rate": 7.641474164131221e-05, "loss": 0.0135, "step": 35670 }, { "loss_action": 0.013187313452363014, "loss_total": 0.013187313452363014, "step": 35670 }, { "grad_norm": 0.24732628464698792, "learning_rate": 7.640070122997913e-05, "loss": 0.0119, "step": 35680 }, { "loss_action": 0.011723695322871208, "loss_total": 0.011723695322871208, "step": 35680 }, { "grad_norm": 0.3331785202026367, "learning_rate": 7.638665793150505e-05, "loss": 0.0151, "step": 35690 }, { "loss_action": 0.01272269245237112, "loss_total": 0.01272269245237112, "step": 35690 }, { "grad_norm": 0.28853029012680054, "learning_rate": 7.637261174742574e-05, "loss": 0.0136, "step": 35700 }, { "loss_action": 0.013606298714876175, "loss_total": 0.013606298714876175, "step": 35700 }, { "grad_norm": 0.25293412804603577, "learning_rate": 7.635856267927725e-05, "loss": 0.0136, "step": 35710 }, { "loss_action": 0.012223482131958008, "loss_total": 0.012223482131958008, "step": 35710 }, { "grad_norm": 0.263557106256485, "learning_rate": 7.634451072859597e-05, "loss": 0.0127, "step": 35720 }, { "loss_action": 0.00981251522898674, "loss_total": 0.00981251522898674, "step": 35720 }, { "grad_norm": 0.3953284025192261, "learning_rate": 7.633045589691863e-05, "loss": 0.0146, "step": 35730 }, { "loss_action": 0.015302030369639397, "loss_total": 0.015302030369639397, "step": 35730 }, { "grad_norm": 0.3002152442932129, "learning_rate": 7.63163981857822e-05, "loss": 0.0126, "step": 35740 }, { "loss_action": 0.009367983788251877, "loss_total": 0.009367983788251877, "step": 35740 }, { "grad_norm": 0.2839505970478058, "learning_rate": 7.630233759672403e-05, "loss": 0.0147, "step": 35750 }, { "loss_action": 0.014119966886937618, "loss_total": 0.014119966886937618, "step": 35750 }, { "grad_norm": 0.27941417694091797, "learning_rate": 7.628827413128177e-05, "loss": 0.0169, "step": 35760 }, { "loss_action": 0.02473757043480873, "loss_total": 0.02473757043480873, "step": 35760 }, { "grad_norm": 0.36909887194633484, "learning_rate": 7.627420779099338e-05, "loss": 0.0167, "step": 35770 }, { "loss_action": 0.018718264997005463, "loss_total": 0.018718264997005463, "step": 35770 }, { "grad_norm": 0.27559271454811096, "learning_rate": 7.626013857739711e-05, "loss": 0.0136, "step": 35780 }, { "loss_action": 0.010077663697302341, "loss_total": 0.010077663697302341, "step": 35780 }, { "grad_norm": 0.36334893107414246, "learning_rate": 7.624606649203158e-05, "loss": 0.0153, "step": 35790 }, { "loss_action": 0.01379475835710764, "loss_total": 0.01379475835710764, "step": 35790 }, { "grad_norm": 0.3932289183139801, "learning_rate": 7.623199153643569e-05, "loss": 0.0153, "step": 35800 }, { "loss_action": 0.01020101085305214, "loss_total": 0.01020101085305214, "step": 35800 }, { "grad_norm": 0.3545270562171936, "learning_rate": 7.621791371214863e-05, "loss": 0.0162, "step": 35810 }, { "loss_action": 0.014536183327436447, "loss_total": 0.014536183327436447, "step": 35810 }, { "grad_norm": 0.4105978012084961, "learning_rate": 7.620383302070995e-05, "loss": 0.0133, "step": 35820 }, { "loss_action": 0.011210095137357712, "loss_total": 0.011210095137357712, "step": 35820 }, { "grad_norm": 0.3225696086883545, "learning_rate": 7.61897494636595e-05, "loss": 0.0144, "step": 35830 }, { "loss_action": 0.01612633466720581, "loss_total": 0.01612633466720581, "step": 35830 }, { "grad_norm": 0.29429084062576294, "learning_rate": 7.617566304253739e-05, "loss": 0.0141, "step": 35840 }, { "loss_action": 0.01444299053400755, "loss_total": 0.01444299053400755, "step": 35840 }, { "grad_norm": 0.300313800573349, "learning_rate": 7.616157375888416e-05, "loss": 0.0139, "step": 35850 }, { "loss_action": 0.014204192906618118, "loss_total": 0.014204192906618118, "step": 35850 }, { "grad_norm": 0.3162583112716675, "learning_rate": 7.614748161424053e-05, "loss": 0.0134, "step": 35860 }, { "loss_action": 0.01844877190887928, "loss_total": 0.01844877190887928, "step": 35860 }, { "grad_norm": 0.365119069814682, "learning_rate": 7.613338661014763e-05, "loss": 0.0146, "step": 35870 }, { "loss_action": 0.021570367738604546, "loss_total": 0.021570367738604546, "step": 35870 }, { "grad_norm": 0.3122006058692932, "learning_rate": 7.611928874814686e-05, "loss": 0.0153, "step": 35880 }, { "loss_action": 0.012432131916284561, "loss_total": 0.012432131916284561, "step": 35880 }, { "grad_norm": 0.3666343092918396, "learning_rate": 7.610518802977996e-05, "loss": 0.0156, "step": 35890 }, { "loss_action": 0.009094278328120708, "loss_total": 0.009094278328120708, "step": 35890 }, { "grad_norm": 0.33196771144866943, "learning_rate": 7.609108445658893e-05, "loss": 0.0144, "step": 35900 }, { "loss_action": 0.01477414183318615, "loss_total": 0.01477414183318615, "step": 35900 }, { "grad_norm": 0.39637282490730286, "learning_rate": 7.607697803011612e-05, "loss": 0.0148, "step": 35910 }, { "loss_action": 0.010989043861627579, "loss_total": 0.010989043861627579, "step": 35910 }, { "grad_norm": 0.33108243346214294, "learning_rate": 7.606286875190421e-05, "loss": 0.0149, "step": 35920 }, { "loss_action": 0.010822602547705173, "loss_total": 0.010822602547705173, "step": 35920 }, { "grad_norm": 0.3153730034828186, "learning_rate": 7.604875662349617e-05, "loss": 0.0141, "step": 35930 }, { "loss_action": 0.019844308495521545, "loss_total": 0.019844308495521545, "step": 35930 }, { "grad_norm": 0.32879117131233215, "learning_rate": 7.603464164643525e-05, "loss": 0.0161, "step": 35940 }, { "loss_action": 0.014816846698522568, "loss_total": 0.014816846698522568, "step": 35940 }, { "grad_norm": 0.2906123399734497, "learning_rate": 7.602052382226507e-05, "loss": 0.0137, "step": 35950 }, { "loss_action": 0.01018682774156332, "loss_total": 0.01018682774156332, "step": 35950 }, { "grad_norm": 0.388517826795578, "learning_rate": 7.600640315252954e-05, "loss": 0.0132, "step": 35960 }, { "loss_action": 0.014625621028244495, "loss_total": 0.014625621028244495, "step": 35960 }, { "grad_norm": 0.31891581416130066, "learning_rate": 7.599227963877284e-05, "loss": 0.014, "step": 35970 }, { "loss_action": 0.01472613774240017, "loss_total": 0.01472613774240017, "step": 35970 }, { "grad_norm": 0.38297906517982483, "learning_rate": 7.597815328253954e-05, "loss": 0.0151, "step": 35980 }, { "loss_action": 0.020426524803042412, "loss_total": 0.020426524803042412, "step": 35980 }, { "grad_norm": 0.2456858903169632, "learning_rate": 7.596402408537443e-05, "loss": 0.014, "step": 35990 }, { "loss_action": 0.010228832252323627, "loss_total": 0.010228832252323627, "step": 35990 }, { "grad_norm": 0.3546028137207031, "learning_rate": 7.59498920488227e-05, "loss": 0.0133, "step": 36000 }, { "loss_action": 0.016325844451785088, "loss_total": 0.016325844451785088, "step": 36000 }, { "grad_norm": 0.3693715035915375, "learning_rate": 7.593575717442979e-05, "loss": 0.014, "step": 36010 }, { "loss_action": 0.020542599260807037, "loss_total": 0.020542599260807037, "step": 36010 }, { "grad_norm": 0.2892862558364868, "learning_rate": 7.592161946374147e-05, "loss": 0.0151, "step": 36020 }, { "loss_action": 0.012629922479391098, "loss_total": 0.012629922479391098, "step": 36020 }, { "grad_norm": 0.38069140911102295, "learning_rate": 7.590747891830381e-05, "loss": 0.0138, "step": 36030 }, { "loss_action": 0.014215300790965557, "loss_total": 0.014215300790965557, "step": 36030 }, { "grad_norm": 0.31410500407218933, "learning_rate": 7.58933355396632e-05, "loss": 0.0143, "step": 36040 }, { "loss_action": 0.012626522220671177, "loss_total": 0.012626522220671177, "step": 36040 }, { "grad_norm": 0.25059255957603455, "learning_rate": 7.587918932936636e-05, "loss": 0.0119, "step": 36050 }, { "loss_action": 0.01396911684423685, "loss_total": 0.01396911684423685, "step": 36050 }, { "grad_norm": 0.3562556207180023, "learning_rate": 7.586504028896028e-05, "loss": 0.0146, "step": 36060 }, { "loss_action": 0.011967921629548073, "loss_total": 0.011967921629548073, "step": 36060 }, { "grad_norm": 0.3015386760234833, "learning_rate": 7.585088841999228e-05, "loss": 0.0119, "step": 36070 }, { "loss_action": 0.014316133223474026, "loss_total": 0.014316133223474026, "step": 36070 }, { "grad_norm": 0.35005781054496765, "learning_rate": 7.583673372400999e-05, "loss": 0.0142, "step": 36080 }, { "loss_action": 0.009348719380795956, "loss_total": 0.009348719380795956, "step": 36080 }, { "grad_norm": 0.3027113974094391, "learning_rate": 7.582257620256134e-05, "loss": 0.0127, "step": 36090 }, { "loss_action": 0.015345375053584576, "loss_total": 0.015345375053584576, "step": 36090 }, { "grad_norm": 0.3080107569694519, "learning_rate": 7.580841585719458e-05, "loss": 0.0146, "step": 36100 }, { "loss_action": 0.017103411257267, "loss_total": 0.017103411257267, "step": 36100 }, { "grad_norm": 0.2896263897418976, "learning_rate": 7.579425268945825e-05, "loss": 0.014, "step": 36110 }, { "loss_action": 0.010135108605027199, "loss_total": 0.010135108605027199, "step": 36110 }, { "grad_norm": 0.29587894678115845, "learning_rate": 7.578008670090127e-05, "loss": 0.0143, "step": 36120 }, { "loss_action": 0.011924666352570057, "loss_total": 0.011924666352570057, "step": 36120 }, { "grad_norm": 0.2665815055370331, "learning_rate": 7.576591789307272e-05, "loss": 0.0141, "step": 36130 }, { "loss_action": 0.013137724250555038, "loss_total": 0.013137724250555038, "step": 36130 }, { "grad_norm": 0.2890520989894867, "learning_rate": 7.575174626752216e-05, "loss": 0.0136, "step": 36140 }, { "loss_action": 0.01013895869255066, "loss_total": 0.01013895869255066, "step": 36140 }, { "grad_norm": 0.2585894465446472, "learning_rate": 7.573757182579934e-05, "loss": 0.0125, "step": 36150 }, { "loss_action": 0.016807887703180313, "loss_total": 0.016807887703180313, "step": 36150 }, { "grad_norm": 0.32652443647384644, "learning_rate": 7.572339456945435e-05, "loss": 0.015, "step": 36160 }, { "loss_action": 0.01176287978887558, "loss_total": 0.01176287978887558, "step": 36160 }, { "grad_norm": 0.3160916864871979, "learning_rate": 7.570921450003762e-05, "loss": 0.013, "step": 36170 }, { "loss_action": 0.013239096850156784, "loss_total": 0.013239096850156784, "step": 36170 }, { "grad_norm": 0.31346750259399414, "learning_rate": 7.569503161909983e-05, "loss": 0.0118, "step": 36180 }, { "loss_action": 0.010360770858824253, "loss_total": 0.010360770858824253, "step": 36180 }, { "grad_norm": 0.28793540596961975, "learning_rate": 7.568084592819202e-05, "loss": 0.0136, "step": 36190 }, { "loss_action": 0.012724571861326694, "loss_total": 0.012724571861326694, "step": 36190 }, { "grad_norm": 0.297135591506958, "learning_rate": 7.566665742886551e-05, "loss": 0.0135, "step": 36200 }, { "loss_action": 0.011625546962022781, "loss_total": 0.011625546962022781, "step": 36200 }, { "grad_norm": 0.33400261402130127, "learning_rate": 7.565246612267194e-05, "loss": 0.0134, "step": 36210 }, { "loss_action": 0.016330644488334656, "loss_total": 0.016330644488334656, "step": 36210 }, { "grad_norm": 0.30541929602622986, "learning_rate": 7.563827201116325e-05, "loss": 0.0132, "step": 36220 }, { "loss_action": 0.011601495556533337, "loss_total": 0.011601495556533337, "step": 36220 }, { "grad_norm": 0.33510521054267883, "learning_rate": 7.562407509589164e-05, "loss": 0.0134, "step": 36230 }, { "loss_action": 0.011476514860987663, "loss_total": 0.011476514860987663, "step": 36230 }, { "grad_norm": 0.3226255774497986, "learning_rate": 7.560987537840973e-05, "loss": 0.0121, "step": 36240 }, { "loss_action": 0.012624089606106281, "loss_total": 0.012624089606106281, "step": 36240 }, { "grad_norm": 0.34681078791618347, "learning_rate": 7.559567286027036e-05, "loss": 0.0133, "step": 36250 }, { "loss_action": 0.011215544305741787, "loss_total": 0.011215544305741787, "step": 36250 }, { "grad_norm": 0.27329450845718384, "learning_rate": 7.558146754302668e-05, "loss": 0.0129, "step": 36260 }, { "loss_action": 0.008910995908081532, "loss_total": 0.008910995908081532, "step": 36260 }, { "grad_norm": 0.38455113768577576, "learning_rate": 7.556725942823217e-05, "loss": 0.0133, "step": 36270 }, { "loss_action": 0.012588939629495144, "loss_total": 0.012588939629495144, "step": 36270 }, { "grad_norm": 0.36422207951545715, "learning_rate": 7.555304851744061e-05, "loss": 0.0134, "step": 36280 }, { "loss_action": 0.011395174078643322, "loss_total": 0.011395174078643322, "step": 36280 }, { "grad_norm": 0.36057302355766296, "learning_rate": 7.553883481220608e-05, "loss": 0.0151, "step": 36290 }, { "loss_action": 0.012265199795365334, "loss_total": 0.012265199795365334, "step": 36290 }, { "grad_norm": 0.28584742546081543, "learning_rate": 7.552461831408298e-05, "loss": 0.0149, "step": 36300 }, { "loss_action": 0.01544515322893858, "loss_total": 0.01544515322893858, "step": 36300 }, { "grad_norm": 0.29577502608299255, "learning_rate": 7.551039902462599e-05, "loss": 0.0142, "step": 36310 }, { "loss_action": 0.01141891349107027, "loss_total": 0.01141891349107027, "step": 36310 }, { "grad_norm": 0.2718607187271118, "learning_rate": 7.549617694539011e-05, "loss": 0.014, "step": 36320 }, { "loss_action": 0.011261854320764542, "loss_total": 0.011261854320764542, "step": 36320 }, { "grad_norm": 0.38555628061294556, "learning_rate": 7.548195207793066e-05, "loss": 0.0137, "step": 36330 }, { "loss_action": 0.01705288514494896, "loss_total": 0.01705288514494896, "step": 36330 }, { "grad_norm": 0.30196231603622437, "learning_rate": 7.546772442380323e-05, "loss": 0.013, "step": 36340 }, { "loss_action": 0.010694487020373344, "loss_total": 0.010694487020373344, "step": 36340 }, { "grad_norm": 0.339388906955719, "learning_rate": 7.545349398456376e-05, "loss": 0.013, "step": 36350 }, { "loss_action": 0.009369834326207638, "loss_total": 0.009369834326207638, "step": 36350 }, { "grad_norm": 0.3254238963127136, "learning_rate": 7.543926076176845e-05, "loss": 0.0154, "step": 36360 }, { "loss_action": 0.011625774204730988, "loss_total": 0.011625774204730988, "step": 36360 }, { "grad_norm": 0.28632432222366333, "learning_rate": 7.542502475697385e-05, "loss": 0.0126, "step": 36370 }, { "loss_action": 0.013102425262331963, "loss_total": 0.013102425262331963, "step": 36370 }, { "grad_norm": 0.3146993815898895, "learning_rate": 7.541078597173675e-05, "loss": 0.0141, "step": 36380 }, { "loss_action": 0.016515223309397697, "loss_total": 0.016515223309397697, "step": 36380 }, { "grad_norm": 0.31317660212516785, "learning_rate": 7.539654440761431e-05, "loss": 0.0139, "step": 36390 }, { "loss_action": 0.012261456809937954, "loss_total": 0.012261456809937954, "step": 36390 }, { "grad_norm": 0.3919794261455536, "learning_rate": 7.538230006616395e-05, "loss": 0.0142, "step": 36400 }, { "loss_action": 0.01573602855205536, "loss_total": 0.01573602855205536, "step": 36400 }, { "grad_norm": 0.30701783299446106, "learning_rate": 7.536805294894342e-05, "loss": 0.0147, "step": 36410 }, { "loss_action": 0.012194686569273472, "loss_total": 0.012194686569273472, "step": 36410 }, { "grad_norm": 0.27631881833076477, "learning_rate": 7.535380305751076e-05, "loss": 0.0133, "step": 36420 }, { "loss_action": 0.009444012306630611, "loss_total": 0.009444012306630611, "step": 36420 }, { "grad_norm": 0.3359311521053314, "learning_rate": 7.533955039342431e-05, "loss": 0.0128, "step": 36430 }, { "loss_action": 0.015055433847010136, "loss_total": 0.015055433847010136, "step": 36430 }, { "grad_norm": 0.2511747181415558, "learning_rate": 7.532529495824274e-05, "loss": 0.0127, "step": 36440 }, { "loss_action": 0.015364478342235088, "loss_total": 0.015364478342235088, "step": 36440 }, { "grad_norm": 0.29120129346847534, "learning_rate": 7.531103675352497e-05, "loss": 0.0131, "step": 36450 }, { "loss_action": 0.01338712777942419, "loss_total": 0.01338712777942419, "step": 36450 }, { "grad_norm": 0.3228060007095337, "learning_rate": 7.529677578083029e-05, "loss": 0.0138, "step": 36460 }, { "loss_action": 0.01195021066814661, "loss_total": 0.01195021066814661, "step": 36460 }, { "grad_norm": 0.26346325874328613, "learning_rate": 7.528251204171823e-05, "loss": 0.0123, "step": 36470 }, { "loss_action": 0.010209924541413784, "loss_total": 0.010209924541413784, "step": 36470 }, { "grad_norm": 0.26256486773490906, "learning_rate": 7.526824553774867e-05, "loss": 0.0126, "step": 36480 }, { "loss_action": 0.014558661729097366, "loss_total": 0.014558661729097366, "step": 36480 }, { "grad_norm": 0.30063483119010925, "learning_rate": 7.525397627048178e-05, "loss": 0.0138, "step": 36490 }, { "loss_action": 0.01853189617395401, "loss_total": 0.01853189617395401, "step": 36490 }, { "grad_norm": 0.31939253211021423, "learning_rate": 7.523970424147802e-05, "loss": 0.0126, "step": 36500 }, { "loss_action": 0.011806675232946873, "loss_total": 0.011806675232946873, "step": 36500 }, { "grad_norm": 0.3819461166858673, "learning_rate": 7.522542945229813e-05, "loss": 0.0119, "step": 36510 }, { "loss_action": 0.009403437376022339, "loss_total": 0.009403437376022339, "step": 36510 }, { "grad_norm": 0.3541012406349182, "learning_rate": 7.521115190450321e-05, "loss": 0.013, "step": 36520 }, { "loss_action": 0.0111074885353446, "loss_total": 0.0111074885353446, "step": 36520 }, { "grad_norm": 0.23768943548202515, "learning_rate": 7.519687159965462e-05, "loss": 0.0128, "step": 36530 }, { "loss_action": 0.011014197953045368, "loss_total": 0.011014197953045368, "step": 36530 }, { "grad_norm": 0.4477764964103699, "learning_rate": 7.518258853931403e-05, "loss": 0.0143, "step": 36540 }, { "loss_action": 0.01620141603052616, "loss_total": 0.01620141603052616, "step": 36540 }, { "grad_norm": 0.33226847648620605, "learning_rate": 7.516830272504342e-05, "loss": 0.0144, "step": 36550 }, { "loss_action": 0.014988499693572521, "loss_total": 0.014988499693572521, "step": 36550 }, { "grad_norm": 0.3275519609451294, "learning_rate": 7.515401415840509e-05, "loss": 0.0172, "step": 36560 }, { "loss_action": 0.01287274993956089, "loss_total": 0.01287274993956089, "step": 36560 }, { "grad_norm": 0.31449568271636963, "learning_rate": 7.513972284096155e-05, "loss": 0.017, "step": 36570 }, { "loss_action": 0.012089285999536514, "loss_total": 0.012089285999536514, "step": 36570 }, { "grad_norm": 0.4309525787830353, "learning_rate": 7.512542877427574e-05, "loss": 0.0141, "step": 36580 }, { "loss_action": 0.012341159395873547, "loss_total": 0.012341159395873547, "step": 36580 }, { "grad_norm": 0.5375614166259766, "learning_rate": 7.51111319599108e-05, "loss": 0.0156, "step": 36590 }, { "loss_action": 0.01654673181474209, "loss_total": 0.01654673181474209, "step": 36590 }, { "grad_norm": 0.353816956281662, "learning_rate": 7.509683239943024e-05, "loss": 0.0155, "step": 36600 }, { "loss_action": 0.014431683346629143, "loss_total": 0.014431683346629143, "step": 36600 }, { "grad_norm": 0.3279757499694824, "learning_rate": 7.50825300943978e-05, "loss": 0.0151, "step": 36610 }, { "loss_action": 0.009800897911190987, "loss_total": 0.009800897911190987, "step": 36610 }, { "grad_norm": 0.4475959241390228, "learning_rate": 7.50682250463776e-05, "loss": 0.0143, "step": 36620 }, { "loss_action": 0.011266898363828659, "loss_total": 0.011266898363828659, "step": 36620 }, { "grad_norm": 0.2387639880180359, "learning_rate": 7.5053917256934e-05, "loss": 0.0123, "step": 36630 }, { "loss_action": 0.011461591348052025, "loss_total": 0.011461591348052025, "step": 36630 }, { "grad_norm": 0.2490481734275818, "learning_rate": 7.503960672763166e-05, "loss": 0.0135, "step": 36640 }, { "loss_action": 0.009899141266942024, "loss_total": 0.009899141266942024, "step": 36640 }, { "grad_norm": 0.36640992760658264, "learning_rate": 7.502529346003559e-05, "loss": 0.0121, "step": 36650 }, { "loss_action": 0.011435296386480331, "loss_total": 0.011435296386480331, "step": 36650 }, { "grad_norm": 0.3393673002719879, "learning_rate": 7.501097745571106e-05, "loss": 0.0131, "step": 36660 }, { "loss_action": 0.016255689784884453, "loss_total": 0.016255689784884453, "step": 36660 }, { "grad_norm": 0.338481068611145, "learning_rate": 7.499665871622361e-05, "loss": 0.0132, "step": 36670 }, { "loss_action": 0.01159832626581192, "loss_total": 0.01159832626581192, "step": 36670 }, { "grad_norm": 0.3025607466697693, "learning_rate": 7.498233724313917e-05, "loss": 0.0132, "step": 36680 }, { "loss_action": 0.017965208739042282, "loss_total": 0.017965208739042282, "step": 36680 }, { "grad_norm": 0.30598536133766174, "learning_rate": 7.496801303802387e-05, "loss": 0.0147, "step": 36690 }, { "loss_action": 0.018849201500415802, "loss_total": 0.018849201500415802, "step": 36690 }, { "grad_norm": 0.35619091987609863, "learning_rate": 7.495368610244423e-05, "loss": 0.0147, "step": 36700 }, { "loss_action": 0.013143532909452915, "loss_total": 0.013143532909452915, "step": 36700 }, { "grad_norm": 0.2804235816001892, "learning_rate": 7.493935643796697e-05, "loss": 0.0126, "step": 36710 }, { "loss_action": 0.012547404505312443, "loss_total": 0.012547404505312443, "step": 36710 }, { "grad_norm": 0.3290817439556122, "learning_rate": 7.49250240461592e-05, "loss": 0.0161, "step": 36720 }, { "loss_action": 0.01241679210215807, "loss_total": 0.01241679210215807, "step": 36720 }, { "grad_norm": 0.33389365673065186, "learning_rate": 7.491068892858826e-05, "loss": 0.0148, "step": 36730 }, { "loss_action": 0.01955328695476055, "loss_total": 0.01955328695476055, "step": 36730 }, { "grad_norm": 0.3374989628791809, "learning_rate": 7.489635108682184e-05, "loss": 0.0143, "step": 36740 }, { "loss_action": 0.010552169755101204, "loss_total": 0.010552169755101204, "step": 36740 }, { "grad_norm": 0.2886591851711273, "learning_rate": 7.48820105224279e-05, "loss": 0.0127, "step": 36750 }, { "loss_action": 0.018929459154605865, "loss_total": 0.018929459154605865, "step": 36750 }, { "grad_norm": 0.33501750230789185, "learning_rate": 7.48676672369747e-05, "loss": 0.0133, "step": 36760 }, { "loss_action": 0.017366932705044746, "loss_total": 0.017366932705044746, "step": 36760 }, { "grad_norm": 0.25598692893981934, "learning_rate": 7.485332123203079e-05, "loss": 0.0118, "step": 36770 }, { "loss_action": 0.013704984448850155, "loss_total": 0.013704984448850155, "step": 36770 }, { "grad_norm": 0.3247019350528717, "learning_rate": 7.483897250916504e-05, "loss": 0.0123, "step": 36780 }, { "loss_action": 0.015378735959529877, "loss_total": 0.015378735959529877, "step": 36780 }, { "grad_norm": 0.32488930225372314, "learning_rate": 7.48246210699466e-05, "loss": 0.0168, "step": 36790 }, { "loss_action": 0.015340846963226795, "loss_total": 0.015340846963226795, "step": 36790 }, { "grad_norm": 0.3481060862541199, "learning_rate": 7.481026691594492e-05, "loss": 0.0136, "step": 36800 }, { "loss_action": 0.010089592076838017, "loss_total": 0.010089592076838017, "step": 36800 }, { "grad_norm": 0.3027053475379944, "learning_rate": 7.479591004872975e-05, "loss": 0.0133, "step": 36810 }, { "loss_action": 0.014010242186486721, "loss_total": 0.014010242186486721, "step": 36810 }, { "grad_norm": 0.3707047998905182, "learning_rate": 7.478155046987114e-05, "loss": 0.0155, "step": 36820 }, { "loss_action": 0.012384124100208282, "loss_total": 0.012384124100208282, "step": 36820 }, { "grad_norm": 0.37794044613838196, "learning_rate": 7.476718818093944e-05, "loss": 0.0137, "step": 36830 }, { "loss_action": 0.015079343691468239, "loss_total": 0.015079343691468239, "step": 36830 }, { "grad_norm": 0.26713189482688904, "learning_rate": 7.475282318350527e-05, "loss": 0.0146, "step": 36840 }, { "loss_action": 0.010997849516570568, "loss_total": 0.010997849516570568, "step": 36840 }, { "grad_norm": 0.2973161041736603, "learning_rate": 7.473845547913957e-05, "loss": 0.0136, "step": 36850 }, { "loss_action": 0.014742565341293812, "loss_total": 0.014742565341293812, "step": 36850 }, { "grad_norm": 0.29935160279273987, "learning_rate": 7.472408506941357e-05, "loss": 0.0131, "step": 36860 }, { "loss_action": 0.014378320425748825, "loss_total": 0.014378320425748825, "step": 36860 }, { "grad_norm": 0.3025202453136444, "learning_rate": 7.470971195589881e-05, "loss": 0.0152, "step": 36870 }, { "loss_action": 0.012941702269017696, "loss_total": 0.012941702269017696, "step": 36870 }, { "grad_norm": 0.29961711168289185, "learning_rate": 7.46953361401671e-05, "loss": 0.0134, "step": 36880 }, { "loss_action": 0.01085558533668518, "loss_total": 0.01085558533668518, "step": 36880 }, { "grad_norm": 0.32747143507003784, "learning_rate": 7.468095762379055e-05, "loss": 0.0138, "step": 36890 }, { "loss_action": 0.016875270754098892, "loss_total": 0.016875270754098892, "step": 36890 }, { "grad_norm": 0.40378594398498535, "learning_rate": 7.466657640834158e-05, "loss": 0.0139, "step": 36900 }, { "loss_action": 0.015683559700846672, "loss_total": 0.015683559700846672, "step": 36900 }, { "grad_norm": 0.32782405614852905, "learning_rate": 7.46521924953929e-05, "loss": 0.0135, "step": 36910 }, { "loss_action": 0.012605722062289715, "loss_total": 0.012605722062289715, "step": 36910 }, { "grad_norm": 0.2674562633037567, "learning_rate": 7.463780588651752e-05, "loss": 0.0134, "step": 36920 }, { "loss_action": 0.014953450299799442, "loss_total": 0.014953450299799442, "step": 36920 }, { "grad_norm": 0.28201404213905334, "learning_rate": 7.462341658328873e-05, "loss": 0.013, "step": 36930 }, { "loss_action": 0.011468399316072464, "loss_total": 0.011468399316072464, "step": 36930 }, { "grad_norm": 0.34549421072006226, "learning_rate": 7.460902458728012e-05, "loss": 0.0126, "step": 36940 }, { "loss_action": 0.01321277767419815, "loss_total": 0.01321277767419815, "step": 36940 }, { "grad_norm": 0.2667043209075928, "learning_rate": 7.459462990006558e-05, "loss": 0.0142, "step": 36950 }, { "loss_action": 0.014405785128474236, "loss_total": 0.014405785128474236, "step": 36950 }, { "grad_norm": 0.26593583822250366, "learning_rate": 7.458023252321929e-05, "loss": 0.0133, "step": 36960 }, { "loss_action": 0.012154885567724705, "loss_total": 0.012154885567724705, "step": 36960 }, { "grad_norm": 0.28546398878097534, "learning_rate": 7.456583245831573e-05, "loss": 0.012, "step": 36970 }, { "loss_action": 0.010722201317548752, "loss_total": 0.010722201317548752, "step": 36970 }, { "grad_norm": 0.2757400572299957, "learning_rate": 7.455142970692968e-05, "loss": 0.014, "step": 36980 }, { "loss_action": 0.011508811265230179, "loss_total": 0.011508811265230179, "step": 36980 }, { "grad_norm": 0.28048911690711975, "learning_rate": 7.453702427063615e-05, "loss": 0.0151, "step": 36990 }, { "loss_action": 0.019108306616544724, "loss_total": 0.019108306616544724, "step": 36990 }, { "grad_norm": 0.2380390763282776, "learning_rate": 7.452261615101057e-05, "loss": 0.0147, "step": 37000 }, { "loss_action": 0.01520418282598257, "loss_total": 0.01520418282598257, "step": 37000 }, { "grad_norm": 0.2976732850074768, "learning_rate": 7.450820534962856e-05, "loss": 0.0176, "step": 37010 }, { "loss_action": 0.014430577866733074, "loss_total": 0.014430577866733074, "step": 37010 }, { "grad_norm": 0.24501775205135345, "learning_rate": 7.449379186806604e-05, "loss": 0.0124, "step": 37020 }, { "loss_action": 0.02154386229813099, "loss_total": 0.02154386229813099, "step": 37020 }, { "grad_norm": 0.3288915157318115, "learning_rate": 7.44793757078993e-05, "loss": 0.0143, "step": 37030 }, { "loss_action": 0.013719695620238781, "loss_total": 0.013719695620238781, "step": 37030 }, { "grad_norm": 0.3036576807498932, "learning_rate": 7.44649568707048e-05, "loss": 0.0132, "step": 37040 }, { "loss_action": 0.0109119126573205, "loss_total": 0.0109119126573205, "step": 37040 }, { "grad_norm": 0.3083643317222595, "learning_rate": 7.445053535805942e-05, "loss": 0.0135, "step": 37050 }, { "loss_action": 0.01436004787683487, "loss_total": 0.01436004787683487, "step": 37050 }, { "grad_norm": 0.30798545479774475, "learning_rate": 7.443611117154024e-05, "loss": 0.0144, "step": 37060 }, { "loss_action": 0.014054309576749802, "loss_total": 0.014054309576749802, "step": 37060 }, { "grad_norm": 0.2854306697845459, "learning_rate": 7.442168431272469e-05, "loss": 0.012, "step": 37070 }, { "loss_action": 0.011433146893978119, "loss_total": 0.011433146893978119, "step": 37070 }, { "grad_norm": 0.2608810067176819, "learning_rate": 7.440725478319044e-05, "loss": 0.0135, "step": 37080 }, { "loss_action": 0.013180220499634743, "loss_total": 0.013180220499634743, "step": 37080 }, { "grad_norm": 0.37028825283050537, "learning_rate": 7.439282258451553e-05, "loss": 0.0127, "step": 37090 }, { "loss_action": 0.012586995027959347, "loss_total": 0.012586995027959347, "step": 37090 }, { "grad_norm": 0.29927483201026917, "learning_rate": 7.43783877182782e-05, "loss": 0.0133, "step": 37100 }, { "loss_action": 0.01360208261758089, "loss_total": 0.01360208261758089, "step": 37100 }, { "grad_norm": 0.36283865571022034, "learning_rate": 7.436395018605707e-05, "loss": 0.0131, "step": 37110 }, { "loss_action": 0.01516141276806593, "loss_total": 0.01516141276806593, "step": 37110 }, { "grad_norm": 0.30869609117507935, "learning_rate": 7.434950998943094e-05, "loss": 0.0158, "step": 37120 }, { "loss_action": 0.009924913756549358, "loss_total": 0.009924913756549358, "step": 37120 }, { "grad_norm": 0.33734312653541565, "learning_rate": 7.433506712997902e-05, "loss": 0.0118, "step": 37130 }, { "loss_action": 0.012571308761835098, "loss_total": 0.012571308761835098, "step": 37130 }, { "grad_norm": 0.2758341133594513, "learning_rate": 7.432062160928077e-05, "loss": 0.0132, "step": 37140 }, { "loss_action": 0.016311101615428925, "loss_total": 0.016311101615428925, "step": 37140 }, { "grad_norm": 0.6368025541305542, "learning_rate": 7.430617342891588e-05, "loss": 0.0134, "step": 37150 }, { "loss_action": 0.012445732019841671, "loss_total": 0.012445732019841671, "step": 37150 }, { "grad_norm": 0.3704667091369629, "learning_rate": 7.429172259046442e-05, "loss": 0.0141, "step": 37160 }, { "loss_action": 0.010755081661045551, "loss_total": 0.010755081661045551, "step": 37160 }, { "grad_norm": 0.3128608763217926, "learning_rate": 7.42772690955067e-05, "loss": 0.0138, "step": 37170 }, { "loss_action": 0.023766450583934784, "loss_total": 0.023766450583934784, "step": 37170 }, { "grad_norm": 0.3643800616264343, "learning_rate": 7.426281294562332e-05, "loss": 0.0176, "step": 37180 }, { "loss_action": 0.01389374677091837, "loss_total": 0.01389374677091837, "step": 37180 }, { "grad_norm": 0.31768304109573364, "learning_rate": 7.424835414239519e-05, "loss": 0.0147, "step": 37190 }, { "loss_action": 0.01667248085141182, "loss_total": 0.01667248085141182, "step": 37190 }, { "grad_norm": 0.2989608645439148, "learning_rate": 7.423389268740352e-05, "loss": 0.0146, "step": 37200 }, { "loss_action": 0.011701332405209541, "loss_total": 0.011701332405209541, "step": 37200 }, { "grad_norm": 0.46705055236816406, "learning_rate": 7.42194285822298e-05, "loss": 0.0168, "step": 37210 }, { "loss_action": 0.014019550755620003, "loss_total": 0.014019550755620003, "step": 37210 }, { "grad_norm": 0.38334837555885315, "learning_rate": 7.420496182845576e-05, "loss": 0.0159, "step": 37220 }, { "loss_action": 0.021560076624155045, "loss_total": 0.021560076624155045, "step": 37220 }, { "grad_norm": 0.30808141827583313, "learning_rate": 7.419049242766348e-05, "loss": 0.0198, "step": 37230 }, { "loss_action": 0.017506016418337822, "loss_total": 0.017506016418337822, "step": 37230 }, { "grad_norm": 0.3370263874530792, "learning_rate": 7.417602038143533e-05, "loss": 0.0174, "step": 37240 }, { "loss_action": 0.016862083226442337, "loss_total": 0.016862083226442337, "step": 37240 }, { "grad_norm": 0.3362285792827606, "learning_rate": 7.416154569135393e-05, "loss": 0.0149, "step": 37250 }, { "loss_action": 0.016541069373488426, "loss_total": 0.016541069373488426, "step": 37250 }, { "grad_norm": 0.3097298741340637, "learning_rate": 7.414706835900222e-05, "loss": 0.0157, "step": 37260 }, { "loss_action": 0.012672185897827148, "loss_total": 0.012672185897827148, "step": 37260 }, { "grad_norm": 0.30794757604599, "learning_rate": 7.413258838596345e-05, "loss": 0.014, "step": 37270 }, { "loss_action": 0.01810859516263008, "loss_total": 0.01810859516263008, "step": 37270 }, { "grad_norm": 0.3338845372200012, "learning_rate": 7.411810577382106e-05, "loss": 0.0134, "step": 37280 }, { "loss_action": 0.015826957300305367, "loss_total": 0.015826957300305367, "step": 37280 }, { "grad_norm": 0.45897480845451355, "learning_rate": 7.410362052415889e-05, "loss": 0.014, "step": 37290 }, { "loss_action": 0.010601096786558628, "loss_total": 0.010601096786558628, "step": 37290 }, { "grad_norm": 0.2722685635089874, "learning_rate": 7.408913263856102e-05, "loss": 0.0151, "step": 37300 }, { "loss_action": 0.013886992819607258, "loss_total": 0.013886992819607258, "step": 37300 }, { "grad_norm": 0.31474435329437256, "learning_rate": 7.407464211861183e-05, "loss": 0.014, "step": 37310 }, { "loss_action": 0.012656820937991142, "loss_total": 0.012656820937991142, "step": 37310 }, { "grad_norm": 0.355598121881485, "learning_rate": 7.406014896589597e-05, "loss": 0.0132, "step": 37320 }, { "loss_action": 0.016918586567044258, "loss_total": 0.016918586567044258, "step": 37320 }, { "grad_norm": 0.3049665689468384, "learning_rate": 7.404565318199838e-05, "loss": 0.0149, "step": 37330 }, { "loss_action": 0.010987486690282822, "loss_total": 0.010987486690282822, "step": 37330 }, { "grad_norm": 0.20866818726062775, "learning_rate": 7.403115476850432e-05, "loss": 0.0134, "step": 37340 }, { "loss_action": 0.012967843562364578, "loss_total": 0.012967843562364578, "step": 37340 }, { "grad_norm": 0.35975098609924316, "learning_rate": 7.401665372699932e-05, "loss": 0.0141, "step": 37350 }, { "loss_action": 0.01778991147875786, "loss_total": 0.01778991147875786, "step": 37350 }, { "grad_norm": 0.33116772770881653, "learning_rate": 7.400215005906916e-05, "loss": 0.0159, "step": 37360 }, { "loss_action": 0.01455742958933115, "loss_total": 0.01455742958933115, "step": 37360 }, { "grad_norm": 0.28387174010276794, "learning_rate": 7.398764376629996e-05, "loss": 0.0143, "step": 37370 }, { "loss_action": 0.014115648344159126, "loss_total": 0.014115648344159126, "step": 37370 }, { "grad_norm": 0.2735224962234497, "learning_rate": 7.39731348502781e-05, "loss": 0.0132, "step": 37380 }, { "loss_action": 0.011405699886381626, "loss_total": 0.011405699886381626, "step": 37380 }, { "grad_norm": 0.29454782605171204, "learning_rate": 7.395862331259028e-05, "loss": 0.0141, "step": 37390 }, { "loss_action": 0.010991634801030159, "loss_total": 0.010991634801030159, "step": 37390 }, { "grad_norm": 0.2370583713054657, "learning_rate": 7.394410915482341e-05, "loss": 0.0121, "step": 37400 }, { "loss_action": 0.011597166769206524, "loss_total": 0.011597166769206524, "step": 37400 }, { "grad_norm": 0.23455215990543365, "learning_rate": 7.392959237856476e-05, "loss": 0.0116, "step": 37410 }, { "loss_action": 0.01187692116945982, "loss_total": 0.01187692116945982, "step": 37410 }, { "grad_norm": 0.3019704818725586, "learning_rate": 7.391507298540187e-05, "loss": 0.0135, "step": 37420 }, { "loss_action": 0.010851837694644928, "loss_total": 0.010851837694644928, "step": 37420 }, { "grad_norm": 0.3463580310344696, "learning_rate": 7.390055097692257e-05, "loss": 0.0115, "step": 37430 }, { "loss_action": 0.014378529973328114, "loss_total": 0.014378529973328114, "step": 37430 }, { "grad_norm": 0.4002749025821686, "learning_rate": 7.388602635471494e-05, "loss": 0.0134, "step": 37440 }, { "loss_action": 0.011291028931736946, "loss_total": 0.011291028931736946, "step": 37440 }, { "grad_norm": 0.3021230399608612, "learning_rate": 7.387149912036738e-05, "loss": 0.0142, "step": 37450 }, { "loss_action": 0.018031595274806023, "loss_total": 0.018031595274806023, "step": 37450 }, { "grad_norm": 0.3952314853668213, "learning_rate": 7.385696927546854e-05, "loss": 0.0149, "step": 37460 }, { "loss_action": 0.011899071745574474, "loss_total": 0.011899071745574474, "step": 37460 }, { "grad_norm": 0.3382074534893036, "learning_rate": 7.384243682160743e-05, "loss": 0.0148, "step": 37470 }, { "loss_action": 0.016506388783454895, "loss_total": 0.016506388783454895, "step": 37470 }, { "grad_norm": 0.2972292900085449, "learning_rate": 7.382790176037329e-05, "loss": 0.0152, "step": 37480 }, { "loss_action": 0.014025789685547352, "loss_total": 0.014025789685547352, "step": 37480 }, { "grad_norm": 0.2709130048751831, "learning_rate": 7.381336409335562e-05, "loss": 0.0155, "step": 37490 }, { "loss_action": 0.010877304710447788, "loss_total": 0.010877304710447788, "step": 37490 }, { "grad_norm": 0.3365752398967743, "learning_rate": 7.379882382214426e-05, "loss": 0.0132, "step": 37500 }, { "loss_action": 0.013757022097706795, "loss_total": 0.013757022097706795, "step": 37500 }, { "grad_norm": 0.2803552746772766, "learning_rate": 7.378428094832931e-05, "loss": 0.0125, "step": 37510 }, { "loss_action": 0.00994802825152874, "loss_total": 0.00994802825152874, "step": 37510 }, { "grad_norm": 0.289389431476593, "learning_rate": 7.376973547350114e-05, "loss": 0.0136, "step": 37520 }, { "loss_action": 0.019400369375944138, "loss_total": 0.019400369375944138, "step": 37520 }, { "grad_norm": 0.31115666031837463, "learning_rate": 7.375518739925046e-05, "loss": 0.0137, "step": 37530 }, { "loss_action": 0.012217707931995392, "loss_total": 0.012217707931995392, "step": 37530 }, { "grad_norm": 0.24511313438415527, "learning_rate": 7.374063672716818e-05, "loss": 0.0135, "step": 37540 }, { "loss_action": 0.012281535193324089, "loss_total": 0.012281535193324089, "step": 37540 }, { "grad_norm": 0.3094535171985626, "learning_rate": 7.372608345884558e-05, "loss": 0.0141, "step": 37550 }, { "loss_action": 0.013221879489719868, "loss_total": 0.013221879489719868, "step": 37550 }, { "grad_norm": 0.29459089040756226, "learning_rate": 7.371152759587415e-05, "loss": 0.0135, "step": 37560 }, { "loss_action": 0.015108455903828144, "loss_total": 0.015108455903828144, "step": 37560 }, { "grad_norm": 0.3646409511566162, "learning_rate": 7.369696913984572e-05, "loss": 0.0132, "step": 37570 }, { "loss_action": 0.014746495522558689, "loss_total": 0.014746495522558689, "step": 37570 }, { "grad_norm": 0.24092838168144226, "learning_rate": 7.368240809235237e-05, "loss": 0.0135, "step": 37580 }, { "loss_action": 0.02006078138947487, "loss_total": 0.02006078138947487, "step": 37580 }, { "grad_norm": 0.2579475939273834, "learning_rate": 7.366784445498649e-05, "loss": 0.0135, "step": 37590 }, { "loss_action": 0.011043667793273926, "loss_total": 0.011043667793273926, "step": 37590 }, { "grad_norm": 0.28093215823173523, "learning_rate": 7.36532782293407e-05, "loss": 0.0126, "step": 37600 }, { "loss_action": 0.011663554236292839, "loss_total": 0.011663554236292839, "step": 37600 }, { "grad_norm": 0.29012322425842285, "learning_rate": 7.363870941700797e-05, "loss": 0.0115, "step": 37610 }, { "loss_action": 0.008467288687825203, "loss_total": 0.008467288687825203, "step": 37610 }, { "grad_norm": 0.2775384783744812, "learning_rate": 7.362413801958152e-05, "loss": 0.0118, "step": 37620 }, { "loss_action": 0.013799243606626987, "loss_total": 0.013799243606626987, "step": 37620 }, { "grad_norm": 0.2791292071342468, "learning_rate": 7.360956403865486e-05, "loss": 0.0128, "step": 37630 }, { "loss_action": 0.013362371362745762, "loss_total": 0.013362371362745762, "step": 37630 }, { "grad_norm": 0.26308953762054443, "learning_rate": 7.359498747582177e-05, "loss": 0.0119, "step": 37640 }, { "loss_action": 0.010054392740130424, "loss_total": 0.010054392740130424, "step": 37640 }, { "grad_norm": 0.23997282981872559, "learning_rate": 7.358040833267634e-05, "loss": 0.0111, "step": 37650 }, { "loss_action": 0.010715408250689507, "loss_total": 0.010715408250689507, "step": 37650 }, { "grad_norm": 0.26999253034591675, "learning_rate": 7.356582661081288e-05, "loss": 0.0116, "step": 37660 }, { "loss_action": 0.008166992105543613, "loss_total": 0.008166992105543613, "step": 37660 }, { "grad_norm": 0.2344764769077301, "learning_rate": 7.355124231182607e-05, "loss": 0.0106, "step": 37670 }, { "loss_action": 0.012908111326396465, "loss_total": 0.012908111326396465, "step": 37670 }, { "grad_norm": 0.23776954412460327, "learning_rate": 7.353665543731083e-05, "loss": 0.0125, "step": 37680 }, { "loss_action": 0.009649031795561314, "loss_total": 0.009649031795561314, "step": 37680 }, { "grad_norm": 0.19846674799919128, "learning_rate": 7.352206598886229e-05, "loss": 0.0119, "step": 37690 }, { "loss_action": 0.008862761780619621, "loss_total": 0.008862761780619621, "step": 37690 }, { "grad_norm": 0.30212393403053284, "learning_rate": 7.350747396807601e-05, "loss": 0.0131, "step": 37700 }, { "loss_action": 0.01928185485303402, "loss_total": 0.01928185485303402, "step": 37700 }, { "grad_norm": 0.32547736167907715, "learning_rate": 7.349287937654772e-05, "loss": 0.0151, "step": 37710 }, { "loss_action": 0.009545143693685532, "loss_total": 0.009545143693685532, "step": 37710 }, { "grad_norm": 0.28462451696395874, "learning_rate": 7.347828221587345e-05, "loss": 0.0138, "step": 37720 }, { "loss_action": 0.01499762013554573, "loss_total": 0.01499762013554573, "step": 37720 }, { "grad_norm": 0.2961835265159607, "learning_rate": 7.346368248764955e-05, "loss": 0.0138, "step": 37730 }, { "loss_action": 0.012213749811053276, "loss_total": 0.012213749811053276, "step": 37730 }, { "grad_norm": 0.2584400773048401, "learning_rate": 7.34490801934726e-05, "loss": 0.0118, "step": 37740 }, { "loss_action": 0.01489307265728712, "loss_total": 0.01489307265728712, "step": 37740 }, { "grad_norm": 0.39475736021995544, "learning_rate": 7.343447533493947e-05, "loss": 0.0147, "step": 37750 }, { "loss_action": 0.022163772955536842, "loss_total": 0.022163772955536842, "step": 37750 }, { "grad_norm": 0.26746270060539246, "learning_rate": 7.341986791364739e-05, "loss": 0.0149, "step": 37760 }, { "loss_action": 0.011124730110168457, "loss_total": 0.011124730110168457, "step": 37760 }, { "grad_norm": 0.3394078314304352, "learning_rate": 7.340525793119374e-05, "loss": 0.0139, "step": 37770 }, { "loss_action": 0.012568882666528225, "loss_total": 0.012568882666528225, "step": 37770 }, { "grad_norm": 0.3684212565422058, "learning_rate": 7.33906453891763e-05, "loss": 0.0115, "step": 37780 }, { "loss_action": 0.015087147243320942, "loss_total": 0.015087147243320942, "step": 37780 }, { "grad_norm": 0.2634543478488922, "learning_rate": 7.337603028919303e-05, "loss": 0.0132, "step": 37790 }, { "loss_action": 0.01267505344003439, "loss_total": 0.01267505344003439, "step": 37790 }, { "grad_norm": 0.28595495223999023, "learning_rate": 7.336141263284225e-05, "loss": 0.0126, "step": 37800 }, { "loss_action": 0.009660474956035614, "loss_total": 0.009660474956035614, "step": 37800 }, { "grad_norm": 0.2927733361721039, "learning_rate": 7.334679242172249e-05, "loss": 0.0128, "step": 37810 }, { "loss_action": 0.01105889119207859, "loss_total": 0.01105889119207859, "step": 37810 }, { "grad_norm": 0.33001795411109924, "learning_rate": 7.33321696574326e-05, "loss": 0.0135, "step": 37820 }, { "loss_action": 0.020078280940651894, "loss_total": 0.020078280940651894, "step": 37820 }, { "grad_norm": 0.2725330591201782, "learning_rate": 7.331754434157174e-05, "loss": 0.0142, "step": 37830 }, { "loss_action": 0.012705103494226933, "loss_total": 0.012705103494226933, "step": 37830 }, { "grad_norm": 0.2501739263534546, "learning_rate": 7.330291647573928e-05, "loss": 0.0132, "step": 37840 }, { "loss_action": 0.014438534155488014, "loss_total": 0.014438534155488014, "step": 37840 }, { "grad_norm": 0.29415515065193176, "learning_rate": 7.32882860615349e-05, "loss": 0.0118, "step": 37850 }, { "loss_action": 0.010904785245656967, "loss_total": 0.010904785245656967, "step": 37850 }, { "grad_norm": 0.4169785976409912, "learning_rate": 7.327365310055858e-05, "loss": 0.0136, "step": 37860 }, { "loss_action": 0.01815726049244404, "loss_total": 0.01815726049244404, "step": 37860 }, { "grad_norm": 0.4142530858516693, "learning_rate": 7.325901759441055e-05, "loss": 0.0137, "step": 37870 }, { "loss_action": 0.010254091583192348, "loss_total": 0.010254091583192348, "step": 37870 }, { "grad_norm": 0.3188619911670685, "learning_rate": 7.324437954469132e-05, "loss": 0.0142, "step": 37880 }, { "loss_action": 0.011758537031710148, "loss_total": 0.011758537031710148, "step": 37880 }, { "grad_norm": 0.2576344907283783, "learning_rate": 7.32297389530017e-05, "loss": 0.0144, "step": 37890 }, { "loss_action": 0.015106565319001675, "loss_total": 0.015106565319001675, "step": 37890 }, { "grad_norm": 0.3480991721153259, "learning_rate": 7.321509582094274e-05, "loss": 0.0134, "step": 37900 }, { "loss_action": 0.013585821725428104, "loss_total": 0.013585821725428104, "step": 37900 }, { "grad_norm": 0.2969520688056946, "learning_rate": 7.320045015011582e-05, "loss": 0.0141, "step": 37910 }, { "loss_action": 0.0159177016466856, "loss_total": 0.0159177016466856, "step": 37910 }, { "grad_norm": 0.37412840127944946, "learning_rate": 7.318580194212253e-05, "loss": 0.0136, "step": 37920 }, { "loss_action": 0.017187025398015976, "loss_total": 0.017187025398015976, "step": 37920 }, { "grad_norm": 0.30164191126823425, "learning_rate": 7.317115119856483e-05, "loss": 0.0131, "step": 37930 }, { "loss_action": 0.01909753866493702, "loss_total": 0.01909753866493702, "step": 37930 }, { "grad_norm": 0.3270355463027954, "learning_rate": 7.315649792104485e-05, "loss": 0.0128, "step": 37940 }, { "loss_action": 0.011262355372309685, "loss_total": 0.011262355372309685, "step": 37940 }, { "grad_norm": 0.31066152453422546, "learning_rate": 7.314184211116507e-05, "loss": 0.0135, "step": 37950 }, { "loss_action": 0.013197791762650013, "loss_total": 0.013197791762650013, "step": 37950 }, { "grad_norm": 0.26457351446151733, "learning_rate": 7.312718377052823e-05, "loss": 0.0136, "step": 37960 }, { "loss_action": 0.011089324951171875, "loss_total": 0.011089324951171875, "step": 37960 }, { "grad_norm": 0.2670106291770935, "learning_rate": 7.311252290073737e-05, "loss": 0.0123, "step": 37970 }, { "loss_action": 0.011200792156159878, "loss_total": 0.011200792156159878, "step": 37970 }, { "grad_norm": 0.3334656059741974, "learning_rate": 7.309785950339572e-05, "loss": 0.0134, "step": 37980 }, { "loss_action": 0.014431975781917572, "loss_total": 0.014431975781917572, "step": 37980 }, { "grad_norm": 0.27931085228919983, "learning_rate": 7.308319358010692e-05, "loss": 0.0137, "step": 37990 }, { "loss_action": 0.009980286471545696, "loss_total": 0.009980286471545696, "step": 37990 }, { "grad_norm": 0.2814388871192932, "learning_rate": 7.306852513247474e-05, "loss": 0.0126, "step": 38000 }, { "loss_action": 0.011140627786517143, "loss_total": 0.011140627786517143, "step": 38000 }, { "grad_norm": 0.36815205216407776, "learning_rate": 7.305385416210336e-05, "loss": 0.0155, "step": 38010 }, { "loss_action": 0.013234441168606281, "loss_total": 0.013234441168606281, "step": 38010 }, { "grad_norm": 0.3923218846321106, "learning_rate": 7.303918067059711e-05, "loss": 0.013, "step": 38020 }, { "loss_action": 0.012433111667633057, "loss_total": 0.012433111667633057, "step": 38020 }, { "grad_norm": 0.2688208520412445, "learning_rate": 7.302450465956075e-05, "loss": 0.0141, "step": 38030 }, { "loss_action": 0.010092165321111679, "loss_total": 0.010092165321111679, "step": 38030 }, { "grad_norm": 0.4197181463241577, "learning_rate": 7.300982613059914e-05, "loss": 0.0139, "step": 38040 }, { "loss_action": 0.019180001690983772, "loss_total": 0.019180001690983772, "step": 38040 }, { "grad_norm": 0.2686893045902252, "learning_rate": 7.299514508531757e-05, "loss": 0.0152, "step": 38050 }, { "loss_action": 0.016603928059339523, "loss_total": 0.016603928059339523, "step": 38050 }, { "grad_norm": 0.26132825016975403, "learning_rate": 7.298046152532148e-05, "loss": 0.0151, "step": 38060 }, { "loss_action": 0.016056828200817108, "loss_total": 0.016056828200817108, "step": 38060 }, { "grad_norm": 0.24629686772823334, "learning_rate": 7.296577545221668e-05, "loss": 0.0148, "step": 38070 }, { "loss_action": 0.016613487154245377, "loss_total": 0.016613487154245377, "step": 38070 }, { "grad_norm": 0.293382465839386, "learning_rate": 7.29510868676092e-05, "loss": 0.015, "step": 38080 }, { "loss_action": 0.01318575069308281, "loss_total": 0.01318575069308281, "step": 38080 }, { "grad_norm": 0.26578250527381897, "learning_rate": 7.293639577310538e-05, "loss": 0.0133, "step": 38090 }, { "loss_action": 0.013190900906920433, "loss_total": 0.013190900906920433, "step": 38090 }, { "grad_norm": 0.26799848675727844, "learning_rate": 7.292170217031179e-05, "loss": 0.0151, "step": 38100 }, { "loss_action": 0.014828626997768879, "loss_total": 0.014828626997768879, "step": 38100 }, { "grad_norm": 0.33719417452812195, "learning_rate": 7.290700606083532e-05, "loss": 0.0135, "step": 38110 }, { "loss_action": 0.011762564070522785, "loss_total": 0.011762564070522785, "step": 38110 }, { "grad_norm": 0.29053691029548645, "learning_rate": 7.28923074462831e-05, "loss": 0.0125, "step": 38120 }, { "loss_action": 0.017311468720436096, "loss_total": 0.017311468720436096, "step": 38120 }, { "grad_norm": 0.32038262486457825, "learning_rate": 7.287760632826255e-05, "loss": 0.0145, "step": 38130 }, { "loss_action": 0.009693271480500698, "loss_total": 0.009693271480500698, "step": 38130 }, { "grad_norm": 0.26805463433265686, "learning_rate": 7.286290270838139e-05, "loss": 0.0134, "step": 38140 }, { "loss_action": 0.0148208849132061, "loss_total": 0.0148208849132061, "step": 38140 }, { "grad_norm": 0.4731155037879944, "learning_rate": 7.284819658824756e-05, "loss": 0.0128, "step": 38150 }, { "loss_action": 0.012172486633062363, "loss_total": 0.012172486633062363, "step": 38150 }, { "grad_norm": 0.26186901330947876, "learning_rate": 7.283348796946929e-05, "loss": 0.0128, "step": 38160 }, { "loss_action": 0.01532518770545721, "loss_total": 0.01532518770545721, "step": 38160 }, { "grad_norm": 0.29728975892066956, "learning_rate": 7.28187768536551e-05, "loss": 0.0134, "step": 38170 }, { "loss_action": 0.011061549186706543, "loss_total": 0.011061549186706543, "step": 38170 }, { "grad_norm": 0.26622089743614197, "learning_rate": 7.280406324241379e-05, "loss": 0.0121, "step": 38180 }, { "loss_action": 0.01073477417230606, "loss_total": 0.01073477417230606, "step": 38180 }, { "grad_norm": 0.2687828242778778, "learning_rate": 7.278934713735441e-05, "loss": 0.0113, "step": 38190 }, { "loss_action": 0.010488234460353851, "loss_total": 0.010488234460353851, "step": 38190 }, { "grad_norm": 0.3081757128238678, "learning_rate": 7.277462854008629e-05, "loss": 0.0127, "step": 38200 }, { "loss_action": 0.010812955908477306, "loss_total": 0.010812955908477306, "step": 38200 }, { "grad_norm": 0.35300514101982117, "learning_rate": 7.275990745221904e-05, "loss": 0.0114, "step": 38210 }, { "loss_action": 0.012617357075214386, "loss_total": 0.012617357075214386, "step": 38210 }, { "grad_norm": 0.3441923260688782, "learning_rate": 7.274518387536252e-05, "loss": 0.0127, "step": 38220 }, { "loss_action": 0.01007795799523592, "loss_total": 0.01007795799523592, "step": 38220 }, { "grad_norm": 0.3627093732357025, "learning_rate": 7.273045781112689e-05, "loss": 0.0129, "step": 38230 }, { "loss_action": 0.010393782518804073, "loss_total": 0.010393782518804073, "step": 38230 }, { "grad_norm": 0.26333218812942505, "learning_rate": 7.271572926112257e-05, "loss": 0.0121, "step": 38240 }, { "loss_action": 0.018118586391210556, "loss_total": 0.018118586391210556, "step": 38240 }, { "grad_norm": 0.30237534642219543, "learning_rate": 7.270099822696024e-05, "loss": 0.0139, "step": 38250 }, { "loss_action": 0.012865392491221428, "loss_total": 0.012865392491221428, "step": 38250 }, { "grad_norm": 0.35913601517677307, "learning_rate": 7.26862647102509e-05, "loss": 0.0129, "step": 38260 }, { "loss_action": 0.019573425874114037, "loss_total": 0.019573425874114037, "step": 38260 }, { "grad_norm": 0.25313135981559753, "learning_rate": 7.267152871260573e-05, "loss": 0.0133, "step": 38270 }, { "loss_action": 0.013493455946445465, "loss_total": 0.013493455946445465, "step": 38270 }, { "grad_norm": 0.38188615441322327, "learning_rate": 7.265679023563629e-05, "loss": 0.0134, "step": 38280 }, { "loss_action": 0.013791232369840145, "loss_total": 0.013791232369840145, "step": 38280 }, { "grad_norm": 0.2637946307659149, "learning_rate": 7.264204928095433e-05, "loss": 0.0134, "step": 38290 }, { "loss_action": 0.013633972965180874, "loss_total": 0.013633972965180874, "step": 38290 }, { "grad_norm": 0.30966776609420776, "learning_rate": 7.262730585017188e-05, "loss": 0.0138, "step": 38300 }, { "loss_action": 0.013087148778140545, "loss_total": 0.013087148778140545, "step": 38300 }, { "grad_norm": 0.23085816204547882, "learning_rate": 7.261255994490131e-05, "loss": 0.0119, "step": 38310 }, { "loss_action": 0.012358886189758778, "loss_total": 0.012358886189758778, "step": 38310 }, { "grad_norm": 0.2652508020401001, "learning_rate": 7.259781156675517e-05, "loss": 0.0117, "step": 38320 }, { "loss_action": 0.013636630959808826, "loss_total": 0.013636630959808826, "step": 38320 }, { "grad_norm": 0.2626245617866516, "learning_rate": 7.258306071734633e-05, "loss": 0.0123, "step": 38330 }, { "loss_action": 0.011868072673678398, "loss_total": 0.011868072673678398, "step": 38330 }, { "grad_norm": 0.2651278078556061, "learning_rate": 7.256830739828792e-05, "loss": 0.0141, "step": 38340 }, { "loss_action": 0.009339148178696632, "loss_total": 0.009339148178696632, "step": 38340 }, { "grad_norm": 0.1930292397737503, "learning_rate": 7.255355161119336e-05, "loss": 0.0113, "step": 38350 }, { "loss_action": 0.011072083376348019, "loss_total": 0.011072083376348019, "step": 38350 }, { "grad_norm": 0.3099020719528198, "learning_rate": 7.253879335767628e-05, "loss": 0.0118, "step": 38360 }, { "loss_action": 0.01355856191366911, "loss_total": 0.01355856191366911, "step": 38360 }, { "grad_norm": 0.3954152762889862, "learning_rate": 7.252403263935067e-05, "loss": 0.0136, "step": 38370 }, { "loss_action": 0.011804493144154549, "loss_total": 0.011804493144154549, "step": 38370 }, { "grad_norm": 0.43039825558662415, "learning_rate": 7.25092694578307e-05, "loss": 0.0152, "step": 38380 }, { "loss_action": 0.015348244458436966, "loss_total": 0.015348244458436966, "step": 38380 }, { "grad_norm": 0.4446863532066345, "learning_rate": 7.249450381473087e-05, "loss": 0.0136, "step": 38390 }, { "loss_action": 0.0186612606048584, "loss_total": 0.0186612606048584, "step": 38390 }, { "grad_norm": 0.30888310074806213, "learning_rate": 7.247973571166593e-05, "loss": 0.0142, "step": 38400 }, { "loss_action": 0.011353341862559319, "loss_total": 0.011353341862559319, "step": 38400 }, { "grad_norm": 0.2773014307022095, "learning_rate": 7.246496515025089e-05, "loss": 0.0118, "step": 38410 }, { "loss_action": 0.014802604913711548, "loss_total": 0.014802604913711548, "step": 38410 }, { "grad_norm": 0.28158703446388245, "learning_rate": 7.245019213210101e-05, "loss": 0.0126, "step": 38420 }, { "loss_action": 0.010266797617077827, "loss_total": 0.010266797617077827, "step": 38420 }, { "grad_norm": 0.2666899859905243, "learning_rate": 7.24354166588319e-05, "loss": 0.0131, "step": 38430 }, { "loss_action": 0.01482132263481617, "loss_total": 0.01482132263481617, "step": 38430 }, { "grad_norm": 0.2646835148334503, "learning_rate": 7.242063873205935e-05, "loss": 0.0145, "step": 38440 }, { "loss_action": 0.0148025993257761, "loss_total": 0.0148025993257761, "step": 38440 }, { "grad_norm": 0.2414575219154358, "learning_rate": 7.240585835339946e-05, "loss": 0.014, "step": 38450 }, { "loss_action": 0.013959677889943123, "loss_total": 0.013959677889943123, "step": 38450 }, { "grad_norm": 0.35058847069740295, "learning_rate": 7.239107552446857e-05, "loss": 0.0149, "step": 38460 }, { "loss_action": 0.013141586445271969, "loss_total": 0.013141586445271969, "step": 38460 }, { "grad_norm": 0.292590469121933, "learning_rate": 7.237629024688334e-05, "loss": 0.0133, "step": 38470 }, { "loss_action": 0.014638901688158512, "loss_total": 0.014638901688158512, "step": 38470 }, { "grad_norm": 0.269538938999176, "learning_rate": 7.236150252226064e-05, "loss": 0.0147, "step": 38480 }, { "loss_action": 0.013916604220867157, "loss_total": 0.013916604220867157, "step": 38480 }, { "grad_norm": 0.32423049211502075, "learning_rate": 7.234671235221765e-05, "loss": 0.0133, "step": 38490 }, { "loss_action": 0.013658035546541214, "loss_total": 0.013658035546541214, "step": 38490 }, { "grad_norm": 0.26361310482025146, "learning_rate": 7.233191973837179e-05, "loss": 0.0136, "step": 38500 }, { "loss_action": 0.013320587575435638, "loss_total": 0.013320587575435638, "step": 38500 }, { "grad_norm": 0.3062809109687805, "learning_rate": 7.231712468234078e-05, "loss": 0.0128, "step": 38510 }, { "loss_action": 0.010370980948209763, "loss_total": 0.010370980948209763, "step": 38510 }, { "grad_norm": 0.3649854063987732, "learning_rate": 7.230232718574254e-05, "loss": 0.0141, "step": 38520 }, { "loss_action": 0.01237682718783617, "loss_total": 0.01237682718783617, "step": 38520 }, { "grad_norm": 0.291437029838562, "learning_rate": 7.228752725019535e-05, "loss": 0.0135, "step": 38530 }, { "loss_action": 0.020737750455737114, "loss_total": 0.020737750455737114, "step": 38530 }, { "grad_norm": 0.29887112975120544, "learning_rate": 7.227272487731769e-05, "loss": 0.0137, "step": 38540 }, { "loss_action": 0.01257400494068861, "loss_total": 0.01257400494068861, "step": 38540 }, { "grad_norm": 0.2332972288131714, "learning_rate": 7.225792006872831e-05, "loss": 0.0136, "step": 38550 }, { "loss_action": 0.01499931700527668, "loss_total": 0.01499931700527668, "step": 38550 }, { "grad_norm": 0.27613404393196106, "learning_rate": 7.224311282604628e-05, "loss": 0.0143, "step": 38560 }, { "loss_action": 0.011994953267276287, "loss_total": 0.011994953267276287, "step": 38560 }, { "grad_norm": 0.30862975120544434, "learning_rate": 7.222830315089085e-05, "loss": 0.014, "step": 38570 }, { "loss_action": 0.01367715373635292, "loss_total": 0.01367715373635292, "step": 38570 }, { "grad_norm": 0.31905829906463623, "learning_rate": 7.22134910448816e-05, "loss": 0.0137, "step": 38580 }, { "loss_action": 0.013888459652662277, "loss_total": 0.013888459652662277, "step": 38580 }, { "grad_norm": 0.36491838097572327, "learning_rate": 7.219867650963839e-05, "loss": 0.0153, "step": 38590 }, { "loss_action": 0.01373568270355463, "loss_total": 0.01373568270355463, "step": 38590 }, { "grad_norm": 0.3063741624355316, "learning_rate": 7.21838595467813e-05, "loss": 0.0146, "step": 38600 }, { "loss_action": 0.01627209410071373, "loss_total": 0.01627209410071373, "step": 38600 }, { "grad_norm": 0.2905270457267761, "learning_rate": 7.216904015793067e-05, "loss": 0.0131, "step": 38610 }, { "loss_action": 0.01676892302930355, "loss_total": 0.01676892302930355, "step": 38610 }, { "grad_norm": 0.27807873487472534, "learning_rate": 7.215421834470713e-05, "loss": 0.0148, "step": 38620 }, { "loss_action": 0.011135631240904331, "loss_total": 0.011135631240904331, "step": 38620 }, { "grad_norm": 0.26021671295166016, "learning_rate": 7.213939410873158e-05, "loss": 0.0121, "step": 38630 }, { "loss_action": 0.014572683721780777, "loss_total": 0.014572683721780777, "step": 38630 }, { "grad_norm": 0.3368833661079407, "learning_rate": 7.212456745162519e-05, "loss": 0.0141, "step": 38640 }, { "loss_action": 0.014567829668521881, "loss_total": 0.014567829668521881, "step": 38640 }, { "grad_norm": 0.310183584690094, "learning_rate": 7.210973837500937e-05, "loss": 0.0131, "step": 38650 }, { "loss_action": 0.020152194425463676, "loss_total": 0.020152194425463676, "step": 38650 }, { "grad_norm": 0.3402172327041626, "learning_rate": 7.209490688050578e-05, "loss": 0.0125, "step": 38660 }, { "loss_action": 0.010448837652802467, "loss_total": 0.010448837652802467, "step": 38660 }, { "grad_norm": 0.3394175171852112, "learning_rate": 7.208007296973641e-05, "loss": 0.0136, "step": 38670 }, { "loss_action": 0.008645408786833286, "loss_total": 0.008645408786833286, "step": 38670 }, { "grad_norm": 0.3335784077644348, "learning_rate": 7.206523664432345e-05, "loss": 0.0122, "step": 38680 }, { "loss_action": 0.013803199864923954, "loss_total": 0.013803199864923954, "step": 38680 }, { "grad_norm": 0.37989673018455505, "learning_rate": 7.205039790588939e-05, "loss": 0.0138, "step": 38690 }, { "loss_action": 0.011818913742899895, "loss_total": 0.011818913742899895, "step": 38690 }, { "grad_norm": 0.26232200860977173, "learning_rate": 7.203555675605697e-05, "loss": 0.0127, "step": 38700 }, { "loss_action": 0.014256875030696392, "loss_total": 0.014256875030696392, "step": 38700 }, { "grad_norm": 0.28515326976776123, "learning_rate": 7.202071319644917e-05, "loss": 0.013, "step": 38710 }, { "loss_action": 0.012136923149228096, "loss_total": 0.012136923149228096, "step": 38710 }, { "grad_norm": 0.2379937320947647, "learning_rate": 7.200586722868932e-05, "loss": 0.0124, "step": 38720 }, { "loss_action": 0.011937204748392105, "loss_total": 0.011937204748392105, "step": 38720 }, { "grad_norm": 0.33941149711608887, "learning_rate": 7.199101885440088e-05, "loss": 0.0127, "step": 38730 }, { "loss_action": 0.0071657802909612656, "loss_total": 0.0071657802909612656, "step": 38730 }, { "grad_norm": 0.33464327454566956, "learning_rate": 7.197616807520771e-05, "loss": 0.0134, "step": 38740 }, { "loss_action": 0.014845437370240688, "loss_total": 0.014845437370240688, "step": 38740 }, { "grad_norm": 0.2475733458995819, "learning_rate": 7.196131489273381e-05, "loss": 0.0152, "step": 38750 }, { "loss_action": 0.013917488045990467, "loss_total": 0.013917488045990467, "step": 38750 }, { "grad_norm": 0.2845812737941742, "learning_rate": 7.194645930860355e-05, "loss": 0.0154, "step": 38760 }, { "loss_action": 0.011231385171413422, "loss_total": 0.011231385171413422, "step": 38760 }, { "grad_norm": 0.3227699398994446, "learning_rate": 7.19316013244415e-05, "loss": 0.0146, "step": 38770 }, { "loss_action": 0.016943158581852913, "loss_total": 0.016943158581852913, "step": 38770 }, { "grad_norm": 0.2432926744222641, "learning_rate": 7.191674094187248e-05, "loss": 0.014, "step": 38780 }, { "loss_action": 0.010670292191207409, "loss_total": 0.010670292191207409, "step": 38780 }, { "grad_norm": 0.2687956392765045, "learning_rate": 7.190187816252165e-05, "loss": 0.0131, "step": 38790 }, { "loss_action": 0.015404628589749336, "loss_total": 0.015404628589749336, "step": 38790 }, { "grad_norm": 0.2177959382534027, "learning_rate": 7.188701298801435e-05, "loss": 0.0113, "step": 38800 }, { "loss_action": 0.009953890927135944, "loss_total": 0.009953890927135944, "step": 38800 }, { "grad_norm": 0.31127017736434937, "learning_rate": 7.18721454199762e-05, "loss": 0.0124, "step": 38810 }, { "loss_action": 0.016110142692923546, "loss_total": 0.016110142692923546, "step": 38810 }, { "grad_norm": 0.27725884318351746, "learning_rate": 7.185727546003312e-05, "loss": 0.013, "step": 38820 }, { "loss_action": 0.01966637559235096, "loss_total": 0.01966637559235096, "step": 38820 }, { "grad_norm": 0.26553139090538025, "learning_rate": 7.184240310981126e-05, "loss": 0.0136, "step": 38830 }, { "loss_action": 0.01248091645538807, "loss_total": 0.01248091645538807, "step": 38830 }, { "grad_norm": 0.30074089765548706, "learning_rate": 7.182752837093704e-05, "loss": 0.0123, "step": 38840 }, { "loss_action": 0.009514115750789642, "loss_total": 0.009514115750789642, "step": 38840 }, { "grad_norm": 0.2802470028400421, "learning_rate": 7.181265124503711e-05, "loss": 0.0128, "step": 38850 }, { "loss_action": 0.014935211278498173, "loss_total": 0.014935211278498173, "step": 38850 }, { "grad_norm": 0.3396596312522888, "learning_rate": 7.179777173373847e-05, "loss": 0.012, "step": 38860 }, { "loss_action": 0.011058886535465717, "loss_total": 0.011058886535465717, "step": 38860 }, { "grad_norm": 0.2745797336101532, "learning_rate": 7.178288983866826e-05, "loss": 0.0122, "step": 38870 }, { "loss_action": 0.012903405353426933, "loss_total": 0.012903405353426933, "step": 38870 }, { "grad_norm": 0.30495983362197876, "learning_rate": 7.176800556145397e-05, "loss": 0.012, "step": 38880 }, { "loss_action": 0.013563036918640137, "loss_total": 0.013563036918640137, "step": 38880 }, { "grad_norm": 0.2940322458744049, "learning_rate": 7.175311890372334e-05, "loss": 0.0146, "step": 38890 }, { "loss_action": 0.019371340051293373, "loss_total": 0.019371340051293373, "step": 38890 }, { "grad_norm": 0.23547124862670898, "learning_rate": 7.17382298671043e-05, "loss": 0.014, "step": 38900 }, { "loss_action": 0.018937595188617706, "loss_total": 0.018937595188617706, "step": 38900 }, { "grad_norm": 0.27738818526268005, "learning_rate": 7.172333845322515e-05, "loss": 0.013, "step": 38910 }, { "loss_action": 0.011493002995848656, "loss_total": 0.011493002995848656, "step": 38910 }, { "grad_norm": 0.3296661376953125, "learning_rate": 7.170844466371436e-05, "loss": 0.0131, "step": 38920 }, { "loss_action": 0.015456593595445156, "loss_total": 0.015456593595445156, "step": 38920 }, { "grad_norm": 0.31981027126312256, "learning_rate": 7.16935485002007e-05, "loss": 0.0132, "step": 38930 }, { "loss_action": 0.010950633324682713, "loss_total": 0.010950633324682713, "step": 38930 }, { "grad_norm": 0.23971588909626007, "learning_rate": 7.167864996431319e-05, "loss": 0.0111, "step": 38940 }, { "loss_action": 0.012763451784849167, "loss_total": 0.012763451784849167, "step": 38940 }, { "grad_norm": 0.39251261949539185, "learning_rate": 7.166374905768111e-05, "loss": 0.0134, "step": 38950 }, { "loss_action": 0.010414112359285355, "loss_total": 0.010414112359285355, "step": 38950 }, { "grad_norm": 0.3426673710346222, "learning_rate": 7.164884578193401e-05, "loss": 0.0123, "step": 38960 }, { "loss_action": 0.012819238938391209, "loss_total": 0.012819238938391209, "step": 38960 }, { "grad_norm": 0.3322766125202179, "learning_rate": 7.163394013870168e-05, "loss": 0.0124, "step": 38970 }, { "loss_action": 0.016239019110798836, "loss_total": 0.016239019110798836, "step": 38970 }, { "grad_norm": 0.2904943823814392, "learning_rate": 7.161903212961419e-05, "loss": 0.0135, "step": 38980 }, { "loss_action": 0.01082878839224577, "loss_total": 0.01082878839224577, "step": 38980 }, { "grad_norm": 0.33213478326797485, "learning_rate": 7.160412175630183e-05, "loss": 0.012, "step": 38990 }, { "loss_action": 0.01083393208682537, "loss_total": 0.01083393208682537, "step": 38990 }, { "grad_norm": 0.30738547444343567, "learning_rate": 7.158920902039521e-05, "loss": 0.0116, "step": 39000 }, { "loss_action": 0.018248803913593292, "loss_total": 0.018248803913593292, "step": 39000 }, { "grad_norm": 0.3005410134792328, "learning_rate": 7.157429392352514e-05, "loss": 0.015, "step": 39010 }, { "loss_action": 0.0130311893299222, "loss_total": 0.0130311893299222, "step": 39010 }, { "grad_norm": 0.2548494040966034, "learning_rate": 7.155937646732275e-05, "loss": 0.0113, "step": 39020 }, { "loss_action": 0.0108264135196805, "loss_total": 0.0108264135196805, "step": 39020 }, { "grad_norm": 0.26090162992477417, "learning_rate": 7.154445665341933e-05, "loss": 0.0124, "step": 39030 }, { "loss_action": 0.010374815203249454, "loss_total": 0.010374815203249454, "step": 39030 }, { "grad_norm": 0.31702351570129395, "learning_rate": 7.152953448344654e-05, "loss": 0.0129, "step": 39040 }, { "loss_action": 0.008092265576124191, "loss_total": 0.008092265576124191, "step": 39040 }, { "grad_norm": 0.25954386591911316, "learning_rate": 7.151460995903624e-05, "loss": 0.0123, "step": 39050 }, { "loss_action": 0.010413178242743015, "loss_total": 0.010413178242743015, "step": 39050 }, { "grad_norm": 0.3470672070980072, "learning_rate": 7.149968308182052e-05, "loss": 0.0129, "step": 39060 }, { "loss_action": 0.016311997547745705, "loss_total": 0.016311997547745705, "step": 39060 }, { "grad_norm": 0.29021841287612915, "learning_rate": 7.14847538534318e-05, "loss": 0.0165, "step": 39070 }, { "loss_action": 0.014700536616146564, "loss_total": 0.014700536616146564, "step": 39070 }, { "grad_norm": 0.31176263093948364, "learning_rate": 7.14698222755027e-05, "loss": 0.0145, "step": 39080 }, { "loss_action": 0.014132506214082241, "loss_total": 0.014132506214082241, "step": 39080 }, { "grad_norm": 0.2739526033401489, "learning_rate": 7.14548883496661e-05, "loss": 0.0139, "step": 39090 }, { "loss_action": 0.015553184784948826, "loss_total": 0.015553184784948826, "step": 39090 }, { "grad_norm": 0.3069361746311188, "learning_rate": 7.143995207755517e-05, "loss": 0.0153, "step": 39100 }, { "loss_action": 0.015690090134739876, "loss_total": 0.015690090134739876, "step": 39100 }, { "grad_norm": 0.3078468143939972, "learning_rate": 7.142501346080333e-05, "loss": 0.0131, "step": 39110 }, { "loss_action": 0.013047468848526478, "loss_total": 0.013047468848526478, "step": 39110 }, { "grad_norm": 0.26682934165000916, "learning_rate": 7.141007250104421e-05, "loss": 0.0136, "step": 39120 }, { "loss_action": 0.014481344260275364, "loss_total": 0.014481344260275364, "step": 39120 }, { "grad_norm": 0.26178643107414246, "learning_rate": 7.139512919991176e-05, "loss": 0.013, "step": 39130 }, { "loss_action": 0.01700771227478981, "loss_total": 0.01700771227478981, "step": 39130 }, { "grad_norm": 0.331506609916687, "learning_rate": 7.138018355904014e-05, "loss": 0.0145, "step": 39140 }, { "loss_action": 0.01671227253973484, "loss_total": 0.01671227253973484, "step": 39140 }, { "grad_norm": 0.2230675369501114, "learning_rate": 7.13652355800638e-05, "loss": 0.0128, "step": 39150 }, { "loss_action": 0.012118291109800339, "loss_total": 0.012118291109800339, "step": 39150 }, { "grad_norm": 0.27496156096458435, "learning_rate": 7.135028526461743e-05, "loss": 0.0127, "step": 39160 }, { "loss_action": 0.008571094833314419, "loss_total": 0.008571094833314419, "step": 39160 }, { "grad_norm": 0.2605089545249939, "learning_rate": 7.133533261433594e-05, "loss": 0.0125, "step": 39170 }, { "loss_action": 0.017437336966395378, "loss_total": 0.017437336966395378, "step": 39170 }, { "grad_norm": 0.27126163244247437, "learning_rate": 7.132037763085457e-05, "loss": 0.013, "step": 39180 }, { "loss_action": 0.01808549463748932, "loss_total": 0.01808549463748932, "step": 39180 }, { "grad_norm": 0.30703648924827576, "learning_rate": 7.130542031580875e-05, "loss": 0.0139, "step": 39190 }, { "loss_action": 0.013514646328985691, "loss_total": 0.013514646328985691, "step": 39190 }, { "grad_norm": 0.35903626680374146, "learning_rate": 7.12904606708342e-05, "loss": 0.0162, "step": 39200 }, { "loss_action": 0.011495804414153099, "loss_total": 0.011495804414153099, "step": 39200 }, { "grad_norm": 0.29757243394851685, "learning_rate": 7.127549869756687e-05, "loss": 0.0131, "step": 39210 }, { "loss_action": 0.010982964187860489, "loss_total": 0.010982964187860489, "step": 39210 }, { "grad_norm": 0.34944015741348267, "learning_rate": 7.126053439764299e-05, "loss": 0.0122, "step": 39220 }, { "loss_action": 0.01482896227389574, "loss_total": 0.01482896227389574, "step": 39220 }, { "grad_norm": 0.3171347677707672, "learning_rate": 7.124556777269904e-05, "loss": 0.0123, "step": 39230 }, { "loss_action": 0.009971718303859234, "loss_total": 0.009971718303859234, "step": 39230 }, { "grad_norm": 0.25815480947494507, "learning_rate": 7.123059882437174e-05, "loss": 0.0114, "step": 39240 }, { "loss_action": 0.012373208999633789, "loss_total": 0.012373208999633789, "step": 39240 }, { "grad_norm": 0.28266677260398865, "learning_rate": 7.121562755429807e-05, "loss": 0.0129, "step": 39250 }, { "loss_action": 0.01154405903071165, "loss_total": 0.01154405903071165, "step": 39250 }, { "grad_norm": 0.27321121096611023, "learning_rate": 7.120065396411528e-05, "loss": 0.0109, "step": 39260 }, { "loss_action": 0.015009583905339241, "loss_total": 0.015009583905339241, "step": 39260 }, { "grad_norm": 0.30323952436447144, "learning_rate": 7.118567805546084e-05, "loss": 0.0143, "step": 39270 }, { "loss_action": 0.014403052628040314, "loss_total": 0.014403052628040314, "step": 39270 }, { "grad_norm": 0.34245893359184265, "learning_rate": 7.117069982997248e-05, "loss": 0.0124, "step": 39280 }, { "loss_action": 0.016977917402982712, "loss_total": 0.016977917402982712, "step": 39280 }, { "grad_norm": 0.32494932413101196, "learning_rate": 7.115571928928825e-05, "loss": 0.014, "step": 39290 }, { "loss_action": 0.014823315665125847, "loss_total": 0.014823315665125847, "step": 39290 }, { "grad_norm": 0.2779795229434967, "learning_rate": 7.114073643504635e-05, "loss": 0.0147, "step": 39300 }, { "loss_action": 0.0132485032081604, "loss_total": 0.0132485032081604, "step": 39300 }, { "grad_norm": 0.24919116497039795, "learning_rate": 7.11257512688853e-05, "loss": 0.0123, "step": 39310 }, { "loss_action": 0.012531335465610027, "loss_total": 0.012531335465610027, "step": 39310 }, { "grad_norm": 0.28397828340530396, "learning_rate": 7.111076379244384e-05, "loss": 0.0123, "step": 39320 }, { "loss_action": 0.018465949222445488, "loss_total": 0.018465949222445488, "step": 39320 }, { "grad_norm": 0.39339667558670044, "learning_rate": 7.109577400736101e-05, "loss": 0.0134, "step": 39330 }, { "loss_action": 0.012482642196118832, "loss_total": 0.012482642196118832, "step": 39330 }, { "grad_norm": 0.35483676195144653, "learning_rate": 7.108078191527605e-05, "loss": 0.0161, "step": 39340 }, { "loss_action": 0.017398038879036903, "loss_total": 0.017398038879036903, "step": 39340 }, { "grad_norm": 0.3773214817047119, "learning_rate": 7.106578751782847e-05, "loss": 0.0155, "step": 39350 }, { "loss_action": 0.015208425000309944, "loss_total": 0.015208425000309944, "step": 39350 }, { "grad_norm": 0.28323128819465637, "learning_rate": 7.105079081665803e-05, "loss": 0.0135, "step": 39360 }, { "loss_action": 0.013093390502035618, "loss_total": 0.013093390502035618, "step": 39360 }, { "grad_norm": 0.28837111592292786, "learning_rate": 7.103579181340476e-05, "loss": 0.013, "step": 39370 }, { "loss_action": 0.015551128424704075, "loss_total": 0.015551128424704075, "step": 39370 }, { "grad_norm": 0.2713701128959656, "learning_rate": 7.102079050970893e-05, "loss": 0.0128, "step": 39380 }, { "loss_action": 0.011753994040191174, "loss_total": 0.011753994040191174, "step": 39380 }, { "grad_norm": 0.36227089166641235, "learning_rate": 7.100578690721105e-05, "loss": 0.0123, "step": 39390 }, { "loss_action": 0.014497973024845123, "loss_total": 0.014497973024845123, "step": 39390 }, { "grad_norm": 0.2627381682395935, "learning_rate": 7.09907810075519e-05, "loss": 0.0132, "step": 39400 }, { "loss_action": 0.018625793978571892, "loss_total": 0.018625793978571892, "step": 39400 }, { "grad_norm": 0.2838788330554962, "learning_rate": 7.097577281237249e-05, "loss": 0.0146, "step": 39410 }, { "loss_action": 0.014787925407290459, "loss_total": 0.014787925407290459, "step": 39410 }, { "grad_norm": 0.3690269887447357, "learning_rate": 7.09607623233141e-05, "loss": 0.0125, "step": 39420 }, { "loss_action": 0.01784372329711914, "loss_total": 0.01784372329711914, "step": 39420 }, { "grad_norm": 0.3034263849258423, "learning_rate": 7.094574954201827e-05, "loss": 0.0143, "step": 39430 }, { "loss_action": 0.01599692925810814, "loss_total": 0.01599692925810814, "step": 39430 }, { "grad_norm": 0.31998366117477417, "learning_rate": 7.093073447012675e-05, "loss": 0.0127, "step": 39440 }, { "loss_action": 0.014986837282776833, "loss_total": 0.014986837282776833, "step": 39440 }, { "grad_norm": 0.3356594741344452, "learning_rate": 7.09157171092816e-05, "loss": 0.0134, "step": 39450 }, { "loss_action": 0.01256859116256237, "loss_total": 0.01256859116256237, "step": 39450 }, { "grad_norm": 0.33246731758117676, "learning_rate": 7.090069746112504e-05, "loss": 0.0118, "step": 39460 }, { "loss_action": 0.015521872788667679, "loss_total": 0.015521872788667679, "step": 39460 }, { "grad_norm": 0.26272058486938477, "learning_rate": 7.088567552729965e-05, "loss": 0.0124, "step": 39470 }, { "loss_action": 0.012819645926356316, "loss_total": 0.012819645926356316, "step": 39470 }, { "grad_norm": 0.31765273213386536, "learning_rate": 7.087065130944818e-05, "loss": 0.0132, "step": 39480 }, { "loss_action": 0.01063182856887579, "loss_total": 0.01063182856887579, "step": 39480 }, { "grad_norm": 0.304434210062027, "learning_rate": 7.085562480921366e-05, "loss": 0.0125, "step": 39490 }, { "loss_action": 0.01391383446753025, "loss_total": 0.01391383446753025, "step": 39490 }, { "grad_norm": 0.28409817814826965, "learning_rate": 7.084059602823937e-05, "loss": 0.0133, "step": 39500 }, { "loss_action": 0.012219748459756374, "loss_total": 0.012219748459756374, "step": 39500 }, { "grad_norm": 0.2939416766166687, "learning_rate": 7.082556496816882e-05, "loss": 0.0127, "step": 39510 }, { "loss_action": 0.008295980282127857, "loss_total": 0.008295980282127857, "step": 39510 }, { "grad_norm": 0.2862371802330017, "learning_rate": 7.081053163064582e-05, "loss": 0.0123, "step": 39520 }, { "loss_action": 0.009898899123072624, "loss_total": 0.009898899123072624, "step": 39520 }, { "grad_norm": 0.33392420411109924, "learning_rate": 7.079549601731434e-05, "loss": 0.0126, "step": 39530 }, { "loss_action": 0.01236124150454998, "loss_total": 0.01236124150454998, "step": 39530 }, { "grad_norm": 0.27930790185928345, "learning_rate": 7.07804581298187e-05, "loss": 0.0129, "step": 39540 }, { "loss_action": 0.013561027124524117, "loss_total": 0.013561027124524117, "step": 39540 }, { "grad_norm": 0.33806145191192627, "learning_rate": 7.07654179698034e-05, "loss": 0.0131, "step": 39550 }, { "loss_action": 0.014718206599354744, "loss_total": 0.014718206599354744, "step": 39550 }, { "grad_norm": 0.2613086700439453, "learning_rate": 7.075037553891321e-05, "loss": 0.0129, "step": 39560 }, { "loss_action": 0.014147631824016571, "loss_total": 0.014147631824016571, "step": 39560 }, { "grad_norm": 0.2292620986700058, "learning_rate": 7.073533083879315e-05, "loss": 0.0141, "step": 39570 }, { "loss_action": 0.018431739881634712, "loss_total": 0.018431739881634712, "step": 39570 }, { "grad_norm": 0.37648314237594604, "learning_rate": 7.072028387108849e-05, "loss": 0.0128, "step": 39580 }, { "loss_action": 0.013886907137930393, "loss_total": 0.013886907137930393, "step": 39580 }, { "grad_norm": 0.3009307384490967, "learning_rate": 7.070523463744472e-05, "loss": 0.0132, "step": 39590 }, { "loss_action": 0.013516010716557503, "loss_total": 0.013516010716557503, "step": 39590 }, { "grad_norm": 0.3096790909767151, "learning_rate": 7.069018313950763e-05, "loss": 0.0128, "step": 39600 }, { "loss_action": 0.011468185111880302, "loss_total": 0.011468185111880302, "step": 39600 }, { "grad_norm": 0.32435908913612366, "learning_rate": 7.067512937892322e-05, "loss": 0.013, "step": 39610 }, { "loss_action": 0.010846908204257488, "loss_total": 0.010846908204257488, "step": 39610 }, { "grad_norm": 0.24271811544895172, "learning_rate": 7.066007335733775e-05, "loss": 0.0113, "step": 39620 }, { "loss_action": 0.015056484378874302, "loss_total": 0.015056484378874302, "step": 39620 }, { "grad_norm": 0.3442504107952118, "learning_rate": 7.064501507639772e-05, "loss": 0.0125, "step": 39630 }, { "loss_action": 0.011477697640657425, "loss_total": 0.011477697640657425, "step": 39630 }, { "grad_norm": 0.3122940957546234, "learning_rate": 7.062995453774987e-05, "loss": 0.0117, "step": 39640 }, { "loss_action": 0.011832509189844131, "loss_total": 0.011832509189844131, "step": 39640 }, { "grad_norm": 0.31587767601013184, "learning_rate": 7.061489174304121e-05, "loss": 0.013, "step": 39650 }, { "loss_action": 0.013509713113307953, "loss_total": 0.013509713113307953, "step": 39650 }, { "grad_norm": 0.2710312306880951, "learning_rate": 7.0599826693919e-05, "loss": 0.0129, "step": 39660 }, { "loss_action": 0.00955138448625803, "loss_total": 0.00955138448625803, "step": 39660 }, { "grad_norm": 0.33288443088531494, "learning_rate": 7.05847593920307e-05, "loss": 0.0134, "step": 39670 }, { "loss_action": 0.019075708463788033, "loss_total": 0.019075708463788033, "step": 39670 }, { "grad_norm": 0.3121553957462311, "learning_rate": 7.056968983902406e-05, "loss": 0.0138, "step": 39680 }, { "loss_action": 0.01904284954071045, "loss_total": 0.01904284954071045, "step": 39680 }, { "grad_norm": 0.3078290522098541, "learning_rate": 7.055461803654706e-05, "loss": 0.0155, "step": 39690 }, { "loss_action": 0.012341328896582127, "loss_total": 0.012341328896582127, "step": 39690 }, { "grad_norm": 0.3182685375213623, "learning_rate": 7.053954398624794e-05, "loss": 0.0125, "step": 39700 }, { "loss_action": 0.014601601287722588, "loss_total": 0.014601601287722588, "step": 39700 }, { "grad_norm": 0.29268816113471985, "learning_rate": 7.052446768977518e-05, "loss": 0.0128, "step": 39710 }, { "loss_action": 0.01392384059727192, "loss_total": 0.01392384059727192, "step": 39710 }, { "grad_norm": 0.29380351305007935, "learning_rate": 7.050938914877748e-05, "loss": 0.012, "step": 39720 }, { "loss_action": 0.015126938931643963, "loss_total": 0.015126938931643963, "step": 39720 }, { "grad_norm": 0.2399510145187378, "learning_rate": 7.049430836490382e-05, "loss": 0.0123, "step": 39730 }, { "loss_action": 0.011318773031234741, "loss_total": 0.011318773031234741, "step": 39730 }, { "grad_norm": 0.2573334872722626, "learning_rate": 7.047922533980342e-05, "loss": 0.0117, "step": 39740 }, { "loss_action": 0.01610264740884304, "loss_total": 0.01610264740884304, "step": 39740 }, { "grad_norm": 0.3155372440814972, "learning_rate": 7.046414007512571e-05, "loss": 0.015, "step": 39750 }, { "loss_action": 0.016074243932962418, "loss_total": 0.016074243932962418, "step": 39750 }, { "grad_norm": 0.38255438208580017, "learning_rate": 7.044905257252042e-05, "loss": 0.0126, "step": 39760 }, { "loss_action": 0.011656282469630241, "loss_total": 0.011656282469630241, "step": 39760 }, { "grad_norm": 0.2508688271045685, "learning_rate": 7.04339628336375e-05, "loss": 0.0145, "step": 39770 }, { "loss_action": 0.018555834889411926, "loss_total": 0.018555834889411926, "step": 39770 }, { "grad_norm": 0.2588229775428772, "learning_rate": 7.041887086012711e-05, "loss": 0.015, "step": 39780 }, { "loss_action": 0.016859140247106552, "loss_total": 0.016859140247106552, "step": 39780 }, { "grad_norm": 0.3914341330528259, "learning_rate": 7.040377665363969e-05, "loss": 0.0134, "step": 39790 }, { "loss_action": 0.012852792628109455, "loss_total": 0.012852792628109455, "step": 39790 }, { "grad_norm": 0.40349826216697693, "learning_rate": 7.038868021582594e-05, "loss": 0.0146, "step": 39800 }, { "loss_action": 0.012677205726504326, "loss_total": 0.012677205726504326, "step": 39800 }, { "grad_norm": 0.2822418510913849, "learning_rate": 7.037358154833679e-05, "loss": 0.013, "step": 39810 }, { "loss_action": 0.011650031432509422, "loss_total": 0.011650031432509422, "step": 39810 }, { "grad_norm": 0.40557166934013367, "learning_rate": 7.035848065282339e-05, "loss": 0.0136, "step": 39820 }, { "loss_action": 0.011508037336170673, "loss_total": 0.011508037336170673, "step": 39820 }, { "grad_norm": 0.23292292654514313, "learning_rate": 7.034337753093714e-05, "loss": 0.0134, "step": 39830 }, { "loss_action": 0.010300520807504654, "loss_total": 0.010300520807504654, "step": 39830 }, { "grad_norm": 0.31385257840156555, "learning_rate": 7.032827218432972e-05, "loss": 0.0126, "step": 39840 }, { "loss_action": 0.019910873845219612, "loss_total": 0.019910873845219612, "step": 39840 }, { "grad_norm": 0.40088120102882385, "learning_rate": 7.031316461465302e-05, "loss": 0.0143, "step": 39850 }, { "loss_action": 0.011300737969577312, "loss_total": 0.011300737969577312, "step": 39850 }, { "grad_norm": 0.2700352966785431, "learning_rate": 7.029805482355915e-05, "loss": 0.0126, "step": 39860 }, { "loss_action": 0.013927774503827095, "loss_total": 0.013927774503827095, "step": 39860 }, { "grad_norm": 0.2443324774503708, "learning_rate": 7.028294281270055e-05, "loss": 0.0128, "step": 39870 }, { "loss_action": 0.010886604897677898, "loss_total": 0.010886604897677898, "step": 39870 }, { "grad_norm": 0.33594608306884766, "learning_rate": 7.026782858372982e-05, "loss": 0.0112, "step": 39880 }, { "loss_action": 0.010934717021882534, "loss_total": 0.010934717021882534, "step": 39880 }, { "grad_norm": 0.31858116388320923, "learning_rate": 7.025271213829982e-05, "loss": 0.0118, "step": 39890 }, { "loss_action": 0.010621903464198112, "loss_total": 0.010621903464198112, "step": 39890 }, { "grad_norm": 0.34531983733177185, "learning_rate": 7.023759347806366e-05, "loss": 0.0126, "step": 39900 }, { "loss_action": 0.02294091135263443, "loss_total": 0.02294091135263443, "step": 39900 }, { "grad_norm": 0.28740692138671875, "learning_rate": 7.022247260467472e-05, "loss": 0.0133, "step": 39910 }, { "loss_action": 0.010948609560728073, "loss_total": 0.010948609560728073, "step": 39910 }, { "grad_norm": 0.3186231851577759, "learning_rate": 7.020734951978658e-05, "loss": 0.0127, "step": 39920 }, { "loss_action": 0.019740207120776176, "loss_total": 0.019740207120776176, "step": 39920 }, { "grad_norm": 0.2715027332305908, "learning_rate": 7.019222422505307e-05, "loss": 0.0163, "step": 39930 }, { "loss_action": 0.011151165701448917, "loss_total": 0.011151165701448917, "step": 39930 }, { "grad_norm": 0.32957595586776733, "learning_rate": 7.017709672212827e-05, "loss": 0.0149, "step": 39940 }, { "loss_action": 0.01153346337378025, "loss_total": 0.01153346337378025, "step": 39940 }, { "grad_norm": 0.25317031145095825, "learning_rate": 7.016196701266652e-05, "loss": 0.0146, "step": 39950 }, { "loss_action": 0.015898140147328377, "loss_total": 0.015898140147328377, "step": 39950 }, { "grad_norm": 0.34660804271698, "learning_rate": 7.014683509832238e-05, "loss": 0.0135, "step": 39960 }, { "loss_action": 0.012331556528806686, "loss_total": 0.012331556528806686, "step": 39960 }, { "grad_norm": 0.4860309064388275, "learning_rate": 7.013170098075063e-05, "loss": 0.0136, "step": 39970 }, { "loss_action": 0.014733272604644299, "loss_total": 0.014733272604644299, "step": 39970 }, { "grad_norm": 0.2913222312927246, "learning_rate": 7.011656466160632e-05, "loss": 0.0129, "step": 39980 }, { "loss_action": 0.016604792326688766, "loss_total": 0.016604792326688766, "step": 39980 }, { "grad_norm": 0.24186858534812927, "learning_rate": 7.010142614254475e-05, "loss": 0.0135, "step": 39990 }, { "loss_action": 0.016254780814051628, "loss_total": 0.016254780814051628, "step": 39990 }, { "grad_norm": 0.25861239433288574, "learning_rate": 7.008628542522147e-05, "loss": 0.0118, "step": 40000 }, { "loss_action": 0.01092568039894104, "loss_total": 0.01092568039894104, "step": 40000 }, { "grad_norm": 0.41683387756347656, "learning_rate": 7.007114251129218e-05, "loss": 0.0136, "step": 40010 }, { "loss_action": 0.015671147033572197, "loss_total": 0.015671147033572197, "step": 40010 }, { "grad_norm": 0.2553865611553192, "learning_rate": 7.005599740241293e-05, "loss": 0.0127, "step": 40020 }, { "loss_action": 0.01613013818860054, "loss_total": 0.01613013818860054, "step": 40020 }, { "grad_norm": 0.32714173197746277, "learning_rate": 7.004085010023996e-05, "loss": 0.0131, "step": 40030 }, { "loss_action": 0.012769968248903751, "loss_total": 0.012769968248903751, "step": 40030 }, { "grad_norm": 0.2968757152557373, "learning_rate": 7.002570060642976e-05, "loss": 0.0125, "step": 40040 }, { "loss_action": 0.015646057203412056, "loss_total": 0.015646057203412056, "step": 40040 }, { "grad_norm": 0.3427012860774994, "learning_rate": 7.001054892263903e-05, "loss": 0.0139, "step": 40050 }, { "loss_action": 0.012584781274199486, "loss_total": 0.012584781274199486, "step": 40050 }, { "grad_norm": 0.31081005930900574, "learning_rate": 6.999539505052477e-05, "loss": 0.0128, "step": 40060 }, { "loss_action": 0.013242151588201523, "loss_total": 0.013242151588201523, "step": 40060 }, { "grad_norm": 0.2823636829853058, "learning_rate": 6.998023899174418e-05, "loss": 0.0142, "step": 40070 }, { "loss_action": 0.016758255660533905, "loss_total": 0.016758255660533905, "step": 40070 }, { "grad_norm": 0.2763434946537018, "learning_rate": 6.996508074795467e-05, "loss": 0.0133, "step": 40080 }, { "loss_action": 0.011300209909677505, "loss_total": 0.011300209909677505, "step": 40080 }, { "grad_norm": 0.2570817172527313, "learning_rate": 6.994992032081396e-05, "loss": 0.0118, "step": 40090 }, { "loss_action": 0.01496193464845419, "loss_total": 0.01496193464845419, "step": 40090 }, { "grad_norm": 0.2611558735370636, "learning_rate": 6.993475771197995e-05, "loss": 0.0122, "step": 40100 }, { "loss_action": 0.012429586611688137, "loss_total": 0.012429586611688137, "step": 40100 }, { "grad_norm": 0.3748566210269928, "learning_rate": 6.991959292311082e-05, "loss": 0.0127, "step": 40110 }, { "loss_action": 0.012157336808741093, "loss_total": 0.012157336808741093, "step": 40110 }, { "grad_norm": 0.25055748224258423, "learning_rate": 6.990442595586495e-05, "loss": 0.0118, "step": 40120 }, { "loss_action": 0.015137500129640102, "loss_total": 0.015137500129640102, "step": 40120 }, { "grad_norm": 0.3253094553947449, "learning_rate": 6.988925681190098e-05, "loss": 0.0122, "step": 40130 }, { "loss_action": 0.013097950257360935, "loss_total": 0.013097950257360935, "step": 40130 }, { "grad_norm": 0.24583563208580017, "learning_rate": 6.987408549287778e-05, "loss": 0.012, "step": 40140 }, { "loss_action": 0.017017055302858353, "loss_total": 0.017017055302858353, "step": 40140 }, { "grad_norm": 0.28307363390922546, "learning_rate": 6.985891200045449e-05, "loss": 0.0125, "step": 40150 }, { "loss_action": 0.009229396469891071, "loss_total": 0.009229396469891071, "step": 40150 }, { "grad_norm": 0.257234126329422, "learning_rate": 6.984373633629045e-05, "loss": 0.0118, "step": 40160 }, { "loss_action": 0.013759555295109749, "loss_total": 0.013759555295109749, "step": 40160 }, { "grad_norm": 0.18055075407028198, "learning_rate": 6.98285585020452e-05, "loss": 0.0124, "step": 40170 }, { "loss_action": 0.013996846042573452, "loss_total": 0.013996846042573452, "step": 40170 }, { "grad_norm": 0.25416475534439087, "learning_rate": 6.981337849937864e-05, "loss": 0.0114, "step": 40180 }, { "loss_action": 0.011185995303094387, "loss_total": 0.011185995303094387, "step": 40180 }, { "grad_norm": 0.3258642852306366, "learning_rate": 6.979819632995078e-05, "loss": 0.0131, "step": 40190 }, { "loss_action": 0.011900113895535469, "loss_total": 0.011900113895535469, "step": 40190 }, { "grad_norm": 0.3453253209590912, "learning_rate": 6.978301199542193e-05, "loss": 0.0134, "step": 40200 }, { "loss_action": 0.012637430801987648, "loss_total": 0.012637430801987648, "step": 40200 }, { "grad_norm": 0.26851075887680054, "learning_rate": 6.976782549745263e-05, "loss": 0.0119, "step": 40210 }, { "loss_action": 0.014048360288143158, "loss_total": 0.014048360288143158, "step": 40210 }, { "grad_norm": 0.39300215244293213, "learning_rate": 6.975263683770367e-05, "loss": 0.0133, "step": 40220 }, { "loss_action": 0.01253108587116003, "loss_total": 0.01253108587116003, "step": 40220 }, { "grad_norm": 0.251929372549057, "learning_rate": 6.973744601783604e-05, "loss": 0.0132, "step": 40230 }, { "loss_action": 0.014624017290771008, "loss_total": 0.014624017290771008, "step": 40230 }, { "grad_norm": 0.30981603264808655, "learning_rate": 6.972225303951097e-05, "loss": 0.0127, "step": 40240 }, { "loss_action": 0.014574757777154446, "loss_total": 0.014574757777154446, "step": 40240 }, { "grad_norm": 0.2527886927127838, "learning_rate": 6.970705790438998e-05, "loss": 0.0119, "step": 40250 }, { "loss_action": 0.011790708638727665, "loss_total": 0.011790708638727665, "step": 40250 }, { "grad_norm": 0.2967953681945801, "learning_rate": 6.969186061413477e-05, "loss": 0.0129, "step": 40260 }, { "loss_action": 0.009591096080839634, "loss_total": 0.009591096080839634, "step": 40260 }, { "grad_norm": 0.2782667279243469, "learning_rate": 6.967666117040727e-05, "loss": 0.0119, "step": 40270 }, { "loss_action": 0.012461713515222073, "loss_total": 0.012461713515222073, "step": 40270 }, { "grad_norm": 0.26443254947662354, "learning_rate": 6.966145957486972e-05, "loss": 0.0116, "step": 40280 }, { "loss_action": 0.012807230465114117, "loss_total": 0.012807230465114117, "step": 40280 }, { "grad_norm": 0.25581657886505127, "learning_rate": 6.964625582918449e-05, "loss": 0.0119, "step": 40290 }, { "loss_action": 0.011005555279552937, "loss_total": 0.011005555279552937, "step": 40290 }, { "grad_norm": 0.3944166898727417, "learning_rate": 6.963104993501425e-05, "loss": 0.0145, "step": 40300 }, { "loss_action": 0.01324010081589222, "loss_total": 0.01324010081589222, "step": 40300 }, { "grad_norm": 0.20436151325702667, "learning_rate": 6.961584189402192e-05, "loss": 0.0126, "step": 40310 }, { "loss_action": 0.014825690537691116, "loss_total": 0.014825690537691116, "step": 40310 }, { "grad_norm": 0.29200682044029236, "learning_rate": 6.96006317078706e-05, "loss": 0.0129, "step": 40320 }, { "loss_action": 0.014211082831025124, "loss_total": 0.014211082831025124, "step": 40320 }, { "grad_norm": 0.2511415183544159, "learning_rate": 6.958541937822367e-05, "loss": 0.0124, "step": 40330 }, { "loss_action": 0.012608368881046772, "loss_total": 0.012608368881046772, "step": 40330 }, { "grad_norm": 0.2838500738143921, "learning_rate": 6.957020490674473e-05, "loss": 0.0109, "step": 40340 }, { "loss_action": 0.013653726316988468, "loss_total": 0.013653726316988468, "step": 40340 }, { "grad_norm": 0.2514738440513611, "learning_rate": 6.95549882950976e-05, "loss": 0.0108, "step": 40350 }, { "loss_action": 0.01782206818461418, "loss_total": 0.01782206818461418, "step": 40350 }, { "grad_norm": 0.24406766891479492, "learning_rate": 6.953976954494635e-05, "loss": 0.0124, "step": 40360 }, { "loss_action": 0.0111948661506176, "loss_total": 0.0111948661506176, "step": 40360 }, { "grad_norm": 0.2930130660533905, "learning_rate": 6.952454865795528e-05, "loss": 0.0111, "step": 40370 }, { "loss_action": 0.011233369819819927, "loss_total": 0.011233369819819927, "step": 40370 }, { "grad_norm": 0.28741735219955444, "learning_rate": 6.950932563578892e-05, "loss": 0.0117, "step": 40380 }, { "loss_action": 0.010225280188024044, "loss_total": 0.010225280188024044, "step": 40380 }, { "grad_norm": 0.21525725722312927, "learning_rate": 6.949410048011206e-05, "loss": 0.0124, "step": 40390 }, { "loss_action": 0.012571257539093494, "loss_total": 0.012571257539093494, "step": 40390 }, { "grad_norm": 0.2019806206226349, "learning_rate": 6.947887319258966e-05, "loss": 0.0124, "step": 40400 }, { "loss_action": 0.021412834525108337, "loss_total": 0.021412834525108337, "step": 40400 }, { "grad_norm": 0.2642798125743866, "learning_rate": 6.946364377488696e-05, "loss": 0.0142, "step": 40410 }, { "loss_action": 0.015397886745631695, "loss_total": 0.015397886745631695, "step": 40410 }, { "grad_norm": 0.3556371331214905, "learning_rate": 6.944841222866947e-05, "loss": 0.0137, "step": 40420 }, { "loss_action": 0.012579413130879402, "loss_total": 0.012579413130879402, "step": 40420 }, { "grad_norm": 0.3243905007839203, "learning_rate": 6.943317855560284e-05, "loss": 0.0136, "step": 40430 }, { "loss_action": 0.016252154484391212, "loss_total": 0.016252154484391212, "step": 40430 }, { "grad_norm": 0.29336977005004883, "learning_rate": 6.941794275735302e-05, "loss": 0.0135, "step": 40440 }, { "loss_action": 0.01110861450433731, "loss_total": 0.01110861450433731, "step": 40440 }, { "grad_norm": 0.2866290807723999, "learning_rate": 6.94027048355862e-05, "loss": 0.0138, "step": 40450 }, { "loss_action": 0.011481497436761856, "loss_total": 0.011481497436761856, "step": 40450 }, { "grad_norm": 0.32879820466041565, "learning_rate": 6.938746479196871e-05, "loss": 0.013, "step": 40460 }, { "loss_action": 0.014576137065887451, "loss_total": 0.014576137065887451, "step": 40460 }, { "grad_norm": 0.27352380752563477, "learning_rate": 6.937222262816724e-05, "loss": 0.0129, "step": 40470 }, { "loss_action": 0.011012307368218899, "loss_total": 0.011012307368218899, "step": 40470 }, { "grad_norm": 0.2666095793247223, "learning_rate": 6.935697834584865e-05, "loss": 0.0119, "step": 40480 }, { "loss_action": 0.011462923139333725, "loss_total": 0.011462923139333725, "step": 40480 }, { "grad_norm": 0.2837896943092346, "learning_rate": 6.934173194667998e-05, "loss": 0.012, "step": 40490 }, { "loss_action": 0.013644738122820854, "loss_total": 0.013644738122820854, "step": 40490 }, { "grad_norm": 0.25750190019607544, "learning_rate": 6.93264834323286e-05, "loss": 0.0137, "step": 40500 }, { "loss_action": 0.011715115047991276, "loss_total": 0.011715115047991276, "step": 40500 }, { "grad_norm": 0.3205169141292572, "learning_rate": 6.931123280446206e-05, "loss": 0.0133, "step": 40510 }, { "loss_action": 0.011018633842468262, "loss_total": 0.011018633842468262, "step": 40510 }, { "grad_norm": 0.32622578740119934, "learning_rate": 6.929598006474811e-05, "loss": 0.0143, "step": 40520 }, { "loss_action": 0.012409825809299946, "loss_total": 0.012409825809299946, "step": 40520 }, { "grad_norm": 0.3499331474304199, "learning_rate": 6.92807252148548e-05, "loss": 0.015, "step": 40530 }, { "loss_action": 0.011334097012877464, "loss_total": 0.011334097012877464, "step": 40530 }, { "grad_norm": 0.25201141834259033, "learning_rate": 6.926546825645037e-05, "loss": 0.0125, "step": 40540 }, { "loss_action": 0.01902088150382042, "loss_total": 0.01902088150382042, "step": 40540 }, { "grad_norm": 0.28480082750320435, "learning_rate": 6.92502091912033e-05, "loss": 0.0131, "step": 40550 }, { "loss_action": 0.013003221713006496, "loss_total": 0.013003221713006496, "step": 40550 }, { "grad_norm": 0.5471484661102295, "learning_rate": 6.923494802078229e-05, "loss": 0.0131, "step": 40560 }, { "loss_action": 0.00992478709667921, "loss_total": 0.00992478709667921, "step": 40560 }, { "grad_norm": 0.29985690116882324, "learning_rate": 6.921968474685628e-05, "loss": 0.0134, "step": 40570 }, { "loss_action": 0.02194058895111084, "loss_total": 0.02194058895111084, "step": 40570 }, { "grad_norm": 0.3467285931110382, "learning_rate": 6.920441937109445e-05, "loss": 0.0152, "step": 40580 }, { "loss_action": 0.012249516323208809, "loss_total": 0.012249516323208809, "step": 40580 }, { "grad_norm": 0.41219642758369446, "learning_rate": 6.91891518951662e-05, "loss": 0.0138, "step": 40590 }, { "loss_action": 0.011714203283190727, "loss_total": 0.011714203283190727, "step": 40590 }, { "grad_norm": 0.29393547773361206, "learning_rate": 6.917388232074114e-05, "loss": 0.0126, "step": 40600 }, { "loss_action": 0.012566301971673965, "loss_total": 0.012566301971673965, "step": 40600 }, { "grad_norm": 0.3338702321052551, "learning_rate": 6.915861064948914e-05, "loss": 0.0124, "step": 40610 }, { "loss_action": 0.013018704950809479, "loss_total": 0.013018704950809479, "step": 40610 }, { "grad_norm": 0.32906991243362427, "learning_rate": 6.914333688308025e-05, "loss": 0.0134, "step": 40620 }, { "loss_action": 0.01582842692732811, "loss_total": 0.01582842692732811, "step": 40620 }, { "grad_norm": 0.2349664568901062, "learning_rate": 6.912806102318487e-05, "loss": 0.0137, "step": 40630 }, { "loss_action": 0.014026977121829987, "loss_total": 0.014026977121829987, "step": 40630 }, { "grad_norm": 0.2633286416530609, "learning_rate": 6.911278307147347e-05, "loss": 0.0133, "step": 40640 }, { "loss_action": 0.01061840821057558, "loss_total": 0.01061840821057558, "step": 40640 }, { "grad_norm": 0.23390136659145355, "learning_rate": 6.909750302961684e-05, "loss": 0.0124, "step": 40650 }, { "loss_action": 0.011848078109323978, "loss_total": 0.011848078109323978, "step": 40650 }, { "grad_norm": 0.3164505064487457, "learning_rate": 6.9082220899286e-05, "loss": 0.0129, "step": 40660 }, { "loss_action": 0.01171102374792099, "loss_total": 0.01171102374792099, "step": 40660 }, { "grad_norm": 0.4210606813430786, "learning_rate": 6.906693668215219e-05, "loss": 0.0141, "step": 40670 }, { "loss_action": 0.01105551328510046, "loss_total": 0.01105551328510046, "step": 40670 }, { "grad_norm": 0.34959936141967773, "learning_rate": 6.905165037988683e-05, "loss": 0.0124, "step": 40680 }, { "loss_action": 0.010534608736634254, "loss_total": 0.010534608736634254, "step": 40680 }, { "grad_norm": 0.28620606660842896, "learning_rate": 6.903636199416164e-05, "loss": 0.0129, "step": 40690 }, { "loss_action": 0.02640446275472641, "loss_total": 0.02640446275472641, "step": 40690 }, { "grad_norm": 0.30308011174201965, "learning_rate": 6.902107152664851e-05, "loss": 0.0152, "step": 40700 }, { "loss_action": 0.013149111531674862, "loss_total": 0.013149111531674862, "step": 40700 }, { "grad_norm": 0.4078644812107086, "learning_rate": 6.90057789790196e-05, "loss": 0.0134, "step": 40710 }, { "loss_action": 0.011299367994070053, "loss_total": 0.011299367994070053, "step": 40710 }, { "grad_norm": 0.3772096633911133, "learning_rate": 6.899048435294728e-05, "loss": 0.0131, "step": 40720 }, { "loss_action": 0.01467212475836277, "loss_total": 0.01467212475836277, "step": 40720 }, { "grad_norm": 0.23154251277446747, "learning_rate": 6.897518765010415e-05, "loss": 0.0133, "step": 40730 }, { "loss_action": 0.01348691713064909, "loss_total": 0.01348691713064909, "step": 40730 }, { "grad_norm": 0.2722751498222351, "learning_rate": 6.895988887216302e-05, "loss": 0.0131, "step": 40740 }, { "loss_action": 0.011654705740511417, "loss_total": 0.011654705740511417, "step": 40740 }, { "grad_norm": 0.2686956822872162, "learning_rate": 6.894458802079694e-05, "loss": 0.0127, "step": 40750 }, { "loss_action": 0.01566399820148945, "loss_total": 0.01566399820148945, "step": 40750 }, { "grad_norm": 0.3179064691066742, "learning_rate": 6.892928509767922e-05, "loss": 0.0121, "step": 40760 }, { "loss_action": 0.009647767059504986, "loss_total": 0.009647767059504986, "step": 40760 }, { "grad_norm": 0.3483303487300873, "learning_rate": 6.891398010448333e-05, "loss": 0.0112, "step": 40770 }, { "loss_action": 0.011335025541484356, "loss_total": 0.011335025541484356, "step": 40770 }, { "grad_norm": 0.3311994671821594, "learning_rate": 6.8898673042883e-05, "loss": 0.0131, "step": 40780 }, { "loss_action": 0.011802677996456623, "loss_total": 0.011802677996456623, "step": 40780 }, { "grad_norm": 0.2335129678249359, "learning_rate": 6.888336391455222e-05, "loss": 0.0134, "step": 40790 }, { "loss_action": 0.018529042601585388, "loss_total": 0.018529042601585388, "step": 40790 }, { "grad_norm": 0.2790611982345581, "learning_rate": 6.886805272116513e-05, "loss": 0.0122, "step": 40800 }, { "loss_action": 0.011905230581760406, "loss_total": 0.011905230581760406, "step": 40800 }, { "grad_norm": 0.23732808232307434, "learning_rate": 6.885273946439617e-05, "loss": 0.0118, "step": 40810 }, { "loss_action": 0.008055725134909153, "loss_total": 0.008055725134909153, "step": 40810 }, { "grad_norm": 0.26749199628829956, "learning_rate": 6.883742414591998e-05, "loss": 0.0114, "step": 40820 }, { "loss_action": 0.010538456961512566, "loss_total": 0.010538456961512566, "step": 40820 }, { "grad_norm": 0.2233378142118454, "learning_rate": 6.88221067674114e-05, "loss": 0.0125, "step": 40830 }, { "loss_action": 0.011305641382932663, "loss_total": 0.011305641382932663, "step": 40830 }, { "grad_norm": 0.29944276809692383, "learning_rate": 6.88067873305455e-05, "loss": 0.0121, "step": 40840 }, { "loss_action": 0.01089761033654213, "loss_total": 0.01089761033654213, "step": 40840 }, { "grad_norm": 0.339182585477829, "learning_rate": 6.879146583699765e-05, "loss": 0.0124, "step": 40850 }, { "loss_action": 0.014179975725710392, "loss_total": 0.014179975725710392, "step": 40850 }, { "grad_norm": 0.30324888229370117, "learning_rate": 6.877614228844334e-05, "loss": 0.0145, "step": 40860 }, { "loss_action": 0.012050317600369453, "loss_total": 0.012050317600369453, "step": 40860 }, { "grad_norm": 0.26731401681900024, "learning_rate": 6.876081668655832e-05, "loss": 0.0134, "step": 40870 }, { "loss_action": 0.010539787821471691, "loss_total": 0.010539787821471691, "step": 40870 }, { "grad_norm": 0.26635098457336426, "learning_rate": 6.874548903301861e-05, "loss": 0.012, "step": 40880 }, { "loss_action": 0.015554212033748627, "loss_total": 0.015554212033748627, "step": 40880 }, { "grad_norm": 0.342121958732605, "learning_rate": 6.873015932950039e-05, "loss": 0.0134, "step": 40890 }, { "loss_action": 0.01609913818538189, "loss_total": 0.01609913818538189, "step": 40890 }, { "grad_norm": 0.34182286262512207, "learning_rate": 6.871482757768012e-05, "loss": 0.0149, "step": 40900 }, { "loss_action": 0.014090278185904026, "loss_total": 0.014090278185904026, "step": 40900 }, { "grad_norm": 0.26833027601242065, "learning_rate": 6.869949377923442e-05, "loss": 0.0128, "step": 40910 }, { "loss_action": 0.015068049542605877, "loss_total": 0.015068049542605877, "step": 40910 }, { "grad_norm": 0.2802683115005493, "learning_rate": 6.868415793584022e-05, "loss": 0.0153, "step": 40920 }, { "loss_action": 0.014775609597563744, "loss_total": 0.014775609597563744, "step": 40920 }, { "grad_norm": 0.3235199451446533, "learning_rate": 6.86688200491746e-05, "loss": 0.016, "step": 40930 }, { "loss_action": 0.012119107879698277, "loss_total": 0.012119107879698277, "step": 40930 }, { "grad_norm": 0.3174121379852295, "learning_rate": 6.865348012091488e-05, "loss": 0.0141, "step": 40940 }, { "loss_action": 0.013769925571978092, "loss_total": 0.013769925571978092, "step": 40940 }, { "grad_norm": 0.3548896908760071, "learning_rate": 6.86381381527386e-05, "loss": 0.0134, "step": 40950 }, { "loss_action": 0.014327062293887138, "loss_total": 0.014327062293887138, "step": 40950 }, { "grad_norm": 0.336530476808548, "learning_rate": 6.862279414632359e-05, "loss": 0.0124, "step": 40960 }, { "loss_action": 0.015119599178433418, "loss_total": 0.015119599178433418, "step": 40960 }, { "grad_norm": 0.3375217616558075, "learning_rate": 6.860744810334778e-05, "loss": 0.0136, "step": 40970 }, { "loss_action": 0.016494523733854294, "loss_total": 0.016494523733854294, "step": 40970 }, { "grad_norm": 0.3322725296020508, "learning_rate": 6.859210002548943e-05, "loss": 0.0125, "step": 40980 }, { "loss_action": 0.012997142970561981, "loss_total": 0.012997142970561981, "step": 40980 }, { "grad_norm": 0.3531268537044525, "learning_rate": 6.8576749914427e-05, "loss": 0.014, "step": 40990 }, { "loss_action": 0.019009776413440704, "loss_total": 0.019009776413440704, "step": 40990 }, { "grad_norm": 0.34847256541252136, "learning_rate": 6.85613977718391e-05, "loss": 0.0139, "step": 41000 }, { "loss_action": 0.01766837388277054, "loss_total": 0.01766837388277054, "step": 41000 }, { "grad_norm": 0.3554188907146454, "learning_rate": 6.854604359940464e-05, "loss": 0.0141, "step": 41010 }, { "loss_action": 0.016555624082684517, "loss_total": 0.016555624082684517, "step": 41010 }, { "grad_norm": 0.29649561643600464, "learning_rate": 6.853068739880276e-05, "loss": 0.013, "step": 41020 }, { "loss_action": 0.015531339682638645, "loss_total": 0.015531339682638645, "step": 41020 }, { "grad_norm": 0.3727908730506897, "learning_rate": 6.851532917171276e-05, "loss": 0.0137, "step": 41030 }, { "loss_action": 0.011296497657895088, "loss_total": 0.011296497657895088, "step": 41030 }, { "grad_norm": 0.2646802067756653, "learning_rate": 6.849996891981418e-05, "loss": 0.0128, "step": 41040 }, { "loss_action": 0.0284490454941988, "loss_total": 0.0284490454941988, "step": 41040 }, { "grad_norm": 0.25841036438941956, "learning_rate": 6.848460664478684e-05, "loss": 0.015, "step": 41050 }, { "loss_action": 0.015861770138144493, "loss_total": 0.015861770138144493, "step": 41050 }, { "grad_norm": 0.2877478003501892, "learning_rate": 6.846924234831069e-05, "loss": 0.0148, "step": 41060 }, { "loss_action": 0.014241081662476063, "loss_total": 0.014241081662476063, "step": 41060 }, { "grad_norm": 0.2732929587364197, "learning_rate": 6.845387603206597e-05, "loss": 0.0141, "step": 41070 }, { "loss_action": 0.009323219768702984, "loss_total": 0.009323219768702984, "step": 41070 }, { "grad_norm": 0.3034464716911316, "learning_rate": 6.843850769773312e-05, "loss": 0.0127, "step": 41080 }, { "loss_action": 0.01779649779200554, "loss_total": 0.01779649779200554, "step": 41080 }, { "grad_norm": 0.288604736328125, "learning_rate": 6.842313734699278e-05, "loss": 0.0126, "step": 41090 }, { "loss_action": 0.013654879294335842, "loss_total": 0.013654879294335842, "step": 41090 }, { "grad_norm": 0.2742456793785095, "learning_rate": 6.840776498152584e-05, "loss": 0.0132, "step": 41100 }, { "loss_action": 0.013094516471028328, "loss_total": 0.013094516471028328, "step": 41100 }, { "grad_norm": 0.23180150985717773, "learning_rate": 6.83923906030134e-05, "loss": 0.0124, "step": 41110 }, { "loss_action": 0.010425089858472347, "loss_total": 0.010425089858472347, "step": 41110 }, { "grad_norm": 0.3485495448112488, "learning_rate": 6.837701421313677e-05, "loss": 0.013, "step": 41120 }, { "loss_action": 0.012618647888302803, "loss_total": 0.012618647888302803, "step": 41120 }, { "grad_norm": 0.42298707365989685, "learning_rate": 6.83616358135775e-05, "loss": 0.013, "step": 41130 }, { "loss_action": 0.00939094927161932, "loss_total": 0.00939094927161932, "step": 41130 }, { "grad_norm": 0.329187273979187, "learning_rate": 6.834625540601734e-05, "loss": 0.0116, "step": 41140 }, { "loss_action": 0.013924296014010906, "loss_total": 0.013924296014010906, "step": 41140 }, { "grad_norm": 0.3598434031009674, "learning_rate": 6.833087299213829e-05, "loss": 0.0139, "step": 41150 }, { "loss_action": 0.014059682376682758, "loss_total": 0.014059682376682758, "step": 41150 }, { "grad_norm": 0.21907451748847961, "learning_rate": 6.83154885736225e-05, "loss": 0.0142, "step": 41160 }, { "loss_action": 0.008619183674454689, "loss_total": 0.008619183674454689, "step": 41160 }, { "grad_norm": 0.2576974630355835, "learning_rate": 6.830010215215244e-05, "loss": 0.0135, "step": 41170 }, { "loss_action": 0.010896258987486362, "loss_total": 0.010896258987486362, "step": 41170 }, { "grad_norm": 0.29409492015838623, "learning_rate": 6.828471372941072e-05, "loss": 0.012, "step": 41180 }, { "loss_action": 0.01741185411810875, "loss_total": 0.01741185411810875, "step": 41180 }, { "grad_norm": 0.2711152136325836, "learning_rate": 6.826932330708018e-05, "loss": 0.0122, "step": 41190 }, { "loss_action": 0.010843910276889801, "loss_total": 0.010843910276889801, "step": 41190 }, { "grad_norm": 0.23244601488113403, "learning_rate": 6.825393088684393e-05, "loss": 0.0118, "step": 41200 }, { "loss_action": 0.010740639641880989, "loss_total": 0.010740639641880989, "step": 41200 }, { "grad_norm": 0.21412065625190735, "learning_rate": 6.823853647038524e-05, "loss": 0.013, "step": 41210 }, { "loss_action": 0.012187975458800793, "loss_total": 0.012187975458800793, "step": 41210 }, { "grad_norm": 0.32436004281044006, "learning_rate": 6.822314005938762e-05, "loss": 0.0121, "step": 41220 }, { "loss_action": 0.011345992796123028, "loss_total": 0.011345992796123028, "step": 41220 }, { "grad_norm": 0.1936313807964325, "learning_rate": 6.820774165553479e-05, "loss": 0.013, "step": 41230 }, { "loss_action": 0.010745896026492119, "loss_total": 0.010745896026492119, "step": 41230 }, { "grad_norm": 0.2585334777832031, "learning_rate": 6.819234126051072e-05, "loss": 0.0114, "step": 41240 }, { "loss_action": 0.010096358135342598, "loss_total": 0.010096358135342598, "step": 41240 }, { "grad_norm": 0.2488853484392166, "learning_rate": 6.817693887599956e-05, "loss": 0.013, "step": 41250 }, { "loss_action": 0.010716641321778297, "loss_total": 0.010716641321778297, "step": 41250 }, { "grad_norm": 0.24469907581806183, "learning_rate": 6.816153450368568e-05, "loss": 0.0132, "step": 41260 }, { "loss_action": 0.009969457052648067, "loss_total": 0.009969457052648067, "step": 41260 }, { "grad_norm": 0.27976444363594055, "learning_rate": 6.814612814525372e-05, "loss": 0.0128, "step": 41270 }, { "loss_action": 0.00974778551608324, "loss_total": 0.00974778551608324, "step": 41270 }, { "grad_norm": 0.23309826850891113, "learning_rate": 6.813071980238846e-05, "loss": 0.0108, "step": 41280 }, { "loss_action": 0.010283839888870716, "loss_total": 0.010283839888870716, "step": 41280 }, { "grad_norm": 0.352940171957016, "learning_rate": 6.811530947677492e-05, "loss": 0.0113, "step": 41290 }, { "loss_action": 0.013932277448475361, "loss_total": 0.013932277448475361, "step": 41290 }, { "grad_norm": 0.3251838684082031, "learning_rate": 6.809989717009839e-05, "loss": 0.0113, "step": 41300 }, { "loss_action": 0.015617446973919868, "loss_total": 0.015617446973919868, "step": 41300 }, { "grad_norm": 0.33873239159584045, "learning_rate": 6.808448288404431e-05, "loss": 0.0139, "step": 41310 }, { "loss_action": 0.012462807819247246, "loss_total": 0.012462807819247246, "step": 41310 }, { "grad_norm": 0.3209015429019928, "learning_rate": 6.806906662029838e-05, "loss": 0.0136, "step": 41320 }, { "loss_action": 0.013145999051630497, "loss_total": 0.013145999051630497, "step": 41320 }, { "grad_norm": 0.24634438753128052, "learning_rate": 6.805364838054647e-05, "loss": 0.0126, "step": 41330 }, { "loss_action": 0.013058705255389214, "loss_total": 0.013058705255389214, "step": 41330 }, { "grad_norm": 0.26199817657470703, "learning_rate": 6.803822816647474e-05, "loss": 0.0124, "step": 41340 }, { "loss_action": 0.015628566965460777, "loss_total": 0.015628566965460777, "step": 41340 }, { "grad_norm": 0.35151949524879456, "learning_rate": 6.802280597976949e-05, "loss": 0.0149, "step": 41350 }, { "loss_action": 0.009365606121718884, "loss_total": 0.009365606121718884, "step": 41350 }, { "grad_norm": 0.2143591046333313, "learning_rate": 6.800738182211727e-05, "loss": 0.0106, "step": 41360 }, { "loss_action": 0.01024352665990591, "loss_total": 0.01024352665990591, "step": 41360 }, { "grad_norm": 0.20908264815807343, "learning_rate": 6.799195569520485e-05, "loss": 0.011, "step": 41370 }, { "loss_action": 0.011158152483403683, "loss_total": 0.011158152483403683, "step": 41370 }, { "grad_norm": 0.3207560181617737, "learning_rate": 6.79765276007192e-05, "loss": 0.012, "step": 41380 }, { "loss_action": 0.01027018390595913, "loss_total": 0.01027018390595913, "step": 41380 }, { "grad_norm": 0.23721101880073547, "learning_rate": 6.796109754034753e-05, "loss": 0.0118, "step": 41390 }, { "loss_action": 0.011356479488313198, "loss_total": 0.011356479488313198, "step": 41390 }, { "grad_norm": 0.24710111320018768, "learning_rate": 6.794566551577724e-05, "loss": 0.0129, "step": 41400 }, { "loss_action": 0.016214482486248016, "loss_total": 0.016214482486248016, "step": 41400 }, { "grad_norm": 0.2928139567375183, "learning_rate": 6.793023152869594e-05, "loss": 0.0143, "step": 41410 }, { "loss_action": 0.01106210332363844, "loss_total": 0.01106210332363844, "step": 41410 }, { "grad_norm": 0.3477471172809601, "learning_rate": 6.791479558079147e-05, "loss": 0.0127, "step": 41420 }, { "loss_action": 0.01421428844332695, "loss_total": 0.01421428844332695, "step": 41420 }, { "grad_norm": 0.24650441110134125, "learning_rate": 6.789935767375191e-05, "loss": 0.0127, "step": 41430 }, { "loss_action": 0.010800891555845737, "loss_total": 0.010800891555845737, "step": 41430 }, { "grad_norm": 0.2514609098434448, "learning_rate": 6.78839178092655e-05, "loss": 0.0119, "step": 41440 }, { "loss_action": 0.01586271822452545, "loss_total": 0.01586271822452545, "step": 41440 }, { "grad_norm": 0.30919480323791504, "learning_rate": 6.786847598902072e-05, "loss": 0.0141, "step": 41450 }, { "loss_action": 0.011203334666788578, "loss_total": 0.011203334666788578, "step": 41450 }, { "grad_norm": 0.349789023399353, "learning_rate": 6.785303221470627e-05, "loss": 0.0132, "step": 41460 }, { "loss_action": 0.013258806429803371, "loss_total": 0.013258806429803371, "step": 41460 }, { "grad_norm": 0.2694515287876129, "learning_rate": 6.783758648801108e-05, "loss": 0.0134, "step": 41470 }, { "loss_action": 0.010732533410191536, "loss_total": 0.010732533410191536, "step": 41470 }, { "grad_norm": 0.30401530861854553, "learning_rate": 6.782213881062422e-05, "loss": 0.0119, "step": 41480 }, { "loss_action": 0.012440565973520279, "loss_total": 0.012440565973520279, "step": 41480 }, { "grad_norm": 0.22096213698387146, "learning_rate": 6.780668918423508e-05, "loss": 0.011, "step": 41490 }, { "loss_action": 0.01355931255966425, "loss_total": 0.01355931255966425, "step": 41490 }, { "grad_norm": 0.39828523993492126, "learning_rate": 6.779123761053317e-05, "loss": 0.0132, "step": 41500 }, { "loss_action": 0.009559983387589455, "loss_total": 0.009559983387589455, "step": 41500 }, { "grad_norm": 0.30669769644737244, "learning_rate": 6.777578409120826e-05, "loss": 0.0137, "step": 41510 }, { "loss_action": 0.013166640885174274, "loss_total": 0.013166640885174274, "step": 41510 }, { "grad_norm": 0.24229231476783752, "learning_rate": 6.776032862795033e-05, "loss": 0.0115, "step": 41520 }, { "loss_action": 0.01132175512611866, "loss_total": 0.01132175512611866, "step": 41520 }, { "grad_norm": 0.2722729444503784, "learning_rate": 6.774487122244956e-05, "loss": 0.0125, "step": 41530 }, { "loss_action": 0.012468677945435047, "loss_total": 0.012468677945435047, "step": 41530 }, { "grad_norm": 0.3069705069065094, "learning_rate": 6.772941187639637e-05, "loss": 0.0121, "step": 41540 }, { "loss_action": 0.010576282627880573, "loss_total": 0.010576282627880573, "step": 41540 }, { "grad_norm": 0.32391420006752014, "learning_rate": 6.771395059148134e-05, "loss": 0.0133, "step": 41550 }, { "loss_action": 0.012171060778200626, "loss_total": 0.012171060778200626, "step": 41550 }, { "grad_norm": 0.2607259750366211, "learning_rate": 6.76984873693953e-05, "loss": 0.0128, "step": 41560 }, { "loss_action": 0.011413974687457085, "loss_total": 0.011413974687457085, "step": 41560 }, { "grad_norm": 0.3436136245727539, "learning_rate": 6.768302221182931e-05, "loss": 0.012, "step": 41570 }, { "loss_action": 0.00940622016787529, "loss_total": 0.00940622016787529, "step": 41570 }, { "grad_norm": 0.27035433053970337, "learning_rate": 6.766755512047457e-05, "loss": 0.0127, "step": 41580 }, { "loss_action": 0.012906457297503948, "loss_total": 0.012906457297503948, "step": 41580 }, { "grad_norm": 0.2450217753648758, "learning_rate": 6.765208609702259e-05, "loss": 0.0122, "step": 41590 }, { "loss_action": 0.010717085562646389, "loss_total": 0.010717085562646389, "step": 41590 }, { "grad_norm": 0.33066022396087646, "learning_rate": 6.763661514316499e-05, "loss": 0.0112, "step": 41600 }, { "loss_action": 0.010982959531247616, "loss_total": 0.010982959531247616, "step": 41600 }, { "grad_norm": 0.2846924662590027, "learning_rate": 6.76211422605937e-05, "loss": 0.0111, "step": 41610 }, { "loss_action": 0.016271378844976425, "loss_total": 0.016271378844976425, "step": 41610 }, { "grad_norm": 0.26879754662513733, "learning_rate": 6.760566745100076e-05, "loss": 0.0128, "step": 41620 }, { "loss_action": 0.01295583788305521, "loss_total": 0.01295583788305521, "step": 41620 }, { "grad_norm": 0.2636747658252716, "learning_rate": 6.75901907160785e-05, "loss": 0.0113, "step": 41630 }, { "loss_action": 0.014470593072474003, "loss_total": 0.014470593072474003, "step": 41630 }, { "grad_norm": 0.26774802803993225, "learning_rate": 6.757471205751943e-05, "loss": 0.0117, "step": 41640 }, { "loss_action": 0.011659516021609306, "loss_total": 0.011659516021609306, "step": 41640 }, { "grad_norm": 0.30069857835769653, "learning_rate": 6.75592314770163e-05, "loss": 0.0128, "step": 41650 }, { "loss_action": 0.011489110998809338, "loss_total": 0.011489110998809338, "step": 41650 }, { "grad_norm": 0.2850338816642761, "learning_rate": 6.7543748976262e-05, "loss": 0.0139, "step": 41660 }, { "loss_action": 0.01015505101531744, "loss_total": 0.01015505101531744, "step": 41660 }, { "grad_norm": 0.2705162763595581, "learning_rate": 6.752826455694968e-05, "loss": 0.0127, "step": 41670 }, { "loss_action": 0.009504060260951519, "loss_total": 0.009504060260951519, "step": 41670 }, { "grad_norm": 0.3106437623500824, "learning_rate": 6.751277822077271e-05, "loss": 0.0122, "step": 41680 }, { "loss_action": 0.014150859788060188, "loss_total": 0.014150859788060188, "step": 41680 }, { "grad_norm": 0.3389762341976166, "learning_rate": 6.749728996942465e-05, "loss": 0.0135, "step": 41690 }, { "loss_action": 0.011369945481419563, "loss_total": 0.011369945481419563, "step": 41690 }, { "grad_norm": 0.24753372371196747, "learning_rate": 6.748179980459924e-05, "loss": 0.0133, "step": 41700 }, { "loss_action": 0.011772303842008114, "loss_total": 0.011772303842008114, "step": 41700 }, { "grad_norm": 0.4136747419834137, "learning_rate": 6.746630772799052e-05, "loss": 0.0133, "step": 41710 }, { "loss_action": 0.017852701246738434, "loss_total": 0.017852701246738434, "step": 41710 }, { "grad_norm": 0.3167709410190582, "learning_rate": 6.745081374129262e-05, "loss": 0.0145, "step": 41720 }, { "loss_action": 0.014983559027314186, "loss_total": 0.014983559027314186, "step": 41720 }, { "grad_norm": 0.32448211312294006, "learning_rate": 6.743531784619998e-05, "loss": 0.0135, "step": 41730 }, { "loss_action": 0.0123898321762681, "loss_total": 0.0123898321762681, "step": 41730 }, { "grad_norm": 2.0370402336120605, "learning_rate": 6.741982004440719e-05, "loss": 0.0245, "step": 41740 }, { "loss_action": 0.020453505218029022, "loss_total": 0.020453505218029022, "step": 41740 }, { "grad_norm": 0.3261062502861023, "learning_rate": 6.740432033760907e-05, "loss": 0.0202, "step": 41750 }, { "loss_action": 0.01671515218913555, "loss_total": 0.01671515218913555, "step": 41750 }, { "grad_norm": 0.37837716937065125, "learning_rate": 6.738881872750066e-05, "loss": 0.0176, "step": 41760 }, { "loss_action": 0.01538301631808281, "loss_total": 0.01538301631808281, "step": 41760 }, { "grad_norm": 0.29989224672317505, "learning_rate": 6.737331521577715e-05, "loss": 0.0157, "step": 41770 }, { "loss_action": 0.016496853902935982, "loss_total": 0.016496853902935982, "step": 41770 }, { "grad_norm": 0.32630571722984314, "learning_rate": 6.735780980413403e-05, "loss": 0.0168, "step": 41780 }, { "loss_action": 0.021968841552734375, "loss_total": 0.021968841552734375, "step": 41780 }, { "grad_norm": 0.3289649188518524, "learning_rate": 6.734230249426692e-05, "loss": 0.0146, "step": 41790 }, { "loss_action": 0.010884481482207775, "loss_total": 0.010884481482207775, "step": 41790 }, { "grad_norm": 0.27908533811569214, "learning_rate": 6.732679328787168e-05, "loss": 0.0129, "step": 41800 }, { "loss_action": 0.010873144492506981, "loss_total": 0.010873144492506981, "step": 41800 }, { "grad_norm": 0.29721155762672424, "learning_rate": 6.731128218664438e-05, "loss": 0.0126, "step": 41810 }, { "loss_action": 0.012981023639440536, "loss_total": 0.012981023639440536, "step": 41810 }, { "grad_norm": 0.31926363706588745, "learning_rate": 6.729576919228129e-05, "loss": 0.0125, "step": 41820 }, { "loss_action": 0.017421774566173553, "loss_total": 0.017421774566173553, "step": 41820 }, { "grad_norm": 0.2848849594593048, "learning_rate": 6.728025430647888e-05, "loss": 0.0134, "step": 41830 }, { "loss_action": 0.010167647153139114, "loss_total": 0.010167647153139114, "step": 41830 }, { "grad_norm": 0.2886313796043396, "learning_rate": 6.726473753093383e-05, "loss": 0.0125, "step": 41840 }, { "loss_action": 0.014679738320410252, "loss_total": 0.014679738320410252, "step": 41840 }, { "grad_norm": 0.2665295898914337, "learning_rate": 6.724921886734305e-05, "loss": 0.0129, "step": 41850 }, { "loss_action": 0.010973862372338772, "loss_total": 0.010973862372338772, "step": 41850 }, { "grad_norm": 0.28958436846733093, "learning_rate": 6.723369831740363e-05, "loss": 0.014, "step": 41860 }, { "loss_action": 0.010243220254778862, "loss_total": 0.010243220254778862, "step": 41860 }, { "grad_norm": 0.2423558235168457, "learning_rate": 6.721817588281288e-05, "loss": 0.012, "step": 41870 }, { "loss_action": 0.013486341573297977, "loss_total": 0.013486341573297977, "step": 41870 }, { "grad_norm": 0.3388097882270813, "learning_rate": 6.720265156526828e-05, "loss": 0.0105, "step": 41880 }, { "loss_action": 0.008537407033145428, "loss_total": 0.008537407033145428, "step": 41880 }, { "grad_norm": 0.2934558391571045, "learning_rate": 6.718712536646758e-05, "loss": 0.0126, "step": 41890 }, { "loss_action": 0.015362092293798923, "loss_total": 0.015362092293798923, "step": 41890 }, { "grad_norm": 0.3208562731742859, "learning_rate": 6.71715972881087e-05, "loss": 0.0136, "step": 41900 }, { "loss_action": 0.01590314321219921, "loss_total": 0.01590314321219921, "step": 41900 }, { "grad_norm": 0.2567577362060547, "learning_rate": 6.715606733188974e-05, "loss": 0.014, "step": 41910 }, { "loss_action": 0.014054479077458382, "loss_total": 0.014054479077458382, "step": 41910 }, { "grad_norm": 0.2963418960571289, "learning_rate": 6.714053549950909e-05, "loss": 0.0132, "step": 41920 }, { "loss_action": 0.01444642897695303, "loss_total": 0.01444642897695303, "step": 41920 }, { "grad_norm": 0.2098819613456726, "learning_rate": 6.71250017926652e-05, "loss": 0.0122, "step": 41930 }, { "loss_action": 0.015189253725111485, "loss_total": 0.015189253725111485, "step": 41930 }, { "grad_norm": 0.2739485502243042, "learning_rate": 6.71094662130569e-05, "loss": 0.0133, "step": 41940 }, { "loss_action": 0.01791396550834179, "loss_total": 0.01791396550834179, "step": 41940 }, { "grad_norm": 0.2905582785606384, "learning_rate": 6.709392876238307e-05, "loss": 0.0135, "step": 41950 }, { "loss_action": 0.0180934090167284, "loss_total": 0.0180934090167284, "step": 41950 }, { "grad_norm": 0.2652060091495514, "learning_rate": 6.707838944234289e-05, "loss": 0.0134, "step": 41960 }, { "loss_action": 0.016435643658041954, "loss_total": 0.016435643658041954, "step": 41960 }, { "grad_norm": 0.34109869599342346, "learning_rate": 6.706284825463574e-05, "loss": 0.0122, "step": 41970 }, { "loss_action": 0.012174553237855434, "loss_total": 0.012174553237855434, "step": 41970 }, { "grad_norm": 0.29630404710769653, "learning_rate": 6.704730520096114e-05, "loss": 0.0124, "step": 41980 }, { "loss_action": 0.017504099756479263, "loss_total": 0.017504099756479263, "step": 41980 }, { "grad_norm": 0.3149394392967224, "learning_rate": 6.703176028301888e-05, "loss": 0.0137, "step": 41990 }, { "loss_action": 0.01726054772734642, "loss_total": 0.01726054772734642, "step": 41990 }, { "grad_norm": 0.3183084726333618, "learning_rate": 6.701621350250892e-05, "loss": 0.0129, "step": 42000 }, { "loss_action": 0.011132661253213882, "loss_total": 0.011132661253213882, "step": 42000 }, { "grad_norm": 0.321597158908844, "learning_rate": 6.700066486113144e-05, "loss": 0.0137, "step": 42010 }, { "loss_action": 0.012938185594975948, "loss_total": 0.012938185594975948, "step": 42010 }, { "grad_norm": 0.235081285238266, "learning_rate": 6.69851143605868e-05, "loss": 0.0115, "step": 42020 }, { "loss_action": 0.015128768049180508, "loss_total": 0.015128768049180508, "step": 42020 }, { "grad_norm": 0.29401129484176636, "learning_rate": 6.696956200257561e-05, "loss": 0.0146, "step": 42030 }, { "loss_action": 0.014192456379532814, "loss_total": 0.014192456379532814, "step": 42030 }, { "grad_norm": 0.2534174919128418, "learning_rate": 6.695400778879863e-05, "loss": 0.0104, "step": 42040 }, { "loss_action": 0.010911731980741024, "loss_total": 0.010911731980741024, "step": 42040 }, { "grad_norm": 0.2632386386394501, "learning_rate": 6.693845172095683e-05, "loss": 0.0112, "step": 42050 }, { "loss_action": 0.013547193259000778, "loss_total": 0.013547193259000778, "step": 42050 }, { "grad_norm": 0.27082210779190063, "learning_rate": 6.692289380075142e-05, "loss": 0.0116, "step": 42060 }, { "loss_action": 0.01366701815277338, "loss_total": 0.01366701815277338, "step": 42060 }, { "grad_norm": 0.4396570324897766, "learning_rate": 6.690733402988379e-05, "loss": 0.0124, "step": 42070 }, { "loss_action": 0.015205742791295052, "loss_total": 0.015205742791295052, "step": 42070 }, { "grad_norm": 0.3651401698589325, "learning_rate": 6.689177241005553e-05, "loss": 0.012, "step": 42080 }, { "loss_action": 0.008599348366260529, "loss_total": 0.008599348366260529, "step": 42080 }, { "grad_norm": 0.275785356760025, "learning_rate": 6.687620894296844e-05, "loss": 0.0127, "step": 42090 }, { "loss_action": 0.011711208149790764, "loss_total": 0.011711208149790764, "step": 42090 }, { "grad_norm": 0.36895716190338135, "learning_rate": 6.686064363032451e-05, "loss": 0.013, "step": 42100 }, { "loss_action": 0.009290959686040878, "loss_total": 0.009290959686040878, "step": 42100 }, { "grad_norm": 0.3195900022983551, "learning_rate": 6.684507647382596e-05, "loss": 0.0125, "step": 42110 }, { "loss_action": 0.00941984448581934, "loss_total": 0.00941984448581934, "step": 42110 }, { "grad_norm": 0.2964649498462677, "learning_rate": 6.682950747517513e-05, "loss": 0.0138, "step": 42120 }, { "loss_action": 0.013924811035394669, "loss_total": 0.013924811035394669, "step": 42120 }, { "grad_norm": 0.26876217126846313, "learning_rate": 6.68139366360747e-05, "loss": 0.0127, "step": 42130 }, { "loss_action": 0.00788062997162342, "loss_total": 0.00788062997162342, "step": 42130 }, { "grad_norm": 0.21484670042991638, "learning_rate": 6.679836395822744e-05, "loss": 0.0111, "step": 42140 }, { "loss_action": 0.011987029574811459, "loss_total": 0.011987029574811459, "step": 42140 }, { "grad_norm": 0.35056158900260925, "learning_rate": 6.678278944333633e-05, "loss": 0.0127, "step": 42150 }, { "loss_action": 0.018467584624886513, "loss_total": 0.018467584624886513, "step": 42150 }, { "grad_norm": 0.28508466482162476, "learning_rate": 6.676721309310462e-05, "loss": 0.0174, "step": 42160 }, { "loss_action": 0.010411611758172512, "loss_total": 0.010411611758172512, "step": 42160 }, { "grad_norm": 0.3123207688331604, "learning_rate": 6.67516349092357e-05, "loss": 0.0122, "step": 42170 }, { "loss_action": 0.015605170279741287, "loss_total": 0.015605170279741287, "step": 42170 }, { "grad_norm": 0.22062751650810242, "learning_rate": 6.673605489343315e-05, "loss": 0.0124, "step": 42180 }, { "loss_action": 0.014684896916151047, "loss_total": 0.014684896916151047, "step": 42180 }, { "grad_norm": 0.2471935749053955, "learning_rate": 6.672047304740081e-05, "loss": 0.0122, "step": 42190 }, { "loss_action": 0.016316697001457214, "loss_total": 0.016316697001457214, "step": 42190 }, { "grad_norm": 0.3090054988861084, "learning_rate": 6.670488937284268e-05, "loss": 0.0113, "step": 42200 }, { "loss_action": 0.01068329717963934, "loss_total": 0.01068329717963934, "step": 42200 }, { "grad_norm": 0.29627910256385803, "learning_rate": 6.668930387146294e-05, "loss": 0.0116, "step": 42210 }, { "loss_action": 0.011496590450406075, "loss_total": 0.011496590450406075, "step": 42210 }, { "grad_norm": 0.25976645946502686, "learning_rate": 6.667371654496605e-05, "loss": 0.0138, "step": 42220 }, { "loss_action": 0.011178662069141865, "loss_total": 0.011178662069141865, "step": 42220 }, { "grad_norm": 0.2825223505496979, "learning_rate": 6.665812739505659e-05, "loss": 0.0123, "step": 42230 }, { "loss_action": 0.012467295862734318, "loss_total": 0.012467295862734318, "step": 42230 }, { "grad_norm": 0.25013449788093567, "learning_rate": 6.664253642343935e-05, "loss": 0.0118, "step": 42240 }, { "loss_action": 0.013272946700453758, "loss_total": 0.013272946700453758, "step": 42240 }, { "grad_norm": 0.32615357637405396, "learning_rate": 6.662694363181935e-05, "loss": 0.0124, "step": 42250 }, { "loss_action": 0.012335066683590412, "loss_total": 0.012335066683590412, "step": 42250 }, { "grad_norm": 0.2838592529296875, "learning_rate": 6.66113490219018e-05, "loss": 0.0122, "step": 42260 }, { "loss_action": 0.010426427237689495, "loss_total": 0.010426427237689495, "step": 42260 }, { "grad_norm": 0.29378899931907654, "learning_rate": 6.659575259539207e-05, "loss": 0.0128, "step": 42270 }, { "loss_action": 0.010875933803617954, "loss_total": 0.010875933803617954, "step": 42270 }, { "grad_norm": 0.23427711427211761, "learning_rate": 6.65801543539958e-05, "loss": 0.0118, "step": 42280 }, { "loss_action": 0.011241842061281204, "loss_total": 0.011241842061281204, "step": 42280 }, { "grad_norm": 0.3217538893222809, "learning_rate": 6.65645542994188e-05, "loss": 0.0121, "step": 42290 }, { "loss_action": 0.012328719720244408, "loss_total": 0.012328719720244408, "step": 42290 }, { "grad_norm": 0.31579309701919556, "learning_rate": 6.654895243336702e-05, "loss": 0.0114, "step": 42300 }, { "loss_action": 0.013047192245721817, "loss_total": 0.013047192245721817, "step": 42300 }, { "grad_norm": 0.26536187529563904, "learning_rate": 6.65333487575467e-05, "loss": 0.0135, "step": 42310 }, { "loss_action": 0.011270067654550076, "loss_total": 0.011270067654550076, "step": 42310 }, { "grad_norm": 0.45107367634773254, "learning_rate": 6.651774327366422e-05, "loss": 0.0152, "step": 42320 }, { "loss_action": 0.015482528135180473, "loss_total": 0.015482528135180473, "step": 42320 }, { "grad_norm": 0.31024545431137085, "learning_rate": 6.650213598342613e-05, "loss": 0.0131, "step": 42330 }, { "loss_action": 0.022344352677464485, "loss_total": 0.022344352677464485, "step": 42330 }, { "grad_norm": 0.3687788248062134, "learning_rate": 6.648652688853931e-05, "loss": 0.0128, "step": 42340 }, { "loss_action": 0.011044599115848541, "loss_total": 0.011044599115848541, "step": 42340 }, { "grad_norm": 0.3641926050186157, "learning_rate": 6.647091599071066e-05, "loss": 0.0133, "step": 42350 }, { "loss_action": 0.011867114342749119, "loss_total": 0.011867114342749119, "step": 42350 }, { "grad_norm": 0.2752792239189148, "learning_rate": 6.645530329164743e-05, "loss": 0.012, "step": 42360 }, { "loss_action": 0.016397029161453247, "loss_total": 0.016397029161453247, "step": 42360 }, { "grad_norm": 0.24376091361045837, "learning_rate": 6.643968879305694e-05, "loss": 0.0128, "step": 42370 }, { "loss_action": 0.009948275983333588, "loss_total": 0.009948275983333588, "step": 42370 }, { "grad_norm": 0.30166855454444885, "learning_rate": 6.642407249664683e-05, "loss": 0.0114, "step": 42380 }, { "loss_action": 0.010837609879672527, "loss_total": 0.010837609879672527, "step": 42380 }, { "grad_norm": 0.29108503460884094, "learning_rate": 6.640845440412483e-05, "loss": 0.0114, "step": 42390 }, { "loss_action": 0.009494849480688572, "loss_total": 0.009494849480688572, "step": 42390 }, { "grad_norm": 0.3228495419025421, "learning_rate": 6.639283451719893e-05, "loss": 0.0115, "step": 42400 }, { "loss_action": 0.013898116536438465, "loss_total": 0.013898116536438465, "step": 42400 }, { "grad_norm": 0.27849119901657104, "learning_rate": 6.637721283757729e-05, "loss": 0.0119, "step": 42410 }, { "loss_action": 0.01102113351225853, "loss_total": 0.01102113351225853, "step": 42410 }, { "grad_norm": 0.24235135316848755, "learning_rate": 6.636158936696828e-05, "loss": 0.0115, "step": 42420 }, { "loss_action": 0.00965872872620821, "loss_total": 0.00965872872620821, "step": 42420 }, { "grad_norm": 0.23750688135623932, "learning_rate": 6.634596410708047e-05, "loss": 0.0124, "step": 42430 }, { "loss_action": 0.011142818257212639, "loss_total": 0.011142818257212639, "step": 42430 }, { "grad_norm": 0.20999446511268616, "learning_rate": 6.633033705962257e-05, "loss": 0.0107, "step": 42440 }, { "loss_action": 0.015278437174856663, "loss_total": 0.015278437174856663, "step": 42440 }, { "grad_norm": 0.24823516607284546, "learning_rate": 6.631470822630359e-05, "loss": 0.0113, "step": 42450 }, { "loss_action": 0.013129566796123981, "loss_total": 0.013129566796123981, "step": 42450 }, { "grad_norm": 0.3679329454898834, "learning_rate": 6.629907760883263e-05, "loss": 0.0114, "step": 42460 }, { "loss_action": 0.018674539402127266, "loss_total": 0.018674539402127266, "step": 42460 }, { "grad_norm": 0.2956717908382416, "learning_rate": 6.628344520891905e-05, "loss": 0.0134, "step": 42470 }, { "loss_action": 0.012977556325495243, "loss_total": 0.012977556325495243, "step": 42470 }, { "grad_norm": 0.2465558648109436, "learning_rate": 6.62678110282724e-05, "loss": 0.0126, "step": 42480 }, { "loss_action": 0.012129830196499825, "loss_total": 0.012129830196499825, "step": 42480 }, { "grad_norm": 0.24257855117321014, "learning_rate": 6.625217506860237e-05, "loss": 0.0122, "step": 42490 }, { "loss_action": 0.014099379070103168, "loss_total": 0.014099379070103168, "step": 42490 }, { "grad_norm": 0.25390422344207764, "learning_rate": 6.623653733161892e-05, "loss": 0.0107, "step": 42500 }, { "loss_action": 0.00855404045432806, "loss_total": 0.00855404045432806, "step": 42500 }, { "grad_norm": 0.23652417957782745, "learning_rate": 6.622089781903217e-05, "loss": 0.0118, "step": 42510 }, { "loss_action": 0.015092240646481514, "loss_total": 0.015092240646481514, "step": 42510 }, { "grad_norm": 0.26023513078689575, "learning_rate": 6.620525653255241e-05, "loss": 0.0123, "step": 42520 }, { "loss_action": 0.012653147801756859, "loss_total": 0.012653147801756859, "step": 42520 }, { "grad_norm": 0.28819191455841064, "learning_rate": 6.618961347389015e-05, "loss": 0.0128, "step": 42530 }, { "loss_action": 0.011200403794646263, "loss_total": 0.011200403794646263, "step": 42530 }, { "grad_norm": 0.26761379837989807, "learning_rate": 6.617396864475613e-05, "loss": 0.0117, "step": 42540 }, { "loss_action": 0.008890773169696331, "loss_total": 0.008890773169696331, "step": 42540 }, { "grad_norm": 0.28524455428123474, "learning_rate": 6.61583220468612e-05, "loss": 0.0112, "step": 42550 }, { "loss_action": 0.010885744355618954, "loss_total": 0.010885744355618954, "step": 42550 }, { "grad_norm": 0.26049456000328064, "learning_rate": 6.614267368191645e-05, "loss": 0.0125, "step": 42560 }, { "loss_action": 0.010764033533632755, "loss_total": 0.010764033533632755, "step": 42560 }, { "grad_norm": 0.2983330488204956, "learning_rate": 6.61270235516332e-05, "loss": 0.0132, "step": 42570 }, { "loss_action": 0.012603038921952248, "loss_total": 0.012603038921952248, "step": 42570 }, { "grad_norm": 0.26397499442100525, "learning_rate": 6.611137165772287e-05, "loss": 0.0121, "step": 42580 }, { "loss_action": 0.011933119036257267, "loss_total": 0.011933119036257267, "step": 42580 }, { "grad_norm": 0.25225913524627686, "learning_rate": 6.60957180018972e-05, "loss": 0.0124, "step": 42590 }, { "loss_action": 0.01593427173793316, "loss_total": 0.01593427173793316, "step": 42590 }, { "grad_norm": 0.35391536355018616, "learning_rate": 6.608006258586797e-05, "loss": 0.014, "step": 42600 }, { "loss_action": 0.009100339375436306, "loss_total": 0.009100339375436306, "step": 42600 }, { "grad_norm": 0.3421185612678528, "learning_rate": 6.606440541134731e-05, "loss": 0.0134, "step": 42610 }, { "loss_action": 0.009135770611464977, "loss_total": 0.009135770611464977, "step": 42610 }, { "grad_norm": 0.24087555706501007, "learning_rate": 6.60487464800474e-05, "loss": 0.012, "step": 42620 }, { "loss_action": 0.008920997381210327, "loss_total": 0.008920997381210327, "step": 42620 }, { "grad_norm": 0.29112792015075684, "learning_rate": 6.603308579368071e-05, "loss": 0.0131, "step": 42630 }, { "loss_action": 0.01199758518487215, "loss_total": 0.01199758518487215, "step": 42630 }, { "grad_norm": 0.2685907185077667, "learning_rate": 6.601742335395987e-05, "loss": 0.0119, "step": 42640 }, { "loss_action": 0.01131125632673502, "loss_total": 0.01131125632673502, "step": 42640 }, { "grad_norm": 0.3420753479003906, "learning_rate": 6.600175916259769e-05, "loss": 0.013, "step": 42650 }, { "loss_action": 0.014168756082654, "loss_total": 0.014168756082654, "step": 42650 }, { "grad_norm": 0.2913990020751953, "learning_rate": 6.598609322130718e-05, "loss": 0.0152, "step": 42660 }, { "loss_action": 0.012628125958144665, "loss_total": 0.012628125958144665, "step": 42660 }, { "grad_norm": 0.2924680709838867, "learning_rate": 6.597042553180155e-05, "loss": 0.0122, "step": 42670 }, { "loss_action": 0.013673907145857811, "loss_total": 0.013673907145857811, "step": 42670 }, { "grad_norm": 0.6480641961097717, "learning_rate": 6.59547560957942e-05, "loss": 0.0123, "step": 42680 }, { "loss_action": 0.018453164026141167, "loss_total": 0.018453164026141167, "step": 42680 }, { "grad_norm": 0.2688050866127014, "learning_rate": 6.59390849149987e-05, "loss": 0.0146, "step": 42690 }, { "loss_action": 0.009883756749331951, "loss_total": 0.009883756749331951, "step": 42690 }, { "grad_norm": 0.3074110448360443, "learning_rate": 6.592341199112886e-05, "loss": 0.0129, "step": 42700 }, { "loss_action": 0.012617550790309906, "loss_total": 0.012617550790309906, "step": 42700 }, { "grad_norm": 0.25084635615348816, "learning_rate": 6.590773732589861e-05, "loss": 0.0122, "step": 42710 }, { "loss_action": 0.01008955854922533, "loss_total": 0.01008955854922533, "step": 42710 }, { "grad_norm": 0.3587723672389984, "learning_rate": 6.589206092102213e-05, "loss": 0.0138, "step": 42720 }, { "loss_action": 0.011685926467180252, "loss_total": 0.011685926467180252, "step": 42720 }, { "grad_norm": 0.3046117424964905, "learning_rate": 6.587638277821375e-05, "loss": 0.0138, "step": 42730 }, { "loss_action": 0.0121833560988307, "loss_total": 0.0121833560988307, "step": 42730 }, { "grad_norm": 0.20343509316444397, "learning_rate": 6.586070289918803e-05, "loss": 0.0121, "step": 42740 }, { "loss_action": 0.012906116433441639, "loss_total": 0.012906116433441639, "step": 42740 }, { "grad_norm": 0.25666314363479614, "learning_rate": 6.584502128565968e-05, "loss": 0.0133, "step": 42750 }, { "loss_action": 0.01003513764590025, "loss_total": 0.01003513764590025, "step": 42750 }, { "grad_norm": 0.2823076546192169, "learning_rate": 6.582933793934363e-05, "loss": 0.0121, "step": 42760 }, { "loss_action": 0.012859132140874863, "loss_total": 0.012859132140874863, "step": 42760 }, { "grad_norm": 0.3283213973045349, "learning_rate": 6.581365286195498e-05, "loss": 0.0139, "step": 42770 }, { "loss_action": 0.011381157673895359, "loss_total": 0.011381157673895359, "step": 42770 }, { "grad_norm": 0.2682570517063141, "learning_rate": 6.579796605520903e-05, "loss": 0.0134, "step": 42780 }, { "loss_action": 0.02204209752380848, "loss_total": 0.02204209752380848, "step": 42780 }, { "grad_norm": 0.288686066865921, "learning_rate": 6.578227752082127e-05, "loss": 0.0136, "step": 42790 }, { "loss_action": 0.013757594861090183, "loss_total": 0.013757594861090183, "step": 42790 }, { "grad_norm": 0.3169505298137665, "learning_rate": 6.576658726050735e-05, "loss": 0.0114, "step": 42800 }, { "loss_action": 0.010272474959492683, "loss_total": 0.010272474959492683, "step": 42800 }, { "grad_norm": 0.385392963886261, "learning_rate": 6.575089527598316e-05, "loss": 0.0129, "step": 42810 }, { "loss_action": 0.013661731034517288, "loss_total": 0.013661731034517288, "step": 42810 }, { "grad_norm": 0.2784164249897003, "learning_rate": 6.573520156896476e-05, "loss": 0.0128, "step": 42820 }, { "loss_action": 0.011202799156308174, "loss_total": 0.011202799156308174, "step": 42820 }, { "grad_norm": 0.3890407383441925, "learning_rate": 6.571950614116835e-05, "loss": 0.0121, "step": 42830 }, { "loss_action": 0.012235182337462902, "loss_total": 0.012235182337462902, "step": 42830 }, { "grad_norm": 0.23520773649215698, "learning_rate": 6.570380899431039e-05, "loss": 0.0111, "step": 42840 }, { "loss_action": 0.009637883864343166, "loss_total": 0.009637883864343166, "step": 42840 }, { "grad_norm": 0.30823269486427307, "learning_rate": 6.568811013010749e-05, "loss": 0.0122, "step": 42850 }, { "loss_action": 0.015150947496294975, "loss_total": 0.015150947496294975, "step": 42850 }, { "grad_norm": 0.27918145060539246, "learning_rate": 6.567240955027645e-05, "loss": 0.0154, "step": 42860 }, { "loss_action": 0.011027798987925053, "loss_total": 0.011027798987925053, "step": 42860 }, { "grad_norm": 0.38490021228790283, "learning_rate": 6.565670725653427e-05, "loss": 0.0124, "step": 42870 }, { "loss_action": 0.013038641773164272, "loss_total": 0.013038641773164272, "step": 42870 }, { "grad_norm": 0.2785756587982178, "learning_rate": 6.564100325059812e-05, "loss": 0.0129, "step": 42880 }, { "loss_action": 0.008982349187135696, "loss_total": 0.008982349187135696, "step": 42880 }, { "grad_norm": 0.3015643358230591, "learning_rate": 6.562529753418538e-05, "loss": 0.0116, "step": 42890 }, { "loss_action": 0.00888412818312645, "loss_total": 0.00888412818312645, "step": 42890 }, { "grad_norm": 0.28322362899780273, "learning_rate": 6.56095901090136e-05, "loss": 0.0116, "step": 42900 }, { "loss_action": 0.011236355639994144, "loss_total": 0.011236355639994144, "step": 42900 }, { "grad_norm": 0.2755393087863922, "learning_rate": 6.55938809768005e-05, "loss": 0.0128, "step": 42910 }, { "loss_action": 0.014417754486203194, "loss_total": 0.014417754486203194, "step": 42910 }, { "grad_norm": 0.23698769509792328, "learning_rate": 6.557817013926402e-05, "loss": 0.0126, "step": 42920 }, { "loss_action": 0.01040114276111126, "loss_total": 0.01040114276111126, "step": 42920 }, { "grad_norm": 0.2637670040130615, "learning_rate": 6.556245759812227e-05, "loss": 0.0118, "step": 42930 }, { "loss_action": 0.015447843819856644, "loss_total": 0.015447843819856644, "step": 42930 }, { "grad_norm": 0.22066126763820648, "learning_rate": 6.554674335509357e-05, "loss": 0.0119, "step": 42940 }, { "loss_action": 0.011142255738377571, "loss_total": 0.011142255738377571, "step": 42940 }, { "grad_norm": 0.22838467359542847, "learning_rate": 6.553102741189638e-05, "loss": 0.0124, "step": 42950 }, { "loss_action": 0.010621660389006138, "loss_total": 0.010621660389006138, "step": 42950 }, { "grad_norm": 0.2994614243507385, "learning_rate": 6.55153097702494e-05, "loss": 0.0114, "step": 42960 }, { "loss_action": 0.013360518030822277, "loss_total": 0.013360518030822277, "step": 42960 }, { "grad_norm": 0.313534140586853, "learning_rate": 6.549959043187146e-05, "loss": 0.0116, "step": 42970 }, { "loss_action": 0.013602126389741898, "loss_total": 0.013602126389741898, "step": 42970 }, { "grad_norm": 0.2505341172218323, "learning_rate": 6.54838693984816e-05, "loss": 0.0127, "step": 42980 }, { "loss_action": 0.011200935579836369, "loss_total": 0.011200935579836369, "step": 42980 }, { "grad_norm": 0.2340899407863617, "learning_rate": 6.546814667179909e-05, "loss": 0.0109, "step": 42990 }, { "loss_action": 0.014109582640230656, "loss_total": 0.014109582640230656, "step": 42990 }, { "grad_norm": 0.2773245871067047, "learning_rate": 6.545242225354328e-05, "loss": 0.0119, "step": 43000 }, { "loss_action": 0.011653094552457333, "loss_total": 0.011653094552457333, "step": 43000 }, { "grad_norm": 0.28996238112449646, "learning_rate": 6.543669614543383e-05, "loss": 0.0121, "step": 43010 }, { "loss_action": 0.014335720799863338, "loss_total": 0.014335720799863338, "step": 43010 }, { "grad_norm": 0.3095437288284302, "learning_rate": 6.542096834919049e-05, "loss": 0.011, "step": 43020 }, { "loss_action": 0.015792544931173325, "loss_total": 0.015792544931173325, "step": 43020 }, { "grad_norm": 0.2397976815700531, "learning_rate": 6.540523886653324e-05, "loss": 0.0117, "step": 43030 }, { "loss_action": 0.011494042351841927, "loss_total": 0.011494042351841927, "step": 43030 }, { "grad_norm": 0.292091965675354, "learning_rate": 6.538950769918222e-05, "loss": 0.0122, "step": 43040 }, { "loss_action": 0.009232569485902786, "loss_total": 0.009232569485902786, "step": 43040 }, { "grad_norm": 0.31365257501602173, "learning_rate": 6.537377484885779e-05, "loss": 0.0124, "step": 43050 }, { "loss_action": 0.012293667532503605, "loss_total": 0.012293667532503605, "step": 43050 }, { "grad_norm": 0.21948452293872833, "learning_rate": 6.535804031728045e-05, "loss": 0.0121, "step": 43060 }, { "loss_action": 0.015349995344877243, "loss_total": 0.015349995344877243, "step": 43060 }, { "grad_norm": 0.2899133563041687, "learning_rate": 6.534230410617092e-05, "loss": 0.0111, "step": 43070 }, { "loss_action": 0.012820552103221416, "loss_total": 0.012820552103221416, "step": 43070 }, { "grad_norm": 0.25474363565444946, "learning_rate": 6.532656621725007e-05, "loss": 0.0104, "step": 43080 }, { "loss_action": 0.010231963358819485, "loss_total": 0.010231963358819485, "step": 43080 }, { "grad_norm": 0.290501207113266, "learning_rate": 6.531082665223898e-05, "loss": 0.0128, "step": 43090 }, { "loss_action": 0.013140056282281876, "loss_total": 0.013140056282281876, "step": 43090 }, { "grad_norm": 0.38591885566711426, "learning_rate": 6.529508541285889e-05, "loss": 0.0123, "step": 43100 }, { "loss_action": 0.01109154149889946, "loss_total": 0.01109154149889946, "step": 43100 }, { "grad_norm": 0.22843992710113525, "learning_rate": 6.527934250083128e-05, "loss": 0.0117, "step": 43110 }, { "loss_action": 0.00997149758040905, "loss_total": 0.00997149758040905, "step": 43110 }, { "grad_norm": 0.27734652161598206, "learning_rate": 6.526359791787775e-05, "loss": 0.0104, "step": 43120 }, { "loss_action": 0.009113883599638939, "loss_total": 0.009113883599638939, "step": 43120 }, { "grad_norm": 0.1948033720254898, "learning_rate": 6.524785166572009e-05, "loss": 0.0113, "step": 43130 }, { "loss_action": 0.012481349520385265, "loss_total": 0.012481349520385265, "step": 43130 }, { "grad_norm": 0.2645392119884491, "learning_rate": 6.523210374608029e-05, "loss": 0.0134, "step": 43140 }, { "loss_action": 0.010747320018708706, "loss_total": 0.010747320018708706, "step": 43140 }, { "grad_norm": 0.2292349636554718, "learning_rate": 6.521635416068054e-05, "loss": 0.0107, "step": 43150 }, { "loss_action": 0.011578094214200974, "loss_total": 0.011578094214200974, "step": 43150 }, { "grad_norm": 0.2715834975242615, "learning_rate": 6.520060291124317e-05, "loss": 0.0107, "step": 43160 }, { "loss_action": 0.013508617877960205, "loss_total": 0.013508617877960205, "step": 43160 }, { "grad_norm": 0.28304311633110046, "learning_rate": 6.518484999949072e-05, "loss": 0.0125, "step": 43170 }, { "loss_action": 0.00994197279214859, "loss_total": 0.00994197279214859, "step": 43170 }, { "grad_norm": 0.3023850917816162, "learning_rate": 6.516909542714591e-05, "loss": 0.0115, "step": 43180 }, { "loss_action": 0.00906226597726345, "loss_total": 0.00906226597726345, "step": 43180 }, { "grad_norm": 0.23213495314121246, "learning_rate": 6.515333919593161e-05, "loss": 0.0114, "step": 43190 }, { "loss_action": 0.010055958293378353, "loss_total": 0.010055958293378353, "step": 43190 }, { "grad_norm": 0.2618117332458496, "learning_rate": 6.513758130757094e-05, "loss": 0.0114, "step": 43200 }, { "loss_action": 0.01060343999415636, "loss_total": 0.01060343999415636, "step": 43200 }, { "grad_norm": 0.25304731726646423, "learning_rate": 6.512182176378713e-05, "loss": 0.0107, "step": 43210 }, { "loss_action": 0.011419284157454967, "loss_total": 0.011419284157454967, "step": 43210 }, { "grad_norm": 0.3033733367919922, "learning_rate": 6.510606056630362e-05, "loss": 0.0112, "step": 43220 }, { "loss_action": 0.012337245047092438, "loss_total": 0.012337245047092438, "step": 43220 }, { "grad_norm": 0.23822125792503357, "learning_rate": 6.509029771684405e-05, "loss": 0.0105, "step": 43230 }, { "loss_action": 0.009958147071301937, "loss_total": 0.009958147071301937, "step": 43230 }, { "grad_norm": 0.2543256878852844, "learning_rate": 6.50745332171322e-05, "loss": 0.0138, "step": 43240 }, { "loss_action": 0.009210273623466492, "loss_total": 0.009210273623466492, "step": 43240 }, { "grad_norm": 0.311114102602005, "learning_rate": 6.505876706889207e-05, "loss": 0.0127, "step": 43250 }, { "loss_action": 0.00931703019887209, "loss_total": 0.00931703019887209, "step": 43250 }, { "grad_norm": 0.3082210421562195, "learning_rate": 6.504299927384781e-05, "loss": 0.0121, "step": 43260 }, { "loss_action": 0.012174485251307487, "loss_total": 0.012174485251307487, "step": 43260 }, { "grad_norm": 0.3597981035709381, "learning_rate": 6.502722983372378e-05, "loss": 0.0129, "step": 43270 }, { "loss_action": 0.015381674282252789, "loss_total": 0.015381674282252789, "step": 43270 }, { "grad_norm": 0.396223247051239, "learning_rate": 6.501145875024446e-05, "loss": 0.0131, "step": 43280 }, { "loss_action": 0.009047827683389187, "loss_total": 0.009047827683389187, "step": 43280 }, { "grad_norm": 0.24303993582725525, "learning_rate": 6.499568602513459e-05, "loss": 0.0122, "step": 43290 }, { "loss_action": 0.017001302912831306, "loss_total": 0.017001302912831306, "step": 43290 }, { "grad_norm": 0.2559014558792114, "learning_rate": 6.497991166011903e-05, "loss": 0.0143, "step": 43300 }, { "loss_action": 0.0118327671661973, "loss_total": 0.0118327671661973, "step": 43300 }, { "grad_norm": 0.22124633193016052, "learning_rate": 6.49641356569229e-05, "loss": 0.0119, "step": 43310 }, { "loss_action": 0.015077013522386551, "loss_total": 0.015077013522386551, "step": 43310 }, { "grad_norm": 0.3048083782196045, "learning_rate": 6.494835801727135e-05, "loss": 0.0114, "step": 43320 }, { "loss_action": 0.014527227729558945, "loss_total": 0.014527227729558945, "step": 43320 }, { "grad_norm": 0.267892986536026, "learning_rate": 6.493257874288986e-05, "loss": 0.0136, "step": 43330 }, { "loss_action": 0.008661010302603245, "loss_total": 0.008661010302603245, "step": 43330 }, { "grad_norm": 0.27012646198272705, "learning_rate": 6.491679783550399e-05, "loss": 0.0111, "step": 43340 }, { "loss_action": 0.013653552159667015, "loss_total": 0.013653552159667015, "step": 43340 }, { "grad_norm": 0.2503926157951355, "learning_rate": 6.490101529683957e-05, "loss": 0.0117, "step": 43350 }, { "loss_action": 0.010168654844164848, "loss_total": 0.010168654844164848, "step": 43350 }, { "grad_norm": 0.27891698479652405, "learning_rate": 6.488523112862248e-05, "loss": 0.0107, "step": 43360 }, { "loss_action": 0.008738365024328232, "loss_total": 0.008738365024328232, "step": 43360 }, { "grad_norm": 0.20931603014469147, "learning_rate": 6.486944533257891e-05, "loss": 0.0117, "step": 43370 }, { "loss_action": 0.01217653602361679, "loss_total": 0.01217653602361679, "step": 43370 }, { "grad_norm": 0.26908040046691895, "learning_rate": 6.485365791043517e-05, "loss": 0.0109, "step": 43380 }, { "loss_action": 0.012381209060549736, "loss_total": 0.012381209060549736, "step": 43380 }, { "grad_norm": 0.3193429112434387, "learning_rate": 6.483786886391772e-05, "loss": 0.0119, "step": 43390 }, { "loss_action": 0.011987777426838875, "loss_total": 0.011987777426838875, "step": 43390 }, { "grad_norm": 0.2589295208454132, "learning_rate": 6.482207819475323e-05, "loss": 0.0112, "step": 43400 }, { "loss_action": 0.01444101333618164, "loss_total": 0.01444101333618164, "step": 43400 }, { "grad_norm": 0.2836453914642334, "learning_rate": 6.480628590466857e-05, "loss": 0.0132, "step": 43410 }, { "loss_action": 0.014954673126339912, "loss_total": 0.014954673126339912, "step": 43410 }, { "grad_norm": 0.2754671573638916, "learning_rate": 6.479049199539074e-05, "loss": 0.0122, "step": 43420 }, { "loss_action": 0.016442647203803062, "loss_total": 0.016442647203803062, "step": 43420 }, { "grad_norm": 0.27802133560180664, "learning_rate": 6.477469646864693e-05, "loss": 0.0103, "step": 43430 }, { "loss_action": 0.013810199685394764, "loss_total": 0.013810199685394764, "step": 43430 }, { "grad_norm": 0.24871061742305756, "learning_rate": 6.475889932616454e-05, "loss": 0.0115, "step": 43440 }, { "loss_action": 0.010162604972720146, "loss_total": 0.010162604972720146, "step": 43440 }, { "grad_norm": 0.3024528920650482, "learning_rate": 6.474310056967111e-05, "loss": 0.0118, "step": 43450 }, { "loss_action": 0.013944285921752453, "loss_total": 0.013944285921752453, "step": 43450 }, { "grad_norm": 0.2602379024028778, "learning_rate": 6.472730020089437e-05, "loss": 0.0123, "step": 43460 }, { "loss_action": 0.008457394316792488, "loss_total": 0.008457394316792488, "step": 43460 }, { "grad_norm": 0.33663609623908997, "learning_rate": 6.471149822156222e-05, "loss": 0.0115, "step": 43470 }, { "loss_action": 0.011625600047409534, "loss_total": 0.011625600047409534, "step": 43470 }, { "grad_norm": 0.2832169532775879, "learning_rate": 6.469569463340275e-05, "loss": 0.0117, "step": 43480 }, { "loss_action": 0.01370612159371376, "loss_total": 0.01370612159371376, "step": 43480 }, { "grad_norm": 0.5642528533935547, "learning_rate": 6.467988943814418e-05, "loss": 0.0112, "step": 43490 }, { "loss_action": 0.013826957903802395, "loss_total": 0.013826957903802395, "step": 43490 }, { "grad_norm": 0.35988548398017883, "learning_rate": 6.4664082637515e-05, "loss": 0.0135, "step": 43500 }, { "loss_action": 0.011683364398777485, "loss_total": 0.011683364398777485, "step": 43500 }, { "grad_norm": 0.3275170922279358, "learning_rate": 6.464827423324377e-05, "loss": 0.0132, "step": 43510 }, { "loss_action": 0.00853094831109047, "loss_total": 0.00853094831109047, "step": 43510 }, { "grad_norm": 0.3961307108402252, "learning_rate": 6.463246422705931e-05, "loss": 0.0125, "step": 43520 }, { "loss_action": 0.0140619408339262, "loss_total": 0.0140619408339262, "step": 43520 }, { "grad_norm": 0.30219152569770813, "learning_rate": 6.461665262069055e-05, "loss": 0.0131, "step": 43530 }, { "loss_action": 0.013787196017801762, "loss_total": 0.013787196017801762, "step": 43530 }, { "grad_norm": 0.31199324131011963, "learning_rate": 6.460083941586665e-05, "loss": 0.0129, "step": 43540 }, { "loss_action": 0.012756196781992912, "loss_total": 0.012756196781992912, "step": 43540 }, { "grad_norm": 0.21956896781921387, "learning_rate": 6.45850246143169e-05, "loss": 0.0118, "step": 43550 }, { "loss_action": 0.008121475577354431, "loss_total": 0.008121475577354431, "step": 43550 }, { "grad_norm": 0.3188113570213318, "learning_rate": 6.456920821777077e-05, "loss": 0.0127, "step": 43560 }, { "loss_action": 0.010076986625790596, "loss_total": 0.010076986625790596, "step": 43560 }, { "grad_norm": 0.2399294674396515, "learning_rate": 6.455339022795796e-05, "loss": 0.0117, "step": 43570 }, { "loss_action": 0.008983992040157318, "loss_total": 0.008983992040157318, "step": 43570 }, { "grad_norm": 0.27829742431640625, "learning_rate": 6.453757064660825e-05, "loss": 0.0105, "step": 43580 }, { "loss_action": 0.013837764970958233, "loss_total": 0.013837764970958233, "step": 43580 }, { "grad_norm": 0.22208258509635925, "learning_rate": 6.452174947545169e-05, "loss": 0.0126, "step": 43590 }, { "loss_action": 0.00995954405516386, "loss_total": 0.00995954405516386, "step": 43590 }, { "grad_norm": 0.3394700586795807, "learning_rate": 6.450592671621842e-05, "loss": 0.0118, "step": 43600 }, { "loss_action": 0.014781618490815163, "loss_total": 0.014781618490815163, "step": 43600 }, { "grad_norm": 0.2543811798095703, "learning_rate": 6.449010237063882e-05, "loss": 0.0109, "step": 43610 }, { "loss_action": 0.009878565557301044, "loss_total": 0.009878565557301044, "step": 43610 }, { "grad_norm": 0.33665579557418823, "learning_rate": 6.447427644044343e-05, "loss": 0.0122, "step": 43620 }, { "loss_action": 0.009349153377115726, "loss_total": 0.009349153377115726, "step": 43620 }, { "grad_norm": 0.25898581743240356, "learning_rate": 6.44584489273629e-05, "loss": 0.0114, "step": 43630 }, { "loss_action": 0.01206653006374836, "loss_total": 0.01206653006374836, "step": 43630 }, { "grad_norm": 0.27593615651130676, "learning_rate": 6.444261983312817e-05, "loss": 0.0124, "step": 43640 }, { "loss_action": 0.00963642168790102, "loss_total": 0.00963642168790102, "step": 43640 }, { "grad_norm": 0.3043556213378906, "learning_rate": 6.442678915947023e-05, "loss": 0.0114, "step": 43650 }, { "loss_action": 0.013867873698472977, "loss_total": 0.013867873698472977, "step": 43650 }, { "grad_norm": 0.2060505449771881, "learning_rate": 6.441095690812032e-05, "loss": 0.0127, "step": 43660 }, { "loss_action": 0.01352185383439064, "loss_total": 0.01352185383439064, "step": 43660 }, { "grad_norm": 0.2493772804737091, "learning_rate": 6.439512308080982e-05, "loss": 0.0104, "step": 43670 }, { "loss_action": 0.00894689466804266, "loss_total": 0.00894689466804266, "step": 43670 }, { "grad_norm": 0.2854400873184204, "learning_rate": 6.43792876792703e-05, "loss": 0.0107, "step": 43680 }, { "loss_action": 0.01131411176174879, "loss_total": 0.01131411176174879, "step": 43680 }, { "grad_norm": 0.28351667523384094, "learning_rate": 6.43634507052335e-05, "loss": 0.0122, "step": 43690 }, { "loss_action": 0.012401421554386616, "loss_total": 0.012401421554386616, "step": 43690 }, { "grad_norm": 0.32506853342056274, "learning_rate": 6.434761216043135e-05, "loss": 0.0121, "step": 43700 }, { "loss_action": 0.012015051208436489, "loss_total": 0.012015051208436489, "step": 43700 }, { "grad_norm": 0.23678900301456451, "learning_rate": 6.433177204659589e-05, "loss": 0.0135, "step": 43710 }, { "loss_action": 0.011724810115993023, "loss_total": 0.011724810115993023, "step": 43710 }, { "grad_norm": 0.23676107823848724, "learning_rate": 6.431593036545938e-05, "loss": 0.012, "step": 43720 }, { "loss_action": 0.00899919867515564, "loss_total": 0.00899919867515564, "step": 43720 }, { "grad_norm": 0.29988893866539, "learning_rate": 6.430008711875426e-05, "loss": 0.0137, "step": 43730 }, { "loss_action": 0.01088301744312048, "loss_total": 0.01088301744312048, "step": 43730 }, { "grad_norm": 0.26562148332595825, "learning_rate": 6.42842423082131e-05, "loss": 0.0123, "step": 43740 }, { "loss_action": 0.009945950470864773, "loss_total": 0.009945950470864773, "step": 43740 }, { "grad_norm": 0.2843274474143982, "learning_rate": 6.426839593556868e-05, "loss": 0.0115, "step": 43750 }, { "loss_action": 0.013889695517718792, "loss_total": 0.013889695517718792, "step": 43750 }, { "grad_norm": 0.34846174716949463, "learning_rate": 6.425254800255392e-05, "loss": 0.014, "step": 43760 }, { "loss_action": 0.012315635569393635, "loss_total": 0.012315635569393635, "step": 43760 }, { "grad_norm": 0.25559619069099426, "learning_rate": 6.423669851090196e-05, "loss": 0.0113, "step": 43770 }, { "loss_action": 0.013492869213223457, "loss_total": 0.013492869213223457, "step": 43770 }, { "grad_norm": 0.2512666881084442, "learning_rate": 6.422084746234604e-05, "loss": 0.0126, "step": 43780 }, { "loss_action": 0.009393060579895973, "loss_total": 0.009393060579895973, "step": 43780 }, { "grad_norm": 0.21747112274169922, "learning_rate": 6.420499485861965e-05, "loss": 0.0111, "step": 43790 }, { "loss_action": 0.013500780798494816, "loss_total": 0.013500780798494816, "step": 43790 }, { "grad_norm": 0.24456433951854706, "learning_rate": 6.418914070145636e-05, "loss": 0.0119, "step": 43800 }, { "loss_action": 0.009993243962526321, "loss_total": 0.009993243962526321, "step": 43800 }, { "grad_norm": 0.2706855535507202, "learning_rate": 6.417328499258996e-05, "loss": 0.014, "step": 43810 }, { "loss_action": 0.010647274553775787, "loss_total": 0.010647274553775787, "step": 43810 }, { "grad_norm": 0.36904582381248474, "learning_rate": 6.415742773375446e-05, "loss": 0.0121, "step": 43820 }, { "loss_action": 0.010216142982244492, "loss_total": 0.010216142982244492, "step": 43820 }, { "grad_norm": 0.29448312520980835, "learning_rate": 6.414156892668393e-05, "loss": 0.012, "step": 43830 }, { "loss_action": 0.011344448663294315, "loss_total": 0.011344448663294315, "step": 43830 }, { "grad_norm": 0.24535402655601501, "learning_rate": 6.412570857311267e-05, "loss": 0.0116, "step": 43840 }, { "loss_action": 0.013521673157811165, "loss_total": 0.013521673157811165, "step": 43840 }, { "grad_norm": 0.28296712040901184, "learning_rate": 6.410984667477518e-05, "loss": 0.012, "step": 43850 }, { "loss_action": 0.016894971951842308, "loss_total": 0.016894971951842308, "step": 43850 }, { "grad_norm": 0.21246285736560822, "learning_rate": 6.409398323340607e-05, "loss": 0.0132, "step": 43860 }, { "loss_action": 0.01712024211883545, "loss_total": 0.01712024211883545, "step": 43860 }, { "grad_norm": 0.28872421383857727, "learning_rate": 6.407811825074012e-05, "loss": 0.0121, "step": 43870 }, { "loss_action": 0.00899954792112112, "loss_total": 0.00899954792112112, "step": 43870 }, { "grad_norm": 0.24574677646160126, "learning_rate": 6.406225172851234e-05, "loss": 0.0112, "step": 43880 }, { "loss_action": 0.016313236206769943, "loss_total": 0.016313236206769943, "step": 43880 }, { "grad_norm": 0.32396766543388367, "learning_rate": 6.404638366845786e-05, "loss": 0.012, "step": 43890 }, { "loss_action": 0.009825886227190495, "loss_total": 0.009825886227190495, "step": 43890 }, { "grad_norm": 0.2607513964176178, "learning_rate": 6.403051407231196e-05, "loss": 0.0122, "step": 43900 }, { "loss_action": 0.01638718880712986, "loss_total": 0.01638718880712986, "step": 43900 }, { "grad_norm": 0.2712600529193878, "learning_rate": 6.401464294181016e-05, "loss": 0.0119, "step": 43910 }, { "loss_action": 0.010907956399023533, "loss_total": 0.010907956399023533, "step": 43910 }, { "grad_norm": 0.3118976950645447, "learning_rate": 6.399877027868808e-05, "loss": 0.0129, "step": 43920 }, { "loss_action": 0.01626233011484146, "loss_total": 0.01626233011484146, "step": 43920 }, { "grad_norm": 0.2597021162509918, "learning_rate": 6.39828960846815e-05, "loss": 0.0116, "step": 43930 }, { "loss_action": 0.008021866902709007, "loss_total": 0.008021866902709007, "step": 43930 }, { "grad_norm": 0.284486323595047, "learning_rate": 6.396702036152644e-05, "loss": 0.011, "step": 43940 }, { "loss_action": 0.012800832279026508, "loss_total": 0.012800832279026508, "step": 43940 }, { "grad_norm": 0.2850883901119232, "learning_rate": 6.395114311095905e-05, "loss": 0.0113, "step": 43950 }, { "loss_action": 0.012878821231424809, "loss_total": 0.012878821231424809, "step": 43950 }, { "grad_norm": 0.23874486982822418, "learning_rate": 6.393526433471559e-05, "loss": 0.0126, "step": 43960 }, { "loss_action": 0.007646788377314806, "loss_total": 0.007646788377314806, "step": 43960 }, { "grad_norm": 0.3263852596282959, "learning_rate": 6.391938403453262e-05, "loss": 0.0101, "step": 43970 }, { "loss_action": 0.013883058913052082, "loss_total": 0.013883058913052082, "step": 43970 }, { "grad_norm": 0.3147173821926117, "learning_rate": 6.390350221214671e-05, "loss": 0.0113, "step": 43980 }, { "loss_action": 0.00993286445736885, "loss_total": 0.00993286445736885, "step": 43980 }, { "grad_norm": 0.3219287395477295, "learning_rate": 6.38876188692947e-05, "loss": 0.0111, "step": 43990 }, { "loss_action": 0.009898249059915543, "loss_total": 0.009898249059915543, "step": 43990 }, { "grad_norm": 0.2521565854549408, "learning_rate": 6.387173400771358e-05, "loss": 0.0125, "step": 44000 }, { "loss_action": 0.01331681851297617, "loss_total": 0.01331681851297617, "step": 44000 }, { "grad_norm": 0.3150208592414856, "learning_rate": 6.385584762914047e-05, "loss": 0.0116, "step": 44010 }, { "loss_action": 0.009656906127929688, "loss_total": 0.009656906127929688, "step": 44010 }, { "grad_norm": 0.25044235587120056, "learning_rate": 6.38399597353127e-05, "loss": 0.0121, "step": 44020 }, { "loss_action": 0.009983323514461517, "loss_total": 0.009983323514461517, "step": 44020 }, { "grad_norm": 0.2588041126728058, "learning_rate": 6.382407032796775e-05, "loss": 0.0108, "step": 44030 }, { "loss_action": 0.009698834270238876, "loss_total": 0.009698834270238876, "step": 44030 }, { "grad_norm": 0.34074729681015015, "learning_rate": 6.380817940884325e-05, "loss": 0.0121, "step": 44040 }, { "loss_action": 0.018299315124750137, "loss_total": 0.018299315124750137, "step": 44040 }, { "grad_norm": 0.36927521228790283, "learning_rate": 6.379228697967702e-05, "loss": 0.0124, "step": 44050 }, { "loss_action": 0.014169212430715561, "loss_total": 0.014169212430715561, "step": 44050 }, { "grad_norm": 0.27921000123023987, "learning_rate": 6.3776393042207e-05, "loss": 0.0127, "step": 44060 }, { "loss_action": 0.011060666292905807, "loss_total": 0.011060666292905807, "step": 44060 }, { "grad_norm": 0.26894426345825195, "learning_rate": 6.376049759817137e-05, "loss": 0.0127, "step": 44070 }, { "loss_action": 0.013093573041260242, "loss_total": 0.013093573041260242, "step": 44070 }, { "grad_norm": 0.23067210614681244, "learning_rate": 6.37446006493084e-05, "loss": 0.0119, "step": 44080 }, { "loss_action": 0.010783419944345951, "loss_total": 0.010783419944345951, "step": 44080 }, { "grad_norm": 0.2838963270187378, "learning_rate": 6.372870219735656e-05, "loss": 0.0116, "step": 44090 }, { "loss_action": 0.013837127014994621, "loss_total": 0.013837127014994621, "step": 44090 }, { "grad_norm": 0.23024924099445343, "learning_rate": 6.371280224405452e-05, "loss": 0.0107, "step": 44100 }, { "loss_action": 0.01011163741350174, "loss_total": 0.01011163741350174, "step": 44100 }, { "grad_norm": 0.2080545276403427, "learning_rate": 6.369690079114101e-05, "loss": 0.0112, "step": 44110 }, { "loss_action": 0.010667813941836357, "loss_total": 0.010667813941836357, "step": 44110 }, { "grad_norm": 0.28771379590034485, "learning_rate": 6.368099784035504e-05, "loss": 0.0114, "step": 44120 }, { "loss_action": 0.007917307317256927, "loss_total": 0.007917307317256927, "step": 44120 }, { "grad_norm": 0.2721450924873352, "learning_rate": 6.366509339343572e-05, "loss": 0.0115, "step": 44130 }, { "loss_action": 0.011014931835234165, "loss_total": 0.011014931835234165, "step": 44130 }, { "grad_norm": 0.2306516170501709, "learning_rate": 6.364918745212232e-05, "loss": 0.0105, "step": 44140 }, { "loss_action": 0.007818220183253288, "loss_total": 0.007818220183253288, "step": 44140 }, { "grad_norm": 0.3090234398841858, "learning_rate": 6.363328001815431e-05, "loss": 0.0116, "step": 44150 }, { "loss_action": 0.012391767464578152, "loss_total": 0.012391767464578152, "step": 44150 }, { "grad_norm": 0.2638692557811737, "learning_rate": 6.361737109327128e-05, "loss": 0.0112, "step": 44160 }, { "loss_action": 0.011915155686438084, "loss_total": 0.011915155686438084, "step": 44160 }, { "grad_norm": 0.32999512553215027, "learning_rate": 6.360146067921301e-05, "loss": 0.0115, "step": 44170 }, { "loss_action": 0.009674208238720894, "loss_total": 0.009674208238720894, "step": 44170 }, { "grad_norm": 0.2799310088157654, "learning_rate": 6.35855487777195e-05, "loss": 0.0112, "step": 44180 }, { "loss_action": 0.010055244900286198, "loss_total": 0.010055244900286198, "step": 44180 }, { "grad_norm": 0.1907413899898529, "learning_rate": 6.356963539053076e-05, "loss": 0.0104, "step": 44190 }, { "loss_action": 0.008210256695747375, "loss_total": 0.008210256695747375, "step": 44190 }, { "grad_norm": 0.22179055213928223, "learning_rate": 6.355372051938711e-05, "loss": 0.0118, "step": 44200 }, { "loss_action": 0.011787599883973598, "loss_total": 0.011787599883973598, "step": 44200 }, { "grad_norm": 0.2884422540664673, "learning_rate": 6.353780416602894e-05, "loss": 0.0095, "step": 44210 }, { "loss_action": 0.0078527657315135, "loss_total": 0.0078527657315135, "step": 44210 }, { "grad_norm": 0.2730010747909546, "learning_rate": 6.352188633219689e-05, "loss": 0.0109, "step": 44220 }, { "loss_action": 0.010379948653280735, "loss_total": 0.010379948653280735, "step": 44220 }, { "grad_norm": 0.2672070860862732, "learning_rate": 6.350596701963166e-05, "loss": 0.0109, "step": 44230 }, { "loss_action": 0.013089737854897976, "loss_total": 0.013089737854897976, "step": 44230 }, { "grad_norm": 0.23990559577941895, "learning_rate": 6.349004623007419e-05, "loss": 0.0119, "step": 44240 }, { "loss_action": 0.013362694531679153, "loss_total": 0.013362694531679153, "step": 44240 }, { "grad_norm": 0.28574663400650024, "learning_rate": 6.347412396526555e-05, "loss": 0.0108, "step": 44250 }, { "loss_action": 0.012687833048403263, "loss_total": 0.012687833048403263, "step": 44250 }, { "grad_norm": 0.2966536283493042, "learning_rate": 6.345820022694696e-05, "loss": 0.0131, "step": 44260 }, { "loss_action": 0.014214696362614632, "loss_total": 0.014214696362614632, "step": 44260 }, { "grad_norm": 0.36780187487602234, "learning_rate": 6.344227501685984e-05, "loss": 0.0142, "step": 44270 }, { "loss_action": 0.01088883075863123, "loss_total": 0.01088883075863123, "step": 44270 }, { "grad_norm": 0.2653750479221344, "learning_rate": 6.342634833674572e-05, "loss": 0.0139, "step": 44280 }, { "loss_action": 0.010569360107183456, "loss_total": 0.010569360107183456, "step": 44280 }, { "grad_norm": 0.2909316122531891, "learning_rate": 6.341042018834635e-05, "loss": 0.0131, "step": 44290 }, { "loss_action": 0.010482157580554485, "loss_total": 0.010482157580554485, "step": 44290 }, { "grad_norm": 0.2803727686405182, "learning_rate": 6.339449057340359e-05, "loss": 0.0123, "step": 44300 }, { "loss_action": 0.020133651793003082, "loss_total": 0.020133651793003082, "step": 44300 }, { "grad_norm": 0.35894346237182617, "learning_rate": 6.337855949365945e-05, "loss": 0.0138, "step": 44310 }, { "loss_action": 0.014089600183069706, "loss_total": 0.014089600183069706, "step": 44310 }, { "grad_norm": 0.3475426733493805, "learning_rate": 6.336262695085619e-05, "loss": 0.0126, "step": 44320 }, { "loss_action": 0.014484403654932976, "loss_total": 0.014484403654932976, "step": 44320 }, { "grad_norm": 0.22146661579608917, "learning_rate": 6.334669294673612e-05, "loss": 0.012, "step": 44330 }, { "loss_action": 0.009586974047124386, "loss_total": 0.009586974047124386, "step": 44330 }, { "grad_norm": 0.30342257022857666, "learning_rate": 6.333075748304179e-05, "loss": 0.0121, "step": 44340 }, { "loss_action": 0.0093148248270154, "loss_total": 0.0093148248270154, "step": 44340 }, { "grad_norm": 0.3410448133945465, "learning_rate": 6.331482056151585e-05, "loss": 0.0126, "step": 44350 }, { "loss_action": 0.013333769515156746, "loss_total": 0.013333769515156746, "step": 44350 }, { "grad_norm": 0.2088581770658493, "learning_rate": 6.329888218390117e-05, "loss": 0.012, "step": 44360 }, { "loss_action": 0.010503615252673626, "loss_total": 0.010503615252673626, "step": 44360 }, { "grad_norm": 0.24884146451950073, "learning_rate": 6.328294235194072e-05, "loss": 0.0123, "step": 44370 }, { "loss_action": 0.01168372854590416, "loss_total": 0.01168372854590416, "step": 44370 }, { "grad_norm": 0.268032431602478, "learning_rate": 6.326700106737765e-05, "loss": 0.012, "step": 44380 }, { "loss_action": 0.010589639656245708, "loss_total": 0.010589639656245708, "step": 44380 }, { "grad_norm": 0.2803821563720703, "learning_rate": 6.325105833195531e-05, "loss": 0.0114, "step": 44390 }, { "loss_action": 0.010526425205171108, "loss_total": 0.010526425205171108, "step": 44390 }, { "grad_norm": 0.3147627115249634, "learning_rate": 6.323511414741715e-05, "loss": 0.0126, "step": 44400 }, { "loss_action": 0.01062700618058443, "loss_total": 0.01062700618058443, "step": 44400 }, { "grad_norm": 0.31531012058258057, "learning_rate": 6.321916851550678e-05, "loss": 0.0111, "step": 44410 }, { "loss_action": 0.013669345527887344, "loss_total": 0.013669345527887344, "step": 44410 }, { "grad_norm": 0.25741854310035706, "learning_rate": 6.320322143796806e-05, "loss": 0.0119, "step": 44420 }, { "loss_action": 0.015793103724718094, "loss_total": 0.015793103724718094, "step": 44420 }, { "grad_norm": 0.24261145293712616, "learning_rate": 6.318727291654488e-05, "loss": 0.0134, "step": 44430 }, { "loss_action": 0.014657660387456417, "loss_total": 0.014657660387456417, "step": 44430 }, { "grad_norm": 0.3777276277542114, "learning_rate": 6.317132295298134e-05, "loss": 0.0129, "step": 44440 }, { "loss_action": 0.015372280962765217, "loss_total": 0.015372280962765217, "step": 44440 }, { "grad_norm": 0.2284580022096634, "learning_rate": 6.315537154902173e-05, "loss": 0.0128, "step": 44450 }, { "loss_action": 0.010412408038973808, "loss_total": 0.010412408038973808, "step": 44450 }, { "grad_norm": 0.3091317415237427, "learning_rate": 6.313941870641048e-05, "loss": 0.0116, "step": 44460 }, { "loss_action": 0.015944218263030052, "loss_total": 0.015944218263030052, "step": 44460 }, { "grad_norm": 0.2741259038448334, "learning_rate": 6.312346442689214e-05, "loss": 0.0113, "step": 44470 }, { "loss_action": 0.00900720339268446, "loss_total": 0.00900720339268446, "step": 44470 }, { "grad_norm": 0.29422780871391296, "learning_rate": 6.310750871221147e-05, "loss": 0.0125, "step": 44480 }, { "loss_action": 0.011206529103219509, "loss_total": 0.011206529103219509, "step": 44480 }, { "grad_norm": 0.2437821328639984, "learning_rate": 6.309155156411335e-05, "loss": 0.0105, "step": 44490 }, { "loss_action": 0.010663471184670925, "loss_total": 0.010663471184670925, "step": 44490 }, { "grad_norm": 0.26345953345298767, "learning_rate": 6.307559298434284e-05, "loss": 0.0107, "step": 44500 }, { "loss_action": 0.010153079405426979, "loss_total": 0.010153079405426979, "step": 44500 }, { "grad_norm": 0.267657607793808, "learning_rate": 6.305963297464512e-05, "loss": 0.012, "step": 44510 }, { "loss_action": 0.01138948556035757, "loss_total": 0.01138948556035757, "step": 44510 }, { "grad_norm": 0.2659659683704376, "learning_rate": 6.304367153676561e-05, "loss": 0.0118, "step": 44520 }, { "loss_action": 0.011886285617947578, "loss_total": 0.011886285617947578, "step": 44520 }, { "grad_norm": 0.2901092767715454, "learning_rate": 6.302770867244978e-05, "loss": 0.0115, "step": 44530 }, { "loss_action": 0.009104205295443535, "loss_total": 0.009104205295443535, "step": 44530 }, { "grad_norm": 0.27533432841300964, "learning_rate": 6.301174438344328e-05, "loss": 0.0128, "step": 44540 }, { "loss_action": 0.011734907515347004, "loss_total": 0.011734907515347004, "step": 44540 }, { "grad_norm": 0.4083403944969177, "learning_rate": 6.299577867149202e-05, "loss": 0.0137, "step": 44550 }, { "loss_action": 0.014905141666531563, "loss_total": 0.014905141666531563, "step": 44550 }, { "grad_norm": 0.2654007077217102, "learning_rate": 6.297981153834192e-05, "loss": 0.0119, "step": 44560 }, { "loss_action": 0.013031452894210815, "loss_total": 0.013031452894210815, "step": 44560 }, { "grad_norm": 0.2665664255619049, "learning_rate": 6.296384298573916e-05, "loss": 0.0126, "step": 44570 }, { "loss_action": 0.01655644364655018, "loss_total": 0.01655644364655018, "step": 44570 }, { "grad_norm": 0.2490759938955307, "learning_rate": 6.294787301543001e-05, "loss": 0.0105, "step": 44580 }, { "loss_action": 0.011415868066251278, "loss_total": 0.011415868066251278, "step": 44580 }, { "grad_norm": 0.32214638590812683, "learning_rate": 6.293190162916095e-05, "loss": 0.0121, "step": 44590 }, { "loss_action": 0.013947248458862305, "loss_total": 0.013947248458862305, "step": 44590 }, { "grad_norm": 0.2603861689567566, "learning_rate": 6.291592882867855e-05, "loss": 0.0125, "step": 44600 }, { "loss_action": 0.015260954387485981, "loss_total": 0.015260954387485981, "step": 44600 }, { "grad_norm": 0.2761635184288025, "learning_rate": 6.28999546157296e-05, "loss": 0.0129, "step": 44610 }, { "loss_action": 0.008782207034528255, "loss_total": 0.008782207034528255, "step": 44610 }, { "grad_norm": 0.2902791500091553, "learning_rate": 6.288397899206102e-05, "loss": 0.0154, "step": 44620 }, { "loss_action": 0.012920377776026726, "loss_total": 0.012920377776026726, "step": 44620 }, { "grad_norm": 0.30765852332115173, "learning_rate": 6.286800195941984e-05, "loss": 0.0149, "step": 44630 }, { "loss_action": 0.014039545319974422, "loss_total": 0.014039545319974422, "step": 44630 }, { "grad_norm": 0.23591762781143188, "learning_rate": 6.285202351955334e-05, "loss": 0.0128, "step": 44640 }, { "loss_action": 0.011699657887220383, "loss_total": 0.011699657887220383, "step": 44640 }, { "grad_norm": 0.28652194142341614, "learning_rate": 6.283604367420887e-05, "loss": 0.0131, "step": 44650 }, { "loss_action": 0.010135025717318058, "loss_total": 0.010135025717318058, "step": 44650 }, { "grad_norm": 0.20634713768959045, "learning_rate": 6.282006242513394e-05, "loss": 0.0099, "step": 44660 }, { "loss_action": 0.01076751109212637, "loss_total": 0.01076751109212637, "step": 44660 }, { "grad_norm": 0.18329131603240967, "learning_rate": 6.280407977407628e-05, "loss": 0.012, "step": 44670 }, { "loss_action": 0.013532353565096855, "loss_total": 0.013532353565096855, "step": 44670 }, { "grad_norm": 0.21091045439243317, "learning_rate": 6.27880957227837e-05, "loss": 0.0109, "step": 44680 }, { "loss_action": 0.009517294354736805, "loss_total": 0.009517294354736805, "step": 44680 }, { "grad_norm": 0.2806568741798401, "learning_rate": 6.27721102730042e-05, "loss": 0.0113, "step": 44690 }, { "loss_action": 0.010386346839368343, "loss_total": 0.010386346839368343, "step": 44690 }, { "grad_norm": 0.2502046227455139, "learning_rate": 6.275612342648592e-05, "loss": 0.011, "step": 44700 }, { "loss_action": 0.010661758482456207, "loss_total": 0.010661758482456207, "step": 44700 }, { "grad_norm": 0.5389909148216248, "learning_rate": 6.274013518497716e-05, "loss": 0.0102, "step": 44710 }, { "loss_action": 0.012328249402344227, "loss_total": 0.012328249402344227, "step": 44710 }, { "grad_norm": 0.4298517405986786, "learning_rate": 6.272414555022636e-05, "loss": 0.015, "step": 44720 }, { "loss_action": 0.014676774851977825, "loss_total": 0.014676774851977825, "step": 44720 }, { "grad_norm": 0.420747309923172, "learning_rate": 6.270815452398215e-05, "loss": 0.0135, "step": 44730 }, { "loss_action": 0.014062825590372086, "loss_total": 0.014062825590372086, "step": 44730 }, { "grad_norm": 0.2672099471092224, "learning_rate": 6.269216210799326e-05, "loss": 0.0123, "step": 44740 }, { "loss_action": 0.019350381568074226, "loss_total": 0.019350381568074226, "step": 44740 }, { "grad_norm": 0.2950603663921356, "learning_rate": 6.26761683040086e-05, "loss": 0.0128, "step": 44750 }, { "loss_action": 0.00933634489774704, "loss_total": 0.00933634489774704, "step": 44750 }, { "grad_norm": 0.36170637607574463, "learning_rate": 6.266017311377723e-05, "loss": 0.0109, "step": 44760 }, { "loss_action": 0.009425632655620575, "loss_total": 0.009425632655620575, "step": 44760 }, { "grad_norm": 0.2871427536010742, "learning_rate": 6.264417653904839e-05, "loss": 0.013, "step": 44770 }, { "loss_action": 0.01026763953268528, "loss_total": 0.01026763953268528, "step": 44770 }, { "grad_norm": 0.3117161989212036, "learning_rate": 6.262817858157139e-05, "loss": 0.0137, "step": 44780 }, { "loss_action": 0.010974041186273098, "loss_total": 0.010974041186273098, "step": 44780 }, { "grad_norm": 0.27147138118743896, "learning_rate": 6.261217924309576e-05, "loss": 0.012, "step": 44790 }, { "loss_action": 0.011273860931396484, "loss_total": 0.011273860931396484, "step": 44790 }, { "grad_norm": 0.28221800923347473, "learning_rate": 6.259617852537118e-05, "loss": 0.0118, "step": 44800 }, { "loss_action": 0.009654399007558823, "loss_total": 0.009654399007558823, "step": 44800 }, { "grad_norm": 0.3344346284866333, "learning_rate": 6.258017643014747e-05, "loss": 0.0111, "step": 44810 }, { "loss_action": 0.01016371138393879, "loss_total": 0.01016371138393879, "step": 44810 }, { "grad_norm": 0.25048890709877014, "learning_rate": 6.256417295917456e-05, "loss": 0.0105, "step": 44820 }, { "loss_action": 0.010687647387385368, "loss_total": 0.010687647387385368, "step": 44820 }, { "grad_norm": 0.2649870216846466, "learning_rate": 6.254816811420258e-05, "loss": 0.0109, "step": 44830 }, { "loss_action": 0.008000907488167286, "loss_total": 0.008000907488167286, "step": 44830 }, { "grad_norm": 0.24730025231838226, "learning_rate": 6.253216189698183e-05, "loss": 0.01, "step": 44840 }, { "loss_action": 0.009465735405683517, "loss_total": 0.009465735405683517, "step": 44840 }, { "grad_norm": 0.26217320561408997, "learning_rate": 6.251615430926267e-05, "loss": 0.01, "step": 44850 }, { "loss_action": 0.009495335631072521, "loss_total": 0.009495335631072521, "step": 44850 }, { "grad_norm": 0.26821985840797424, "learning_rate": 6.25001453527957e-05, "loss": 0.0115, "step": 44860 }, { "loss_action": 0.01139396894723177, "loss_total": 0.01139396894723177, "step": 44860 }, { "grad_norm": 0.2735568583011627, "learning_rate": 6.248413502933164e-05, "loss": 0.0106, "step": 44870 }, { "loss_action": 0.008644815534353256, "loss_total": 0.008644815534353256, "step": 44870 }, { "grad_norm": 0.23534099757671356, "learning_rate": 6.246812334062133e-05, "loss": 0.0116, "step": 44880 }, { "loss_action": 0.010342065244913101, "loss_total": 0.010342065244913101, "step": 44880 }, { "grad_norm": 0.3959859609603882, "learning_rate": 6.245211028841579e-05, "loss": 0.0127, "step": 44890 }, { "loss_action": 0.011906429193913937, "loss_total": 0.011906429193913937, "step": 44890 }, { "grad_norm": 0.26227468252182007, "learning_rate": 6.24360958744662e-05, "loss": 0.0131, "step": 44900 }, { "loss_action": 0.01532752439379692, "loss_total": 0.01532752439379692, "step": 44900 }, { "grad_norm": 0.292745441198349, "learning_rate": 6.242008010052387e-05, "loss": 0.0126, "step": 44910 }, { "loss_action": 0.012125276029109955, "loss_total": 0.012125276029109955, "step": 44910 }, { "grad_norm": 0.25320762395858765, "learning_rate": 6.240406296834024e-05, "loss": 0.0107, "step": 44920 }, { "loss_action": 0.012416473589837551, "loss_total": 0.012416473589837551, "step": 44920 }, { "grad_norm": 0.2742709219455719, "learning_rate": 6.238804447966694e-05, "loss": 0.0104, "step": 44930 }, { "loss_action": 0.00989654753357172, "loss_total": 0.00989654753357172, "step": 44930 }, { "grad_norm": 0.22682888805866241, "learning_rate": 6.237202463625573e-05, "loss": 0.0134, "step": 44940 }, { "loss_action": 0.008322185836732388, "loss_total": 0.008322185836732388, "step": 44940 }, { "grad_norm": 0.30058708786964417, "learning_rate": 6.235600343985848e-05, "loss": 0.0102, "step": 44950 }, { "loss_action": 0.011050700210034847, "loss_total": 0.011050700210034847, "step": 44950 }, { "grad_norm": 0.26271846890449524, "learning_rate": 6.233998089222729e-05, "loss": 0.011, "step": 44960 }, { "loss_action": 0.013290522620081902, "loss_total": 0.013290522620081902, "step": 44960 }, { "grad_norm": 0.29862311482429504, "learning_rate": 6.232395699511433e-05, "loss": 0.0127, "step": 44970 }, { "loss_action": 0.010218660347163677, "loss_total": 0.010218660347163677, "step": 44970 }, { "grad_norm": 0.3591204583644867, "learning_rate": 6.230793175027199e-05, "loss": 0.013, "step": 44980 }, { "loss_action": 0.013585754670202732, "loss_total": 0.013585754670202732, "step": 44980 }, { "grad_norm": 0.24148622155189514, "learning_rate": 6.22919051594527e-05, "loss": 0.012, "step": 44990 }, { "loss_action": 0.010754372924566269, "loss_total": 0.010754372924566269, "step": 44990 }, { "grad_norm": 0.218675896525383, "learning_rate": 6.227587722440917e-05, "loss": 0.0105, "step": 45000 }, { "loss_action": 0.009252653457224369, "loss_total": 0.009252653457224369, "step": 45000 }, { "grad_norm": 0.27569860219955444, "learning_rate": 6.225984794689414e-05, "loss": 0.0116, "step": 45010 }, { "loss_action": 0.012047206982970238, "loss_total": 0.012047206982970238, "step": 45010 }, { "grad_norm": 0.2822090685367584, "learning_rate": 6.22438173286606e-05, "loss": 0.0112, "step": 45020 }, { "loss_action": 0.009667141363024712, "loss_total": 0.009667141363024712, "step": 45020 }, { "grad_norm": 0.3720133900642395, "learning_rate": 6.222778537146159e-05, "loss": 0.0126, "step": 45030 }, { "loss_action": 0.008415436372160912, "loss_total": 0.008415436372160912, "step": 45030 }, { "grad_norm": 0.2690768241882324, "learning_rate": 6.221175207705037e-05, "loss": 0.0106, "step": 45040 }, { "loss_action": 0.01023851428180933, "loss_total": 0.01023851428180933, "step": 45040 }, { "grad_norm": 0.3448449969291687, "learning_rate": 6.219571744718027e-05, "loss": 0.0114, "step": 45050 }, { "loss_action": 0.011798353865742683, "loss_total": 0.011798353865742683, "step": 45050 }, { "grad_norm": 0.2626810669898987, "learning_rate": 6.217968148360487e-05, "loss": 0.0115, "step": 45060 }, { "loss_action": 0.0116190230473876, "loss_total": 0.0116190230473876, "step": 45060 }, { "grad_norm": 0.2280064970254898, "learning_rate": 6.216364418807782e-05, "loss": 0.0113, "step": 45070 }, { "loss_action": 0.009884189814329147, "loss_total": 0.009884189814329147, "step": 45070 }, { "grad_norm": 0.31776610016822815, "learning_rate": 6.214760556235292e-05, "loss": 0.0118, "step": 45080 }, { "loss_action": 0.010189896449446678, "loss_total": 0.010189896449446678, "step": 45080 }, { "grad_norm": 0.3222619295120239, "learning_rate": 6.213156560818414e-05, "loss": 0.0102, "step": 45090 }, { "loss_action": 0.009762243367731571, "loss_total": 0.009762243367731571, "step": 45090 }, { "grad_norm": 0.2221035361289978, "learning_rate": 6.211552432732559e-05, "loss": 0.0106, "step": 45100 }, { "loss_action": 0.016530701890587807, "loss_total": 0.016530701890587807, "step": 45100 }, { "grad_norm": 0.308331698179245, "learning_rate": 6.20994817215315e-05, "loss": 0.0114, "step": 45110 }, { "loss_action": 0.00953962653875351, "loss_total": 0.00953962653875351, "step": 45110 }, { "grad_norm": 0.2562774419784546, "learning_rate": 6.208343779255628e-05, "loss": 0.0135, "step": 45120 }, { "loss_action": 0.01272556185722351, "loss_total": 0.01272556185722351, "step": 45120 }, { "grad_norm": 0.293038547039032, "learning_rate": 6.206739254215449e-05, "loss": 0.0131, "step": 45130 }, { "loss_action": 0.00899803452193737, "loss_total": 0.00899803452193737, "step": 45130 }, { "grad_norm": 0.2586999535560608, "learning_rate": 6.205134597208077e-05, "loss": 0.0102, "step": 45140 }, { "loss_action": 0.010346298106014729, "loss_total": 0.010346298106014729, "step": 45140 }, { "grad_norm": 0.2817195653915405, "learning_rate": 6.203529808409e-05, "loss": 0.0104, "step": 45150 }, { "loss_action": 0.010734654031693935, "loss_total": 0.010734654031693935, "step": 45150 }, { "grad_norm": 0.2556106448173523, "learning_rate": 6.201924887993712e-05, "loss": 0.0118, "step": 45160 }, { "loss_action": 0.011626267805695534, "loss_total": 0.011626267805695534, "step": 45160 }, { "grad_norm": 0.2857128977775574, "learning_rate": 6.200319836137725e-05, "loss": 0.0128, "step": 45170 }, { "loss_action": 0.011836644262075424, "loss_total": 0.011836644262075424, "step": 45170 }, { "grad_norm": 0.2648274004459381, "learning_rate": 6.198714653016565e-05, "loss": 0.0114, "step": 45180 }, { "loss_action": 0.011446735821664333, "loss_total": 0.011446735821664333, "step": 45180 }, { "grad_norm": 0.25777339935302734, "learning_rate": 6.197109338805774e-05, "loss": 0.0141, "step": 45190 }, { "loss_action": 0.01422492042183876, "loss_total": 0.01422492042183876, "step": 45190 }, { "grad_norm": 0.2601330876350403, "learning_rate": 6.195503893680903e-05, "loss": 0.0121, "step": 45200 }, { "loss_action": 0.01388784870505333, "loss_total": 0.01388784870505333, "step": 45200 }, { "grad_norm": 0.26439759135246277, "learning_rate": 6.193898317817524e-05, "loss": 0.0126, "step": 45210 }, { "loss_action": 0.01690000481903553, "loss_total": 0.01690000481903553, "step": 45210 }, { "grad_norm": 0.24979284405708313, "learning_rate": 6.192292611391221e-05, "loss": 0.0124, "step": 45220 }, { "loss_action": 0.013488487340509892, "loss_total": 0.013488487340509892, "step": 45220 }, { "grad_norm": 0.24183771014213562, "learning_rate": 6.190686774577591e-05, "loss": 0.0118, "step": 45230 }, { "loss_action": 0.009819352999329567, "loss_total": 0.009819352999329567, "step": 45230 }, { "grad_norm": 0.2791791558265686, "learning_rate": 6.189080807552245e-05, "loss": 0.0119, "step": 45240 }, { "loss_action": 0.01065524760633707, "loss_total": 0.01065524760633707, "step": 45240 }, { "grad_norm": 0.20910988748073578, "learning_rate": 6.187474710490809e-05, "loss": 0.0098, "step": 45250 }, { "loss_action": 0.01168038323521614, "loss_total": 0.01168038323521614, "step": 45250 }, { "grad_norm": 0.23803111910820007, "learning_rate": 6.185868483568926e-05, "loss": 0.011, "step": 45260 }, { "loss_action": 0.009020483121275902, "loss_total": 0.009020483121275902, "step": 45260 }, { "grad_norm": 0.2900485098361969, "learning_rate": 6.184262126962245e-05, "loss": 0.0112, "step": 45270 }, { "loss_action": 0.011890994384884834, "loss_total": 0.011890994384884834, "step": 45270 }, { "grad_norm": 0.252655029296875, "learning_rate": 6.182655640846442e-05, "loss": 0.012, "step": 45280 }, { "loss_action": 0.015001477673649788, "loss_total": 0.015001477673649788, "step": 45280 }, { "grad_norm": 0.2581844627857208, "learning_rate": 6.181049025397196e-05, "loss": 0.0121, "step": 45290 }, { "loss_action": 0.012171034701168537, "loss_total": 0.012171034701168537, "step": 45290 }, { "grad_norm": 0.31717896461486816, "learning_rate": 6.179442280790202e-05, "loss": 0.0119, "step": 45300 }, { "loss_action": 0.011220462620258331, "loss_total": 0.011220462620258331, "step": 45300 }, { "grad_norm": 0.24495819211006165, "learning_rate": 6.177835407201174e-05, "loss": 0.0104, "step": 45310 }, { "loss_action": 0.012863713316619396, "loss_total": 0.012863713316619396, "step": 45310 }, { "grad_norm": 0.2995709478855133, "learning_rate": 6.176228404805839e-05, "loss": 0.0113, "step": 45320 }, { "loss_action": 0.007748125120997429, "loss_total": 0.007748125120997429, "step": 45320 }, { "grad_norm": 0.26076313853263855, "learning_rate": 6.174621273779932e-05, "loss": 0.0109, "step": 45330 }, { "loss_action": 0.015756215900182724, "loss_total": 0.015756215900182724, "step": 45330 }, { "grad_norm": 0.2884814143180847, "learning_rate": 6.17301401429921e-05, "loss": 0.0112, "step": 45340 }, { "loss_action": 0.010875447653234005, "loss_total": 0.010875447653234005, "step": 45340 }, { "grad_norm": 0.27811601758003235, "learning_rate": 6.171406626539436e-05, "loss": 0.0132, "step": 45350 }, { "loss_action": 0.009301133453845978, "loss_total": 0.009301133453845978, "step": 45350 }, { "grad_norm": 0.27743253111839294, "learning_rate": 6.169799110676398e-05, "loss": 0.0115, "step": 45360 }, { "loss_action": 0.016088752076029778, "loss_total": 0.016088752076029778, "step": 45360 }, { "grad_norm": 0.2690819501876831, "learning_rate": 6.168191466885885e-05, "loss": 0.0115, "step": 45370 }, { "loss_action": 0.008474769070744514, "loss_total": 0.008474769070744514, "step": 45370 }, { "grad_norm": 0.26589590311050415, "learning_rate": 6.166583695343711e-05, "loss": 0.0113, "step": 45380 }, { "loss_action": 0.011386094614863396, "loss_total": 0.011386094614863396, "step": 45380 }, { "grad_norm": 0.2490507811307907, "learning_rate": 6.164975796225698e-05, "loss": 0.0108, "step": 45390 }, { "loss_action": 0.014102030545473099, "loss_total": 0.014102030545473099, "step": 45390 }, { "grad_norm": 0.21173135936260223, "learning_rate": 6.163367769707683e-05, "loss": 0.0099, "step": 45400 }, { "loss_action": 0.012671454809606075, "loss_total": 0.012671454809606075, "step": 45400 }, { "grad_norm": 0.2705904543399811, "learning_rate": 6.161759615965519e-05, "loss": 0.0104, "step": 45410 }, { "loss_action": 0.009116594679653645, "loss_total": 0.009116594679653645, "step": 45410 }, { "grad_norm": 0.22250348329544067, "learning_rate": 6.16015133517507e-05, "loss": 0.0107, "step": 45420 }, { "loss_action": 0.010318583808839321, "loss_total": 0.010318583808839321, "step": 45420 }, { "grad_norm": 0.3017977476119995, "learning_rate": 6.158542927512214e-05, "loss": 0.0115, "step": 45430 }, { "loss_action": 0.011096563190221786, "loss_total": 0.011096563190221786, "step": 45430 }, { "grad_norm": 0.30198466777801514, "learning_rate": 6.156934393152846e-05, "loss": 0.0099, "step": 45440 }, { "loss_action": 0.009448982775211334, "loss_total": 0.009448982775211334, "step": 45440 }, { "grad_norm": 0.23726201057434082, "learning_rate": 6.15532573227287e-05, "loss": 0.0104, "step": 45450 }, { "loss_action": 0.009559154510498047, "loss_total": 0.009559154510498047, "step": 45450 }, { "grad_norm": 0.25005239248275757, "learning_rate": 6.153716945048212e-05, "loss": 0.0099, "step": 45460 }, { "loss_action": 0.014892102219164371, "loss_total": 0.014892102219164371, "step": 45460 }, { "grad_norm": 0.2276957482099533, "learning_rate": 6.152108031654802e-05, "loss": 0.0111, "step": 45470 }, { "loss_action": 0.011196275241672993, "loss_total": 0.011196275241672993, "step": 45470 }, { "grad_norm": 0.26735439896583557, "learning_rate": 6.15049899226859e-05, "loss": 0.013, "step": 45480 }, { "loss_action": 0.014932038262486458, "loss_total": 0.014932038262486458, "step": 45480 }, { "grad_norm": 0.2469751089811325, "learning_rate": 6.148889827065537e-05, "loss": 0.012, "step": 45490 }, { "loss_action": 0.01019843015819788, "loss_total": 0.01019843015819788, "step": 45490 }, { "grad_norm": 0.24005736410617828, "learning_rate": 6.147280536221622e-05, "loss": 0.0115, "step": 45500 }, { "loss_action": 0.01056481059640646, "loss_total": 0.01056481059640646, "step": 45500 }, { "grad_norm": 0.3388117849826813, "learning_rate": 6.145671119912832e-05, "loss": 0.0104, "step": 45510 }, { "loss_action": 0.010597225278615952, "loss_total": 0.010597225278615952, "step": 45510 }, { "grad_norm": 0.31086206436157227, "learning_rate": 6.144061578315169e-05, "loss": 0.0127, "step": 45520 }, { "loss_action": 0.00908188708126545, "loss_total": 0.00908188708126545, "step": 45520 }, { "grad_norm": 0.3123098909854889, "learning_rate": 6.142451911604654e-05, "loss": 0.0105, "step": 45530 }, { "loss_action": 0.009326950646936893, "loss_total": 0.009326950646936893, "step": 45530 }, { "grad_norm": 0.33952009677886963, "learning_rate": 6.140842119957315e-05, "loss": 0.012, "step": 45540 }, { "loss_action": 0.008436603471636772, "loss_total": 0.008436603471636772, "step": 45540 }, { "grad_norm": 0.33877184987068176, "learning_rate": 6.139232203549197e-05, "loss": 0.0107, "step": 45550 }, { "loss_action": 0.00985513161867857, "loss_total": 0.00985513161867857, "step": 45550 }, { "grad_norm": 0.3168375492095947, "learning_rate": 6.137622162556357e-05, "loss": 0.011, "step": 45560 }, { "loss_action": 0.010132230818271637, "loss_total": 0.010132230818271637, "step": 45560 }, { "grad_norm": 0.29474684596061707, "learning_rate": 6.13601199715487e-05, "loss": 0.0114, "step": 45570 }, { "loss_action": 0.009395631030201912, "loss_total": 0.009395631030201912, "step": 45570 }, { "grad_norm": 0.22011029720306396, "learning_rate": 6.134401707520816e-05, "loss": 0.0109, "step": 45580 }, { "loss_action": 0.011778050102293491, "loss_total": 0.011778050102293491, "step": 45580 }, { "grad_norm": 0.3194519877433777, "learning_rate": 6.132791293830298e-05, "loss": 0.0109, "step": 45590 }, { "loss_action": 0.010698669590055943, "loss_total": 0.010698669590055943, "step": 45590 }, { "grad_norm": 0.24638402462005615, "learning_rate": 6.131180756259428e-05, "loss": 0.0117, "step": 45600 }, { "loss_action": 0.009442358277738094, "loss_total": 0.009442358277738094, "step": 45600 }, { "grad_norm": 0.3210780620574951, "learning_rate": 6.129570094984331e-05, "loss": 0.0123, "step": 45610 }, { "loss_action": 0.016132459044456482, "loss_total": 0.016132459044456482, "step": 45610 }, { "grad_norm": 0.38746631145477295, "learning_rate": 6.127959310181145e-05, "loss": 0.0122, "step": 45620 }, { "loss_action": 0.011098992079496384, "loss_total": 0.011098992079496384, "step": 45620 }, { "grad_norm": 0.2666413187980652, "learning_rate": 6.126348402026026e-05, "loss": 0.0111, "step": 45630 }, { "loss_action": 0.010657609440386295, "loss_total": 0.010657609440386295, "step": 45630 }, { "grad_norm": 0.31122010946273804, "learning_rate": 6.12473737069514e-05, "loss": 0.0117, "step": 45640 }, { "loss_action": 0.010799456387758255, "loss_total": 0.010799456387758255, "step": 45640 }, { "grad_norm": 0.2657119035720825, "learning_rate": 6.123126216364665e-05, "loss": 0.0118, "step": 45650 }, { "loss_action": 0.011930749751627445, "loss_total": 0.011930749751627445, "step": 45650 }, { "grad_norm": 0.2587200701236725, "learning_rate": 6.121514939210797e-05, "loss": 0.012, "step": 45660 }, { "loss_action": 0.018946103751659393, "loss_total": 0.018946103751659393, "step": 45660 }, { "grad_norm": 0.23338226974010468, "learning_rate": 6.119903539409741e-05, "loss": 0.0108, "step": 45670 }, { "loss_action": 0.012496151961386204, "loss_total": 0.012496151961386204, "step": 45670 }, { "grad_norm": 0.257767915725708, "learning_rate": 6.118292017137716e-05, "loss": 0.0113, "step": 45680 }, { "loss_action": 0.012361758388578892, "loss_total": 0.012361758388578892, "step": 45680 }, { "grad_norm": 0.3662796914577484, "learning_rate": 6.116680372570959e-05, "loss": 0.0129, "step": 45690 }, { "loss_action": 0.011988865211606026, "loss_total": 0.011988865211606026, "step": 45690 }, { "grad_norm": 0.3287593424320221, "learning_rate": 6.115068605885713e-05, "loss": 0.0134, "step": 45700 }, { "loss_action": 0.01284189336001873, "loss_total": 0.01284189336001873, "step": 45700 }, { "grad_norm": 0.2713126540184021, "learning_rate": 6.113456717258243e-05, "loss": 0.0133, "step": 45710 }, { "loss_action": 0.012553621083498001, "loss_total": 0.012553621083498001, "step": 45710 }, { "grad_norm": 0.2515110969543457, "learning_rate": 6.11184470686482e-05, "loss": 0.0133, "step": 45720 }, { "loss_action": 0.012639911845326424, "loss_total": 0.012639911845326424, "step": 45720 }, { "grad_norm": 0.28236091136932373, "learning_rate": 6.110232574881731e-05, "loss": 0.0109, "step": 45730 }, { "loss_action": 0.00923688430339098, "loss_total": 0.00923688430339098, "step": 45730 }, { "grad_norm": 0.23966754972934723, "learning_rate": 6.108620321485277e-05, "loss": 0.0125, "step": 45740 }, { "loss_action": 0.013923699036240578, "loss_total": 0.013923699036240578, "step": 45740 }, { "grad_norm": 0.30284133553504944, "learning_rate": 6.107007946851773e-05, "loss": 0.0123, "step": 45750 }, { "loss_action": 0.00818578153848648, "loss_total": 0.00818578153848648, "step": 45750 }, { "grad_norm": 0.2992236018180847, "learning_rate": 6.105395451157542e-05, "loss": 0.0121, "step": 45760 }, { "loss_action": 0.011346757411956787, "loss_total": 0.011346757411956787, "step": 45760 }, { "grad_norm": 0.23894265294075012, "learning_rate": 6.103782834578928e-05, "loss": 0.0104, "step": 45770 }, { "loss_action": 0.010226194746792316, "loss_total": 0.010226194746792316, "step": 45770 }, { "grad_norm": 0.25973501801490784, "learning_rate": 6.102170097292281e-05, "loss": 0.0116, "step": 45780 }, { "loss_action": 0.007684322539716959, "loss_total": 0.007684322539716959, "step": 45780 }, { "grad_norm": 0.22864510118961334, "learning_rate": 6.1005572394739716e-05, "loss": 0.0112, "step": 45790 }, { "loss_action": 0.008615046739578247, "loss_total": 0.008615046739578247, "step": 45790 }, { "grad_norm": 0.2477654069662094, "learning_rate": 6.0989442613003765e-05, "loss": 0.0118, "step": 45800 }, { "loss_action": 0.008318609558045864, "loss_total": 0.008318609558045864, "step": 45800 }, { "grad_norm": 0.3808705806732178, "learning_rate": 6.097331162947888e-05, "loss": 0.0106, "step": 45810 }, { "loss_action": 0.01193000003695488, "loss_total": 0.01193000003695488, "step": 45810 }, { "grad_norm": 0.22232887148857117, "learning_rate": 6.095717944592914e-05, "loss": 0.0112, "step": 45820 }, { "loss_action": 0.022098729386925697, "loss_total": 0.022098729386925697, "step": 45820 }, { "grad_norm": 0.23103231191635132, "learning_rate": 6.094104606411873e-05, "loss": 0.012, "step": 45830 }, { "loss_action": 0.010477342642843723, "loss_total": 0.010477342642843723, "step": 45830 }, { "grad_norm": 0.3312370479106903, "learning_rate": 6.0924911485811966e-05, "loss": 0.011, "step": 45840 }, { "loss_action": 0.008782767690718174, "loss_total": 0.008782767690718174, "step": 45840 }, { "grad_norm": 0.22331887483596802, "learning_rate": 6.090877571277331e-05, "loss": 0.0105, "step": 45850 }, { "loss_action": 0.013484145514667034, "loss_total": 0.013484145514667034, "step": 45850 }, { "grad_norm": 0.26573559641838074, "learning_rate": 6.089263874676736e-05, "loss": 0.0131, "step": 45860 }, { "loss_action": 0.012898361310362816, "loss_total": 0.012898361310362816, "step": 45860 }, { "grad_norm": 0.26780134439468384, "learning_rate": 6.0876500589558796e-05, "loss": 0.0132, "step": 45870 }, { "loss_action": 0.011155717074871063, "loss_total": 0.011155717074871063, "step": 45870 }, { "grad_norm": 0.29958948493003845, "learning_rate": 6.086036124291248e-05, "loss": 0.0119, "step": 45880 }, { "loss_action": 0.009475771337747574, "loss_total": 0.009475771337747574, "step": 45880 }, { "grad_norm": 0.2797859311103821, "learning_rate": 6.084422070859339e-05, "loss": 0.0099, "step": 45890 }, { "loss_action": 0.015762707218527794, "loss_total": 0.015762707218527794, "step": 45890 }, { "grad_norm": 0.3311667740345001, "learning_rate": 6.082807898836663e-05, "loss": 0.0129, "step": 45900 }, { "loss_action": 0.011121386662125587, "loss_total": 0.011121386662125587, "step": 45900 }, { "grad_norm": 0.3616035580635071, "learning_rate": 6.081193608399742e-05, "loss": 0.0129, "step": 45910 }, { "loss_action": 0.008862108923494816, "loss_total": 0.008862108923494816, "step": 45910 }, { "grad_norm": 0.24851897358894348, "learning_rate": 6.0795791997251164e-05, "loss": 0.0115, "step": 45920 }, { "loss_action": 0.011402787640690804, "loss_total": 0.011402787640690804, "step": 45920 }, { "grad_norm": 0.23947827517986298, "learning_rate": 6.0779646729893294e-05, "loss": 0.0118, "step": 45930 }, { "loss_action": 0.011053665541112423, "loss_total": 0.011053665541112423, "step": 45930 }, { "grad_norm": 0.19658443331718445, "learning_rate": 6.0763500283689476e-05, "loss": 0.0113, "step": 45940 }, { "loss_action": 0.012199018150568008, "loss_total": 0.012199018150568008, "step": 45940 }, { "grad_norm": 0.24937565624713898, "learning_rate": 6.0747352660405455e-05, "loss": 0.0109, "step": 45950 }, { "loss_action": 0.013555741868913174, "loss_total": 0.013555741868913174, "step": 45950 }, { "grad_norm": 0.27482137084007263, "learning_rate": 6.073120386180709e-05, "loss": 0.0125, "step": 45960 }, { "loss_action": 0.010878216475248337, "loss_total": 0.010878216475248337, "step": 45960 }, { "grad_norm": 0.20297794044017792, "learning_rate": 6.0715053889660425e-05, "loss": 0.0118, "step": 45970 }, { "loss_action": 0.010531855747103691, "loss_total": 0.010531855747103691, "step": 45970 }, { "grad_norm": 0.3062158226966858, "learning_rate": 6.069890274573157e-05, "loss": 0.0125, "step": 45980 }, { "loss_action": 0.009439523331820965, "loss_total": 0.009439523331820965, "step": 45980 }, { "grad_norm": 0.29157134890556335, "learning_rate": 6.068275043178679e-05, "loss": 0.0125, "step": 45990 }, { "loss_action": 0.008221860975027084, "loss_total": 0.008221860975027084, "step": 45990 }, { "grad_norm": 0.2929646074771881, "learning_rate": 6.066659694959248e-05, "loss": 0.0129, "step": 46000 }, { "loss_action": 0.016209466382861137, "loss_total": 0.016209466382861137, "step": 46000 }, { "grad_norm": 0.3170126676559448, "learning_rate": 6.0650442300915176e-05, "loss": 0.0136, "step": 46010 }, { "loss_action": 0.009007235057651997, "loss_total": 0.009007235057651997, "step": 46010 }, { "grad_norm": 0.31565412878990173, "learning_rate": 6.063428648752152e-05, "loss": 0.0122, "step": 46020 }, { "loss_action": 0.01240874920040369, "loss_total": 0.01240874920040369, "step": 46020 }, { "grad_norm": 0.28777217864990234, "learning_rate": 6.0618129511178266e-05, "loss": 0.0122, "step": 46030 }, { "loss_action": 0.015008772723376751, "loss_total": 0.015008772723376751, "step": 46030 }, { "grad_norm": 0.2619006931781769, "learning_rate": 6.060197137365234e-05, "loss": 0.0118, "step": 46040 }, { "loss_action": 0.012176599353551865, "loss_total": 0.012176599353551865, "step": 46040 }, { "grad_norm": 0.226511150598526, "learning_rate": 6.058581207671077e-05, "loss": 0.0112, "step": 46050 }, { "loss_action": 0.009938099421560764, "loss_total": 0.009938099421560764, "step": 46050 }, { "grad_norm": 0.263139009475708, "learning_rate": 6.056965162212072e-05, "loss": 0.0105, "step": 46060 }, { "loss_action": 0.007703917101025581, "loss_total": 0.007703917101025581, "step": 46060 }, { "grad_norm": 0.28833770751953125, "learning_rate": 6.055349001164943e-05, "loss": 0.0102, "step": 46070 }, { "loss_action": 0.01416478306055069, "loss_total": 0.01416478306055069, "step": 46070 }, { "grad_norm": 0.3008928894996643, "learning_rate": 6.0537327247064347e-05, "loss": 0.0123, "step": 46080 }, { "loss_action": 0.017418088391423225, "loss_total": 0.017418088391423225, "step": 46080 }, { "grad_norm": 0.3700200915336609, "learning_rate": 6.0521163330133014e-05, "loss": 0.0123, "step": 46090 }, { "loss_action": 0.018431343138217926, "loss_total": 0.018431343138217926, "step": 46090 }, { "grad_norm": 0.280412495136261, "learning_rate": 6.050499826262306e-05, "loss": 0.0141, "step": 46100 }, { "loss_action": 0.01039881817996502, "loss_total": 0.01039881817996502, "step": 46100 }, { "grad_norm": 0.28426337242126465, "learning_rate": 6.0488832046302294e-05, "loss": 0.0117, "step": 46110 }, { "loss_action": 0.012452034279704094, "loss_total": 0.012452034279704094, "step": 46110 }, { "grad_norm": 0.3127439618110657, "learning_rate": 6.0472664682938626e-05, "loss": 0.0107, "step": 46120 }, { "loss_action": 0.009605721570551395, "loss_total": 0.009605721570551395, "step": 46120 }, { "grad_norm": 0.3096923828125, "learning_rate": 6.045649617430009e-05, "loss": 0.013, "step": 46130 }, { "loss_action": 0.008332616649568081, "loss_total": 0.008332616649568081, "step": 46130 }, { "grad_norm": 0.2881767451763153, "learning_rate": 6.0440326522154866e-05, "loss": 0.0106, "step": 46140 }, { "loss_action": 0.00865717139095068, "loss_total": 0.00865717139095068, "step": 46140 }, { "grad_norm": 0.28997713327407837, "learning_rate": 6.0424155728271224e-05, "loss": 0.0135, "step": 46150 }, { "loss_action": 0.012811783701181412, "loss_total": 0.012811783701181412, "step": 46150 }, { "grad_norm": 0.2793848216533661, "learning_rate": 6.040798379441758e-05, "loss": 0.0104, "step": 46160 }, { "loss_action": 0.011368592269718647, "loss_total": 0.011368592269718647, "step": 46160 }, { "grad_norm": 0.266097754240036, "learning_rate": 6.0391810722362485e-05, "loss": 0.0117, "step": 46170 }, { "loss_action": 0.01518042478710413, "loss_total": 0.01518042478710413, "step": 46170 }, { "grad_norm": 0.24752631783485413, "learning_rate": 6.037563651387458e-05, "loss": 0.012, "step": 46180 }, { "loss_action": 0.011691365391016006, "loss_total": 0.011691365391016006, "step": 46180 }, { "grad_norm": 0.28197184205055237, "learning_rate": 6.0359461170722666e-05, "loss": 0.0139, "step": 46190 }, { "loss_action": 0.017272762954235077, "loss_total": 0.017272762954235077, "step": 46190 }, { "grad_norm": 0.32859641313552856, "learning_rate": 6.034328469467566e-05, "loss": 0.0121, "step": 46200 }, { "loss_action": 0.017446182668209076, "loss_total": 0.017446182668209076, "step": 46200 }, { "grad_norm": 0.3346032202243805, "learning_rate": 6.0327107087502596e-05, "loss": 0.0132, "step": 46210 }, { "loss_action": 0.014512467198073864, "loss_total": 0.014512467198073864, "step": 46210 }, { "grad_norm": 0.3095252215862274, "learning_rate": 6.031092835097262e-05, "loss": 0.0123, "step": 46220 }, { "loss_action": 0.012476803734898567, "loss_total": 0.012476803734898567, "step": 46220 }, { "grad_norm": 0.21790939569473267, "learning_rate": 6.0294748486855024e-05, "loss": 0.0111, "step": 46230 }, { "loss_action": 0.015646206215023994, "loss_total": 0.015646206215023994, "step": 46230 }, { "grad_norm": 0.3119676113128662, "learning_rate": 6.0278567496919216e-05, "loss": 0.0111, "step": 46240 }, { "loss_action": 0.018131639808416367, "loss_total": 0.018131639808416367, "step": 46240 }, { "grad_norm": 0.2369639128446579, "learning_rate": 6.026238538293472e-05, "loss": 0.0108, "step": 46250 }, { "loss_action": 0.00864071398973465, "loss_total": 0.00864071398973465, "step": 46250 }, { "grad_norm": 0.24871774017810822, "learning_rate": 6.024620214667118e-05, "loss": 0.011, "step": 46260 }, { "loss_action": 0.011949563398957253, "loss_total": 0.011949563398957253, "step": 46260 }, { "grad_norm": 0.3301858901977539, "learning_rate": 6.0230017789898384e-05, "loss": 0.0132, "step": 46270 }, { "loss_action": 0.014246847480535507, "loss_total": 0.014246847480535507, "step": 46270 }, { "grad_norm": 0.28142306208610535, "learning_rate": 6.021383231438622e-05, "loss": 0.0116, "step": 46280 }, { "loss_action": 0.01123871374875307, "loss_total": 0.01123871374875307, "step": 46280 }, { "grad_norm": 0.27531659603118896, "learning_rate": 6.0197645721904704e-05, "loss": 0.0113, "step": 46290 }, { "loss_action": 0.011249873787164688, "loss_total": 0.011249873787164688, "step": 46290 }, { "grad_norm": 0.24868518114089966, "learning_rate": 6.0181458014224e-05, "loss": 0.0109, "step": 46300 }, { "loss_action": 0.007570873945951462, "loss_total": 0.007570873945951462, "step": 46300 }, { "grad_norm": 0.23724065721035004, "learning_rate": 6.016526919311435e-05, "loss": 0.0103, "step": 46310 }, { "loss_action": 0.0068591018207371235, "loss_total": 0.0068591018207371235, "step": 46310 }, { "grad_norm": 0.24410194158554077, "learning_rate": 6.014907926034613e-05, "loss": 0.0099, "step": 46320 }, { "loss_action": 0.009275676682591438, "loss_total": 0.009275676682591438, "step": 46320 }, { "grad_norm": 0.26610371470451355, "learning_rate": 6.0132888217689875e-05, "loss": 0.0114, "step": 46330 }, { "loss_action": 0.013480312190949917, "loss_total": 0.013480312190949917, "step": 46330 }, { "grad_norm": 0.2529132068157196, "learning_rate": 6.01166960669162e-05, "loss": 0.0113, "step": 46340 }, { "loss_action": 0.010567699559032917, "loss_total": 0.010567699559032917, "step": 46340 }, { "grad_norm": 0.32862579822540283, "learning_rate": 6.0100502809795845e-05, "loss": 0.011, "step": 46350 }, { "loss_action": 0.011621998623013496, "loss_total": 0.011621998623013496, "step": 46350 }, { "grad_norm": 0.2930956184864044, "learning_rate": 6.00843084480997e-05, "loss": 0.0118, "step": 46360 }, { "loss_action": 0.012840614654123783, "loss_total": 0.012840614654123783, "step": 46360 }, { "grad_norm": 0.21121694147586823, "learning_rate": 6.0068112983598736e-05, "loss": 0.0111, "step": 46370 }, { "loss_action": 0.010119863785803318, "loss_total": 0.010119863785803318, "step": 46370 }, { "grad_norm": 0.280714213848114, "learning_rate": 6.005191641806407e-05, "loss": 0.0109, "step": 46380 }, { "loss_action": 0.009480683133006096, "loss_total": 0.009480683133006096, "step": 46380 }, { "grad_norm": 0.3401622474193573, "learning_rate": 6.003571875326694e-05, "loss": 0.0104, "step": 46390 }, { "loss_action": 0.008958090096712112, "loss_total": 0.008958090096712112, "step": 46390 }, { "grad_norm": 0.2773352563381195, "learning_rate": 6.00195199909787e-05, "loss": 0.0108, "step": 46400 }, { "loss_action": 0.012126849964261055, "loss_total": 0.012126849964261055, "step": 46400 }, { "grad_norm": 0.2839053273200989, "learning_rate": 6.000332013297082e-05, "loss": 0.0106, "step": 46410 }, { "loss_action": 0.013517015613615513, "loss_total": 0.013517015613615513, "step": 46410 }, { "grad_norm": 0.24756057560443878, "learning_rate": 5.998711918101487e-05, "loss": 0.0113, "step": 46420 }, { "loss_action": 0.008316336199641228, "loss_total": 0.008316336199641228, "step": 46420 }, { "grad_norm": 0.2935095429420471, "learning_rate": 5.997091713688261e-05, "loss": 0.0114, "step": 46430 }, { "loss_action": 0.009537781588733196, "loss_total": 0.009537781588733196, "step": 46430 }, { "grad_norm": 0.26300275325775146, "learning_rate": 5.9954714002345836e-05, "loss": 0.0107, "step": 46440 }, { "loss_action": 0.007880624383687973, "loss_total": 0.007880624383687973, "step": 46440 }, { "grad_norm": 0.22111551463603973, "learning_rate": 5.993850977917649e-05, "loss": 0.0106, "step": 46450 }, { "loss_action": 0.009455585852265358, "loss_total": 0.009455585852265358, "step": 46450 }, { "grad_norm": 0.27644044160842896, "learning_rate": 5.992230446914667e-05, "loss": 0.0112, "step": 46460 }, { "loss_action": 0.012112457305192947, "loss_total": 0.012112457305192947, "step": 46460 }, { "grad_norm": 0.27983203530311584, "learning_rate": 5.990609807402855e-05, "loss": 0.0105, "step": 46470 }, { "loss_action": 0.00946908537298441, "loss_total": 0.00946908537298441, "step": 46470 }, { "grad_norm": 0.21732251346111298, "learning_rate": 5.988989059559443e-05, "loss": 0.0112, "step": 46480 }, { "loss_action": 0.008117838762700558, "loss_total": 0.008117838762700558, "step": 46480 }, { "grad_norm": 0.26680874824523926, "learning_rate": 5.987368203561675e-05, "loss": 0.0102, "step": 46490 }, { "loss_action": 0.010842991061508656, "loss_total": 0.010842991061508656, "step": 46490 }, { "grad_norm": 0.24295087158679962, "learning_rate": 5.9857472395868055e-05, "loss": 0.0132, "step": 46500 }, { "loss_action": 0.008646775968372822, "loss_total": 0.008646775968372822, "step": 46500 }, { "grad_norm": 0.21416257321834564, "learning_rate": 5.9841261678120983e-05, "loss": 0.011, "step": 46510 }, { "loss_action": 0.010876201093196869, "loss_total": 0.010876201093196869, "step": 46510 }, { "grad_norm": 0.2575570344924927, "learning_rate": 5.982504988414834e-05, "loss": 0.0116, "step": 46520 }, { "loss_action": 0.009426092728972435, "loss_total": 0.009426092728972435, "step": 46520 }, { "grad_norm": 0.277436226606369, "learning_rate": 5.9808837015723015e-05, "loss": 0.0105, "step": 46530 }, { "loss_action": 0.015738507732748985, "loss_total": 0.015738507732748985, "step": 46530 }, { "grad_norm": 0.33992552757263184, "learning_rate": 5.9792623074618016e-05, "loss": 0.0111, "step": 46540 }, { "loss_action": 0.011862649582326412, "loss_total": 0.011862649582326412, "step": 46540 }, { "grad_norm": 0.23909026384353638, "learning_rate": 5.977640806260648e-05, "loss": 0.0103, "step": 46550 }, { "loss_action": 0.010334162041544914, "loss_total": 0.010334162041544914, "step": 46550 }, { "grad_norm": 0.26408225297927856, "learning_rate": 5.976019198146166e-05, "loss": 0.01, "step": 46560 }, { "loss_action": 0.009429460391402245, "loss_total": 0.009429460391402245, "step": 46560 }, { "grad_norm": 0.26851123571395874, "learning_rate": 5.974397483295692e-05, "loss": 0.0095, "step": 46570 }, { "loss_action": 0.010434603318572044, "loss_total": 0.010434603318572044, "step": 46570 }, { "grad_norm": 0.28561097383499146, "learning_rate": 5.972775661886575e-05, "loss": 0.0103, "step": 46580 }, { "loss_action": 0.009316768497228622, "loss_total": 0.009316768497228622, "step": 46580 }, { "grad_norm": 0.23719218373298645, "learning_rate": 5.971153734096173e-05, "loss": 0.0108, "step": 46590 }, { "loss_action": 0.010373027063906193, "loss_total": 0.010373027063906193, "step": 46590 }, { "grad_norm": 0.25328996777534485, "learning_rate": 5.969531700101859e-05, "loss": 0.0105, "step": 46600 }, { "loss_action": 0.010259668342769146, "loss_total": 0.010259668342769146, "step": 46600 }, { "grad_norm": 0.28322741389274597, "learning_rate": 5.9679095600810155e-05, "loss": 0.0089, "step": 46610 }, { "loss_action": 0.009471372701227665, "loss_total": 0.009471372701227665, "step": 46610 }, { "grad_norm": 0.2551327049732208, "learning_rate": 5.9662873142110384e-05, "loss": 0.011, "step": 46620 }, { "loss_action": 0.01734897680580616, "loss_total": 0.01734897680580616, "step": 46620 }, { "grad_norm": 0.27903908491134644, "learning_rate": 5.964664962669333e-05, "loss": 0.0127, "step": 46630 }, { "loss_action": 0.011473034508526325, "loss_total": 0.011473034508526325, "step": 46630 }, { "grad_norm": 0.28597965836524963, "learning_rate": 5.9630425056333186e-05, "loss": 0.013, "step": 46640 }, { "loss_action": 0.011277294717729092, "loss_total": 0.011277294717729092, "step": 46640 }, { "grad_norm": 0.3024367094039917, "learning_rate": 5.961419943280422e-05, "loss": 0.0116, "step": 46650 }, { "loss_action": 0.010280718095600605, "loss_total": 0.010280718095600605, "step": 46650 }, { "grad_norm": 0.286382794380188, "learning_rate": 5.959797275788087e-05, "loss": 0.0123, "step": 46660 }, { "loss_action": 0.014678732492029667, "loss_total": 0.014678732492029667, "step": 46660 }, { "grad_norm": 0.29459938406944275, "learning_rate": 5.958174503333765e-05, "loss": 0.0123, "step": 46670 }, { "loss_action": 0.01314134057611227, "loss_total": 0.01314134057611227, "step": 46670 }, { "grad_norm": 0.2698339521884918, "learning_rate": 5.9565516260949195e-05, "loss": 0.0136, "step": 46680 }, { "loss_action": 0.010386808775365353, "loss_total": 0.010386808775365353, "step": 46680 }, { "grad_norm": 0.259640097618103, "learning_rate": 5.9549286442490273e-05, "loss": 0.0111, "step": 46690 }, { "loss_action": 0.00988241471350193, "loss_total": 0.00988241471350193, "step": 46690 }, { "grad_norm": 0.3094412386417389, "learning_rate": 5.953305557973572e-05, "loss": 0.0104, "step": 46700 }, { "loss_action": 0.010245214216411114, "loss_total": 0.010245214216411114, "step": 46700 }, { "grad_norm": 0.28697893023490906, "learning_rate": 5.9516823674460564e-05, "loss": 0.0113, "step": 46710 }, { "loss_action": 0.010350560769438744, "loss_total": 0.010350560769438744, "step": 46710 }, { "grad_norm": 0.26364848017692566, "learning_rate": 5.9500590728439875e-05, "loss": 0.0124, "step": 46720 }, { "loss_action": 0.009455888532102108, "loss_total": 0.009455888532102108, "step": 46720 }, { "grad_norm": 0.292616605758667, "learning_rate": 5.948435674344886e-05, "loss": 0.0107, "step": 46730 }, { "loss_action": 0.013747956603765488, "loss_total": 0.013747956603765488, "step": 46730 }, { "grad_norm": 0.2622438669204712, "learning_rate": 5.946812172126285e-05, "loss": 0.0108, "step": 46740 }, { "loss_action": 0.010541633702814579, "loss_total": 0.010541633702814579, "step": 46740 }, { "grad_norm": 0.2249094843864441, "learning_rate": 5.945188566365729e-05, "loss": 0.0107, "step": 46750 }, { "loss_action": 0.010386710055172443, "loss_total": 0.010386710055172443, "step": 46750 }, { "grad_norm": 0.2930988669395447, "learning_rate": 5.943564857240773e-05, "loss": 0.0101, "step": 46760 }, { "loss_action": 0.009774120524525642, "loss_total": 0.009774120524525642, "step": 46760 }, { "grad_norm": 0.20266880095005035, "learning_rate": 5.941941044928981e-05, "loss": 0.0099, "step": 46770 }, { "loss_action": 0.008285955525934696, "loss_total": 0.008285955525934696, "step": 46770 }, { "grad_norm": 0.3081842064857483, "learning_rate": 5.940317129607935e-05, "loss": 0.0122, "step": 46780 }, { "loss_action": 0.01115200575441122, "loss_total": 0.01115200575441122, "step": 46780 }, { "grad_norm": 0.2810594439506531, "learning_rate": 5.9386931114552204e-05, "loss": 0.0116, "step": 46790 }, { "loss_action": 0.008842199109494686, "loss_total": 0.008842199109494686, "step": 46790 }, { "grad_norm": 0.2959265410900116, "learning_rate": 5.937068990648438e-05, "loss": 0.0117, "step": 46800 }, { "loss_action": 0.01536426693201065, "loss_total": 0.01536426693201065, "step": 46800 }, { "grad_norm": 0.2958868443965912, "learning_rate": 5.935444767365199e-05, "loss": 0.0118, "step": 46810 }, { "loss_action": 0.012564591132104397, "loss_total": 0.012564591132104397, "step": 46810 }, { "grad_norm": 0.2117760330438614, "learning_rate": 5.933820441783129e-05, "loss": 0.0119, "step": 46820 }, { "loss_action": 0.008600412867963314, "loss_total": 0.008600412867963314, "step": 46820 }, { "grad_norm": 0.30330517888069153, "learning_rate": 5.932196014079857e-05, "loss": 0.0103, "step": 46830 }, { "loss_action": 0.008429180830717087, "loss_total": 0.008429180830717087, "step": 46830 }, { "grad_norm": 0.25874921679496765, "learning_rate": 5.930571484433032e-05, "loss": 0.0102, "step": 46840 }, { "loss_action": 0.01170001458376646, "loss_total": 0.01170001458376646, "step": 46840 }, { "grad_norm": 0.2972007393836975, "learning_rate": 5.928946853020309e-05, "loss": 0.0129, "step": 46850 }, { "loss_action": 0.007740860339254141, "loss_total": 0.007740860339254141, "step": 46850 }, { "grad_norm": 0.185444176197052, "learning_rate": 5.927322120019352e-05, "loss": 0.01, "step": 46860 }, { "loss_action": 0.01072140783071518, "loss_total": 0.01072140783071518, "step": 46860 }, { "grad_norm": 0.27173444628715515, "learning_rate": 5.925697285607844e-05, "loss": 0.0105, "step": 46870 }, { "loss_action": 0.009653477929532528, "loss_total": 0.009653477929532528, "step": 46870 }, { "grad_norm": 0.27738669514656067, "learning_rate": 5.924072349963472e-05, "loss": 0.012, "step": 46880 }, { "loss_action": 0.011338936164975166, "loss_total": 0.011338936164975166, "step": 46880 }, { "grad_norm": 0.23333165049552917, "learning_rate": 5.922447313263938e-05, "loss": 0.0111, "step": 46890 }, { "loss_action": 0.010550390928983688, "loss_total": 0.010550390928983688, "step": 46890 }, { "grad_norm": 0.22763189673423767, "learning_rate": 5.920822175686952e-05, "loss": 0.0108, "step": 46900 }, { "loss_action": 0.00827633123844862, "loss_total": 0.00827633123844862, "step": 46900 }, { "grad_norm": 0.2091122567653656, "learning_rate": 5.919196937410239e-05, "loss": 0.0097, "step": 46910 }, { "loss_action": 0.0078333904966712, "loss_total": 0.0078333904966712, "step": 46910 }, { "grad_norm": 0.23989896476268768, "learning_rate": 5.917571598611529e-05, "loss": 0.0109, "step": 46920 }, { "loss_action": 0.012220431119203568, "loss_total": 0.012220431119203568, "step": 46920 }, { "grad_norm": 0.25539708137512207, "learning_rate": 5.9159461594685686e-05, "loss": 0.0114, "step": 46930 }, { "loss_action": 0.011428256519138813, "loss_total": 0.011428256519138813, "step": 46930 }, { "grad_norm": 0.1946999430656433, "learning_rate": 5.914320620159114e-05, "loss": 0.01, "step": 46940 }, { "loss_action": 0.009931175969541073, "loss_total": 0.009931175969541073, "step": 46940 }, { "grad_norm": 0.2843218445777893, "learning_rate": 5.912694980860931e-05, "loss": 0.0109, "step": 46950 }, { "loss_action": 0.014070809818804264, "loss_total": 0.014070809818804264, "step": 46950 }, { "grad_norm": 0.22935457527637482, "learning_rate": 5.9110692417517964e-05, "loss": 0.0115, "step": 46960 }, { "loss_action": 0.011164446361362934, "loss_total": 0.011164446361362934, "step": 46960 }, { "grad_norm": 0.26616114377975464, "learning_rate": 5.9094434030095e-05, "loss": 0.0122, "step": 46970 }, { "loss_action": 0.011560744605958462, "loss_total": 0.011560744605958462, "step": 46970 }, { "grad_norm": 0.2663363516330719, "learning_rate": 5.907817464811841e-05, "loss": 0.0126, "step": 46980 }, { "loss_action": 0.010399337857961655, "loss_total": 0.010399337857961655, "step": 46980 }, { "grad_norm": 0.28518563508987427, "learning_rate": 5.906191427336627e-05, "loss": 0.0119, "step": 46990 }, { "loss_action": 0.011105113662779331, "loss_total": 0.011105113662779331, "step": 46990 }, { "grad_norm": 0.24849696457386017, "learning_rate": 5.9045652907616835e-05, "loss": 0.0119, "step": 47000 }, { "loss_action": 0.010121149010956287, "loss_total": 0.010121149010956287, "step": 47000 }, { "grad_norm": 0.27684804797172546, "learning_rate": 5.902939055264838e-05, "loss": 0.0115, "step": 47010 }, { "loss_action": 0.00950066652148962, "loss_total": 0.00950066652148962, "step": 47010 }, { "grad_norm": 0.2722227871417999, "learning_rate": 5.901312721023935e-05, "loss": 0.0104, "step": 47020 }, { "loss_action": 0.017082534730434418, "loss_total": 0.017082534730434418, "step": 47020 }, { "grad_norm": 0.38562238216400146, "learning_rate": 5.8996862882168294e-05, "loss": 0.0136, "step": 47030 }, { "loss_action": 0.010075544938445091, "loss_total": 0.010075544938445091, "step": 47030 }, { "grad_norm": 0.30520719289779663, "learning_rate": 5.8980597570213826e-05, "loss": 0.0119, "step": 47040 }, { "loss_action": 0.01010217797011137, "loss_total": 0.01010217797011137, "step": 47040 }, { "grad_norm": 0.2696608603000641, "learning_rate": 5.896433127615471e-05, "loss": 0.0121, "step": 47050 }, { "loss_action": 0.009885273873806, "loss_total": 0.009885273873806, "step": 47050 }, { "grad_norm": 0.24301394820213318, "learning_rate": 5.894806400176981e-05, "loss": 0.0112, "step": 47060 }, { "loss_action": 0.013761268928647041, "loss_total": 0.013761268928647041, "step": 47060 }, { "grad_norm": 0.2245602309703827, "learning_rate": 5.893179574883808e-05, "loss": 0.0102, "step": 47070 }, { "loss_action": 0.013062657788395882, "loss_total": 0.013062657788395882, "step": 47070 }, { "grad_norm": 0.26300856471061707, "learning_rate": 5.8915526519138585e-05, "loss": 0.011, "step": 47080 }, { "loss_action": 0.011572398245334625, "loss_total": 0.011572398245334625, "step": 47080 }, { "grad_norm": 0.29830417037010193, "learning_rate": 5.889925631445053e-05, "loss": 0.0118, "step": 47090 }, { "loss_action": 0.012048518285155296, "loss_total": 0.012048518285155296, "step": 47090 }, { "grad_norm": 0.2549302875995636, "learning_rate": 5.888298513655318e-05, "loss": 0.0109, "step": 47100 }, { "loss_action": 0.013915454968810081, "loss_total": 0.013915454968810081, "step": 47100 }, { "grad_norm": 0.29489192366600037, "learning_rate": 5.886671298722592e-05, "loss": 0.0105, "step": 47110 }, { "loss_action": 0.012845571152865887, "loss_total": 0.012845571152865887, "step": 47110 }, { "grad_norm": 0.24795155227184296, "learning_rate": 5.885043986824828e-05, "loss": 0.0105, "step": 47120 }, { "loss_action": 0.009953289292752743, "loss_total": 0.009953289292752743, "step": 47120 }, { "grad_norm": 0.24597443640232086, "learning_rate": 5.883416578139982e-05, "loss": 0.0116, "step": 47130 }, { "loss_action": 0.010774224065244198, "loss_total": 0.010774224065244198, "step": 47130 }, { "grad_norm": 0.26659077405929565, "learning_rate": 5.881789072846029e-05, "loss": 0.011, "step": 47140 }, { "loss_action": 0.012373924255371094, "loss_total": 0.012373924255371094, "step": 47140 }, { "grad_norm": 0.2646581530570984, "learning_rate": 5.8801614711209474e-05, "loss": 0.0133, "step": 47150 }, { "loss_action": 0.010278665460646152, "loss_total": 0.010278665460646152, "step": 47150 }, { "grad_norm": 0.2810470759868622, "learning_rate": 5.878533773142732e-05, "loss": 0.0115, "step": 47160 }, { "loss_action": 0.015985362231731415, "loss_total": 0.015985362231731415, "step": 47160 }, { "grad_norm": 0.21627277135849, "learning_rate": 5.8769059790893834e-05, "loss": 0.0116, "step": 47170 }, { "loss_action": 0.011955512687563896, "loss_total": 0.011955512687563896, "step": 47170 }, { "grad_norm": 0.2867780327796936, "learning_rate": 5.8752780891389145e-05, "loss": 0.0107, "step": 47180 }, { "loss_action": 0.012996026314795017, "loss_total": 0.012996026314795017, "step": 47180 }, { "grad_norm": 0.3436015546321869, "learning_rate": 5.873650103469351e-05, "loss": 0.0124, "step": 47190 }, { "loss_action": 0.010416697710752487, "loss_total": 0.010416697710752487, "step": 47190 }, { "grad_norm": 0.2527831196784973, "learning_rate": 5.872022022258725e-05, "loss": 0.0102, "step": 47200 }, { "loss_action": 0.010593723505735397, "loss_total": 0.010593723505735397, "step": 47200 }, { "grad_norm": 0.25394874811172485, "learning_rate": 5.8703938456850814e-05, "loss": 0.0107, "step": 47210 }, { "loss_action": 0.009662248194217682, "loss_total": 0.009662248194217682, "step": 47210 }, { "grad_norm": 0.319216787815094, "learning_rate": 5.868765573926477e-05, "loss": 0.0105, "step": 47220 }, { "loss_action": 0.01543456967920065, "loss_total": 0.01543456967920065, "step": 47220 }, { "grad_norm": 0.3274710178375244, "learning_rate": 5.867137207160974e-05, "loss": 0.0117, "step": 47230 }, { "loss_action": 0.009606913663446903, "loss_total": 0.009606913663446903, "step": 47230 }, { "grad_norm": 0.2313724309206009, "learning_rate": 5.86550874556665e-05, "loss": 0.0113, "step": 47240 }, { "loss_action": 0.011765485629439354, "loss_total": 0.011765485629439354, "step": 47240 }, { "grad_norm": 0.2861826419830322, "learning_rate": 5.863880189321592e-05, "loss": 0.011, "step": 47250 }, { "loss_action": 0.007933433167636395, "loss_total": 0.007933433167636395, "step": 47250 }, { "grad_norm": 0.28985992074012756, "learning_rate": 5.862251538603894e-05, "loss": 0.0111, "step": 47260 }, { "loss_action": 0.010329736396670341, "loss_total": 0.010329736396670341, "step": 47260 }, { "grad_norm": 0.2906753122806549, "learning_rate": 5.8606227935916656e-05, "loss": 0.0117, "step": 47270 }, { "loss_action": 0.00938364677131176, "loss_total": 0.00938364677131176, "step": 47270 }, { "grad_norm": 0.308267205953598, "learning_rate": 5.858993954463021e-05, "loss": 0.0104, "step": 47280 }, { "loss_action": 0.008899593725800514, "loss_total": 0.008899593725800514, "step": 47280 }, { "grad_norm": 0.26527097821235657, "learning_rate": 5.8573650213960896e-05, "loss": 0.0117, "step": 47290 }, { "loss_action": 0.010559909977018833, "loss_total": 0.010559909977018833, "step": 47290 }, { "grad_norm": 0.29055723547935486, "learning_rate": 5.8557359945690084e-05, "loss": 0.0118, "step": 47300 }, { "loss_action": 0.01077954564243555, "loss_total": 0.01077954564243555, "step": 47300 }, { "grad_norm": 0.250522643327713, "learning_rate": 5.8541068741599246e-05, "loss": 0.0106, "step": 47310 }, { "loss_action": 0.008119409903883934, "loss_total": 0.008119409903883934, "step": 47310 }, { "grad_norm": 0.2250242680311203, "learning_rate": 5.8524776603469985e-05, "loss": 0.0109, "step": 47320 }, { "loss_action": 0.013378053903579712, "loss_total": 0.013378053903579712, "step": 47320 }, { "grad_norm": 0.21944501996040344, "learning_rate": 5.850848353308397e-05, "loss": 0.0107, "step": 47330 }, { "loss_action": 0.008867721073329449, "loss_total": 0.008867721073329449, "step": 47330 }, { "grad_norm": 0.30001240968704224, "learning_rate": 5.849218953222297e-05, "loss": 0.0093, "step": 47340 }, { "loss_action": 0.012735861353576183, "loss_total": 0.012735861353576183, "step": 47340 }, { "grad_norm": 0.28925156593322754, "learning_rate": 5.847589460266891e-05, "loss": 0.0125, "step": 47350 }, { "loss_action": 0.011064482852816582, "loss_total": 0.011064482852816582, "step": 47350 }, { "grad_norm": 0.2310178130865097, "learning_rate": 5.845959874620375e-05, "loss": 0.0102, "step": 47360 }, { "loss_action": 0.009862427599728107, "loss_total": 0.009862427599728107, "step": 47360 }, { "grad_norm": 0.2493782788515091, "learning_rate": 5.84433019646096e-05, "loss": 0.0119, "step": 47370 }, { "loss_action": 0.010902691632509232, "loss_total": 0.010902691632509232, "step": 47370 }, { "grad_norm": 0.2687828540802002, "learning_rate": 5.842700425966863e-05, "loss": 0.0125, "step": 47380 }, { "loss_action": 0.0068493131548166275, "loss_total": 0.0068493131548166275, "step": 47380 }, { "grad_norm": 0.20596396923065186, "learning_rate": 5.841070563316315e-05, "loss": 0.011, "step": 47390 }, { "loss_action": 0.00946687813848257, "loss_total": 0.00946687813848257, "step": 47390 }, { "grad_norm": 0.21093183755874634, "learning_rate": 5.839440608687554e-05, "loss": 0.0105, "step": 47400 }, { "loss_action": 0.008140398189425468, "loss_total": 0.008140398189425468, "step": 47400 }, { "grad_norm": 0.33248835802078247, "learning_rate": 5.837810562258831e-05, "loss": 0.0103, "step": 47410 }, { "loss_action": 0.009004072286188602, "loss_total": 0.009004072286188602, "step": 47410 }, { "grad_norm": 0.21407784521579742, "learning_rate": 5.836180424208405e-05, "loss": 0.0101, "step": 47420 }, { "loss_action": 0.014922475442290306, "loss_total": 0.014922475442290306, "step": 47420 }, { "grad_norm": 0.3306269943714142, "learning_rate": 5.834550194714543e-05, "loss": 0.0103, "step": 47430 }, { "loss_action": 0.013464589603245258, "loss_total": 0.013464589603245258, "step": 47430 }, { "grad_norm": 0.25561073422431946, "learning_rate": 5.832919873955528e-05, "loss": 0.0113, "step": 47440 }, { "loss_action": 0.011709855869412422, "loss_total": 0.011709855869412422, "step": 47440 }, { "grad_norm": 0.2279847115278244, "learning_rate": 5.831289462109648e-05, "loss": 0.0117, "step": 47450 }, { "loss_action": 0.012537239119410515, "loss_total": 0.012537239119410515, "step": 47450 }, { "grad_norm": 0.32042568922042847, "learning_rate": 5.829658959355202e-05, "loss": 0.0117, "step": 47460 }, { "loss_action": 0.011187132447957993, "loss_total": 0.011187132447957993, "step": 47460 }, { "grad_norm": 0.2910970151424408, "learning_rate": 5.8280283658704995e-05, "loss": 0.0111, "step": 47470 }, { "loss_action": 0.011641605757176876, "loss_total": 0.011641605757176876, "step": 47470 }, { "grad_norm": 0.2480795532464981, "learning_rate": 5.826397681833859e-05, "loss": 0.0109, "step": 47480 }, { "loss_action": 0.008880343288183212, "loss_total": 0.008880343288183212, "step": 47480 }, { "grad_norm": 0.29773178696632385, "learning_rate": 5.824766907423612e-05, "loss": 0.0114, "step": 47490 }, { "loss_action": 0.008372698910534382, "loss_total": 0.008372698910534382, "step": 47490 }, { "grad_norm": 0.2730947434902191, "learning_rate": 5.8231360428180945e-05, "loss": 0.011, "step": 47500 }, { "loss_action": 0.01071927696466446, "loss_total": 0.01071927696466446, "step": 47500 }, { "grad_norm": 0.2798624634742737, "learning_rate": 5.821505088195658e-05, "loss": 0.0117, "step": 47510 }, { "loss_action": 0.010527490638196468, "loss_total": 0.010527490638196468, "step": 47510 }, { "grad_norm": 0.29154589772224426, "learning_rate": 5.819874043734661e-05, "loss": 0.0114, "step": 47520 }, { "loss_action": 0.008350840769708157, "loss_total": 0.008350840769708157, "step": 47520 }, { "grad_norm": 0.24762742221355438, "learning_rate": 5.8182429096134695e-05, "loss": 0.0117, "step": 47530 }, { "loss_action": 0.00800983514636755, "loss_total": 0.00800983514636755, "step": 47530 }, { "grad_norm": 0.30693739652633667, "learning_rate": 5.816611686010465e-05, "loss": 0.0124, "step": 47540 }, { "loss_action": 0.010212384164333344, "loss_total": 0.010212384164333344, "step": 47540 }, { "grad_norm": 0.26248010993003845, "learning_rate": 5.814980373104033e-05, "loss": 0.0118, "step": 47550 }, { "loss_action": 0.009247726760804653, "loss_total": 0.009247726760804653, "step": 47550 }, { "grad_norm": 0.26863327622413635, "learning_rate": 5.813348971072572e-05, "loss": 0.0113, "step": 47560 }, { "loss_action": 0.011007118038833141, "loss_total": 0.011007118038833141, "step": 47560 }, { "grad_norm": 0.27253666520118713, "learning_rate": 5.811717480094492e-05, "loss": 0.0113, "step": 47570 }, { "loss_action": 0.01121219526976347, "loss_total": 0.01121219526976347, "step": 47570 }, { "grad_norm": 0.2971121072769165, "learning_rate": 5.810085900348209e-05, "loss": 0.0134, "step": 47580 }, { "loss_action": 0.015067856758832932, "loss_total": 0.015067856758832932, "step": 47580 }, { "grad_norm": 0.31110629439353943, "learning_rate": 5.8084542320121483e-05, "loss": 0.0127, "step": 47590 }, { "loss_action": 0.007997220382094383, "loss_total": 0.007997220382094383, "step": 47590 }, { "grad_norm": 0.2813637852668762, "learning_rate": 5.8068224752647497e-05, "loss": 0.0115, "step": 47600 }, { "loss_action": 0.013734976761043072, "loss_total": 0.013734976761043072, "step": 47600 }, { "grad_norm": 0.2538657784461975, "learning_rate": 5.805190630284457e-05, "loss": 0.0113, "step": 47610 }, { "loss_action": 0.008884088136255741, "loss_total": 0.008884088136255741, "step": 47610 }, { "grad_norm": 0.24724744260311127, "learning_rate": 5.803558697249729e-05, "loss": 0.0109, "step": 47620 }, { "loss_action": 0.015544787980616093, "loss_total": 0.015544787980616093, "step": 47620 }, { "grad_norm": 0.27981629967689514, "learning_rate": 5.8019266763390276e-05, "loss": 0.0111, "step": 47630 }, { "loss_action": 0.00791705772280693, "loss_total": 0.00791705772280693, "step": 47630 }, { "grad_norm": 0.392600953578949, "learning_rate": 5.800294567730833e-05, "loss": 0.0119, "step": 47640 }, { "loss_action": 0.007003466133028269, "loss_total": 0.007003466133028269, "step": 47640 }, { "grad_norm": 0.33047419786453247, "learning_rate": 5.798662371603628e-05, "loss": 0.0116, "step": 47650 }, { "loss_action": 0.01500850822776556, "loss_total": 0.01500850822776556, "step": 47650 }, { "grad_norm": 0.3221237361431122, "learning_rate": 5.797030088135904e-05, "loss": 0.011, "step": 47660 }, { "loss_action": 0.011731107719242573, "loss_total": 0.011731107719242573, "step": 47660 }, { "grad_norm": 0.28169119358062744, "learning_rate": 5.7953977175061705e-05, "loss": 0.0121, "step": 47670 }, { "loss_action": 0.017050430178642273, "loss_total": 0.017050430178642273, "step": 47670 }, { "grad_norm": 0.18136213719844818, "learning_rate": 5.793765259892938e-05, "loss": 0.0119, "step": 47680 }, { "loss_action": 0.008957727812230587, "loss_total": 0.008957727812230587, "step": 47680 }, { "grad_norm": 0.22376230359077454, "learning_rate": 5.792132715474729e-05, "loss": 0.0115, "step": 47690 }, { "loss_action": 0.008404728025197983, "loss_total": 0.008404728025197983, "step": 47690 }, { "grad_norm": 0.202427938580513, "learning_rate": 5.790500084430078e-05, "loss": 0.0109, "step": 47700 }, { "loss_action": 0.009308797307312489, "loss_total": 0.009308797307312489, "step": 47700 }, { "grad_norm": 0.2571808993816376, "learning_rate": 5.7888673669375274e-05, "loss": 0.0115, "step": 47710 }, { "loss_action": 0.008715806528925896, "loss_total": 0.008715806528925896, "step": 47710 }, { "grad_norm": 0.29198792576789856, "learning_rate": 5.787234563175625e-05, "loss": 0.0105, "step": 47720 }, { "loss_action": 0.01084747165441513, "loss_total": 0.01084747165441513, "step": 47720 }, { "grad_norm": 0.3227101266384125, "learning_rate": 5.7856016733229355e-05, "loss": 0.0102, "step": 47730 }, { "loss_action": 0.008470922708511353, "loss_total": 0.008470922708511353, "step": 47730 }, { "grad_norm": 0.23187939822673798, "learning_rate": 5.7839686975580297e-05, "loss": 0.0096, "step": 47740 }, { "loss_action": 0.009680944494903088, "loss_total": 0.009680944494903088, "step": 47740 }, { "grad_norm": 0.2349884957075119, "learning_rate": 5.782335636059484e-05, "loss": 0.0089, "step": 47750 }, { "loss_action": 0.009537582285702229, "loss_total": 0.009537582285702229, "step": 47750 }, { "grad_norm": 0.27937471866607666, "learning_rate": 5.780702489005889e-05, "loss": 0.0097, "step": 47760 }, { "loss_action": 0.008603418245911598, "loss_total": 0.008603418245911598, "step": 47760 }, { "grad_norm": 0.2686587870121002, "learning_rate": 5.779069256575845e-05, "loss": 0.0117, "step": 47770 }, { "loss_action": 0.011447560042142868, "loss_total": 0.011447560042142868, "step": 47770 }, { "grad_norm": 0.27259567379951477, "learning_rate": 5.7774359389479574e-05, "loss": 0.0114, "step": 47780 }, { "loss_action": 0.007919593714177608, "loss_total": 0.007919593714177608, "step": 47780 }, { "grad_norm": 0.22635608911514282, "learning_rate": 5.775802536300845e-05, "loss": 0.0091, "step": 47790 }, { "loss_action": 0.009486326016485691, "loss_total": 0.009486326016485691, "step": 47790 }, { "grad_norm": 0.23538173735141754, "learning_rate": 5.774169048813134e-05, "loss": 0.0106, "step": 47800 }, { "loss_action": 0.012870945036411285, "loss_total": 0.012870945036411285, "step": 47800 }, { "grad_norm": 0.36991438269615173, "learning_rate": 5.77253547666346e-05, "loss": 0.011, "step": 47810 }, { "loss_action": 0.008778693154454231, "loss_total": 0.008778693154454231, "step": 47810 }, { "grad_norm": 0.256000816822052, "learning_rate": 5.770901820030465e-05, "loss": 0.0107, "step": 47820 }, { "loss_action": 0.009856484830379486, "loss_total": 0.009856484830379486, "step": 47820 }, { "grad_norm": 0.24549874663352966, "learning_rate": 5.769268079092809e-05, "loss": 0.0115, "step": 47830 }, { "loss_action": 0.015360669232904911, "loss_total": 0.015360669232904911, "step": 47830 }, { "grad_norm": 0.25159934163093567, "learning_rate": 5.767634254029151e-05, "loss": 0.0121, "step": 47840 }, { "loss_action": 0.009206626564264297, "loss_total": 0.009206626564264297, "step": 47840 }, { "grad_norm": 0.2116554081439972, "learning_rate": 5.7660003450181655e-05, "loss": 0.0112, "step": 47850 }, { "loss_action": 0.00932424794882536, "loss_total": 0.00932424794882536, "step": 47850 }, { "grad_norm": 0.33836179971694946, "learning_rate": 5.764366352238534e-05, "loss": 0.0116, "step": 47860 }, { "loss_action": 0.014675467275083065, "loss_total": 0.014675467275083065, "step": 47860 }, { "grad_norm": 0.21382750570774078, "learning_rate": 5.7627322758689474e-05, "loss": 0.0112, "step": 47870 }, { "loss_action": 0.007213234901428223, "loss_total": 0.007213234901428223, "step": 47870 }, { "grad_norm": 0.26810452342033386, "learning_rate": 5.761098116088105e-05, "loss": 0.0112, "step": 47880 }, { "loss_action": 0.008307804353535175, "loss_total": 0.008307804353535175, "step": 47880 }, { "grad_norm": 0.23055721819400787, "learning_rate": 5.759463873074717e-05, "loss": 0.0104, "step": 47890 }, { "loss_action": 0.008353856392204762, "loss_total": 0.008353856392204762, "step": 47890 }, { "grad_norm": 0.25374171137809753, "learning_rate": 5.757829547007504e-05, "loss": 0.0107, "step": 47900 }, { "loss_action": 0.009586060419678688, "loss_total": 0.009586060419678688, "step": 47900 }, { "grad_norm": 0.31104668974876404, "learning_rate": 5.756195138065189e-05, "loss": 0.01, "step": 47910 }, { "loss_action": 0.009480430744588375, "loss_total": 0.009480430744588375, "step": 47910 }, { "grad_norm": 0.25838005542755127, "learning_rate": 5.754560646426511e-05, "loss": 0.0112, "step": 47920 }, { "loss_action": 0.011171191930770874, "loss_total": 0.011171191930770874, "step": 47920 }, { "grad_norm": 0.25272777676582336, "learning_rate": 5.752926072270216e-05, "loss": 0.0106, "step": 47930 }, { "loss_action": 0.007986661046743393, "loss_total": 0.007986661046743393, "step": 47930 }, { "grad_norm": 0.2748328149318695, "learning_rate": 5.7512914157750563e-05, "loss": 0.0102, "step": 47940 }, { "loss_action": 0.009349647909402847, "loss_total": 0.009349647909402847, "step": 47940 }, { "grad_norm": 0.19669078290462494, "learning_rate": 5.749656677119798e-05, "loss": 0.01, "step": 47950 }, { "loss_action": 0.007616667076945305, "loss_total": 0.007616667076945305, "step": 47950 }, { "grad_norm": 0.222331240773201, "learning_rate": 5.7480218564832125e-05, "loss": 0.0095, "step": 47960 }, { "loss_action": 0.01154538244009018, "loss_total": 0.01154538244009018, "step": 47960 }, { "grad_norm": 0.26288214325904846, "learning_rate": 5.746386954044082e-05, "loss": 0.0109, "step": 47970 }, { "loss_action": 0.015122957527637482, "loss_total": 0.015122957527637482, "step": 47970 }, { "grad_norm": 0.34003329277038574, "learning_rate": 5.744751969981195e-05, "loss": 0.0119, "step": 47980 }, { "loss_action": 0.009248325601220131, "loss_total": 0.009248325601220131, "step": 47980 }, { "grad_norm": 0.2069377452135086, "learning_rate": 5.7431169044733526e-05, "loss": 0.0101, "step": 47990 }, { "loss_action": 0.0103258416056633, "loss_total": 0.0103258416056633, "step": 47990 }, { "grad_norm": 0.20314115285873413, "learning_rate": 5.741481757699364e-05, "loss": 0.0106, "step": 48000 }, { "loss_action": 0.007381280418485403, "loss_total": 0.007381280418485403, "step": 48000 }, { "grad_norm": 0.2560993731021881, "learning_rate": 5.7398465298380434e-05, "loss": 0.0096, "step": 48010 }, { "loss_action": 0.01198359951376915, "loss_total": 0.01198359951376915, "step": 48010 }, { "grad_norm": 0.22971148788928986, "learning_rate": 5.7382112210682193e-05, "loss": 0.0099, "step": 48020 }, { "loss_action": 0.011206602677702904, "loss_total": 0.011206602677702904, "step": 48020 }, { "grad_norm": 0.24339598417282104, "learning_rate": 5.7365758315687266e-05, "loss": 0.0113, "step": 48030 }, { "loss_action": 0.008365167304873466, "loss_total": 0.008365167304873466, "step": 48030 }, { "grad_norm": 0.3030685484409332, "learning_rate": 5.734940361518407e-05, "loss": 0.0107, "step": 48040 }, { "loss_action": 0.009247246198356152, "loss_total": 0.009247246198356152, "step": 48040 }, { "grad_norm": 0.2852468192577362, "learning_rate": 5.733304811096116e-05, "loss": 0.0103, "step": 48050 }, { "loss_action": 0.008378512226045132, "loss_total": 0.008378512226045132, "step": 48050 }, { "grad_norm": 0.20764365792274475, "learning_rate": 5.731669180480713e-05, "loss": 0.01, "step": 48060 }, { "loss_action": 0.010575522668659687, "loss_total": 0.010575522668659687, "step": 48060 }, { "grad_norm": 0.23595193028450012, "learning_rate": 5.730033469851067e-05, "loss": 0.0102, "step": 48070 }, { "loss_action": 0.0068487306125462055, "loss_total": 0.0068487306125462055, "step": 48070 }, { "grad_norm": 0.43034282326698303, "learning_rate": 5.7283976793860607e-05, "loss": 0.0107, "step": 48080 }, { "loss_action": 0.01065040659159422, "loss_total": 0.01065040659159422, "step": 48080 }, { "grad_norm": 0.26292964816093445, "learning_rate": 5.726761809264577e-05, "loss": 0.0108, "step": 48090 }, { "loss_action": 0.012534845620393753, "loss_total": 0.012534845620393753, "step": 48090 }, { "grad_norm": 0.36691105365753174, "learning_rate": 5.7251258596655155e-05, "loss": 0.0109, "step": 48100 }, { "loss_action": 0.012557071633636951, "loss_total": 0.012557071633636951, "step": 48100 }, { "grad_norm": 0.23715521395206451, "learning_rate": 5.72348983076778e-05, "loss": 0.0112, "step": 48110 }, { "loss_action": 0.012870320118963718, "loss_total": 0.012870320118963718, "step": 48110 }, { "grad_norm": 0.29529479146003723, "learning_rate": 5.7218537227502854e-05, "loss": 0.0119, "step": 48120 }, { "loss_action": 0.011567069217562675, "loss_total": 0.011567069217562675, "step": 48120 }, { "grad_norm": 0.34736865758895874, "learning_rate": 5.720217535791951e-05, "loss": 0.0119, "step": 48130 }, { "loss_action": 0.016012290492653847, "loss_total": 0.016012290492653847, "step": 48130 }, { "grad_norm": 0.3145485520362854, "learning_rate": 5.718581270071711e-05, "loss": 0.0122, "step": 48140 }, { "loss_action": 0.013180233538150787, "loss_total": 0.013180233538150787, "step": 48140 }, { "grad_norm": 0.25122910737991333, "learning_rate": 5.716944925768505e-05, "loss": 0.0125, "step": 48150 }, { "loss_action": 0.012156755663454533, "loss_total": 0.012156755663454533, "step": 48150 }, { "grad_norm": 0.24089168012142181, "learning_rate": 5.7153085030612786e-05, "loss": 0.0116, "step": 48160 }, { "loss_action": 0.013311916962265968, "loss_total": 0.013311916962265968, "step": 48160 }, { "grad_norm": 0.2972024083137512, "learning_rate": 5.713672002128989e-05, "loss": 0.0115, "step": 48170 }, { "loss_action": 0.008655649609863758, "loss_total": 0.008655649609863758, "step": 48170 }, { "grad_norm": 0.1977522075176239, "learning_rate": 5.712035423150602e-05, "loss": 0.0097, "step": 48180 }, { "loss_action": 0.008172903209924698, "loss_total": 0.008172903209924698, "step": 48180 }, { "grad_norm": 0.2727634012699127, "learning_rate": 5.710398766305094e-05, "loss": 0.0097, "step": 48190 }, { "loss_action": 0.014788300730288029, "loss_total": 0.014788300730288029, "step": 48190 }, { "grad_norm": 0.256678968667984, "learning_rate": 5.708762031771442e-05, "loss": 0.0102, "step": 48200 }, { "loss_action": 0.009727553464472294, "loss_total": 0.009727553464472294, "step": 48200 }, { "grad_norm": 0.29629749059677124, "learning_rate": 5.707125219728642e-05, "loss": 0.0115, "step": 48210 }, { "loss_action": 0.007515051867812872, "loss_total": 0.007515051867812872, "step": 48210 }, { "grad_norm": 0.3104708194732666, "learning_rate": 5.7054883303556905e-05, "loss": 0.0107, "step": 48220 }, { "loss_action": 0.011175374500453472, "loss_total": 0.011175374500453472, "step": 48220 }, { "grad_norm": 0.29779279232025146, "learning_rate": 5.703851363831595e-05, "loss": 0.0112, "step": 48230 }, { "loss_action": 0.008927950635552406, "loss_total": 0.008927950635552406, "step": 48230 }, { "grad_norm": 0.26810401678085327, "learning_rate": 5.702214320335374e-05, "loss": 0.0109, "step": 48240 }, { "loss_action": 0.012565944343805313, "loss_total": 0.012565944343805313, "step": 48240 }, { "grad_norm": 0.24702373147010803, "learning_rate": 5.7005772000460514e-05, "loss": 0.0108, "step": 48250 }, { "loss_action": 0.009162293747067451, "loss_total": 0.009162293747067451, "step": 48250 }, { "grad_norm": 0.2617318630218506, "learning_rate": 5.698940003142656e-05, "loss": 0.0104, "step": 48260 }, { "loss_action": 0.00824698992073536, "loss_total": 0.00824698992073536, "step": 48260 }, { "grad_norm": 0.26218369603157043, "learning_rate": 5.697302729804236e-05, "loss": 0.0101, "step": 48270 }, { "loss_action": 0.008131206966936588, "loss_total": 0.008131206966936588, "step": 48270 }, { "grad_norm": 0.2382265329360962, "learning_rate": 5.695665380209837e-05, "loss": 0.0113, "step": 48280 }, { "loss_action": 0.009589391760528088, "loss_total": 0.009589391760528088, "step": 48280 }, { "grad_norm": 0.28257718682289124, "learning_rate": 5.6940279545385165e-05, "loss": 0.0108, "step": 48290 }, { "loss_action": 0.00841348897665739, "loss_total": 0.00841348897665739, "step": 48290 }, { "grad_norm": 0.2285400778055191, "learning_rate": 5.692390452969344e-05, "loss": 0.0097, "step": 48300 }, { "loss_action": 0.012221439741551876, "loss_total": 0.012221439741551876, "step": 48300 }, { "grad_norm": 0.28383031487464905, "learning_rate": 5.690752875681392e-05, "loss": 0.0116, "step": 48310 }, { "loss_action": 0.009851501323282719, "loss_total": 0.009851501323282719, "step": 48310 }, { "grad_norm": 0.3146378695964813, "learning_rate": 5.6891152228537435e-05, "loss": 0.0111, "step": 48320 }, { "loss_action": 0.010798676870763302, "loss_total": 0.010798676870763302, "step": 48320 }, { "grad_norm": 0.2569906413555145, "learning_rate": 5.687477494665492e-05, "loss": 0.0094, "step": 48330 }, { "loss_action": 0.011068030260503292, "loss_total": 0.011068030260503292, "step": 48330 }, { "grad_norm": 0.27886971831321716, "learning_rate": 5.685839691295733e-05, "loss": 0.0097, "step": 48340 }, { "loss_action": 0.011340686120092869, "loss_total": 0.011340686120092869, "step": 48340 }, { "grad_norm": 0.20917831361293793, "learning_rate": 5.6842018129235786e-05, "loss": 0.0098, "step": 48350 }, { "loss_action": 0.012314427644014359, "loss_total": 0.012314427644014359, "step": 48350 }, { "grad_norm": 0.26619431376457214, "learning_rate": 5.6825638597281404e-05, "loss": 0.0115, "step": 48360 }, { "loss_action": 0.00956621766090393, "loss_total": 0.00956621766090393, "step": 48360 }, { "grad_norm": 0.17434298992156982, "learning_rate": 5.680925831888546e-05, "loss": 0.0095, "step": 48370 }, { "loss_action": 0.011110893450677395, "loss_total": 0.011110893450677395, "step": 48370 }, { "grad_norm": 0.25803834199905396, "learning_rate": 5.6792877295839274e-05, "loss": 0.0092, "step": 48380 }, { "loss_action": 0.013013612478971481, "loss_total": 0.013013612478971481, "step": 48380 }, { "grad_norm": 0.21169689297676086, "learning_rate": 5.6776495529934224e-05, "loss": 0.0106, "step": 48390 }, { "loss_action": 0.007692384999245405, "loss_total": 0.007692384999245405, "step": 48390 }, { "grad_norm": 0.26111018657684326, "learning_rate": 5.6760113022961824e-05, "loss": 0.0106, "step": 48400 }, { "loss_action": 0.01306940894573927, "loss_total": 0.01306940894573927, "step": 48400 }, { "grad_norm": 0.28969576954841614, "learning_rate": 5.6743729776713617e-05, "loss": 0.0123, "step": 48410 }, { "loss_action": 0.010079003870487213, "loss_total": 0.010079003870487213, "step": 48410 }, { "grad_norm": 0.34621384739875793, "learning_rate": 5.672734579298126e-05, "loss": 0.0142, "step": 48420 }, { "loss_action": 0.013893309980630875, "loss_total": 0.013893309980630875, "step": 48420 }, { "grad_norm": 0.26799145340919495, "learning_rate": 5.671096107355649e-05, "loss": 0.0102, "step": 48430 }, { "loss_action": 0.009150141850113869, "loss_total": 0.009150141850113869, "step": 48430 }, { "grad_norm": 0.23767001926898956, "learning_rate": 5.66945756202311e-05, "loss": 0.0116, "step": 48440 }, { "loss_action": 0.015441106632351875, "loss_total": 0.015441106632351875, "step": 48440 }, { "grad_norm": 0.2686847150325775, "learning_rate": 5.667818943479699e-05, "loss": 0.0123, "step": 48450 }, { "loss_action": 0.008002366870641708, "loss_total": 0.008002366870641708, "step": 48450 }, { "grad_norm": 0.2681681513786316, "learning_rate": 5.666180251904612e-05, "loss": 0.0115, "step": 48460 }, { "loss_action": 0.012378853745758533, "loss_total": 0.012378853745758533, "step": 48460 }, { "grad_norm": 0.2752324342727661, "learning_rate": 5.6645414874770555e-05, "loss": 0.0095, "step": 48470 }, { "loss_action": 0.02263924665749073, "loss_total": 0.02263924665749073, "step": 48470 }, { "grad_norm": 0.2717481553554535, "learning_rate": 5.66290265037624e-05, "loss": 0.0116, "step": 48480 }, { "loss_action": 0.010883918963372707, "loss_total": 0.010883918963372707, "step": 48480 }, { "grad_norm": 0.22835808992385864, "learning_rate": 5.661263740781386e-05, "loss": 0.0113, "step": 48490 }, { "loss_action": 0.010340352542698383, "loss_total": 0.010340352542698383, "step": 48490 }, { "grad_norm": 0.2745310664176941, "learning_rate": 5.6596247588717254e-05, "loss": 0.0115, "step": 48500 }, { "loss_action": 0.0098219383507967, "loss_total": 0.0098219383507967, "step": 48500 }, { "grad_norm": 0.3391570746898651, "learning_rate": 5.6579857048264926e-05, "loss": 0.0117, "step": 48510 }, { "loss_action": 0.01106219831854105, "loss_total": 0.01106219831854105, "step": 48510 }, { "grad_norm": 0.3101808726787567, "learning_rate": 5.6563465788249314e-05, "loss": 0.0128, "step": 48520 }, { "loss_action": 0.009753920137882233, "loss_total": 0.009753920137882233, "step": 48520 }, { "grad_norm": 0.277217298746109, "learning_rate": 5.6547073810462956e-05, "loss": 0.0113, "step": 48530 }, { "loss_action": 0.01829170249402523, "loss_total": 0.01829170249402523, "step": 48530 }, { "grad_norm": 0.21784797310829163, "learning_rate": 5.653068111669846e-05, "loss": 0.0107, "step": 48540 }, { "loss_action": 0.01479857787489891, "loss_total": 0.01479857787489891, "step": 48540 }, { "grad_norm": 0.24427060782909393, "learning_rate": 5.651428770874848e-05, "loss": 0.0114, "step": 48550 }, { "loss_action": 0.009672059677541256, "loss_total": 0.009672059677541256, "step": 48550 }, { "grad_norm": 0.2916487157344818, "learning_rate": 5.64978935884058e-05, "loss": 0.0113, "step": 48560 }, { "loss_action": 0.010275645181536674, "loss_total": 0.010275645181536674, "step": 48560 }, { "grad_norm": 0.3233385682106018, "learning_rate": 5.6481498757463244e-05, "loss": 0.0105, "step": 48570 }, { "loss_action": 0.01147992629557848, "loss_total": 0.01147992629557848, "step": 48570 }, { "grad_norm": 0.31137219071388245, "learning_rate": 5.646510321771373e-05, "loss": 0.0108, "step": 48580 }, { "loss_action": 0.011716553010046482, "loss_total": 0.011716553010046482, "step": 48580 }, { "grad_norm": 0.25753188133239746, "learning_rate": 5.644870697095024e-05, "loss": 0.0119, "step": 48590 }, { "loss_action": 0.009545128792524338, "loss_total": 0.009545128792524338, "step": 48590 }, { "grad_norm": 0.3491126596927643, "learning_rate": 5.643231001896586e-05, "loss": 0.0117, "step": 48600 }, { "loss_action": 0.01278532762080431, "loss_total": 0.01278532762080431, "step": 48600 }, { "grad_norm": 0.22325704991817474, "learning_rate": 5.6415912363553726e-05, "loss": 0.0095, "step": 48610 }, { "loss_action": 0.009718752466142178, "loss_total": 0.009718752466142178, "step": 48610 }, { "grad_norm": 0.31068626046180725, "learning_rate": 5.639951400650706e-05, "loss": 0.0104, "step": 48620 }, { "loss_action": 0.00927019864320755, "loss_total": 0.00927019864320755, "step": 48620 }, { "grad_norm": 0.31993234157562256, "learning_rate": 5.6383114949619165e-05, "loss": 0.0124, "step": 48630 }, { "loss_action": 0.012136142700910568, "loss_total": 0.012136142700910568, "step": 48630 }, { "grad_norm": 0.29887309670448303, "learning_rate": 5.636671519468342e-05, "loss": 0.0116, "step": 48640 }, { "loss_action": 0.008438270539045334, "loss_total": 0.008438270539045334, "step": 48640 }, { "grad_norm": 0.25524255633354187, "learning_rate": 5.635031474349327e-05, "loss": 0.0097, "step": 48650 }, { "loss_action": 0.010155386291444302, "loss_total": 0.010155386291444302, "step": 48650 }, { "grad_norm": 0.2383059859275818, "learning_rate": 5.6333913597842246e-05, "loss": 0.0104, "step": 48660 }, { "loss_action": 0.014400346204638481, "loss_total": 0.014400346204638481, "step": 48660 }, { "grad_norm": 0.1818467527627945, "learning_rate": 5.6317511759523955e-05, "loss": 0.0097, "step": 48670 }, { "loss_action": 0.006159383803606033, "loss_total": 0.006159383803606033, "step": 48670 }, { "grad_norm": 0.22653482854366302, "learning_rate": 5.630110923033207e-05, "loss": 0.0108, "step": 48680 }, { "loss_action": 0.01392904482781887, "loss_total": 0.01392904482781887, "step": 48680 }, { "grad_norm": 0.301392525434494, "learning_rate": 5.628470601206036e-05, "loss": 0.0101, "step": 48690 }, { "loss_action": 0.01173719298094511, "loss_total": 0.01173719298094511, "step": 48690 }, { "grad_norm": 0.40440791845321655, "learning_rate": 5.626830210650266e-05, "loss": 0.0107, "step": 48700 }, { "loss_action": 0.009535901248455048, "loss_total": 0.009535901248455048, "step": 48700 }, { "grad_norm": 0.23003220558166504, "learning_rate": 5.625189751545285e-05, "loss": 0.0102, "step": 48710 }, { "loss_action": 0.011599653400480747, "loss_total": 0.011599653400480747, "step": 48710 }, { "grad_norm": 0.2522071897983551, "learning_rate": 5.6235492240704936e-05, "loss": 0.0101, "step": 48720 }, { "loss_action": 0.008548803627490997, "loss_total": 0.008548803627490997, "step": 48720 }, { "grad_norm": 0.24362896382808685, "learning_rate": 5.621908628405296e-05, "loss": 0.0116, "step": 48730 }, { "loss_action": 0.009832145646214485, "loss_total": 0.009832145646214485, "step": 48730 }, { "grad_norm": 0.2063436508178711, "learning_rate": 5.620267964729106e-05, "loss": 0.0107, "step": 48740 }, { "loss_action": 0.009694925509393215, "loss_total": 0.009694925509393215, "step": 48740 }, { "grad_norm": 0.2681087255477905, "learning_rate": 5.618627233221344e-05, "loss": 0.0106, "step": 48750 }, { "loss_action": 0.01028198841959238, "loss_total": 0.01028198841959238, "step": 48750 }, { "grad_norm": 0.27926722168922424, "learning_rate": 5.616986434061438e-05, "loss": 0.0106, "step": 48760 }, { "loss_action": 0.010304057039320469, "loss_total": 0.010304057039320469, "step": 48760 }, { "grad_norm": 0.3198097050189972, "learning_rate": 5.615345567428822e-05, "loss": 0.0121, "step": 48770 }, { "loss_action": 0.013724954798817635, "loss_total": 0.013724954798817635, "step": 48770 }, { "grad_norm": 0.2169826477766037, "learning_rate": 5.613704633502941e-05, "loss": 0.0096, "step": 48780 }, { "loss_action": 0.010151217691600323, "loss_total": 0.010151217691600323, "step": 48780 }, { "grad_norm": 0.2718814015388489, "learning_rate": 5.612063632463245e-05, "loss": 0.0106, "step": 48790 }, { "loss_action": 0.00935582909733057, "loss_total": 0.00935582909733057, "step": 48790 }, { "grad_norm": 0.2817841172218323, "learning_rate": 5.610422564489188e-05, "loss": 0.0109, "step": 48800 }, { "loss_action": 0.012755296193063259, "loss_total": 0.012755296193063259, "step": 48800 }, { "grad_norm": 0.24763265252113342, "learning_rate": 5.608781429760239e-05, "loss": 0.0098, "step": 48810 }, { "loss_action": 0.0087667778134346, "loss_total": 0.0087667778134346, "step": 48810 }, { "grad_norm": 0.2206127941608429, "learning_rate": 5.607140228455866e-05, "loss": 0.0099, "step": 48820 }, { "loss_action": 0.010106921195983887, "loss_total": 0.010106921195983887, "step": 48820 }, { "grad_norm": 0.23522107303142548, "learning_rate": 5.605498960755553e-05, "loss": 0.0106, "step": 48830 }, { "loss_action": 0.00986863486468792, "loss_total": 0.00986863486468792, "step": 48830 }, { "grad_norm": 0.2767447531223297, "learning_rate": 5.603857626838782e-05, "loss": 0.0121, "step": 48840 }, { "loss_action": 0.0112282894551754, "loss_total": 0.0112282894551754, "step": 48840 }, { "grad_norm": 0.2310497760772705, "learning_rate": 5.60221622688505e-05, "loss": 0.0102, "step": 48850 }, { "loss_action": 0.008088686503469944, "loss_total": 0.008088686503469944, "step": 48850 }, { "grad_norm": 0.2759403586387634, "learning_rate": 5.6005747610738565e-05, "loss": 0.0132, "step": 48860 }, { "loss_action": 0.009246586821973324, "loss_total": 0.009246586821973324, "step": 48860 }, { "grad_norm": 0.3745485544204712, "learning_rate": 5.59893322958471e-05, "loss": 0.0125, "step": 48870 }, { "loss_action": 0.013723666779696941, "loss_total": 0.013723666779696941, "step": 48870 }, { "grad_norm": 0.24595655500888824, "learning_rate": 5.5972916325971256e-05, "loss": 0.013, "step": 48880 }, { "loss_action": 0.012422855012118816, "loss_total": 0.012422855012118816, "step": 48880 }, { "grad_norm": 0.339374303817749, "learning_rate": 5.595649970290628e-05, "loss": 0.0118, "step": 48890 }, { "loss_action": 0.010517120361328125, "loss_total": 0.010517120361328125, "step": 48890 }, { "grad_norm": 0.2509027123451233, "learning_rate": 5.5940082428447426e-05, "loss": 0.0123, "step": 48900 }, { "loss_action": 0.01440284214913845, "loss_total": 0.01440284214913845, "step": 48900 }, { "grad_norm": 0.4081728756427765, "learning_rate": 5.592366450439012e-05, "loss": 0.0127, "step": 48910 }, { "loss_action": 0.012334616854786873, "loss_total": 0.012334616854786873, "step": 48910 }, { "grad_norm": 0.2726041078567505, "learning_rate": 5.590724593252975e-05, "loss": 0.0129, "step": 48920 }, { "loss_action": 0.012055081315338612, "loss_total": 0.012055081315338612, "step": 48920 }, { "grad_norm": 0.27176687121391296, "learning_rate": 5.589082671466184e-05, "loss": 0.0111, "step": 48930 }, { "loss_action": 0.019030388444662094, "loss_total": 0.019030388444662094, "step": 48930 }, { "grad_norm": 0.34769362211227417, "learning_rate": 5.587440685258199e-05, "loss": 0.0132, "step": 48940 }, { "loss_action": 0.010183622129261494, "loss_total": 0.010183622129261494, "step": 48940 }, { "grad_norm": 0.38120365142822266, "learning_rate": 5.585798634808583e-05, "loss": 0.0119, "step": 48950 }, { "loss_action": 0.010409207083284855, "loss_total": 0.010409207083284855, "step": 48950 }, { "grad_norm": 0.3427448868751526, "learning_rate": 5.584156520296909e-05, "loss": 0.0113, "step": 48960 }, { "loss_action": 0.009795021265745163, "loss_total": 0.009795021265745163, "step": 48960 }, { "grad_norm": 0.2776813209056854, "learning_rate": 5.582514341902757e-05, "loss": 0.0105, "step": 48970 }, { "loss_action": 0.00937473401427269, "loss_total": 0.00937473401427269, "step": 48970 }, { "grad_norm": 0.2625476121902466, "learning_rate": 5.580872099805713e-05, "loss": 0.0103, "step": 48980 }, { "loss_action": 0.016239361837506294, "loss_total": 0.016239361837506294, "step": 48980 }, { "grad_norm": 0.270841509103775, "learning_rate": 5.5792297941853674e-05, "loss": 0.0109, "step": 48990 }, { "loss_action": 0.011902141384780407, "loss_total": 0.011902141384780407, "step": 48990 }, { "grad_norm": 0.26790663599967957, "learning_rate": 5.5775874252213247e-05, "loss": 0.0116, "step": 49000 }, { "loss_action": 0.014477599412202835, "loss_total": 0.014477599412202835, "step": 49000 }, { "grad_norm": 0.24076004326343536, "learning_rate": 5.575944993093189e-05, "loss": 0.0123, "step": 49010 }, { "loss_action": 0.007491645868867636, "loss_total": 0.007491645868867636, "step": 49010 }, { "grad_norm": 0.22554358839988708, "learning_rate": 5.574302497980574e-05, "loss": 0.0101, "step": 49020 }, { "loss_action": 0.011159646324813366, "loss_total": 0.011159646324813366, "step": 49020 }, { "grad_norm": 0.2286606878042221, "learning_rate": 5.5726599400631005e-05, "loss": 0.0105, "step": 49030 }, { "loss_action": 0.010210497304797173, "loss_total": 0.010210497304797173, "step": 49030 }, { "grad_norm": 0.2449335902929306, "learning_rate": 5.571017319520399e-05, "loss": 0.0104, "step": 49040 }, { "loss_action": 0.012799780815839767, "loss_total": 0.012799780815839767, "step": 49040 }, { "grad_norm": 0.25864437222480774, "learning_rate": 5.5693746365320984e-05, "loss": 0.0108, "step": 49050 }, { "loss_action": 0.00977269932627678, "loss_total": 0.00977269932627678, "step": 49050 }, { "grad_norm": 0.2694491446018219, "learning_rate": 5.567731891277848e-05, "loss": 0.0101, "step": 49060 }, { "loss_action": 0.008993283845484257, "loss_total": 0.008993283845484257, "step": 49060 }, { "grad_norm": 0.26909375190734863, "learning_rate": 5.566089083937288e-05, "loss": 0.0105, "step": 49070 }, { "loss_action": 0.007634402252733707, "loss_total": 0.007634402252733707, "step": 49070 }, { "grad_norm": 0.258013516664505, "learning_rate": 5.564446214690079e-05, "loss": 0.0092, "step": 49080 }, { "loss_action": 0.008911950513720512, "loss_total": 0.008911950513720512, "step": 49080 }, { "grad_norm": 0.39034223556518555, "learning_rate": 5.56280328371588e-05, "loss": 0.0112, "step": 49090 }, { "loss_action": 0.01420400757342577, "loss_total": 0.01420400757342577, "step": 49090 }, { "grad_norm": 0.2232769876718521, "learning_rate": 5.5611602911943596e-05, "loss": 0.0117, "step": 49100 }, { "loss_action": 0.01059818733483553, "loss_total": 0.01059818733483553, "step": 49100 }, { "grad_norm": 0.2634027302265167, "learning_rate": 5.559517237305194e-05, "loss": 0.0112, "step": 49110 }, { "loss_action": 0.008977841585874557, "loss_total": 0.008977841585874557, "step": 49110 }, { "grad_norm": 0.30046454071998596, "learning_rate": 5.557874122228064e-05, "loss": 0.011, "step": 49120 }, { "loss_action": 0.013253052718937397, "loss_total": 0.013253052718937397, "step": 49120 }, { "grad_norm": 0.23227809369564056, "learning_rate": 5.55623094614266e-05, "loss": 0.0111, "step": 49130 }, { "loss_action": 0.008694328367710114, "loss_total": 0.008694328367710114, "step": 49130 }, { "grad_norm": 0.2784028947353363, "learning_rate": 5.5545877092286743e-05, "loss": 0.0109, "step": 49140 }, { "loss_action": 0.008775600232183933, "loss_total": 0.008775600232183933, "step": 49140 }, { "grad_norm": 0.2568252682685852, "learning_rate": 5.552944411665811e-05, "loss": 0.0109, "step": 49150 }, { "loss_action": 0.013229603879153728, "loss_total": 0.013229603879153728, "step": 49150 }, { "grad_norm": 0.2778420150279999, "learning_rate": 5.5513010536337795e-05, "loss": 0.0113, "step": 49160 }, { "loss_action": 0.015824249014258385, "loss_total": 0.015824249014258385, "step": 49160 }, { "grad_norm": 0.2130279839038849, "learning_rate": 5.5496576353122934e-05, "loss": 0.0104, "step": 49170 }, { "loss_action": 0.013352804817259312, "loss_total": 0.013352804817259312, "step": 49170 }, { "grad_norm": 0.2408929318189621, "learning_rate": 5.548014156881074e-05, "loss": 0.0111, "step": 49180 }, { "loss_action": 0.010830779559910297, "loss_total": 0.010830779559910297, "step": 49180 }, { "grad_norm": 0.20722442865371704, "learning_rate": 5.5463706185198494e-05, "loss": 0.0105, "step": 49190 }, { "loss_action": 0.008567309007048607, "loss_total": 0.008567309007048607, "step": 49190 }, { "grad_norm": 0.23031289875507355, "learning_rate": 5.544727020408358e-05, "loss": 0.0117, "step": 49200 }, { "loss_action": 0.009615651331841946, "loss_total": 0.009615651331841946, "step": 49200 }, { "grad_norm": 0.234760120511055, "learning_rate": 5.5430833627263366e-05, "loss": 0.0103, "step": 49210 }, { "loss_action": 0.01015626359730959, "loss_total": 0.01015626359730959, "step": 49210 }, { "grad_norm": 0.3374118208885193, "learning_rate": 5.5414396456535354e-05, "loss": 0.0106, "step": 49220 }, { "loss_action": 0.014645726419985294, "loss_total": 0.014645726419985294, "step": 49220 }, { "grad_norm": 0.19735021889209747, "learning_rate": 5.539795869369709e-05, "loss": 0.0102, "step": 49230 }, { "loss_action": 0.015205551870167255, "loss_total": 0.015205551870167255, "step": 49230 }, { "grad_norm": 0.23020265996456146, "learning_rate": 5.538152034054618e-05, "loss": 0.0111, "step": 49240 }, { "loss_action": 0.009222873486578465, "loss_total": 0.009222873486578465, "step": 49240 }, { "grad_norm": 0.28190603852272034, "learning_rate": 5.536508139888028e-05, "loss": 0.011, "step": 49250 }, { "loss_action": 0.008503571152687073, "loss_total": 0.008503571152687073, "step": 49250 }, { "grad_norm": 0.2650469243526459, "learning_rate": 5.534864187049716e-05, "loss": 0.0113, "step": 49260 }, { "loss_action": 0.00887114554643631, "loss_total": 0.00887114554643631, "step": 49260 }, { "grad_norm": 0.21653962135314941, "learning_rate": 5.5332201757194615e-05, "loss": 0.0109, "step": 49270 }, { "loss_action": 0.00889948382973671, "loss_total": 0.00889948382973671, "step": 49270 }, { "grad_norm": 0.3003203272819519, "learning_rate": 5.531576106077049e-05, "loss": 0.01, "step": 49280 }, { "loss_action": 0.008286693133413792, "loss_total": 0.008286693133413792, "step": 49280 }, { "grad_norm": 0.31403499841690063, "learning_rate": 5.529931978302272e-05, "loss": 0.0112, "step": 49290 }, { "loss_action": 0.012150254100561142, "loss_total": 0.012150254100561142, "step": 49290 }, { "grad_norm": 0.24010787904262543, "learning_rate": 5.528287792574932e-05, "loss": 0.0096, "step": 49300 }, { "loss_action": 0.0076459851115942, "loss_total": 0.0076459851115942, "step": 49300 }, { "grad_norm": 0.25008708238601685, "learning_rate": 5.5266435490748324e-05, "loss": 0.0107, "step": 49310 }, { "loss_action": 0.010086316615343094, "loss_total": 0.010086316615343094, "step": 49310 }, { "grad_norm": 0.25497063994407654, "learning_rate": 5.524999247981787e-05, "loss": 0.0108, "step": 49320 }, { "loss_action": 0.00956539437174797, "loss_total": 0.00956539437174797, "step": 49320 }, { "grad_norm": 0.2642359137535095, "learning_rate": 5.523354889475613e-05, "loss": 0.0122, "step": 49330 }, { "loss_action": 0.017695460468530655, "loss_total": 0.017695460468530655, "step": 49330 }, { "grad_norm": 0.254253625869751, "learning_rate": 5.521710473736134e-05, "loss": 0.0106, "step": 49340 }, { "loss_action": 0.009106523357331753, "loss_total": 0.009106523357331753, "step": 49340 }, { "grad_norm": 0.3336150348186493, "learning_rate": 5.5200660009431826e-05, "loss": 0.01, "step": 49350 }, { "loss_action": 0.010751824826002121, "loss_total": 0.010751824826002121, "step": 49350 }, { "grad_norm": 0.2845182716846466, "learning_rate": 5.518421471276596e-05, "loss": 0.0093, "step": 49360 }, { "loss_action": 0.013063673861324787, "loss_total": 0.013063673861324787, "step": 49360 }, { "grad_norm": 0.2162574678659439, "learning_rate": 5.5167768849162174e-05, "loss": 0.0099, "step": 49370 }, { "loss_action": 0.008942008018493652, "loss_total": 0.008942008018493652, "step": 49370 }, { "grad_norm": 0.2619131803512573, "learning_rate": 5.515132242041893e-05, "loss": 0.0107, "step": 49380 }, { "loss_action": 0.008511073887348175, "loss_total": 0.008511073887348175, "step": 49380 }, { "grad_norm": 0.24980369210243225, "learning_rate": 5.513487542833483e-05, "loss": 0.0096, "step": 49390 }, { "loss_action": 0.009920107200741768, "loss_total": 0.009920107200741768, "step": 49390 }, { "grad_norm": 0.24396440386772156, "learning_rate": 5.5118427874708466e-05, "loss": 0.011, "step": 49400 }, { "loss_action": 0.010770709253847599, "loss_total": 0.010770709253847599, "step": 49400 }, { "grad_norm": 0.22263869643211365, "learning_rate": 5.510197976133853e-05, "loss": 0.0104, "step": 49410 }, { "loss_action": 0.010266349650919437, "loss_total": 0.010266349650919437, "step": 49410 }, { "grad_norm": 0.23361878097057343, "learning_rate": 5.508553109002376e-05, "loss": 0.0097, "step": 49420 }, { "loss_action": 0.01012938842177391, "loss_total": 0.01012938842177391, "step": 49420 }, { "grad_norm": 0.22158785164356232, "learning_rate": 5.5069081862562957e-05, "loss": 0.0102, "step": 49430 }, { "loss_action": 0.011450904421508312, "loss_total": 0.011450904421508312, "step": 49430 }, { "grad_norm": 0.30554908514022827, "learning_rate": 5.5052632080754965e-05, "loss": 0.0107, "step": 49440 }, { "loss_action": 0.007619240786880255, "loss_total": 0.007619240786880255, "step": 49440 }, { "grad_norm": 0.2522341310977936, "learning_rate": 5.503618174639874e-05, "loss": 0.0105, "step": 49450 }, { "loss_action": 0.009963251650333405, "loss_total": 0.009963251650333405, "step": 49450 }, { "grad_norm": 0.1886892169713974, "learning_rate": 5.501973086129325e-05, "loss": 0.011, "step": 49460 }, { "loss_action": 0.010760135017335415, "loss_total": 0.010760135017335415, "step": 49460 }, { "grad_norm": 0.2210424542427063, "learning_rate": 5.500327942723753e-05, "loss": 0.0107, "step": 49470 }, { "loss_action": 0.011192013509571552, "loss_total": 0.011192013509571552, "step": 49470 }, { "grad_norm": 0.27421385049819946, "learning_rate": 5.498682744603071e-05, "loss": 0.0102, "step": 49480 }, { "loss_action": 0.012281826697289944, "loss_total": 0.012281826697289944, "step": 49480 }, { "grad_norm": 0.2339451014995575, "learning_rate": 5.497037491947194e-05, "loss": 0.0102, "step": 49490 }, { "loss_action": 0.009931804612278938, "loss_total": 0.009931804612278938, "step": 49490 }, { "grad_norm": 0.2583167552947998, "learning_rate": 5.4953921849360424e-05, "loss": 0.0111, "step": 49500 }, { "loss_action": 0.012074927799403667, "loss_total": 0.012074927799403667, "step": 49500 }, { "grad_norm": 0.34242895245552063, "learning_rate": 5.493746823749547e-05, "loss": 0.011, "step": 49510 }, { "loss_action": 0.011938810348510742, "loss_total": 0.011938810348510742, "step": 49510 }, { "grad_norm": 0.28655773401260376, "learning_rate": 5.49210140856764e-05, "loss": 0.011, "step": 49520 }, { "loss_action": 0.00775092002004385, "loss_total": 0.00775092002004385, "step": 49520 }, { "grad_norm": 0.23240551352500916, "learning_rate": 5.4904559395702647e-05, "loss": 0.0096, "step": 49530 }, { "loss_action": 0.014285575598478317, "loss_total": 0.014285575598478317, "step": 49530 }, { "grad_norm": 0.27029767632484436, "learning_rate": 5.488810416937364e-05, "loss": 0.0118, "step": 49540 }, { "loss_action": 0.006923837587237358, "loss_total": 0.006923837587237358, "step": 49540 }, { "grad_norm": 0.23196089267730713, "learning_rate": 5.4871648408488926e-05, "loss": 0.0104, "step": 49550 }, { "loss_action": 0.00857800804078579, "loss_total": 0.00857800804078579, "step": 49550 }, { "grad_norm": 0.21974532306194305, "learning_rate": 5.485519211484807e-05, "loss": 0.0126, "step": 49560 }, { "loss_action": 0.008889925666153431, "loss_total": 0.008889925666153431, "step": 49560 }, { "grad_norm": 0.28459081053733826, "learning_rate": 5.4838735290250676e-05, "loss": 0.0108, "step": 49570 }, { "loss_action": 0.011685210280120373, "loss_total": 0.011685210280120373, "step": 49570 }, { "grad_norm": 0.25622400641441345, "learning_rate": 5.482227793649649e-05, "loss": 0.0109, "step": 49580 }, { "loss_action": 0.009408899582922459, "loss_total": 0.009408899582922459, "step": 49580 }, { "grad_norm": 0.2352580577135086, "learning_rate": 5.480582005538524e-05, "loss": 0.0098, "step": 49590 }, { "loss_action": 0.012173875235021114, "loss_total": 0.012173875235021114, "step": 49590 }, { "grad_norm": 0.31143417954444885, "learning_rate": 5.478936164871671e-05, "loss": 0.0105, "step": 49600 }, { "loss_action": 0.008294500410556793, "loss_total": 0.008294500410556793, "step": 49600 }, { "grad_norm": 0.22119709849357605, "learning_rate": 5.477290271829081e-05, "loss": 0.011, "step": 49610 }, { "loss_action": 0.014174514450132847, "loss_total": 0.014174514450132847, "step": 49610 }, { "grad_norm": 0.25875523686408997, "learning_rate": 5.475644326590744e-05, "loss": 0.013, "step": 49620 }, { "loss_action": 0.013654835522174835, "loss_total": 0.013654835522174835, "step": 49620 }, { "grad_norm": 0.26144394278526306, "learning_rate": 5.473998329336658e-05, "loss": 0.012, "step": 49630 }, { "loss_action": 0.009455866180360317, "loss_total": 0.009455866180360317, "step": 49630 }, { "grad_norm": 0.2363368421792984, "learning_rate": 5.4723522802468286e-05, "loss": 0.0092, "step": 49640 }, { "loss_action": 0.015040813013911247, "loss_total": 0.015040813013911247, "step": 49640 }, { "grad_norm": 0.3520713150501251, "learning_rate": 5.470706179501264e-05, "loss": 0.0125, "step": 49650 }, { "loss_action": 0.018108675256371498, "loss_total": 0.018108675256371498, "step": 49650 }, { "grad_norm": 0.2678927183151245, "learning_rate": 5.4690600272799776e-05, "loss": 0.0121, "step": 49660 }, { "loss_action": 0.010323620401322842, "loss_total": 0.010323620401322842, "step": 49660 }, { "grad_norm": 0.33037763833999634, "learning_rate": 5.467413823762993e-05, "loss": 0.0117, "step": 49670 }, { "loss_action": 0.011760600842535496, "loss_total": 0.011760600842535496, "step": 49670 }, { "grad_norm": 0.2642153799533844, "learning_rate": 5.465767569130335e-05, "loss": 0.0106, "step": 49680 }, { "loss_action": 0.008115999400615692, "loss_total": 0.008115999400615692, "step": 49680 }, { "grad_norm": 0.266613245010376, "learning_rate": 5.464121263562036e-05, "loss": 0.01, "step": 49690 }, { "loss_action": 0.010663403198122978, "loss_total": 0.010663403198122978, "step": 49690 }, { "grad_norm": 0.3395044505596161, "learning_rate": 5.4624749072381343e-05, "loss": 0.0118, "step": 49700 }, { "loss_action": 0.007222998887300491, "loss_total": 0.007222998887300491, "step": 49700 }, { "grad_norm": 0.3289375901222229, "learning_rate": 5.460828500338672e-05, "loss": 0.0103, "step": 49710 }, { "loss_action": 0.008945942856371403, "loss_total": 0.008945942856371403, "step": 49710 }, { "grad_norm": 0.26590418815612793, "learning_rate": 5.459182043043698e-05, "loss": 0.0114, "step": 49720 }, { "loss_action": 0.009840462356805801, "loss_total": 0.009840462356805801, "step": 49720 }, { "grad_norm": 0.2553647458553314, "learning_rate": 5.457535535533265e-05, "loss": 0.0108, "step": 49730 }, { "loss_action": 0.01069878414273262, "loss_total": 0.01069878414273262, "step": 49730 }, { "grad_norm": 0.28611961007118225, "learning_rate": 5.4558889779874334e-05, "loss": 0.0096, "step": 49740 }, { "loss_action": 0.008767972700297832, "loss_total": 0.008767972700297832, "step": 49740 }, { "grad_norm": 0.31507474184036255, "learning_rate": 5.454242370586269e-05, "loss": 0.0122, "step": 49750 }, { "loss_action": 0.010359366424381733, "loss_total": 0.010359366424381733, "step": 49750 }, { "grad_norm": 0.2703031897544861, "learning_rate": 5.452595713509843e-05, "loss": 0.0117, "step": 49760 }, { "loss_action": 0.012506481260061264, "loss_total": 0.012506481260061264, "step": 49760 }, { "grad_norm": 0.26317399740219116, "learning_rate": 5.4509490069382274e-05, "loss": 0.0129, "step": 49770 }, { "loss_action": 0.015047483146190643, "loss_total": 0.015047483146190643, "step": 49770 }, { "grad_norm": 0.4087221324443817, "learning_rate": 5.449302251051509e-05, "loss": 0.0119, "step": 49780 }, { "loss_action": 0.01824137382209301, "loss_total": 0.01824137382209301, "step": 49780 }, { "grad_norm": 0.45964744687080383, "learning_rate": 5.44765544602977e-05, "loss": 0.0129, "step": 49790 }, { "loss_action": 0.009221918880939484, "loss_total": 0.009221918880939484, "step": 49790 }, { "grad_norm": 0.23383361101150513, "learning_rate": 5.446008592053107e-05, "loss": 0.0115, "step": 49800 }, { "loss_action": 0.012892220169305801, "loss_total": 0.012892220169305801, "step": 49800 }, { "grad_norm": 0.26483529806137085, "learning_rate": 5.4443616893016135e-05, "loss": 0.0148, "step": 49810 }, { "loss_action": 0.0114174485206604, "loss_total": 0.0114174485206604, "step": 49810 }, { "grad_norm": 0.24599795043468475, "learning_rate": 5.4427147379553934e-05, "loss": 0.0121, "step": 49820 }, { "loss_action": 0.012298708781599998, "loss_total": 0.012298708781599998, "step": 49820 }, { "grad_norm": 0.2545260787010193, "learning_rate": 5.441067738194556e-05, "loss": 0.0118, "step": 49830 }, { "loss_action": 0.011903110891580582, "loss_total": 0.011903110891580582, "step": 49830 }, { "grad_norm": 0.1945914775133133, "learning_rate": 5.439420690199214e-05, "loss": 0.0109, "step": 49840 }, { "loss_action": 0.009823862463235855, "loss_total": 0.009823862463235855, "step": 49840 }, { "grad_norm": 0.2661621570587158, "learning_rate": 5.437773594149484e-05, "loss": 0.0108, "step": 49850 }, { "loss_action": 0.008627049624919891, "loss_total": 0.008627049624919891, "step": 49850 }, { "grad_norm": 0.2777964472770691, "learning_rate": 5.436126450225495e-05, "loss": 0.0096, "step": 49860 }, { "loss_action": 0.00961186271160841, "loss_total": 0.00961186271160841, "step": 49860 }, { "grad_norm": 0.2776205539703369, "learning_rate": 5.434479258607371e-05, "loss": 0.0094, "step": 49870 }, { "loss_action": 0.006937745492905378, "loss_total": 0.006937745492905378, "step": 49870 }, { "grad_norm": 0.19683857262134552, "learning_rate": 5.43283201947525e-05, "loss": 0.0094, "step": 49880 }, { "loss_action": 0.017829231917858124, "loss_total": 0.017829231917858124, "step": 49880 }, { "grad_norm": 0.23388206958770752, "learning_rate": 5.431184733009268e-05, "loss": 0.0114, "step": 49890 }, { "loss_action": 0.0088961161673069, "loss_total": 0.0088961161673069, "step": 49890 }, { "grad_norm": 0.24855682253837585, "learning_rate": 5.4295373993895736e-05, "loss": 0.0097, "step": 49900 }, { "loss_action": 0.013549919240176678, "loss_total": 0.013549919240176678, "step": 49900 }, { "grad_norm": 0.2639963626861572, "learning_rate": 5.4278900187963157e-05, "loss": 0.0113, "step": 49910 }, { "loss_action": 0.011677383445203304, "loss_total": 0.011677383445203304, "step": 49910 }, { "grad_norm": 0.2825172245502472, "learning_rate": 5.426242591409646e-05, "loss": 0.0103, "step": 49920 }, { "loss_action": 0.008321937173604965, "loss_total": 0.008321937173604965, "step": 49920 }, { "grad_norm": 0.26812201738357544, "learning_rate": 5.42459511740973e-05, "loss": 0.0094, "step": 49930 }, { "loss_action": 0.010770393535494804, "loss_total": 0.010770393535494804, "step": 49930 }, { "grad_norm": 0.24071836471557617, "learning_rate": 5.422947596976729e-05, "loss": 0.0103, "step": 49940 }, { "loss_action": 0.012339633889496326, "loss_total": 0.012339633889496326, "step": 49940 }, { "grad_norm": 0.27042514085769653, "learning_rate": 5.4213000302908134e-05, "loss": 0.0107, "step": 49950 }, { "loss_action": 0.008162792772054672, "loss_total": 0.008162792772054672, "step": 49950 }, { "grad_norm": 0.22201518714427948, "learning_rate": 5.419652417532162e-05, "loss": 0.0114, "step": 49960 }, { "loss_action": 0.01656694896519184, "loss_total": 0.01656694896519184, "step": 49960 }, { "grad_norm": 0.2479807734489441, "learning_rate": 5.4180047588809534e-05, "loss": 0.0113, "step": 49970 }, { "loss_action": 0.01341165229678154, "loss_total": 0.01341165229678154, "step": 49970 }, { "grad_norm": 0.18791788816452026, "learning_rate": 5.4163570545173704e-05, "loss": 0.0096, "step": 49980 }, { "loss_action": 0.008603067137300968, "loss_total": 0.008603067137300968, "step": 49980 }, { "grad_norm": 0.2397354692220688, "learning_rate": 5.414709304621608e-05, "loss": 0.0106, "step": 49990 }, { "loss_action": 0.009787563234567642, "loss_total": 0.009787563234567642, "step": 49990 }, { "grad_norm": 0.27778732776641846, "learning_rate": 5.413061509373858e-05, "loss": 0.0104, "step": 50000 }, { "loss_action": 0.010518454015254974, "loss_total": 0.010518454015254974, "step": 50000 }, { "grad_norm": 0.22645695507526398, "learning_rate": 5.411413668954324e-05, "loss": 0.0105, "step": 50010 }, { "loss_action": 0.007560596335679293, "loss_total": 0.007560596335679293, "step": 50010 }, { "grad_norm": 0.2390393316745758, "learning_rate": 5.4097657835432083e-05, "loss": 0.0094, "step": 50020 }, { "loss_action": 0.010826675221323967, "loss_total": 0.010826675221323967, "step": 50020 }, { "grad_norm": 0.2584865093231201, "learning_rate": 5.408117853320723e-05, "loss": 0.0109, "step": 50030 }, { "loss_action": 0.009462244808673859, "loss_total": 0.009462244808673859, "step": 50030 }, { "grad_norm": 0.2523461878299713, "learning_rate": 5.406469878467084e-05, "loss": 0.0112, "step": 50040 }, { "loss_action": 0.010707098990678787, "loss_total": 0.010707098990678787, "step": 50040 }, { "grad_norm": 0.21468983590602875, "learning_rate": 5.404821859162509e-05, "loss": 0.0107, "step": 50050 }, { "loss_action": 0.009096367284655571, "loss_total": 0.009096367284655571, "step": 50050 }, { "grad_norm": 0.22405831515789032, "learning_rate": 5.403173795587225e-05, "loss": 0.0101, "step": 50060 }, { "loss_action": 0.010370863601565361, "loss_total": 0.010370863601565361, "step": 50060 }, { "grad_norm": 0.23379482328891754, "learning_rate": 5.4015256879214606e-05, "loss": 0.01, "step": 50070 }, { "loss_action": 0.00912349671125412, "loss_total": 0.00912349671125412, "step": 50070 }, { "grad_norm": 0.2977353632450104, "learning_rate": 5.39987753634545e-05, "loss": 0.0103, "step": 50080 }, { "loss_action": 0.0089547298848629, "loss_total": 0.0089547298848629, "step": 50080 }, { "grad_norm": 0.27717113494873047, "learning_rate": 5.3982293410394335e-05, "loss": 0.0102, "step": 50090 }, { "loss_action": 0.006542452611029148, "loss_total": 0.006542452611029148, "step": 50090 }, { "grad_norm": 0.33185720443725586, "learning_rate": 5.396581102183655e-05, "loss": 0.0097, "step": 50100 }, { "loss_action": 0.010395662859082222, "loss_total": 0.010395662859082222, "step": 50100 }, { "grad_norm": 0.265419065952301, "learning_rate": 5.3949328199583634e-05, "loss": 0.0118, "step": 50110 }, { "loss_action": 0.009463257156312466, "loss_total": 0.009463257156312466, "step": 50110 }, { "grad_norm": 0.3882827162742615, "learning_rate": 5.393284494543813e-05, "loss": 0.0101, "step": 50120 }, { "loss_action": 0.008550828322768211, "loss_total": 0.008550828322768211, "step": 50120 }, { "grad_norm": 0.32609209418296814, "learning_rate": 5.391636126120262e-05, "loss": 0.0104, "step": 50130 }, { "loss_action": 0.013864733278751373, "loss_total": 0.013864733278751373, "step": 50130 }, { "grad_norm": 0.20174525678157806, "learning_rate": 5.389987714867971e-05, "loss": 0.0117, "step": 50140 }, { "loss_action": 0.012127794325351715, "loss_total": 0.012127794325351715, "step": 50140 }, { "grad_norm": 0.21402737498283386, "learning_rate": 5.3883392609672114e-05, "loss": 0.0099, "step": 50150 }, { "loss_action": 0.009432848542928696, "loss_total": 0.009432848542928696, "step": 50150 }, { "grad_norm": 0.2275102585554123, "learning_rate": 5.3866907645982545e-05, "loss": 0.0098, "step": 50160 }, { "loss_action": 0.008526022545993328, "loss_total": 0.008526022545993328, "step": 50160 }, { "grad_norm": 0.1990853250026703, "learning_rate": 5.385042225941375e-05, "loss": 0.0095, "step": 50170 }, { "loss_action": 0.008827386423945427, "loss_total": 0.008827386423945427, "step": 50170 }, { "grad_norm": 0.1921939253807068, "learning_rate": 5.3833936451768585e-05, "loss": 0.0097, "step": 50180 }, { "loss_action": 0.0066271680407226086, "loss_total": 0.0066271680407226086, "step": 50180 }, { "grad_norm": 0.25841742753982544, "learning_rate": 5.3817450224849884e-05, "loss": 0.0093, "step": 50190 }, { "loss_action": 0.007270382717251778, "loss_total": 0.007270382717251778, "step": 50190 }, { "grad_norm": 0.20139923691749573, "learning_rate": 5.380096358046056e-05, "loss": 0.0095, "step": 50200 }, { "loss_action": 0.014002876356244087, "loss_total": 0.014002876356244087, "step": 50200 }, { "grad_norm": 0.23706898093223572, "learning_rate": 5.378447652040359e-05, "loss": 0.0102, "step": 50210 }, { "loss_action": 0.00910627469420433, "loss_total": 0.00910627469420433, "step": 50210 }, { "grad_norm": 0.25498056411743164, "learning_rate": 5.376798904648195e-05, "loss": 0.0115, "step": 50220 }, { "loss_action": 0.015514027327299118, "loss_total": 0.015514027327299118, "step": 50220 }, { "grad_norm": 0.2571250796318054, "learning_rate": 5.375150116049869e-05, "loss": 0.0106, "step": 50230 }, { "loss_action": 0.012021477334201336, "loss_total": 0.012021477334201336, "step": 50230 }, { "grad_norm": 0.2708289921283722, "learning_rate": 5.373501286425691e-05, "loss": 0.0104, "step": 50240 }, { "loss_action": 0.010310471057891846, "loss_total": 0.010310471057891846, "step": 50240 }, { "grad_norm": 0.240743488073349, "learning_rate": 5.3718524159559726e-05, "loss": 0.009, "step": 50250 }, { "loss_action": 0.015113599598407745, "loss_total": 0.015113599598407745, "step": 50250 }, { "grad_norm": 0.2669605314731598, "learning_rate": 5.370203504821034e-05, "loss": 0.0108, "step": 50260 }, { "loss_action": 0.006848589517176151, "loss_total": 0.006848589517176151, "step": 50260 }, { "grad_norm": 0.20495112240314484, "learning_rate": 5.368554553201196e-05, "loss": 0.0102, "step": 50270 }, { "loss_action": 0.010547447949647903, "loss_total": 0.010547447949647903, "step": 50270 }, { "grad_norm": 0.27939000725746155, "learning_rate": 5.3669055612767874e-05, "loss": 0.0098, "step": 50280 }, { "loss_action": 0.008099405094981194, "loss_total": 0.008099405094981194, "step": 50280 }, { "grad_norm": 0.27892544865608215, "learning_rate": 5.3652565292281376e-05, "loss": 0.0096, "step": 50290 }, { "loss_action": 0.010161472484469414, "loss_total": 0.010161472484469414, "step": 50290 }, { "grad_norm": 0.24591311812400818, "learning_rate": 5.3636074572355824e-05, "loss": 0.0111, "step": 50300 }, { "loss_action": 0.010709778405725956, "loss_total": 0.010709778405725956, "step": 50300 }, { "grad_norm": 0.23774737119674683, "learning_rate": 5.361958345479463e-05, "loss": 0.0095, "step": 50310 }, { "loss_action": 0.008960203267633915, "loss_total": 0.008960203267633915, "step": 50310 }, { "grad_norm": 0.3098691403865814, "learning_rate": 5.360309194140123e-05, "loss": 0.0097, "step": 50320 }, { "loss_action": 0.00880182720720768, "loss_total": 0.00880182720720768, "step": 50320 }, { "grad_norm": 0.361471027135849, "learning_rate": 5.3586600033979106e-05, "loss": 0.0095, "step": 50330 }, { "loss_action": 0.011036832816898823, "loss_total": 0.011036832816898823, "step": 50330 }, { "grad_norm": 0.21977660059928894, "learning_rate": 5.357010773433181e-05, "loss": 0.0097, "step": 50340 }, { "loss_action": 0.007314485963433981, "loss_total": 0.007314485963433981, "step": 50340 }, { "grad_norm": 0.1648441106081009, "learning_rate": 5.3553615044262895e-05, "loss": 0.0092, "step": 50350 }, { "loss_action": 0.007534143980592489, "loss_total": 0.007534143980592489, "step": 50350 }, { "grad_norm": 0.26771581172943115, "learning_rate": 5.3537121965575964e-05, "loss": 0.0107, "step": 50360 }, { "loss_action": 0.010563218966126442, "loss_total": 0.010563218966126442, "step": 50360 }, { "grad_norm": 0.25780031085014343, "learning_rate": 5.352062850007471e-05, "loss": 0.011, "step": 50370 }, { "loss_action": 0.009542005136609077, "loss_total": 0.009542005136609077, "step": 50370 }, { "grad_norm": 0.3483877182006836, "learning_rate": 5.350413464956282e-05, "loss": 0.0099, "step": 50380 }, { "loss_action": 0.007466388866305351, "loss_total": 0.007466388866305351, "step": 50380 }, { "grad_norm": 0.2647343873977661, "learning_rate": 5.348764041584403e-05, "loss": 0.0119, "step": 50390 }, { "loss_action": 0.011712182313203812, "loss_total": 0.011712182313203812, "step": 50390 }, { "grad_norm": 0.2681950032711029, "learning_rate": 5.347114580072212e-05, "loss": 0.0126, "step": 50400 }, { "loss_action": 0.011270361952483654, "loss_total": 0.011270361952483654, "step": 50400 }, { "grad_norm": 0.27865198254585266, "learning_rate": 5.345465080600093e-05, "loss": 0.012, "step": 50410 }, { "loss_action": 0.010190720669925213, "loss_total": 0.010190720669925213, "step": 50410 }, { "grad_norm": 0.27427735924720764, "learning_rate": 5.3438155433484326e-05, "loss": 0.0103, "step": 50420 }, { "loss_action": 0.013329658657312393, "loss_total": 0.013329658657312393, "step": 50420 }, { "grad_norm": 0.2012752741575241, "learning_rate": 5.3421659684976197e-05, "loss": 0.0106, "step": 50430 }, { "loss_action": 0.012501772493124008, "loss_total": 0.012501772493124008, "step": 50430 }, { "grad_norm": 0.38387951254844666, "learning_rate": 5.340516356228052e-05, "loss": 0.0118, "step": 50440 }, { "loss_action": 0.008855571039021015, "loss_total": 0.008855571039021015, "step": 50440 }, { "grad_norm": 0.2997581362724304, "learning_rate": 5.338866706720128e-05, "loss": 0.0114, "step": 50450 }, { "loss_action": 0.010540640912950039, "loss_total": 0.010540640912950039, "step": 50450 }, { "grad_norm": 0.2955341339111328, "learning_rate": 5.337217020154249e-05, "loss": 0.011, "step": 50460 }, { "loss_action": 0.00968955084681511, "loss_total": 0.00968955084681511, "step": 50460 }, { "grad_norm": 0.2893218994140625, "learning_rate": 5.335567296710825e-05, "loss": 0.0114, "step": 50470 }, { "loss_action": 0.012336613610386848, "loss_total": 0.012336613610386848, "step": 50470 }, { "grad_norm": 0.22320206463336945, "learning_rate": 5.333917536570265e-05, "loss": 0.0118, "step": 50480 }, { "loss_action": 0.014940018765628338, "loss_total": 0.014940018765628338, "step": 50480 }, { "grad_norm": 0.29722854495048523, "learning_rate": 5.332267739912986e-05, "loss": 0.0096, "step": 50490 }, { "loss_action": 0.010828248225152493, "loss_total": 0.010828248225152493, "step": 50490 }, { "grad_norm": 0.20539772510528564, "learning_rate": 5.330617906919405e-05, "loss": 0.0109, "step": 50500 }, { "loss_action": 0.011043097823858261, "loss_total": 0.011043097823858261, "step": 50500 }, { "grad_norm": 0.25247448682785034, "learning_rate": 5.328968037769949e-05, "loss": 0.0105, "step": 50510 }, { "loss_action": 0.011129666119813919, "loss_total": 0.011129666119813919, "step": 50510 }, { "grad_norm": 0.2326621115207672, "learning_rate": 5.327318132645042e-05, "loss": 0.0104, "step": 50520 }, { "loss_action": 0.01244039461016655, "loss_total": 0.01244039461016655, "step": 50520 }, { "grad_norm": 0.28595003485679626, "learning_rate": 5.325668191725116e-05, "loss": 0.0114, "step": 50530 }, { "loss_action": 0.009340287186205387, "loss_total": 0.009340287186205387, "step": 50530 }, { "grad_norm": 0.23739023506641388, "learning_rate": 5.324018215190606e-05, "loss": 0.0117, "step": 50540 }, { "loss_action": 0.012297069653868675, "loss_total": 0.012297069653868675, "step": 50540 }, { "grad_norm": 0.282426118850708, "learning_rate": 5.3223682032219515e-05, "loss": 0.0103, "step": 50550 }, { "loss_action": 0.01069498062133789, "loss_total": 0.01069498062133789, "step": 50550 }, { "grad_norm": 0.2313494086265564, "learning_rate": 5.320718155999595e-05, "loss": 0.0103, "step": 50560 }, { "loss_action": 0.0163216982036829, "loss_total": 0.0163216982036829, "step": 50560 }, { "grad_norm": 0.37995103001594543, "learning_rate": 5.3190680737039835e-05, "loss": 0.0121, "step": 50570 }, { "loss_action": 0.009322572499513626, "loss_total": 0.009322572499513626, "step": 50570 }, { "grad_norm": 0.2132527232170105, "learning_rate": 5.317417956515567e-05, "loss": 0.0095, "step": 50580 }, { "loss_action": 0.009721938520669937, "loss_total": 0.009721938520669937, "step": 50580 }, { "grad_norm": 0.2618669271469116, "learning_rate": 5.315767804614798e-05, "loss": 0.0094, "step": 50590 }, { "loss_action": 0.007996058091521263, "loss_total": 0.007996058091521263, "step": 50590 }, { "grad_norm": 0.19733701646327972, "learning_rate": 5.3141176181821395e-05, "loss": 0.0102, "step": 50600 }, { "loss_action": 0.016758130863308907, "loss_total": 0.016758130863308907, "step": 50600 }, { "grad_norm": 0.36192962527275085, "learning_rate": 5.31246739739805e-05, "loss": 0.0121, "step": 50610 }, { "loss_action": 0.009786022827029228, "loss_total": 0.009786022827029228, "step": 50610 }, { "grad_norm": 0.18206335604190826, "learning_rate": 5.310817142442994e-05, "loss": 0.0106, "step": 50620 }, { "loss_action": 0.013765157200396061, "loss_total": 0.013765157200396061, "step": 50620 }, { "grad_norm": 0.28810039162635803, "learning_rate": 5.309166853497445e-05, "loss": 0.0122, "step": 50630 }, { "loss_action": 0.00803590752184391, "loss_total": 0.00803590752184391, "step": 50630 }, { "grad_norm": 0.18232545256614685, "learning_rate": 5.307516530741873e-05, "loss": 0.0102, "step": 50640 }, { "loss_action": 0.009026522748172283, "loss_total": 0.009026522748172283, "step": 50640 }, { "grad_norm": 0.20658178627490997, "learning_rate": 5.305866174356754e-05, "loss": 0.0116, "step": 50650 }, { "loss_action": 0.01265951432287693, "loss_total": 0.01265951432287693, "step": 50650 }, { "grad_norm": 0.18687838315963745, "learning_rate": 5.304215784522571e-05, "loss": 0.0118, "step": 50660 }, { "loss_action": 0.008683602325618267, "loss_total": 0.008683602325618267, "step": 50660 }, { "grad_norm": 0.3239601254463196, "learning_rate": 5.302565361419808e-05, "loss": 0.0097, "step": 50670 }, { "loss_action": 0.012488267384469509, "loss_total": 0.012488267384469509, "step": 50670 }, { "grad_norm": 0.2161472886800766, "learning_rate": 5.3009149052289507e-05, "loss": 0.0102, "step": 50680 }, { "loss_action": 0.01169018354266882, "loss_total": 0.01169018354266882, "step": 50680 }, { "grad_norm": 0.2480059117078781, "learning_rate": 5.299264416130493e-05, "loss": 0.0095, "step": 50690 }, { "loss_action": 0.009281317703425884, "loss_total": 0.009281317703425884, "step": 50690 }, { "grad_norm": 0.26254695653915405, "learning_rate": 5.297613894304928e-05, "loss": 0.0093, "step": 50700 }, { "loss_action": 0.009595791809260845, "loss_total": 0.009595791809260845, "step": 50700 }, { "grad_norm": 0.2778779864311218, "learning_rate": 5.2959633399327534e-05, "loss": 0.0107, "step": 50710 }, { "loss_action": 0.007975021377205849, "loss_total": 0.007975021377205849, "step": 50710 }, { "grad_norm": 0.25643396377563477, "learning_rate": 5.294312753194476e-05, "loss": 0.0106, "step": 50720 }, { "loss_action": 0.015260325744748116, "loss_total": 0.015260325744748116, "step": 50720 }, { "grad_norm": 0.28048795461654663, "learning_rate": 5.292662134270596e-05, "loss": 0.0112, "step": 50730 }, { "loss_action": 0.013447116129100323, "loss_total": 0.013447116129100323, "step": 50730 }, { "grad_norm": 0.2489534467458725, "learning_rate": 5.291011483341626e-05, "loss": 0.0107, "step": 50740 }, { "loss_action": 0.008565451949834824, "loss_total": 0.008565451949834824, "step": 50740 }, { "grad_norm": 0.2995317876338959, "learning_rate": 5.2893608005880767e-05, "loss": 0.0104, "step": 50750 }, { "loss_action": 0.011512864381074905, "loss_total": 0.011512864381074905, "step": 50750 }, { "grad_norm": 0.2531225383281708, "learning_rate": 5.287710086190467e-05, "loss": 0.0103, "step": 50760 }, { "loss_action": 0.008992292918264866, "loss_total": 0.008992292918264866, "step": 50760 }, { "grad_norm": 0.23687708377838135, "learning_rate": 5.286059340329314e-05, "loss": 0.0107, "step": 50770 }, { "loss_action": 0.008846815675497055, "loss_total": 0.008846815675497055, "step": 50770 }, { "grad_norm": 0.28516870737075806, "learning_rate": 5.284408563185141e-05, "loss": 0.0099, "step": 50780 }, { "loss_action": 0.00752447172999382, "loss_total": 0.00752447172999382, "step": 50780 }, { "grad_norm": 0.36127445101737976, "learning_rate": 5.282757754938476e-05, "loss": 0.0105, "step": 50790 }, { "loss_action": 0.010255474597215652, "loss_total": 0.010255474597215652, "step": 50790 }, { "grad_norm": 0.23738349974155426, "learning_rate": 5.281106915769849e-05, "loss": 0.0092, "step": 50800 }, { "loss_action": 0.012142439372837543, "loss_total": 0.012142439372837543, "step": 50800 }, { "grad_norm": 0.3046010434627533, "learning_rate": 5.2794560458597897e-05, "loss": 0.0112, "step": 50810 }, { "loss_action": 0.007857261225581169, "loss_total": 0.007857261225581169, "step": 50810 }, { "grad_norm": 0.26412642002105713, "learning_rate": 5.27780514538884e-05, "loss": 0.0096, "step": 50820 }, { "loss_action": 0.009397746063768864, "loss_total": 0.009397746063768864, "step": 50820 }, { "grad_norm": 0.25176653265953064, "learning_rate": 5.2761542145375365e-05, "loss": 0.0109, "step": 50830 }, { "loss_action": 0.009481783024966717, "loss_total": 0.009481783024966717, "step": 50830 }, { "grad_norm": 0.19723781943321228, "learning_rate": 5.274503253486421e-05, "loss": 0.0105, "step": 50840 }, { "loss_action": 0.00954780075699091, "loss_total": 0.00954780075699091, "step": 50840 }, { "grad_norm": 0.30236801505088806, "learning_rate": 5.272852262416046e-05, "loss": 0.0105, "step": 50850 }, { "loss_action": 0.01201319694519043, "loss_total": 0.01201319694519043, "step": 50850 }, { "grad_norm": 0.2574636936187744, "learning_rate": 5.2712012415069555e-05, "loss": 0.0118, "step": 50860 }, { "loss_action": 0.010318573564291, "loss_total": 0.010318573564291, "step": 50860 }, { "grad_norm": 0.2706747055053711, "learning_rate": 5.269550190939705e-05, "loss": 0.01, "step": 50870 }, { "loss_action": 0.009496464394032955, "loss_total": 0.009496464394032955, "step": 50870 }, { "grad_norm": 0.33213990926742554, "learning_rate": 5.267899110894852e-05, "loss": 0.0108, "step": 50880 }, { "loss_action": 0.007576277945190668, "loss_total": 0.007576277945190668, "step": 50880 }, { "grad_norm": 0.37180081009864807, "learning_rate": 5.266248001552955e-05, "loss": 0.0096, "step": 50890 }, { "loss_action": 0.008332719095051289, "loss_total": 0.008332719095051289, "step": 50890 }, { "grad_norm": 0.3139978051185608, "learning_rate": 5.264596863094575e-05, "loss": 0.0112, "step": 50900 }, { "loss_action": 0.014084049500524998, "loss_total": 0.014084049500524998, "step": 50900 }, { "grad_norm": 0.22255727648735046, "learning_rate": 5.262945695700282e-05, "loss": 0.01, "step": 50910 }, { "loss_action": 0.009575748816132545, "loss_total": 0.009575748816132545, "step": 50910 }, { "grad_norm": 0.2571183145046234, "learning_rate": 5.261294499550643e-05, "loss": 0.0118, "step": 50920 }, { "loss_action": 0.008749661967158318, "loss_total": 0.008749661967158318, "step": 50920 }, { "grad_norm": 0.21188445389270782, "learning_rate": 5.25964327482623e-05, "loss": 0.0094, "step": 50930 }, { "loss_action": 0.012502258643507957, "loss_total": 0.012502258643507957, "step": 50930 }, { "grad_norm": 0.1962595134973526, "learning_rate": 5.257992021707617e-05, "loss": 0.0116, "step": 50940 }, { "loss_action": 0.011828894726932049, "loss_total": 0.011828894726932049, "step": 50940 }, { "grad_norm": 0.226091668009758, "learning_rate": 5.256340740375387e-05, "loss": 0.01, "step": 50950 }, { "loss_action": 0.012494532391428947, "loss_total": 0.012494532391428947, "step": 50950 }, { "grad_norm": 0.1791277527809143, "learning_rate": 5.254689431010117e-05, "loss": 0.0106, "step": 50960 }, { "loss_action": 0.012745016254484653, "loss_total": 0.012745016254484653, "step": 50960 }, { "grad_norm": 0.20896174013614655, "learning_rate": 5.253038093792395e-05, "loss": 0.0099, "step": 50970 }, { "loss_action": 0.009105508215725422, "loss_total": 0.009105508215725422, "step": 50970 }, { "grad_norm": 0.2737797498703003, "learning_rate": 5.251386728902806e-05, "loss": 0.0094, "step": 50980 }, { "loss_action": 0.011567188426852226, "loss_total": 0.011567188426852226, "step": 50980 }, { "grad_norm": 0.3097136616706848, "learning_rate": 5.2497353365219446e-05, "loss": 0.0105, "step": 50990 }, { "loss_action": 0.008603914640843868, "loss_total": 0.008603914640843868, "step": 50990 }, { "grad_norm": 0.2396310418844223, "learning_rate": 5.2480839168304e-05, "loss": 0.0103, "step": 51000 }, { "loss_action": 0.010176795534789562, "loss_total": 0.010176795534789562, "step": 51000 }, { "grad_norm": 0.23886607587337494, "learning_rate": 5.246432470008773e-05, "loss": 0.0098, "step": 51010 }, { "loss_action": 0.010187297128140926, "loss_total": 0.010187297128140926, "step": 51010 }, { "grad_norm": 0.23223626613616943, "learning_rate": 5.2447809962376616e-05, "loss": 0.0113, "step": 51020 }, { "loss_action": 0.008088215254247189, "loss_total": 0.008088215254247189, "step": 51020 }, { "grad_norm": 0.2622393071651459, "learning_rate": 5.243129495697666e-05, "loss": 0.009, "step": 51030 }, { "loss_action": 0.010088834911584854, "loss_total": 0.010088834911584854, "step": 51030 }, { "grad_norm": 0.23915304243564606, "learning_rate": 5.241477968569397e-05, "loss": 0.0098, "step": 51040 }, { "loss_action": 0.009468477219343185, "loss_total": 0.009468477219343185, "step": 51040 }, { "grad_norm": 0.26553890109062195, "learning_rate": 5.23982641503346e-05, "loss": 0.0107, "step": 51050 }, { "loss_action": 0.009634477086365223, "loss_total": 0.009634477086365223, "step": 51050 }, { "grad_norm": 0.2218378782272339, "learning_rate": 5.238174835270465e-05, "loss": 0.0105, "step": 51060 }, { "loss_action": 0.015147458761930466, "loss_total": 0.015147458761930466, "step": 51060 }, { "grad_norm": 0.2611524760723114, "learning_rate": 5.23652322946103e-05, "loss": 0.0117, "step": 51070 }, { "loss_action": 0.009939533658325672, "loss_total": 0.009939533658325672, "step": 51070 }, { "grad_norm": 0.23739729821681976, "learning_rate": 5.234871597785771e-05, "loss": 0.0095, "step": 51080 }, { "loss_action": 0.010007161647081375, "loss_total": 0.010007161647081375, "step": 51080 }, { "grad_norm": 0.2563648223876953, "learning_rate": 5.233219940425306e-05, "loss": 0.0102, "step": 51090 }, { "loss_action": 0.014522203244268894, "loss_total": 0.014522203244268894, "step": 51090 }, { "grad_norm": 0.26178231835365295, "learning_rate": 5.2315682575602576e-05, "loss": 0.0089, "step": 51100 }, { "loss_action": 0.0084109241142869, "loss_total": 0.0084109241142869, "step": 51100 }, { "grad_norm": 0.26553773880004883, "learning_rate": 5.229916549371254e-05, "loss": 0.0101, "step": 51110 }, { "loss_action": 0.00674773845821619, "loss_total": 0.00674773845821619, "step": 51110 }, { "grad_norm": 0.24758023023605347, "learning_rate": 5.228264816038924e-05, "loss": 0.0084, "step": 51120 }, { "loss_action": 0.008610398508608341, "loss_total": 0.008610398508608341, "step": 51120 }, { "grad_norm": 0.17948533594608307, "learning_rate": 5.2266130577438935e-05, "loss": 0.0104, "step": 51130 }, { "loss_action": 0.011122796684503555, "loss_total": 0.011122796684503555, "step": 51130 }, { "grad_norm": 0.18859615921974182, "learning_rate": 5.224961274666802e-05, "loss": 0.0117, "step": 51140 }, { "loss_action": 0.009270163252949715, "loss_total": 0.009270163252949715, "step": 51140 }, { "grad_norm": 0.26378530263900757, "learning_rate": 5.223309466988283e-05, "loss": 0.0102, "step": 51150 }, { "loss_action": 0.007614827249199152, "loss_total": 0.007614827249199152, "step": 51150 }, { "grad_norm": 0.21800507605075836, "learning_rate": 5.221657634888976e-05, "loss": 0.0103, "step": 51160 }, { "loss_action": 0.00865147728472948, "loss_total": 0.00865147728472948, "step": 51160 }, { "grad_norm": 0.3299176096916199, "learning_rate": 5.2200057785495235e-05, "loss": 0.0096, "step": 51170 }, { "loss_action": 0.007337062619626522, "loss_total": 0.007337062619626522, "step": 51170 }, { "grad_norm": 0.254597008228302, "learning_rate": 5.2183538981505706e-05, "loss": 0.0107, "step": 51180 }, { "loss_action": 0.007923346012830734, "loss_total": 0.007923346012830734, "step": 51180 }, { "grad_norm": 0.2433827668428421, "learning_rate": 5.216701993872762e-05, "loss": 0.0099, "step": 51190 }, { "loss_action": 0.011304273270070553, "loss_total": 0.011304273270070553, "step": 51190 }, { "grad_norm": 0.24115146696567535, "learning_rate": 5.215050065896752e-05, "loss": 0.0105, "step": 51200 }, { "loss_action": 0.010432793758809566, "loss_total": 0.010432793758809566, "step": 51200 }, { "grad_norm": 0.2650556266307831, "learning_rate": 5.2133981144031875e-05, "loss": 0.0099, "step": 51210 }, { "loss_action": 0.013224023394286633, "loss_total": 0.013224023394286633, "step": 51210 }, { "grad_norm": 0.22538341581821442, "learning_rate": 5.211746139572727e-05, "loss": 0.0103, "step": 51220 }, { "loss_action": 0.010297244414687157, "loss_total": 0.010297244414687157, "step": 51220 }, { "grad_norm": 0.31245702505111694, "learning_rate": 5.210094141586026e-05, "loss": 0.0105, "step": 51230 }, { "loss_action": 0.008086461573839188, "loss_total": 0.008086461573839188, "step": 51230 }, { "grad_norm": 0.3375587463378906, "learning_rate": 5.2084421206237476e-05, "loss": 0.0097, "step": 51240 }, { "loss_action": 0.009864388033747673, "loss_total": 0.009864388033747673, "step": 51240 }, { "grad_norm": 0.21111848950386047, "learning_rate": 5.20679007686655e-05, "loss": 0.0115, "step": 51250 }, { "loss_action": 0.00762510858476162, "loss_total": 0.00762510858476162, "step": 51250 }, { "grad_norm": 0.2381155639886856, "learning_rate": 5.205138010495102e-05, "loss": 0.011, "step": 51260 }, { "loss_action": 0.008989071473479271, "loss_total": 0.008989071473479271, "step": 51260 }, { "grad_norm": 0.31801003217697144, "learning_rate": 5.20348592169007e-05, "loss": 0.0098, "step": 51270 }, { "loss_action": 0.00940518919378519, "loss_total": 0.00940518919378519, "step": 51270 }, { "grad_norm": 0.27995869517326355, "learning_rate": 5.201833810632123e-05, "loss": 0.0099, "step": 51280 }, { "loss_action": 0.007916275411844254, "loss_total": 0.007916275411844254, "step": 51280 }, { "grad_norm": 0.2211100161075592, "learning_rate": 5.200181677501933e-05, "loss": 0.011, "step": 51290 }, { "loss_action": 0.008648053742945194, "loss_total": 0.008648053742945194, "step": 51290 }, { "grad_norm": 0.24252380430698395, "learning_rate": 5.1985295224801777e-05, "loss": 0.0112, "step": 51300 }, { "loss_action": 0.015210416167974472, "loss_total": 0.015210416167974472, "step": 51300 }, { "grad_norm": 0.25206229090690613, "learning_rate": 5.196877345747531e-05, "loss": 0.0108, "step": 51310 }, { "loss_action": 0.010458624921739101, "loss_total": 0.010458624921739101, "step": 51310 }, { "grad_norm": 0.23575466871261597, "learning_rate": 5.195225147484674e-05, "loss": 0.0105, "step": 51320 }, { "loss_action": 0.014374010264873505, "loss_total": 0.014374010264873505, "step": 51320 }, { "grad_norm": 0.24599291384220123, "learning_rate": 5.193572927872288e-05, "loss": 0.0128, "step": 51330 }, { "loss_action": 0.011489521712064743, "loss_total": 0.011489521712064743, "step": 51330 }, { "grad_norm": 0.2430076003074646, "learning_rate": 5.191920687091059e-05, "loss": 0.0106, "step": 51340 }, { "loss_action": 0.014064949937164783, "loss_total": 0.014064949937164783, "step": 51340 }, { "grad_norm": 0.27814802527427673, "learning_rate": 5.1902684253216695e-05, "loss": 0.0108, "step": 51350 }, { "loss_action": 0.007747844327241182, "loss_total": 0.007747844327241182, "step": 51350 }, { "grad_norm": 0.2620883584022522, "learning_rate": 5.1886161427448134e-05, "loss": 0.0083, "step": 51360 }, { "loss_action": 0.008649379946291447, "loss_total": 0.008649379946291447, "step": 51360 }, { "grad_norm": 0.30948299169540405, "learning_rate": 5.186963839541179e-05, "loss": 0.0099, "step": 51370 }, { "loss_action": 0.010024904273450375, "loss_total": 0.010024904273450375, "step": 51370 }, { "grad_norm": 0.1640162467956543, "learning_rate": 5.185311515891459e-05, "loss": 0.0092, "step": 51380 }, { "loss_action": 0.011004401370882988, "loss_total": 0.011004401370882988, "step": 51380 }, { "grad_norm": 0.29157745838165283, "learning_rate": 5.1836591719763516e-05, "loss": 0.0108, "step": 51390 }, { "loss_action": 0.010262567549943924, "loss_total": 0.010262567549943924, "step": 51390 }, { "grad_norm": 0.31694087386131287, "learning_rate": 5.182006807976554e-05, "loss": 0.0104, "step": 51400 }, { "loss_action": 0.0076940325088799, "loss_total": 0.0076940325088799, "step": 51400 }, { "grad_norm": 0.2746061682701111, "learning_rate": 5.180354424072763e-05, "loss": 0.0104, "step": 51410 }, { "loss_action": 0.012468790635466576, "loss_total": 0.012468790635466576, "step": 51410 }, { "grad_norm": 0.2657775580883026, "learning_rate": 5.178702020445686e-05, "loss": 0.0091, "step": 51420 }, { "loss_action": 0.008140775375068188, "loss_total": 0.008140775375068188, "step": 51420 }, { "grad_norm": 0.23972392082214355, "learning_rate": 5.177049597276024e-05, "loss": 0.01, "step": 51430 }, { "loss_action": 0.010311652906239033, "loss_total": 0.010311652906239033, "step": 51430 }, { "grad_norm": 0.30696702003479004, "learning_rate": 5.175397154744482e-05, "loss": 0.0102, "step": 51440 }, { "loss_action": 0.014593632891774178, "loss_total": 0.014593632891774178, "step": 51440 }, { "grad_norm": 0.22729292511940002, "learning_rate": 5.1737446930317736e-05, "loss": 0.0099, "step": 51450 }, { "loss_action": 0.008737840689718723, "loss_total": 0.008737840689718723, "step": 51450 }, { "grad_norm": 0.21526288986206055, "learning_rate": 5.172092212318604e-05, "loss": 0.0111, "step": 51460 }, { "loss_action": 0.007503805216401815, "loss_total": 0.007503805216401815, "step": 51460 }, { "grad_norm": 0.21011747419834137, "learning_rate": 5.170439712785692e-05, "loss": 0.0097, "step": 51470 }, { "loss_action": 0.012794183567166328, "loss_total": 0.012794183567166328, "step": 51470 }, { "grad_norm": 0.26970478892326355, "learning_rate": 5.1687871946137467e-05, "loss": 0.0113, "step": 51480 }, { "loss_action": 0.00853758491575718, "loss_total": 0.00853758491575718, "step": 51480 }, { "grad_norm": 0.2307986170053482, "learning_rate": 5.16713465798349e-05, "loss": 0.0101, "step": 51490 }, { "loss_action": 0.011687166057527065, "loss_total": 0.011687166057527065, "step": 51490 }, { "grad_norm": 0.24200725555419922, "learning_rate": 5.165482103075637e-05, "loss": 0.0086, "step": 51500 }, { "loss_action": 0.007144862320274115, "loss_total": 0.007144862320274115, "step": 51500 }, { "grad_norm": 0.2983379662036896, "learning_rate": 5.163829530070909e-05, "loss": 0.0095, "step": 51510 }, { "loss_action": 0.0068589141592383385, "loss_total": 0.0068589141592383385, "step": 51510 }, { "grad_norm": 0.22842416167259216, "learning_rate": 5.162176939150032e-05, "loss": 0.0097, "step": 51520 }, { "loss_action": 0.009515062905848026, "loss_total": 0.009515062905848026, "step": 51520 }, { "grad_norm": 0.32392558455467224, "learning_rate": 5.160524330493728e-05, "loss": 0.0108, "step": 51530 }, { "loss_action": 0.010615063831210136, "loss_total": 0.010615063831210136, "step": 51530 }, { "grad_norm": 0.32544729113578796, "learning_rate": 5.158871704282724e-05, "loss": 0.0103, "step": 51540 }, { "loss_action": 0.012044091708958149, "loss_total": 0.012044091708958149, "step": 51540 }, { "grad_norm": 0.2798037827014923, "learning_rate": 5.15721906069775e-05, "loss": 0.0115, "step": 51550 }, { "loss_action": 0.011139373295009136, "loss_total": 0.011139373295009136, "step": 51550 }, { "grad_norm": 0.2045092135667801, "learning_rate": 5.155566399919536e-05, "loss": 0.009, "step": 51560 }, { "loss_action": 0.008788682520389557, "loss_total": 0.008788682520389557, "step": 51560 }, { "grad_norm": 0.178905189037323, "learning_rate": 5.153913722128813e-05, "loss": 0.0115, "step": 51570 }, { "loss_action": 0.011705184355378151, "loss_total": 0.011705184355378151, "step": 51570 }, { "grad_norm": 0.25077033042907715, "learning_rate": 5.1522610275063176e-05, "loss": 0.0103, "step": 51580 }, { "loss_action": 0.010859648697078228, "loss_total": 0.010859648697078228, "step": 51580 }, { "grad_norm": 0.2026081681251526, "learning_rate": 5.150608316232786e-05, "loss": 0.01, "step": 51590 }, { "loss_action": 0.016184911131858826, "loss_total": 0.016184911131858826, "step": 51590 }, { "grad_norm": 0.26576319336891174, "learning_rate": 5.148955588488955e-05, "loss": 0.0106, "step": 51600 }, { "loss_action": 0.007787779439240694, "loss_total": 0.007787779439240694, "step": 51600 }, { "grad_norm": 0.3304488956928253, "learning_rate": 5.147302844455564e-05, "loss": 0.0108, "step": 51610 }, { "loss_action": 0.007996474392712116, "loss_total": 0.007996474392712116, "step": 51610 }, { "grad_norm": 0.27682557702064514, "learning_rate": 5.145650084313356e-05, "loss": 0.0088, "step": 51620 }, { "loss_action": 0.009923649951815605, "loss_total": 0.009923649951815605, "step": 51620 }, { "grad_norm": 0.22608120739459991, "learning_rate": 5.1439973082430734e-05, "loss": 0.0099, "step": 51630 }, { "loss_action": 0.011387498117983341, "loss_total": 0.011387498117983341, "step": 51630 }, { "grad_norm": 0.2877008616924286, "learning_rate": 5.142344516425461e-05, "loss": 0.0105, "step": 51640 }, { "loss_action": 0.0112615330144763, "loss_total": 0.0112615330144763, "step": 51640 }, { "grad_norm": 0.2328265905380249, "learning_rate": 5.1406917090412673e-05, "loss": 0.0109, "step": 51650 }, { "loss_action": 0.007410084828734398, "loss_total": 0.007410084828734398, "step": 51650 }, { "grad_norm": 0.21482053399085999, "learning_rate": 5.1390388862712404e-05, "loss": 0.009, "step": 51660 }, { "loss_action": 0.008926996029913425, "loss_total": 0.008926996029913425, "step": 51660 }, { "grad_norm": 0.29557156562805176, "learning_rate": 5.137386048296129e-05, "loss": 0.0099, "step": 51670 }, { "loss_action": 0.008516211062669754, "loss_total": 0.008516211062669754, "step": 51670 }, { "grad_norm": 0.21696144342422485, "learning_rate": 5.135733195296686e-05, "loss": 0.0098, "step": 51680 }, { "loss_action": 0.01290417555719614, "loss_total": 0.01290417555719614, "step": 51680 }, { "grad_norm": 0.29354003071784973, "learning_rate": 5.134080327453664e-05, "loss": 0.0111, "step": 51690 }, { "loss_action": 0.009549843147397041, "loss_total": 0.009549843147397041, "step": 51690 }, { "grad_norm": 0.2621285915374756, "learning_rate": 5.1324274449478204e-05, "loss": 0.0093, "step": 51700 }, { "loss_action": 0.009827095083892345, "loss_total": 0.009827095083892345, "step": 51700 }, { "grad_norm": 0.28938332200050354, "learning_rate": 5.130774547959909e-05, "loss": 0.011, "step": 51710 }, { "loss_action": 0.009222556836903095, "loss_total": 0.009222556836903095, "step": 51710 }, { "grad_norm": 0.2259172797203064, "learning_rate": 5.129121636670692e-05, "loss": 0.01, "step": 51720 }, { "loss_action": 0.007088386919349432, "loss_total": 0.007088386919349432, "step": 51720 }, { "grad_norm": 0.3293370008468628, "learning_rate": 5.1274687112609246e-05, "loss": 0.0095, "step": 51730 }, { "loss_action": 0.009946518577635288, "loss_total": 0.009946518577635288, "step": 51730 }, { "grad_norm": 0.334183931350708, "learning_rate": 5.125815771911372e-05, "loss": 0.0091, "step": 51740 }, { "loss_action": 0.010121709667146206, "loss_total": 0.010121709667146206, "step": 51740 }, { "grad_norm": 0.22130915522575378, "learning_rate": 5.1241628188027956e-05, "loss": 0.0099, "step": 51750 }, { "loss_action": 0.014771755784749985, "loss_total": 0.014771755784749985, "step": 51750 }, { "grad_norm": 0.18695206940174103, "learning_rate": 5.1225098521159585e-05, "loss": 0.0091, "step": 51760 }, { "loss_action": 0.01563246361911297, "loss_total": 0.01563246361911297, "step": 51760 }, { "grad_norm": 0.2601293623447418, "learning_rate": 5.12085687203163e-05, "loss": 0.0115, "step": 51770 }, { "loss_action": 0.011502840556204319, "loss_total": 0.011502840556204319, "step": 51770 }, { "grad_norm": 0.3387022316455841, "learning_rate": 5.119203878730575e-05, "loss": 0.0097, "step": 51780 }, { "loss_action": 0.009853013791143894, "loss_total": 0.009853013791143894, "step": 51780 }, { "grad_norm": 0.2189626842737198, "learning_rate": 5.117550872393564e-05, "loss": 0.009, "step": 51790 }, { "loss_action": 0.009619495831429958, "loss_total": 0.009619495831429958, "step": 51790 }, { "grad_norm": 0.2180357128381729, "learning_rate": 5.1158978532013645e-05, "loss": 0.0101, "step": 51800 }, { "loss_action": 0.010480503551661968, "loss_total": 0.010480503551661968, "step": 51800 }, { "grad_norm": 0.23551449179649353, "learning_rate": 5.114244821334751e-05, "loss": 0.0108, "step": 51810 }, { "loss_action": 0.011671004816889763, "loss_total": 0.011671004816889763, "step": 51810 }, { "grad_norm": 0.24662542343139648, "learning_rate": 5.112591776974497e-05, "loss": 0.0103, "step": 51820 }, { "loss_action": 0.00887569785118103, "loss_total": 0.00887569785118103, "step": 51820 }, { "grad_norm": 0.2670747637748718, "learning_rate": 5.110938720301374e-05, "loss": 0.0101, "step": 51830 }, { "loss_action": 0.010831126011908054, "loss_total": 0.010831126011908054, "step": 51830 }, { "grad_norm": 0.26377934217453003, "learning_rate": 5.1092856514961595e-05, "loss": 0.0108, "step": 51840 }, { "loss_action": 0.010184694081544876, "loss_total": 0.010184694081544876, "step": 51840 }, { "grad_norm": 0.2346377968788147, "learning_rate": 5.107632570739631e-05, "loss": 0.0094, "step": 51850 }, { "loss_action": 0.008406950160861015, "loss_total": 0.008406950160861015, "step": 51850 }, { "grad_norm": 0.2615632712841034, "learning_rate": 5.1059794782125645e-05, "loss": 0.0105, "step": 51860 }, { "loss_action": 0.007648315280675888, "loss_total": 0.007648315280675888, "step": 51860 }, { "grad_norm": 0.22748732566833496, "learning_rate": 5.104326374095744e-05, "loss": 0.0101, "step": 51870 }, { "loss_action": 0.006704941391944885, "loss_total": 0.006704941391944885, "step": 51870 }, { "grad_norm": 0.2281574010848999, "learning_rate": 5.102673258569947e-05, "loss": 0.0098, "step": 51880 }, { "loss_action": 0.0098992008715868, "loss_total": 0.0098992008715868, "step": 51880 }, { "grad_norm": 0.2589576542377472, "learning_rate": 5.101020131815956e-05, "loss": 0.011, "step": 51890 }, { "loss_action": 0.0093460101634264, "loss_total": 0.0093460101634264, "step": 51890 }, { "grad_norm": 0.2452751249074936, "learning_rate": 5.099366994014556e-05, "loss": 0.011, "step": 51900 }, { "loss_action": 0.008933327160775661, "loss_total": 0.008933327160775661, "step": 51900 }, { "grad_norm": 0.2754174470901489, "learning_rate": 5.097713845346532e-05, "loss": 0.009, "step": 51910 }, { "loss_action": 0.009859742596745491, "loss_total": 0.009859742596745491, "step": 51910 }, { "grad_norm": 0.22767826914787292, "learning_rate": 5.096060685992668e-05, "loss": 0.0105, "step": 51920 }, { "loss_action": 0.009411359205842018, "loss_total": 0.009411359205842018, "step": 51920 }, { "grad_norm": 0.2567189037799835, "learning_rate": 5.0944075161337514e-05, "loss": 0.0112, "step": 51930 }, { "loss_action": 0.008883907459676266, "loss_total": 0.008883907459676266, "step": 51930 }, { "grad_norm": 0.25648313760757446, "learning_rate": 5.09275433595057e-05, "loss": 0.0086, "step": 51940 }, { "loss_action": 0.0097077377140522, "loss_total": 0.0097077377140522, "step": 51940 }, { "grad_norm": 0.24560467898845673, "learning_rate": 5.0911011456239157e-05, "loss": 0.0097, "step": 51950 }, { "loss_action": 0.007492449134588242, "loss_total": 0.007492449134588242, "step": 51950 }, { "grad_norm": 0.2910315692424774, "learning_rate": 5.089447945334574e-05, "loss": 0.0098, "step": 51960 }, { "loss_action": 0.008878582157194614, "loss_total": 0.008878582157194614, "step": 51960 }, { "grad_norm": 0.258571058511734, "learning_rate": 5.087794735263343e-05, "loss": 0.0094, "step": 51970 }, { "loss_action": 0.010199759155511856, "loss_total": 0.010199759155511856, "step": 51970 }, { "grad_norm": 0.26714059710502625, "learning_rate": 5.086141515591011e-05, "loss": 0.0096, "step": 51980 }, { "loss_action": 0.011176508851349354, "loss_total": 0.011176508851349354, "step": 51980 }, { "grad_norm": 0.30032867193222046, "learning_rate": 5.084488286498371e-05, "loss": 0.0089, "step": 51990 }, { "loss_action": 0.010659958235919476, "loss_total": 0.010659958235919476, "step": 51990 }, { "grad_norm": 0.20351380109786987, "learning_rate": 5.08283504816622e-05, "loss": 0.0101, "step": 52000 }, { "loss_action": 0.009056372568011284, "loss_total": 0.009056372568011284, "step": 52000 }, { "grad_norm": 0.2767515778541565, "learning_rate": 5.081181800775353e-05, "loss": 0.0105, "step": 52010 }, { "loss_action": 0.01456019189208746, "loss_total": 0.01456019189208746, "step": 52010 }, { "grad_norm": 0.23568284511566162, "learning_rate": 5.079528544506565e-05, "loss": 0.0095, "step": 52020 }, { "loss_action": 0.007355767767876387, "loss_total": 0.007355767767876387, "step": 52020 }, { "grad_norm": 0.2526896595954895, "learning_rate": 5.077875279540657e-05, "loss": 0.0095, "step": 52030 }, { "loss_action": 0.01278984360396862, "loss_total": 0.01278984360396862, "step": 52030 }, { "grad_norm": 0.19661462306976318, "learning_rate": 5.076222006058424e-05, "loss": 0.0097, "step": 52040 }, { "loss_action": 0.007832912728190422, "loss_total": 0.007832912728190422, "step": 52040 }, { "grad_norm": 0.24676792323589325, "learning_rate": 5.074568724240667e-05, "loss": 0.0092, "step": 52050 }, { "loss_action": 0.007217757869511843, "loss_total": 0.007217757869511843, "step": 52050 }, { "grad_norm": 0.2204148918390274, "learning_rate": 5.072915434268187e-05, "loss": 0.0099, "step": 52060 }, { "loss_action": 0.010401668027043343, "loss_total": 0.010401668027043343, "step": 52060 }, { "grad_norm": 0.22346606850624084, "learning_rate": 5.071262136321785e-05, "loss": 0.0091, "step": 52070 }, { "loss_action": 0.009482813067734241, "loss_total": 0.009482813067734241, "step": 52070 }, { "grad_norm": 0.20160122215747833, "learning_rate": 5.069608830582262e-05, "loss": 0.0099, "step": 52080 }, { "loss_action": 0.010349588468670845, "loss_total": 0.010349588468670845, "step": 52080 }, { "grad_norm": 0.27174681425094604, "learning_rate": 5.067955517230423e-05, "loss": 0.0104, "step": 52090 }, { "loss_action": 0.015310327522456646, "loss_total": 0.015310327522456646, "step": 52090 }, { "grad_norm": 0.20994685590267181, "learning_rate": 5.06630219644707e-05, "loss": 0.0106, "step": 52100 }, { "loss_action": 0.009283049963414669, "loss_total": 0.009283049963414669, "step": 52100 }, { "grad_norm": 0.2102980613708496, "learning_rate": 5.064648868413008e-05, "loss": 0.0099, "step": 52110 }, { "loss_action": 0.013215826824307442, "loss_total": 0.013215826824307442, "step": 52110 }, { "grad_norm": 0.20597520470619202, "learning_rate": 5.062995533309044e-05, "loss": 0.0093, "step": 52120 }, { "loss_action": 0.006674575619399548, "loss_total": 0.006674575619399548, "step": 52120 }, { "grad_norm": 0.21076475083827972, "learning_rate": 5.061342191315983e-05, "loss": 0.0091, "step": 52130 }, { "loss_action": 0.009021809324622154, "loss_total": 0.009021809324622154, "step": 52130 }, { "grad_norm": 0.23812860250473022, "learning_rate": 5.0596888426146325e-05, "loss": 0.0105, "step": 52140 }, { "loss_action": 0.007015621289610863, "loss_total": 0.007015621289610863, "step": 52140 }, { "grad_norm": 0.19311976432800293, "learning_rate": 5.058035487385798e-05, "loss": 0.0093, "step": 52150 }, { "loss_action": 0.006361015606671572, "loss_total": 0.006361015606671572, "step": 52150 }, { "grad_norm": 0.2583070993423462, "learning_rate": 5.0563821258102915e-05, "loss": 0.0098, "step": 52160 }, { "loss_action": 0.009549646638333797, "loss_total": 0.009549646638333797, "step": 52160 }, { "grad_norm": 0.2825946807861328, "learning_rate": 5.05472875806892e-05, "loss": 0.0099, "step": 52170 }, { "loss_action": 0.008067711256444454, "loss_total": 0.008067711256444454, "step": 52170 }, { "grad_norm": 0.29199153184890747, "learning_rate": 5.053075384342494e-05, "loss": 0.0094, "step": 52180 }, { "loss_action": 0.013731402345001698, "loss_total": 0.013731402345001698, "step": 52180 }, { "grad_norm": 0.24476420879364014, "learning_rate": 5.0514220048118234e-05, "loss": 0.0108, "step": 52190 }, { "loss_action": 0.008738075383007526, "loss_total": 0.008738075383007526, "step": 52190 }, { "grad_norm": 0.36503392457962036, "learning_rate": 5.049768619657721e-05, "loss": 0.0096, "step": 52200 }, { "loss_action": 0.014308512210845947, "loss_total": 0.014308512210845947, "step": 52200 }, { "grad_norm": 0.21670657396316528, "learning_rate": 5.048115229060996e-05, "loss": 0.0107, "step": 52210 }, { "loss_action": 0.009174973703920841, "loss_total": 0.009174973703920841, "step": 52210 }, { "grad_norm": 0.33079543709754944, "learning_rate": 5.046461833202462e-05, "loss": 0.0097, "step": 52220 }, { "loss_action": 0.0098817003890872, "loss_total": 0.0098817003890872, "step": 52220 }, { "grad_norm": 0.3362624943256378, "learning_rate": 5.044808432262932e-05, "loss": 0.0085, "step": 52230 }, { "loss_action": 0.00665458757430315, "loss_total": 0.00665458757430315, "step": 52230 }, { "grad_norm": 0.20206980407238007, "learning_rate": 5.043155026423219e-05, "loss": 0.0087, "step": 52240 }, { "loss_action": 0.01116738561540842, "loss_total": 0.01116738561540842, "step": 52240 }, { "grad_norm": 0.2617695927619934, "learning_rate": 5.041501615864137e-05, "loss": 0.0104, "step": 52250 }, { "loss_action": 0.007511415518820286, "loss_total": 0.007511415518820286, "step": 52250 }, { "grad_norm": 0.2943307161331177, "learning_rate": 5.039848200766502e-05, "loss": 0.0094, "step": 52260 }, { "loss_action": 0.0070931133814156055, "loss_total": 0.0070931133814156055, "step": 52260 }, { "grad_norm": 0.25041380524635315, "learning_rate": 5.038194781311125e-05, "loss": 0.0092, "step": 52270 }, { "loss_action": 0.007129126228392124, "loss_total": 0.007129126228392124, "step": 52270 }, { "grad_norm": 0.23790405690670013, "learning_rate": 5.0365413576788264e-05, "loss": 0.0099, "step": 52280 }, { "loss_action": 0.013593443669378757, "loss_total": 0.013593443669378757, "step": 52280 }, { "grad_norm": 0.20757123827934265, "learning_rate": 5.0348879300504194e-05, "loss": 0.0118, "step": 52290 }, { "loss_action": 0.016596181318163872, "loss_total": 0.016596181318163872, "step": 52290 }, { "grad_norm": 0.24923083186149597, "learning_rate": 5.033234498606721e-05, "loss": 0.0102, "step": 52300 }, { "loss_action": 0.008187569677829742, "loss_total": 0.008187569677829742, "step": 52300 }, { "grad_norm": 0.2899593114852905, "learning_rate": 5.0315810635285476e-05, "loss": 0.0099, "step": 52310 }, { "loss_action": 0.007991306483745575, "loss_total": 0.007991306483745575, "step": 52310 }, { "grad_norm": 0.2799447774887085, "learning_rate": 5.0299276249967164e-05, "loss": 0.0104, "step": 52320 }, { "loss_action": 0.009294728748500347, "loss_total": 0.009294728748500347, "step": 52320 }, { "grad_norm": 0.1813778430223465, "learning_rate": 5.0282741831920454e-05, "loss": 0.0105, "step": 52330 }, { "loss_action": 0.010086584836244583, "loss_total": 0.010086584836244583, "step": 52330 }, { "grad_norm": 0.2139960378408432, "learning_rate": 5.026620738295351e-05, "loss": 0.0091, "step": 52340 }, { "loss_action": 0.010003780946135521, "loss_total": 0.010003780946135521, "step": 52340 }, { "grad_norm": 0.21714749932289124, "learning_rate": 5.024967290487455e-05, "loss": 0.0095, "step": 52350 }, { "loss_action": 0.009690348990261555, "loss_total": 0.009690348990261555, "step": 52350 }, { "grad_norm": 0.3626250922679901, "learning_rate": 5.023313839949172e-05, "loss": 0.0102, "step": 52360 }, { "loss_action": 0.013389178551733494, "loss_total": 0.013389178551733494, "step": 52360 }, { "grad_norm": 0.22179828584194183, "learning_rate": 5.0216603868613224e-05, "loss": 0.011, "step": 52370 }, { "loss_action": 0.00793071836233139, "loss_total": 0.00793071836233139, "step": 52370 }, { "grad_norm": 0.21831761300563812, "learning_rate": 5.020006931404726e-05, "loss": 0.0099, "step": 52380 }, { "loss_action": 0.007379814516752958, "loss_total": 0.007379814516752958, "step": 52380 }, { "grad_norm": 0.16548477113246918, "learning_rate": 5.0183534737602014e-05, "loss": 0.0099, "step": 52390 }, { "loss_action": 0.008376400917768478, "loss_total": 0.008376400917768478, "step": 52390 }, { "grad_norm": 0.30231499671936035, "learning_rate": 5.0167000141085686e-05, "loss": 0.01, "step": 52400 }, { "loss_action": 0.009448843076825142, "loss_total": 0.009448843076825142, "step": 52400 }, { "grad_norm": 0.26620057225227356, "learning_rate": 5.015046552630647e-05, "loss": 0.0094, "step": 52410 }, { "loss_action": 0.00914037600159645, "loss_total": 0.00914037600159645, "step": 52410 }, { "grad_norm": 0.23762306571006775, "learning_rate": 5.013393089507258e-05, "loss": 0.009, "step": 52420 }, { "loss_action": 0.00901115220040083, "loss_total": 0.00901115220040083, "step": 52420 }, { "grad_norm": 0.2150384783744812, "learning_rate": 5.011739624919219e-05, "loss": 0.0088, "step": 52430 }, { "loss_action": 0.010209999047219753, "loss_total": 0.010209999047219753, "step": 52430 }, { "grad_norm": 0.21569858491420746, "learning_rate": 5.0100861590473545e-05, "loss": 0.0103, "step": 52440 }, { "loss_action": 0.010872297920286655, "loss_total": 0.010872297920286655, "step": 52440 }, { "grad_norm": 0.22003856301307678, "learning_rate": 5.008432692072482e-05, "loss": 0.0096, "step": 52450 }, { "loss_action": 0.00904044695198536, "loss_total": 0.00904044695198536, "step": 52450 }, { "grad_norm": 0.284568727016449, "learning_rate": 5.006779224175423e-05, "loss": 0.0094, "step": 52460 }, { "loss_action": 0.011489340104162693, "loss_total": 0.011489340104162693, "step": 52460 }, { "grad_norm": 0.23915190994739532, "learning_rate": 5.005125755536998e-05, "loss": 0.011, "step": 52470 }, { "loss_action": 0.013193570077419281, "loss_total": 0.013193570077419281, "step": 52470 }, { "grad_norm": 0.2283744066953659, "learning_rate": 5.003472286338029e-05, "loss": 0.0101, "step": 52480 }, { "loss_action": 0.010927475057542324, "loss_total": 0.010927475057542324, "step": 52480 }, { "grad_norm": 0.23019737005233765, "learning_rate": 5.001818816759335e-05, "loss": 0.0096, "step": 52490 }, { "loss_action": 0.010552192106842995, "loss_total": 0.010552192106842995, "step": 52490 }, { "grad_norm": 0.2262285202741623, "learning_rate": 5.000165346981738e-05, "loss": 0.0123, "step": 52500 }, { "loss_action": 0.008303613401949406, "loss_total": 0.008303613401949406, "step": 52500 }, { "grad_norm": 0.3367036283016205, "learning_rate": 4.9985118771860595e-05, "loss": 0.0091, "step": 52510 }, { "loss_action": 0.008839823305606842, "loss_total": 0.008839823305606842, "step": 52510 }, { "grad_norm": 0.19020624458789825, "learning_rate": 4.996858407553119e-05, "loss": 0.0095, "step": 52520 }, { "loss_action": 0.011993397027254105, "loss_total": 0.011993397027254105, "step": 52520 }, { "grad_norm": 0.20870962738990784, "learning_rate": 4.99520493826374e-05, "loss": 0.0091, "step": 52530 }, { "loss_action": 0.007308044005185366, "loss_total": 0.007308044005185366, "step": 52530 }, { "grad_norm": 0.2032875418663025, "learning_rate": 4.9935514694987384e-05, "loss": 0.0091, "step": 52540 }, { "loss_action": 0.010682598687708378, "loss_total": 0.010682598687708378, "step": 52540 }, { "grad_norm": 0.25644201040267944, "learning_rate": 4.991898001438941e-05, "loss": 0.0102, "step": 52550 }, { "loss_action": 0.008659657090902328, "loss_total": 0.008659657090902328, "step": 52550 }, { "grad_norm": 0.24246439337730408, "learning_rate": 4.990244534265166e-05, "loss": 0.01, "step": 52560 }, { "loss_action": 0.010311479680240154, "loss_total": 0.010311479680240154, "step": 52560 }, { "grad_norm": 0.2802720367908478, "learning_rate": 4.988591068158234e-05, "loss": 0.0094, "step": 52570 }, { "loss_action": 0.007301730569452047, "loss_total": 0.007301730569452047, "step": 52570 }, { "grad_norm": 0.23188696801662445, "learning_rate": 4.986937603298965e-05, "loss": 0.0082, "step": 52580 }, { "loss_action": 0.008298702538013458, "loss_total": 0.008298702538013458, "step": 52580 }, { "grad_norm": 0.31452250480651855, "learning_rate": 4.985284139868181e-05, "loss": 0.01, "step": 52590 }, { "loss_action": 0.013830414973199368, "loss_total": 0.013830414973199368, "step": 52590 }, { "grad_norm": 0.2940972149372101, "learning_rate": 4.9836306780467e-05, "loss": 0.0113, "step": 52600 }, { "loss_action": 0.011370531283318996, "loss_total": 0.011370531283318996, "step": 52600 }, { "grad_norm": 0.2850836515426636, "learning_rate": 4.981977218015343e-05, "loss": 0.0095, "step": 52610 }, { "loss_action": 0.010155011899769306, "loss_total": 0.010155011899769306, "step": 52610 }, { "grad_norm": 0.2245349884033203, "learning_rate": 4.980323759954932e-05, "loss": 0.0103, "step": 52620 }, { "loss_action": 0.012449576519429684, "loss_total": 0.012449576519429684, "step": 52620 }, { "grad_norm": 0.21517887711524963, "learning_rate": 4.978670304046284e-05, "loss": 0.0109, "step": 52630 }, { "loss_action": 0.012387949042022228, "loss_total": 0.012387949042022228, "step": 52630 }, { "grad_norm": 0.23534522950649261, "learning_rate": 4.9770168504702195e-05, "loss": 0.0099, "step": 52640 }, { "loss_action": 0.010738182812929153, "loss_total": 0.010738182812929153, "step": 52640 }, { "grad_norm": 0.2614786922931671, "learning_rate": 4.975363399407559e-05, "loss": 0.0104, "step": 52650 }, { "loss_action": 0.008881542831659317, "loss_total": 0.008881542831659317, "step": 52650 }, { "grad_norm": 0.20094941556453705, "learning_rate": 4.9737099510391194e-05, "loss": 0.01, "step": 52660 }, { "loss_action": 0.007448164746165276, "loss_total": 0.007448164746165276, "step": 52660 }, { "grad_norm": 0.20421160757541656, "learning_rate": 4.972056505545719e-05, "loss": 0.0101, "step": 52670 }, { "loss_action": 0.008135398849844933, "loss_total": 0.008135398849844933, "step": 52670 }, { "grad_norm": 0.23215456306934357, "learning_rate": 4.9704030631081775e-05, "loss": 0.0104, "step": 52680 }, { "loss_action": 0.009722409769892693, "loss_total": 0.009722409769892693, "step": 52680 }, { "grad_norm": 0.22672265768051147, "learning_rate": 4.968749623907313e-05, "loss": 0.0104, "step": 52690 }, { "loss_action": 0.010652422904968262, "loss_total": 0.010652422904968262, "step": 52690 }, { "grad_norm": 0.24007324874401093, "learning_rate": 4.967096188123943e-05, "loss": 0.0114, "step": 52700 }, { "loss_action": 0.008580386638641357, "loss_total": 0.008580386638641357, "step": 52700 }, { "grad_norm": 0.23733632266521454, "learning_rate": 4.965442755938884e-05, "loss": 0.0104, "step": 52710 }, { "loss_action": 0.008884834125638008, "loss_total": 0.008884834125638008, "step": 52710 }, { "grad_norm": 0.2182304859161377, "learning_rate": 4.963789327532954e-05, "loss": 0.0093, "step": 52720 }, { "loss_action": 0.009870381094515324, "loss_total": 0.009870381094515324, "step": 52720 }, { "grad_norm": 0.2585573196411133, "learning_rate": 4.962135903086968e-05, "loss": 0.0103, "step": 52730 }, { "loss_action": 0.0090291453525424, "loss_total": 0.0090291453525424, "step": 52730 }, { "grad_norm": 0.23378044366836548, "learning_rate": 4.960482482781741e-05, "loss": 0.0081, "step": 52740 }, { "loss_action": 0.01043279841542244, "loss_total": 0.01043279841542244, "step": 52740 }, { "grad_norm": 0.20375819504261017, "learning_rate": 4.958829066798092e-05, "loss": 0.009, "step": 52750 }, { "loss_action": 0.007646474055945873, "loss_total": 0.007646474055945873, "step": 52750 }, { "grad_norm": 0.21610352396965027, "learning_rate": 4.957175655316835e-05, "loss": 0.0086, "step": 52760 }, { "loss_action": 0.011195105500519276, "loss_total": 0.011195105500519276, "step": 52760 }, { "grad_norm": 0.2982774078845978, "learning_rate": 4.9555222485187834e-05, "loss": 0.0093, "step": 52770 }, { "loss_action": 0.007330967113375664, "loss_total": 0.007330967113375664, "step": 52770 }, { "grad_norm": 0.2755204141139984, "learning_rate": 4.953868846584752e-05, "loss": 0.0086, "step": 52780 }, { "loss_action": 0.00897258147597313, "loss_total": 0.00897258147597313, "step": 52780 }, { "grad_norm": 0.2525865137577057, "learning_rate": 4.9522154496955544e-05, "loss": 0.0103, "step": 52790 }, { "loss_action": 0.00741658266633749, "loss_total": 0.00741658266633749, "step": 52790 }, { "grad_norm": 0.20831814408302307, "learning_rate": 4.950562058032001e-05, "loss": 0.0092, "step": 52800 }, { "loss_action": 0.011504972353577614, "loss_total": 0.011504972353577614, "step": 52800 }, { "grad_norm": 0.23514080047607422, "learning_rate": 4.948908671774909e-05, "loss": 0.0103, "step": 52810 }, { "loss_action": 0.01174477580934763, "loss_total": 0.01174477580934763, "step": 52810 }, { "grad_norm": 0.19993188977241516, "learning_rate": 4.947255291105087e-05, "loss": 0.0088, "step": 52820 }, { "loss_action": 0.00920764822512865, "loss_total": 0.00920764822512865, "step": 52820 }, { "grad_norm": 0.3025144040584564, "learning_rate": 4.945601916203348e-05, "loss": 0.0102, "step": 52830 }, { "loss_action": 0.009173201397061348, "loss_total": 0.009173201397061348, "step": 52830 }, { "grad_norm": 0.2584255039691925, "learning_rate": 4.9439485472505016e-05, "loss": 0.0094, "step": 52840 }, { "loss_action": 0.009043299593031406, "loss_total": 0.009043299593031406, "step": 52840 }, { "grad_norm": 0.26693567633628845, "learning_rate": 4.942295184427356e-05, "loss": 0.0096, "step": 52850 }, { "loss_action": 0.0082857022061944, "loss_total": 0.0082857022061944, "step": 52850 }, { "grad_norm": 0.29613280296325684, "learning_rate": 4.9406418279147234e-05, "loss": 0.0099, "step": 52860 }, { "loss_action": 0.011510150507092476, "loss_total": 0.011510150507092476, "step": 52860 }, { "grad_norm": 0.2516055703163147, "learning_rate": 4.9389884778934116e-05, "loss": 0.0109, "step": 52870 }, { "loss_action": 0.011255006305873394, "loss_total": 0.011255006305873394, "step": 52870 }, { "grad_norm": 0.2716468572616577, "learning_rate": 4.937335134544228e-05, "loss": 0.0098, "step": 52880 }, { "loss_action": 0.01220425870269537, "loss_total": 0.01220425870269537, "step": 52880 }, { "grad_norm": 0.20008113980293274, "learning_rate": 4.935681798047979e-05, "loss": 0.0109, "step": 52890 }, { "loss_action": 0.007000157609581947, "loss_total": 0.007000157609581947, "step": 52890 }, { "grad_norm": 0.2641198933124542, "learning_rate": 4.934028468585473e-05, "loss": 0.01, "step": 52900 }, { "loss_action": 0.01033482700586319, "loss_total": 0.01033482700586319, "step": 52900 }, { "grad_norm": 0.22634030878543854, "learning_rate": 4.932375146337514e-05, "loss": 0.0111, "step": 52910 }, { "loss_action": 0.009341847151517868, "loss_total": 0.009341847151517868, "step": 52910 }, { "grad_norm": 0.20700471103191376, "learning_rate": 4.930721831484908e-05, "loss": 0.0101, "step": 52920 }, { "loss_action": 0.009917155839502811, "loss_total": 0.009917155839502811, "step": 52920 }, { "grad_norm": 0.23860877752304077, "learning_rate": 4.929068524208456e-05, "loss": 0.0107, "step": 52930 }, { "loss_action": 0.012950167991220951, "loss_total": 0.012950167991220951, "step": 52930 }, { "grad_norm": 0.3079583942890167, "learning_rate": 4.927415224688965e-05, "loss": 0.0099, "step": 52940 }, { "loss_action": 0.008370318450033665, "loss_total": 0.008370318450033665, "step": 52940 }, { "grad_norm": 0.2657255232334137, "learning_rate": 4.9257619331072375e-05, "loss": 0.0112, "step": 52950 }, { "loss_action": 0.00983895268291235, "loss_total": 0.00983895268291235, "step": 52950 }, { "grad_norm": 0.25982704758644104, "learning_rate": 4.924108649644072e-05, "loss": 0.0105, "step": 52960 }, { "loss_action": 0.012860958464443684, "loss_total": 0.012860958464443684, "step": 52960 }, { "grad_norm": 0.2525654435157776, "learning_rate": 4.922455374480271e-05, "loss": 0.0106, "step": 52970 }, { "loss_action": 0.01137204747647047, "loss_total": 0.01137204747647047, "step": 52970 }, { "grad_norm": 0.22659260034561157, "learning_rate": 4.920802107796634e-05, "loss": 0.0088, "step": 52980 }, { "loss_action": 0.009797711856663227, "loss_total": 0.009797711856663227, "step": 52980 }, { "grad_norm": 0.2210206538438797, "learning_rate": 4.9191488497739564e-05, "loss": 0.0107, "step": 52990 }, { "loss_action": 0.00999695248901844, "loss_total": 0.00999695248901844, "step": 52990 }, { "grad_norm": 0.17318078875541687, "learning_rate": 4.917495600593042e-05, "loss": 0.0087, "step": 53000 }, { "loss_action": 0.009542649611830711, "loss_total": 0.009542649611830711, "step": 53000 }, { "grad_norm": 0.2546846568584442, "learning_rate": 4.915842360434684e-05, "loss": 0.0111, "step": 53010 }, { "loss_action": 0.008371672593057156, "loss_total": 0.008371672593057156, "step": 53010 }, { "grad_norm": 0.2559055984020233, "learning_rate": 4.914189129479679e-05, "loss": 0.0098, "step": 53020 }, { "loss_action": 0.013676561415195465, "loss_total": 0.013676561415195465, "step": 53020 }, { "grad_norm": 0.2805016338825226, "learning_rate": 4.912535907908822e-05, "loss": 0.0099, "step": 53030 }, { "loss_action": 0.010457963682711124, "loss_total": 0.010457963682711124, "step": 53030 }, { "grad_norm": 0.3493145704269409, "learning_rate": 4.910882695902907e-05, "loss": 0.0093, "step": 53040 }, { "loss_action": 0.007303998339921236, "loss_total": 0.007303998339921236, "step": 53040 }, { "grad_norm": 0.21830487251281738, "learning_rate": 4.9092294936427234e-05, "loss": 0.0109, "step": 53050 }, { "loss_action": 0.015171077102422714, "loss_total": 0.015171077102422714, "step": 53050 }, { "grad_norm": 0.2589614987373352, "learning_rate": 4.9075763013090685e-05, "loss": 0.0114, "step": 53060 }, { "loss_action": 0.00829877145588398, "loss_total": 0.00829877145588398, "step": 53060 }, { "grad_norm": 0.2035178393125534, "learning_rate": 4.9059231190827305e-05, "loss": 0.0092, "step": 53070 }, { "loss_action": 0.010324012488126755, "loss_total": 0.010324012488126755, "step": 53070 }, { "grad_norm": 0.2152951955795288, "learning_rate": 4.904269947144499e-05, "loss": 0.0085, "step": 53080 }, { "loss_action": 0.008186391554772854, "loss_total": 0.008186391554772854, "step": 53080 }, { "grad_norm": 0.24331824481487274, "learning_rate": 4.902616785675161e-05, "loss": 0.0091, "step": 53090 }, { "loss_action": 0.011137666180729866, "loss_total": 0.011137666180729866, "step": 53090 }, { "grad_norm": 0.2847643196582794, "learning_rate": 4.900963634855505e-05, "loss": 0.011, "step": 53100 }, { "loss_action": 0.010090433992445469, "loss_total": 0.010090433992445469, "step": 53100 }, { "grad_norm": 0.3695216476917267, "learning_rate": 4.8993104948663173e-05, "loss": 0.0102, "step": 53110 }, { "loss_action": 0.007555007003247738, "loss_total": 0.007555007003247738, "step": 53110 }, { "grad_norm": 0.261430948972702, "learning_rate": 4.8976573658883823e-05, "loss": 0.0094, "step": 53120 }, { "loss_action": 0.009628684259951115, "loss_total": 0.009628684259951115, "step": 53120 }, { "grad_norm": 0.22052377462387085, "learning_rate": 4.896004248102484e-05, "loss": 0.0093, "step": 53130 }, { "loss_action": 0.007134685758501291, "loss_total": 0.007134685758501291, "step": 53130 }, { "grad_norm": 0.2364976853132248, "learning_rate": 4.8943511416894045e-05, "loss": 0.0089, "step": 53140 }, { "loss_action": 0.011197785846889019, "loss_total": 0.011197785846889019, "step": 53140 }, { "grad_norm": 0.3153100311756134, "learning_rate": 4.892698046829926e-05, "loss": 0.01, "step": 53150 }, { "loss_action": 0.0080984216183424, "loss_total": 0.0080984216183424, "step": 53150 }, { "grad_norm": 0.21722066402435303, "learning_rate": 4.8910449637048275e-05, "loss": 0.0092, "step": 53160 }, { "loss_action": 0.0069874865002930164, "loss_total": 0.0069874865002930164, "step": 53160 }, { "grad_norm": 0.23532290756702423, "learning_rate": 4.8893918924948884e-05, "loss": 0.0108, "step": 53170 }, { "loss_action": 0.007591541390866041, "loss_total": 0.007591541390866041, "step": 53170 }, { "grad_norm": 0.24048729240894318, "learning_rate": 4.8877388333808835e-05, "loss": 0.0089, "step": 53180 }, { "loss_action": 0.010068285278975964, "loss_total": 0.010068285278975964, "step": 53180 }, { "grad_norm": 0.20573784410953522, "learning_rate": 4.8860857865435925e-05, "loss": 0.0117, "step": 53190 }, { "loss_action": 0.00835234671831131, "loss_total": 0.00835234671831131, "step": 53190 }, { "grad_norm": 0.17260093986988068, "learning_rate": 4.884432752163789e-05, "loss": 0.0087, "step": 53200 }, { "loss_action": 0.008317933417856693, "loss_total": 0.008317933417856693, "step": 53200 }, { "grad_norm": 0.2613385319709778, "learning_rate": 4.8827797304222466e-05, "loss": 0.0104, "step": 53210 }, { "loss_action": 0.011463715694844723, "loss_total": 0.011463715694844723, "step": 53210 }, { "grad_norm": 0.2508399784564972, "learning_rate": 4.8811267214997366e-05, "loss": 0.0114, "step": 53220 }, { "loss_action": 0.010375721380114555, "loss_total": 0.010375721380114555, "step": 53220 }, { "grad_norm": 0.28819721937179565, "learning_rate": 4.879473725577029e-05, "loss": 0.0092, "step": 53230 }, { "loss_action": 0.007909814827144146, "loss_total": 0.007909814827144146, "step": 53230 }, { "grad_norm": 0.2550642490386963, "learning_rate": 4.877820742834891e-05, "loss": 0.0106, "step": 53240 }, { "loss_action": 0.008836504071950912, "loss_total": 0.008836504071950912, "step": 53240 }, { "grad_norm": 0.24960598349571228, "learning_rate": 4.8761677734540956e-05, "loss": 0.01, "step": 53250 }, { "loss_action": 0.011716034263372421, "loss_total": 0.011716034263372421, "step": 53250 }, { "grad_norm": 0.2795039117336273, "learning_rate": 4.874514817615407e-05, "loss": 0.0105, "step": 53260 }, { "loss_action": 0.009695781394839287, "loss_total": 0.009695781394839287, "step": 53260 }, { "grad_norm": 0.27021270990371704, "learning_rate": 4.872861875499588e-05, "loss": 0.0091, "step": 53270 }, { "loss_action": 0.0079801045358181, "loss_total": 0.0079801045358181, "step": 53270 }, { "grad_norm": 0.22796426713466644, "learning_rate": 4.871208947287404e-05, "loss": 0.009, "step": 53280 }, { "loss_action": 0.011116331443190575, "loss_total": 0.011116331443190575, "step": 53280 }, { "grad_norm": 0.23259595036506653, "learning_rate": 4.869556033159615e-05, "loss": 0.0092, "step": 53290 }, { "loss_action": 0.008742398582398891, "loss_total": 0.008742398582398891, "step": 53290 }, { "grad_norm": 0.2506553530693054, "learning_rate": 4.8679031332969835e-05, "loss": 0.0083, "step": 53300 }, { "loss_action": 0.014225845225155354, "loss_total": 0.014225845225155354, "step": 53300 }, { "grad_norm": 0.19702476263046265, "learning_rate": 4.8662502478802635e-05, "loss": 0.0098, "step": 53310 }, { "loss_action": 0.007678764406591654, "loss_total": 0.007678764406591654, "step": 53310 }, { "grad_norm": 0.28607478737831116, "learning_rate": 4.8645973770902176e-05, "loss": 0.0097, "step": 53320 }, { "loss_action": 0.012601770460605621, "loss_total": 0.012601770460605621, "step": 53320 }, { "grad_norm": 0.26031365990638733, "learning_rate": 4.862944521107599e-05, "loss": 0.0111, "step": 53330 }, { "loss_action": 0.012147321365773678, "loss_total": 0.012147321365773678, "step": 53330 }, { "grad_norm": 0.23363259434700012, "learning_rate": 4.861291680113162e-05, "loss": 0.0093, "step": 53340 }, { "loss_action": 0.00675693154335022, "loss_total": 0.00675693154335022, "step": 53340 }, { "grad_norm": 0.3264613449573517, "learning_rate": 4.8596388542876563e-05, "loss": 0.0098, "step": 53350 }, { "loss_action": 0.007862670347094536, "loss_total": 0.007862670347094536, "step": 53350 }, { "grad_norm": 0.3050040900707245, "learning_rate": 4.857986043811836e-05, "loss": 0.0098, "step": 53360 }, { "loss_action": 0.009064929559826851, "loss_total": 0.009064929559826851, "step": 53360 }, { "grad_norm": 0.19108320772647858, "learning_rate": 4.856333248866448e-05, "loss": 0.0101, "step": 53370 }, { "loss_action": 0.010974573902785778, "loss_total": 0.010974573902785778, "step": 53370 }, { "grad_norm": 0.20521175861358643, "learning_rate": 4.85468046963224e-05, "loss": 0.0088, "step": 53380 }, { "loss_action": 0.009328005835413933, "loss_total": 0.009328005835413933, "step": 53380 }, { "grad_norm": 0.28305715322494507, "learning_rate": 4.853027706289957e-05, "loss": 0.0098, "step": 53390 }, { "loss_action": 0.005717199761420488, "loss_total": 0.005717199761420488, "step": 53390 }, { "grad_norm": 0.2618214786052704, "learning_rate": 4.851374959020344e-05, "loss": 0.0088, "step": 53400 }, { "loss_action": 0.009910031221807003, "loss_total": 0.009910031221807003, "step": 53400 }, { "grad_norm": 0.24965326488018036, "learning_rate": 4.849722228004141e-05, "loss": 0.0095, "step": 53410 }, { "loss_action": 0.011140519753098488, "loss_total": 0.011140519753098488, "step": 53410 }, { "grad_norm": 0.22570741176605225, "learning_rate": 4.848069513422091e-05, "loss": 0.0085, "step": 53420 }, { "loss_action": 0.009863958694040775, "loss_total": 0.009863958694040775, "step": 53420 }, { "grad_norm": 0.2648242712020874, "learning_rate": 4.8464168154549294e-05, "loss": 0.0095, "step": 53430 }, { "loss_action": 0.010027476586401463, "loss_total": 0.010027476586401463, "step": 53430 }, { "grad_norm": 0.24480071663856506, "learning_rate": 4.844764134283392e-05, "loss": 0.0097, "step": 53440 }, { "loss_action": 0.00908826757222414, "loss_total": 0.00908826757222414, "step": 53440 }, { "grad_norm": 0.25071144104003906, "learning_rate": 4.843111470088218e-05, "loss": 0.0103, "step": 53450 }, { "loss_action": 0.010279083624482155, "loss_total": 0.010279083624482155, "step": 53450 }, { "grad_norm": 0.3008560240268707, "learning_rate": 4.841458823050137e-05, "loss": 0.0099, "step": 53460 }, { "loss_action": 0.011023062281310558, "loss_total": 0.011023062281310558, "step": 53460 }, { "grad_norm": 0.23470625281333923, "learning_rate": 4.8398061933498816e-05, "loss": 0.0101, "step": 53470 }, { "loss_action": 0.012114000506699085, "loss_total": 0.012114000506699085, "step": 53470 }, { "grad_norm": 0.20566508173942566, "learning_rate": 4.83815358116818e-05, "loss": 0.0086, "step": 53480 }, { "loss_action": 0.00998386088758707, "loss_total": 0.00998386088758707, "step": 53480 }, { "grad_norm": 0.21734075248241425, "learning_rate": 4.8365009866857584e-05, "loss": 0.0091, "step": 53490 }, { "loss_action": 0.006237272638827562, "loss_total": 0.006237272638827562, "step": 53490 }, { "grad_norm": 0.17351041734218597, "learning_rate": 4.834848410083342e-05, "loss": 0.0086, "step": 53500 }, { "loss_action": 0.011475537903606892, "loss_total": 0.011475537903606892, "step": 53500 }, { "grad_norm": 0.3089885115623474, "learning_rate": 4.833195851541657e-05, "loss": 0.0112, "step": 53510 }, { "loss_action": 0.010146591812372208, "loss_total": 0.010146591812372208, "step": 53510 }, { "grad_norm": 0.3152931034564972, "learning_rate": 4.831543311241423e-05, "loss": 0.011, "step": 53520 }, { "loss_action": 0.01609039679169655, "loss_total": 0.01609039679169655, "step": 53520 }, { "grad_norm": 0.28205883502960205, "learning_rate": 4.829890789363359e-05, "loss": 0.0106, "step": 53530 }, { "loss_action": 0.010473658330738544, "loss_total": 0.010473658330738544, "step": 53530 }, { "grad_norm": 0.2968568801879883, "learning_rate": 4.828238286088182e-05, "loss": 0.0107, "step": 53540 }, { "loss_action": 0.009574437513947487, "loss_total": 0.009574437513947487, "step": 53540 }, { "grad_norm": 0.2711188793182373, "learning_rate": 4.826585801596609e-05, "loss": 0.0102, "step": 53550 }, { "loss_action": 0.008645564317703247, "loss_total": 0.008645564317703247, "step": 53550 }, { "grad_norm": 0.2905973792076111, "learning_rate": 4.8249333360693486e-05, "loss": 0.0096, "step": 53560 }, { "loss_action": 0.00683180708438158, "loss_total": 0.00683180708438158, "step": 53560 }, { "grad_norm": 0.2251712679862976, "learning_rate": 4.8232808896871185e-05, "loss": 0.0111, "step": 53570 }, { "loss_action": 0.010712890885770321, "loss_total": 0.010712890885770321, "step": 53570 }, { "grad_norm": 0.29002735018730164, "learning_rate": 4.821628462630624e-05, "loss": 0.01, "step": 53580 }, { "loss_action": 0.009473484009504318, "loss_total": 0.009473484009504318, "step": 53580 }, { "grad_norm": 0.16373541951179504, "learning_rate": 4.8199760550805735e-05, "loss": 0.0104, "step": 53590 }, { "loss_action": 0.008352656848728657, "loss_total": 0.008352656848728657, "step": 53590 }, { "grad_norm": 0.30446332693099976, "learning_rate": 4.818323667217669e-05, "loss": 0.0094, "step": 53600 }, { "loss_action": 0.011817306280136108, "loss_total": 0.011817306280136108, "step": 53600 }, { "grad_norm": 0.20952212810516357, "learning_rate": 4.8166712992226165e-05, "loss": 0.0095, "step": 53610 }, { "loss_action": 0.0109182707965374, "loss_total": 0.0109182707965374, "step": 53610 }, { "grad_norm": 0.21318525075912476, "learning_rate": 4.8150189512761154e-05, "loss": 0.0094, "step": 53620 }, { "loss_action": 0.007901066914200783, "loss_total": 0.007901066914200783, "step": 53620 }, { "grad_norm": 0.2960704267024994, "learning_rate": 4.813366623558862e-05, "loss": 0.0095, "step": 53630 }, { "loss_action": 0.008445686660706997, "loss_total": 0.008445686660706997, "step": 53630 }, { "grad_norm": 0.23326197266578674, "learning_rate": 4.811714316251554e-05, "loss": 0.0111, "step": 53640 }, { "loss_action": 0.00904048141092062, "loss_total": 0.00904048141092062, "step": 53640 }, { "grad_norm": 0.25631076097488403, "learning_rate": 4.810062029534886e-05, "loss": 0.0098, "step": 53650 }, { "loss_action": 0.008110569790005684, "loss_total": 0.008110569790005684, "step": 53650 }, { "grad_norm": 0.2934196889400482, "learning_rate": 4.8084097635895505e-05, "loss": 0.0108, "step": 53660 }, { "loss_action": 0.007056010887026787, "loss_total": 0.007056010887026787, "step": 53660 }, { "grad_norm": 0.26289817690849304, "learning_rate": 4.8067575185962335e-05, "loss": 0.0093, "step": 53670 }, { "loss_action": 0.011686638928949833, "loss_total": 0.011686638928949833, "step": 53670 }, { "grad_norm": 0.22602279484272003, "learning_rate": 4.805105294735625e-05, "loss": 0.0119, "step": 53680 }, { "loss_action": 0.007768565788865089, "loss_total": 0.007768565788865089, "step": 53680 }, { "grad_norm": 0.227748841047287, "learning_rate": 4.803453092188406e-05, "loss": 0.0087, "step": 53690 }, { "loss_action": 0.007030124310404062, "loss_total": 0.007030124310404062, "step": 53690 }, { "grad_norm": 0.29108989238739014, "learning_rate": 4.801800911135263e-05, "loss": 0.0098, "step": 53700 }, { "loss_action": 0.009939577430486679, "loss_total": 0.009939577430486679, "step": 53700 }, { "grad_norm": 0.30577465891838074, "learning_rate": 4.8001487517568744e-05, "loss": 0.0099, "step": 53710 }, { "loss_action": 0.009638710878789425, "loss_total": 0.009638710878789425, "step": 53710 }, { "grad_norm": 0.22056637704372406, "learning_rate": 4.798496614233918e-05, "loss": 0.0087, "step": 53720 }, { "loss_action": 0.0085194306448102, "loss_total": 0.0085194306448102, "step": 53720 }, { "grad_norm": 0.22968889772891998, "learning_rate": 4.796844498747069e-05, "loss": 0.0098, "step": 53730 }, { "loss_action": 0.006429214030504227, "loss_total": 0.006429214030504227, "step": 53730 }, { "grad_norm": 0.2528044581413269, "learning_rate": 4.795192405477e-05, "loss": 0.0105, "step": 53740 }, { "loss_action": 0.01151675172150135, "loss_total": 0.01151675172150135, "step": 53740 }, { "grad_norm": 0.3244367837905884, "learning_rate": 4.79354033460438e-05, "loss": 0.0098, "step": 53750 }, { "loss_action": 0.007062092889100313, "loss_total": 0.007062092889100313, "step": 53750 }, { "grad_norm": 0.24099411070346832, "learning_rate": 4.79188828630988e-05, "loss": 0.0086, "step": 53760 }, { "loss_action": 0.008335917256772518, "loss_total": 0.008335917256772518, "step": 53760 }, { "grad_norm": 0.21225406229496002, "learning_rate": 4.790236260774165e-05, "loss": 0.0089, "step": 53770 }, { "loss_action": 0.008325197733938694, "loss_total": 0.008325197733938694, "step": 53770 }, { "grad_norm": 0.19531524181365967, "learning_rate": 4.788584258177896e-05, "loss": 0.0089, "step": 53780 }, { "loss_action": 0.008150877431035042, "loss_total": 0.008150877431035042, "step": 53780 }, { "grad_norm": 0.21165874600410461, "learning_rate": 4.7869322787017356e-05, "loss": 0.0104, "step": 53790 }, { "loss_action": 0.007785805035382509, "loss_total": 0.007785805035382509, "step": 53790 }, { "grad_norm": 0.21825788915157318, "learning_rate": 4.78528032252634e-05, "loss": 0.009, "step": 53800 }, { "loss_action": 0.0060274116694927216, "loss_total": 0.0060274116694927216, "step": 53800 }, { "grad_norm": 0.2585592567920685, "learning_rate": 4.783628389832366e-05, "loss": 0.0099, "step": 53810 }, { "loss_action": 0.01377950981259346, "loss_total": 0.01377950981259346, "step": 53810 }, { "grad_norm": 0.23770131170749664, "learning_rate": 4.7819764808004644e-05, "loss": 0.0098, "step": 53820 }, { "loss_action": 0.010470476001501083, "loss_total": 0.010470476001501083, "step": 53820 }, { "grad_norm": 0.222573384642601, "learning_rate": 4.780324595611289e-05, "loss": 0.0098, "step": 53830 }, { "loss_action": 0.00771779241040349, "loss_total": 0.00771779241040349, "step": 53830 }, { "grad_norm": 0.23273544013500214, "learning_rate": 4.7786727344454854e-05, "loss": 0.0094, "step": 53840 }, { "loss_action": 0.009595491923391819, "loss_total": 0.009595491923391819, "step": 53840 }, { "grad_norm": 0.23027582466602325, "learning_rate": 4.777020897483697e-05, "loss": 0.009, "step": 53850 }, { "loss_action": 0.013163535855710506, "loss_total": 0.013163535855710506, "step": 53850 }, { "grad_norm": 0.22970987856388092, "learning_rate": 4.775369084906569e-05, "loss": 0.0116, "step": 53860 }, { "loss_action": 0.011107731610536575, "loss_total": 0.011107731610536575, "step": 53860 }, { "grad_norm": 0.3056514263153076, "learning_rate": 4.773717296894742e-05, "loss": 0.0088, "step": 53870 }, { "loss_action": 0.01045539416372776, "loss_total": 0.01045539416372776, "step": 53870 }, { "grad_norm": 0.20884032547473907, "learning_rate": 4.772065533628848e-05, "loss": 0.01, "step": 53880 }, { "loss_action": 0.0076597146689891815, "loss_total": 0.0076597146689891815, "step": 53880 }, { "grad_norm": 0.17870695888996124, "learning_rate": 4.7704137952895265e-05, "loss": 0.0078, "step": 53890 }, { "loss_action": 0.008454008027911186, "loss_total": 0.008454008027911186, "step": 53890 }, { "grad_norm": 0.20297686755657196, "learning_rate": 4.768762082057407e-05, "loss": 0.0084, "step": 53900 }, { "loss_action": 0.0061590769328176975, "loss_total": 0.0061590769328176975, "step": 53900 }, { "grad_norm": 0.23083552718162537, "learning_rate": 4.7671103941131186e-05, "loss": 0.0088, "step": 53910 }, { "loss_action": 0.008888691663742065, "loss_total": 0.008888691663742065, "step": 53910 }, { "grad_norm": 0.2094433754682541, "learning_rate": 4.765458731637287e-05, "loss": 0.0088, "step": 53920 }, { "loss_action": 0.008263721130788326, "loss_total": 0.008263721130788326, "step": 53920 }, { "grad_norm": 0.2096949815750122, "learning_rate": 4.763807094810537e-05, "loss": 0.0094, "step": 53930 }, { "loss_action": 0.011909520253539085, "loss_total": 0.011909520253539085, "step": 53930 }, { "grad_norm": 0.21849271655082703, "learning_rate": 4.762155483813487e-05, "loss": 0.0093, "step": 53940 }, { "loss_action": 0.007927827537059784, "loss_total": 0.007927827537059784, "step": 53940 }, { "grad_norm": 0.20526377856731415, "learning_rate": 4.760503898826754e-05, "loss": 0.0083, "step": 53950 }, { "loss_action": 0.00882942695170641, "loss_total": 0.00882942695170641, "step": 53950 }, { "grad_norm": 0.26250767707824707, "learning_rate": 4.758852340030957e-05, "loss": 0.0102, "step": 53960 }, { "loss_action": 0.008656843565404415, "loss_total": 0.008656843565404415, "step": 53960 }, { "grad_norm": 0.24075362086296082, "learning_rate": 4.757200807606705e-05, "loss": 0.0105, "step": 53970 }, { "loss_action": 0.010361938737332821, "loss_total": 0.010361938737332821, "step": 53970 }, { "grad_norm": 0.21785488724708557, "learning_rate": 4.755549301734607e-05, "loss": 0.01, "step": 53980 }, { "loss_action": 0.008654502220451832, "loss_total": 0.008654502220451832, "step": 53980 }, { "grad_norm": 0.27932682633399963, "learning_rate": 4.753897822595271e-05, "loss": 0.0091, "step": 53990 }, { "loss_action": 0.006564714480191469, "loss_total": 0.006564714480191469, "step": 53990 }, { "grad_norm": 0.24466444551944733, "learning_rate": 4.7522463703692994e-05, "loss": 0.0107, "step": 54000 }, { "loss_action": 0.00981774739921093, "loss_total": 0.00981774739921093, "step": 54000 }, { "grad_norm": 0.23151832818984985, "learning_rate": 4.75059494523729e-05, "loss": 0.01, "step": 54010 }, { "loss_action": 0.005981731228530407, "loss_total": 0.005981731228530407, "step": 54010 }, { "grad_norm": 0.31395456194877625, "learning_rate": 4.748943547379843e-05, "loss": 0.0096, "step": 54020 }, { "loss_action": 0.009057152085006237, "loss_total": 0.009057152085006237, "step": 54020 }, { "grad_norm": 0.2521436810493469, "learning_rate": 4.7472921769775535e-05, "loss": 0.0108, "step": 54030 }, { "loss_action": 0.009706053882837296, "loss_total": 0.009706053882837296, "step": 54030 }, { "grad_norm": 0.24647000432014465, "learning_rate": 4.745640834211011e-05, "loss": 0.01, "step": 54040 }, { "loss_action": 0.00694733951240778, "loss_total": 0.00694733951240778, "step": 54040 }, { "grad_norm": 0.22202083468437195, "learning_rate": 4.7439895192608054e-05, "loss": 0.0091, "step": 54050 }, { "loss_action": 0.008200696669518948, "loss_total": 0.008200696669518948, "step": 54050 }, { "grad_norm": 0.22068533301353455, "learning_rate": 4.7423382323075186e-05, "loss": 0.0078, "step": 54060 }, { "loss_action": 0.00785948894917965, "loss_total": 0.00785948894917965, "step": 54060 }, { "grad_norm": 0.21896804869174957, "learning_rate": 4.740686973531737e-05, "loss": 0.0076, "step": 54070 }, { "loss_action": 0.0071675656363368034, "loss_total": 0.0071675656363368034, "step": 54070 }, { "grad_norm": 0.23316389322280884, "learning_rate": 4.7390357431140375e-05, "loss": 0.0089, "step": 54080 }, { "loss_action": 0.012311062775552273, "loss_total": 0.012311062775552273, "step": 54080 }, { "grad_norm": 0.2268168032169342, "learning_rate": 4.737384541234998e-05, "loss": 0.0095, "step": 54090 }, { "loss_action": 0.011559774167835712, "loss_total": 0.011559774167835712, "step": 54090 }, { "grad_norm": 0.23811927437782288, "learning_rate": 4.735733368075189e-05, "loss": 0.011, "step": 54100 }, { "loss_action": 0.007942205294966698, "loss_total": 0.007942205294966698, "step": 54100 }, { "grad_norm": 0.1994321197271347, "learning_rate": 4.734082223815182e-05, "loss": 0.01, "step": 54110 }, { "loss_action": 0.00787805113941431, "loss_total": 0.00787805113941431, "step": 54110 }, { "grad_norm": 0.23956231772899628, "learning_rate": 4.7324311086355436e-05, "loss": 0.0077, "step": 54120 }, { "loss_action": 0.007832587696611881, "loss_total": 0.007832587696611881, "step": 54120 }, { "grad_norm": 0.24680006504058838, "learning_rate": 4.730780022716836e-05, "loss": 0.0089, "step": 54130 }, { "loss_action": 0.00835129152983427, "loss_total": 0.00835129152983427, "step": 54130 }, { "grad_norm": 0.19394488632678986, "learning_rate": 4.729128966239619e-05, "loss": 0.0089, "step": 54140 }, { "loss_action": 0.008002787828445435, "loss_total": 0.008002787828445435, "step": 54140 }, { "grad_norm": 0.2940014600753784, "learning_rate": 4.7274779393844536e-05, "loss": 0.0103, "step": 54150 }, { "loss_action": 0.008948751725256443, "loss_total": 0.008948751725256443, "step": 54150 }, { "grad_norm": 0.20357605814933777, "learning_rate": 4.725826942331891e-05, "loss": 0.0093, "step": 54160 }, { "loss_action": 0.009131313301622868, "loss_total": 0.009131313301622868, "step": 54160 }, { "grad_norm": 0.21436625719070435, "learning_rate": 4.724175975262481e-05, "loss": 0.009, "step": 54170 }, { "loss_action": 0.011799891479313374, "loss_total": 0.011799891479313374, "step": 54170 }, { "grad_norm": 0.21994586288928986, "learning_rate": 4.722525038356772e-05, "loss": 0.0097, "step": 54180 }, { "loss_action": 0.009341065771877766, "loss_total": 0.009341065771877766, "step": 54180 }, { "grad_norm": 0.18196623027324677, "learning_rate": 4.7208741317953075e-05, "loss": 0.0092, "step": 54190 }, { "loss_action": 0.0063444641418755054, "loss_total": 0.0063444641418755054, "step": 54190 }, { "grad_norm": 0.17932704091072083, "learning_rate": 4.7192232557586264e-05, "loss": 0.009, "step": 54200 }, { "loss_action": 0.009004016406834126, "loss_total": 0.009004016406834126, "step": 54200 }, { "grad_norm": 0.2609255909919739, "learning_rate": 4.717572410427269e-05, "loss": 0.0091, "step": 54210 }, { "loss_action": 0.008402179926633835, "loss_total": 0.008402179926633835, "step": 54210 }, { "grad_norm": 0.20507018268108368, "learning_rate": 4.71592159598177e-05, "loss": 0.0085, "step": 54220 }, { "loss_action": 0.008218799717724323, "loss_total": 0.008218799717724323, "step": 54220 }, { "grad_norm": 0.25589627027511597, "learning_rate": 4.714270812602657e-05, "loss": 0.0103, "step": 54230 }, { "loss_action": 0.010333333164453506, "loss_total": 0.010333333164453506, "step": 54230 }, { "grad_norm": 0.2094714343547821, "learning_rate": 4.712620060470458e-05, "loss": 0.0093, "step": 54240 }, { "loss_action": 0.0070397877134382725, "loss_total": 0.0070397877134382725, "step": 54240 }, { "grad_norm": 0.23487715423107147, "learning_rate": 4.7109693397656986e-05, "loss": 0.0105, "step": 54250 }, { "loss_action": 0.010518848896026611, "loss_total": 0.010518848896026611, "step": 54250 }, { "grad_norm": 0.295095831155777, "learning_rate": 4.709318650668894e-05, "loss": 0.0106, "step": 54260 }, { "loss_action": 0.006916064769029617, "loss_total": 0.006916064769029617, "step": 54260 }, { "grad_norm": 0.24875760078430176, "learning_rate": 4.7076679933605676e-05, "loss": 0.011, "step": 54270 }, { "loss_action": 0.009574313648045063, "loss_total": 0.009574313648045063, "step": 54270 }, { "grad_norm": 0.25312352180480957, "learning_rate": 4.70601736802123e-05, "loss": 0.0082, "step": 54280 }, { "loss_action": 0.008176062256097794, "loss_total": 0.008176062256097794, "step": 54280 }, { "grad_norm": 0.2602725327014923, "learning_rate": 4.704366774831391e-05, "loss": 0.0094, "step": 54290 }, { "loss_action": 0.011830134317278862, "loss_total": 0.011830134317278862, "step": 54290 }, { "grad_norm": 0.2300392985343933, "learning_rate": 4.702716213971557e-05, "loss": 0.0105, "step": 54300 }, { "loss_action": 0.01110459491610527, "loss_total": 0.01110459491610527, "step": 54300 }, { "grad_norm": 0.2453145831823349, "learning_rate": 4.70106568562223e-05, "loss": 0.0119, "step": 54310 }, { "loss_action": 0.007534683682024479, "loss_total": 0.007534683682024479, "step": 54310 }, { "grad_norm": 0.22131486237049103, "learning_rate": 4.6994151899639105e-05, "loss": 0.0087, "step": 54320 }, { "loss_action": 0.01004720851778984, "loss_total": 0.01004720851778984, "step": 54320 }, { "grad_norm": 0.25350940227508545, "learning_rate": 4.697764727177093e-05, "loss": 0.0094, "step": 54330 }, { "loss_action": 0.008108980022370815, "loss_total": 0.008108980022370815, "step": 54330 }, { "grad_norm": 0.23680414259433746, "learning_rate": 4.696114297442272e-05, "loss": 0.0087, "step": 54340 }, { "loss_action": 0.00873483344912529, "loss_total": 0.00873483344912529, "step": 54340 }, { "grad_norm": 0.2553909122943878, "learning_rate": 4.694463900939933e-05, "loss": 0.0112, "step": 54350 }, { "loss_action": 0.009172694757580757, "loss_total": 0.009172694757580757, "step": 54350 }, { "grad_norm": 0.24466276168823242, "learning_rate": 4.692813537850564e-05, "loss": 0.0091, "step": 54360 }, { "loss_action": 0.01359102688729763, "loss_total": 0.01359102688729763, "step": 54360 }, { "grad_norm": 0.2284240871667862, "learning_rate": 4.6911632083546445e-05, "loss": 0.0107, "step": 54370 }, { "loss_action": 0.00847147312015295, "loss_total": 0.00847147312015295, "step": 54370 }, { "grad_norm": 0.268595427274704, "learning_rate": 4.6895129126326525e-05, "loss": 0.0099, "step": 54380 }, { "loss_action": 0.009465204551815987, "loss_total": 0.009465204551815987, "step": 54380 }, { "grad_norm": 0.2631278336048126, "learning_rate": 4.687862650865059e-05, "loss": 0.0104, "step": 54390 }, { "loss_action": 0.007822545245289803, "loss_total": 0.007822545245289803, "step": 54390 }, { "grad_norm": 0.28158947825431824, "learning_rate": 4.686212423232339e-05, "loss": 0.0108, "step": 54400 }, { "loss_action": 0.00814272090792656, "loss_total": 0.00814272090792656, "step": 54400 }, { "grad_norm": 0.30705055594444275, "learning_rate": 4.6845622299149565e-05, "loss": 0.0097, "step": 54410 }, { "loss_action": 0.008627898059785366, "loss_total": 0.008627898059785366, "step": 54410 }, { "grad_norm": 0.212042436003685, "learning_rate": 4.682912071093374e-05, "loss": 0.0097, "step": 54420 }, { "loss_action": 0.007950752973556519, "loss_total": 0.007950752973556519, "step": 54420 }, { "grad_norm": 0.2707979679107666, "learning_rate": 4.681261946948052e-05, "loss": 0.0095, "step": 54430 }, { "loss_action": 0.009559708647429943, "loss_total": 0.009559708647429943, "step": 54430 }, { "grad_norm": 0.23783794045448303, "learning_rate": 4.679611857659443e-05, "loss": 0.0099, "step": 54440 }, { "loss_action": 0.008880455046892166, "loss_total": 0.008880455046892166, "step": 54440 }, { "grad_norm": 0.20266489684581757, "learning_rate": 4.6779618034079975e-05, "loss": 0.0095, "step": 54450 }, { "loss_action": 0.009228340350091457, "loss_total": 0.009228340350091457, "step": 54450 }, { "grad_norm": 0.23963439464569092, "learning_rate": 4.6763117843741675e-05, "loss": 0.0088, "step": 54460 }, { "loss_action": 0.010201551020145416, "loss_total": 0.010201551020145416, "step": 54460 }, { "grad_norm": 0.24302160739898682, "learning_rate": 4.674661800738394e-05, "loss": 0.0101, "step": 54470 }, { "loss_action": 0.011205580085515976, "loss_total": 0.011205580085515976, "step": 54470 }, { "grad_norm": 0.222696453332901, "learning_rate": 4.673011852681117e-05, "loss": 0.0111, "step": 54480 }, { "loss_action": 0.008385288529098034, "loss_total": 0.008385288529098034, "step": 54480 }, { "grad_norm": 0.22936666011810303, "learning_rate": 4.671361940382772e-05, "loss": 0.0095, "step": 54490 }, { "loss_action": 0.008900057524442673, "loss_total": 0.008900057524442673, "step": 54490 }, { "grad_norm": 0.21836814284324646, "learning_rate": 4.669712064023791e-05, "loss": 0.0088, "step": 54500 }, { "loss_action": 0.006240605376660824, "loss_total": 0.006240605376660824, "step": 54500 }, { "grad_norm": 0.21941789984703064, "learning_rate": 4.668062223784602e-05, "loss": 0.0083, "step": 54510 }, { "loss_action": 0.007515282370150089, "loss_total": 0.007515282370150089, "step": 54510 }, { "grad_norm": 0.24551589787006378, "learning_rate": 4.6664124198456274e-05, "loss": 0.0095, "step": 54520 }, { "loss_action": 0.007842118851840496, "loss_total": 0.007842118851840496, "step": 54520 }, { "grad_norm": 0.23539184033870697, "learning_rate": 4.6647626523872905e-05, "loss": 0.0102, "step": 54530 }, { "loss_action": 0.011102993972599506, "loss_total": 0.011102993972599506, "step": 54530 }, { "grad_norm": 0.17363552749156952, "learning_rate": 4.6631129215900066e-05, "loss": 0.0097, "step": 54540 }, { "loss_action": 0.013235356658697128, "loss_total": 0.013235356658697128, "step": 54540 }, { "grad_norm": 0.22167515754699707, "learning_rate": 4.661463227634187e-05, "loss": 0.0097, "step": 54550 }, { "loss_action": 0.007955222390592098, "loss_total": 0.007955222390592098, "step": 54550 }, { "grad_norm": 0.2698019742965698, "learning_rate": 4.659813570700238e-05, "loss": 0.0088, "step": 54560 }, { "loss_action": 0.006070726551115513, "loss_total": 0.006070726551115513, "step": 54560 }, { "grad_norm": 0.28261324763298035, "learning_rate": 4.658163950968568e-05, "loss": 0.0093, "step": 54570 }, { "loss_action": 0.012602399103343487, "loss_total": 0.012602399103343487, "step": 54570 }, { "grad_norm": 0.22846554219722748, "learning_rate": 4.6565143686195726e-05, "loss": 0.0101, "step": 54580 }, { "loss_action": 0.008589738048613071, "loss_total": 0.008589738048613071, "step": 54580 }, { "grad_norm": 0.22919581830501556, "learning_rate": 4.654864823833649e-05, "loss": 0.0092, "step": 54590 }, { "loss_action": 0.007645323406904936, "loss_total": 0.007645323406904936, "step": 54590 }, { "grad_norm": 0.3489736020565033, "learning_rate": 4.65321531679119e-05, "loss": 0.0093, "step": 54600 }, { "loss_action": 0.009076438844203949, "loss_total": 0.009076438844203949, "step": 54600 }, { "grad_norm": 0.23618139326572418, "learning_rate": 4.6515658476725834e-05, "loss": 0.0095, "step": 54610 }, { "loss_action": 0.009674787521362305, "loss_total": 0.009674787521362305, "step": 54610 }, { "grad_norm": 0.24013690650463104, "learning_rate": 4.649916416658212e-05, "loss": 0.0099, "step": 54620 }, { "loss_action": 0.011244208551943302, "loss_total": 0.011244208551943302, "step": 54620 }, { "grad_norm": 0.20663459599018097, "learning_rate": 4.648267023928455e-05, "loss": 0.0099, "step": 54630 }, { "loss_action": 0.008557220920920372, "loss_total": 0.008557220920920372, "step": 54630 }, { "grad_norm": 0.20818369090557098, "learning_rate": 4.646617669663687e-05, "loss": 0.0092, "step": 54640 }, { "loss_action": 0.006568032316863537, "loss_total": 0.006568032316863537, "step": 54640 }, { "grad_norm": 0.21643894910812378, "learning_rate": 4.644968354044277e-05, "loss": 0.0093, "step": 54650 }, { "loss_action": 0.007294844835996628, "loss_total": 0.007294844835996628, "step": 54650 }, { "grad_norm": 0.20849338173866272, "learning_rate": 4.643319077250596e-05, "loss": 0.0105, "step": 54660 }, { "loss_action": 0.010172159411013126, "loss_total": 0.010172159411013126, "step": 54660 }, { "grad_norm": 0.2576087713241577, "learning_rate": 4.6416698394630055e-05, "loss": 0.0095, "step": 54670 }, { "loss_action": 0.009492701850831509, "loss_total": 0.009492701850831509, "step": 54670 }, { "grad_norm": 0.23239919543266296, "learning_rate": 4.640020640861862e-05, "loss": 0.0097, "step": 54680 }, { "loss_action": 0.01088382676243782, "loss_total": 0.01088382676243782, "step": 54680 }, { "grad_norm": 0.2868604362010956, "learning_rate": 4.6383714816275195e-05, "loss": 0.0099, "step": 54690 }, { "loss_action": 0.009866708889603615, "loss_total": 0.009866708889603615, "step": 54690 }, { "grad_norm": 0.2715151906013489, "learning_rate": 4.636722361940329e-05, "loss": 0.0099, "step": 54700 }, { "loss_action": 0.011892197653651237, "loss_total": 0.011892197653651237, "step": 54700 }, { "grad_norm": 0.23455481231212616, "learning_rate": 4.635073281980632e-05, "loss": 0.0082, "step": 54710 }, { "loss_action": 0.010512332431972027, "loss_total": 0.010512332431972027, "step": 54710 }, { "grad_norm": 0.27316048741340637, "learning_rate": 4.633424241928775e-05, "loss": 0.0096, "step": 54720 }, { "loss_action": 0.007337397430092096, "loss_total": 0.007337397430092096, "step": 54720 }, { "grad_norm": 0.23674926161766052, "learning_rate": 4.6317752419650914e-05, "loss": 0.0078, "step": 54730 }, { "loss_action": 0.0065168715082108974, "loss_total": 0.0065168715082108974, "step": 54730 }, { "grad_norm": 0.1923973113298416, "learning_rate": 4.630126282269914e-05, "loss": 0.0079, "step": 54740 }, { "loss_action": 0.009644933044910431, "loss_total": 0.009644933044910431, "step": 54740 }, { "grad_norm": 0.2285308688879013, "learning_rate": 4.628477363023569e-05, "loss": 0.0086, "step": 54750 }, { "loss_action": 0.007852204144001007, "loss_total": 0.007852204144001007, "step": 54750 }, { "grad_norm": 0.24158184230327606, "learning_rate": 4.626828484406383e-05, "loss": 0.008, "step": 54760 }, { "loss_action": 0.012402970343828201, "loss_total": 0.012402970343828201, "step": 54760 }, { "grad_norm": 0.24137148261070251, "learning_rate": 4.625179646598669e-05, "loss": 0.0087, "step": 54770 }, { "loss_action": 0.007970141246914864, "loss_total": 0.007970141246914864, "step": 54770 }, { "grad_norm": 0.20953840017318726, "learning_rate": 4.6235308497807487e-05, "loss": 0.0077, "step": 54780 }, { "loss_action": 0.008252064697444439, "loss_total": 0.008252064697444439, "step": 54780 }, { "grad_norm": 0.19255711138248444, "learning_rate": 4.6218820941329276e-05, "loss": 0.0092, "step": 54790 }, { "loss_action": 0.011118276044726372, "loss_total": 0.011118276044726372, "step": 54790 }, { "grad_norm": 0.27922552824020386, "learning_rate": 4.620233379835513e-05, "loss": 0.009, "step": 54800 }, { "loss_action": 0.006083082407712936, "loss_total": 0.006083082407712936, "step": 54800 }, { "grad_norm": 0.18167966604232788, "learning_rate": 4.618584707068804e-05, "loss": 0.0088, "step": 54810 }, { "loss_action": 0.008278446272015572, "loss_total": 0.008278446272015572, "step": 54810 }, { "grad_norm": 0.21988995373249054, "learning_rate": 4.616936076013099e-05, "loss": 0.0087, "step": 54820 }, { "loss_action": 0.014022108167409897, "loss_total": 0.014022108167409897, "step": 54820 }, { "grad_norm": 0.2873381972312927, "learning_rate": 4.615287486848688e-05, "loss": 0.0099, "step": 54830 }, { "loss_action": 0.017276518046855927, "loss_total": 0.017276518046855927, "step": 54830 }, { "grad_norm": 0.2673340439796448, "learning_rate": 4.6136389397558584e-05, "loss": 0.0103, "step": 54840 }, { "loss_action": 0.010078401304781437, "loss_total": 0.010078401304781437, "step": 54840 }, { "grad_norm": 0.24566984176635742, "learning_rate": 4.6119904349148935e-05, "loss": 0.0099, "step": 54850 }, { "loss_action": 0.011674444191157818, "loss_total": 0.011674444191157818, "step": 54850 }, { "grad_norm": 0.2387211173772812, "learning_rate": 4.6103419725060726e-05, "loss": 0.0092, "step": 54860 }, { "loss_action": 0.010118822567164898, "loss_total": 0.010118822567164898, "step": 54860 }, { "grad_norm": 0.24468760192394257, "learning_rate": 4.608693552709667e-05, "loss": 0.0092, "step": 54870 }, { "loss_action": 0.009394391439855099, "loss_total": 0.009394391439855099, "step": 54870 }, { "grad_norm": 0.21371853351593018, "learning_rate": 4.607045175705947e-05, "loss": 0.009, "step": 54880 }, { "loss_action": 0.006171527784317732, "loss_total": 0.006171527784317732, "step": 54880 }, { "grad_norm": 0.22295457124710083, "learning_rate": 4.605396841675176e-05, "loss": 0.009, "step": 54890 }, { "loss_action": 0.009089569561183453, "loss_total": 0.009089569561183453, "step": 54890 }, { "grad_norm": 0.2235039621591568, "learning_rate": 4.6037485507976094e-05, "loss": 0.0084, "step": 54900 }, { "loss_action": 0.009393729269504547, "loss_total": 0.009393729269504547, "step": 54900 }, { "grad_norm": 0.2793435752391815, "learning_rate": 4.602100303253509e-05, "loss": 0.0079, "step": 54910 }, { "loss_action": 0.006726720370352268, "loss_total": 0.006726720370352268, "step": 54910 }, { "grad_norm": 0.24910873174667358, "learning_rate": 4.600452099223122e-05, "loss": 0.0093, "step": 54920 }, { "loss_action": 0.010233145207166672, "loss_total": 0.010233145207166672, "step": 54920 }, { "grad_norm": 0.25099506974220276, "learning_rate": 4.598803938886691e-05, "loss": 0.0098, "step": 54930 }, { "loss_action": 0.009902344085276127, "loss_total": 0.009902344085276127, "step": 54930 }, { "grad_norm": 0.23282989859580994, "learning_rate": 4.597155822424459e-05, "loss": 0.009, "step": 54940 }, { "loss_action": 0.009217893704771996, "loss_total": 0.009217893704771996, "step": 54940 }, { "grad_norm": 0.21992656588554382, "learning_rate": 4.59550775001666e-05, "loss": 0.0093, "step": 54950 }, { "loss_action": 0.012763247825205326, "loss_total": 0.012763247825205326, "step": 54950 }, { "grad_norm": 0.24053028225898743, "learning_rate": 4.5938597218435234e-05, "loss": 0.0092, "step": 54960 }, { "loss_action": 0.008091842755675316, "loss_total": 0.008091842755675316, "step": 54960 }, { "grad_norm": 0.2670344412326813, "learning_rate": 4.592211738085279e-05, "loss": 0.01, "step": 54970 }, { "loss_action": 0.011220704764127731, "loss_total": 0.011220704764127731, "step": 54970 }, { "grad_norm": 0.2503011226654053, "learning_rate": 4.590563798922146e-05, "loss": 0.0085, "step": 54980 }, { "loss_action": 0.009736008010804653, "loss_total": 0.009736008010804653, "step": 54980 }, { "grad_norm": 0.2080056369304657, "learning_rate": 4.5889159045343404e-05, "loss": 0.009, "step": 54990 }, { "loss_action": 0.007820775732398033, "loss_total": 0.007820775732398033, "step": 54990 }, { "grad_norm": 0.25195109844207764, "learning_rate": 4.5872680551020734e-05, "loss": 0.0101, "step": 55000 }, { "loss_action": 0.008281107060611248, "loss_total": 0.008281107060611248, "step": 55000 }, { "grad_norm": 0.3245237469673157, "learning_rate": 4.585620250805552e-05, "loss": 0.0098, "step": 55010 }, { "loss_action": 0.013619990088045597, "loss_total": 0.013619990088045597, "step": 55010 }, { "grad_norm": 0.20538078248500824, "learning_rate": 4.583972491824975e-05, "loss": 0.0096, "step": 55020 }, { "loss_action": 0.009628099389374256, "loss_total": 0.009628099389374256, "step": 55020 }, { "grad_norm": 0.23997001349925995, "learning_rate": 4.582324778340541e-05, "loss": 0.0098, "step": 55030 }, { "loss_action": 0.00797693245112896, "loss_total": 0.00797693245112896, "step": 55030 }, { "grad_norm": 0.21335862576961517, "learning_rate": 4.5806771105324424e-05, "loss": 0.0103, "step": 55040 }, { "loss_action": 0.013638242147862911, "loss_total": 0.013638242147862911, "step": 55040 }, { "grad_norm": 0.2877674400806427, "learning_rate": 4.579029488580865e-05, "loss": 0.0113, "step": 55050 }, { "loss_action": 0.00880779791623354, "loss_total": 0.00880779791623354, "step": 55050 }, { "grad_norm": 0.26319852471351624, "learning_rate": 4.5773819126659876e-05, "loss": 0.0111, "step": 55060 }, { "loss_action": 0.007950939238071442, "loss_total": 0.007950939238071442, "step": 55060 }, { "grad_norm": 0.2658257484436035, "learning_rate": 4.575734382967991e-05, "loss": 0.0104, "step": 55070 }, { "loss_action": 0.010392164811491966, "loss_total": 0.010392164811491966, "step": 55070 }, { "grad_norm": 0.30948400497436523, "learning_rate": 4.574086899667044e-05, "loss": 0.0098, "step": 55080 }, { "loss_action": 0.007265442982316017, "loss_total": 0.007265442982316017, "step": 55080 }, { "grad_norm": 0.2976619601249695, "learning_rate": 4.5724394629433106e-05, "loss": 0.0099, "step": 55090 }, { "loss_action": 0.00956665351986885, "loss_total": 0.00956665351986885, "step": 55090 }, { "grad_norm": 0.221382737159729, "learning_rate": 4.570792072976958e-05, "loss": 0.009, "step": 55100 }, { "loss_action": 0.009450221434235573, "loss_total": 0.009450221434235573, "step": 55100 }, { "grad_norm": 0.283614844083786, "learning_rate": 4.569144729948138e-05, "loss": 0.0096, "step": 55110 }, { "loss_action": 0.008278422988951206, "loss_total": 0.008278422988951206, "step": 55110 }, { "grad_norm": 0.2445708066225052, "learning_rate": 4.5674974340370033e-05, "loss": 0.0094, "step": 55120 }, { "loss_action": 0.008210908621549606, "loss_total": 0.008210908621549606, "step": 55120 }, { "grad_norm": 0.2338806390762329, "learning_rate": 4.565850185423699e-05, "loss": 0.0093, "step": 55130 }, { "loss_action": 0.008247213438153267, "loss_total": 0.008247213438153267, "step": 55130 }, { "grad_norm": 0.23887735605239868, "learning_rate": 4.564202984288365e-05, "loss": 0.0095, "step": 55140 }, { "loss_action": 0.006550153251737356, "loss_total": 0.006550153251737356, "step": 55140 }, { "grad_norm": 0.2762793302536011, "learning_rate": 4.5625558308111356e-05, "loss": 0.0082, "step": 55150 }, { "loss_action": 0.009020436555147171, "loss_total": 0.009020436555147171, "step": 55150 }, { "grad_norm": 0.1995035856962204, "learning_rate": 4.560908725172145e-05, "loss": 0.01, "step": 55160 }, { "loss_action": 0.010624494403600693, "loss_total": 0.010624494403600693, "step": 55160 }, { "grad_norm": 0.32636862993240356, "learning_rate": 4.559261667551516e-05, "loss": 0.0087, "step": 55170 }, { "loss_action": 0.009264618158340454, "loss_total": 0.009264618158340454, "step": 55170 }, { "grad_norm": 0.2045259326696396, "learning_rate": 4.5576146581293685e-05, "loss": 0.0078, "step": 55180 }, { "loss_action": 0.008038846775889397, "loss_total": 0.008038846775889397, "step": 55180 }, { "grad_norm": 0.2633744180202484, "learning_rate": 4.5559676970858164e-05, "loss": 0.0083, "step": 55190 }, { "loss_action": 0.009232092648744583, "loss_total": 0.009232092648744583, "step": 55190 }, { "grad_norm": 0.22659124433994293, "learning_rate": 4.5543207846009705e-05, "loss": 0.0114, "step": 55200 }, { "loss_action": 0.005557004362344742, "loss_total": 0.005557004362344742, "step": 55200 }, { "grad_norm": 0.2850917875766754, "learning_rate": 4.552673920854933e-05, "loss": 0.0087, "step": 55210 }, { "loss_action": 0.012074125930666924, "loss_total": 0.012074125930666924, "step": 55210 }, { "grad_norm": 0.21651721000671387, "learning_rate": 4.5510271060278006e-05, "loss": 0.0092, "step": 55220 }, { "loss_action": 0.008354940451681614, "loss_total": 0.008354940451681614, "step": 55220 }, { "grad_norm": 0.2546032965183258, "learning_rate": 4.5493803402996704e-05, "loss": 0.0102, "step": 55230 }, { "loss_action": 0.007727477233856916, "loss_total": 0.007727477233856916, "step": 55230 }, { "grad_norm": 0.24601903557777405, "learning_rate": 4.5477336238506295e-05, "loss": 0.0093, "step": 55240 }, { "loss_action": 0.007343405857682228, "loss_total": 0.007343405857682228, "step": 55240 }, { "grad_norm": 0.29119718074798584, "learning_rate": 4.546086956860759e-05, "loss": 0.0084, "step": 55250 }, { "loss_action": 0.007083243690431118, "loss_total": 0.007083243690431118, "step": 55250 }, { "grad_norm": 0.24960099160671234, "learning_rate": 4.5444403395101374e-05, "loss": 0.0112, "step": 55260 }, { "loss_action": 0.007306164130568504, "loss_total": 0.007306164130568504, "step": 55260 }, { "grad_norm": 0.26929327845573425, "learning_rate": 4.542793771978834e-05, "loss": 0.0107, "step": 55270 }, { "loss_action": 0.008370397612452507, "loss_total": 0.008370397612452507, "step": 55270 }, { "grad_norm": 0.23502793908119202, "learning_rate": 4.541147254446916e-05, "loss": 0.0091, "step": 55280 }, { "loss_action": 0.012471156194806099, "loss_total": 0.012471156194806099, "step": 55280 }, { "grad_norm": 0.2041425257921219, "learning_rate": 4.539500787094445e-05, "loss": 0.0086, "step": 55290 }, { "loss_action": 0.012545512989163399, "loss_total": 0.012545512989163399, "step": 55290 }, { "grad_norm": 0.15949538350105286, "learning_rate": 4.537854370101475e-05, "loss": 0.0093, "step": 55300 }, { "loss_action": 0.009343810379505157, "loss_total": 0.009343810379505157, "step": 55300 }, { "grad_norm": 0.24130216240882874, "learning_rate": 4.5362080036480566e-05, "loss": 0.0088, "step": 55310 }, { "loss_action": 0.009236528538167477, "loss_total": 0.009236528538167477, "step": 55310 }, { "grad_norm": 0.3213803768157959, "learning_rate": 4.534561687914235e-05, "loss": 0.0086, "step": 55320 }, { "loss_action": 0.005949567537754774, "loss_total": 0.005949567537754774, "step": 55320 }, { "grad_norm": 0.2645246386528015, "learning_rate": 4.5329154230800466e-05, "loss": 0.0089, "step": 55330 }, { "loss_action": 0.006915479898452759, "loss_total": 0.006915479898452759, "step": 55330 }, { "grad_norm": 0.31820574402809143, "learning_rate": 4.531269209325525e-05, "loss": 0.0092, "step": 55340 }, { "loss_action": 0.011690684594213963, "loss_total": 0.011690684594213963, "step": 55340 }, { "grad_norm": 0.21293091773986816, "learning_rate": 4.529623046830696e-05, "loss": 0.0096, "step": 55350 }, { "loss_action": 0.011562986299395561, "loss_total": 0.011562986299395561, "step": 55350 }, { "grad_norm": 0.28875136375427246, "learning_rate": 4.5279769357755866e-05, "loss": 0.009, "step": 55360 }, { "loss_action": 0.011417222209274769, "loss_total": 0.011417222209274769, "step": 55360 }, { "grad_norm": 0.19431272149085999, "learning_rate": 4.5263308763402084e-05, "loss": 0.0086, "step": 55370 }, { "loss_action": 0.007449079304933548, "loss_total": 0.007449079304933548, "step": 55370 }, { "grad_norm": 0.26731759309768677, "learning_rate": 4.524684868704574e-05, "loss": 0.0086, "step": 55380 }, { "loss_action": 0.009959633462131023, "loss_total": 0.009959633462131023, "step": 55380 }, { "grad_norm": 0.2504097819328308, "learning_rate": 4.523038913048688e-05, "loss": 0.0091, "step": 55390 }, { "loss_action": 0.01142803393304348, "loss_total": 0.01142803393304348, "step": 55390 }, { "grad_norm": 0.22688153386116028, "learning_rate": 4.521393009552549e-05, "loss": 0.0102, "step": 55400 }, { "loss_action": 0.007162770722061396, "loss_total": 0.007162770722061396, "step": 55400 }, { "grad_norm": 0.27946895360946655, "learning_rate": 4.5197471583961484e-05, "loss": 0.0101, "step": 55410 }, { "loss_action": 0.00919080525636673, "loss_total": 0.00919080525636673, "step": 55410 }, { "grad_norm": 0.19348664581775665, "learning_rate": 4.51810135975948e-05, "loss": 0.0095, "step": 55420 }, { "loss_action": 0.00838550180196762, "loss_total": 0.00838550180196762, "step": 55420 }, { "grad_norm": 0.19829894602298737, "learning_rate": 4.516455613822521e-05, "loss": 0.0085, "step": 55430 }, { "loss_action": 0.007770978845655918, "loss_total": 0.007770978845655918, "step": 55430 }, { "grad_norm": 0.21216197311878204, "learning_rate": 4.514809920765249e-05, "loss": 0.0097, "step": 55440 }, { "loss_action": 0.009754689410328865, "loss_total": 0.009754689410328865, "step": 55440 }, { "grad_norm": 0.1901281177997589, "learning_rate": 4.5131642807676356e-05, "loss": 0.009, "step": 55450 }, { "loss_action": 0.008416279219090939, "loss_total": 0.008416279219090939, "step": 55450 }, { "grad_norm": 0.2355530858039856, "learning_rate": 4.511518694009644e-05, "loss": 0.0081, "step": 55460 }, { "loss_action": 0.008519154042005539, "loss_total": 0.008519154042005539, "step": 55460 }, { "grad_norm": 0.2213529348373413, "learning_rate": 4.509873160671231e-05, "loss": 0.0087, "step": 55470 }, { "loss_action": 0.009516801685094833, "loss_total": 0.009516801685094833, "step": 55470 }, { "grad_norm": 0.2587440311908722, "learning_rate": 4.508227680932356e-05, "loss": 0.0089, "step": 55480 }, { "loss_action": 0.008039762265980244, "loss_total": 0.008039762265980244, "step": 55480 }, { "grad_norm": 0.19736231863498688, "learning_rate": 4.5065822549729605e-05, "loss": 0.0073, "step": 55490 }, { "loss_action": 0.008086957968771458, "loss_total": 0.008086957968771458, "step": 55490 }, { "grad_norm": 0.18115998804569244, "learning_rate": 4.504936882972989e-05, "loss": 0.0097, "step": 55500 }, { "loss_action": 0.00877914484590292, "loss_total": 0.00877914484590292, "step": 55500 }, { "grad_norm": 0.23770560324192047, "learning_rate": 4.503291565112374e-05, "loss": 0.0092, "step": 55510 }, { "loss_action": 0.020341603085398674, "loss_total": 0.020341603085398674, "step": 55510 }, { "grad_norm": 0.21225078403949738, "learning_rate": 4.501646301571048e-05, "loss": 0.01, "step": 55520 }, { "loss_action": 0.00900892075151205, "loss_total": 0.00900892075151205, "step": 55520 }, { "grad_norm": 0.256125807762146, "learning_rate": 4.500001092528933e-05, "loss": 0.0105, "step": 55530 }, { "loss_action": 0.011293490417301655, "loss_total": 0.011293490417301655, "step": 55530 }, { "grad_norm": 0.2983521521091461, "learning_rate": 4.4983559381659455e-05, "loss": 0.0102, "step": 55540 }, { "loss_action": 0.008711260743439198, "loss_total": 0.008711260743439198, "step": 55540 }, { "grad_norm": 0.20301425457000732, "learning_rate": 4.496710838661999e-05, "loss": 0.0084, "step": 55550 }, { "loss_action": 0.007998486049473286, "loss_total": 0.007998486049473286, "step": 55550 }, { "grad_norm": 0.2525966763496399, "learning_rate": 4.495065794196999e-05, "loss": 0.0086, "step": 55560 }, { "loss_action": 0.009313088841736317, "loss_total": 0.009313088841736317, "step": 55560 }, { "grad_norm": 0.22284646332263947, "learning_rate": 4.4934208049508455e-05, "loss": 0.0094, "step": 55570 }, { "loss_action": 0.011398069560527802, "loss_total": 0.011398069560527802, "step": 55570 }, { "grad_norm": 0.1985091269016266, "learning_rate": 4.4917758711034303e-05, "loss": 0.0094, "step": 55580 }, { "loss_action": 0.006996918469667435, "loss_total": 0.006996918469667435, "step": 55580 }, { "grad_norm": 0.27482637763023376, "learning_rate": 4.490130992834642e-05, "loss": 0.0086, "step": 55590 }, { "loss_action": 0.008500846102833748, "loss_total": 0.008500846102833748, "step": 55590 }, { "grad_norm": 0.2856871783733368, "learning_rate": 4.488486170324359e-05, "loss": 0.0085, "step": 55600 }, { "loss_action": 0.006142433267086744, "loss_total": 0.006142433267086744, "step": 55600 }, { "grad_norm": 0.2535427510738373, "learning_rate": 4.486841403752463e-05, "loss": 0.0081, "step": 55610 }, { "loss_action": 0.006877982057631016, "loss_total": 0.006877982057631016, "step": 55610 }, { "grad_norm": 0.319243848323822, "learning_rate": 4.4851966932988174e-05, "loss": 0.0079, "step": 55620 }, { "loss_action": 0.008768914267420769, "loss_total": 0.008768914267420769, "step": 55620 }, { "grad_norm": 0.28915756940841675, "learning_rate": 4.4835520391432894e-05, "loss": 0.0088, "step": 55630 }, { "loss_action": 0.007070744410157204, "loss_total": 0.007070744410157204, "step": 55630 }, { "grad_norm": 0.24800066649913788, "learning_rate": 4.481907441465733e-05, "loss": 0.0082, "step": 55640 }, { "loss_action": 0.008948025293648243, "loss_total": 0.008948025293648243, "step": 55640 }, { "grad_norm": 0.2004421204328537, "learning_rate": 4.480262900446e-05, "loss": 0.0093, "step": 55650 }, { "loss_action": 0.01586790941655636, "loss_total": 0.01586790941655636, "step": 55650 }, { "grad_norm": 0.20234866440296173, "learning_rate": 4.478618416263933e-05, "loss": 0.0116, "step": 55660 }, { "loss_action": 0.009070762433111668, "loss_total": 0.009070762433111668, "step": 55660 }, { "grad_norm": 0.1991012543439865, "learning_rate": 4.476973989099373e-05, "loss": 0.0095, "step": 55670 }, { "loss_action": 0.007303016725927591, "loss_total": 0.007303016725927591, "step": 55670 }, { "grad_norm": 0.2412901073694229, "learning_rate": 4.475329619132153e-05, "loss": 0.0096, "step": 55680 }, { "loss_action": 0.009809310548007488, "loss_total": 0.009809310548007488, "step": 55680 }, { "grad_norm": 0.22897829115390778, "learning_rate": 4.4736853065420956e-05, "loss": 0.0083, "step": 55690 }, { "loss_action": 0.009614706039428711, "loss_total": 0.009614706039428711, "step": 55690 }, { "grad_norm": 0.2736714482307434, "learning_rate": 4.472041051509023e-05, "loss": 0.0085, "step": 55700 }, { "loss_action": 0.0088210329413414, "loss_total": 0.0088210329413414, "step": 55700 }, { "grad_norm": 0.20941941440105438, "learning_rate": 4.470396854212746e-05, "loss": 0.0106, "step": 55710 }, { "loss_action": 0.00831532571464777, "loss_total": 0.00831532571464777, "step": 55710 }, { "grad_norm": 0.2095683366060257, "learning_rate": 4.468752714833072e-05, "loss": 0.0091, "step": 55720 }, { "loss_action": 0.008763163350522518, "loss_total": 0.008763163350522518, "step": 55720 }, { "grad_norm": 0.22261907160282135, "learning_rate": 4.467108633549803e-05, "loss": 0.0086, "step": 55730 }, { "loss_action": 0.007098023314028978, "loss_total": 0.007098023314028978, "step": 55730 }, { "grad_norm": 0.2862253785133362, "learning_rate": 4.4654646105427335e-05, "loss": 0.0083, "step": 55740 }, { "loss_action": 0.0070401523262262344, "loss_total": 0.0070401523262262344, "step": 55740 }, { "grad_norm": 0.24449340999126434, "learning_rate": 4.463820645991651e-05, "loss": 0.0086, "step": 55750 }, { "loss_action": 0.008113783784210682, "loss_total": 0.008113783784210682, "step": 55750 }, { "grad_norm": 0.22836044430732727, "learning_rate": 4.462176740076334e-05, "loss": 0.0092, "step": 55760 }, { "loss_action": 0.008108310401439667, "loss_total": 0.008108310401439667, "step": 55760 }, { "grad_norm": 0.19381599128246307, "learning_rate": 4.4605328929765624e-05, "loss": 0.0106, "step": 55770 }, { "loss_action": 0.010117837227880955, "loss_total": 0.010117837227880955, "step": 55770 }, { "grad_norm": 0.278152197599411, "learning_rate": 4.458889104872102e-05, "loss": 0.0102, "step": 55780 }, { "loss_action": 0.008990728296339512, "loss_total": 0.008990728296339512, "step": 55780 }, { "grad_norm": 0.21970228850841522, "learning_rate": 4.457245375942715e-05, "loss": 0.0091, "step": 55790 }, { "loss_action": 0.009127588011324406, "loss_total": 0.009127588011324406, "step": 55790 }, { "grad_norm": 0.28308331966400146, "learning_rate": 4.455601706368157e-05, "loss": 0.0098, "step": 55800 }, { "loss_action": 0.009271188639104366, "loss_total": 0.009271188639104366, "step": 55800 }, { "grad_norm": 0.23086382448673248, "learning_rate": 4.453958096328179e-05, "loss": 0.0088, "step": 55810 }, { "loss_action": 0.009074234403669834, "loss_total": 0.009074234403669834, "step": 55810 }, { "grad_norm": 0.22147732973098755, "learning_rate": 4.452314546002523e-05, "loss": 0.0089, "step": 55820 }, { "loss_action": 0.007293963339179754, "loss_total": 0.007293963339179754, "step": 55820 }, { "grad_norm": 0.24342134594917297, "learning_rate": 4.4506710555709246e-05, "loss": 0.0084, "step": 55830 }, { "loss_action": 0.007130372803658247, "loss_total": 0.007130372803658247, "step": 55830 }, { "grad_norm": 0.20136451721191406, "learning_rate": 4.449027625213114e-05, "loss": 0.0091, "step": 55840 }, { "loss_action": 0.007837790995836258, "loss_total": 0.007837790995836258, "step": 55840 }, { "grad_norm": 0.2580467760562897, "learning_rate": 4.4473842551088135e-05, "loss": 0.0088, "step": 55850 }, { "loss_action": 0.013596278615295887, "loss_total": 0.013596278615295887, "step": 55850 }, { "grad_norm": 0.2684388756752014, "learning_rate": 4.445740945437738e-05, "loss": 0.0091, "step": 55860 }, { "loss_action": 0.01431278046220541, "loss_total": 0.01431278046220541, "step": 55860 }, { "grad_norm": 0.2439209371805191, "learning_rate": 4.444097696379602e-05, "loss": 0.0102, "step": 55870 }, { "loss_action": 0.00970978382974863, "loss_total": 0.00970978382974863, "step": 55870 }, { "grad_norm": 0.25283700227737427, "learning_rate": 4.442454508114106e-05, "loss": 0.0085, "step": 55880 }, { "loss_action": 0.01415958907455206, "loss_total": 0.01415958907455206, "step": 55880 }, { "grad_norm": 0.2312205582857132, "learning_rate": 4.4408113808209465e-05, "loss": 0.0081, "step": 55890 }, { "loss_action": 0.007963478565216064, "loss_total": 0.007963478565216064, "step": 55890 }, { "grad_norm": 0.19885602593421936, "learning_rate": 4.439168314679813e-05, "loss": 0.0082, "step": 55900 }, { "loss_action": 0.00902037788182497, "loss_total": 0.00902037788182497, "step": 55900 }, { "grad_norm": 0.20296598970890045, "learning_rate": 4.43752530987039e-05, "loss": 0.008, "step": 55910 }, { "loss_action": 0.009211031720042229, "loss_total": 0.009211031720042229, "step": 55910 }, { "grad_norm": 0.24563755095005035, "learning_rate": 4.4358823665723515e-05, "loss": 0.0096, "step": 55920 }, { "loss_action": 0.011759890243411064, "loss_total": 0.011759890243411064, "step": 55920 }, { "grad_norm": 0.24363955855369568, "learning_rate": 4.434239484965371e-05, "loss": 0.0085, "step": 55930 }, { "loss_action": 0.006392889190465212, "loss_total": 0.006392889190465212, "step": 55930 }, { "grad_norm": 0.20614907145500183, "learning_rate": 4.4325966652291103e-05, "loss": 0.0087, "step": 55940 }, { "loss_action": 0.007999739609658718, "loss_total": 0.007999739609658718, "step": 55940 }, { "grad_norm": 0.18862111866474152, "learning_rate": 4.430953907543225e-05, "loss": 0.0089, "step": 55950 }, { "loss_action": 0.008052203804254532, "loss_total": 0.008052203804254532, "step": 55950 }, { "grad_norm": 0.24519680440425873, "learning_rate": 4.4293112120873645e-05, "loss": 0.0096, "step": 55960 }, { "loss_action": 0.01132995542138815, "loss_total": 0.01132995542138815, "step": 55960 }, { "grad_norm": 0.25707486271858215, "learning_rate": 4.427668579041172e-05, "loss": 0.0088, "step": 55970 }, { "loss_action": 0.008919700048863888, "loss_total": 0.008919700048863888, "step": 55970 }, { "grad_norm": 0.24055446684360504, "learning_rate": 4.4260260085842816e-05, "loss": 0.0081, "step": 55980 }, { "loss_action": 0.009559666737914085, "loss_total": 0.009559666737914085, "step": 55980 }, { "grad_norm": 0.2300744354724884, "learning_rate": 4.4243835008963256e-05, "loss": 0.0086, "step": 55990 }, { "loss_action": 0.010581772774457932, "loss_total": 0.010581772774457932, "step": 55990 }, { "grad_norm": 0.2655755579471588, "learning_rate": 4.422741056156925e-05, "loss": 0.0094, "step": 56000 }, { "loss_action": 0.008323019370436668, "loss_total": 0.008323019370436668, "step": 56000 }, { "grad_norm": 0.22643180191516876, "learning_rate": 4.421098674545693e-05, "loss": 0.0086, "step": 56010 }, { "loss_action": 0.006511921063065529, "loss_total": 0.006511921063065529, "step": 56010 }, { "grad_norm": 0.1912921965122223, "learning_rate": 4.419456356242241e-05, "loss": 0.0096, "step": 56020 }, { "loss_action": 0.009661347605288029, "loss_total": 0.009661347605288029, "step": 56020 }, { "grad_norm": 0.2231292575597763, "learning_rate": 4.4178141014261685e-05, "loss": 0.0088, "step": 56030 }, { "loss_action": 0.007404680829495192, "loss_total": 0.007404680829495192, "step": 56030 }, { "grad_norm": 0.25558537244796753, "learning_rate": 4.416171910277071e-05, "loss": 0.009, "step": 56040 }, { "loss_action": 0.008310518227517605, "loss_total": 0.008310518227517605, "step": 56040 }, { "grad_norm": 0.19886024296283722, "learning_rate": 4.414529782974533e-05, "loss": 0.0087, "step": 56050 }, { "loss_action": 0.006628294009715319, "loss_total": 0.006628294009715319, "step": 56050 }, { "grad_norm": 0.22548766434192657, "learning_rate": 4.41288771969814e-05, "loss": 0.0101, "step": 56060 }, { "loss_action": 0.009206324815750122, "loss_total": 0.009206324815750122, "step": 56060 }, { "grad_norm": 0.2039637416601181, "learning_rate": 4.411245720627464e-05, "loss": 0.0099, "step": 56070 }, { "loss_action": 0.008845188654959202, "loss_total": 0.008845188654959202, "step": 56070 }, { "grad_norm": 0.24022555351257324, "learning_rate": 4.40960378594207e-05, "loss": 0.0091, "step": 56080 }, { "loss_action": 0.00701883202418685, "loss_total": 0.00701883202418685, "step": 56080 }, { "grad_norm": 0.2238517552614212, "learning_rate": 4.407961915821519e-05, "loss": 0.0087, "step": 56090 }, { "loss_action": 0.006791377905756235, "loss_total": 0.006791377905756235, "step": 56090 }, { "grad_norm": 0.1950797140598297, "learning_rate": 4.406320110445362e-05, "loss": 0.0087, "step": 56100 }, { "loss_action": 0.009395845234394073, "loss_total": 0.009395845234394073, "step": 56100 }, { "grad_norm": 0.23963411152362823, "learning_rate": 4.404678369993144e-05, "loss": 0.0089, "step": 56110 }, { "loss_action": 0.007714603561908007, "loss_total": 0.007714603561908007, "step": 56110 }, { "grad_norm": 0.17779769003391266, "learning_rate": 4.403036694644406e-05, "loss": 0.0084, "step": 56120 }, { "loss_action": 0.008932588621973991, "loss_total": 0.008932588621973991, "step": 56120 }, { "grad_norm": 0.19607140123844147, "learning_rate": 4.4013950845786764e-05, "loss": 0.009, "step": 56130 }, { "loss_action": 0.007206794340163469, "loss_total": 0.007206794340163469, "step": 56130 }, { "grad_norm": 0.2543376684188843, "learning_rate": 4.399753539975482e-05, "loss": 0.0087, "step": 56140 }, { "loss_action": 0.008237835019826889, "loss_total": 0.008237835019826889, "step": 56140 }, { "grad_norm": 0.2641857862472534, "learning_rate": 4.398112061014337e-05, "loss": 0.0088, "step": 56150 }, { "loss_action": 0.0067892796359956264, "loss_total": 0.0067892796359956264, "step": 56150 }, { "grad_norm": 0.2097390741109848, "learning_rate": 4.396470647874753e-05, "loss": 0.0089, "step": 56160 }, { "loss_action": 0.00840573851019144, "loss_total": 0.00840573851019144, "step": 56160 }, { "grad_norm": 0.24641714990139008, "learning_rate": 4.394829300736229e-05, "loss": 0.0074, "step": 56170 }, { "loss_action": 0.008685729466378689, "loss_total": 0.008685729466378689, "step": 56170 }, { "grad_norm": 0.334524929523468, "learning_rate": 4.393188019778265e-05, "loss": 0.009, "step": 56180 }, { "loss_action": 0.006556314416229725, "loss_total": 0.006556314416229725, "step": 56180 }, { "grad_norm": 0.24272464215755463, "learning_rate": 4.391546805180347e-05, "loss": 0.0087, "step": 56190 }, { "loss_action": 0.011514538899064064, "loss_total": 0.011514538899064064, "step": 56190 }, { "grad_norm": 0.2278834730386734, "learning_rate": 4.389905657121955e-05, "loss": 0.0095, "step": 56200 }, { "loss_action": 0.008763776160776615, "loss_total": 0.008763776160776615, "step": 56200 }, { "grad_norm": 0.24082742631435394, "learning_rate": 4.3882645757825635e-05, "loss": 0.0085, "step": 56210 }, { "loss_action": 0.008289400488138199, "loss_total": 0.008289400488138199, "step": 56210 }, { "grad_norm": 0.1791924089193344, "learning_rate": 4.386623561341637e-05, "loss": 0.0098, "step": 56220 }, { "loss_action": 0.007326007820665836, "loss_total": 0.007326007820665836, "step": 56220 }, { "grad_norm": 0.23427461087703705, "learning_rate": 4.384982613978637e-05, "loss": 0.0088, "step": 56230 }, { "loss_action": 0.01607462391257286, "loss_total": 0.01607462391257286, "step": 56230 }, { "grad_norm": 0.17646263539791107, "learning_rate": 4.383341733873012e-05, "loss": 0.0116, "step": 56240 }, { "loss_action": 0.0077485498040914536, "loss_total": 0.0077485498040914536, "step": 56240 }, { "grad_norm": 0.2544735074043274, "learning_rate": 4.381700921204209e-05, "loss": 0.0112, "step": 56250 }, { "loss_action": 0.01038096658885479, "loss_total": 0.01038096658885479, "step": 56250 }, { "grad_norm": 0.23878240585327148, "learning_rate": 4.380060176151663e-05, "loss": 0.0088, "step": 56260 }, { "loss_action": 0.007153723388910294, "loss_total": 0.007153723388910294, "step": 56260 }, { "grad_norm": 0.2650582492351532, "learning_rate": 4.378419498894805e-05, "loss": 0.0096, "step": 56270 }, { "loss_action": 0.009012852795422077, "loss_total": 0.009012852795422077, "step": 56270 }, { "grad_norm": 0.2190617024898529, "learning_rate": 4.376778889613056e-05, "loss": 0.0092, "step": 56280 }, { "loss_action": 0.008875551633536816, "loss_total": 0.008875551633536816, "step": 56280 }, { "grad_norm": 0.17504651844501495, "learning_rate": 4.375138348485831e-05, "loss": 0.0088, "step": 56290 }, { "loss_action": 0.010226599872112274, "loss_total": 0.010226599872112274, "step": 56290 }, { "grad_norm": 0.20762307941913605, "learning_rate": 4.3734978756925346e-05, "loss": 0.0091, "step": 56300 }, { "loss_action": 0.008725171908736229, "loss_total": 0.008725171908736229, "step": 56300 }, { "grad_norm": 0.1911507546901703, "learning_rate": 4.3718574714125706e-05, "loss": 0.0088, "step": 56310 }, { "loss_action": 0.0071433912962675095, "loss_total": 0.0071433912962675095, "step": 56310 }, { "grad_norm": 0.20444871485233307, "learning_rate": 4.370217135825329e-05, "loss": 0.0079, "step": 56320 }, { "loss_action": 0.0077923196367919445, "loss_total": 0.0077923196367919445, "step": 56320 }, { "grad_norm": 0.331234872341156, "learning_rate": 4.368576869110194e-05, "loss": 0.0093, "step": 56330 }, { "loss_action": 0.00906325038522482, "loss_total": 0.00906325038522482, "step": 56330 }, { "grad_norm": 0.23785939812660217, "learning_rate": 4.366936671446544e-05, "loss": 0.0104, "step": 56340 }, { "loss_action": 0.006541994865983725, "loss_total": 0.006541994865983725, "step": 56340 }, { "grad_norm": 0.2528366446495056, "learning_rate": 4.3652965430137474e-05, "loss": 0.009, "step": 56350 }, { "loss_action": 0.013545332476496696, "loss_total": 0.013545332476496696, "step": 56350 }, { "grad_norm": 0.1634308099746704, "learning_rate": 4.3636564839911646e-05, "loss": 0.0092, "step": 56360 }, { "loss_action": 0.006697762757539749, "loss_total": 0.006697762757539749, "step": 56360 }, { "grad_norm": 0.2114821970462799, "learning_rate": 4.3620164945581545e-05, "loss": 0.0095, "step": 56370 }, { "loss_action": 0.01394597440958023, "loss_total": 0.01394597440958023, "step": 56370 }, { "grad_norm": 0.23989860713481903, "learning_rate": 4.360376574894061e-05, "loss": 0.0102, "step": 56380 }, { "loss_action": 0.007088911719620228, "loss_total": 0.007088911719620228, "step": 56380 }, { "grad_norm": 0.24748927354812622, "learning_rate": 4.358736725178224e-05, "loss": 0.0098, "step": 56390 }, { "loss_action": 0.007802353240549564, "loss_total": 0.007802353240549564, "step": 56390 }, { "grad_norm": 0.2200307995080948, "learning_rate": 4.357096945589974e-05, "loss": 0.0098, "step": 56400 }, { "loss_action": 0.007465319707989693, "loss_total": 0.007465319707989693, "step": 56400 }, { "grad_norm": 0.25695547461509705, "learning_rate": 4.355457236308636e-05, "loss": 0.009, "step": 56410 }, { "loss_action": 0.008415156044065952, "loss_total": 0.008415156044065952, "step": 56410 }, { "grad_norm": 0.5983982086181641, "learning_rate": 4.353817597513526e-05, "loss": 0.0106, "step": 56420 }, { "loss_action": 0.009076276794075966, "loss_total": 0.009076276794075966, "step": 56420 }, { "grad_norm": 0.31674739718437195, "learning_rate": 4.352178029383948e-05, "loss": 0.0116, "step": 56430 }, { "loss_action": 0.012403011322021484, "loss_total": 0.012403011322021484, "step": 56430 }, { "grad_norm": 0.22280342876911163, "learning_rate": 4.3505385320992105e-05, "loss": 0.0109, "step": 56440 }, { "loss_action": 0.010596264153718948, "loss_total": 0.010596264153718948, "step": 56440 }, { "grad_norm": 0.2691734731197357, "learning_rate": 4.348899105838602e-05, "loss": 0.01, "step": 56450 }, { "loss_action": 0.01292098592966795, "loss_total": 0.01292098592966795, "step": 56450 }, { "grad_norm": 0.2095598578453064, "learning_rate": 4.3472597507814087e-05, "loss": 0.0103, "step": 56460 }, { "loss_action": 0.010962842963635921, "loss_total": 0.010962842963635921, "step": 56460 }, { "grad_norm": 0.3513747453689575, "learning_rate": 4.3456204671069066e-05, "loss": 0.0104, "step": 56470 }, { "loss_action": 0.01947746053338051, "loss_total": 0.01947746053338051, "step": 56470 }, { "grad_norm": 0.20824845135211945, "learning_rate": 4.343981254994367e-05, "loss": 0.0109, "step": 56480 }, { "loss_action": 0.008035901933908463, "loss_total": 0.008035901933908463, "step": 56480 }, { "grad_norm": 0.28473207354545593, "learning_rate": 4.34234211462305e-05, "loss": 0.0098, "step": 56490 }, { "loss_action": 0.007903262041509151, "loss_total": 0.007903262041509151, "step": 56490 }, { "grad_norm": 0.22125190496444702, "learning_rate": 4.340703046172213e-05, "loss": 0.01, "step": 56500 }, { "loss_action": 0.008730526082217693, "loss_total": 0.008730526082217693, "step": 56500 }, { "grad_norm": 0.22030451893806458, "learning_rate": 4.339064049821097e-05, "loss": 0.0089, "step": 56510 }, { "loss_action": 0.009661036543548107, "loss_total": 0.009661036543548107, "step": 56510 }, { "grad_norm": 0.23345258831977844, "learning_rate": 4.3374251257489446e-05, "loss": 0.0095, "step": 56520 }, { "loss_action": 0.0062134298495948315, "loss_total": 0.0062134298495948315, "step": 56520 }, { "grad_norm": 0.3289684057235718, "learning_rate": 4.335786274134984e-05, "loss": 0.0109, "step": 56530 }, { "loss_action": 0.01041225902736187, "loss_total": 0.01041225902736187, "step": 56530 }, { "grad_norm": 0.24759025871753693, "learning_rate": 4.334147495158438e-05, "loss": 0.0098, "step": 56540 }, { "loss_action": 0.007906974293291569, "loss_total": 0.007906974293291569, "step": 56540 }, { "grad_norm": 0.1850128173828125, "learning_rate": 4.33250878899852e-05, "loss": 0.0082, "step": 56550 }, { "loss_action": 0.011533020064234734, "loss_total": 0.011533020064234734, "step": 56550 }, { "grad_norm": 0.18823421001434326, "learning_rate": 4.330870155834437e-05, "loss": 0.0093, "step": 56560 }, { "loss_action": 0.013116510584950447, "loss_total": 0.013116510584950447, "step": 56560 }, { "grad_norm": 0.184046670794487, "learning_rate": 4.3292315958453884e-05, "loss": 0.0107, "step": 56570 }, { "loss_action": 0.008584761992096901, "loss_total": 0.008584761992096901, "step": 56570 }, { "grad_norm": 0.2568866014480591, "learning_rate": 4.3275931092105646e-05, "loss": 0.0094, "step": 56580 }, { "loss_action": 0.007218397222459316, "loss_total": 0.007218397222459316, "step": 56580 }, { "grad_norm": 0.29678577184677124, "learning_rate": 4.325954696109147e-05, "loss": 0.0087, "step": 56590 }, { "loss_action": 0.008969396352767944, "loss_total": 0.008969396352767944, "step": 56590 }, { "grad_norm": 0.27305135130882263, "learning_rate": 4.32431635672031e-05, "loss": 0.0097, "step": 56600 }, { "loss_action": 0.015458855777978897, "loss_total": 0.015458855777978897, "step": 56600 }, { "grad_norm": 0.2298537790775299, "learning_rate": 4.3226780912232214e-05, "loss": 0.0096, "step": 56610 }, { "loss_action": 0.016527902334928513, "loss_total": 0.016527902334928513, "step": 56610 }, { "grad_norm": 0.2010461688041687, "learning_rate": 4.321039899797036e-05, "loss": 0.0099, "step": 56620 }, { "loss_action": 0.00831836648285389, "loss_total": 0.00831836648285389, "step": 56620 }, { "grad_norm": 0.2082078605890274, "learning_rate": 4.319401782620908e-05, "loss": 0.0094, "step": 56630 }, { "loss_action": 0.007291258312761784, "loss_total": 0.007291258312761784, "step": 56630 }, { "grad_norm": 0.19230926036834717, "learning_rate": 4.317763739873978e-05, "loss": 0.0094, "step": 56640 }, { "loss_action": 0.010408163070678711, "loss_total": 0.010408163070678711, "step": 56640 }, { "grad_norm": 0.19557784497737885, "learning_rate": 4.31612577173538e-05, "loss": 0.0089, "step": 56650 }, { "loss_action": 0.008944403380155563, "loss_total": 0.008944403380155563, "step": 56650 }, { "grad_norm": 0.20807680487632751, "learning_rate": 4.314487878384239e-05, "loss": 0.0098, "step": 56660 }, { "loss_action": 0.008660413324832916, "loss_total": 0.008660413324832916, "step": 56660 }, { "grad_norm": 0.23876751959323883, "learning_rate": 4.3128500599996736e-05, "loss": 0.0085, "step": 56670 }, { "loss_action": 0.008898142725229263, "loss_total": 0.008898142725229263, "step": 56670 }, { "grad_norm": 0.1913256198167801, "learning_rate": 4.31121231676079e-05, "loss": 0.0089, "step": 56680 }, { "loss_action": 0.0060714720748364925, "loss_total": 0.0060714720748364925, "step": 56680 }, { "grad_norm": 0.20244382321834564, "learning_rate": 4.309574648846694e-05, "loss": 0.008, "step": 56690 }, { "loss_action": 0.009683013893663883, "loss_total": 0.009683013893663883, "step": 56690 }, { "grad_norm": 0.2200773060321808, "learning_rate": 4.3079370564364755e-05, "loss": 0.0094, "step": 56700 }, { "loss_action": 0.00666965264827013, "loss_total": 0.00666965264827013, "step": 56700 }, { "grad_norm": 0.2032116949558258, "learning_rate": 4.306299539709221e-05, "loss": 0.0097, "step": 56710 }, { "loss_action": 0.007668972015380859, "loss_total": 0.007668972015380859, "step": 56710 }, { "grad_norm": 0.2111019343137741, "learning_rate": 4.3046620988440046e-05, "loss": 0.0094, "step": 56720 }, { "loss_action": 0.008103685453534126, "loss_total": 0.008103685453534126, "step": 56720 }, { "grad_norm": 0.22373591363430023, "learning_rate": 4.303024734019897e-05, "loss": 0.0079, "step": 56730 }, { "loss_action": 0.009639178402721882, "loss_total": 0.009639178402721882, "step": 56730 }, { "grad_norm": 0.22383515536785126, "learning_rate": 4.3013874454159565e-05, "loss": 0.0095, "step": 56740 }, { "loss_action": 0.006008388940244913, "loss_total": 0.006008388940244913, "step": 56740 }, { "grad_norm": 0.2562576234340668, "learning_rate": 4.299750233211233e-05, "loss": 0.009, "step": 56750 }, { "loss_action": 0.008494196459650993, "loss_total": 0.008494196459650993, "step": 56750 }, { "grad_norm": 0.26141345500946045, "learning_rate": 4.2981130975847715e-05, "loss": 0.0092, "step": 56760 }, { "loss_action": 0.009304874576628208, "loss_total": 0.009304874576628208, "step": 56760 }, { "grad_norm": 0.29491621255874634, "learning_rate": 4.2964760387156076e-05, "loss": 0.0087, "step": 56770 }, { "loss_action": 0.007336366456001997, "loss_total": 0.007336366456001997, "step": 56770 }, { "grad_norm": 0.20621447265148163, "learning_rate": 4.294839056782767e-05, "loss": 0.009, "step": 56780 }, { "loss_action": 0.008716398850083351, "loss_total": 0.008716398850083351, "step": 56780 }, { "grad_norm": 0.1650260090827942, "learning_rate": 4.293202151965266e-05, "loss": 0.0083, "step": 56790 }, { "loss_action": 0.007523066364228725, "loss_total": 0.007523066364228725, "step": 56790 }, { "grad_norm": 0.26606544852256775, "learning_rate": 4.291565324442115e-05, "loss": 0.0087, "step": 56800 }, { "loss_action": 0.008684641681611538, "loss_total": 0.008684641681611538, "step": 56800 }, { "grad_norm": 0.21723826229572296, "learning_rate": 4.2899285743923135e-05, "loss": 0.0107, "step": 56810 }, { "loss_action": 0.007394011598080397, "loss_total": 0.007394011598080397, "step": 56810 }, { "grad_norm": 0.2340305894613266, "learning_rate": 4.288291901994857e-05, "loss": 0.0088, "step": 56820 }, { "loss_action": 0.009189199656248093, "loss_total": 0.009189199656248093, "step": 56820 }, { "grad_norm": 0.22367647290229797, "learning_rate": 4.286655307428729e-05, "loss": 0.0086, "step": 56830 }, { "loss_action": 0.006718400865793228, "loss_total": 0.006718400865793228, "step": 56830 }, { "grad_norm": 0.2213277667760849, "learning_rate": 4.285018790872903e-05, "loss": 0.0097, "step": 56840 }, { "loss_action": 0.006364631466567516, "loss_total": 0.006364631466567516, "step": 56840 }, { "grad_norm": 0.2549411654472351, "learning_rate": 4.283382352506347e-05, "loss": 0.0088, "step": 56850 }, { "loss_action": 0.009034102782607079, "loss_total": 0.009034102782607079, "step": 56850 }, { "grad_norm": 0.20538799464702606, "learning_rate": 4.2817459925080205e-05, "loss": 0.0079, "step": 56860 }, { "loss_action": 0.008460241369903088, "loss_total": 0.008460241369903088, "step": 56860 }, { "grad_norm": 0.21925385296344757, "learning_rate": 4.28010971105687e-05, "loss": 0.008, "step": 56870 }, { "loss_action": 0.00733945332467556, "loss_total": 0.00733945332467556, "step": 56870 }, { "grad_norm": 0.1817118227481842, "learning_rate": 4.278473508331841e-05, "loss": 0.0089, "step": 56880 }, { "loss_action": 0.011159591376781464, "loss_total": 0.011159591376781464, "step": 56880 }, { "grad_norm": 0.1915329247713089, "learning_rate": 4.276837384511864e-05, "loss": 0.0093, "step": 56890 }, { "loss_action": 0.010775168426334858, "loss_total": 0.010775168426334858, "step": 56890 }, { "grad_norm": 0.18759126961231232, "learning_rate": 4.275201339775864e-05, "loss": 0.0088, "step": 56900 }, { "loss_action": 0.005451446399092674, "loss_total": 0.005451446399092674, "step": 56900 }, { "grad_norm": 0.2089952975511551, "learning_rate": 4.273565374302756e-05, "loss": 0.0084, "step": 56910 }, { "loss_action": 0.010947702452540398, "loss_total": 0.010947702452540398, "step": 56910 }, { "grad_norm": 0.18673451244831085, "learning_rate": 4.2719294882714454e-05, "loss": 0.01, "step": 56920 }, { "loss_action": 0.006529142614454031, "loss_total": 0.006529142614454031, "step": 56920 }, { "grad_norm": 0.2871127724647522, "learning_rate": 4.270293681860831e-05, "loss": 0.0085, "step": 56930 }, { "loss_action": 0.006807425525039434, "loss_total": 0.006807425525039434, "step": 56930 }, { "grad_norm": 0.2570984661579132, "learning_rate": 4.268657955249802e-05, "loss": 0.0079, "step": 56940 }, { "loss_action": 0.007943139411509037, "loss_total": 0.007943139411509037, "step": 56940 }, { "grad_norm": 0.21343819797039032, "learning_rate": 4.267022308617241e-05, "loss": 0.009, "step": 56950 }, { "loss_action": 0.019871341064572334, "loss_total": 0.019871341064572334, "step": 56950 }, { "grad_norm": 0.23299415409564972, "learning_rate": 4.265386742142018e-05, "loss": 0.0108, "step": 56960 }, { "loss_action": 0.011084962636232376, "loss_total": 0.011084962636232376, "step": 56960 }, { "grad_norm": 0.22199171781539917, "learning_rate": 4.263751256002996e-05, "loss": 0.0099, "step": 56970 }, { "loss_action": 0.010989140719175339, "loss_total": 0.010989140719175339, "step": 56970 }, { "grad_norm": 0.2387440800666809, "learning_rate": 4.26211585037903e-05, "loss": 0.0096, "step": 56980 }, { "loss_action": 0.010509039275348186, "loss_total": 0.010509039275348186, "step": 56980 }, { "grad_norm": 0.26946601271629333, "learning_rate": 4.2604805254489656e-05, "loss": 0.0097, "step": 56990 }, { "loss_action": 0.007766022812575102, "loss_total": 0.007766022812575102, "step": 56990 }, { "grad_norm": 0.29701393842697144, "learning_rate": 4.258845281391638e-05, "loss": 0.0077, "step": 57000 }, { "loss_action": 0.007377946749329567, "loss_total": 0.007377946749329567, "step": 57000 }, { "grad_norm": 0.20966419577598572, "learning_rate": 4.257210118385876e-05, "loss": 0.008, "step": 57010 }, { "loss_action": 0.006721509620547295, "loss_total": 0.006721509620547295, "step": 57010 }, { "grad_norm": 0.22418539226055145, "learning_rate": 4.2555750366104994e-05, "loss": 0.0086, "step": 57020 }, { "loss_action": 0.009700681082904339, "loss_total": 0.009700681082904339, "step": 57020 }, { "grad_norm": 0.25906801223754883, "learning_rate": 4.2539400362443184e-05, "loss": 0.0101, "step": 57030 }, { "loss_action": 0.00884238537400961, "loss_total": 0.00884238537400961, "step": 57030 }, { "grad_norm": 0.2791379988193512, "learning_rate": 4.252305117466133e-05, "loss": 0.0097, "step": 57040 }, { "loss_action": 0.008184069767594337, "loss_total": 0.008184069767594337, "step": 57040 }, { "grad_norm": 0.34107542037963867, "learning_rate": 4.2506702804547356e-05, "loss": 0.0098, "step": 57050 }, { "loss_action": 0.010222150944173336, "loss_total": 0.010222150944173336, "step": 57050 }, { "grad_norm": 0.2606103718280792, "learning_rate": 4.249035525388907e-05, "loss": 0.0088, "step": 57060 }, { "loss_action": 0.010968857444822788, "loss_total": 0.010968857444822788, "step": 57060 }, { "grad_norm": 0.23531746864318848, "learning_rate": 4.247400852447427e-05, "loss": 0.0097, "step": 57070 }, { "loss_action": 0.005922705866396427, "loss_total": 0.005922705866396427, "step": 57070 }, { "grad_norm": 0.2573351562023163, "learning_rate": 4.245766261809059e-05, "loss": 0.0089, "step": 57080 }, { "loss_action": 0.011777378618717194, "loss_total": 0.011777378618717194, "step": 57080 }, { "grad_norm": 0.21350698173046112, "learning_rate": 4.244131753652558e-05, "loss": 0.0094, "step": 57090 }, { "loss_action": 0.008774270303547382, "loss_total": 0.008774270303547382, "step": 57090 }, { "grad_norm": 0.2365843951702118, "learning_rate": 4.242497328156672e-05, "loss": 0.0081, "step": 57100 }, { "loss_action": 0.007720563095062971, "loss_total": 0.007720563095062971, "step": 57100 }, { "grad_norm": 0.1810975968837738, "learning_rate": 4.240862985500139e-05, "loss": 0.009, "step": 57110 }, { "loss_action": 0.008400766178965569, "loss_total": 0.008400766178965569, "step": 57110 }, { "grad_norm": 0.20368005335330963, "learning_rate": 4.2392287258616894e-05, "loss": 0.0096, "step": 57120 }, { "loss_action": 0.01418787706643343, "loss_total": 0.01418787706643343, "step": 57120 }, { "grad_norm": 0.2563041150569916, "learning_rate": 4.2375945494200396e-05, "loss": 0.0086, "step": 57130 }, { "loss_action": 0.00656772218644619, "loss_total": 0.00656772218644619, "step": 57130 }, { "grad_norm": 0.25943079590797424, "learning_rate": 4.2359604563539054e-05, "loss": 0.0089, "step": 57140 }, { "loss_action": 0.011053593829274178, "loss_total": 0.011053593829274178, "step": 57140 }, { "grad_norm": 0.21084991097450256, "learning_rate": 4.2343264468419885e-05, "loss": 0.0079, "step": 57150 }, { "loss_action": 0.0076287793926894665, "loss_total": 0.0076287793926894665, "step": 57150 }, { "grad_norm": 0.2866767644882202, "learning_rate": 4.232692521062979e-05, "loss": 0.0084, "step": 57160 }, { "loss_action": 0.009416292421519756, "loss_total": 0.009416292421519756, "step": 57160 }, { "grad_norm": 0.22577986121177673, "learning_rate": 4.231058679195562e-05, "loss": 0.0101, "step": 57170 }, { "loss_action": 0.010135442949831486, "loss_total": 0.010135442949831486, "step": 57170 }, { "grad_norm": 0.2600451111793518, "learning_rate": 4.229424921418411e-05, "loss": 0.0087, "step": 57180 }, { "loss_action": 0.009343872778117657, "loss_total": 0.009343872778117657, "step": 57180 }, { "grad_norm": 0.2312646061182022, "learning_rate": 4.2277912479101916e-05, "loss": 0.0103, "step": 57190 }, { "loss_action": 0.0083486782386899, "loss_total": 0.0083486782386899, "step": 57190 }, { "grad_norm": 0.21809537708759308, "learning_rate": 4.226157658849562e-05, "loss": 0.01, "step": 57200 }, { "loss_action": 0.008417445234954357, "loss_total": 0.008417445234954357, "step": 57200 }, { "grad_norm": 0.21257513761520386, "learning_rate": 4.2245241544151664e-05, "loss": 0.0103, "step": 57210 }, { "loss_action": 0.00932664331048727, "loss_total": 0.00932664331048727, "step": 57210 }, { "grad_norm": 0.2482565939426422, "learning_rate": 4.2228907347856425e-05, "loss": 0.0093, "step": 57220 }, { "loss_action": 0.010680408217012882, "loss_total": 0.010680408217012882, "step": 57220 }, { "grad_norm": 0.22043094038963318, "learning_rate": 4.2212574001396214e-05, "loss": 0.009, "step": 57230 }, { "loss_action": 0.005778428632766008, "loss_total": 0.005778428632766008, "step": 57230 }, { "grad_norm": 0.23112338781356812, "learning_rate": 4.21962415065572e-05, "loss": 0.0088, "step": 57240 }, { "loss_action": 0.008532521314918995, "loss_total": 0.008532521314918995, "step": 57240 }, { "grad_norm": 0.22052009403705597, "learning_rate": 4.217990986512548e-05, "loss": 0.0096, "step": 57250 }, { "loss_action": 0.005889562424272299, "loss_total": 0.005889562424272299, "step": 57250 }, { "grad_norm": 0.212660551071167, "learning_rate": 4.216357907888704e-05, "loss": 0.0089, "step": 57260 }, { "loss_action": 0.010600067675113678, "loss_total": 0.010600067675113678, "step": 57260 }, { "grad_norm": 0.31693235039711, "learning_rate": 4.2147249149627824e-05, "loss": 0.009, "step": 57270 }, { "loss_action": 0.006296947598457336, "loss_total": 0.006296947598457336, "step": 57270 }, { "grad_norm": 0.23633511364459991, "learning_rate": 4.213092007913364e-05, "loss": 0.0085, "step": 57280 }, { "loss_action": 0.00731942942366004, "loss_total": 0.00731942942366004, "step": 57280 }, { "grad_norm": 0.2627330422401428, "learning_rate": 4.2114591869190205e-05, "loss": 0.01, "step": 57290 }, { "loss_action": 0.010589207522571087, "loss_total": 0.010589207522571087, "step": 57290 }, { "grad_norm": 0.25190138816833496, "learning_rate": 4.209826452158315e-05, "loss": 0.0091, "step": 57300 }, { "loss_action": 0.007781037129461765, "loss_total": 0.007781037129461765, "step": 57300 }, { "grad_norm": 0.2342197448015213, "learning_rate": 4.2081938038098e-05, "loss": 0.0079, "step": 57310 }, { "loss_action": 0.013791642151772976, "loss_total": 0.013791642151772976, "step": 57310 }, { "grad_norm": 0.27065831422805786, "learning_rate": 4.2065612420520185e-05, "loss": 0.0096, "step": 57320 }, { "loss_action": 0.010469445027410984, "loss_total": 0.010469445027410984, "step": 57320 }, { "grad_norm": 0.2754228413105011, "learning_rate": 4.204928767063509e-05, "loss": 0.0096, "step": 57330 }, { "loss_action": 0.007072030566632748, "loss_total": 0.007072030566632748, "step": 57330 }, { "grad_norm": 0.23675718903541565, "learning_rate": 4.2032963790227944e-05, "loss": 0.0098, "step": 57340 }, { "loss_action": 0.007981638424098492, "loss_total": 0.007981638424098492, "step": 57340 }, { "grad_norm": 0.22422637045383453, "learning_rate": 4.2016640781083887e-05, "loss": 0.0091, "step": 57350 }, { "loss_action": 0.009874159470200539, "loss_total": 0.009874159470200539, "step": 57350 }, { "grad_norm": 0.19914408028125763, "learning_rate": 4.2000318644988004e-05, "loss": 0.0084, "step": 57360 }, { "loss_action": 0.008028151467442513, "loss_total": 0.008028151467442513, "step": 57360 }, { "grad_norm": 0.2211351841688156, "learning_rate": 4.198399738372524e-05, "loss": 0.0083, "step": 57370 }, { "loss_action": 0.00901135616004467, "loss_total": 0.00901135616004467, "step": 57370 }, { "grad_norm": 0.26736146211624146, "learning_rate": 4.196767699908045e-05, "loss": 0.0093, "step": 57380 }, { "loss_action": 0.010238973423838615, "loss_total": 0.010238973423838615, "step": 57380 }, { "grad_norm": 0.26837867498397827, "learning_rate": 4.195135749283845e-05, "loss": 0.0102, "step": 57390 }, { "loss_action": 0.007063073106110096, "loss_total": 0.007063073106110096, "step": 57390 }, { "grad_norm": 0.17686480283737183, "learning_rate": 4.1935038866783894e-05, "loss": 0.0087, "step": 57400 }, { "loss_action": 0.007462405599653721, "loss_total": 0.007462405599653721, "step": 57400 }, { "grad_norm": 0.25147512555122375, "learning_rate": 4.1918721122701355e-05, "loss": 0.0095, "step": 57410 }, { "loss_action": 0.008338267914950848, "loss_total": 0.008338267914950848, "step": 57410 }, { "grad_norm": 0.22680313885211945, "learning_rate": 4.190240426237533e-05, "loss": 0.0095, "step": 57420 }, { "loss_action": 0.00784362480044365, "loss_total": 0.00784362480044365, "step": 57420 }, { "grad_norm": 0.20718418061733246, "learning_rate": 4.188608828759019e-05, "loss": 0.0092, "step": 57430 }, { "loss_action": 0.01596524938941002, "loss_total": 0.01596524938941002, "step": 57430 }, { "grad_norm": 0.2084764689207077, "learning_rate": 4.1869773200130246e-05, "loss": 0.009, "step": 57440 }, { "loss_action": 0.007952435873448849, "loss_total": 0.007952435873448849, "step": 57440 }, { "grad_norm": 0.2616441547870636, "learning_rate": 4.185345900177967e-05, "loss": 0.0096, "step": 57450 }, { "loss_action": 0.007314188405871391, "loss_total": 0.007314188405871391, "step": 57450 }, { "grad_norm": 0.24546228349208832, "learning_rate": 4.183714569432258e-05, "loss": 0.0092, "step": 57460 }, { "loss_action": 0.012207640334963799, "loss_total": 0.012207640334963799, "step": 57460 }, { "grad_norm": 0.21901489794254303, "learning_rate": 4.182083327954295e-05, "loss": 0.0101, "step": 57470 }, { "loss_action": 0.011585921980440617, "loss_total": 0.011585921980440617, "step": 57470 }, { "grad_norm": 0.17567260563373566, "learning_rate": 4.1804521759224714e-05, "loss": 0.0081, "step": 57480 }, { "loss_action": 0.00849766656756401, "loss_total": 0.00849766656756401, "step": 57480 }, { "grad_norm": 0.29017525911331177, "learning_rate": 4.178821113515165e-05, "loss": 0.0085, "step": 57490 }, { "loss_action": 0.011345888487994671, "loss_total": 0.011345888487994671, "step": 57490 }, { "grad_norm": 0.24379058182239532, "learning_rate": 4.1771901409107476e-05, "loss": 0.0088, "step": 57500 }, { "loss_action": 0.007081989664584398, "loss_total": 0.007081989664584398, "step": 57500 }, { "grad_norm": 0.24497786164283752, "learning_rate": 4.175559258287577e-05, "loss": 0.0079, "step": 57510 }, { "loss_action": 0.008216994814574718, "loss_total": 0.008216994814574718, "step": 57510 }, { "grad_norm": 0.2491595596075058, "learning_rate": 4.173928465824008e-05, "loss": 0.009, "step": 57520 }, { "loss_action": 0.006598153151571751, "loss_total": 0.006598153151571751, "step": 57520 }, { "grad_norm": 0.19072358310222626, "learning_rate": 4.17229776369838e-05, "loss": 0.009, "step": 57530 }, { "loss_action": 0.008515564724802971, "loss_total": 0.008515564724802971, "step": 57530 }, { "grad_norm": 0.2063596099615097, "learning_rate": 4.170667152089025e-05, "loss": 0.0086, "step": 57540 }, { "loss_action": 0.008047816343605518, "loss_total": 0.008047816343605518, "step": 57540 }, { "grad_norm": 0.20758894085884094, "learning_rate": 4.1690366311742626e-05, "loss": 0.0107, "step": 57550 }, { "loss_action": 0.011990200728178024, "loss_total": 0.011990200728178024, "step": 57550 }, { "grad_norm": 0.2811551094055176, "learning_rate": 4.1674062011324055e-05, "loss": 0.0088, "step": 57560 }, { "loss_action": 0.006191676016896963, "loss_total": 0.006191676016896963, "step": 57560 }, { "grad_norm": 0.2850951552391052, "learning_rate": 4.165775862141752e-05, "loss": 0.0083, "step": 57570 }, { "loss_action": 0.008254243060946465, "loss_total": 0.008254243060946465, "step": 57570 }, { "grad_norm": 0.18959090113639832, "learning_rate": 4.164145614380598e-05, "loss": 0.0078, "step": 57580 }, { "loss_action": 0.008459705859422684, "loss_total": 0.008459705859422684, "step": 57580 }, { "grad_norm": 0.19956998527050018, "learning_rate": 4.162515458027223e-05, "loss": 0.0093, "step": 57590 }, { "loss_action": 0.011942075565457344, "loss_total": 0.011942075565457344, "step": 57590 }, { "grad_norm": 0.1990954577922821, "learning_rate": 4.160885393259899e-05, "loss": 0.0089, "step": 57600 }, { "loss_action": 0.006321406923234463, "loss_total": 0.006321406923234463, "step": 57600 }, { "grad_norm": 0.21907073259353638, "learning_rate": 4.159255420256886e-05, "loss": 0.0086, "step": 57610 }, { "loss_action": 0.007630256004631519, "loss_total": 0.007630256004631519, "step": 57610 }, { "grad_norm": 0.19256830215454102, "learning_rate": 4.157625539196436e-05, "loss": 0.008, "step": 57620 }, { "loss_action": 0.008159689605236053, "loss_total": 0.008159689605236053, "step": 57620 }, { "grad_norm": 0.22001367807388306, "learning_rate": 4.155995750256791e-05, "loss": 0.009, "step": 57630 }, { "loss_action": 0.009174616076052189, "loss_total": 0.009174616076052189, "step": 57630 }, { "grad_norm": 0.21655762195587158, "learning_rate": 4.15436605361618e-05, "loss": 0.009, "step": 57640 }, { "loss_action": 0.007411072496324778, "loss_total": 0.007411072496324778, "step": 57640 }, { "grad_norm": 0.23588354885578156, "learning_rate": 4.152736449452827e-05, "loss": 0.009, "step": 57650 }, { "loss_action": 0.0059677003882825375, "loss_total": 0.0059677003882825375, "step": 57650 }, { "grad_norm": 0.23591725528240204, "learning_rate": 4.151106937944943e-05, "loss": 0.0077, "step": 57660 }, { "loss_action": 0.010113485157489777, "loss_total": 0.010113485157489777, "step": 57660 }, { "grad_norm": 0.1940242201089859, "learning_rate": 4.149477519270727e-05, "loss": 0.0094, "step": 57670 }, { "loss_action": 0.012802733108401299, "loss_total": 0.012802733108401299, "step": 57670 }, { "grad_norm": 0.19050876796245575, "learning_rate": 4.147848193608371e-05, "loss": 0.0097, "step": 57680 }, { "loss_action": 0.012445143423974514, "loss_total": 0.012445143423974514, "step": 57680 }, { "grad_norm": 0.1966051161289215, "learning_rate": 4.146218961136056e-05, "loss": 0.0094, "step": 57690 }, { "loss_action": 0.008307753130793571, "loss_total": 0.008307753130793571, "step": 57690 }, { "grad_norm": 0.2402517944574356, "learning_rate": 4.14458982203195e-05, "loss": 0.0098, "step": 57700 }, { "loss_action": 0.011703838594257832, "loss_total": 0.011703838594257832, "step": 57700 }, { "grad_norm": 0.3270595371723175, "learning_rate": 4.1429607764742165e-05, "loss": 0.0101, "step": 57710 }, { "loss_action": 0.00876353308558464, "loss_total": 0.00876353308558464, "step": 57710 }, { "grad_norm": 0.294863760471344, "learning_rate": 4.141331824641003e-05, "loss": 0.01, "step": 57720 }, { "loss_action": 0.012330083176493645, "loss_total": 0.012330083176493645, "step": 57720 }, { "grad_norm": 0.22630435228347778, "learning_rate": 4.139702966710452e-05, "loss": 0.0098, "step": 57730 }, { "loss_action": 0.00904788263142109, "loss_total": 0.00904788263142109, "step": 57730 }, { "grad_norm": 0.22688747942447662, "learning_rate": 4.13807420286069e-05, "loss": 0.0094, "step": 57740 }, { "loss_action": 0.012696610763669014, "loss_total": 0.012696610763669014, "step": 57740 }, { "grad_norm": 0.260189026594162, "learning_rate": 4.136445533269837e-05, "loss": 0.0093, "step": 57750 }, { "loss_action": 0.008721658028662205, "loss_total": 0.008721658028662205, "step": 57750 }, { "grad_norm": 0.24852152168750763, "learning_rate": 4.134816958116003e-05, "loss": 0.0103, "step": 57760 }, { "loss_action": 0.008308266289532185, "loss_total": 0.008308266289532185, "step": 57760 }, { "grad_norm": 0.2554803192615509, "learning_rate": 4.133188477577283e-05, "loss": 0.009, "step": 57770 }, { "loss_action": 0.008567231707274914, "loss_total": 0.008567231707274914, "step": 57770 }, { "grad_norm": 0.22289566695690155, "learning_rate": 4.131560091831771e-05, "loss": 0.009, "step": 57780 }, { "loss_action": 0.009387565776705742, "loss_total": 0.009387565776705742, "step": 57780 }, { "grad_norm": 0.22555477917194366, "learning_rate": 4.1299318010575405e-05, "loss": 0.0103, "step": 57790 }, { "loss_action": 0.009241262450814247, "loss_total": 0.009241262450814247, "step": 57790 }, { "grad_norm": 0.3140776753425598, "learning_rate": 4.128303605432661e-05, "loss": 0.0101, "step": 57800 }, { "loss_action": 0.007682130206376314, "loss_total": 0.007682130206376314, "step": 57800 }, { "grad_norm": 0.36322730779647827, "learning_rate": 4.126675505135188e-05, "loss": 0.0099, "step": 57810 }, { "loss_action": 0.00954251829534769, "loss_total": 0.00954251829534769, "step": 57810 }, { "grad_norm": 0.266817569732666, "learning_rate": 4.125047500343169e-05, "loss": 0.0095, "step": 57820 }, { "loss_action": 0.009614987298846245, "loss_total": 0.009614987298846245, "step": 57820 }, { "grad_norm": 0.16453805565834045, "learning_rate": 4.1234195912346376e-05, "loss": 0.0097, "step": 57830 }, { "loss_action": 0.007134394720196724, "loss_total": 0.007134394720196724, "step": 57830 }, { "grad_norm": 0.21558338403701782, "learning_rate": 4.1217917779876235e-05, "loss": 0.0094, "step": 57840 }, { "loss_action": 0.007828334346413612, "loss_total": 0.007828334346413612, "step": 57840 }, { "grad_norm": 0.2413318157196045, "learning_rate": 4.120164060780141e-05, "loss": 0.0084, "step": 57850 }, { "loss_action": 0.007856921292841434, "loss_total": 0.007856921292841434, "step": 57850 }, { "grad_norm": 0.24502183496952057, "learning_rate": 4.1185364397901935e-05, "loss": 0.0081, "step": 57860 }, { "loss_action": 0.007478924933820963, "loss_total": 0.007478924933820963, "step": 57860 }, { "grad_norm": 0.2480054646730423, "learning_rate": 4.116908915195776e-05, "loss": 0.0081, "step": 57870 }, { "loss_action": 0.006893312558531761, "loss_total": 0.006893312558531761, "step": 57870 }, { "grad_norm": 0.24594919383525848, "learning_rate": 4.115281487174872e-05, "loss": 0.0099, "step": 57880 }, { "loss_action": 0.005984913557767868, "loss_total": 0.005984913557767868, "step": 57880 }, { "grad_norm": 0.22694726288318634, "learning_rate": 4.113654155905452e-05, "loss": 0.0092, "step": 57890 }, { "loss_action": 0.009149100631475449, "loss_total": 0.009149100631475449, "step": 57890 }, { "grad_norm": 0.3017907738685608, "learning_rate": 4.112026921565483e-05, "loss": 0.0104, "step": 57900 }, { "loss_action": 0.009615863673388958, "loss_total": 0.009615863673388958, "step": 57900 }, { "grad_norm": 0.24840182065963745, "learning_rate": 4.1103997843329147e-05, "loss": 0.0099, "step": 57910 }, { "loss_action": 0.006569298449903727, "loss_total": 0.006569298449903727, "step": 57910 }, { "grad_norm": 0.21446311473846436, "learning_rate": 4.108772744385689e-05, "loss": 0.009, "step": 57920 }, { "loss_action": 0.0077907186932861805, "loss_total": 0.0077907186932861805, "step": 57920 }, { "grad_norm": 0.23624178767204285, "learning_rate": 4.1071458019017346e-05, "loss": 0.009, "step": 57930 }, { "loss_action": 0.011663522571325302, "loss_total": 0.011663522571325302, "step": 57930 }, { "grad_norm": 0.24731893837451935, "learning_rate": 4.1055189570589734e-05, "loss": 0.0104, "step": 57940 }, { "loss_action": 0.012366586364805698, "loss_total": 0.012366586364805698, "step": 57940 }, { "grad_norm": 0.23705467581748962, "learning_rate": 4.103892210035315e-05, "loss": 0.0091, "step": 57950 }, { "loss_action": 0.009621710516512394, "loss_total": 0.009621710516512394, "step": 57950 }, { "grad_norm": 0.24130383133888245, "learning_rate": 4.102265561008656e-05, "loss": 0.0088, "step": 57960 }, { "loss_action": 0.004915183410048485, "loss_total": 0.004915183410048485, "step": 57960 }, { "grad_norm": 0.21478389203548431, "learning_rate": 4.100639010156885e-05, "loss": 0.0079, "step": 57970 }, { "loss_action": 0.00846326444298029, "loss_total": 0.00846326444298029, "step": 57970 }, { "grad_norm": 0.1868433952331543, "learning_rate": 4.099012557657882e-05, "loss": 0.0088, "step": 57980 }, { "loss_action": 0.008306952193379402, "loss_total": 0.008306952193379402, "step": 57980 }, { "grad_norm": 0.20119382441043854, "learning_rate": 4.09738620368951e-05, "loss": 0.0084, "step": 57990 }, { "loss_action": 0.009114901535212994, "loss_total": 0.009114901535212994, "step": 57990 }, { "grad_norm": 0.24876242876052856, "learning_rate": 4.095759948429626e-05, "loss": 0.0084, "step": 58000 }, { "loss_action": 0.011127566918730736, "loss_total": 0.011127566918730736, "step": 58000 }, { "grad_norm": 0.24204128980636597, "learning_rate": 4.094133792056075e-05, "loss": 0.0095, "step": 58010 }, { "loss_action": 0.011000823229551315, "loss_total": 0.011000823229551315, "step": 58010 }, { "grad_norm": 0.3208925127983093, "learning_rate": 4.092507734746688e-05, "loss": 0.0092, "step": 58020 }, { "loss_action": 0.007177642080932856, "loss_total": 0.007177642080932856, "step": 58020 }, { "grad_norm": 0.25876370072364807, "learning_rate": 4.090881776679293e-05, "loss": 0.0082, "step": 58030 }, { "loss_action": 0.007921983487904072, "loss_total": 0.007921983487904072, "step": 58030 }, { "grad_norm": 0.34229785203933716, "learning_rate": 4.0892559180316994e-05, "loss": 0.0104, "step": 58040 }, { "loss_action": 0.005897185765206814, "loss_total": 0.005897185765206814, "step": 58040 }, { "grad_norm": 0.21476557850837708, "learning_rate": 4.08763015898171e-05, "loss": 0.008, "step": 58050 }, { "loss_action": 0.0075543965213000774, "loss_total": 0.0075543965213000774, "step": 58050 }, { "grad_norm": 0.21742720901966095, "learning_rate": 4.0860044997071145e-05, "loss": 0.0092, "step": 58060 }, { "loss_action": 0.006663215812295675, "loss_total": 0.006663215812295675, "step": 58060 }, { "grad_norm": 0.2061353623867035, "learning_rate": 4.084378940385693e-05, "loss": 0.0081, "step": 58070 }, { "loss_action": 0.008352363482117653, "loss_total": 0.008352363482117653, "step": 58070 }, { "grad_norm": 0.24923934042453766, "learning_rate": 4.082753481195211e-05, "loss": 0.0083, "step": 58080 }, { "loss_action": 0.01383341196924448, "loss_total": 0.01383341196924448, "step": 58080 }, { "grad_norm": 0.2095993608236313, "learning_rate": 4.0811281223134324e-05, "loss": 0.0091, "step": 58090 }, { "loss_action": 0.009191639721393585, "loss_total": 0.009191639721393585, "step": 58090 }, { "grad_norm": 0.2734728753566742, "learning_rate": 4.0795028639181e-05, "loss": 0.0097, "step": 58100 }, { "loss_action": 0.00832863338291645, "loss_total": 0.00832863338291645, "step": 58100 }, { "grad_norm": 0.2592650353908539, "learning_rate": 4.077877706186951e-05, "loss": 0.0096, "step": 58110 }, { "loss_action": 0.01195484772324562, "loss_total": 0.01195484772324562, "step": 58110 }, { "grad_norm": 0.17725569009780884, "learning_rate": 4.076252649297709e-05, "loss": 0.0082, "step": 58120 }, { "loss_action": 0.006972066592425108, "loss_total": 0.006972066592425108, "step": 58120 }, { "grad_norm": 0.1756335198879242, "learning_rate": 4.07462769342809e-05, "loss": 0.0078, "step": 58130 }, { "loss_action": 0.006802293937653303, "loss_total": 0.006802293937653303, "step": 58130 }, { "grad_norm": 0.1811303347349167, "learning_rate": 4.073002838755793e-05, "loss": 0.0088, "step": 58140 }, { "loss_action": 0.006640575360506773, "loss_total": 0.006640575360506773, "step": 58140 }, { "grad_norm": 0.28227323293685913, "learning_rate": 4.0713780854585115e-05, "loss": 0.0082, "step": 58150 }, { "loss_action": 0.008765662088990211, "loss_total": 0.008765662088990211, "step": 58150 }, { "grad_norm": 0.1839502453804016, "learning_rate": 4.069753433713927e-05, "loss": 0.0088, "step": 58160 }, { "loss_action": 0.007925532758235931, "loss_total": 0.007925532758235931, "step": 58160 }, { "grad_norm": 0.20549769699573517, "learning_rate": 4.068128883699709e-05, "loss": 0.0087, "step": 58170 }, { "loss_action": 0.008260051719844341, "loss_total": 0.008260051719844341, "step": 58170 }, { "grad_norm": 0.23395447432994843, "learning_rate": 4.0665044355935155e-05, "loss": 0.0082, "step": 58180 }, { "loss_action": 0.005605275277048349, "loss_total": 0.005605275277048349, "step": 58180 }, { "grad_norm": 0.22847795486450195, "learning_rate": 4.064880089572993e-05, "loss": 0.0081, "step": 58190 }, { "loss_action": 0.010374374687671661, "loss_total": 0.010374374687671661, "step": 58190 }, { "grad_norm": 0.1874750852584839, "learning_rate": 4.063255845815779e-05, "loss": 0.0077, "step": 58200 }, { "loss_action": 0.0056615062057971954, "loss_total": 0.0056615062057971954, "step": 58200 }, { "grad_norm": 0.17294920980930328, "learning_rate": 4.0616317044994945e-05, "loss": 0.0079, "step": 58210 }, { "loss_action": 0.00905151292681694, "loss_total": 0.00905151292681694, "step": 58210 }, { "grad_norm": 0.21573080122470856, "learning_rate": 4.0600076658017585e-05, "loss": 0.0078, "step": 58220 }, { "loss_action": 0.009057889692485332, "loss_total": 0.009057889692485332, "step": 58220 }, { "grad_norm": 0.2544836699962616, "learning_rate": 4.0583837299001706e-05, "loss": 0.0082, "step": 58230 }, { "loss_action": 0.01470712199807167, "loss_total": 0.01470712199807167, "step": 58230 }, { "grad_norm": 0.2775874733924866, "learning_rate": 4.056759896972322e-05, "loss": 0.0086, "step": 58240 }, { "loss_action": 0.007324497681111097, "loss_total": 0.007324497681111097, "step": 58240 }, { "grad_norm": 0.25746625661849976, "learning_rate": 4.055136167195793e-05, "loss": 0.0086, "step": 58250 }, { "loss_action": 0.007579934783279896, "loss_total": 0.007579934783279896, "step": 58250 }, { "grad_norm": 0.17259302735328674, "learning_rate": 4.053512540748152e-05, "loss": 0.008, "step": 58260 }, { "loss_action": 0.00974663533270359, "loss_total": 0.00974663533270359, "step": 58260 }, { "grad_norm": 0.19441601634025574, "learning_rate": 4.051889017806955e-05, "loss": 0.0087, "step": 58270 }, { "loss_action": 0.007580241654068232, "loss_total": 0.007580241654068232, "step": 58270 }, { "grad_norm": 0.16656194627285004, "learning_rate": 4.0502655985497516e-05, "loss": 0.0086, "step": 58280 }, { "loss_action": 0.010489839129149914, "loss_total": 0.010489839129149914, "step": 58280 }, { "grad_norm": 0.20091034471988678, "learning_rate": 4.048642283154074e-05, "loss": 0.0095, "step": 58290 }, { "loss_action": 0.012681527063250542, "loss_total": 0.012681527063250542, "step": 58290 }, { "grad_norm": 0.1851455420255661, "learning_rate": 4.0470190717974464e-05, "loss": 0.0084, "step": 58300 }, { "loss_action": 0.011048112995922565, "loss_total": 0.011048112995922565, "step": 58300 }, { "grad_norm": 0.16233932971954346, "learning_rate": 4.045395964657381e-05, "loss": 0.0079, "step": 58310 }, { "loss_action": 0.009072617627680302, "loss_total": 0.009072617627680302, "step": 58310 }, { "grad_norm": 0.16905011236667633, "learning_rate": 4.043772961911376e-05, "loss": 0.0074, "step": 58320 }, { "loss_action": 0.011591358110308647, "loss_total": 0.011591358110308647, "step": 58320 }, { "grad_norm": 0.22279831767082214, "learning_rate": 4.042150063736924e-05, "loss": 0.0083, "step": 58330 }, { "loss_action": 0.007318777032196522, "loss_total": 0.007318777032196522, "step": 58330 }, { "grad_norm": 0.2152455896139145, "learning_rate": 4.0405272703114976e-05, "loss": 0.0086, "step": 58340 }, { "loss_action": 0.00858538318425417, "loss_total": 0.00858538318425417, "step": 58340 }, { "grad_norm": 0.24827639758586884, "learning_rate": 4.038904581812569e-05, "loss": 0.0089, "step": 58350 }, { "loss_action": 0.007851880043745041, "loss_total": 0.007851880043745041, "step": 58350 }, { "grad_norm": 0.17090553045272827, "learning_rate": 4.03728199841759e-05, "loss": 0.007, "step": 58360 }, { "loss_action": 0.007960264571011066, "loss_total": 0.007960264571011066, "step": 58360 }, { "grad_norm": 0.18027576804161072, "learning_rate": 4.0356595203040044e-05, "loss": 0.0085, "step": 58370 }, { "loss_action": 0.006473573390394449, "loss_total": 0.006473573390394449, "step": 58370 }, { "grad_norm": 0.2097846120595932, "learning_rate": 4.0340371476492426e-05, "loss": 0.0078, "step": 58380 }, { "loss_action": 0.007501518353819847, "loss_total": 0.007501518353819847, "step": 58380 }, { "grad_norm": 0.22742018103599548, "learning_rate": 4.032414880630727e-05, "loss": 0.008, "step": 58390 }, { "loss_action": 0.006667909678071737, "loss_total": 0.006667909678071737, "step": 58390 }, { "grad_norm": 0.21468742191791534, "learning_rate": 4.0307927194258646e-05, "loss": 0.008, "step": 58400 }, { "loss_action": 0.008055605925619602, "loss_total": 0.008055605925619602, "step": 58400 }, { "grad_norm": 0.18156130611896515, "learning_rate": 4.029170664212054e-05, "loss": 0.0081, "step": 58410 }, { "loss_action": 0.006441344972699881, "loss_total": 0.006441344972699881, "step": 58410 }, { "grad_norm": 0.28282976150512695, "learning_rate": 4.0275487151666794e-05, "loss": 0.0079, "step": 58420 }, { "loss_action": 0.011068756692111492, "loss_total": 0.011068756692111492, "step": 58420 }, { "grad_norm": 0.2712092399597168, "learning_rate": 4.025926872467116e-05, "loss": 0.0075, "step": 58430 }, { "loss_action": 0.011752039194107056, "loss_total": 0.011752039194107056, "step": 58430 }, { "grad_norm": 0.20267122983932495, "learning_rate": 4.024305136290725e-05, "loss": 0.0085, "step": 58440 }, { "loss_action": 0.0055484464392066, "loss_total": 0.0055484464392066, "step": 58440 }, { "grad_norm": 0.18568743765354156, "learning_rate": 4.022683506814858e-05, "loss": 0.0083, "step": 58450 }, { "loss_action": 0.008734498172998428, "loss_total": 0.008734498172998428, "step": 58450 }, { "grad_norm": 0.27622169256210327, "learning_rate": 4.021061984216853e-05, "loss": 0.0083, "step": 58460 }, { "loss_action": 0.006362426094710827, "loss_total": 0.006362426094710827, "step": 58460 }, { "grad_norm": 0.24888376891613007, "learning_rate": 4.019440568674035e-05, "loss": 0.008, "step": 58470 }, { "loss_action": 0.008475331589579582, "loss_total": 0.008475331589579582, "step": 58470 }, { "grad_norm": 0.22906051576137543, "learning_rate": 4.017819260363724e-05, "loss": 0.0077, "step": 58480 }, { "loss_action": 0.007371545769274235, "loss_total": 0.007371545769274235, "step": 58480 }, { "grad_norm": 0.2196095585823059, "learning_rate": 4.016198059463223e-05, "loss": 0.0091, "step": 58490 }, { "loss_action": 0.00882148090749979, "loss_total": 0.00882148090749979, "step": 58490 }, { "grad_norm": 0.3116007149219513, "learning_rate": 4.0145769661498233e-05, "loss": 0.0108, "step": 58500 }, { "loss_action": 0.00657243374735117, "loss_total": 0.00657243374735117, "step": 58500 }, { "grad_norm": 0.15056566894054413, "learning_rate": 4.012955980600804e-05, "loss": 0.0105, "step": 58510 }, { "loss_action": 0.009772866033017635, "loss_total": 0.009772866033017635, "step": 58510 }, { "grad_norm": 0.24057678878307343, "learning_rate": 4.0113351029934355e-05, "loss": 0.0093, "step": 58520 }, { "loss_action": 0.010317034088075161, "loss_total": 0.010317034088075161, "step": 58520 }, { "grad_norm": 0.23277100920677185, "learning_rate": 4.0097143335049714e-05, "loss": 0.0089, "step": 58530 }, { "loss_action": 0.006704035680741072, "loss_total": 0.006704035680741072, "step": 58530 }, { "grad_norm": 0.304212749004364, "learning_rate": 4.0080936723126606e-05, "loss": 0.0084, "step": 58540 }, { "loss_action": 0.006422536447644234, "loss_total": 0.006422536447644234, "step": 58540 }, { "grad_norm": 0.232131689786911, "learning_rate": 4.006473119593735e-05, "loss": 0.0081, "step": 58550 }, { "loss_action": 0.006430161651223898, "loss_total": 0.006430161651223898, "step": 58550 }, { "grad_norm": 0.21888300776481628, "learning_rate": 4.004852675525415e-05, "loss": 0.0085, "step": 58560 }, { "loss_action": 0.008119666017591953, "loss_total": 0.008119666017591953, "step": 58560 }, { "grad_norm": 0.22300419211387634, "learning_rate": 4.00323234028491e-05, "loss": 0.0089, "step": 58570 }, { "loss_action": 0.007835444062948227, "loss_total": 0.007835444062948227, "step": 58570 }, { "grad_norm": 0.2455117255449295, "learning_rate": 4.0016121140494186e-05, "loss": 0.0088, "step": 58580 }, { "loss_action": 0.006444359198212624, "loss_total": 0.006444359198212624, "step": 58580 }, { "grad_norm": 0.23160794377326965, "learning_rate": 3.999991996996122e-05, "loss": 0.0089, "step": 58590 }, { "loss_action": 0.005797072779387236, "loss_total": 0.005797072779387236, "step": 58590 }, { "grad_norm": 0.21375423669815063, "learning_rate": 3.9983719893022e-05, "loss": 0.0084, "step": 58600 }, { "loss_action": 0.009706222452223301, "loss_total": 0.009706222452223301, "step": 58600 }, { "grad_norm": 0.20935538411140442, "learning_rate": 3.996752091144812e-05, "loss": 0.0081, "step": 58610 }, { "loss_action": 0.01015406847000122, "loss_total": 0.01015406847000122, "step": 58610 }, { "grad_norm": 0.22172977030277252, "learning_rate": 3.9951323027011055e-05, "loss": 0.0097, "step": 58620 }, { "loss_action": 0.009887099266052246, "loss_total": 0.009887099266052246, "step": 58620 }, { "grad_norm": 0.24258407950401306, "learning_rate": 3.993512624148219e-05, "loss": 0.0101, "step": 58630 }, { "loss_action": 0.008734147064387798, "loss_total": 0.008734147064387798, "step": 58630 }, { "grad_norm": 0.1997632384300232, "learning_rate": 3.99189305566328e-05, "loss": 0.0089, "step": 58640 }, { "loss_action": 0.008279718458652496, "loss_total": 0.008279718458652496, "step": 58640 }, { "grad_norm": 0.20771510899066925, "learning_rate": 3.990273597423401e-05, "loss": 0.0092, "step": 58650 }, { "loss_action": 0.008287438191473484, "loss_total": 0.008287438191473484, "step": 58650 }, { "grad_norm": 0.30978861451148987, "learning_rate": 3.988654249605681e-05, "loss": 0.0119, "step": 58660 }, { "loss_action": 0.008131830021739006, "loss_total": 0.008131830021739006, "step": 58660 }, { "grad_norm": 0.22099685668945312, "learning_rate": 3.987035012387213e-05, "loss": 0.0092, "step": 58670 }, { "loss_action": 0.006617624778300524, "loss_total": 0.006617624778300524, "step": 58670 }, { "grad_norm": 0.20491334795951843, "learning_rate": 3.9854158859450735e-05, "loss": 0.0079, "step": 58680 }, { "loss_action": 0.006265802308917046, "loss_total": 0.006265802308917046, "step": 58680 }, { "grad_norm": 0.2044655829668045, "learning_rate": 3.983796870456328e-05, "loss": 0.0094, "step": 58690 }, { "loss_action": 0.012069914489984512, "loss_total": 0.012069914489984512, "step": 58690 }, { "grad_norm": 0.20079302787780762, "learning_rate": 3.982177966098028e-05, "loss": 0.0086, "step": 58700 }, { "loss_action": 0.00784017238765955, "loss_total": 0.00784017238765955, "step": 58700 }, { "grad_norm": 0.22541844844818115, "learning_rate": 3.980559173047216e-05, "loss": 0.0085, "step": 58710 }, { "loss_action": 0.0105927474796772, "loss_total": 0.0105927474796772, "step": 58710 }, { "grad_norm": 0.26034098863601685, "learning_rate": 3.9789404914809176e-05, "loss": 0.0083, "step": 58720 }, { "loss_action": 0.009095742367208004, "loss_total": 0.009095742367208004, "step": 58720 }, { "grad_norm": 0.2100142240524292, "learning_rate": 3.9773219215761544e-05, "loss": 0.009, "step": 58730 }, { "loss_action": 0.008203632198274136, "loss_total": 0.008203632198274136, "step": 58730 }, { "grad_norm": 0.24599693715572357, "learning_rate": 3.975703463509928e-05, "loss": 0.0092, "step": 58740 }, { "loss_action": 0.00908919982612133, "loss_total": 0.00908919982612133, "step": 58740 }, { "grad_norm": 0.21141642332077026, "learning_rate": 3.974085117459231e-05, "loss": 0.008, "step": 58750 }, { "loss_action": 0.006993615999817848, "loss_total": 0.006993615999817848, "step": 58750 }, { "grad_norm": 0.2541426420211792, "learning_rate": 3.972466883601043e-05, "loss": 0.0089, "step": 58760 }, { "loss_action": 0.012477781623601913, "loss_total": 0.012477781623601913, "step": 58760 }, { "grad_norm": 0.2619107663631439, "learning_rate": 3.9708487621123316e-05, "loss": 0.0093, "step": 58770 }, { "loss_action": 0.008049171417951584, "loss_total": 0.008049171417951584, "step": 58770 }, { "grad_norm": 0.2117815613746643, "learning_rate": 3.969230753170051e-05, "loss": 0.0087, "step": 58780 }, { "loss_action": 0.0075568524189293385, "loss_total": 0.0075568524189293385, "step": 58780 }, { "grad_norm": 0.24338506162166595, "learning_rate": 3.967612856951146e-05, "loss": 0.009, "step": 58790 }, { "loss_action": 0.009881571866571903, "loss_total": 0.009881571866571903, "step": 58790 }, { "grad_norm": 0.2587372958660126, "learning_rate": 3.9659950736325476e-05, "loss": 0.0097, "step": 58800 }, { "loss_action": 0.006537195760756731, "loss_total": 0.006537195760756731, "step": 58800 }, { "grad_norm": 0.24170859158039093, "learning_rate": 3.964377403391174e-05, "loss": 0.0082, "step": 58810 }, { "loss_action": 0.009672742336988449, "loss_total": 0.009672742336988449, "step": 58810 }, { "grad_norm": 0.2230156809091568, "learning_rate": 3.9627598464039303e-05, "loss": 0.0086, "step": 58820 }, { "loss_action": 0.011334868147969246, "loss_total": 0.011334868147969246, "step": 58820 }, { "grad_norm": 0.1992396116256714, "learning_rate": 3.9611424028477096e-05, "loss": 0.0094, "step": 58830 }, { "loss_action": 0.00588970398530364, "loss_total": 0.00588970398530364, "step": 58830 }, { "grad_norm": 0.2602428197860718, "learning_rate": 3.959525072899394e-05, "loss": 0.0088, "step": 58840 }, { "loss_action": 0.012010701932013035, "loss_total": 0.012010701932013035, "step": 58840 }, { "grad_norm": 0.2706022560596466, "learning_rate": 3.9579078567358506e-05, "loss": 0.0097, "step": 58850 }, { "loss_action": 0.008731032721698284, "loss_total": 0.008731032721698284, "step": 58850 }, { "grad_norm": 0.23961898684501648, "learning_rate": 3.956290754533939e-05, "loss": 0.0086, "step": 58860 }, { "loss_action": 0.007468815892934799, "loss_total": 0.007468815892934799, "step": 58860 }, { "grad_norm": 0.20459438860416412, "learning_rate": 3.954673766470501e-05, "loss": 0.008, "step": 58870 }, { "loss_action": 0.007424579933285713, "loss_total": 0.007424579933285713, "step": 58870 }, { "grad_norm": 0.21287798881530762, "learning_rate": 3.9530568927223674e-05, "loss": 0.0088, "step": 58880 }, { "loss_action": 0.009030944667756557, "loss_total": 0.009030944667756557, "step": 58880 }, { "grad_norm": 0.23138266801834106, "learning_rate": 3.95144013346636e-05, "loss": 0.0086, "step": 58890 }, { "loss_action": 0.008220313116908073, "loss_total": 0.008220313116908073, "step": 58890 }, { "grad_norm": 0.2092139571905136, "learning_rate": 3.949823488879282e-05, "loss": 0.0085, "step": 58900 }, { "loss_action": 0.012831085361540318, "loss_total": 0.012831085361540318, "step": 58900 }, { "grad_norm": 0.17602205276489258, "learning_rate": 3.9482069591379276e-05, "loss": 0.0088, "step": 58910 }, { "loss_action": 0.008640686981379986, "loss_total": 0.008640686981379986, "step": 58910 }, { "grad_norm": 0.19484290480613708, "learning_rate": 3.9465905444190784e-05, "loss": 0.0083, "step": 58920 }, { "loss_action": 0.008697493001818657, "loss_total": 0.008697493001818657, "step": 58920 }, { "grad_norm": 0.19368933141231537, "learning_rate": 3.944974244899505e-05, "loss": 0.0089, "step": 58930 }, { "loss_action": 0.008334202691912651, "loss_total": 0.008334202691912651, "step": 58930 }, { "grad_norm": 0.2250341922044754, "learning_rate": 3.9433580607559616e-05, "loss": 0.0085, "step": 58940 }, { "loss_action": 0.010183715261518955, "loss_total": 0.010183715261518955, "step": 58940 }, { "grad_norm": 0.25098103284835815, "learning_rate": 3.941741992165193e-05, "loss": 0.0105, "step": 58950 }, { "loss_action": 0.006427225191146135, "loss_total": 0.006427225191146135, "step": 58950 }, { "grad_norm": 0.22910819947719574, "learning_rate": 3.940126039303928e-05, "loss": 0.0084, "step": 58960 }, { "loss_action": 0.007729651872068644, "loss_total": 0.007729651872068644, "step": 58960 }, { "grad_norm": 0.228936105966568, "learning_rate": 3.938510202348886e-05, "loss": 0.0083, "step": 58970 }, { "loss_action": 0.010825620032846928, "loss_total": 0.010825620032846928, "step": 58970 }, { "grad_norm": 0.19385254383087158, "learning_rate": 3.93689448147677e-05, "loss": 0.009, "step": 58980 }, { "loss_action": 0.007719519082456827, "loss_total": 0.007719519082456827, "step": 58980 }, { "grad_norm": 0.24537459015846252, "learning_rate": 3.935278876864278e-05, "loss": 0.0083, "step": 58990 }, { "loss_action": 0.008102219551801682, "loss_total": 0.008102219551801682, "step": 58990 }, { "grad_norm": 0.21106429398059845, "learning_rate": 3.933663388688087e-05, "loss": 0.0099, "step": 59000 }, { "loss_action": 0.008006548509001732, "loss_total": 0.008006548509001732, "step": 59000 }, { "grad_norm": 0.19969075918197632, "learning_rate": 3.9320480171248645e-05, "loss": 0.0082, "step": 59010 }, { "loss_action": 0.005364153068512678, "loss_total": 0.005364153068512678, "step": 59010 }, { "grad_norm": 0.23106172680854797, "learning_rate": 3.930432762351265e-05, "loss": 0.0085, "step": 59020 }, { "loss_action": 0.00922092143446207, "loss_total": 0.00922092143446207, "step": 59020 }, { "grad_norm": 0.2007460594177246, "learning_rate": 3.928817624543931e-05, "loss": 0.0084, "step": 59030 }, { "loss_action": 0.00906165037304163, "loss_total": 0.00906165037304163, "step": 59030 }, { "grad_norm": 0.21383242309093475, "learning_rate": 3.9272026038794885e-05, "loss": 0.008, "step": 59040 }, { "loss_action": 0.006560241803526878, "loss_total": 0.006560241803526878, "step": 59040 }, { "grad_norm": 0.1413710117340088, "learning_rate": 3.9255877005345586e-05, "loss": 0.0077, "step": 59050 }, { "loss_action": 0.011536487378180027, "loss_total": 0.011536487378180027, "step": 59050 }, { "grad_norm": 0.19593840837478638, "learning_rate": 3.923972914685743e-05, "loss": 0.0087, "step": 59060 }, { "loss_action": 0.008151539601385593, "loss_total": 0.008151539601385593, "step": 59060 }, { "grad_norm": 0.19577008485794067, "learning_rate": 3.922358246509631e-05, "loss": 0.0088, "step": 59070 }, { "loss_action": 0.007163354195654392, "loss_total": 0.007163354195654392, "step": 59070 }, { "grad_norm": 0.21852101385593414, "learning_rate": 3.920743696182801e-05, "loss": 0.0064, "step": 59080 }, { "loss_action": 0.010007994249463081, "loss_total": 0.010007994249463081, "step": 59080 }, { "grad_norm": 0.1916918158531189, "learning_rate": 3.9191292638818164e-05, "loss": 0.0081, "step": 59090 }, { "loss_action": 0.008620106615126133, "loss_total": 0.008620106615126133, "step": 59090 }, { "grad_norm": 0.22077175974845886, "learning_rate": 3.9175149497832316e-05, "loss": 0.0092, "step": 59100 }, { "loss_action": 0.015457307919859886, "loss_total": 0.015457307919859886, "step": 59100 }, { "grad_norm": 0.2092065066099167, "learning_rate": 3.915900754063584e-05, "loss": 0.0101, "step": 59110 }, { "loss_action": 0.00643910514190793, "loss_total": 0.00643910514190793, "step": 59110 }, { "grad_norm": 0.2315787971019745, "learning_rate": 3.9142866768994014e-05, "loss": 0.0076, "step": 59120 }, { "loss_action": 0.009415160864591599, "loss_total": 0.009415160864591599, "step": 59120 }, { "grad_norm": 0.2090461701154709, "learning_rate": 3.912672718467193e-05, "loss": 0.0089, "step": 59130 }, { "loss_action": 0.0063978093676269054, "loss_total": 0.0063978093676269054, "step": 59130 }, { "grad_norm": 0.18460404872894287, "learning_rate": 3.911058878943463e-05, "loss": 0.0078, "step": 59140 }, { "loss_action": 0.0061626858077943325, "loss_total": 0.0061626858077943325, "step": 59140 }, { "grad_norm": 0.23854824900627136, "learning_rate": 3.9094451585046974e-05, "loss": 0.0074, "step": 59150 }, { "loss_action": 0.007722589652985334, "loss_total": 0.007722589652985334, "step": 59150 }, { "grad_norm": 0.21555538475513458, "learning_rate": 3.90783155732737e-05, "loss": 0.0081, "step": 59160 }, { "loss_action": 0.010649360716342926, "loss_total": 0.010649360716342926, "step": 59160 }, { "grad_norm": 0.22092872858047485, "learning_rate": 3.9062180755879373e-05, "loss": 0.0084, "step": 59170 }, { "loss_action": 0.007565716281533241, "loss_total": 0.007565716281533241, "step": 59170 }, { "grad_norm": 0.20424231886863708, "learning_rate": 3.904604713462855e-05, "loss": 0.0086, "step": 59180 }, { "loss_action": 0.010083346627652645, "loss_total": 0.010083346627652645, "step": 59180 }, { "grad_norm": 0.179693803191185, "learning_rate": 3.902991471128554e-05, "loss": 0.0084, "step": 59190 }, { "loss_action": 0.008995967917144299, "loss_total": 0.008995967917144299, "step": 59190 }, { "grad_norm": 0.28861719369888306, "learning_rate": 3.901378348761456e-05, "loss": 0.0095, "step": 59200 }, { "loss_action": 0.011025404557585716, "loss_total": 0.011025404557585716, "step": 59200 }, { "grad_norm": 0.19925610721111298, "learning_rate": 3.899765346537971e-05, "loss": 0.009, "step": 59210 }, { "loss_action": 0.008300749585032463, "loss_total": 0.008300749585032463, "step": 59210 }, { "grad_norm": 0.2153589278459549, "learning_rate": 3.898152464634493e-05, "loss": 0.008, "step": 59220 }, { "loss_action": 0.011579393409192562, "loss_total": 0.011579393409192562, "step": 59220 }, { "grad_norm": 0.24807444214820862, "learning_rate": 3.896539703227402e-05, "loss": 0.0097, "step": 59230 }, { "loss_action": 0.00665846886113286, "loss_total": 0.00665846886113286, "step": 59230 }, { "grad_norm": 0.2334263175725937, "learning_rate": 3.894927062493073e-05, "loss": 0.0082, "step": 59240 }, { "loss_action": 0.014842163771390915, "loss_total": 0.014842163771390915, "step": 59240 }, { "grad_norm": 0.2394595891237259, "learning_rate": 3.893314542607859e-05, "loss": 0.0084, "step": 59250 }, { "loss_action": 0.005723202135413885, "loss_total": 0.005723202135413885, "step": 59250 }, { "grad_norm": 0.2180851399898529, "learning_rate": 3.891702143748103e-05, "loss": 0.0073, "step": 59260 }, { "loss_action": 0.011432378552854061, "loss_total": 0.011432378552854061, "step": 59260 }, { "grad_norm": 0.17948314547538757, "learning_rate": 3.890089866090133e-05, "loss": 0.0079, "step": 59270 }, { "loss_action": 0.007681133225560188, "loss_total": 0.007681133225560188, "step": 59270 }, { "grad_norm": 0.26049450039863586, "learning_rate": 3.888477709810267e-05, "loss": 0.0078, "step": 59280 }, { "loss_action": 0.007445949129760265, "loss_total": 0.007445949129760265, "step": 59280 }, { "grad_norm": 0.22496117651462555, "learning_rate": 3.886865675084806e-05, "loss": 0.0099, "step": 59290 }, { "loss_action": 0.010074692778289318, "loss_total": 0.010074692778289318, "step": 59290 }, { "grad_norm": 0.21243467926979065, "learning_rate": 3.885253762090043e-05, "loss": 0.0092, "step": 59300 }, { "loss_action": 0.007407473400235176, "loss_total": 0.007407473400235176, "step": 59300 }, { "grad_norm": 0.2227226197719574, "learning_rate": 3.8836419710022534e-05, "loss": 0.0095, "step": 59310 }, { "loss_action": 0.008853950537741184, "loss_total": 0.008853950537741184, "step": 59310 }, { "grad_norm": 0.24145099520683289, "learning_rate": 3.882030301997698e-05, "loss": 0.0092, "step": 59320 }, { "loss_action": 0.009632128290832043, "loss_total": 0.009632128290832043, "step": 59320 }, { "grad_norm": 0.27473530173301697, "learning_rate": 3.880418755252629e-05, "loss": 0.0104, "step": 59330 }, { "loss_action": 0.009466568939387798, "loss_total": 0.009466568939387798, "step": 59330 }, { "grad_norm": 0.21768800914287567, "learning_rate": 3.87880733094328e-05, "loss": 0.0079, "step": 59340 }, { "loss_action": 0.01135143730789423, "loss_total": 0.01135143730789423, "step": 59340 }, { "grad_norm": 0.2172980159521103, "learning_rate": 3.877196029245877e-05, "loss": 0.0085, "step": 59350 }, { "loss_action": 0.012264298275113106, "loss_total": 0.012264298275113106, "step": 59350 }, { "grad_norm": 0.21632030606269836, "learning_rate": 3.875584850336627e-05, "loss": 0.009, "step": 59360 }, { "loss_action": 0.013342224061489105, "loss_total": 0.013342224061489105, "step": 59360 }, { "grad_norm": 0.17079880833625793, "learning_rate": 3.873973794391728e-05, "loss": 0.0086, "step": 59370 }, { "loss_action": 0.006507262121886015, "loss_total": 0.006507262121886015, "step": 59370 }, { "grad_norm": 0.19876085221767426, "learning_rate": 3.872362861587361e-05, "loss": 0.0089, "step": 59380 }, { "loss_action": 0.013676942326128483, "loss_total": 0.013676942326128483, "step": 59380 }, { "grad_norm": 0.19240522384643555, "learning_rate": 3.870752052099698e-05, "loss": 0.009, "step": 59390 }, { "loss_action": 0.006630709860473871, "loss_total": 0.006630709860473871, "step": 59390 }, { "grad_norm": 0.2276538610458374, "learning_rate": 3.8691413661048916e-05, "loss": 0.0086, "step": 59400 }, { "loss_action": 0.011400812305510044, "loss_total": 0.011400812305510044, "step": 59400 }, { "grad_norm": 0.1802387237548828, "learning_rate": 3.867530803779085e-05, "loss": 0.0102, "step": 59410 }, { "loss_action": 0.007867224514484406, "loss_total": 0.007867224514484406, "step": 59410 }, { "grad_norm": 0.24733920395374298, "learning_rate": 3.8659203652984054e-05, "loss": 0.0101, "step": 59420 }, { "loss_action": 0.007398221641778946, "loss_total": 0.007398221641778946, "step": 59420 }, { "grad_norm": 0.17833036184310913, "learning_rate": 3.864310050838972e-05, "loss": 0.0088, "step": 59430 }, { "loss_action": 0.007828589528799057, "loss_total": 0.007828589528799057, "step": 59430 }, { "grad_norm": 0.2497371882200241, "learning_rate": 3.8626998605768835e-05, "loss": 0.0093, "step": 59440 }, { "loss_action": 0.006029405165463686, "loss_total": 0.006029405165463686, "step": 59440 }, { "grad_norm": 0.22791291773319244, "learning_rate": 3.8610897946882294e-05, "loss": 0.0069, "step": 59450 }, { "loss_action": 0.00718331104144454, "loss_total": 0.00718331104144454, "step": 59450 }, { "grad_norm": 0.24369345605373383, "learning_rate": 3.859479853349082e-05, "loss": 0.0083, "step": 59460 }, { "loss_action": 0.007858420722186565, "loss_total": 0.007858420722186565, "step": 59460 }, { "grad_norm": 0.227292001247406, "learning_rate": 3.857870036735503e-05, "loss": 0.0098, "step": 59470 }, { "loss_action": 0.009630839340388775, "loss_total": 0.009630839340388775, "step": 59470 }, { "grad_norm": 0.18868471682071686, "learning_rate": 3.856260345023538e-05, "loss": 0.0088, "step": 59480 }, { "loss_action": 0.010904609225690365, "loss_total": 0.010904609225690365, "step": 59480 }, { "grad_norm": 0.2913297414779663, "learning_rate": 3.854650778389224e-05, "loss": 0.0098, "step": 59490 }, { "loss_action": 0.010571705177426338, "loss_total": 0.010571705177426338, "step": 59490 }, { "grad_norm": 0.34633246064186096, "learning_rate": 3.8530413370085786e-05, "loss": 0.0088, "step": 59500 }, { "loss_action": 0.008540337905287743, "loss_total": 0.008540337905287743, "step": 59500 }, { "grad_norm": 0.20323900878429413, "learning_rate": 3.851432021057608e-05, "loss": 0.008, "step": 59510 }, { "loss_action": 0.007778278086334467, "loss_total": 0.007778278086334467, "step": 59510 }, { "grad_norm": 0.284681111574173, "learning_rate": 3.849822830712306e-05, "loss": 0.0087, "step": 59520 }, { "loss_action": 0.006448631640523672, "loss_total": 0.006448631640523672, "step": 59520 }, { "grad_norm": 0.2631587088108063, "learning_rate": 3.848213766148649e-05, "loss": 0.009, "step": 59530 }, { "loss_action": 0.009605892933905125, "loss_total": 0.009605892933905125, "step": 59530 }, { "grad_norm": 0.2888656258583069, "learning_rate": 3.846604827542602e-05, "loss": 0.0088, "step": 59540 }, { "loss_action": 0.010382814332842827, "loss_total": 0.010382814332842827, "step": 59540 }, { "grad_norm": 0.26649075746536255, "learning_rate": 3.844996015070117e-05, "loss": 0.0094, "step": 59550 }, { "loss_action": 0.008220955729484558, "loss_total": 0.008220955729484558, "step": 59550 }, { "grad_norm": 0.23990096151828766, "learning_rate": 3.843387328907132e-05, "loss": 0.0094, "step": 59560 }, { "loss_action": 0.013781951740384102, "loss_total": 0.013781951740384102, "step": 59560 }, { "grad_norm": 0.21443410217761993, "learning_rate": 3.8417787692295696e-05, "loss": 0.0094, "step": 59570 }, { "loss_action": 0.008197964169085026, "loss_total": 0.008197964169085026, "step": 59570 }, { "grad_norm": 0.21542604267597198, "learning_rate": 3.84017033621334e-05, "loss": 0.0086, "step": 59580 }, { "loss_action": 0.006465749815106392, "loss_total": 0.006465749815106392, "step": 59580 }, { "grad_norm": 0.2282400131225586, "learning_rate": 3.838562030034338e-05, "loss": 0.0092, "step": 59590 }, { "loss_action": 0.008750504814088345, "loss_total": 0.008750504814088345, "step": 59590 }, { "grad_norm": 0.24451009929180145, "learning_rate": 3.836953850868447e-05, "loss": 0.0083, "step": 59600 }, { "loss_action": 0.006097158882766962, "loss_total": 0.006097158882766962, "step": 59600 }, { "grad_norm": 0.23105065524578094, "learning_rate": 3.835345798891533e-05, "loss": 0.0075, "step": 59610 }, { "loss_action": 0.00952939037233591, "loss_total": 0.00952939037233591, "step": 59610 }, { "grad_norm": 0.2024385929107666, "learning_rate": 3.833737874279452e-05, "loss": 0.0097, "step": 59620 }, { "loss_action": 0.009011462330818176, "loss_total": 0.009011462330818176, "step": 59620 }, { "grad_norm": 0.258916974067688, "learning_rate": 3.8321300772080433e-05, "loss": 0.0082, "step": 59630 }, { "loss_action": 0.010632986202836037, "loss_total": 0.010632986202836037, "step": 59630 }, { "grad_norm": 0.19809362292289734, "learning_rate": 3.8305224078531345e-05, "loss": 0.0077, "step": 59640 }, { "loss_action": 0.008207719773054123, "loss_total": 0.008207719773054123, "step": 59640 }, { "grad_norm": 0.24501459300518036, "learning_rate": 3.828914866390537e-05, "loss": 0.0083, "step": 59650 }, { "loss_action": 0.014354481361806393, "loss_total": 0.014354481361806393, "step": 59650 }, { "grad_norm": 0.2727980315685272, "learning_rate": 3.827307452996048e-05, "loss": 0.0086, "step": 59660 }, { "loss_action": 0.006101266015321016, "loss_total": 0.006101266015321016, "step": 59660 }, { "grad_norm": 0.25973963737487793, "learning_rate": 3.825700167845454e-05, "loss": 0.0091, "step": 59670 }, { "loss_action": 0.008748451247811317, "loss_total": 0.008748451247811317, "step": 59670 }, { "grad_norm": 0.19094228744506836, "learning_rate": 3.8240930111145214e-05, "loss": 0.0083, "step": 59680 }, { "loss_action": 0.008639740757644176, "loss_total": 0.008639740757644176, "step": 59680 }, { "grad_norm": 0.26473379135131836, "learning_rate": 3.8224859829790116e-05, "loss": 0.0091, "step": 59690 }, { "loss_action": 0.0077345590107142925, "loss_total": 0.0077345590107142925, "step": 59690 }, { "grad_norm": 0.27813664078712463, "learning_rate": 3.820879083614664e-05, "loss": 0.0082, "step": 59700 }, { "loss_action": 0.009873964823782444, "loss_total": 0.009873964823782444, "step": 59700 }, { "grad_norm": 0.20552493631839752, "learning_rate": 3.819272313197208e-05, "loss": 0.0086, "step": 59710 }, { "loss_action": 0.009222621098160744, "loss_total": 0.009222621098160744, "step": 59710 }, { "grad_norm": 0.3377647399902344, "learning_rate": 3.817665671902355e-05, "loss": 0.0091, "step": 59720 }, { "loss_action": 0.01489067729562521, "loss_total": 0.01489067729562521, "step": 59720 }, { "grad_norm": 0.23204992711544037, "learning_rate": 3.816059159905808e-05, "loss": 0.0104, "step": 59730 }, { "loss_action": 0.009396315552294254, "loss_total": 0.009396315552294254, "step": 59730 }, { "grad_norm": 0.2758563458919525, "learning_rate": 3.8144527773832476e-05, "loss": 0.0097, "step": 59740 }, { "loss_action": 0.0064668175764381886, "loss_total": 0.0064668175764381886, "step": 59740 }, { "grad_norm": 0.1810014545917511, "learning_rate": 3.812846524510352e-05, "loss": 0.0073, "step": 59750 }, { "loss_action": 0.008096173405647278, "loss_total": 0.008096173405647278, "step": 59750 }, { "grad_norm": 0.19733993709087372, "learning_rate": 3.811240401462775e-05, "loss": 0.0088, "step": 59760 }, { "loss_action": 0.008423859253525734, "loss_total": 0.008423859253525734, "step": 59760 }, { "grad_norm": 0.19968929886817932, "learning_rate": 3.809634408416162e-05, "loss": 0.008, "step": 59770 }, { "loss_action": 0.008549435995519161, "loss_total": 0.008549435995519161, "step": 59770 }, { "grad_norm": 0.21920427680015564, "learning_rate": 3.8080285455461394e-05, "loss": 0.0083, "step": 59780 }, { "loss_action": 0.006549816578626633, "loss_total": 0.006549816578626633, "step": 59780 }, { "grad_norm": 0.20238864421844482, "learning_rate": 3.806422813028323e-05, "loss": 0.0085, "step": 59790 }, { "loss_action": 0.005518898833543062, "loss_total": 0.005518898833543062, "step": 59790 }, { "grad_norm": 0.1990886926651001, "learning_rate": 3.8048172110383114e-05, "loss": 0.0084, "step": 59800 }, { "loss_action": 0.008007793687283993, "loss_total": 0.008007793687283993, "step": 59800 }, { "grad_norm": 0.19610731303691864, "learning_rate": 3.8032117397516944e-05, "loss": 0.0078, "step": 59810 }, { "loss_action": 0.007394302636384964, "loss_total": 0.007394302636384964, "step": 59810 }, { "grad_norm": 0.1858823597431183, "learning_rate": 3.801606399344042e-05, "loss": 0.0076, "step": 59820 }, { "loss_action": 0.004517051856964827, "loss_total": 0.004517051856964827, "step": 59820 }, { "grad_norm": 0.19950713217258453, "learning_rate": 3.800001189990913e-05, "loss": 0.0074, "step": 59830 }, { "loss_action": 0.007666421122848988, "loss_total": 0.007666421122848988, "step": 59830 }, { "grad_norm": 0.2560795545578003, "learning_rate": 3.798396111867847e-05, "loss": 0.0089, "step": 59840 }, { "loss_action": 0.007165614981204271, "loss_total": 0.007165614981204271, "step": 59840 }, { "grad_norm": 0.21014201641082764, "learning_rate": 3.796791165150378e-05, "loss": 0.0084, "step": 59850 }, { "loss_action": 0.0068565369583666325, "loss_total": 0.0068565369583666325, "step": 59850 }, { "grad_norm": 0.2237706184387207, "learning_rate": 3.795186350014018e-05, "loss": 0.0083, "step": 59860 }, { "loss_action": 0.006231373175978661, "loss_total": 0.006231373175978661, "step": 59860 }, { "grad_norm": 0.2007516473531723, "learning_rate": 3.793581666634266e-05, "loss": 0.0093, "step": 59870 }, { "loss_action": 0.0072024851106107235, "loss_total": 0.0072024851106107235, "step": 59870 }, { "grad_norm": 0.2121739685535431, "learning_rate": 3.791977115186609e-05, "loss": 0.0085, "step": 59880 }, { "loss_action": 0.007905800826847553, "loss_total": 0.007905800826847553, "step": 59880 }, { "grad_norm": 0.17540767788887024, "learning_rate": 3.79037269584652e-05, "loss": 0.0073, "step": 59890 }, { "loss_action": 0.009832066483795643, "loss_total": 0.009832066483795643, "step": 59890 }, { "grad_norm": 0.15981605648994446, "learning_rate": 3.7887684087894545e-05, "loss": 0.0077, "step": 59900 }, { "loss_action": 0.007948668673634529, "loss_total": 0.007948668673634529, "step": 59900 }, { "grad_norm": 0.25241419672966003, "learning_rate": 3.787164254190854e-05, "loss": 0.008, "step": 59910 }, { "loss_action": 0.010586166754364967, "loss_total": 0.010586166754364967, "step": 59910 }, { "grad_norm": 0.22613263130187988, "learning_rate": 3.7855602322261473e-05, "loss": 0.0088, "step": 59920 }, { "loss_action": 0.008390409871935844, "loss_total": 0.008390409871935844, "step": 59920 }, { "grad_norm": 0.20990458130836487, "learning_rate": 3.783956343070746e-05, "loss": 0.0085, "step": 59930 }, { "loss_action": 0.006348671857267618, "loss_total": 0.006348671857267618, "step": 59930 }, { "grad_norm": 0.24852220714092255, "learning_rate": 3.7823525869000526e-05, "loss": 0.0079, "step": 59940 }, { "loss_action": 0.006546490825712681, "loss_total": 0.006546490825712681, "step": 59940 }, { "grad_norm": 0.24712596833705902, "learning_rate": 3.78074896388945e-05, "loss": 0.0074, "step": 59950 }, { "loss_action": 0.010854304768145084, "loss_total": 0.010854304768145084, "step": 59950 }, { "grad_norm": 0.24917887151241302, "learning_rate": 3.7791454742143075e-05, "loss": 0.0093, "step": 59960 }, { "loss_action": 0.009274049662053585, "loss_total": 0.009274049662053585, "step": 59960 }, { "grad_norm": 0.2980136573314667, "learning_rate": 3.7775421180499795e-05, "loss": 0.009, "step": 59970 }, { "loss_action": 0.01063021644949913, "loss_total": 0.01063021644949913, "step": 59970 }, { "grad_norm": 0.2070463001728058, "learning_rate": 3.7759388955718086e-05, "loss": 0.0085, "step": 59980 }, { "loss_action": 0.007761385757476091, "loss_total": 0.007761385757476091, "step": 59980 }, { "grad_norm": 0.15058891475200653, "learning_rate": 3.774335806955117e-05, "loss": 0.0068, "step": 59990 }, { "loss_action": 0.008588962256908417, "loss_total": 0.008588962256908417, "step": 59990 }, { "grad_norm": 0.2574402391910553, "learning_rate": 3.7727328523752215e-05, "loss": 0.008, "step": 60000 }, { "loss_action": 0.008111190982162952, "loss_total": 0.008111190982162952, "step": 60000 }, { "grad_norm": 0.25262486934661865, "learning_rate": 3.771130032007415e-05, "loss": 0.0082, "step": 60010 }, { "loss_action": 0.0067427861504256725, "loss_total": 0.0067427861504256725, "step": 60010 }, { "grad_norm": 0.20799018442630768, "learning_rate": 3.769527346026982e-05, "loss": 0.0073, "step": 60020 }, { "loss_action": 0.007368267513811588, "loss_total": 0.007368267513811588, "step": 60020 }, { "grad_norm": 0.25733426213264465, "learning_rate": 3.767924794609188e-05, "loss": 0.0085, "step": 60030 }, { "loss_action": 0.007858273573219776, "loss_total": 0.007858273573219776, "step": 60030 }, { "grad_norm": 0.192106693983078, "learning_rate": 3.7663223779292854e-05, "loss": 0.0086, "step": 60040 }, { "loss_action": 0.0072290608659386635, "loss_total": 0.0072290608659386635, "step": 60040 }, { "grad_norm": 0.26211094856262207, "learning_rate": 3.764720096162512e-05, "loss": 0.0083, "step": 60050 }, { "loss_action": 0.013109706342220306, "loss_total": 0.013109706342220306, "step": 60050 }, { "grad_norm": 0.25221681594848633, "learning_rate": 3.763117949484092e-05, "loss": 0.009, "step": 60060 }, { "loss_action": 0.011380770243704319, "loss_total": 0.011380770243704319, "step": 60060 }, { "grad_norm": 0.18436601758003235, "learning_rate": 3.7615159380692344e-05, "loss": 0.0092, "step": 60070 }, { "loss_action": 0.009321344085037708, "loss_total": 0.009321344085037708, "step": 60070 }, { "grad_norm": 0.20536144077777863, "learning_rate": 3.759914062093132e-05, "loss": 0.008, "step": 60080 }, { "loss_action": 0.012743799015879631, "loss_total": 0.012743799015879631, "step": 60080 }, { "grad_norm": 0.18388766050338745, "learning_rate": 3.7583123217309615e-05, "loss": 0.0082, "step": 60090 }, { "loss_action": 0.006866203621029854, "loss_total": 0.006866203621029854, "step": 60090 }, { "grad_norm": 0.21646994352340698, "learning_rate": 3.7567107171578904e-05, "loss": 0.0076, "step": 60100 }, { "loss_action": 0.009344774298369884, "loss_total": 0.009344774298369884, "step": 60100 }, { "grad_norm": 0.27389290928840637, "learning_rate": 3.755109248549066e-05, "loss": 0.0094, "step": 60110 }, { "loss_action": 0.012545885518193245, "loss_total": 0.012545885518193245, "step": 60110 }, { "grad_norm": 0.17111964523792267, "learning_rate": 3.75350791607962e-05, "loss": 0.0071, "step": 60120 }, { "loss_action": 0.005864401813596487, "loss_total": 0.005864401813596487, "step": 60120 }, { "grad_norm": 0.18398627638816833, "learning_rate": 3.751906719924676e-05, "loss": 0.0069, "step": 60130 }, { "loss_action": 0.006705032661557198, "loss_total": 0.006705032661557198, "step": 60130 }, { "grad_norm": 0.16234345734119415, "learning_rate": 3.750305660259337e-05, "loss": 0.0071, "step": 60140 }, { "loss_action": 0.008711748756468296, "loss_total": 0.008711748756468296, "step": 60140 }, { "grad_norm": 0.27313748002052307, "learning_rate": 3.748704737258693e-05, "loss": 0.0108, "step": 60150 }, { "loss_action": 0.010727482847869396, "loss_total": 0.010727482847869396, "step": 60150 }, { "grad_norm": 0.30514660477638245, "learning_rate": 3.747103951097816e-05, "loss": 0.0089, "step": 60160 }, { "loss_action": 0.007095601409673691, "loss_total": 0.007095601409673691, "step": 60160 }, { "grad_norm": 0.2184593826532364, "learning_rate": 3.745503301951768e-05, "loss": 0.0084, "step": 60170 }, { "loss_action": 0.008131652139127254, "loss_total": 0.008131652139127254, "step": 60170 }, { "grad_norm": 0.213653564453125, "learning_rate": 3.743902789995592e-05, "loss": 0.008, "step": 60180 }, { "loss_action": 0.00482123764231801, "loss_total": 0.00482123764231801, "step": 60180 }, { "grad_norm": 0.23454023897647858, "learning_rate": 3.7423024154043183e-05, "loss": 0.0077, "step": 60190 }, { "loss_action": 0.00649869441986084, "loss_total": 0.00649869441986084, "step": 60190 }, { "grad_norm": 0.2664545774459839, "learning_rate": 3.740702178352963e-05, "loss": 0.0089, "step": 60200 }, { "loss_action": 0.009737842716276646, "loss_total": 0.009737842716276646, "step": 60200 }, { "grad_norm": 0.23840779066085815, "learning_rate": 3.739102079016523e-05, "loss": 0.009, "step": 60210 }, { "loss_action": 0.010876188986003399, "loss_total": 0.010876188986003399, "step": 60210 }, { "grad_norm": 0.26962801814079285, "learning_rate": 3.7375021175699846e-05, "loss": 0.0082, "step": 60220 }, { "loss_action": 0.0073272245936095715, "loss_total": 0.0073272245936095715, "step": 60220 }, { "grad_norm": 0.20307931303977966, "learning_rate": 3.735902294188317e-05, "loss": 0.0087, "step": 60230 }, { "loss_action": 0.0160058680921793, "loss_total": 0.0160058680921793, "step": 60230 }, { "grad_norm": 0.19898289442062378, "learning_rate": 3.734302609046473e-05, "loss": 0.0081, "step": 60240 }, { "loss_action": 0.008851160295307636, "loss_total": 0.008851160295307636, "step": 60240 }, { "grad_norm": 0.1856907308101654, "learning_rate": 3.732703062319391e-05, "loss": 0.0079, "step": 60250 }, { "loss_action": 0.009538658894598484, "loss_total": 0.009538658894598484, "step": 60250 }, { "grad_norm": 0.18151237070560455, "learning_rate": 3.731103654181999e-05, "loss": 0.008, "step": 60260 }, { "loss_action": 0.006203487981110811, "loss_total": 0.006203487981110811, "step": 60260 }, { "grad_norm": 0.19479773938655853, "learning_rate": 3.729504384809203e-05, "loss": 0.0073, "step": 60270 }, { "loss_action": 0.007450757548213005, "loss_total": 0.007450757548213005, "step": 60270 }, { "grad_norm": 0.17874234914779663, "learning_rate": 3.727905254375898e-05, "loss": 0.0082, "step": 60280 }, { "loss_action": 0.00760478712618351, "loss_total": 0.00760478712618351, "step": 60280 }, { "grad_norm": 0.1761535108089447, "learning_rate": 3.7263062630569614e-05, "loss": 0.0083, "step": 60290 }, { "loss_action": 0.005873633082956076, "loss_total": 0.005873633082956076, "step": 60290 }, { "grad_norm": 0.29061681032180786, "learning_rate": 3.724707411027256e-05, "loss": 0.0089, "step": 60300 }, { "loss_action": 0.012128526344895363, "loss_total": 0.012128526344895363, "step": 60300 }, { "grad_norm": 0.25216245651245117, "learning_rate": 3.723108698461631e-05, "loss": 0.0092, "step": 60310 }, { "loss_action": 0.009431700222194195, "loss_total": 0.009431700222194195, "step": 60310 }, { "grad_norm": 0.23431190848350525, "learning_rate": 3.72151012553492e-05, "loss": 0.0088, "step": 60320 }, { "loss_action": 0.0090562142431736, "loss_total": 0.0090562142431736, "step": 60320 }, { "grad_norm": 0.2695605456829071, "learning_rate": 3.719911692421939e-05, "loss": 0.0078, "step": 60330 }, { "loss_action": 0.008635769598186016, "loss_total": 0.008635769598186016, "step": 60330 }, { "grad_norm": 0.2273256927728653, "learning_rate": 3.71831339929749e-05, "loss": 0.0082, "step": 60340 }, { "loss_action": 0.010208535939455032, "loss_total": 0.010208535939455032, "step": 60340 }, { "grad_norm": 0.2225228250026703, "learning_rate": 3.716715246336362e-05, "loss": 0.0086, "step": 60350 }, { "loss_action": 0.010726481676101685, "loss_total": 0.010726481676101685, "step": 60350 }, { "grad_norm": 0.16962650418281555, "learning_rate": 3.715117233713324e-05, "loss": 0.0097, "step": 60360 }, { "loss_action": 0.00951598770916462, "loss_total": 0.00951598770916462, "step": 60360 }, { "grad_norm": 0.20340405404567719, "learning_rate": 3.713519361603135e-05, "loss": 0.0094, "step": 60370 }, { "loss_action": 0.007012839894741774, "loss_total": 0.007012839894741774, "step": 60370 }, { "grad_norm": 0.1939186453819275, "learning_rate": 3.711921630180532e-05, "loss": 0.0075, "step": 60380 }, { "loss_action": 0.007447794545441866, "loss_total": 0.007447794545441866, "step": 60380 }, { "grad_norm": 0.22753870487213135, "learning_rate": 3.710324039620245e-05, "loss": 0.009, "step": 60390 }, { "loss_action": 0.010782546363770962, "loss_total": 0.010782546363770962, "step": 60390 }, { "grad_norm": 0.18715518712997437, "learning_rate": 3.708726590096982e-05, "loss": 0.0077, "step": 60400 }, { "loss_action": 0.009191309101879597, "loss_total": 0.009191309101879597, "step": 60400 }, { "grad_norm": 0.2175097018480301, "learning_rate": 3.707129281785437e-05, "loss": 0.0071, "step": 60410 }, { "loss_action": 0.014239530079066753, "loss_total": 0.014239530079066753, "step": 60410 }, { "grad_norm": 0.20512670278549194, "learning_rate": 3.705532114860291e-05, "loss": 0.0104, "step": 60420 }, { "loss_action": 0.008260722272098064, "loss_total": 0.008260722272098064, "step": 60420 }, { "grad_norm": 0.2636852562427521, "learning_rate": 3.703935089496207e-05, "loss": 0.0079, "step": 60430 }, { "loss_action": 0.010588233359158039, "loss_total": 0.010588233359158039, "step": 60430 }, { "grad_norm": 0.20304962992668152, "learning_rate": 3.702338205867829e-05, "loss": 0.0083, "step": 60440 }, { "loss_action": 0.009385727345943451, "loss_total": 0.009385727345943451, "step": 60440 }, { "grad_norm": 0.19249723851680756, "learning_rate": 3.7007414641497976e-05, "loss": 0.0083, "step": 60450 }, { "loss_action": 0.00792081281542778, "loss_total": 0.00792081281542778, "step": 60450 }, { "grad_norm": 0.2027295082807541, "learning_rate": 3.699144864516726e-05, "loss": 0.008, "step": 60460 }, { "loss_action": 0.018492545932531357, "loss_total": 0.018492545932531357, "step": 60460 }, { "grad_norm": 0.2571098208427429, "learning_rate": 3.6975484071432153e-05, "loss": 0.0098, "step": 60470 }, { "loss_action": 0.010746627114713192, "loss_total": 0.010746627114713192, "step": 60470 }, { "grad_norm": 0.2450914978981018, "learning_rate": 3.695952092203854e-05, "loss": 0.0073, "step": 60480 }, { "loss_action": 0.005420914385467768, "loss_total": 0.005420914385467768, "step": 60480 }, { "grad_norm": 0.19101804494857788, "learning_rate": 3.69435591987321e-05, "loss": 0.0078, "step": 60490 }, { "loss_action": 0.009865383617579937, "loss_total": 0.009865383617579937, "step": 60490 }, { "grad_norm": 0.21439890563488007, "learning_rate": 3.6927598903258374e-05, "loss": 0.0083, "step": 60500 }, { "loss_action": 0.007220831234008074, "loss_total": 0.007220831234008074, "step": 60500 }, { "grad_norm": 0.23827865719795227, "learning_rate": 3.691164003736281e-05, "loss": 0.0093, "step": 60510 }, { "loss_action": 0.010010666213929653, "loss_total": 0.010010666213929653, "step": 60510 }, { "grad_norm": 0.2222004234790802, "learning_rate": 3.689568260279061e-05, "loss": 0.0081, "step": 60520 }, { "loss_action": 0.008379824459552765, "loss_total": 0.008379824459552765, "step": 60520 }, { "grad_norm": 0.18816813826560974, "learning_rate": 3.687972660128686e-05, "loss": 0.0098, "step": 60530 }, { "loss_action": 0.005335972178727388, "loss_total": 0.005335972178727388, "step": 60530 }, { "grad_norm": 0.17729750275611877, "learning_rate": 3.686377203459648e-05, "loss": 0.0084, "step": 60540 }, { "loss_action": 0.00625963881611824, "loss_total": 0.00625963881611824, "step": 60540 }, { "grad_norm": 0.22052259743213654, "learning_rate": 3.6847818904464226e-05, "loss": 0.0074, "step": 60550 }, { "loss_action": 0.006958990357816219, "loss_total": 0.006958990357816219, "step": 60550 }, { "grad_norm": 0.1668688952922821, "learning_rate": 3.683186721263474e-05, "loss": 0.0077, "step": 60560 }, { "loss_action": 0.005028640851378441, "loss_total": 0.005028640851378441, "step": 60560 }, { "grad_norm": 0.23058000206947327, "learning_rate": 3.6815916960852435e-05, "loss": 0.0083, "step": 60570 }, { "loss_action": 0.007268718909472227, "loss_total": 0.007268718909472227, "step": 60570 }, { "grad_norm": 0.19161812961101532, "learning_rate": 3.679996815086165e-05, "loss": 0.0087, "step": 60580 }, { "loss_action": 0.007136930245906115, "loss_total": 0.007136930245906115, "step": 60580 }, { "grad_norm": 0.1820698231458664, "learning_rate": 3.678402078440649e-05, "loss": 0.0079, "step": 60590 }, { "loss_action": 0.00939140934497118, "loss_total": 0.00939140934497118, "step": 60590 }, { "grad_norm": 0.16531269252300262, "learning_rate": 3.676807486323096e-05, "loss": 0.0073, "step": 60600 }, { "loss_action": 0.0072327423840761185, "loss_total": 0.0072327423840761185, "step": 60600 }, { "grad_norm": 0.2061733603477478, "learning_rate": 3.6752130389078864e-05, "loss": 0.0077, "step": 60610 }, { "loss_action": 0.005605390295386314, "loss_total": 0.005605390295386314, "step": 60610 }, { "grad_norm": 0.22772487998008728, "learning_rate": 3.673618736369388e-05, "loss": 0.009, "step": 60620 }, { "loss_action": 0.0076006269082427025, "loss_total": 0.0076006269082427025, "step": 60620 }, { "grad_norm": 0.1905328631401062, "learning_rate": 3.6720245788819474e-05, "loss": 0.0072, "step": 60630 }, { "loss_action": 0.011425602249801159, "loss_total": 0.011425602249801159, "step": 60630 }, { "grad_norm": 0.21449707448482513, "learning_rate": 3.6704305666199044e-05, "loss": 0.0073, "step": 60640 }, { "loss_action": 0.006425222381949425, "loss_total": 0.006425222381949425, "step": 60640 }, { "grad_norm": 0.3013549745082855, "learning_rate": 3.668836699757576e-05, "loss": 0.0092, "step": 60650 }, { "loss_action": 0.006443756632506847, "loss_total": 0.006443756632506847, "step": 60650 }, { "grad_norm": 0.32417556643486023, "learning_rate": 3.667242978469265e-05, "loss": 0.0083, "step": 60660 }, { "loss_action": 0.01547603402286768, "loss_total": 0.01547603402286768, "step": 60660 }, { "grad_norm": 0.27308183908462524, "learning_rate": 3.6656494029292575e-05, "loss": 0.0105, "step": 60670 }, { "loss_action": 0.0064912824891507626, "loss_total": 0.0064912824891507626, "step": 60670 }, { "grad_norm": 0.3012692332267761, "learning_rate": 3.664055973311825e-05, "loss": 0.0092, "step": 60680 }, { "loss_action": 0.009900969453155994, "loss_total": 0.009900969453155994, "step": 60680 }, { "grad_norm": 0.26351627707481384, "learning_rate": 3.662462689791221e-05, "loss": 0.0088, "step": 60690 }, { "loss_action": 0.007582005579024553, "loss_total": 0.007582005579024553, "step": 60690 }, { "grad_norm": 0.22645695507526398, "learning_rate": 3.660869552541689e-05, "loss": 0.0085, "step": 60700 }, { "loss_action": 0.006492667831480503, "loss_total": 0.006492667831480503, "step": 60700 }, { "grad_norm": 0.28626057505607605, "learning_rate": 3.659276561737448e-05, "loss": 0.0099, "step": 60710 }, { "loss_action": 0.007858493365347385, "loss_total": 0.007858493365347385, "step": 60710 }, { "grad_norm": 0.2561211884021759, "learning_rate": 3.657683717552708e-05, "loss": 0.0095, "step": 60720 }, { "loss_action": 0.005368354264646769, "loss_total": 0.005368354264646769, "step": 60720 }, { "grad_norm": 0.20090410113334656, "learning_rate": 3.6560910201616574e-05, "loss": 0.0076, "step": 60730 }, { "loss_action": 0.007529668044298887, "loss_total": 0.007529668044298887, "step": 60730 }, { "grad_norm": 0.18018600344657898, "learning_rate": 3.654498469738472e-05, "loss": 0.008, "step": 60740 }, { "loss_action": 0.0087653249502182, "loss_total": 0.0087653249502182, "step": 60740 }, { "grad_norm": 0.20987263321876526, "learning_rate": 3.6529060664573126e-05, "loss": 0.008, "step": 60750 }, { "loss_action": 0.00681711221113801, "loss_total": 0.00681711221113801, "step": 60750 }, { "grad_norm": 0.18218322098255157, "learning_rate": 3.6513138104923176e-05, "loss": 0.0095, "step": 60760 }, { "loss_action": 0.007627070415765047, "loss_total": 0.007627070415765047, "step": 60760 }, { "grad_norm": 0.21529890596866608, "learning_rate": 3.6497217020176176e-05, "loss": 0.008, "step": 60770 }, { "loss_action": 0.007088179234415293, "loss_total": 0.007088179234415293, "step": 60770 }, { "grad_norm": 0.1746002435684204, "learning_rate": 3.648129741207323e-05, "loss": 0.0077, "step": 60780 }, { "loss_action": 0.008000709116458893, "loss_total": 0.008000709116458893, "step": 60780 }, { "grad_norm": 0.23099954426288605, "learning_rate": 3.646537928235527e-05, "loss": 0.0094, "step": 60790 }, { "loss_action": 0.01017728354781866, "loss_total": 0.01017728354781866, "step": 60790 }, { "grad_norm": 0.17722462117671967, "learning_rate": 3.6449462632763075e-05, "loss": 0.0081, "step": 60800 }, { "loss_action": 0.01240371260792017, "loss_total": 0.01240371260792017, "step": 60800 }, { "grad_norm": 0.2065136432647705, "learning_rate": 3.643354746503729e-05, "loss": 0.0093, "step": 60810 }, { "loss_action": 0.006414496805518866, "loss_total": 0.006414496805518866, "step": 60810 }, { "grad_norm": 0.23164308071136475, "learning_rate": 3.6417633780918345e-05, "loss": 0.0082, "step": 60820 }, { "loss_action": 0.008877134881913662, "loss_total": 0.008877134881913662, "step": 60820 }, { "grad_norm": 0.21527539193630219, "learning_rate": 3.640172158214655e-05, "loss": 0.0085, "step": 60830 }, { "loss_action": 0.009840874001383781, "loss_total": 0.009840874001383781, "step": 60830 }, { "grad_norm": 0.1831669807434082, "learning_rate": 3.6385810870462035e-05, "loss": 0.0086, "step": 60840 }, { "loss_action": 0.007705195806920528, "loss_total": 0.007705195806920528, "step": 60840 }, { "grad_norm": 0.16922415792942047, "learning_rate": 3.636990164760479e-05, "loss": 0.0082, "step": 60850 }, { "loss_action": 0.008105074986815453, "loss_total": 0.008105074986815453, "step": 60850 }, { "grad_norm": 0.15576474368572235, "learning_rate": 3.6353993915314596e-05, "loss": 0.0083, "step": 60860 }, { "loss_action": 0.008738629519939423, "loss_total": 0.008738629519939423, "step": 60860 }, { "grad_norm": 0.17744101583957672, "learning_rate": 3.6338087675331124e-05, "loss": 0.0081, "step": 60870 }, { "loss_action": 0.006758918520063162, "loss_total": 0.006758918520063162, "step": 60870 }, { "grad_norm": 0.181706964969635, "learning_rate": 3.632218292939383e-05, "loss": 0.0073, "step": 60880 }, { "loss_action": 0.007285413332283497, "loss_total": 0.007285413332283497, "step": 60880 }, { "grad_norm": 0.21230711042881012, "learning_rate": 3.6306279679242033e-05, "loss": 0.0084, "step": 60890 }, { "loss_action": 0.007504277862608433, "loss_total": 0.007504277862608433, "step": 60890 }, { "grad_norm": 0.1806454062461853, "learning_rate": 3.629037792661492e-05, "loss": 0.0077, "step": 60900 }, { "loss_action": 0.006906422320753336, "loss_total": 0.006906422320753336, "step": 60900 }, { "grad_norm": 0.19986934959888458, "learning_rate": 3.627447767325147e-05, "loss": 0.009, "step": 60910 }, { "loss_action": 0.010008372366428375, "loss_total": 0.010008372366428375, "step": 60910 }, { "grad_norm": 0.25164684653282166, "learning_rate": 3.62585789208905e-05, "loss": 0.0085, "step": 60920 }, { "loss_action": 0.0070353117771446705, "loss_total": 0.0070353117771446705, "step": 60920 }, { "grad_norm": 0.2212264984846115, "learning_rate": 3.624268167127068e-05, "loss": 0.0075, "step": 60930 }, { "loss_action": 0.010059673339128494, "loss_total": 0.010059673339128494, "step": 60930 }, { "grad_norm": 0.1534678190946579, "learning_rate": 3.622678592613051e-05, "loss": 0.0087, "step": 60940 }, { "loss_action": 0.009961544536054134, "loss_total": 0.009961544536054134, "step": 60940 }, { "grad_norm": 0.21685878932476044, "learning_rate": 3.6210891687208304e-05, "loss": 0.0079, "step": 60950 }, { "loss_action": 0.010831866413354874, "loss_total": 0.010831866413354874, "step": 60950 }, { "grad_norm": 0.18463999032974243, "learning_rate": 3.619499895624228e-05, "loss": 0.0078, "step": 60960 }, { "loss_action": 0.010957450605928898, "loss_total": 0.010957450605928898, "step": 60960 }, { "grad_norm": 0.2010972648859024, "learning_rate": 3.61791077349704e-05, "loss": 0.0084, "step": 60970 }, { "loss_action": 0.007172819692641497, "loss_total": 0.007172819692641497, "step": 60970 }, { "grad_norm": 0.22967638075351715, "learning_rate": 3.616321802513053e-05, "loss": 0.0095, "step": 60980 }, { "loss_action": 0.00546754477545619, "loss_total": 0.00546754477545619, "step": 60980 }, { "grad_norm": 0.2304566651582718, "learning_rate": 3.6147329828460325e-05, "loss": 0.0093, "step": 60990 }, { "loss_action": 0.0070333946496248245, "loss_total": 0.0070333946496248245, "step": 60990 }, { "grad_norm": 0.250108003616333, "learning_rate": 3.6131443146697306e-05, "loss": 0.0087, "step": 61000 }, { "loss_action": 0.007734376005828381, "loss_total": 0.007734376005828381, "step": 61000 }, { "grad_norm": 0.2284017652273178, "learning_rate": 3.611555798157879e-05, "loss": 0.0081, "step": 61010 }, { "loss_action": 0.006858598440885544, "loss_total": 0.006858598440885544, "step": 61010 }, { "grad_norm": 0.19328564405441284, "learning_rate": 3.6099674334842e-05, "loss": 0.0071, "step": 61020 }, { "loss_action": 0.006980345118790865, "loss_total": 0.006980345118790865, "step": 61020 }, { "grad_norm": 0.17788159847259521, "learning_rate": 3.6083792208223934e-05, "loss": 0.0079, "step": 61030 }, { "loss_action": 0.008507493883371353, "loss_total": 0.008507493883371353, "step": 61030 }, { "grad_norm": 0.16839173436164856, "learning_rate": 3.606791160346142e-05, "loss": 0.0081, "step": 61040 }, { "loss_action": 0.009663800708949566, "loss_total": 0.009663800708949566, "step": 61040 }, { "grad_norm": 0.21473164856433868, "learning_rate": 3.6052032522291134e-05, "loss": 0.0081, "step": 61050 }, { "loss_action": 0.008602079004049301, "loss_total": 0.008602079004049301, "step": 61050 }, { "grad_norm": 0.24897919595241547, "learning_rate": 3.603615496644962e-05, "loss": 0.009, "step": 61060 }, { "loss_action": 0.010205456055700779, "loss_total": 0.010205456055700779, "step": 61060 }, { "grad_norm": 0.19702385365962982, "learning_rate": 3.60202789376732e-05, "loss": 0.008, "step": 61070 }, { "loss_action": 0.007006049156188965, "loss_total": 0.007006049156188965, "step": 61070 }, { "grad_norm": 0.24499478936195374, "learning_rate": 3.6004404437698036e-05, "loss": 0.008, "step": 61080 }, { "loss_action": 0.008500088937580585, "loss_total": 0.008500088937580585, "step": 61080 }, { "grad_norm": 0.1846633106470108, "learning_rate": 3.5988531468260184e-05, "loss": 0.0078, "step": 61090 }, { "loss_action": 0.006840773392468691, "loss_total": 0.006840773392468691, "step": 61090 }, { "grad_norm": 0.21211130917072296, "learning_rate": 3.597266003109546e-05, "loss": 0.0072, "step": 61100 }, { "loss_action": 0.007232737261801958, "loss_total": 0.007232737261801958, "step": 61100 }, { "grad_norm": 0.2463761866092682, "learning_rate": 3.5956790127939557e-05, "loss": 0.0081, "step": 61110 }, { "loss_action": 0.008382955566048622, "loss_total": 0.008382955566048622, "step": 61110 }, { "grad_norm": 0.34722626209259033, "learning_rate": 3.594092176052796e-05, "loss": 0.0095, "step": 61120 }, { "loss_action": 0.006160525139421225, "loss_total": 0.006160525139421225, "step": 61120 }, { "grad_norm": 0.1741091012954712, "learning_rate": 3.592505493059603e-05, "loss": 0.0091, "step": 61130 }, { "loss_action": 0.005511612165719271, "loss_total": 0.005511612165719271, "step": 61130 }, { "grad_norm": 0.2043551802635193, "learning_rate": 3.5909189639878905e-05, "loss": 0.0074, "step": 61140 }, { "loss_action": 0.006034203805029392, "loss_total": 0.006034203805029392, "step": 61140 }, { "grad_norm": 0.22963249683380127, "learning_rate": 3.5893325890111626e-05, "loss": 0.0073, "step": 61150 }, { "loss_action": 0.012294091284275055, "loss_total": 0.012294091284275055, "step": 61150 }, { "grad_norm": 0.22785872220993042, "learning_rate": 3.5877463683029034e-05, "loss": 0.0093, "step": 61160 }, { "loss_action": 0.006681203376501799, "loss_total": 0.006681203376501799, "step": 61160 }, { "grad_norm": 0.20969896018505096, "learning_rate": 3.586160302036578e-05, "loss": 0.009, "step": 61170 }, { "loss_action": 0.007909405045211315, "loss_total": 0.007909405045211315, "step": 61170 }, { "grad_norm": 0.2294136881828308, "learning_rate": 3.584574390385636e-05, "loss": 0.01, "step": 61180 }, { "loss_action": 0.00708320178091526, "loss_total": 0.00708320178091526, "step": 61180 }, { "grad_norm": 0.35938769578933716, "learning_rate": 3.582988633523511e-05, "loss": 0.0085, "step": 61190 }, { "loss_action": 0.0076941740699112415, "loss_total": 0.0076941740699112415, "step": 61190 }, { "grad_norm": 0.23678621649742126, "learning_rate": 3.581403031623616e-05, "loss": 0.0077, "step": 61200 }, { "loss_action": 0.00682933209463954, "loss_total": 0.00682933209463954, "step": 61200 }, { "grad_norm": 0.24053263664245605, "learning_rate": 3.579817584859354e-05, "loss": 0.0082, "step": 61210 }, { "loss_action": 0.007348739542067051, "loss_total": 0.007348739542067051, "step": 61210 }, { "grad_norm": 0.23125766217708588, "learning_rate": 3.578232293404107e-05, "loss": 0.0079, "step": 61220 }, { "loss_action": 0.009594245813786983, "loss_total": 0.009594245813786983, "step": 61220 }, { "grad_norm": 0.20061632990837097, "learning_rate": 3.5766471574312385e-05, "loss": 0.0076, "step": 61230 }, { "loss_action": 0.00800799299031496, "loss_total": 0.00800799299031496, "step": 61230 }, { "grad_norm": 0.26477983593940735, "learning_rate": 3.5750621771140964e-05, "loss": 0.0076, "step": 61240 }, { "loss_action": 0.012762618251144886, "loss_total": 0.012762618251144886, "step": 61240 }, { "grad_norm": 0.21415242552757263, "learning_rate": 3.5734773526260115e-05, "loss": 0.0094, "step": 61250 }, { "loss_action": 0.008664515800774097, "loss_total": 0.008664515800774097, "step": 61250 }, { "grad_norm": 0.22613921761512756, "learning_rate": 3.5718926841402996e-05, "loss": 0.008, "step": 61260 }, { "loss_action": 0.007544563151896, "loss_total": 0.007544563151896, "step": 61260 }, { "grad_norm": 0.292664498090744, "learning_rate": 3.5703081718302555e-05, "loss": 0.0089, "step": 61270 }, { "loss_action": 0.00801208894699812, "loss_total": 0.00801208894699812, "step": 61270 }, { "grad_norm": 0.20305319130420685, "learning_rate": 3.568723815869162e-05, "loss": 0.0086, "step": 61280 }, { "loss_action": 0.009204582311213017, "loss_total": 0.009204582311213017, "step": 61280 }, { "grad_norm": 0.22038277983665466, "learning_rate": 3.5671396164302777e-05, "loss": 0.0102, "step": 61290 }, { "loss_action": 0.013263452798128128, "loss_total": 0.013263452798128128, "step": 61290 }, { "grad_norm": 0.19892477989196777, "learning_rate": 3.565555573686853e-05, "loss": 0.0093, "step": 61300 }, { "loss_action": 0.008123908191919327, "loss_total": 0.008123908191919327, "step": 61300 }, { "grad_norm": 0.2551291882991791, "learning_rate": 3.563971687812113e-05, "loss": 0.0097, "step": 61310 }, { "loss_action": 0.011254463344812393, "loss_total": 0.011254463344812393, "step": 61310 }, { "grad_norm": 0.21731093525886536, "learning_rate": 3.5623879589792706e-05, "loss": 0.0089, "step": 61320 }, { "loss_action": 0.018087781965732574, "loss_total": 0.018087781965732574, "step": 61320 }, { "grad_norm": 0.25314098596572876, "learning_rate": 3.5608043873615185e-05, "loss": 0.01, "step": 61330 }, { "loss_action": 0.009020684286952019, "loss_total": 0.009020684286952019, "step": 61330 }, { "grad_norm": 0.17013069987297058, "learning_rate": 3.559220973132035e-05, "loss": 0.0083, "step": 61340 }, { "loss_action": 0.008132528513669968, "loss_total": 0.008132528513669968, "step": 61340 }, { "grad_norm": 0.23209576308727264, "learning_rate": 3.557637716463981e-05, "loss": 0.0083, "step": 61350 }, { "loss_action": 0.007441423367708921, "loss_total": 0.007441423367708921, "step": 61350 }, { "grad_norm": 0.20410719513893127, "learning_rate": 3.556054617530497e-05, "loss": 0.0073, "step": 61360 }, { "loss_action": 0.0068372199311852455, "loss_total": 0.0068372199311852455, "step": 61360 }, { "grad_norm": 0.22283509373664856, "learning_rate": 3.5544716765047106e-05, "loss": 0.0074, "step": 61370 }, { "loss_action": 0.01074845902621746, "loss_total": 0.01074845902621746, "step": 61370 }, { "grad_norm": 0.3837948739528656, "learning_rate": 3.5528888935597274e-05, "loss": 0.0085, "step": 61380 }, { "loss_action": 0.007944554090499878, "loss_total": 0.007944554090499878, "step": 61380 }, { "grad_norm": 0.18598757684230804, "learning_rate": 3.551306268868636e-05, "loss": 0.0088, "step": 61390 }, { "loss_action": 0.006759013514965773, "loss_total": 0.006759013514965773, "step": 61390 }, { "grad_norm": 0.2607264816761017, "learning_rate": 3.5497238026045166e-05, "loss": 0.0075, "step": 61400 }, { "loss_action": 0.006972133181989193, "loss_total": 0.006972133181989193, "step": 61400 }, { "grad_norm": 0.2522670030593872, "learning_rate": 3.548141494940421e-05, "loss": 0.0085, "step": 61410 }, { "loss_action": 0.007653724402189255, "loss_total": 0.007653724402189255, "step": 61410 }, { "grad_norm": 0.23783820867538452, "learning_rate": 3.546559346049388e-05, "loss": 0.009, "step": 61420 }, { "loss_action": 0.008749539032578468, "loss_total": 0.008749539032578468, "step": 61420 }, { "grad_norm": 0.22453537583351135, "learning_rate": 3.544977356104441e-05, "loss": 0.0082, "step": 61430 }, { "loss_action": 0.006964287720620632, "loss_total": 0.006964287720620632, "step": 61430 }, { "grad_norm": 0.2666766941547394, "learning_rate": 3.543395525278582e-05, "loss": 0.0075, "step": 61440 }, { "loss_action": 0.011059128679335117, "loss_total": 0.011059128679335117, "step": 61440 }, { "grad_norm": 0.18990664184093475, "learning_rate": 3.5418138537447985e-05, "loss": 0.008, "step": 61450 }, { "loss_action": 0.006159135606139898, "loss_total": 0.006159135606139898, "step": 61450 }, { "grad_norm": 0.1950889676809311, "learning_rate": 3.5402323416760574e-05, "loss": 0.0094, "step": 61460 }, { "loss_action": 0.00682707317173481, "loss_total": 0.00682707317173481, "step": 61460 }, { "grad_norm": 0.18325018882751465, "learning_rate": 3.538650989245316e-05, "loss": 0.0088, "step": 61470 }, { "loss_action": 0.011298696510493755, "loss_total": 0.011298696510493755, "step": 61470 }, { "grad_norm": 0.2087426483631134, "learning_rate": 3.537069796625504e-05, "loss": 0.0085, "step": 61480 }, { "loss_action": 0.006234135013073683, "loss_total": 0.006234135013073683, "step": 61480 }, { "grad_norm": 0.21091577410697937, "learning_rate": 3.53548876398954e-05, "loss": 0.0083, "step": 61490 }, { "loss_action": 0.008794189430773258, "loss_total": 0.008794189430773258, "step": 61490 }, { "grad_norm": 0.21170252561569214, "learning_rate": 3.5339078915103214e-05, "loss": 0.0082, "step": 61500 }, { "loss_action": 0.011076672002673149, "loss_total": 0.011076672002673149, "step": 61500 }, { "grad_norm": 0.19604472815990448, "learning_rate": 3.532327179360733e-05, "loss": 0.01, "step": 61510 }, { "loss_action": 0.009074009954929352, "loss_total": 0.009074009954929352, "step": 61510 }, { "grad_norm": 0.22129519283771515, "learning_rate": 3.530746627713636e-05, "loss": 0.008, "step": 61520 }, { "loss_action": 0.006412866059690714, "loss_total": 0.006412866059690714, "step": 61520 }, { "grad_norm": 0.1815652847290039, "learning_rate": 3.5291662367418805e-05, "loss": 0.0087, "step": 61530 }, { "loss_action": 0.004850104451179504, "loss_total": 0.004850104451179504, "step": 61530 }, { "grad_norm": 0.2483288049697876, "learning_rate": 3.527586006618293e-05, "loss": 0.0083, "step": 61540 }, { "loss_action": 0.006010936573147774, "loss_total": 0.006010936573147774, "step": 61540 }, { "grad_norm": 0.18992190062999725, "learning_rate": 3.526005937515687e-05, "loss": 0.0077, "step": 61550 }, { "loss_action": 0.006947329267859459, "loss_total": 0.006947329267859459, "step": 61550 }, { "grad_norm": 0.20361293852329254, "learning_rate": 3.524426029606856e-05, "loss": 0.0086, "step": 61560 }, { "loss_action": 0.009789328090846539, "loss_total": 0.009789328090846539, "step": 61560 }, { "grad_norm": 0.20204561948776245, "learning_rate": 3.5228462830645746e-05, "loss": 0.0087, "step": 61570 }, { "loss_action": 0.008061391301453114, "loss_total": 0.008061391301453114, "step": 61570 }, { "grad_norm": 0.22342534363269806, "learning_rate": 3.5212666980616036e-05, "loss": 0.0086, "step": 61580 }, { "loss_action": 0.005291646346449852, "loss_total": 0.005291646346449852, "step": 61580 }, { "grad_norm": 0.19600196182727814, "learning_rate": 3.519687274770681e-05, "loss": 0.008, "step": 61590 }, { "loss_action": 0.0075148968026041985, "loss_total": 0.0075148968026041985, "step": 61590 }, { "grad_norm": 0.2534274756908417, "learning_rate": 3.518108013364535e-05, "loss": 0.0086, "step": 61600 }, { "loss_action": 0.00870897714048624, "loss_total": 0.00870897714048624, "step": 61600 }, { "grad_norm": 0.22966642677783966, "learning_rate": 3.516528914015868e-05, "loss": 0.0081, "step": 61610 }, { "loss_action": 0.010310613550245762, "loss_total": 0.010310613550245762, "step": 61610 }, { "grad_norm": 0.20011001825332642, "learning_rate": 3.5149499768973694e-05, "loss": 0.0078, "step": 61620 }, { "loss_action": 0.007193457335233688, "loss_total": 0.007193457335233688, "step": 61620 }, { "grad_norm": 0.176643967628479, "learning_rate": 3.513371202181708e-05, "loss": 0.0081, "step": 61630 }, { "loss_action": 0.010688739828765392, "loss_total": 0.010688739828765392, "step": 61630 }, { "grad_norm": 0.20236772298812866, "learning_rate": 3.511792590041537e-05, "loss": 0.0094, "step": 61640 }, { "loss_action": 0.007277449127286673, "loss_total": 0.007277449127286673, "step": 61640 }, { "grad_norm": 0.213086798787117, "learning_rate": 3.510214140649488e-05, "loss": 0.0072, "step": 61650 }, { "loss_action": 0.009518895298242569, "loss_total": 0.009518895298242569, "step": 61650 }, { "grad_norm": 0.24152126908302307, "learning_rate": 3.508635854178184e-05, "loss": 0.0079, "step": 61660 }, { "loss_action": 0.00823750626295805, "loss_total": 0.00823750626295805, "step": 61660 }, { "grad_norm": 0.15217739343643188, "learning_rate": 3.50705773080022e-05, "loss": 0.0086, "step": 61670 }, { "loss_action": 0.007943409495055676, "loss_total": 0.007943409495055676, "step": 61670 }, { "grad_norm": 0.23932576179504395, "learning_rate": 3.505479770688178e-05, "loss": 0.0078, "step": 61680 }, { "loss_action": 0.008730875328183174, "loss_total": 0.008730875328183174, "step": 61680 }, { "grad_norm": 0.17026083171367645, "learning_rate": 3.503901974014622e-05, "loss": 0.0078, "step": 61690 }, { "loss_action": 0.008994859643280506, "loss_total": 0.008994859643280506, "step": 61690 }, { "grad_norm": 0.20131537318229675, "learning_rate": 3.502324340952095e-05, "loss": 0.0086, "step": 61700 }, { "loss_action": 0.010980283841490746, "loss_total": 0.010980283841490746, "step": 61700 }, { "grad_norm": 0.17394287884235382, "learning_rate": 3.500746871673126e-05, "loss": 0.0076, "step": 61710 }, { "loss_action": 0.009355735965073109, "loss_total": 0.009355735965073109, "step": 61710 }, { "grad_norm": 0.1632338911294937, "learning_rate": 3.499169566350227e-05, "loss": 0.0073, "step": 61720 }, { "loss_action": 0.009348329156637192, "loss_total": 0.009348329156637192, "step": 61720 }, { "grad_norm": 0.19865572452545166, "learning_rate": 3.4975924251558876e-05, "loss": 0.0078, "step": 61730 }, { "loss_action": 0.007128977216780186, "loss_total": 0.007128977216780186, "step": 61730 }, { "grad_norm": 0.17547956109046936, "learning_rate": 3.496015448262582e-05, "loss": 0.0085, "step": 61740 }, { "loss_action": 0.006549382116645575, "loss_total": 0.006549382116645575, "step": 61740 }, { "grad_norm": 0.16201026737689972, "learning_rate": 3.494438635842764e-05, "loss": 0.007, "step": 61750 }, { "loss_action": 0.008052540011703968, "loss_total": 0.008052540011703968, "step": 61750 }, { "grad_norm": 0.19682106375694275, "learning_rate": 3.492861988068874e-05, "loss": 0.0081, "step": 61760 }, { "loss_action": 0.00877354945987463, "loss_total": 0.00877354945987463, "step": 61760 }, { "grad_norm": 0.18962837755680084, "learning_rate": 3.491285505113332e-05, "loss": 0.0074, "step": 61770 }, { "loss_action": 0.00772663950920105, "loss_total": 0.00772663950920105, "step": 61770 }, { "grad_norm": 0.2192486673593521, "learning_rate": 3.4897091871485376e-05, "loss": 0.0076, "step": 61780 }, { "loss_action": 0.00834382139146328, "loss_total": 0.00834382139146328, "step": 61780 }, { "grad_norm": 0.20239318907260895, "learning_rate": 3.488133034346875e-05, "loss": 0.0083, "step": 61790 }, { "loss_action": 0.0068254293873906136, "loss_total": 0.0068254293873906136, "step": 61790 }, { "grad_norm": 0.1962001621723175, "learning_rate": 3.486557046880713e-05, "loss": 0.0089, "step": 61800 }, { "loss_action": 0.007804590743035078, "loss_total": 0.007804590743035078, "step": 61800 }, { "grad_norm": 0.19887924194335938, "learning_rate": 3.484981224922395e-05, "loss": 0.0086, "step": 61810 }, { "loss_action": 0.015144020318984985, "loss_total": 0.015144020318984985, "step": 61810 }, { "grad_norm": 0.302744597196579, "learning_rate": 3.4834055686442544e-05, "loss": 0.0103, "step": 61820 }, { "loss_action": 0.0096100689843297, "loss_total": 0.0096100689843297, "step": 61820 }, { "grad_norm": 0.1872500628232956, "learning_rate": 3.4818300782186e-05, "loss": 0.008, "step": 61830 }, { "loss_action": 0.0074072605930268764, "loss_total": 0.0074072605930268764, "step": 61830 }, { "grad_norm": 0.27564409375190735, "learning_rate": 3.4802547538177236e-05, "loss": 0.0078, "step": 61840 }, { "loss_action": 0.016753142699599266, "loss_total": 0.016753142699599266, "step": 61840 }, { "grad_norm": 0.2528499364852905, "learning_rate": 3.478679595613905e-05, "loss": 0.0084, "step": 61850 }, { "loss_action": 0.006282177288085222, "loss_total": 0.006282177288085222, "step": 61850 }, { "grad_norm": 0.20967413485050201, "learning_rate": 3.4771046037793975e-05, "loss": 0.0074, "step": 61860 }, { "loss_action": 0.0068940590135753155, "loss_total": 0.0068940590135753155, "step": 61860 }, { "grad_norm": 0.17554815113544464, "learning_rate": 3.4755297784864416e-05, "loss": 0.0076, "step": 61870 }, { "loss_action": 0.007402077782899141, "loss_total": 0.007402077782899141, "step": 61870 }, { "grad_norm": 0.2410787045955658, "learning_rate": 3.473955119907257e-05, "loss": 0.0091, "step": 61880 }, { "loss_action": 0.009878074750304222, "loss_total": 0.009878074750304222, "step": 61880 }, { "grad_norm": 0.23874972760677338, "learning_rate": 3.472380628214046e-05, "loss": 0.0082, "step": 61890 }, { "loss_action": 0.009364347904920578, "loss_total": 0.009364347904920578, "step": 61890 }, { "grad_norm": 0.2179722636938095, "learning_rate": 3.4708063035789906e-05, "loss": 0.0086, "step": 61900 }, { "loss_action": 0.005811401642858982, "loss_total": 0.005811401642858982, "step": 61900 }, { "grad_norm": 0.20594917237758636, "learning_rate": 3.4692321461742614e-05, "loss": 0.0079, "step": 61910 }, { "loss_action": 0.00552122900262475, "loss_total": 0.00552122900262475, "step": 61910 }, { "grad_norm": 0.2559625208377838, "learning_rate": 3.4676581561720023e-05, "loss": 0.0089, "step": 61920 }, { "loss_action": 0.007255495060235262, "loss_total": 0.007255495060235262, "step": 61920 }, { "grad_norm": 0.23266305029392242, "learning_rate": 3.466084333744344e-05, "loss": 0.0083, "step": 61930 }, { "loss_action": 0.008570448495447636, "loss_total": 0.008570448495447636, "step": 61930 }, { "grad_norm": 0.2210318148136139, "learning_rate": 3.4645106790633964e-05, "loss": 0.0071, "step": 61940 }, { "loss_action": 0.00566501822322607, "loss_total": 0.00566501822322607, "step": 61940 }, { "grad_norm": 0.22194528579711914, "learning_rate": 3.4629371923012526e-05, "loss": 0.0073, "step": 61950 }, { "loss_action": 0.006388627924025059, "loss_total": 0.006388627924025059, "step": 61950 }, { "grad_norm": 0.2063751220703125, "learning_rate": 3.4613638736299856e-05, "loss": 0.0079, "step": 61960 }, { "loss_action": 0.010120314545929432, "loss_total": 0.010120314545929432, "step": 61960 }, { "grad_norm": 0.17658372223377228, "learning_rate": 3.459790723221652e-05, "loss": 0.0081, "step": 61970 }, { "loss_action": 0.014534167014062405, "loss_total": 0.014534167014062405, "step": 61970 }, { "grad_norm": 0.268271803855896, "learning_rate": 3.45821774124829e-05, "loss": 0.0086, "step": 61980 }, { "loss_action": 0.005843461491167545, "loss_total": 0.005843461491167545, "step": 61980 }, { "grad_norm": 0.19481420516967773, "learning_rate": 3.456644927881918e-05, "loss": 0.0077, "step": 61990 }, { "loss_action": 0.006105788983404636, "loss_total": 0.006105788983404636, "step": 61990 }, { "grad_norm": 0.20673693716526031, "learning_rate": 3.4550722832945354e-05, "loss": 0.0087, "step": 62000 }, { "loss_action": 0.007341165095567703, "loss_total": 0.007341165095567703, "step": 62000 }, { "grad_norm": 0.18604594469070435, "learning_rate": 3.453499807658126e-05, "loss": 0.0081, "step": 62010 }, { "loss_action": 0.007637482136487961, "loss_total": 0.007637482136487961, "step": 62010 }, { "grad_norm": 0.20639540255069733, "learning_rate": 3.451927501144653e-05, "loss": 0.0083, "step": 62020 }, { "loss_action": 0.008404060266911983, "loss_total": 0.008404060266911983, "step": 62020 }, { "grad_norm": 0.17428907752037048, "learning_rate": 3.450355363926059e-05, "loss": 0.0078, "step": 62030 }, { "loss_action": 0.006455280352383852, "loss_total": 0.006455280352383852, "step": 62030 }, { "grad_norm": 0.18962079286575317, "learning_rate": 3.448783396174273e-05, "loss": 0.0077, "step": 62040 }, { "loss_action": 0.011925927363336086, "loss_total": 0.011925927363336086, "step": 62040 }, { "grad_norm": 0.185380220413208, "learning_rate": 3.4472115980612034e-05, "loss": 0.0087, "step": 62050 }, { "loss_action": 0.008238508366048336, "loss_total": 0.008238508366048336, "step": 62050 }, { "grad_norm": 0.21172967553138733, "learning_rate": 3.4456399697587396e-05, "loss": 0.0095, "step": 62060 }, { "loss_action": 0.00804073829203844, "loss_total": 0.00804073829203844, "step": 62060 }, { "grad_norm": 0.21198125183582306, "learning_rate": 3.4440685114387506e-05, "loss": 0.0112, "step": 62070 }, { "loss_action": 0.00855458527803421, "loss_total": 0.00855458527803421, "step": 62070 }, { "grad_norm": 0.19631578028202057, "learning_rate": 3.442497223273091e-05, "loss": 0.0079, "step": 62080 }, { "loss_action": 0.008401332423090935, "loss_total": 0.008401332423090935, "step": 62080 }, { "grad_norm": 0.24736440181732178, "learning_rate": 3.4409261054335926e-05, "loss": 0.008, "step": 62090 }, { "loss_action": 0.008170352317392826, "loss_total": 0.008170352317392826, "step": 62090 }, { "grad_norm": 0.2209741622209549, "learning_rate": 3.439355158092069e-05, "loss": 0.0085, "step": 62100 }, { "loss_action": 0.00962688960134983, "loss_total": 0.00962688960134983, "step": 62100 }, { "grad_norm": 0.20437636971473694, "learning_rate": 3.437784381420322e-05, "loss": 0.009, "step": 62110 }, { "loss_action": 0.008729108609259129, "loss_total": 0.008729108609259129, "step": 62110 }, { "grad_norm": 0.2204590141773224, "learning_rate": 3.436213775590126e-05, "loss": 0.0078, "step": 62120 }, { "loss_action": 0.010394657030701637, "loss_total": 0.010394657030701637, "step": 62120 }, { "grad_norm": 0.23055720329284668, "learning_rate": 3.4346433407732405e-05, "loss": 0.0081, "step": 62130 }, { "loss_action": 0.010129569098353386, "loss_total": 0.010129569098353386, "step": 62130 }, { "grad_norm": 0.18382586538791656, "learning_rate": 3.433073077141405e-05, "loss": 0.0084, "step": 62140 }, { "loss_action": 0.006890199612826109, "loss_total": 0.006890199612826109, "step": 62140 }, { "grad_norm": 0.18749357759952545, "learning_rate": 3.431502984866343e-05, "loss": 0.0078, "step": 62150 }, { "loss_action": 0.010075354017317295, "loss_total": 0.010075354017317295, "step": 62150 }, { "grad_norm": 0.17924457788467407, "learning_rate": 3.429933064119753e-05, "loss": 0.0079, "step": 62160 }, { "loss_action": 0.010431098751723766, "loss_total": 0.010431098751723766, "step": 62160 }, { "grad_norm": 0.14653511345386505, "learning_rate": 3.4283633150733255e-05, "loss": 0.0084, "step": 62170 }, { "loss_action": 0.009588634595274925, "loss_total": 0.009588634595274925, "step": 62170 }, { "grad_norm": 0.20058341324329376, "learning_rate": 3.4267937378987225e-05, "loss": 0.0082, "step": 62180 }, { "loss_action": 0.009708055295050144, "loss_total": 0.009708055295050144, "step": 62180 }, { "grad_norm": 0.27008774876594543, "learning_rate": 3.425224332767592e-05, "loss": 0.0081, "step": 62190 }, { "loss_action": 0.011215428821742535, "loss_total": 0.011215428821742535, "step": 62190 }, { "grad_norm": 0.23243466019630432, "learning_rate": 3.4236550998515595e-05, "loss": 0.0095, "step": 62200 }, { "loss_action": 0.008512934669852257, "loss_total": 0.008512934669852257, "step": 62200 }, { "grad_norm": 0.2228696495294571, "learning_rate": 3.422086039322235e-05, "loss": 0.0081, "step": 62210 }, { "loss_action": 0.006559170316904783, "loss_total": 0.006559170316904783, "step": 62210 }, { "grad_norm": 0.18360602855682373, "learning_rate": 3.420517151351209e-05, "loss": 0.0076, "step": 62220 }, { "loss_action": 0.010056907311081886, "loss_total": 0.010056907311081886, "step": 62220 }, { "grad_norm": 0.2591336965560913, "learning_rate": 3.418948436110053e-05, "loss": 0.0093, "step": 62230 }, { "loss_action": 0.0077768415212631226, "loss_total": 0.0077768415212631226, "step": 62230 }, { "grad_norm": 0.21583013236522675, "learning_rate": 3.417379893770319e-05, "loss": 0.0084, "step": 62240 }, { "loss_action": 0.009749193675816059, "loss_total": 0.009749193675816059, "step": 62240 }, { "grad_norm": 0.22936196625232697, "learning_rate": 3.41581152450354e-05, "loss": 0.0085, "step": 62250 }, { "loss_action": 0.012559364549815655, "loss_total": 0.012559364549815655, "step": 62250 }, { "grad_norm": 0.2795730531215668, "learning_rate": 3.414243328481231e-05, "loss": 0.0084, "step": 62260 }, { "loss_action": 0.006855624727904797, "loss_total": 0.006855624727904797, "step": 62260 }, { "grad_norm": 0.270681232213974, "learning_rate": 3.412675305874888e-05, "loss": 0.0093, "step": 62270 }, { "loss_action": 0.01053980179131031, "loss_total": 0.01053980179131031, "step": 62270 }, { "grad_norm": 0.2107156366109848, "learning_rate": 3.4111074568559876e-05, "loss": 0.0086, "step": 62280 }, { "loss_action": 0.012780592776834965, "loss_total": 0.012780592776834965, "step": 62280 }, { "grad_norm": 0.21048472821712494, "learning_rate": 3.4095397815959846e-05, "loss": 0.0081, "step": 62290 }, { "loss_action": 0.006829801481217146, "loss_total": 0.006829801481217146, "step": 62290 }, { "grad_norm": 0.18332964181900024, "learning_rate": 3.407972280266322e-05, "loss": 0.0075, "step": 62300 }, { "loss_action": 0.006547624245285988, "loss_total": 0.006547624245285988, "step": 62300 }, { "grad_norm": 0.18588872253894806, "learning_rate": 3.4064049530384166e-05, "loss": 0.0077, "step": 62310 }, { "loss_action": 0.00679499888792634, "loss_total": 0.00679499888792634, "step": 62310 }, { "grad_norm": 0.2344047874212265, "learning_rate": 3.40483780008367e-05, "loss": 0.0079, "step": 62320 }, { "loss_action": 0.006461523938924074, "loss_total": 0.006461523938924074, "step": 62320 }, { "grad_norm": 0.2524661123752594, "learning_rate": 3.4032708215734635e-05, "loss": 0.0078, "step": 62330 }, { "loss_action": 0.006704944185912609, "loss_total": 0.006704944185912609, "step": 62330 }, { "grad_norm": 0.21101585030555725, "learning_rate": 3.4017040176791584e-05, "loss": 0.0069, "step": 62340 }, { "loss_action": 0.004700184799730778, "loss_total": 0.004700184799730778, "step": 62340 }, { "grad_norm": 0.21641016006469727, "learning_rate": 3.4001373885720976e-05, "loss": 0.0086, "step": 62350 }, { "loss_action": 0.009211692959070206, "loss_total": 0.009211692959070206, "step": 62350 }, { "grad_norm": 0.15912015736103058, "learning_rate": 3.398570934423608e-05, "loss": 0.0072, "step": 62360 }, { "loss_action": 0.011204623617231846, "loss_total": 0.011204623617231846, "step": 62360 }, { "grad_norm": 0.24999956786632538, "learning_rate": 3.397004655404994e-05, "loss": 0.0084, "step": 62370 }, { "loss_action": 0.008909981697797775, "loss_total": 0.008909981697797775, "step": 62370 }, { "grad_norm": 0.1346122771501541, "learning_rate": 3.395438551687541e-05, "loss": 0.009, "step": 62380 }, { "loss_action": 0.008196042850613594, "loss_total": 0.008196042850613594, "step": 62380 }, { "grad_norm": 0.24017752707004547, "learning_rate": 3.393872623442515e-05, "loss": 0.0087, "step": 62390 }, { "loss_action": 0.006372553762048483, "loss_total": 0.006372553762048483, "step": 62390 }, { "grad_norm": 0.17033527791500092, "learning_rate": 3.392306870841164e-05, "loss": 0.0083, "step": 62400 }, { "loss_action": 0.006999612785875797, "loss_total": 0.006999612785875797, "step": 62400 }, { "grad_norm": 0.20169572532176971, "learning_rate": 3.390741294054715e-05, "loss": 0.0073, "step": 62410 }, { "loss_action": 0.008491076529026031, "loss_total": 0.008491076529026031, "step": 62410 }, { "grad_norm": 0.23416122794151306, "learning_rate": 3.38917589325438e-05, "loss": 0.0081, "step": 62420 }, { "loss_action": 0.0076893470250070095, "loss_total": 0.0076893470250070095, "step": 62420 }, { "grad_norm": 0.24144555628299713, "learning_rate": 3.387610668611349e-05, "loss": 0.0073, "step": 62430 }, { "loss_action": 0.005707892589271069, "loss_total": 0.005707892589271069, "step": 62430 }, { "grad_norm": 0.20422889292240143, "learning_rate": 3.38604562029679e-05, "loss": 0.0073, "step": 62440 }, { "loss_action": 0.004640855360776186, "loss_total": 0.004640855360776186, "step": 62440 }, { "grad_norm": 0.20026685297489166, "learning_rate": 3.384480748481855e-05, "loss": 0.0069, "step": 62450 }, { "loss_action": 0.006955351214855909, "loss_total": 0.006955351214855909, "step": 62450 }, { "grad_norm": 0.2306339591741562, "learning_rate": 3.382916053337676e-05, "loss": 0.0077, "step": 62460 }, { "loss_action": 0.008644011802971363, "loss_total": 0.008644011802971363, "step": 62460 }, { "grad_norm": 0.21536841988563538, "learning_rate": 3.381351535035366e-05, "loss": 0.0082, "step": 62470 }, { "loss_action": 0.008087005466222763, "loss_total": 0.008087005466222763, "step": 62470 }, { "grad_norm": 0.18261505663394928, "learning_rate": 3.379787193746019e-05, "loss": 0.0079, "step": 62480 }, { "loss_action": 0.0063048009760677814, "loss_total": 0.0063048009760677814, "step": 62480 }, { "grad_norm": 0.16486075520515442, "learning_rate": 3.378223029640709e-05, "loss": 0.0071, "step": 62490 }, { "loss_action": 0.0074563962407410145, "loss_total": 0.0074563962407410145, "step": 62490 }, { "grad_norm": 0.25085559487342834, "learning_rate": 3.376659042890489e-05, "loss": 0.0089, "step": 62500 }, { "loss_action": 0.007714224047958851, "loss_total": 0.007714224047958851, "step": 62500 }, { "grad_norm": 0.25384363532066345, "learning_rate": 3.375095233666397e-05, "loss": 0.008, "step": 62510 }, { "loss_action": 0.007061436772346497, "loss_total": 0.007061436772346497, "step": 62510 }, { "grad_norm": 0.18156558275222778, "learning_rate": 3.373531602139447e-05, "loss": 0.0071, "step": 62520 }, { "loss_action": 0.008020969107747078, "loss_total": 0.008020969107747078, "step": 62520 }, { "grad_norm": 0.16742350161075592, "learning_rate": 3.371968148480635e-05, "loss": 0.0067, "step": 62530 }, { "loss_action": 0.007424656767398119, "loss_total": 0.007424656767398119, "step": 62530 }, { "grad_norm": 0.18601058423519135, "learning_rate": 3.370404872860937e-05, "loss": 0.0071, "step": 62540 }, { "loss_action": 0.014628703705966473, "loss_total": 0.014628703705966473, "step": 62540 }, { "grad_norm": 0.2200208306312561, "learning_rate": 3.3688417754513145e-05, "loss": 0.0082, "step": 62550 }, { "loss_action": 0.007647323422133923, "loss_total": 0.007647323422133923, "step": 62550 }, { "grad_norm": 0.17937703430652618, "learning_rate": 3.367278856422703e-05, "loss": 0.0091, "step": 62560 }, { "loss_action": 0.0067893993109464645, "loss_total": 0.0067893993109464645, "step": 62560 }, { "grad_norm": 0.18718385696411133, "learning_rate": 3.365716115946021e-05, "loss": 0.0085, "step": 62570 }, { "loss_action": 0.007779087405651808, "loss_total": 0.007779087405651808, "step": 62570 }, { "grad_norm": 0.21776416897773743, "learning_rate": 3.3641535541921666e-05, "loss": 0.0077, "step": 62580 }, { "loss_action": 0.006402226630598307, "loss_total": 0.006402226630598307, "step": 62580 }, { "grad_norm": 0.18932822346687317, "learning_rate": 3.36259117133202e-05, "loss": 0.0069, "step": 62590 }, { "loss_action": 0.006020727101713419, "loss_total": 0.006020727101713419, "step": 62590 }, { "grad_norm": 0.20605981349945068, "learning_rate": 3.36102896753644e-05, "loss": 0.0085, "step": 62600 }, { "loss_action": 0.00626543490216136, "loss_total": 0.00626543490216136, "step": 62600 }, { "grad_norm": 0.2046467810869217, "learning_rate": 3.35946694297627e-05, "loss": 0.0082, "step": 62610 }, { "loss_action": 0.008097260259091854, "loss_total": 0.008097260259091854, "step": 62610 }, { "grad_norm": 0.22169452905654907, "learning_rate": 3.357905097822328e-05, "loss": 0.0078, "step": 62620 }, { "loss_action": 0.009949765168130398, "loss_total": 0.009949765168130398, "step": 62620 }, { "grad_norm": 0.15232427418231964, "learning_rate": 3.356343432245416e-05, "loss": 0.0077, "step": 62630 }, { "loss_action": 0.006982487626373768, "loss_total": 0.006982487626373768, "step": 62630 }, { "grad_norm": 0.19896455109119415, "learning_rate": 3.354781946416315e-05, "loss": 0.0092, "step": 62640 }, { "loss_action": 0.008416399359703064, "loss_total": 0.008416399359703064, "step": 62640 }, { "grad_norm": 0.1863224357366562, "learning_rate": 3.3532206405057864e-05, "loss": 0.0088, "step": 62650 }, { "loss_action": 0.005942956078797579, "loss_total": 0.005942956078797579, "step": 62650 }, { "grad_norm": 0.2047051638364792, "learning_rate": 3.351659514684573e-05, "loss": 0.0077, "step": 62660 }, { "loss_action": 0.010563172399997711, "loss_total": 0.010563172399997711, "step": 62660 }, { "grad_norm": 0.22777195274829865, "learning_rate": 3.350098569123395e-05, "loss": 0.0089, "step": 62670 }, { "loss_action": 0.005805034656077623, "loss_total": 0.005805034656077623, "step": 62670 }, { "grad_norm": 0.18279413878917694, "learning_rate": 3.348537803992958e-05, "loss": 0.0072, "step": 62680 }, { "loss_action": 0.010302691720426083, "loss_total": 0.010302691720426083, "step": 62680 }, { "grad_norm": 0.2176218330860138, "learning_rate": 3.346977219463945e-05, "loss": 0.0074, "step": 62690 }, { "loss_action": 0.005003315396606922, "loss_total": 0.005003315396606922, "step": 62690 }, { "grad_norm": 0.185164675116539, "learning_rate": 3.345416815707017e-05, "loss": 0.0075, "step": 62700 }, { "loss_action": 0.005816998891532421, "loss_total": 0.005816998891532421, "step": 62700 }, { "grad_norm": 0.25038713216781616, "learning_rate": 3.3438565928928185e-05, "loss": 0.0074, "step": 62710 }, { "loss_action": 0.0069667440839111805, "loss_total": 0.0069667440839111805, "step": 62710 }, { "grad_norm": 0.262498676776886, "learning_rate": 3.3422965511919736e-05, "loss": 0.0075, "step": 62720 }, { "loss_action": 0.007621739525347948, "loss_total": 0.007621739525347948, "step": 62720 }, { "grad_norm": 0.20445682108402252, "learning_rate": 3.3407366907750846e-05, "loss": 0.0076, "step": 62730 }, { "loss_action": 0.009657390415668488, "loss_total": 0.009657390415668488, "step": 62730 }, { "grad_norm": 0.2237091213464737, "learning_rate": 3.339177011812737e-05, "loss": 0.008, "step": 62740 }, { "loss_action": 0.006319696083664894, "loss_total": 0.006319696083664894, "step": 62740 }, { "grad_norm": 0.21155524253845215, "learning_rate": 3.3376175144754935e-05, "loss": 0.0074, "step": 62750 }, { "loss_action": 0.0066712587140500546, "loss_total": 0.0066712587140500546, "step": 62750 }, { "grad_norm": 0.1657479703426361, "learning_rate": 3.3360581989339004e-05, "loss": 0.0072, "step": 62760 }, { "loss_action": 0.008876245468854904, "loss_total": 0.008876245468854904, "step": 62760 }, { "grad_norm": 0.21331967413425446, "learning_rate": 3.3344990653584804e-05, "loss": 0.0079, "step": 62770 }, { "loss_action": 0.005894181784242392, "loss_total": 0.005894181784242392, "step": 62770 }, { "grad_norm": 0.205058753490448, "learning_rate": 3.332940113919739e-05, "loss": 0.0081, "step": 62780 }, { "loss_action": 0.005394083447754383, "loss_total": 0.005394083447754383, "step": 62780 }, { "grad_norm": 0.22338104248046875, "learning_rate": 3.331381344788161e-05, "loss": 0.0085, "step": 62790 }, { "loss_action": 0.008299370296299458, "loss_total": 0.008299370296299458, "step": 62790 }, { "grad_norm": 0.2259196639060974, "learning_rate": 3.3298227581342076e-05, "loss": 0.0085, "step": 62800 }, { "loss_action": 0.008036850951611996, "loss_total": 0.008036850951611996, "step": 62800 }, { "grad_norm": 0.23881849646568298, "learning_rate": 3.328264354128329e-05, "loss": 0.0086, "step": 62810 }, { "loss_action": 0.009355944581329823, "loss_total": 0.009355944581329823, "step": 62810 }, { "grad_norm": 0.24597887694835663, "learning_rate": 3.3267061329409465e-05, "loss": 0.0074, "step": 62820 }, { "loss_action": 0.00721568800508976, "loss_total": 0.00721568800508976, "step": 62820 }, { "grad_norm": 0.20581583678722382, "learning_rate": 3.325148094742466e-05, "loss": 0.0077, "step": 62830 }, { "loss_action": 0.007082364987581968, "loss_total": 0.007082364987581968, "step": 62830 }, { "grad_norm": 0.2178017795085907, "learning_rate": 3.323590239703271e-05, "loss": 0.0075, "step": 62840 }, { "loss_action": 0.009783596731722355, "loss_total": 0.009783596731722355, "step": 62840 }, { "grad_norm": 0.2064218372106552, "learning_rate": 3.322032567993728e-05, "loss": 0.0072, "step": 62850 }, { "loss_action": 0.007035729940980673, "loss_total": 0.007035729940980673, "step": 62850 }, { "grad_norm": 0.1903470903635025, "learning_rate": 3.3204750797841774e-05, "loss": 0.0087, "step": 62860 }, { "loss_action": 0.01025694701820612, "loss_total": 0.01025694701820612, "step": 62860 }, { "grad_norm": 0.23239848017692566, "learning_rate": 3.31891777524495e-05, "loss": 0.0079, "step": 62870 }, { "loss_action": 0.007938152179121971, "loss_total": 0.007938152179121971, "step": 62870 }, { "grad_norm": 0.250652939081192, "learning_rate": 3.317360654546347e-05, "loss": 0.0089, "step": 62880 }, { "loss_action": 0.007782755419611931, "loss_total": 0.007782755419611931, "step": 62880 }, { "grad_norm": 0.23526468873023987, "learning_rate": 3.3158037178586534e-05, "loss": 0.007, "step": 62890 }, { "loss_action": 0.0060726492665708065, "loss_total": 0.0060726492665708065, "step": 62890 }, { "grad_norm": 0.22083300352096558, "learning_rate": 3.3142469653521316e-05, "loss": 0.0078, "step": 62900 }, { "loss_action": 0.007683489937335253, "loss_total": 0.007683489937335253, "step": 62900 }, { "grad_norm": 0.18524084985256195, "learning_rate": 3.3126903971970284e-05, "loss": 0.0071, "step": 62910 }, { "loss_action": 0.0107344388961792, "loss_total": 0.0107344388961792, "step": 62910 }, { "grad_norm": 0.20873160660266876, "learning_rate": 3.311134013563564e-05, "loss": 0.007, "step": 62920 }, { "loss_action": 0.00780032854527235, "loss_total": 0.00780032854527235, "step": 62920 }, { "grad_norm": 0.23138275742530823, "learning_rate": 3.309577814621947e-05, "loss": 0.0094, "step": 62930 }, { "loss_action": 0.005184225272387266, "loss_total": 0.005184225272387266, "step": 62930 }, { "grad_norm": 0.2169123739004135, "learning_rate": 3.308021800542359e-05, "loss": 0.0074, "step": 62940 }, { "loss_action": 0.0103523014113307, "loss_total": 0.0103523014113307, "step": 62940 }, { "grad_norm": 0.21684393286705017, "learning_rate": 3.306465971494963e-05, "loss": 0.0077, "step": 62950 }, { "loss_action": 0.006233725231140852, "loss_total": 0.006233725231140852, "step": 62950 }, { "grad_norm": 0.21332146227359772, "learning_rate": 3.304910327649901e-05, "loss": 0.0081, "step": 62960 }, { "loss_action": 0.007548895198851824, "loss_total": 0.007548895198851824, "step": 62960 }, { "grad_norm": 0.18586285412311554, "learning_rate": 3.303354869177297e-05, "loss": 0.0072, "step": 62970 }, { "loss_action": 0.005961996503174305, "loss_total": 0.005961996503174305, "step": 62970 }, { "grad_norm": 0.21791240572929382, "learning_rate": 3.301799596247255e-05, "loss": 0.0081, "step": 62980 }, { "loss_action": 0.007105562370270491, "loss_total": 0.007105562370270491, "step": 62980 }, { "grad_norm": 0.2169940322637558, "learning_rate": 3.300244509029854e-05, "loss": 0.0078, "step": 62990 }, { "loss_action": 0.007051670923829079, "loss_total": 0.007051670923829079, "step": 62990 }, { "grad_norm": 0.22210976481437683, "learning_rate": 3.2986896076951585e-05, "loss": 0.0092, "step": 63000 }, { "loss_action": 0.013842795975506306, "loss_total": 0.013842795975506306, "step": 63000 }, { "grad_norm": 0.17389865219593048, "learning_rate": 3.297134892413211e-05, "loss": 0.0087, "step": 63010 }, { "loss_action": 0.005088422447443008, "loss_total": 0.005088422447443008, "step": 63010 }, { "grad_norm": 0.25573018193244934, "learning_rate": 3.295580363354031e-05, "loss": 0.0075, "step": 63020 }, { "loss_action": 0.0074914563447237015, "loss_total": 0.0074914563447237015, "step": 63020 }, { "grad_norm": 0.20018070936203003, "learning_rate": 3.2940260206876194e-05, "loss": 0.0073, "step": 63030 }, { "loss_action": 0.0073575605638325214, "loss_total": 0.0073575605638325214, "step": 63030 }, { "grad_norm": 0.20825830101966858, "learning_rate": 3.292471864583958e-05, "loss": 0.0065, "step": 63040 }, { "loss_action": 0.005044583696871996, "loss_total": 0.005044583696871996, "step": 63040 }, { "grad_norm": 0.15814048051834106, "learning_rate": 3.290917895213004e-05, "loss": 0.0072, "step": 63050 }, { "loss_action": 0.00963348988443613, "loss_total": 0.00963348988443613, "step": 63050 }, { "grad_norm": 0.1399202048778534, "learning_rate": 3.289364112744701e-05, "loss": 0.0072, "step": 63060 }, { "loss_action": 0.006706227082759142, "loss_total": 0.006706227082759142, "step": 63060 }, { "grad_norm": 0.24002468585968018, "learning_rate": 3.287810517348967e-05, "loss": 0.0072, "step": 63070 }, { "loss_action": 0.007095654960721731, "loss_total": 0.007095654960721731, "step": 63070 }, { "grad_norm": 0.2562848627567291, "learning_rate": 3.2862571091957014e-05, "loss": 0.0081, "step": 63080 }, { "loss_action": 0.011235998012125492, "loss_total": 0.011235998012125492, "step": 63080 }, { "grad_norm": 0.20900937914848328, "learning_rate": 3.284703888454781e-05, "loss": 0.0076, "step": 63090 }, { "loss_action": 0.006803182419389486, "loss_total": 0.006803182419389486, "step": 63090 }, { "grad_norm": 0.2292805165052414, "learning_rate": 3.2831508552960646e-05, "loss": 0.0088, "step": 63100 }, { "loss_action": 0.007491819094866514, "loss_total": 0.007491819094866514, "step": 63100 }, { "grad_norm": 0.17194092273712158, "learning_rate": 3.281598009889387e-05, "loss": 0.007, "step": 63110 }, { "loss_action": 0.006796501111239195, "loss_total": 0.006796501111239195, "step": 63110 }, { "grad_norm": 0.16852517426013947, "learning_rate": 3.28004535240457e-05, "loss": 0.0077, "step": 63120 }, { "loss_action": 0.004785850178450346, "loss_total": 0.004785850178450346, "step": 63120 }, { "grad_norm": 0.1695166826248169, "learning_rate": 3.278492883011407e-05, "loss": 0.0077, "step": 63130 }, { "loss_action": 0.008252476342022419, "loss_total": 0.008252476342022419, "step": 63130 }, { "grad_norm": 0.2405659705400467, "learning_rate": 3.276940601879675e-05, "loss": 0.009, "step": 63140 }, { "loss_action": 0.011504764668643475, "loss_total": 0.011504764668643475, "step": 63140 }, { "grad_norm": 0.20129473507404327, "learning_rate": 3.275388509179127e-05, "loss": 0.0088, "step": 63150 }, { "loss_action": 0.008242334239184856, "loss_total": 0.008242334239184856, "step": 63150 }, { "grad_norm": 0.21798425912857056, "learning_rate": 3.2738366050794985e-05, "loss": 0.0076, "step": 63160 }, { "loss_action": 0.010258547030389309, "loss_total": 0.010258547030389309, "step": 63160 }, { "grad_norm": 0.22408674657344818, "learning_rate": 3.2722848897505034e-05, "loss": 0.0081, "step": 63170 }, { "loss_action": 0.013592823408544064, "loss_total": 0.013592823408544064, "step": 63170 }, { "grad_norm": 0.19749149680137634, "learning_rate": 3.2707333633618356e-05, "loss": 0.008, "step": 63180 }, { "loss_action": 0.006793267093598843, "loss_total": 0.006793267093598843, "step": 63180 }, { "grad_norm": 0.18301890790462494, "learning_rate": 3.269182026083167e-05, "loss": 0.0078, "step": 63190 }, { "loss_action": 0.009926563128829002, "loss_total": 0.009926563128829002, "step": 63190 }, { "grad_norm": 0.20892532169818878, "learning_rate": 3.2676308780841516e-05, "loss": 0.0085, "step": 63200 }, { "loss_action": 0.006418630480766296, "loss_total": 0.006418630480766296, "step": 63200 }, { "grad_norm": 0.2129039615392685, "learning_rate": 3.266079919534416e-05, "loss": 0.0081, "step": 63210 }, { "loss_action": 0.006768776103854179, "loss_total": 0.006768776103854179, "step": 63210 }, { "grad_norm": 0.1649988293647766, "learning_rate": 3.264529150603575e-05, "loss": 0.0076, "step": 63220 }, { "loss_action": 0.008351978845894337, "loss_total": 0.008351978845894337, "step": 63220 }, { "grad_norm": 0.21927231550216675, "learning_rate": 3.262978571461217e-05, "loss": 0.009, "step": 63230 }, { "loss_action": 0.0076240128837525845, "loss_total": 0.0076240128837525845, "step": 63230 }, { "grad_norm": 0.22327561676502228, "learning_rate": 3.26142818227691e-05, "loss": 0.0087, "step": 63240 }, { "loss_action": 0.011174917221069336, "loss_total": 0.011174917221069336, "step": 63240 }, { "grad_norm": 0.19285748898983002, "learning_rate": 3.259877983220203e-05, "loss": 0.0083, "step": 63250 }, { "loss_action": 0.008778316900134087, "loss_total": 0.008778316900134087, "step": 63250 }, { "grad_norm": 0.19740627706050873, "learning_rate": 3.2583279744606246e-05, "loss": 0.0072, "step": 63260 }, { "loss_action": 0.0049224551767110825, "loss_total": 0.0049224551767110825, "step": 63260 }, { "grad_norm": 0.17978817224502563, "learning_rate": 3.25677815616768e-05, "loss": 0.0069, "step": 63270 }, { "loss_action": 0.005612081382423639, "loss_total": 0.005612081382423639, "step": 63270 }, { "grad_norm": 0.19279499351978302, "learning_rate": 3.255228528510856e-05, "loss": 0.0075, "step": 63280 }, { "loss_action": 0.005090730264782906, "loss_total": 0.005090730264782906, "step": 63280 }, { "grad_norm": 0.1801496297121048, "learning_rate": 3.253679091659617e-05, "loss": 0.0083, "step": 63290 }, { "loss_action": 0.0064169676043093204, "loss_total": 0.0064169676043093204, "step": 63290 }, { "grad_norm": 0.20665119588375092, "learning_rate": 3.252129845783404e-05, "loss": 0.0076, "step": 63300 }, { "loss_action": 0.005517118610441685, "loss_total": 0.005517118610441685, "step": 63300 }, { "grad_norm": 0.21860231459140778, "learning_rate": 3.2505807910516456e-05, "loss": 0.008, "step": 63310 }, { "loss_action": 0.0069769807159900665, "loss_total": 0.0069769807159900665, "step": 63310 }, { "grad_norm": 0.17884598672389984, "learning_rate": 3.249031927633742e-05, "loss": 0.0072, "step": 63320 }, { "loss_action": 0.006353441160172224, "loss_total": 0.006353441160172224, "step": 63320 }, { "grad_norm": 0.1811394840478897, "learning_rate": 3.2474832556990737e-05, "loss": 0.0079, "step": 63330 }, { "loss_action": 0.004868361167609692, "loss_total": 0.004868361167609692, "step": 63330 }, { "grad_norm": 0.16581234335899353, "learning_rate": 3.245934775417002e-05, "loss": 0.0074, "step": 63340 }, { "loss_action": 0.008009514771401882, "loss_total": 0.008009514771401882, "step": 63340 }, { "grad_norm": 0.1899174600839615, "learning_rate": 3.244386486956866e-05, "loss": 0.0078, "step": 63350 }, { "loss_action": 0.007331931032240391, "loss_total": 0.007331931032240391, "step": 63350 }, { "grad_norm": 0.1999513953924179, "learning_rate": 3.2428383904879846e-05, "loss": 0.0076, "step": 63360 }, { "loss_action": 0.00687756622210145, "loss_total": 0.00687756622210145, "step": 63360 }, { "grad_norm": 0.2303050011396408, "learning_rate": 3.241290486179652e-05, "loss": 0.0077, "step": 63370 }, { "loss_action": 0.009007737040519714, "loss_total": 0.009007737040519714, "step": 63370 }, { "grad_norm": 0.18777668476104736, "learning_rate": 3.239742774201151e-05, "loss": 0.0072, "step": 63380 }, { "loss_action": 0.005371555685997009, "loss_total": 0.005371555685997009, "step": 63380 }, { "grad_norm": 0.21095028519630432, "learning_rate": 3.238195254721733e-05, "loss": 0.0077, "step": 63390 }, { "loss_action": 0.009400762617588043, "loss_total": 0.009400762617588043, "step": 63390 }, { "grad_norm": 0.26143917441368103, "learning_rate": 3.236647927910633e-05, "loss": 0.008, "step": 63400 }, { "loss_action": 0.00716135511174798, "loss_total": 0.00716135511174798, "step": 63400 }, { "grad_norm": 0.1915016919374466, "learning_rate": 3.2351007939370646e-05, "loss": 0.0083, "step": 63410 }, { "loss_action": 0.0052915578708052635, "loss_total": 0.0052915578708052635, "step": 63410 }, { "grad_norm": 0.18017977476119995, "learning_rate": 3.2335538529702184e-05, "loss": 0.0078, "step": 63420 }, { "loss_action": 0.007108844351023436, "loss_total": 0.007108844351023436, "step": 63420 }, { "grad_norm": 0.22952419519424438, "learning_rate": 3.232007105179268e-05, "loss": 0.0081, "step": 63430 }, { "loss_action": 0.009828872047364712, "loss_total": 0.009828872047364712, "step": 63430 }, { "grad_norm": 0.21365083754062653, "learning_rate": 3.230460550733363e-05, "loss": 0.009, "step": 63440 }, { "loss_action": 0.009436697699129581, "loss_total": 0.009436697699129581, "step": 63440 }, { "grad_norm": 0.16330458223819733, "learning_rate": 3.2289141898016315e-05, "loss": 0.0082, "step": 63450 }, { "loss_action": 0.007261852268129587, "loss_total": 0.007261852268129587, "step": 63450 }, { "grad_norm": 0.2256891280412674, "learning_rate": 3.227368022553181e-05, "loss": 0.0076, "step": 63460 }, { "loss_action": 0.009737653657793999, "loss_total": 0.009737653657793999, "step": 63460 }, { "grad_norm": 0.2614811360836029, "learning_rate": 3.225822049157099e-05, "loss": 0.008, "step": 63470 }, { "loss_action": 0.005910684820264578, "loss_total": 0.005910684820264578, "step": 63470 }, { "grad_norm": 0.23208561539649963, "learning_rate": 3.2242762697824494e-05, "loss": 0.0085, "step": 63480 }, { "loss_action": 0.006648623384535313, "loss_total": 0.006648623384535313, "step": 63480 }, { "grad_norm": 0.21641121804714203, "learning_rate": 3.222730684598279e-05, "loss": 0.0082, "step": 63490 }, { "loss_action": 0.009991537779569626, "loss_total": 0.009991537779569626, "step": 63490 }, { "grad_norm": 0.16307564079761505, "learning_rate": 3.221185293773605e-05, "loss": 0.008, "step": 63500 }, { "loss_action": 0.00764837209135294, "loss_total": 0.00764837209135294, "step": 63500 }, { "grad_norm": 0.18846853077411652, "learning_rate": 3.2196400974774354e-05, "loss": 0.0079, "step": 63510 }, { "loss_action": 0.006396075710654259, "loss_total": 0.006396075710654259, "step": 63510 }, { "grad_norm": 0.21627813577651978, "learning_rate": 3.2180950958787485e-05, "loss": 0.0071, "step": 63520 }, { "loss_action": 0.009065531194210052, "loss_total": 0.009065531194210052, "step": 63520 }, { "grad_norm": 0.18432728946208954, "learning_rate": 3.2165502891465024e-05, "loss": 0.0076, "step": 63530 }, { "loss_action": 0.005778359714895487, "loss_total": 0.005778359714895487, "step": 63530 }, { "grad_norm": 0.18529947102069855, "learning_rate": 3.215005677449636e-05, "loss": 0.0069, "step": 63540 }, { "loss_action": 0.00892484001815319, "loss_total": 0.00892484001815319, "step": 63540 }, { "grad_norm": 0.15694929659366608, "learning_rate": 3.2134612609570644e-05, "loss": 0.0072, "step": 63550 }, { "loss_action": 0.012418248690664768, "loss_total": 0.012418248690664768, "step": 63550 }, { "grad_norm": 0.1585119068622589, "learning_rate": 3.211917039837682e-05, "loss": 0.0075, "step": 63560 }, { "loss_action": 0.005314791575074196, "loss_total": 0.005314791575074196, "step": 63560 }, { "grad_norm": 0.17491906881332397, "learning_rate": 3.210373014260365e-05, "loss": 0.0076, "step": 63570 }, { "loss_action": 0.006279700435698032, "loss_total": 0.006279700435698032, "step": 63570 }, { "grad_norm": 0.22859112918376923, "learning_rate": 3.208829184393965e-05, "loss": 0.0077, "step": 63580 }, { "loss_action": 0.004320838488638401, "loss_total": 0.004320838488638401, "step": 63580 }, { "grad_norm": 0.18185363709926605, "learning_rate": 3.207285550407312e-05, "loss": 0.0067, "step": 63590 }, { "loss_action": 0.007266745902597904, "loss_total": 0.007266745902597904, "step": 63590 }, { "grad_norm": 0.21963578462600708, "learning_rate": 3.205742112469217e-05, "loss": 0.0068, "step": 63600 }, { "loss_action": 0.007643780205398798, "loss_total": 0.007643780205398798, "step": 63600 }, { "grad_norm": 0.2004699409008026, "learning_rate": 3.204198870748465e-05, "loss": 0.0081, "step": 63610 }, { "loss_action": 0.006993507966399193, "loss_total": 0.006993507966399193, "step": 63610 }, { "grad_norm": 0.19627119600772858, "learning_rate": 3.202655825413824e-05, "loss": 0.008, "step": 63620 }, { "loss_action": 0.010361880995333195, "loss_total": 0.010361880995333195, "step": 63620 }, { "grad_norm": 0.1848856508731842, "learning_rate": 3.2011129766340416e-05, "loss": 0.0079, "step": 63630 }, { "loss_action": 0.010708795860409737, "loss_total": 0.010708795860409737, "step": 63630 }, { "grad_norm": 0.23362694680690765, "learning_rate": 3.1995703245778384e-05, "loss": 0.0086, "step": 63640 }, { "loss_action": 0.006921578198671341, "loss_total": 0.006921578198671341, "step": 63640 }, { "grad_norm": 0.23832082748413086, "learning_rate": 3.1980278694139186e-05, "loss": 0.0074, "step": 63650 }, { "loss_action": 0.012668902985751629, "loss_total": 0.012668902985751629, "step": 63650 }, { "grad_norm": 0.23806452751159668, "learning_rate": 3.196485611310962e-05, "loss": 0.0093, "step": 63660 }, { "loss_action": 0.009179710410535336, "loss_total": 0.009179710410535336, "step": 63660 }, { "grad_norm": 0.1946631371974945, "learning_rate": 3.1949435504376257e-05, "loss": 0.0071, "step": 63670 }, { "loss_action": 0.0061621153727173805, "loss_total": 0.0061621153727173805, "step": 63670 }, { "grad_norm": 0.1832657754421234, "learning_rate": 3.1934016869625505e-05, "loss": 0.0067, "step": 63680 }, { "loss_action": 0.01091436855494976, "loss_total": 0.01091436855494976, "step": 63680 }, { "grad_norm": 0.2739991545677185, "learning_rate": 3.191860021054349e-05, "loss": 0.0084, "step": 63690 }, { "loss_action": 0.007634346839040518, "loss_total": 0.007634346839040518, "step": 63690 }, { "grad_norm": 0.23429442942142487, "learning_rate": 3.190318552881618e-05, "loss": 0.0095, "step": 63700 }, { "loss_action": 0.007233840879052877, "loss_total": 0.007233840879052877, "step": 63700 }, { "grad_norm": 0.23896221816539764, "learning_rate": 3.1887772826129285e-05, "loss": 0.0076, "step": 63710 }, { "loss_action": 0.008508363738656044, "loss_total": 0.008508363738656044, "step": 63710 }, { "grad_norm": 0.22947531938552856, "learning_rate": 3.1872362104168335e-05, "loss": 0.008, "step": 63720 }, { "loss_action": 0.010745681822299957, "loss_total": 0.010745681822299957, "step": 63720 }, { "grad_norm": 0.2751927971839905, "learning_rate": 3.185695336461861e-05, "loss": 0.0087, "step": 63730 }, { "loss_action": 0.008592706173658371, "loss_total": 0.008592706173658371, "step": 63730 }, { "grad_norm": 0.25418660044670105, "learning_rate": 3.184154660916519e-05, "loss": 0.0083, "step": 63740 }, { "loss_action": 0.007702048402279615, "loss_total": 0.007702048402279615, "step": 63740 }, { "grad_norm": 0.21402393281459808, "learning_rate": 3.1826141839492906e-05, "loss": 0.0074, "step": 63750 }, { "loss_action": 0.004414255730807781, "loss_total": 0.004414255730807781, "step": 63750 }, { "grad_norm": 0.225539892911911, "learning_rate": 3.181073905728644e-05, "loss": 0.0065, "step": 63760 }, { "loss_action": 0.00816131941974163, "loss_total": 0.00816131941974163, "step": 63760 }, { "grad_norm": 0.1692386418581009, "learning_rate": 3.1795338264230214e-05, "loss": 0.0081, "step": 63770 }, { "loss_action": 0.008559650741517544, "loss_total": 0.008559650741517544, "step": 63770 }, { "grad_norm": 0.16985058784484863, "learning_rate": 3.1779939462008426e-05, "loss": 0.0072, "step": 63780 }, { "loss_action": 0.006227460224181414, "loss_total": 0.006227460224181414, "step": 63780 }, { "grad_norm": 0.1713370978832245, "learning_rate": 3.1764542652305066e-05, "loss": 0.0069, "step": 63790 }, { "loss_action": 0.011233644559979439, "loss_total": 0.011233644559979439, "step": 63790 }, { "grad_norm": 0.1691925972700119, "learning_rate": 3.17491478368039e-05, "loss": 0.0088, "step": 63800 }, { "loss_action": 0.009669138118624687, "loss_total": 0.009669138118624687, "step": 63800 }, { "grad_norm": 0.1709960401058197, "learning_rate": 3.173375501718847e-05, "loss": 0.0094, "step": 63810 }, { "loss_action": 0.011947034858167171, "loss_total": 0.011947034858167171, "step": 63810 }, { "grad_norm": 0.1738564521074295, "learning_rate": 3.171836419514215e-05, "loss": 0.0083, "step": 63820 }, { "loss_action": 0.011081304401159286, "loss_total": 0.011081304401159286, "step": 63820 }, { "grad_norm": 0.21145980060100555, "learning_rate": 3.170297537234803e-05, "loss": 0.0092, "step": 63830 }, { "loss_action": 0.019332708790898323, "loss_total": 0.019332708790898323, "step": 63830 }, { "grad_norm": 0.2495458573102951, "learning_rate": 3.168758855048901e-05, "loss": 0.0092, "step": 63840 }, { "loss_action": 0.009830587543547153, "loss_total": 0.009830587543547153, "step": 63840 }, { "grad_norm": 0.16714680194854736, "learning_rate": 3.1672203731247785e-05, "loss": 0.0075, "step": 63850 }, { "loss_action": 0.008383049629628658, "loss_total": 0.008383049629628658, "step": 63850 }, { "grad_norm": 0.18630123138427734, "learning_rate": 3.16568209163068e-05, "loss": 0.0078, "step": 63860 }, { "loss_action": 0.01075473241508007, "loss_total": 0.01075473241508007, "step": 63860 }, { "grad_norm": 0.25943082571029663, "learning_rate": 3.1641440107348295e-05, "loss": 0.0075, "step": 63870 }, { "loss_action": 0.006483645178377628, "loss_total": 0.006483645178377628, "step": 63870 }, { "grad_norm": 0.2705141305923462, "learning_rate": 3.162606130605429e-05, "loss": 0.008, "step": 63880 }, { "loss_action": 0.012915898114442825, "loss_total": 0.012915898114442825, "step": 63880 }, { "grad_norm": 0.2055393010377884, "learning_rate": 3.16106845141066e-05, "loss": 0.0081, "step": 63890 }, { "loss_action": 0.007213955745100975, "loss_total": 0.007213955745100975, "step": 63890 }, { "grad_norm": 0.1899174153804779, "learning_rate": 3.159530973318682e-05, "loss": 0.008, "step": 63900 }, { "loss_action": 0.009099561721086502, "loss_total": 0.009099561721086502, "step": 63900 }, { "grad_norm": 0.22673878073692322, "learning_rate": 3.1579936964976286e-05, "loss": 0.0078, "step": 63910 }, { "loss_action": 0.007528557907789946, "loss_total": 0.007528557907789946, "step": 63910 }, { "grad_norm": 0.17582209408283234, "learning_rate": 3.156456621115615e-05, "loss": 0.007, "step": 63920 }, { "loss_action": 0.010217184200882912, "loss_total": 0.010217184200882912, "step": 63920 }, { "grad_norm": 0.2639288008213043, "learning_rate": 3.154919747340734e-05, "loss": 0.0082, "step": 63930 }, { "loss_action": 0.0088283009827137, "loss_total": 0.0088283009827137, "step": 63930 }, { "grad_norm": 0.15943294763565063, "learning_rate": 3.153383075341054e-05, "loss": 0.0091, "step": 63940 }, { "loss_action": 0.0071274880319833755, "loss_total": 0.0071274880319833755, "step": 63940 }, { "grad_norm": 0.2095266729593277, "learning_rate": 3.1518466052846264e-05, "loss": 0.0083, "step": 63950 }, { "loss_action": 0.0073974961414933205, "loss_total": 0.0073974961414933205, "step": 63950 }, { "grad_norm": 0.2598118185997009, "learning_rate": 3.150310337339474e-05, "loss": 0.0075, "step": 63960 }, { "loss_action": 0.007128457073122263, "loss_total": 0.007128457073122263, "step": 63960 }, { "grad_norm": 0.2114650458097458, "learning_rate": 3.148774271673603e-05, "loss": 0.0092, "step": 63970 }, { "loss_action": 0.0073938253335654736, "loss_total": 0.0073938253335654736, "step": 63970 }, { "grad_norm": 0.21823632717132568, "learning_rate": 3.147238408454995e-05, "loss": 0.0089, "step": 63980 }, { "loss_action": 0.0069267828948795795, "loss_total": 0.0069267828948795795, "step": 63980 }, { "grad_norm": 0.1970488727092743, "learning_rate": 3.1457027478516086e-05, "loss": 0.0063, "step": 63990 }, { "loss_action": 0.006005652714520693, "loss_total": 0.006005652714520693, "step": 63990 }, { "grad_norm": 0.20728126168251038, "learning_rate": 3.144167290031382e-05, "loss": 0.0077, "step": 64000 }, { "loss_action": 0.006930246949195862, "loss_total": 0.006930246949195862, "step": 64000 }, { "grad_norm": 0.2210061252117157, "learning_rate": 3.142632035162227e-05, "loss": 0.0062, "step": 64010 }, { "loss_action": 0.009544800966978073, "loss_total": 0.009544800966978073, "step": 64010 }, { "grad_norm": 0.2299342006444931, "learning_rate": 3.141096983412044e-05, "loss": 0.0087, "step": 64020 }, { "loss_action": 0.006038418039679527, "loss_total": 0.006038418039679527, "step": 64020 }, { "grad_norm": 0.20634806156158447, "learning_rate": 3.139562134948699e-05, "loss": 0.0077, "step": 64030 }, { "loss_action": 0.010675481520593166, "loss_total": 0.010675481520593166, "step": 64030 }, { "grad_norm": 0.2714065909385681, "learning_rate": 3.1380274899400424e-05, "loss": 0.0078, "step": 64040 }, { "loss_action": 0.016739586368203163, "loss_total": 0.016739586368203163, "step": 64040 }, { "grad_norm": 0.2341628074645996, "learning_rate": 3.1364930485539e-05, "loss": 0.0085, "step": 64050 }, { "loss_action": 0.009405394084751606, "loss_total": 0.009405394084751606, "step": 64050 }, { "grad_norm": 0.17659586668014526, "learning_rate": 3.134958810958076e-05, "loss": 0.0074, "step": 64060 }, { "loss_action": 0.009697599336504936, "loss_total": 0.009697599336504936, "step": 64060 }, { "grad_norm": 0.15757878124713898, "learning_rate": 3.13342477732035e-05, "loss": 0.0073, "step": 64070 }, { "loss_action": 0.005884095560759306, "loss_total": 0.005884095560759306, "step": 64070 }, { "grad_norm": 0.18743400275707245, "learning_rate": 3.131890947808487e-05, "loss": 0.0088, "step": 64080 }, { "loss_action": 0.0056621599942445755, "loss_total": 0.0056621599942445755, "step": 64080 }, { "grad_norm": 0.16847293078899384, "learning_rate": 3.13035732259022e-05, "loss": 0.0065, "step": 64090 }, { "loss_action": 0.006007933057844639, "loss_total": 0.006007933057844639, "step": 64090 }, { "grad_norm": 0.19760164618492126, "learning_rate": 3.1288239018332656e-05, "loss": 0.0077, "step": 64100 }, { "loss_action": 0.005776846781373024, "loss_total": 0.005776846781373024, "step": 64100 }, { "grad_norm": 0.18886880576610565, "learning_rate": 3.1272906857053164e-05, "loss": 0.0085, "step": 64110 }, { "loss_action": 0.0094622066244483, "loss_total": 0.0094622066244483, "step": 64110 }, { "grad_norm": 0.17287875711917877, "learning_rate": 3.125757674374042e-05, "loss": 0.0081, "step": 64120 }, { "loss_action": 0.0068798307329416275, "loss_total": 0.0068798307329416275, "step": 64120 }, { "grad_norm": 0.19819778203964233, "learning_rate": 3.124224868007088e-05, "loss": 0.007, "step": 64130 }, { "loss_action": 0.007838068529963493, "loss_total": 0.007838068529963493, "step": 64130 }, { "grad_norm": 0.24828192591667175, "learning_rate": 3.1226922667720854e-05, "loss": 0.0088, "step": 64140 }, { "loss_action": 0.006952988915145397, "loss_total": 0.006952988915145397, "step": 64140 }, { "grad_norm": 0.1684943437576294, "learning_rate": 3.121159870836633e-05, "loss": 0.0071, "step": 64150 }, { "loss_action": 0.007833987474441528, "loss_total": 0.007833987474441528, "step": 64150 }, { "grad_norm": 0.1895911544561386, "learning_rate": 3.119627680368312e-05, "loss": 0.0079, "step": 64160 }, { "loss_action": 0.006435033865272999, "loss_total": 0.006435033865272999, "step": 64160 }, { "grad_norm": 0.23323723673820496, "learning_rate": 3.1180956955346816e-05, "loss": 0.0081, "step": 64170 }, { "loss_action": 0.00738773075863719, "loss_total": 0.00738773075863719, "step": 64170 }, { "grad_norm": 0.2294531911611557, "learning_rate": 3.116563916503276e-05, "loss": 0.0074, "step": 64180 }, { "loss_action": 0.006064712069928646, "loss_total": 0.006064712069928646, "step": 64180 }, { "grad_norm": 0.22397641837596893, "learning_rate": 3.1150323434416095e-05, "loss": 0.0084, "step": 64190 }, { "loss_action": 0.007573481183499098, "loss_total": 0.007573481183499098, "step": 64190 }, { "grad_norm": 0.17193160951137543, "learning_rate": 3.1135009765171696e-05, "loss": 0.0083, "step": 64200 }, { "loss_action": 0.006533054169267416, "loss_total": 0.006533054169267416, "step": 64200 }, { "grad_norm": 0.1702117770910263, "learning_rate": 3.111969815897429e-05, "loss": 0.0075, "step": 64210 }, { "loss_action": 0.0064304727129638195, "loss_total": 0.0064304727129638195, "step": 64210 }, { "grad_norm": 0.1712920367717743, "learning_rate": 3.1104388617498295e-05, "loss": 0.0068, "step": 64220 }, { "loss_action": 0.006703424733132124, "loss_total": 0.006703424733132124, "step": 64220 }, { "grad_norm": 0.20186658203601837, "learning_rate": 3.1089081142417966e-05, "loss": 0.0063, "step": 64230 }, { "loss_action": 0.005697623360902071, "loss_total": 0.005697623360902071, "step": 64230 }, { "grad_norm": 0.22269810736179352, "learning_rate": 3.1073775735407285e-05, "loss": 0.0071, "step": 64240 }, { "loss_action": 0.009316674433648586, "loss_total": 0.009316674433648586, "step": 64240 }, { "grad_norm": 0.16132548451423645, "learning_rate": 3.1058472398140035e-05, "loss": 0.007, "step": 64250 }, { "loss_action": 0.006926102563738823, "loss_total": 0.006926102563738823, "step": 64250 }, { "grad_norm": 0.19142749905586243, "learning_rate": 3.1043171132289736e-05, "loss": 0.0079, "step": 64260 }, { "loss_action": 0.0056051830761134624, "loss_total": 0.0056051830761134624, "step": 64260 }, { "grad_norm": 0.15832239389419556, "learning_rate": 3.1027871939529774e-05, "loss": 0.0073, "step": 64270 }, { "loss_action": 0.016055988147854805, "loss_total": 0.016055988147854805, "step": 64270 }, { "grad_norm": 0.2763316333293915, "learning_rate": 3.1012574821533214e-05, "loss": 0.0083, "step": 64280 }, { "loss_action": 0.007531626150012016, "loss_total": 0.007531626150012016, "step": 64280 }, { "grad_norm": 0.2078545093536377, "learning_rate": 3.099727977997291e-05, "loss": 0.0085, "step": 64290 }, { "loss_action": 0.006916906218975782, "loss_total": 0.006916906218975782, "step": 64290 }, { "grad_norm": 0.25173571705818176, "learning_rate": 3.098198681652154e-05, "loss": 0.0097, "step": 64300 }, { "loss_action": 0.008096844889223576, "loss_total": 0.008096844889223576, "step": 64300 }, { "grad_norm": 0.22293721139431, "learning_rate": 3.0966695932851475e-05, "loss": 0.0079, "step": 64310 }, { "loss_action": 0.006067939568310976, "loss_total": 0.006067939568310976, "step": 64310 }, { "grad_norm": 0.18310458958148956, "learning_rate": 3.0951407130634926e-05, "loss": 0.0064, "step": 64320 }, { "loss_action": 0.011476671323180199, "loss_total": 0.011476671323180199, "step": 64320 }, { "grad_norm": 0.24026736617088318, "learning_rate": 3.0936120411543864e-05, "loss": 0.0081, "step": 64330 }, { "loss_action": 0.00653258478268981, "loss_total": 0.00653258478268981, "step": 64330 }, { "grad_norm": 0.28544896841049194, "learning_rate": 3.0920835777250015e-05, "loss": 0.0084, "step": 64340 }, { "loss_action": 0.005326608661562204, "loss_total": 0.005326608661562204, "step": 64340 }, { "grad_norm": 0.17638516426086426, "learning_rate": 3.090555322942488e-05, "loss": 0.0079, "step": 64350 }, { "loss_action": 0.0067494031973183155, "loss_total": 0.0067494031973183155, "step": 64350 }, { "grad_norm": 0.16285845637321472, "learning_rate": 3.089027276973973e-05, "loss": 0.0069, "step": 64360 }, { "loss_action": 0.007827823050320148, "loss_total": 0.007827823050320148, "step": 64360 }, { "grad_norm": 0.14658483862876892, "learning_rate": 3.0874994399865615e-05, "loss": 0.007, "step": 64370 }, { "loss_action": 0.006547475699335337, "loss_total": 0.006547475699335337, "step": 64370 }, { "grad_norm": 0.23156552016735077, "learning_rate": 3.085971812147337e-05, "loss": 0.0073, "step": 64380 }, { "loss_action": 0.010534550994634628, "loss_total": 0.010534550994634628, "step": 64380 }, { "grad_norm": 0.15898650884628296, "learning_rate": 3.0844443936233557e-05, "loss": 0.0083, "step": 64390 }, { "loss_action": 0.006976275704801083, "loss_total": 0.006976275704801083, "step": 64390 }, { "grad_norm": 0.17102017998695374, "learning_rate": 3.082917184581657e-05, "loss": 0.0076, "step": 64400 }, { "loss_action": 0.007306661922484636, "loss_total": 0.007306661922484636, "step": 64400 }, { "grad_norm": 0.19440920650959015, "learning_rate": 3.0813901851892513e-05, "loss": 0.0073, "step": 64410 }, { "loss_action": 0.006651904433965683, "loss_total": 0.006651904433965683, "step": 64410 }, { "grad_norm": 0.17323780059814453, "learning_rate": 3.0798633956131316e-05, "loss": 0.0067, "step": 64420 }, { "loss_action": 0.01075749471783638, "loss_total": 0.01075749471783638, "step": 64420 }, { "grad_norm": 0.17031975090503693, "learning_rate": 3.078336816020264e-05, "loss": 0.0073, "step": 64430 }, { "loss_action": 0.006942471954971552, "loss_total": 0.006942471954971552, "step": 64430 }, { "grad_norm": 0.22383259236812592, "learning_rate": 3.0768104465775935e-05, "loss": 0.0069, "step": 64440 }, { "loss_action": 0.006477135233581066, "loss_total": 0.006477135233581066, "step": 64440 }, { "grad_norm": 0.20988577604293823, "learning_rate": 3.0752842874520396e-05, "loss": 0.006, "step": 64450 }, { "loss_action": 0.010096784681081772, "loss_total": 0.010096784681081772, "step": 64450 }, { "grad_norm": 0.2726953327655792, "learning_rate": 3.073758338810503e-05, "loss": 0.0079, "step": 64460 }, { "loss_action": 0.012072558514773846, "loss_total": 0.012072558514773846, "step": 64460 }, { "grad_norm": 0.2476395219564438, "learning_rate": 3.072232600819859e-05, "loss": 0.0075, "step": 64470 }, { "loss_action": 0.010835818015038967, "loss_total": 0.010835818015038967, "step": 64470 }, { "grad_norm": 0.24925507605075836, "learning_rate": 3.070707073646959e-05, "loss": 0.0076, "step": 64480 }, { "loss_action": 0.009660215117037296, "loss_total": 0.009660215117037296, "step": 64480 }, { "grad_norm": 0.1464475840330124, "learning_rate": 3.069181757458633e-05, "loss": 0.0071, "step": 64490 }, { "loss_action": 0.00576232373714447, "loss_total": 0.00576232373714447, "step": 64490 }, { "grad_norm": 0.15123623609542847, "learning_rate": 3.067656652421687e-05, "loss": 0.0067, "step": 64500 }, { "loss_action": 0.008523780852556229, "loss_total": 0.008523780852556229, "step": 64500 }, { "grad_norm": 0.2768315374851227, "learning_rate": 3.0661317587029025e-05, "loss": 0.0086, "step": 64510 }, { "loss_action": 0.006019546650350094, "loss_total": 0.006019546650350094, "step": 64510 }, { "grad_norm": 0.18629948794841766, "learning_rate": 3.064607076469043e-05, "loss": 0.0065, "step": 64520 }, { "loss_action": 0.00951023492962122, "loss_total": 0.00951023492962122, "step": 64520 }, { "grad_norm": 0.15951405465602875, "learning_rate": 3.063082605886845e-05, "loss": 0.0082, "step": 64530 }, { "loss_action": 0.009729825891554356, "loss_total": 0.009729825891554356, "step": 64530 }, { "grad_norm": 0.17747221887111664, "learning_rate": 3.061558347123019e-05, "loss": 0.0076, "step": 64540 }, { "loss_action": 0.010965744964778423, "loss_total": 0.010965744964778423, "step": 64540 }, { "grad_norm": 0.21519063413143158, "learning_rate": 3.060034300344259e-05, "loss": 0.0079, "step": 64550 }, { "loss_action": 0.005147636868059635, "loss_total": 0.005147636868059635, "step": 64550 }, { "grad_norm": 0.213713139295578, "learning_rate": 3.058510465717231e-05, "loss": 0.0071, "step": 64560 }, { "loss_action": 0.005110918544232845, "loss_total": 0.005110918544232845, "step": 64560 }, { "grad_norm": 0.1652366667985916, "learning_rate": 3.0569868434085804e-05, "loss": 0.009, "step": 64570 }, { "loss_action": 0.012388928793370724, "loss_total": 0.012388928793370724, "step": 64570 }, { "grad_norm": 0.27264997363090515, "learning_rate": 3.055463433584924e-05, "loss": 0.0085, "step": 64580 }, { "loss_action": 0.005734620150178671, "loss_total": 0.005734620150178671, "step": 64580 }, { "grad_norm": 0.23006221652030945, "learning_rate": 3.0539402364128656e-05, "loss": 0.0078, "step": 64590 }, { "loss_action": 0.0082946065813303, "loss_total": 0.0082946065813303, "step": 64590 }, { "grad_norm": 0.18752695620059967, "learning_rate": 3.052417252058977e-05, "loss": 0.0074, "step": 64600 }, { "loss_action": 0.011933023110032082, "loss_total": 0.011933023110032082, "step": 64600 }, { "grad_norm": 0.18997390568256378, "learning_rate": 3.0508944806898092e-05, "loss": 0.0076, "step": 64610 }, { "loss_action": 0.01550490502268076, "loss_total": 0.01550490502268076, "step": 64610 }, { "grad_norm": 0.19372203946113586, "learning_rate": 3.04937192247189e-05, "loss": 0.0094, "step": 64620 }, { "loss_action": 0.005225079599767923, "loss_total": 0.005225079599767923, "step": 64620 }, { "grad_norm": 0.2639348804950714, "learning_rate": 3.047849577571725e-05, "loss": 0.0075, "step": 64630 }, { "loss_action": 0.006801540497690439, "loss_total": 0.006801540497690439, "step": 64630 }, { "grad_norm": 0.21244877576828003, "learning_rate": 3.046327446155795e-05, "loss": 0.0073, "step": 64640 }, { "loss_action": 0.008504769764840603, "loss_total": 0.008504769764840603, "step": 64640 }, { "grad_norm": 0.24359957873821259, "learning_rate": 3.0448055283905587e-05, "loss": 0.0081, "step": 64650 }, { "loss_action": 0.005654006265103817, "loss_total": 0.005654006265103817, "step": 64650 }, { "grad_norm": 0.19833309948444366, "learning_rate": 3.0432838244424494e-05, "loss": 0.0075, "step": 64660 }, { "loss_action": 0.006585655268281698, "loss_total": 0.006585655268281698, "step": 64660 }, { "grad_norm": 0.14449626207351685, "learning_rate": 3.04176233447788e-05, "loss": 0.0078, "step": 64670 }, { "loss_action": 0.007715787272900343, "loss_total": 0.007715787272900343, "step": 64670 }, { "grad_norm": 0.16316689550876617, "learning_rate": 3.040241058663238e-05, "loss": 0.0074, "step": 64680 }, { "loss_action": 0.010649888776242733, "loss_total": 0.010649888776242733, "step": 64680 }, { "grad_norm": 0.17507830262184143, "learning_rate": 3.038719997164887e-05, "loss": 0.0076, "step": 64690 }, { "loss_action": 0.013815694488584995, "loss_total": 0.013815694488584995, "step": 64690 }, { "grad_norm": 0.15473464131355286, "learning_rate": 3.0371991501491683e-05, "loss": 0.0076, "step": 64700 }, { "loss_action": 0.01598857343196869, "loss_total": 0.01598857343196869, "step": 64700 }, { "grad_norm": 0.19627675414085388, "learning_rate": 3.0356785177823975e-05, "loss": 0.0079, "step": 64710 }, { "loss_action": 0.007340126670897007, "loss_total": 0.007340126670897007, "step": 64710 }, { "grad_norm": 0.1795763075351715, "learning_rate": 3.0341581002308726e-05, "loss": 0.0074, "step": 64720 }, { "loss_action": 0.0064812698401510715, "loss_total": 0.0064812698401510715, "step": 64720 }, { "grad_norm": 0.13949266076087952, "learning_rate": 3.0326378976608627e-05, "loss": 0.0074, "step": 64730 }, { "loss_action": 0.007234371732920408, "loss_total": 0.007234371732920408, "step": 64730 }, { "grad_norm": 0.18877637386322021, "learning_rate": 3.0311179102386146e-05, "loss": 0.0076, "step": 64740 }, { "loss_action": 0.006017337087541819, "loss_total": 0.006017337087541819, "step": 64740 }, { "grad_norm": 0.16604070365428925, "learning_rate": 3.0295981381303513e-05, "loss": 0.0081, "step": 64750 }, { "loss_action": 0.013171953149139881, "loss_total": 0.013171953149139881, "step": 64750 }, { "grad_norm": 0.22521841526031494, "learning_rate": 3.0280785815022727e-05, "loss": 0.0089, "step": 64760 }, { "loss_action": 0.005913285072892904, "loss_total": 0.005913285072892904, "step": 64760 }, { "grad_norm": 0.2026669979095459, "learning_rate": 3.0265592405205544e-05, "loss": 0.0063, "step": 64770 }, { "loss_action": 0.008612564764916897, "loss_total": 0.008612564764916897, "step": 64770 }, { "grad_norm": 0.15784886479377747, "learning_rate": 3.0250401153513517e-05, "loss": 0.0076, "step": 64780 }, { "loss_action": 0.008485729806125164, "loss_total": 0.008485729806125164, "step": 64780 }, { "grad_norm": 0.29084745049476624, "learning_rate": 3.0235212061607936e-05, "loss": 0.0076, "step": 64790 }, { "loss_action": 0.004257797729223967, "loss_total": 0.004257797729223967, "step": 64790 }, { "grad_norm": 0.18557782471179962, "learning_rate": 3.0220025131149842e-05, "loss": 0.0074, "step": 64800 }, { "loss_action": 0.006732217501848936, "loss_total": 0.006732217501848936, "step": 64800 }, { "grad_norm": 0.21658077836036682, "learning_rate": 3.020484036380007e-05, "loss": 0.0073, "step": 64810 }, { "loss_action": 0.006272598635405302, "loss_total": 0.006272598635405302, "step": 64810 }, { "grad_norm": 0.20915444195270538, "learning_rate": 3.0189657761219188e-05, "loss": 0.0078, "step": 64820 }, { "loss_action": 0.004448309075087309, "loss_total": 0.004448309075087309, "step": 64820 }, { "grad_norm": 0.1865423023700714, "learning_rate": 3.017447732506753e-05, "loss": 0.0076, "step": 64830 }, { "loss_action": 0.008657241240143776, "loss_total": 0.008657241240143776, "step": 64830 }, { "grad_norm": 0.16819700598716736, "learning_rate": 3.015929905700524e-05, "loss": 0.0073, "step": 64840 }, { "loss_action": 0.0060977814719080925, "loss_total": 0.0060977814719080925, "step": 64840 }, { "grad_norm": 0.20338386297225952, "learning_rate": 3.014412295869218e-05, "loss": 0.0081, "step": 64850 }, { "loss_action": 0.009877628646790981, "loss_total": 0.009877628646790981, "step": 64850 }, { "grad_norm": 0.19674797356128693, "learning_rate": 3.0128949031787977e-05, "loss": 0.008, "step": 64860 }, { "loss_action": 0.008240089751780033, "loss_total": 0.008240089751780033, "step": 64860 }, { "grad_norm": 0.22434961795806885, "learning_rate": 3.0113777277952022e-05, "loss": 0.0069, "step": 64870 }, { "loss_action": 0.006248793099075556, "loss_total": 0.006248793099075556, "step": 64870 }, { "grad_norm": 0.14441770315170288, "learning_rate": 3.0098607698843496e-05, "loss": 0.0069, "step": 64880 }, { "loss_action": 0.013166428543627262, "loss_total": 0.013166428543627262, "step": 64880 }, { "grad_norm": 0.163419708609581, "learning_rate": 3.0083440296121312e-05, "loss": 0.0072, "step": 64890 }, { "loss_action": 0.0059970673173666, "loss_total": 0.0059970673173666, "step": 64890 }, { "grad_norm": 0.20804081857204437, "learning_rate": 3.0068275071444142e-05, "loss": 0.0073, "step": 64900 }, { "loss_action": 0.006248693913221359, "loss_total": 0.006248693913221359, "step": 64900 }, { "grad_norm": 0.24607892334461212, "learning_rate": 3.0053112026470442e-05, "loss": 0.0077, "step": 64910 }, { "loss_action": 0.008993835188448429, "loss_total": 0.008993835188448429, "step": 64910 }, { "grad_norm": 0.19978655874729156, "learning_rate": 3.0037951162858434e-05, "loss": 0.0076, "step": 64920 }, { "loss_action": 0.011800580658018589, "loss_total": 0.011800580658018589, "step": 64920 }, { "grad_norm": 0.21798789501190186, "learning_rate": 3.002279248226607e-05, "loss": 0.008, "step": 64930 }, { "loss_action": 0.005383321549743414, "loss_total": 0.005383321549743414, "step": 64930 }, { "grad_norm": 0.2058916687965393, "learning_rate": 3.000763598635109e-05, "loss": 0.0072, "step": 64940 }, { "loss_action": 0.007185811176896095, "loss_total": 0.007185811176896095, "step": 64940 }, { "grad_norm": 0.21975326538085938, "learning_rate": 2.999248167677098e-05, "loss": 0.0075, "step": 64950 }, { "loss_action": 0.0060274782590568066, "loss_total": 0.0060274782590568066, "step": 64950 }, { "grad_norm": 0.18902671337127686, "learning_rate": 2.9977329555182976e-05, "loss": 0.0075, "step": 64960 }, { "loss_action": 0.013463442213833332, "loss_total": 0.013463442213833332, "step": 64960 }, { "grad_norm": 0.16232001781463623, "learning_rate": 2.9962179623244124e-05, "loss": 0.0085, "step": 64970 }, { "loss_action": 0.006479337811470032, "loss_total": 0.006479337811470032, "step": 64970 }, { "grad_norm": 0.16288530826568604, "learning_rate": 2.9947031882611175e-05, "loss": 0.0072, "step": 64980 }, { "loss_action": 0.010931182652711868, "loss_total": 0.010931182652711868, "step": 64980 }, { "grad_norm": 0.22087332606315613, "learning_rate": 2.9931886334940685e-05, "loss": 0.0077, "step": 64990 }, { "loss_action": 0.007944073528051376, "loss_total": 0.007944073528051376, "step": 64990 }, { "grad_norm": 0.19679191708564758, "learning_rate": 2.9916742981888923e-05, "loss": 0.0075, "step": 65000 }, { "loss_action": 0.0075328536331653595, "loss_total": 0.0075328536331653595, "step": 65000 }, { "grad_norm": 0.20009206235408783, "learning_rate": 2.990160182511196e-05, "loss": 0.0088, "step": 65010 }, { "loss_action": 0.004788141697645187, "loss_total": 0.004788141697645187, "step": 65010 }, { "grad_norm": 0.18998423218727112, "learning_rate": 2.9886462866265574e-05, "loss": 0.0069, "step": 65020 }, { "loss_action": 0.011689556762576103, "loss_total": 0.011689556762576103, "step": 65020 }, { "grad_norm": 0.19327034056186676, "learning_rate": 2.9871326107005392e-05, "loss": 0.0087, "step": 65030 }, { "loss_action": 0.00824824720621109, "loss_total": 0.00824824720621109, "step": 65030 }, { "grad_norm": 0.23157376050949097, "learning_rate": 2.9856191548986735e-05, "loss": 0.0074, "step": 65040 }, { "loss_action": 0.008526402525603771, "loss_total": 0.008526402525603771, "step": 65040 }, { "grad_norm": 0.2223338484764099, "learning_rate": 2.9841059193864672e-05, "loss": 0.0081, "step": 65050 }, { "loss_action": 0.0076860226690769196, "loss_total": 0.0076860226690769196, "step": 65050 }, { "grad_norm": 0.23779913783073425, "learning_rate": 2.982592904329407e-05, "loss": 0.0082, "step": 65060 }, { "loss_action": 0.013974090106785297, "loss_total": 0.013974090106785297, "step": 65060 }, { "grad_norm": 0.24411174654960632, "learning_rate": 2.981080109892954e-05, "loss": 0.0079, "step": 65070 }, { "loss_action": 0.007334086578339338, "loss_total": 0.007334086578339338, "step": 65070 }, { "grad_norm": 0.19460435211658478, "learning_rate": 2.9795675362425434e-05, "loss": 0.0077, "step": 65080 }, { "loss_action": 0.009651239030063152, "loss_total": 0.009651239030063152, "step": 65080 }, { "grad_norm": 0.18904197216033936, "learning_rate": 2.97805518354359e-05, "loss": 0.0082, "step": 65090 }, { "loss_action": 0.006228129845112562, "loss_total": 0.006228129845112562, "step": 65090 }, { "grad_norm": 0.19021135568618774, "learning_rate": 2.9765430519614825e-05, "loss": 0.0078, "step": 65100 }, { "loss_action": 0.00645801005885005, "loss_total": 0.00645801005885005, "step": 65100 }, { "grad_norm": 0.18456152081489563, "learning_rate": 2.975031141661584e-05, "loss": 0.0088, "step": 65110 }, { "loss_action": 0.011106622405350208, "loss_total": 0.011106622405350208, "step": 65110 }, { "grad_norm": 0.20795124769210815, "learning_rate": 2.9735194528092347e-05, "loss": 0.0079, "step": 65120 }, { "loss_action": 0.007990428246557713, "loss_total": 0.007990428246557713, "step": 65120 }, { "grad_norm": 0.18266788125038147, "learning_rate": 2.9720079855697525e-05, "loss": 0.0068, "step": 65130 }, { "loss_action": 0.006080194376409054, "loss_total": 0.006080194376409054, "step": 65130 }, { "grad_norm": 0.2050590217113495, "learning_rate": 2.970496740108427e-05, "loss": 0.007, "step": 65140 }, { "loss_action": 0.007219136226922274, "loss_total": 0.007219136226922274, "step": 65140 }, { "grad_norm": 0.19808362424373627, "learning_rate": 2.968985716590527e-05, "loss": 0.0081, "step": 65150 }, { "loss_action": 0.005248297471553087, "loss_total": 0.005248297471553087, "step": 65150 }, { "grad_norm": 0.26423385739326477, "learning_rate": 2.9674749151812953e-05, "loss": 0.0071, "step": 65160 }, { "loss_action": 0.006658392027020454, "loss_total": 0.006658392027020454, "step": 65160 }, { "grad_norm": 0.22560203075408936, "learning_rate": 2.965964336045951e-05, "loss": 0.0077, "step": 65170 }, { "loss_action": 0.006268246099352837, "loss_total": 0.006268246099352837, "step": 65170 }, { "grad_norm": 0.1920388638973236, "learning_rate": 2.9644539793496894e-05, "loss": 0.0074, "step": 65180 }, { "loss_action": 0.006628185510635376, "loss_total": 0.006628185510635376, "step": 65180 }, { "grad_norm": 0.20596671104431152, "learning_rate": 2.9629438452576807e-05, "loss": 0.0071, "step": 65190 }, { "loss_action": 0.00535176508128643, "loss_total": 0.00535176508128643, "step": 65190 }, { "grad_norm": 0.19847914576530457, "learning_rate": 2.9614339339350698e-05, "loss": 0.0072, "step": 65200 }, { "loss_action": 0.00569433206692338, "loss_total": 0.00569433206692338, "step": 65200 }, { "grad_norm": 0.2371131032705307, "learning_rate": 2.959924245546979e-05, "loss": 0.0065, "step": 65210 }, { "loss_action": 0.009413882158696651, "loss_total": 0.009413882158696651, "step": 65210 }, { "grad_norm": 0.2332567572593689, "learning_rate": 2.9584147802585038e-05, "loss": 0.0077, "step": 65220 }, { "loss_action": 0.007043266668915749, "loss_total": 0.007043266668915749, "step": 65220 }, { "grad_norm": 0.223795548081398, "learning_rate": 2.956905538234721e-05, "loss": 0.0076, "step": 65230 }, { "loss_action": 0.0066622416488826275, "loss_total": 0.0066622416488826275, "step": 65230 }, { "grad_norm": 0.20921628177165985, "learning_rate": 2.9553965196406764e-05, "loss": 0.0074, "step": 65240 }, { "loss_action": 0.006304653361439705, "loss_total": 0.006304653361439705, "step": 65240 }, { "grad_norm": 0.1796540766954422, "learning_rate": 2.9538877246413943e-05, "loss": 0.008, "step": 65250 }, { "loss_action": 0.005114991217851639, "loss_total": 0.005114991217851639, "step": 65250 }, { "grad_norm": 0.20871883630752563, "learning_rate": 2.952379153401874e-05, "loss": 0.006, "step": 65260 }, { "loss_action": 0.011063717305660248, "loss_total": 0.011063717305660248, "step": 65260 }, { "grad_norm": 0.1834443360567093, "learning_rate": 2.9508708060870914e-05, "loss": 0.0078, "step": 65270 }, { "loss_action": 0.005394678562879562, "loss_total": 0.005394678562879562, "step": 65270 }, { "grad_norm": 0.1532672792673111, "learning_rate": 2.9493626828619948e-05, "loss": 0.0067, "step": 65280 }, { "loss_action": 0.007278933189809322, "loss_total": 0.007278933189809322, "step": 65280 }, { "grad_norm": 0.16575130820274353, "learning_rate": 2.9478547838915137e-05, "loss": 0.0068, "step": 65290 }, { "loss_action": 0.010622610338032246, "loss_total": 0.010622610338032246, "step": 65290 }, { "grad_norm": 0.20223471522331238, "learning_rate": 2.946347109340548e-05, "loss": 0.0084, "step": 65300 }, { "loss_action": 0.007359768729656935, "loss_total": 0.007359768729656935, "step": 65300 }, { "grad_norm": 0.22250087559223175, "learning_rate": 2.944839659373976e-05, "loss": 0.0074, "step": 65310 }, { "loss_action": 0.005170607939362526, "loss_total": 0.005170607939362526, "step": 65310 }, { "grad_norm": 0.15523730218410492, "learning_rate": 2.943332434156647e-05, "loss": 0.0073, "step": 65320 }, { "loss_action": 0.009345690719783306, "loss_total": 0.009345690719783306, "step": 65320 }, { "grad_norm": 0.3242455720901489, "learning_rate": 2.9418254338533912e-05, "loss": 0.0073, "step": 65330 }, { "loss_action": 0.010077524930238724, "loss_total": 0.010077524930238724, "step": 65330 }, { "grad_norm": 0.16333921253681183, "learning_rate": 2.940318658629011e-05, "loss": 0.008, "step": 65340 }, { "loss_action": 0.004642761778086424, "loss_total": 0.004642761778086424, "step": 65340 }, { "grad_norm": 0.2059260457754135, "learning_rate": 2.938812108648287e-05, "loss": 0.0074, "step": 65350 }, { "loss_action": 0.0075874351896345615, "loss_total": 0.0075874351896345615, "step": 65350 }, { "grad_norm": 0.1876453459262848, "learning_rate": 2.937305784075972e-05, "loss": 0.0071, "step": 65360 }, { "loss_action": 0.006062007509171963, "loss_total": 0.006062007509171963, "step": 65360 }, { "grad_norm": 0.2165655493736267, "learning_rate": 2.9357996850767937e-05, "loss": 0.0073, "step": 65370 }, { "loss_action": 0.007482963614165783, "loss_total": 0.007482963614165783, "step": 65370 }, { "grad_norm": 0.29770177602767944, "learning_rate": 2.9342938118154595e-05, "loss": 0.0084, "step": 65380 }, { "loss_action": 0.010641236789524555, "loss_total": 0.010641236789524555, "step": 65380 }, { "grad_norm": 0.21499989926815033, "learning_rate": 2.9327881644566485e-05, "loss": 0.0075, "step": 65390 }, { "loss_action": 0.007578580640256405, "loss_total": 0.007578580640256405, "step": 65390 }, { "grad_norm": 0.20742373168468475, "learning_rate": 2.9312827431650157e-05, "loss": 0.0087, "step": 65400 }, { "loss_action": 0.010335324332118034, "loss_total": 0.010335324332118034, "step": 65400 }, { "grad_norm": 0.14684700965881348, "learning_rate": 2.92977754810519e-05, "loss": 0.0071, "step": 65410 }, { "loss_action": 0.006583307404071093, "loss_total": 0.006583307404071093, "step": 65410 }, { "grad_norm": 0.18036112189292908, "learning_rate": 2.928272579441781e-05, "loss": 0.0074, "step": 65420 }, { "loss_action": 0.012170199304819107, "loss_total": 0.012170199304819107, "step": 65420 }, { "grad_norm": 0.19114644825458527, "learning_rate": 2.9267678373393676e-05, "loss": 0.0076, "step": 65430 }, { "loss_action": 0.008551392704248428, "loss_total": 0.008551392704248428, "step": 65430 }, { "grad_norm": 0.14536139369010925, "learning_rate": 2.925263321962507e-05, "loss": 0.0074, "step": 65440 }, { "loss_action": 0.006317149382084608, "loss_total": 0.006317149382084608, "step": 65440 }, { "grad_norm": 0.21899639070034027, "learning_rate": 2.9237590334757292e-05, "loss": 0.0069, "step": 65450 }, { "loss_action": 0.005902094300836325, "loss_total": 0.005902094300836325, "step": 65450 }, { "grad_norm": 0.14044323563575745, "learning_rate": 2.922254972043543e-05, "loss": 0.0068, "step": 65460 }, { "loss_action": 0.012647198513150215, "loss_total": 0.012647198513150215, "step": 65460 }, { "grad_norm": 0.18648333847522736, "learning_rate": 2.9207511378304265e-05, "loss": 0.0077, "step": 65470 }, { "loss_action": 0.006913273595273495, "loss_total": 0.006913273595273495, "step": 65470 }, { "grad_norm": 0.1694517284631729, "learning_rate": 2.9192475310008428e-05, "loss": 0.0077, "step": 65480 }, { "loss_action": 0.008540790528059006, "loss_total": 0.008540790528059006, "step": 65480 }, { "grad_norm": 0.1844695508480072, "learning_rate": 2.917744151719219e-05, "loss": 0.0076, "step": 65490 }, { "loss_action": 0.007787495851516724, "loss_total": 0.007787495851516724, "step": 65490 }, { "grad_norm": 0.16720129549503326, "learning_rate": 2.916241000149964e-05, "loss": 0.007, "step": 65500 }, { "loss_action": 0.00804845243692398, "loss_total": 0.00804845243692398, "step": 65500 }, { "grad_norm": 0.1946369856595993, "learning_rate": 2.9147380764574622e-05, "loss": 0.007, "step": 65510 }, { "loss_action": 0.006383570376783609, "loss_total": 0.006383570376783609, "step": 65510 }, { "grad_norm": 0.2028532475233078, "learning_rate": 2.9132353808060674e-05, "loss": 0.0065, "step": 65520 }, { "loss_action": 0.015712013468146324, "loss_total": 0.015712013468146324, "step": 65520 }, { "grad_norm": 0.20808294415473938, "learning_rate": 2.9117329133601134e-05, "loss": 0.0093, "step": 65530 }, { "loss_action": 0.008559106849133968, "loss_total": 0.008559106849133968, "step": 65530 }, { "grad_norm": 0.22927680611610413, "learning_rate": 2.9102306742839093e-05, "loss": 0.0081, "step": 65540 }, { "loss_action": 0.005713783670216799, "loss_total": 0.005713783670216799, "step": 65540 }, { "grad_norm": 0.17673946917057037, "learning_rate": 2.9087286637417375e-05, "loss": 0.0069, "step": 65550 }, { "loss_action": 0.009553920477628708, "loss_total": 0.009553920477628708, "step": 65550 }, { "grad_norm": 0.2106654942035675, "learning_rate": 2.9072268818978537e-05, "loss": 0.0073, "step": 65560 }, { "loss_action": 0.006883695255964994, "loss_total": 0.006883695255964994, "step": 65560 }, { "grad_norm": 0.24759289622306824, "learning_rate": 2.905725328916493e-05, "loss": 0.0082, "step": 65570 }, { "loss_action": 0.010798867791891098, "loss_total": 0.010798867791891098, "step": 65570 }, { "grad_norm": 0.2063898891210556, "learning_rate": 2.9042240049618608e-05, "loss": 0.0074, "step": 65580 }, { "loss_action": 0.009840881451964378, "loss_total": 0.009840881451964378, "step": 65580 }, { "grad_norm": 0.2357761114835739, "learning_rate": 2.9027229101981413e-05, "loss": 0.008, "step": 65590 }, { "loss_action": 0.009104831144213676, "loss_total": 0.009104831144213676, "step": 65590 }, { "grad_norm": 0.22636421024799347, "learning_rate": 2.901222044789488e-05, "loss": 0.0075, "step": 65600 }, { "loss_action": 0.009298894554376602, "loss_total": 0.009298894554376602, "step": 65600 }, { "grad_norm": 0.180804044008255, "learning_rate": 2.89972140890004e-05, "loss": 0.0082, "step": 65610 }, { "loss_action": 0.006173733621835709, "loss_total": 0.006173733621835709, "step": 65610 }, { "grad_norm": 0.20773464441299438, "learning_rate": 2.8982210026938988e-05, "loss": 0.007, "step": 65620 }, { "loss_action": 0.0065757473930716515, "loss_total": 0.0065757473930716515, "step": 65620 }, { "grad_norm": 0.21779806911945343, "learning_rate": 2.896720826335151e-05, "loss": 0.008, "step": 65630 }, { "loss_action": 0.008909081108868122, "loss_total": 0.008909081108868122, "step": 65630 }, { "grad_norm": 0.1707417219877243, "learning_rate": 2.8952208799878493e-05, "loss": 0.0073, "step": 65640 }, { "loss_action": 0.00585496099665761, "loss_total": 0.00585496099665761, "step": 65640 }, { "grad_norm": 0.13125823438167572, "learning_rate": 2.89372116381603e-05, "loss": 0.0068, "step": 65650 }, { "loss_action": 0.009555346332490444, "loss_total": 0.009555346332490444, "step": 65650 }, { "grad_norm": 0.20964732766151428, "learning_rate": 2.8922216779836932e-05, "loss": 0.0065, "step": 65660 }, { "loss_action": 0.005846494808793068, "loss_total": 0.005846494808793068, "step": 65660 }, { "grad_norm": 0.15980295836925507, "learning_rate": 2.8907224226548285e-05, "loss": 0.0064, "step": 65670 }, { "loss_action": 0.00552327511832118, "loss_total": 0.00552327511832118, "step": 65670 }, { "grad_norm": 0.15778066217899323, "learning_rate": 2.8892233979933868e-05, "loss": 0.0073, "step": 65680 }, { "loss_action": 0.00830343272536993, "loss_total": 0.00830343272536993, "step": 65680 }, { "grad_norm": 0.20376552641391754, "learning_rate": 2.8877246041633026e-05, "loss": 0.0073, "step": 65690 }, { "loss_action": 0.005398140288889408, "loss_total": 0.005398140288889408, "step": 65690 }, { "grad_norm": 0.3170049786567688, "learning_rate": 2.886226041328478e-05, "loss": 0.007, "step": 65700 }, { "loss_action": 0.012141671031713486, "loss_total": 0.012141671031713486, "step": 65700 }, { "grad_norm": 0.24600955843925476, "learning_rate": 2.8847277096527957e-05, "loss": 0.0091, "step": 65710 }, { "loss_action": 0.008520763367414474, "loss_total": 0.008520763367414474, "step": 65710 }, { "grad_norm": 0.2802130877971649, "learning_rate": 2.8832296093001105e-05, "loss": 0.008, "step": 65720 }, { "loss_action": 0.007417845539748669, "loss_total": 0.007417845539748669, "step": 65720 }, { "grad_norm": 0.18761105835437775, "learning_rate": 2.8817317404342547e-05, "loss": 0.0081, "step": 65730 }, { "loss_action": 0.00882706604897976, "loss_total": 0.00882706604897976, "step": 65730 }, { "grad_norm": 0.1541728973388672, "learning_rate": 2.880234103219029e-05, "loss": 0.0081, "step": 65740 }, { "loss_action": 0.011108588427305222, "loss_total": 0.011108588427305222, "step": 65740 }, { "grad_norm": 0.19864514470100403, "learning_rate": 2.878736697818215e-05, "loss": 0.0079, "step": 65750 }, { "loss_action": 0.007954279892146587, "loss_total": 0.007954279892146587, "step": 65750 }, { "grad_norm": 0.26618948578834534, "learning_rate": 2.877239524395568e-05, "loss": 0.0095, "step": 65760 }, { "loss_action": 0.00568560091778636, "loss_total": 0.00568560091778636, "step": 65760 }, { "grad_norm": 0.2383723258972168, "learning_rate": 2.8757425831148134e-05, "loss": 0.008, "step": 65770 }, { "loss_action": 0.004331119824200869, "loss_total": 0.004331119824200869, "step": 65770 }, { "grad_norm": 0.20465439558029175, "learning_rate": 2.874245874139658e-05, "loss": 0.0065, "step": 65780 }, { "loss_action": 0.011759839951992035, "loss_total": 0.011759839951992035, "step": 65780 }, { "grad_norm": 0.206960991024971, "learning_rate": 2.8727493976337737e-05, "loss": 0.0091, "step": 65790 }, { "loss_action": 0.0090654781088233, "loss_total": 0.0090654781088233, "step": 65790 }, { "grad_norm": 0.21028251945972443, "learning_rate": 2.8712531537608218e-05, "loss": 0.0084, "step": 65800 }, { "loss_action": 0.007223537657409906, "loss_total": 0.007223537657409906, "step": 65800 }, { "grad_norm": 0.24122484028339386, "learning_rate": 2.8697571426844217e-05, "loss": 0.0072, "step": 65810 }, { "loss_action": 0.007029865402728319, "loss_total": 0.007029865402728319, "step": 65810 }, { "grad_norm": 0.19580137729644775, "learning_rate": 2.86826136456818e-05, "loss": 0.0077, "step": 65820 }, { "loss_action": 0.0066002896055579185, "loss_total": 0.0066002896055579185, "step": 65820 }, { "grad_norm": 0.22014056146144867, "learning_rate": 2.8667658195756685e-05, "loss": 0.0076, "step": 65830 }, { "loss_action": 0.013869942165911198, "loss_total": 0.013869942165911198, "step": 65830 }, { "grad_norm": 0.23102158308029175, "learning_rate": 2.8652705078704412e-05, "loss": 0.0081, "step": 65840 }, { "loss_action": 0.008856450207531452, "loss_total": 0.008856450207531452, "step": 65840 }, { "grad_norm": 0.17574334144592285, "learning_rate": 2.863775429616018e-05, "loss": 0.0093, "step": 65850 }, { "loss_action": 0.007307959720492363, "loss_total": 0.007307959720492363, "step": 65850 }, { "grad_norm": 0.15522213280200958, "learning_rate": 2.862280584975906e-05, "loss": 0.0078, "step": 65860 }, { "loss_action": 0.007691809441894293, "loss_total": 0.007691809441894293, "step": 65860 }, { "grad_norm": 0.2403707355260849, "learning_rate": 2.8607859741135735e-05, "loss": 0.009, "step": 65870 }, { "loss_action": 0.006321238819509745, "loss_total": 0.006321238819509745, "step": 65870 }, { "grad_norm": 0.20101870596408844, "learning_rate": 2.8592915971924723e-05, "loss": 0.0087, "step": 65880 }, { "loss_action": 0.012983678840100765, "loss_total": 0.012983678840100765, "step": 65880 }, { "grad_norm": 0.14089620113372803, "learning_rate": 2.8577974543760212e-05, "loss": 0.0074, "step": 65890 }, { "loss_action": 0.007013391237705946, "loss_total": 0.007013391237705946, "step": 65890 }, { "grad_norm": 0.17996494472026825, "learning_rate": 2.8563035458276222e-05, "loss": 0.0074, "step": 65900 }, { "loss_action": 0.006152803543955088, "loss_total": 0.006152803543955088, "step": 65900 }, { "grad_norm": 0.1790236532688141, "learning_rate": 2.8548098717106424e-05, "loss": 0.0076, "step": 65910 }, { "loss_action": 0.005617889109998941, "loss_total": 0.005617889109998941, "step": 65910 }, { "grad_norm": 0.21458522975444794, "learning_rate": 2.85331643218843e-05, "loss": 0.0081, "step": 65920 }, { "loss_action": 0.005176576320081949, "loss_total": 0.005176576320081949, "step": 65920 }, { "grad_norm": 0.24296380579471588, "learning_rate": 2.8518232274243046e-05, "loss": 0.0076, "step": 65930 }, { "loss_action": 0.004376515280455351, "loss_total": 0.004376515280455351, "step": 65930 }, { "grad_norm": 0.21481607854366302, "learning_rate": 2.8503302575815638e-05, "loss": 0.008, "step": 65940 }, { "loss_action": 0.006205966230481863, "loss_total": 0.006205966230481863, "step": 65940 }, { "grad_norm": 0.19635307788848877, "learning_rate": 2.8488375228234716e-05, "loss": 0.0081, "step": 65950 }, { "loss_action": 0.00866751093417406, "loss_total": 0.00866751093417406, "step": 65950 }, { "grad_norm": 0.17059171199798584, "learning_rate": 2.8473450233132738e-05, "loss": 0.0085, "step": 65960 }, { "loss_action": 0.005396275781095028, "loss_total": 0.005396275781095028, "step": 65960 }, { "grad_norm": 0.20136140286922455, "learning_rate": 2.8458527592141898e-05, "loss": 0.0079, "step": 65970 }, { "loss_action": 0.006700537167489529, "loss_total": 0.006700537167489529, "step": 65970 }, { "grad_norm": 0.18939267098903656, "learning_rate": 2.8443607306894073e-05, "loss": 0.0067, "step": 65980 }, { "loss_action": 0.011533379554748535, "loss_total": 0.011533379554748535, "step": 65980 }, { "grad_norm": 0.16317640244960785, "learning_rate": 2.8428689379020946e-05, "loss": 0.0064, "step": 65990 }, { "loss_action": 0.0057512251660227776, "loss_total": 0.0057512251660227776, "step": 65990 }, { "grad_norm": 0.18849685788154602, "learning_rate": 2.841377381015391e-05, "loss": 0.007, "step": 66000 }, { "loss_action": 0.0067518772557377815, "loss_total": 0.0067518772557377815, "step": 66000 }, { "grad_norm": 0.1812247782945633, "learning_rate": 2.8398860601924144e-05, "loss": 0.0071, "step": 66010 }, { "loss_action": 0.009312272071838379, "loss_total": 0.009312272071838379, "step": 66010 }, { "grad_norm": 0.1662064641714096, "learning_rate": 2.838394975596248e-05, "loss": 0.007, "step": 66020 }, { "loss_action": 0.005465927068144083, "loss_total": 0.005465927068144083, "step": 66020 }, { "grad_norm": 0.14388100802898407, "learning_rate": 2.83690412738996e-05, "loss": 0.0069, "step": 66030 }, { "loss_action": 0.006063337903469801, "loss_total": 0.006063337903469801, "step": 66030 }, { "grad_norm": 0.20324929058551788, "learning_rate": 2.835413515736579e-05, "loss": 0.0079, "step": 66040 }, { "loss_action": 0.006512075662612915, "loss_total": 0.006512075662612915, "step": 66040 }, { "grad_norm": 0.1715817153453827, "learning_rate": 2.8339231407991267e-05, "loss": 0.0085, "step": 66050 }, { "loss_action": 0.007126296404749155, "loss_total": 0.007126296404749155, "step": 66050 }, { "grad_norm": 0.22675956785678864, "learning_rate": 2.832433002740581e-05, "loss": 0.007, "step": 66060 }, { "loss_action": 0.006232789717614651, "loss_total": 0.006232789717614651, "step": 66060 }, { "grad_norm": 0.18397656083106995, "learning_rate": 2.8309431017239047e-05, "loss": 0.0063, "step": 66070 }, { "loss_action": 0.0075921048410236835, "loss_total": 0.0075921048410236835, "step": 66070 }, { "grad_norm": 0.14183060824871063, "learning_rate": 2.829453437912028e-05, "loss": 0.0073, "step": 66080 }, { "loss_action": 0.008521165698766708, "loss_total": 0.008521165698766708, "step": 66080 }, { "grad_norm": 0.15557193756103516, "learning_rate": 2.8279640114678617e-05, "loss": 0.0075, "step": 66090 }, { "loss_action": 0.006203961092978716, "loss_total": 0.006203961092978716, "step": 66090 }, { "grad_norm": 0.26311594247817993, "learning_rate": 2.8264748225542836e-05, "loss": 0.0079, "step": 66100 }, { "loss_action": 0.0077705979347229, "loss_total": 0.0077705979347229, "step": 66100 }, { "grad_norm": 0.20008976757526398, "learning_rate": 2.8249858713341516e-05, "loss": 0.0083, "step": 66110 }, { "loss_action": 0.00784375611692667, "loss_total": 0.00784375611692667, "step": 66110 }, { "grad_norm": 0.1709403693675995, "learning_rate": 2.823497157970294e-05, "loss": 0.0075, "step": 66120 }, { "loss_action": 0.009707053191959858, "loss_total": 0.009707053191959858, "step": 66120 }, { "grad_norm": 0.24091479182243347, "learning_rate": 2.8220086826255164e-05, "loss": 0.0072, "step": 66130 }, { "loss_action": 0.008988164365291595, "loss_total": 0.008988164365291595, "step": 66130 }, { "grad_norm": 0.1650415062904358, "learning_rate": 2.8205204454625934e-05, "loss": 0.0085, "step": 66140 }, { "loss_action": 0.008580661378800869, "loss_total": 0.008580661378800869, "step": 66140 }, { "grad_norm": 0.2226066142320633, "learning_rate": 2.8190324466442798e-05, "loss": 0.0089, "step": 66150 }, { "loss_action": 0.012686089612543583, "loss_total": 0.012686089612543583, "step": 66150 }, { "grad_norm": 0.17883393168449402, "learning_rate": 2.8175446863332965e-05, "loss": 0.0089, "step": 66160 }, { "loss_action": 0.005944800563156605, "loss_total": 0.005944800563156605, "step": 66160 }, { "grad_norm": 0.20231692492961884, "learning_rate": 2.816057164692345e-05, "loss": 0.0071, "step": 66170 }, { "loss_action": 0.009337675757706165, "loss_total": 0.009337675757706165, "step": 66170 }, { "grad_norm": 0.2358776181936264, "learning_rate": 2.8145698818840992e-05, "loss": 0.0068, "step": 66180 }, { "loss_action": 0.006339305080473423, "loss_total": 0.006339305080473423, "step": 66180 }, { "grad_norm": 0.19746755063533783, "learning_rate": 2.8130828380712065e-05, "loss": 0.0091, "step": 66190 }, { "loss_action": 0.00577895250171423, "loss_total": 0.00577895250171423, "step": 66190 }, { "grad_norm": 0.16041135787963867, "learning_rate": 2.811596033416285e-05, "loss": 0.0079, "step": 66200 }, { "loss_action": 0.013354855589568615, "loss_total": 0.013354855589568615, "step": 66200 }, { "grad_norm": 0.19516076147556305, "learning_rate": 2.8101094680819307e-05, "loss": 0.0078, "step": 66210 }, { "loss_action": 0.005234953016042709, "loss_total": 0.005234953016042709, "step": 66210 }, { "grad_norm": 0.18146002292633057, "learning_rate": 2.808623142230715e-05, "loss": 0.0065, "step": 66220 }, { "loss_action": 0.006849009543657303, "loss_total": 0.006849009543657303, "step": 66220 }, { "grad_norm": 0.18290549516677856, "learning_rate": 2.8071370560251757e-05, "loss": 0.0075, "step": 66230 }, { "loss_action": 0.005510946735739708, "loss_total": 0.005510946735739708, "step": 66230 }, { "grad_norm": 0.1792374551296234, "learning_rate": 2.805651209627831e-05, "loss": 0.0067, "step": 66240 }, { "loss_action": 0.0066797081381082535, "loss_total": 0.0066797081381082535, "step": 66240 }, { "grad_norm": 0.18063616752624512, "learning_rate": 2.804165603201171e-05, "loss": 0.0082, "step": 66250 }, { "loss_action": 0.005228904541581869, "loss_total": 0.005228904541581869, "step": 66250 }, { "grad_norm": 0.19172607362270355, "learning_rate": 2.802680236907661e-05, "loss": 0.0076, "step": 66260 }, { "loss_action": 0.011021243408322334, "loss_total": 0.011021243408322334, "step": 66260 }, { "grad_norm": 0.17807996273040771, "learning_rate": 2.8011951109097344e-05, "loss": 0.0095, "step": 66270 }, { "loss_action": 0.006578885484486818, "loss_total": 0.006578885484486818, "step": 66270 }, { "grad_norm": 0.23429736495018005, "learning_rate": 2.7997102253698072e-05, "loss": 0.0076, "step": 66280 }, { "loss_action": 0.005683646537363529, "loss_total": 0.005683646537363529, "step": 66280 }, { "grad_norm": 0.20153461396694183, "learning_rate": 2.7982255804502588e-05, "loss": 0.0064, "step": 66290 }, { "loss_action": 0.006139231845736504, "loss_total": 0.006139231845736504, "step": 66290 }, { "grad_norm": 0.1977386623620987, "learning_rate": 2.7967411763134516e-05, "loss": 0.0066, "step": 66300 }, { "loss_action": 0.006648599170148373, "loss_total": 0.006648599170148373, "step": 66300 }, { "grad_norm": 0.1711413413286209, "learning_rate": 2.7952570131217166e-05, "loss": 0.0076, "step": 66310 }, { "loss_action": 0.014077109284698963, "loss_total": 0.014077109284698963, "step": 66310 }, { "grad_norm": 0.2114769071340561, "learning_rate": 2.7937730910373618e-05, "loss": 0.0089, "step": 66320 }, { "loss_action": 0.0060074771754443645, "loss_total": 0.0060074771754443645, "step": 66320 }, { "grad_norm": 0.1910070776939392, "learning_rate": 2.7922894102226628e-05, "loss": 0.0061, "step": 66330 }, { "loss_action": 0.005158628802746534, "loss_total": 0.005158628802746534, "step": 66330 }, { "grad_norm": 0.22097282111644745, "learning_rate": 2.790805970839876e-05, "loss": 0.0068, "step": 66340 }, { "loss_action": 0.007201969623565674, "loss_total": 0.007201969623565674, "step": 66340 }, { "grad_norm": 0.1957017481327057, "learning_rate": 2.789322773051225e-05, "loss": 0.0081, "step": 66350 }, { "loss_action": 0.00521116005256772, "loss_total": 0.00521116005256772, "step": 66350 }, { "grad_norm": 0.17188847064971924, "learning_rate": 2.7878398170189124e-05, "loss": 0.007, "step": 66360 }, { "loss_action": 0.005712354090064764, "loss_total": 0.005712354090064764, "step": 66360 }, { "grad_norm": 0.20456162095069885, "learning_rate": 2.7863571029051112e-05, "loss": 0.0079, "step": 66370 }, { "loss_action": 0.009494554251432419, "loss_total": 0.009494554251432419, "step": 66370 }, { "grad_norm": 0.21296612918376923, "learning_rate": 2.784874630871971e-05, "loss": 0.0084, "step": 66380 }, { "loss_action": 0.011018841527402401, "loss_total": 0.011018841527402401, "step": 66380 }, { "grad_norm": 0.18657895922660828, "learning_rate": 2.7833924010816086e-05, "loss": 0.0082, "step": 66390 }, { "loss_action": 0.009898216463625431, "loss_total": 0.009898216463625431, "step": 66390 }, { "grad_norm": 0.21654506027698517, "learning_rate": 2.7819104136961226e-05, "loss": 0.0076, "step": 66400 }, { "loss_action": 0.008333720266819, "loss_total": 0.008333720266819, "step": 66400 }, { "grad_norm": 0.20378857851028442, "learning_rate": 2.780428668877577e-05, "loss": 0.0078, "step": 66410 }, { "loss_action": 0.009341396391391754, "loss_total": 0.009341396391391754, "step": 66410 }, { "grad_norm": 0.166218101978302, "learning_rate": 2.7789471667880152e-05, "loss": 0.008, "step": 66420 }, { "loss_action": 0.007618041709065437, "loss_total": 0.007618041709065437, "step": 66420 }, { "grad_norm": 0.26180845499038696, "learning_rate": 2.7774659075894523e-05, "loss": 0.0064, "step": 66430 }, { "loss_action": 0.006330190226435661, "loss_total": 0.006330190226435661, "step": 66430 }, { "grad_norm": 0.18124522268772125, "learning_rate": 2.7759848914438778e-05, "loss": 0.0072, "step": 66440 }, { "loss_action": 0.0186455100774765, "loss_total": 0.0186455100774765, "step": 66440 }, { "grad_norm": 0.15733855962753296, "learning_rate": 2.7745041185132496e-05, "loss": 0.0082, "step": 66450 }, { "loss_action": 0.009144085459411144, "loss_total": 0.009144085459411144, "step": 66450 }, { "grad_norm": 0.152690589427948, "learning_rate": 2.773023588959506e-05, "loss": 0.0077, "step": 66460 }, { "loss_action": 0.007335397880524397, "loss_total": 0.007335397880524397, "step": 66460 }, { "grad_norm": 0.20267800986766815, "learning_rate": 2.7715433029445555e-05, "loss": 0.0078, "step": 66470 }, { "loss_action": 0.016979683190584183, "loss_total": 0.016979683190584183, "step": 66470 }, { "grad_norm": 0.1866917461156845, "learning_rate": 2.7700632606302766e-05, "loss": 0.0079, "step": 66480 }, { "loss_action": 0.009037903510034084, "loss_total": 0.009037903510034084, "step": 66480 }, { "grad_norm": 0.1864340752363205, "learning_rate": 2.768583462178528e-05, "loss": 0.0075, "step": 66490 }, { "loss_action": 0.010901404544711113, "loss_total": 0.010901404544711113, "step": 66490 }, { "grad_norm": 0.16653522849082947, "learning_rate": 2.767103907751136e-05, "loss": 0.0078, "step": 66500 }, { "loss_action": 0.004849993623793125, "loss_total": 0.004849993623793125, "step": 66500 }, { "grad_norm": 0.17627035081386566, "learning_rate": 2.7656245975099065e-05, "loss": 0.0078, "step": 66510 }, { "loss_action": 0.006017761304974556, "loss_total": 0.006017761304974556, "step": 66510 }, { "grad_norm": 0.19035892188549042, "learning_rate": 2.7641455316166093e-05, "loss": 0.0062, "step": 66520 }, { "loss_action": 0.004433354828506708, "loss_total": 0.004433354828506708, "step": 66520 }, { "grad_norm": 0.19270600378513336, "learning_rate": 2.7626667102329973e-05, "loss": 0.0062, "step": 66530 }, { "loss_action": 0.008554361760616302, "loss_total": 0.008554361760616302, "step": 66530 }, { "grad_norm": 0.2677208483219147, "learning_rate": 2.761188133520788e-05, "loss": 0.0074, "step": 66540 }, { "loss_action": 0.009894054383039474, "loss_total": 0.009894054383039474, "step": 66540 }, { "grad_norm": 0.15868042409420013, "learning_rate": 2.7597098016416784e-05, "loss": 0.0073, "step": 66550 }, { "loss_action": 0.007637995295226574, "loss_total": 0.007637995295226574, "step": 66550 }, { "grad_norm": 0.18444310128688812, "learning_rate": 2.7582317147573368e-05, "loss": 0.0069, "step": 66560 }, { "loss_action": 0.0062700617127120495, "loss_total": 0.0062700617127120495, "step": 66560 }, { "grad_norm": 0.14996333420276642, "learning_rate": 2.7567538730294064e-05, "loss": 0.0069, "step": 66570 }, { "loss_action": 0.007865943014621735, "loss_total": 0.007865943014621735, "step": 66570 }, { "grad_norm": 0.15716947615146637, "learning_rate": 2.7552762766194973e-05, "loss": 0.0073, "step": 66580 }, { "loss_action": 0.009450983256101608, "loss_total": 0.009450983256101608, "step": 66580 }, { "grad_norm": 0.20078788697719574, "learning_rate": 2.753798925689202e-05, "loss": 0.0073, "step": 66590 }, { "loss_action": 0.009871800430119038, "loss_total": 0.009871800430119038, "step": 66590 }, { "grad_norm": 0.19969327747821808, "learning_rate": 2.7523218204000774e-05, "loss": 0.0078, "step": 66600 }, { "loss_action": 0.008768106810748577, "loss_total": 0.008768106810748577, "step": 66600 }, { "grad_norm": 0.1831420660018921, "learning_rate": 2.7508449609136612e-05, "loss": 0.007, "step": 66610 }, { "loss_action": 0.009242733009159565, "loss_total": 0.009242733009159565, "step": 66610 }, { "grad_norm": 0.19654081761837006, "learning_rate": 2.749368347391454e-05, "loss": 0.0073, "step": 66620 }, { "loss_action": 0.010270554572343826, "loss_total": 0.010270554572343826, "step": 66620 }, { "grad_norm": 0.19312720000743866, "learning_rate": 2.7478919799949443e-05, "loss": 0.0075, "step": 66630 }, { "loss_action": 0.004855038598179817, "loss_total": 0.004855038598179817, "step": 66630 }, { "grad_norm": 0.2159373164176941, "learning_rate": 2.7464158588855803e-05, "loss": 0.0067, "step": 66640 }, { "loss_action": 0.0084086237475276, "loss_total": 0.0084086237475276, "step": 66640 }, { "grad_norm": 0.17152370512485504, "learning_rate": 2.7449399842247918e-05, "loss": 0.0077, "step": 66650 }, { "loss_action": 0.0063649374060332775, "loss_total": 0.0063649374060332775, "step": 66650 }, { "grad_norm": 0.2516312003135681, "learning_rate": 2.7434643561739736e-05, "loss": 0.0075, "step": 66660 }, { "loss_action": 0.004991243127733469, "loss_total": 0.004991243127733469, "step": 66660 }, { "grad_norm": 0.20879270136356354, "learning_rate": 2.7419889748945016e-05, "loss": 0.0074, "step": 66670 }, { "loss_action": 0.008981797844171524, "loss_total": 0.008981797844171524, "step": 66670 }, { "grad_norm": 0.17097559571266174, "learning_rate": 2.7405138405477203e-05, "loss": 0.008, "step": 66680 }, { "loss_action": 0.006468652747571468, "loss_total": 0.006468652747571468, "step": 66680 }, { "grad_norm": 0.23224647343158722, "learning_rate": 2.73903895329495e-05, "loss": 0.0074, "step": 66690 }, { "loss_action": 0.0060105593875050545, "loss_total": 0.0060105593875050545, "step": 66690 }, { "grad_norm": 0.17913345992565155, "learning_rate": 2.737564313297478e-05, "loss": 0.0083, "step": 66700 }, { "loss_action": 0.006634082645177841, "loss_total": 0.006634082645177841, "step": 66700 }, { "grad_norm": 0.16913244128227234, "learning_rate": 2.736089920716572e-05, "loss": 0.007, "step": 66710 }, { "loss_action": 0.007278721779584885, "loss_total": 0.007278721779584885, "step": 66710 }, { "grad_norm": 0.17241927981376648, "learning_rate": 2.7346157757134706e-05, "loss": 0.0068, "step": 66720 }, { "loss_action": 0.009479337371885777, "loss_total": 0.009479337371885777, "step": 66720 }, { "grad_norm": 0.18489934504032135, "learning_rate": 2.733141878449379e-05, "loss": 0.0073, "step": 66730 }, { "loss_action": 0.004526163917034864, "loss_total": 0.004526163917034864, "step": 66730 }, { "grad_norm": 0.19824479520320892, "learning_rate": 2.7316682290854844e-05, "loss": 0.0081, "step": 66740 }, { "loss_action": 0.012707291170954704, "loss_total": 0.012707291170954704, "step": 66740 }, { "grad_norm": 0.17160674929618835, "learning_rate": 2.7301948277829414e-05, "loss": 0.0077, "step": 66750 }, { "loss_action": 0.0063613224774599075, "loss_total": 0.0063613224774599075, "step": 66750 }, { "grad_norm": 0.2691430449485779, "learning_rate": 2.7287216747028814e-05, "loss": 0.0075, "step": 66760 }, { "loss_action": 0.005450420547276735, "loss_total": 0.005450420547276735, "step": 66760 }, { "grad_norm": 0.15298044681549072, "learning_rate": 2.7272487700064025e-05, "loss": 0.0077, "step": 66770 }, { "loss_action": 0.007120095659047365, "loss_total": 0.007120095659047365, "step": 66770 }, { "grad_norm": 0.21604344248771667, "learning_rate": 2.725776113854583e-05, "loss": 0.0075, "step": 66780 }, { "loss_action": 0.005927383899688721, "loss_total": 0.005927383899688721, "step": 66780 }, { "grad_norm": 0.22148679196834564, "learning_rate": 2.7243037064084664e-05, "loss": 0.0077, "step": 66790 }, { "loss_action": 0.005277945660054684, "loss_total": 0.005277945660054684, "step": 66790 }, { "grad_norm": 0.2514350712299347, "learning_rate": 2.7228315478290766e-05, "loss": 0.0087, "step": 66800 }, { "loss_action": 0.005492793396115303, "loss_total": 0.005492793396115303, "step": 66800 }, { "grad_norm": 0.20320570468902588, "learning_rate": 2.721359638277402e-05, "loss": 0.0065, "step": 66810 }, { "loss_action": 0.007755005266517401, "loss_total": 0.007755005266517401, "step": 66810 }, { "grad_norm": 0.19974969327449799, "learning_rate": 2.7198879779144148e-05, "loss": 0.0076, "step": 66820 }, { "loss_action": 0.006583583541214466, "loss_total": 0.006583583541214466, "step": 66820 }, { "grad_norm": 0.1997341811656952, "learning_rate": 2.7184165669010485e-05, "loss": 0.0072, "step": 66830 }, { "loss_action": 0.009967606514692307, "loss_total": 0.009967606514692307, "step": 66830 }, { "grad_norm": 0.16344629228115082, "learning_rate": 2.716945405398218e-05, "loss": 0.008, "step": 66840 }, { "loss_action": 0.008066387847065926, "loss_total": 0.008066387847065926, "step": 66840 }, { "grad_norm": 0.24380604922771454, "learning_rate": 2.715474493566803e-05, "loss": 0.0077, "step": 66850 }, { "loss_action": 0.01015537977218628, "loss_total": 0.01015537977218628, "step": 66850 }, { "grad_norm": 0.22543451189994812, "learning_rate": 2.7140038315676652e-05, "loss": 0.0082, "step": 66860 }, { "loss_action": 0.011252597905695438, "loss_total": 0.011252597905695438, "step": 66860 }, { "grad_norm": 0.1792244166135788, "learning_rate": 2.7125334195616275e-05, "loss": 0.0095, "step": 66870 }, { "loss_action": 0.008775128982961178, "loss_total": 0.008775128982961178, "step": 66870 }, { "grad_norm": 0.18740692734718323, "learning_rate": 2.7110632577094997e-05, "loss": 0.0073, "step": 66880 }, { "loss_action": 0.011358009651303291, "loss_total": 0.011358009651303291, "step": 66880 }, { "grad_norm": 0.1353306770324707, "learning_rate": 2.709593346172051e-05, "loss": 0.0067, "step": 66890 }, { "loss_action": 0.005141355562955141, "loss_total": 0.005141355562955141, "step": 66890 }, { "grad_norm": 0.20843908190727234, "learning_rate": 2.708123685110032e-05, "loss": 0.0066, "step": 66900 }, { "loss_action": 0.006559355184435844, "loss_total": 0.006559355184435844, "step": 66900 }, { "grad_norm": 0.2122429460287094, "learning_rate": 2.7066542746841588e-05, "loss": 0.0072, "step": 66910 }, { "loss_action": 0.006340331397950649, "loss_total": 0.006340331397950649, "step": 66910 }, { "grad_norm": 0.16655957698822021, "learning_rate": 2.7051851150551267e-05, "loss": 0.0069, "step": 66920 }, { "loss_action": 0.007480129599571228, "loss_total": 0.007480129599571228, "step": 66920 }, { "grad_norm": 0.17203864455223083, "learning_rate": 2.7037162063835996e-05, "loss": 0.0067, "step": 66930 }, { "loss_action": 0.008671986870467663, "loss_total": 0.008671986870467663, "step": 66930 }, { "grad_norm": 0.15493258833885193, "learning_rate": 2.702247548830218e-05, "loss": 0.007, "step": 66940 }, { "loss_action": 0.006800761912018061, "loss_total": 0.006800761912018061, "step": 66940 }, { "grad_norm": 0.2376495897769928, "learning_rate": 2.7007791425555883e-05, "loss": 0.0075, "step": 66950 }, { "loss_action": 0.007106384728103876, "loss_total": 0.007106384728103876, "step": 66950 }, { "grad_norm": 0.20272736251354218, "learning_rate": 2.6993109877202945e-05, "loss": 0.0076, "step": 66960 }, { "loss_action": 0.006117668002843857, "loss_total": 0.006117668002843857, "step": 66960 }, { "grad_norm": 0.1978307068347931, "learning_rate": 2.6978430844848935e-05, "loss": 0.0063, "step": 66970 }, { "loss_action": 0.006428861990571022, "loss_total": 0.006428861990571022, "step": 66970 }, { "grad_norm": 0.23073552548885345, "learning_rate": 2.69637543300991e-05, "loss": 0.0073, "step": 66980 }, { "loss_action": 0.008254057727754116, "loss_total": 0.008254057727754116, "step": 66980 }, { "grad_norm": 0.19482308626174927, "learning_rate": 2.694908033455848e-05, "loss": 0.0073, "step": 66990 }, { "loss_action": 0.009129134938120842, "loss_total": 0.009129134938120842, "step": 66990 }, { "grad_norm": 0.17293000221252441, "learning_rate": 2.6934408859831733e-05, "loss": 0.0068, "step": 67000 }, { "loss_action": 0.0065863970667123795, "loss_total": 0.0065863970667123795, "step": 67000 }, { "grad_norm": 0.13668493926525116, "learning_rate": 2.69197399075234e-05, "loss": 0.0074, "step": 67010 }, { "loss_action": 0.004671063739806414, "loss_total": 0.004671063739806414, "step": 67010 }, { "grad_norm": 0.21325358748435974, "learning_rate": 2.6905073479237584e-05, "loss": 0.007, "step": 67020 }, { "loss_action": 0.005337847396731377, "loss_total": 0.005337847396731377, "step": 67020 }, { "grad_norm": 0.19484418630599976, "learning_rate": 2.6890409576578235e-05, "loss": 0.0065, "step": 67030 }, { "loss_action": 0.005520375445485115, "loss_total": 0.005520375445485115, "step": 67030 }, { "grad_norm": 0.2542271614074707, "learning_rate": 2.687574820114892e-05, "loss": 0.007, "step": 67040 }, { "loss_action": 0.010171406902372837, "loss_total": 0.010171406902372837, "step": 67040 }, { "grad_norm": 0.24599093198776245, "learning_rate": 2.686108935455305e-05, "loss": 0.0075, "step": 67050 }, { "loss_action": 0.008676459081470966, "loss_total": 0.008676459081470966, "step": 67050 }, { "grad_norm": 0.19252076745033264, "learning_rate": 2.6846433038393603e-05, "loss": 0.0071, "step": 67060 }, { "loss_action": 0.012761293910443783, "loss_total": 0.012761293910443783, "step": 67060 }, { "grad_norm": 0.24118326604366302, "learning_rate": 2.6831779254273482e-05, "loss": 0.0072, "step": 67070 }, { "loss_action": 0.008325924165546894, "loss_total": 0.008325924165546894, "step": 67070 }, { "grad_norm": 0.19116146862506866, "learning_rate": 2.6817128003795122e-05, "loss": 0.0076, "step": 67080 }, { "loss_action": 0.007964997552335262, "loss_total": 0.007964997552335262, "step": 67080 }, { "grad_norm": 0.17950975894927979, "learning_rate": 2.680247928856081e-05, "loss": 0.0083, "step": 67090 }, { "loss_action": 0.010023795068264008, "loss_total": 0.010023795068264008, "step": 67090 }, { "grad_norm": 0.25843745470046997, "learning_rate": 2.6787833110172466e-05, "loss": 0.0084, "step": 67100 }, { "loss_action": 0.008714018389582634, "loss_total": 0.008714018389582634, "step": 67100 }, { "grad_norm": 0.2230965495109558, "learning_rate": 2.6773189470231807e-05, "loss": 0.0081, "step": 67110 }, { "loss_action": 0.005036382935941219, "loss_total": 0.005036382935941219, "step": 67110 }, { "grad_norm": 0.18887284398078918, "learning_rate": 2.675854837034022e-05, "loss": 0.0071, "step": 67120 }, { "loss_action": 0.007322787307202816, "loss_total": 0.007322787307202816, "step": 67120 }, { "grad_norm": 0.1789020299911499, "learning_rate": 2.6743909812098833e-05, "loss": 0.0064, "step": 67130 }, { "loss_action": 0.006372494623064995, "loss_total": 0.006372494623064995, "step": 67130 }, { "grad_norm": 0.18170620501041412, "learning_rate": 2.67292737971085e-05, "loss": 0.0072, "step": 67140 }, { "loss_action": 0.007543635554611683, "loss_total": 0.007543635554611683, "step": 67140 }, { "grad_norm": 0.16115736961364746, "learning_rate": 2.671464032696982e-05, "loss": 0.0064, "step": 67150 }, { "loss_action": 0.008073858916759491, "loss_total": 0.008073858916759491, "step": 67150 }, { "grad_norm": 0.18266205489635468, "learning_rate": 2.6700009403283055e-05, "loss": 0.0075, "step": 67160 }, { "loss_action": 0.004977915436029434, "loss_total": 0.004977915436029434, "step": 67160 }, { "grad_norm": 0.18372340500354767, "learning_rate": 2.6685381027648214e-05, "loss": 0.0062, "step": 67170 }, { "loss_action": 0.005320078693330288, "loss_total": 0.005320078693330288, "step": 67170 }, { "grad_norm": 0.1700308918952942, "learning_rate": 2.6670755201665086e-05, "loss": 0.0067, "step": 67180 }, { "loss_action": 0.013090048916637897, "loss_total": 0.013090048916637897, "step": 67180 }, { "grad_norm": 0.22326894104480743, "learning_rate": 2.6656131926933066e-05, "loss": 0.008, "step": 67190 }, { "loss_action": 0.007235069293528795, "loss_total": 0.007235069293528795, "step": 67190 }, { "grad_norm": 0.23706163465976715, "learning_rate": 2.664151120505136e-05, "loss": 0.0071, "step": 67200 }, { "loss_action": 0.006723386235535145, "loss_total": 0.006723386235535145, "step": 67200 }, { "grad_norm": 0.21393686532974243, "learning_rate": 2.6626893037618873e-05, "loss": 0.0074, "step": 67210 }, { "loss_action": 0.005176436621695757, "loss_total": 0.005176436621695757, "step": 67210 }, { "grad_norm": 0.19264435768127441, "learning_rate": 2.6612277426234243e-05, "loss": 0.008, "step": 67220 }, { "loss_action": 0.00713193416595459, "loss_total": 0.00713193416595459, "step": 67220 }, { "grad_norm": 0.24638813734054565, "learning_rate": 2.659766437249577e-05, "loss": 0.0066, "step": 67230 }, { "loss_action": 0.008105718530714512, "loss_total": 0.008105718530714512, "step": 67230 }, { "grad_norm": 0.17866310477256775, "learning_rate": 2.6583053878001557e-05, "loss": 0.0069, "step": 67240 }, { "loss_action": 0.007008826360106468, "loss_total": 0.007008826360106468, "step": 67240 }, { "grad_norm": 0.200954407453537, "learning_rate": 2.6568445944349323e-05, "loss": 0.007, "step": 67250 }, { "loss_action": 0.006081764120608568, "loss_total": 0.006081764120608568, "step": 67250 }, { "grad_norm": 0.18467748165130615, "learning_rate": 2.6553840573136657e-05, "loss": 0.0065, "step": 67260 }, { "loss_action": 0.007056940346956253, "loss_total": 0.007056940346956253, "step": 67260 }, { "grad_norm": 0.19513612985610962, "learning_rate": 2.6539237765960706e-05, "loss": 0.0073, "step": 67270 }, { "loss_action": 0.00691112270578742, "loss_total": 0.00691112270578742, "step": 67270 }, { "grad_norm": 0.17751753330230713, "learning_rate": 2.6524637524418465e-05, "loss": 0.0066, "step": 67280 }, { "loss_action": 0.0056744408793747425, "loss_total": 0.0056744408793747425, "step": 67280 }, { "grad_norm": 0.15480051934719086, "learning_rate": 2.651003985010655e-05, "loss": 0.0069, "step": 67290 }, { "loss_action": 0.005769119597971439, "loss_total": 0.005769119597971439, "step": 67290 }, { "grad_norm": 0.2050425112247467, "learning_rate": 2.649544474462138e-05, "loss": 0.0066, "step": 67300 }, { "loss_action": 0.007605806924402714, "loss_total": 0.007605806924402714, "step": 67300 }, { "grad_norm": 0.25295335054397583, "learning_rate": 2.6480852209559015e-05, "loss": 0.0079, "step": 67310 }, { "loss_action": 0.008410865440964699, "loss_total": 0.008410865440964699, "step": 67310 }, { "grad_norm": 0.2157375067472458, "learning_rate": 2.6466262246515296e-05, "loss": 0.0074, "step": 67320 }, { "loss_action": 0.007389521691948175, "loss_total": 0.007389521691948175, "step": 67320 }, { "grad_norm": 0.21783211827278137, "learning_rate": 2.6451674857085746e-05, "loss": 0.0073, "step": 67330 }, { "loss_action": 0.008154981769621372, "loss_total": 0.008154981769621372, "step": 67330 }, { "grad_norm": 0.264784038066864, "learning_rate": 2.6437090042865655e-05, "loss": 0.0079, "step": 67340 }, { "loss_action": 0.006676834542304277, "loss_total": 0.006676834542304277, "step": 67340 }, { "grad_norm": 0.20794948935508728, "learning_rate": 2.6422507805449947e-05, "loss": 0.0067, "step": 67350 }, { "loss_action": 0.010284189134836197, "loss_total": 0.010284189134836197, "step": 67350 }, { "grad_norm": 0.1447896808385849, "learning_rate": 2.6407928146433357e-05, "loss": 0.0088, "step": 67360 }, { "loss_action": 0.005057451780885458, "loss_total": 0.005057451780885458, "step": 67360 }, { "grad_norm": 0.17416265606880188, "learning_rate": 2.639335106741026e-05, "loss": 0.0069, "step": 67370 }, { "loss_action": 0.008085259236395359, "loss_total": 0.008085259236395359, "step": 67370 }, { "grad_norm": 0.23425133526325226, "learning_rate": 2.6378776569974796e-05, "loss": 0.0071, "step": 67380 }, { "loss_action": 0.01004431489855051, "loss_total": 0.01004431489855051, "step": 67380 }, { "grad_norm": 0.21440349519252777, "learning_rate": 2.6364204655720814e-05, "loss": 0.0076, "step": 67390 }, { "loss_action": 0.017326755449175835, "loss_total": 0.017326755449175835, "step": 67390 }, { "grad_norm": 0.17503583431243896, "learning_rate": 2.6349635326241894e-05, "loss": 0.0085, "step": 67400 }, { "loss_action": 0.00462440587580204, "loss_total": 0.00462440587580204, "step": 67400 }, { "grad_norm": 0.18385198712348938, "learning_rate": 2.633506858313127e-05, "loss": 0.0079, "step": 67410 }, { "loss_action": 0.006145888473838568, "loss_total": 0.006145888473838568, "step": 67410 }, { "grad_norm": 0.20603103935718536, "learning_rate": 2.6320504427981975e-05, "loss": 0.0077, "step": 67420 }, { "loss_action": 0.006064503453671932, "loss_total": 0.006064503453671932, "step": 67420 }, { "grad_norm": 0.1894744336605072, "learning_rate": 2.6305942862386734e-05, "loss": 0.0072, "step": 67430 }, { "loss_action": 0.005807515699416399, "loss_total": 0.005807515699416399, "step": 67430 }, { "grad_norm": 0.1780286580324173, "learning_rate": 2.629138388793793e-05, "loss": 0.0064, "step": 67440 }, { "loss_action": 0.005293319001793861, "loss_total": 0.005293319001793861, "step": 67440 }, { "grad_norm": 0.1856938898563385, "learning_rate": 2.6276827506227743e-05, "loss": 0.0077, "step": 67450 }, { "loss_action": 0.007376858498901129, "loss_total": 0.007376858498901129, "step": 67450 }, { "grad_norm": 0.21121148765087128, "learning_rate": 2.6262273718848037e-05, "loss": 0.0079, "step": 67460 }, { "loss_action": 0.006093399599194527, "loss_total": 0.006093399599194527, "step": 67460 }, { "grad_norm": 0.21035867929458618, "learning_rate": 2.6247722527390407e-05, "loss": 0.0069, "step": 67470 }, { "loss_action": 0.007416005712002516, "loss_total": 0.007416005712002516, "step": 67470 }, { "grad_norm": 0.1906052827835083, "learning_rate": 2.6233173933446104e-05, "loss": 0.0069, "step": 67480 }, { "loss_action": 0.008559205569326878, "loss_total": 0.008559205569326878, "step": 67480 }, { "grad_norm": 0.17396634817123413, "learning_rate": 2.6218627938606188e-05, "loss": 0.0078, "step": 67490 }, { "loss_action": 0.007175891660153866, "loss_total": 0.007175891660153866, "step": 67490 }, { "grad_norm": 0.16199833154678345, "learning_rate": 2.620408454446135e-05, "loss": 0.0071, "step": 67500 }, { "loss_action": 0.007317421957850456, "loss_total": 0.007317421957850456, "step": 67500 }, { "grad_norm": 0.20520715415477753, "learning_rate": 2.6189543752602046e-05, "loss": 0.0067, "step": 67510 }, { "loss_action": 0.00850517675280571, "loss_total": 0.00850517675280571, "step": 67510 }, { "grad_norm": 0.1578545719385147, "learning_rate": 2.6175005564618444e-05, "loss": 0.0068, "step": 67520 }, { "loss_action": 0.007232511881738901, "loss_total": 0.007232511881738901, "step": 67520 }, { "grad_norm": 0.18842503428459167, "learning_rate": 2.6160469982100428e-05, "loss": 0.0066, "step": 67530 }, { "loss_action": 0.004980510100722313, "loss_total": 0.004980510100722313, "step": 67530 }, { "grad_norm": 0.15281106531620026, "learning_rate": 2.6145937006637555e-05, "loss": 0.0069, "step": 67540 }, { "loss_action": 0.007625861093401909, "loss_total": 0.007625861093401909, "step": 67540 }, { "grad_norm": 0.18573518097400665, "learning_rate": 2.6131406639819166e-05, "loss": 0.0071, "step": 67550 }, { "loss_action": 0.008187739178538322, "loss_total": 0.008187739178538322, "step": 67550 }, { "grad_norm": 0.27344417572021484, "learning_rate": 2.611687888323424e-05, "loss": 0.0088, "step": 67560 }, { "loss_action": 0.0059665497392416, "loss_total": 0.0059665497392416, "step": 67560 }, { "grad_norm": 0.1591988056898117, "learning_rate": 2.610235373847153e-05, "loss": 0.0075, "step": 67570 }, { "loss_action": 0.005763839930295944, "loss_total": 0.005763839930295944, "step": 67570 }, { "grad_norm": 0.16040946543216705, "learning_rate": 2.6087831207119494e-05, "loss": 0.007, "step": 67580 }, { "loss_action": 0.005841583013534546, "loss_total": 0.005841583013534546, "step": 67580 }, { "grad_norm": 0.17015862464904785, "learning_rate": 2.60733112907663e-05, "loss": 0.0072, "step": 67590 }, { "loss_action": 0.009197043254971504, "loss_total": 0.009197043254971504, "step": 67590 }, { "grad_norm": 0.1912977397441864, "learning_rate": 2.6058793990999786e-05, "loss": 0.0073, "step": 67600 }, { "loss_action": 0.006778473034501076, "loss_total": 0.006778473034501076, "step": 67600 }, { "grad_norm": 0.24042056500911713, "learning_rate": 2.6044279309407593e-05, "loss": 0.007, "step": 67610 }, { "loss_action": 0.014175917953252792, "loss_total": 0.014175917953252792, "step": 67610 }, { "grad_norm": 0.17303527891635895, "learning_rate": 2.6029767247576976e-05, "loss": 0.008, "step": 67620 }, { "loss_action": 0.008168836124241352, "loss_total": 0.008168836124241352, "step": 67620 }, { "grad_norm": 0.17855682969093323, "learning_rate": 2.601525780709497e-05, "loss": 0.0073, "step": 67630 }, { "loss_action": 0.005269847344607115, "loss_total": 0.005269847344607115, "step": 67630 }, { "grad_norm": 0.1894785612821579, "learning_rate": 2.6000750989548318e-05, "loss": 0.0067, "step": 67640 }, { "loss_action": 0.005637737922370434, "loss_total": 0.005637737922370434, "step": 67640 }, { "grad_norm": 0.1563265323638916, "learning_rate": 2.5986246796523462e-05, "loss": 0.0068, "step": 67650 }, { "loss_action": 0.006244998890906572, "loss_total": 0.006244998890906572, "step": 67650 }, { "grad_norm": 0.21448159217834473, "learning_rate": 2.5971745229606546e-05, "loss": 0.0084, "step": 67660 }, { "loss_action": 0.005585353821516037, "loss_total": 0.005585353821516037, "step": 67660 }, { "grad_norm": 0.17283834517002106, "learning_rate": 2.5957246290383442e-05, "loss": 0.0075, "step": 67670 }, { "loss_action": 0.005964071489870548, "loss_total": 0.005964071489870548, "step": 67670 }, { "grad_norm": 0.3944547176361084, "learning_rate": 2.594274998043975e-05, "loss": 0.0066, "step": 67680 }, { "loss_action": 0.007460883352905512, "loss_total": 0.007460883352905512, "step": 67680 }, { "grad_norm": 0.18244551122188568, "learning_rate": 2.5928256301360733e-05, "loss": 0.0066, "step": 67690 }, { "loss_action": 0.006528576370328665, "loss_total": 0.006528576370328665, "step": 67690 }, { "grad_norm": 0.19842170178890228, "learning_rate": 2.591376525473142e-05, "loss": 0.0076, "step": 67700 }, { "loss_action": 0.0062327939085662365, "loss_total": 0.0062327939085662365, "step": 67700 }, { "grad_norm": 0.15213246643543243, "learning_rate": 2.5899276842136523e-05, "loss": 0.0066, "step": 67710 }, { "loss_action": 0.007999866269528866, "loss_total": 0.007999866269528866, "step": 67710 }, { "grad_norm": 0.2372686117887497, "learning_rate": 2.5884791065160495e-05, "loss": 0.0078, "step": 67720 }, { "loss_action": 0.007537775672972202, "loss_total": 0.007537775672972202, "step": 67720 }, { "grad_norm": 0.18456317484378815, "learning_rate": 2.5870307925387436e-05, "loss": 0.0076, "step": 67730 }, { "loss_action": 0.005685380659997463, "loss_total": 0.005685380659997463, "step": 67730 }, { "grad_norm": 0.2133864164352417, "learning_rate": 2.585582742440125e-05, "loss": 0.0071, "step": 67740 }, { "loss_action": 0.007470198906958103, "loss_total": 0.007470198906958103, "step": 67740 }, { "grad_norm": 0.18072828650474548, "learning_rate": 2.5841349563785455e-05, "loss": 0.0074, "step": 67750 }, { "loss_action": 0.0073379455134272575, "loss_total": 0.0073379455134272575, "step": 67750 }, { "grad_norm": 0.2298143059015274, "learning_rate": 2.5826874345123355e-05, "loss": 0.0072, "step": 67760 }, { "loss_action": 0.005792321637272835, "loss_total": 0.005792321637272835, "step": 67760 }, { "grad_norm": 0.17331166565418243, "learning_rate": 2.581240176999792e-05, "loss": 0.0063, "step": 67770 }, { "loss_action": 0.00669417018070817, "loss_total": 0.00669417018070817, "step": 67770 }, { "grad_norm": 0.2106565684080124, "learning_rate": 2.579793183999189e-05, "loss": 0.0076, "step": 67780 }, { "loss_action": 0.008259008638560772, "loss_total": 0.008259008638560772, "step": 67780 }, { "grad_norm": 0.1939038783311844, "learning_rate": 2.5783464556687627e-05, "loss": 0.0071, "step": 67790 }, { "loss_action": 0.006176385097205639, "loss_total": 0.006176385097205639, "step": 67790 }, { "grad_norm": 0.18350371718406677, "learning_rate": 2.576899992166729e-05, "loss": 0.0064, "step": 67800 }, { "loss_action": 0.007566293701529503, "loss_total": 0.007566293701529503, "step": 67800 }, { "grad_norm": 0.21596577763557434, "learning_rate": 2.5754537936512668e-05, "loss": 0.0077, "step": 67810 }, { "loss_action": 0.008222915232181549, "loss_total": 0.008222915232181549, "step": 67810 }, { "grad_norm": 0.2211383432149887, "learning_rate": 2.574007860280535e-05, "loss": 0.0086, "step": 67820 }, { "loss_action": 0.005134571343660355, "loss_total": 0.005134571343660355, "step": 67820 }, { "grad_norm": 0.23496554791927338, "learning_rate": 2.5725621922126518e-05, "loss": 0.008, "step": 67830 }, { "loss_action": 0.005674147978425026, "loss_total": 0.005674147978425026, "step": 67830 }, { "grad_norm": 0.1437046229839325, "learning_rate": 2.571116789605722e-05, "loss": 0.0066, "step": 67840 }, { "loss_action": 0.00646321102976799, "loss_total": 0.00646321102976799, "step": 67840 }, { "grad_norm": 0.22080659866333008, "learning_rate": 2.5696716526178054e-05, "loss": 0.0065, "step": 67850 }, { "loss_action": 0.0069926404394209385, "loss_total": 0.0069926404394209385, "step": 67850 }, { "grad_norm": 0.14112795889377594, "learning_rate": 2.568226781406946e-05, "loss": 0.007, "step": 67860 }, { "loss_action": 0.005683532450348139, "loss_total": 0.005683532450348139, "step": 67860 }, { "grad_norm": 0.20222215354442596, "learning_rate": 2.5667821761311474e-05, "loss": 0.0079, "step": 67870 }, { "loss_action": 0.010274318978190422, "loss_total": 0.010274318978190422, "step": 67870 }, { "grad_norm": 0.24528488516807556, "learning_rate": 2.5653378369483917e-05, "loss": 0.0072, "step": 67880 }, { "loss_action": 0.010274163447320461, "loss_total": 0.010274163447320461, "step": 67880 }, { "grad_norm": 0.2088523507118225, "learning_rate": 2.5638937640166292e-05, "loss": 0.0077, "step": 67890 }, { "loss_action": 0.005807905457913876, "loss_total": 0.005807905457913876, "step": 67890 }, { "grad_norm": 0.18806643784046173, "learning_rate": 2.5624499574937842e-05, "loss": 0.0073, "step": 67900 }, { "loss_action": 0.009263573214411736, "loss_total": 0.009263573214411736, "step": 67900 }, { "grad_norm": 0.1470121443271637, "learning_rate": 2.5610064175377456e-05, "loss": 0.0074, "step": 67910 }, { "loss_action": 0.005022975616157055, "loss_total": 0.005022975616157055, "step": 67910 }, { "grad_norm": 0.19196918606758118, "learning_rate": 2.5595631443063782e-05, "loss": 0.0066, "step": 67920 }, { "loss_action": 0.005342812277376652, "loss_total": 0.005342812277376652, "step": 67920 }, { "grad_norm": 0.164451003074646, "learning_rate": 2.5581201379575177e-05, "loss": 0.0067, "step": 67930 }, { "loss_action": 0.008763821795582771, "loss_total": 0.008763821795582771, "step": 67930 }, { "grad_norm": 0.18207134306430817, "learning_rate": 2.5566773986489655e-05, "loss": 0.0084, "step": 67940 }, { "loss_action": 0.010498104616999626, "loss_total": 0.010498104616999626, "step": 67940 }, { "grad_norm": 0.15094898641109467, "learning_rate": 2.5552349265385e-05, "loss": 0.0065, "step": 67950 }, { "loss_action": 0.009211246855556965, "loss_total": 0.009211246855556965, "step": 67950 }, { "grad_norm": 0.14998377859592438, "learning_rate": 2.5537927217838675e-05, "loss": 0.0076, "step": 67960 }, { "loss_action": 0.011048604734241962, "loss_total": 0.011048604734241962, "step": 67960 }, { "grad_norm": 0.17304548621177673, "learning_rate": 2.5523507845427864e-05, "loss": 0.0072, "step": 67970 }, { "loss_action": 0.008545959368348122, "loss_total": 0.008545959368348122, "step": 67970 }, { "grad_norm": 0.21820597350597382, "learning_rate": 2.5509091149729413e-05, "loss": 0.0079, "step": 67980 }, { "loss_action": 0.006895330268889666, "loss_total": 0.006895330268889666, "step": 67980 }, { "grad_norm": 0.18804018199443817, "learning_rate": 2.5494677132319962e-05, "loss": 0.0068, "step": 67990 }, { "loss_action": 0.005937025882303715, "loss_total": 0.005937025882303715, "step": 67990 }, { "grad_norm": 0.19935649633407593, "learning_rate": 2.548026579477575e-05, "loss": 0.0071, "step": 68000 }, { "loss_action": 0.005478973034769297, "loss_total": 0.005478973034769297, "step": 68000 }, { "grad_norm": 0.1496768593788147, "learning_rate": 2.5465857138672834e-05, "loss": 0.0071, "step": 68010 }, { "loss_action": 0.004162587691098452, "loss_total": 0.004162587691098452, "step": 68010 }, { "grad_norm": 0.165986567735672, "learning_rate": 2.5451451165586848e-05, "loss": 0.0078, "step": 68020 }, { "loss_action": 0.005494952667504549, "loss_total": 0.005494952667504549, "step": 68020 }, { "grad_norm": 0.18312309682369232, "learning_rate": 2.543704787709329e-05, "loss": 0.0064, "step": 68030 }, { "loss_action": 0.0100377993658185, "loss_total": 0.0100377993658185, "step": 68030 }, { "grad_norm": 0.14350491762161255, "learning_rate": 2.542264727476723e-05, "loss": 0.0067, "step": 68040 }, { "loss_action": 0.003435088787227869, "loss_total": 0.003435088787227869, "step": 68040 }, { "grad_norm": 0.14025652408599854, "learning_rate": 2.5408249360183535e-05, "loss": 0.0062, "step": 68050 }, { "loss_action": 0.008049441501498222, "loss_total": 0.008049441501498222, "step": 68050 }, { "grad_norm": 0.19197586178779602, "learning_rate": 2.5393854134916694e-05, "loss": 0.0066, "step": 68060 }, { "loss_action": 0.009363149292767048, "loss_total": 0.009363149292767048, "step": 68060 }, { "grad_norm": 0.1912064254283905, "learning_rate": 2.5379461600540993e-05, "loss": 0.0071, "step": 68070 }, { "loss_action": 0.004999438766390085, "loss_total": 0.004999438766390085, "step": 68070 }, { "grad_norm": 0.20811493694782257, "learning_rate": 2.5365071758630317e-05, "loss": 0.0064, "step": 68080 }, { "loss_action": 0.005336953327059746, "loss_total": 0.005336953327059746, "step": 68080 }, { "grad_norm": 0.22112511098384857, "learning_rate": 2.535068461075839e-05, "loss": 0.0067, "step": 68090 }, { "loss_action": 0.006102968007326126, "loss_total": 0.006102968007326126, "step": 68090 }, { "grad_norm": 0.17851340770721436, "learning_rate": 2.5336300158498516e-05, "loss": 0.0072, "step": 68100 }, { "loss_action": 0.006461075972765684, "loss_total": 0.006461075972765684, "step": 68100 }, { "grad_norm": 0.1690184473991394, "learning_rate": 2.5321918403423793e-05, "loss": 0.0069, "step": 68110 }, { "loss_action": 0.00833767931908369, "loss_total": 0.00833767931908369, "step": 68110 }, { "grad_norm": 0.22709105908870697, "learning_rate": 2.5307539347106957e-05, "loss": 0.0081, "step": 68120 }, { "loss_action": 0.008701673708856106, "loss_total": 0.008701673708856106, "step": 68120 }, { "grad_norm": 0.17928192019462585, "learning_rate": 2.529316299112049e-05, "loss": 0.0067, "step": 68130 }, { "loss_action": 0.00699390284717083, "loss_total": 0.00699390284717083, "step": 68130 }, { "grad_norm": 0.19218170642852783, "learning_rate": 2.5278789337036567e-05, "loss": 0.0068, "step": 68140 }, { "loss_action": 0.006567971780896187, "loss_total": 0.006567971780896187, "step": 68140 }, { "grad_norm": 0.14302076399326324, "learning_rate": 2.52644183864271e-05, "loss": 0.0064, "step": 68150 }, { "loss_action": 0.010026355274021626, "loss_total": 0.010026355274021626, "step": 68150 }, { "grad_norm": 0.21584732830524445, "learning_rate": 2.525005014086363e-05, "loss": 0.0065, "step": 68160 }, { "loss_action": 0.004436879884451628, "loss_total": 0.004436879884451628, "step": 68160 }, { "grad_norm": 0.17867591977119446, "learning_rate": 2.5235684601917465e-05, "loss": 0.0066, "step": 68170 }, { "loss_action": 0.009794004261493683, "loss_total": 0.009794004261493683, "step": 68170 }, { "grad_norm": 0.19937019050121307, "learning_rate": 2.5221321771159618e-05, "loss": 0.0072, "step": 68180 }, { "loss_action": 0.005812806077301502, "loss_total": 0.005812806077301502, "step": 68180 }, { "grad_norm": 0.15266850590705872, "learning_rate": 2.5206961650160743e-05, "loss": 0.007, "step": 68190 }, { "loss_action": 0.004723537713289261, "loss_total": 0.004723537713289261, "step": 68190 }, { "grad_norm": 0.22221295535564423, "learning_rate": 2.519260424049129e-05, "loss": 0.0089, "step": 68200 }, { "loss_action": 0.007621157448738813, "loss_total": 0.007621157448738813, "step": 68200 }, { "grad_norm": 0.21468693017959595, "learning_rate": 2.5178249543721304e-05, "loss": 0.0074, "step": 68210 }, { "loss_action": 0.00517636351287365, "loss_total": 0.00517636351287365, "step": 68210 }, { "grad_norm": 0.27235493063926697, "learning_rate": 2.5163897561420668e-05, "loss": 0.0069, "step": 68220 }, { "loss_action": 0.0057831984013319016, "loss_total": 0.0057831984013319016, "step": 68220 }, { "grad_norm": 0.16940484941005707, "learning_rate": 2.514954829515883e-05, "loss": 0.007, "step": 68230 }, { "loss_action": 0.007364583667367697, "loss_total": 0.007364583667367697, "step": 68230 }, { "grad_norm": 0.14216633141040802, "learning_rate": 2.513520174650505e-05, "loss": 0.0077, "step": 68240 }, { "loss_action": 0.006167738698422909, "loss_total": 0.006167738698422909, "step": 68240 }, { "grad_norm": 0.16285154223442078, "learning_rate": 2.5120857917028207e-05, "loss": 0.0065, "step": 68250 }, { "loss_action": 0.009348302148282528, "loss_total": 0.009348302148282528, "step": 68250 }, { "grad_norm": 0.17351935803890228, "learning_rate": 2.5106516808296953e-05, "loss": 0.0064, "step": 68260 }, { "loss_action": 0.005514373537153006, "loss_total": 0.005514373537153006, "step": 68260 }, { "grad_norm": 0.17193901538848877, "learning_rate": 2.5092178421879552e-05, "loss": 0.0065, "step": 68270 }, { "loss_action": 0.00516765471547842, "loss_total": 0.00516765471547842, "step": 68270 }, { "grad_norm": 0.16548939049243927, "learning_rate": 2.5077842759344116e-05, "loss": 0.0069, "step": 68280 }, { "loss_action": 0.007500436156988144, "loss_total": 0.007500436156988144, "step": 68280 }, { "grad_norm": 0.19299733638763428, "learning_rate": 2.5063509822258304e-05, "loss": 0.0077, "step": 68290 }, { "loss_action": 0.007655549794435501, "loss_total": 0.007655549794435501, "step": 68290 }, { "grad_norm": 0.19610975682735443, "learning_rate": 2.5049179612189576e-05, "loss": 0.0073, "step": 68300 }, { "loss_action": 0.006144449580460787, "loss_total": 0.006144449580460787, "step": 68300 }, { "grad_norm": 0.19408999383449554, "learning_rate": 2.5034852130705043e-05, "loss": 0.0066, "step": 68310 }, { "loss_action": 0.006844816729426384, "loss_total": 0.006844816729426384, "step": 68310 }, { "grad_norm": 0.16936732828617096, "learning_rate": 2.5020527379371572e-05, "loss": 0.0071, "step": 68320 }, { "loss_action": 0.007847849279642105, "loss_total": 0.007847849279642105, "step": 68320 }, { "grad_norm": 0.18669763207435608, "learning_rate": 2.500620535975564e-05, "loss": 0.0076, "step": 68330 }, { "loss_action": 0.004556029103696346, "loss_total": 0.004556029103696346, "step": 68330 }, { "grad_norm": 0.15173400938510895, "learning_rate": 2.4991886073423515e-05, "loss": 0.0071, "step": 68340 }, { "loss_action": 0.005554034374654293, "loss_total": 0.005554034374654293, "step": 68340 }, { "grad_norm": 0.18060067296028137, "learning_rate": 2.4977569521941134e-05, "loss": 0.0059, "step": 68350 }, { "loss_action": 0.010558568872511387, "loss_total": 0.010558568872511387, "step": 68350 }, { "grad_norm": 0.2046828716993332, "learning_rate": 2.4963255706874143e-05, "loss": 0.0072, "step": 68360 }, { "loss_action": 0.0078048608265817165, "loss_total": 0.0078048608265817165, "step": 68360 }, { "grad_norm": 0.15840542316436768, "learning_rate": 2.4948944629787853e-05, "loss": 0.0065, "step": 68370 }, { "loss_action": 0.009583610109984875, "loss_total": 0.009583610109984875, "step": 68370 }, { "grad_norm": 0.21173526346683502, "learning_rate": 2.493463629224731e-05, "loss": 0.0069, "step": 68380 }, { "loss_action": 0.005061764270067215, "loss_total": 0.005061764270067215, "step": 68380 }, { "grad_norm": 0.2416701763868332, "learning_rate": 2.492033069581728e-05, "loss": 0.0067, "step": 68390 }, { "loss_action": 0.005887309554964304, "loss_total": 0.005887309554964304, "step": 68390 }, { "grad_norm": 0.30271440744400024, "learning_rate": 2.4906027842062137e-05, "loss": 0.0077, "step": 68400 }, { "loss_action": 0.007278966251760721, "loss_total": 0.007278966251760721, "step": 68400 }, { "grad_norm": 0.15448322892189026, "learning_rate": 2.48917277325461e-05, "loss": 0.0068, "step": 68410 }, { "loss_action": 0.005121384281665087, "loss_total": 0.005121384281665087, "step": 68410 }, { "grad_norm": 0.18589633703231812, "learning_rate": 2.487743036883295e-05, "loss": 0.0065, "step": 68420 }, { "loss_action": 0.005606099497526884, "loss_total": 0.005606099497526884, "step": 68420 }, { "grad_norm": 0.1871946156024933, "learning_rate": 2.486313575248626e-05, "loss": 0.0061, "step": 68430 }, { "loss_action": 0.010676862671971321, "loss_total": 0.010676862671971321, "step": 68430 }, { "grad_norm": 0.205193892121315, "learning_rate": 2.4848843885069235e-05, "loss": 0.0072, "step": 68440 }, { "loss_action": 0.007660983130335808, "loss_total": 0.007660983130335808, "step": 68440 }, { "grad_norm": 0.22889593243598938, "learning_rate": 2.483455476814484e-05, "loss": 0.0076, "step": 68450 }, { "loss_action": 0.009396274574100971, "loss_total": 0.009396274574100971, "step": 68450 }, { "grad_norm": 0.2029695212841034, "learning_rate": 2.4820268403275672e-05, "loss": 0.0063, "step": 68460 }, { "loss_action": 0.009440811350941658, "loss_total": 0.009440811350941658, "step": 68460 }, { "grad_norm": 0.16979877650737762, "learning_rate": 2.480598479202413e-05, "loss": 0.0066, "step": 68470 }, { "loss_action": 0.003972157370299101, "loss_total": 0.003972157370299101, "step": 68470 }, { "grad_norm": 0.18812298774719238, "learning_rate": 2.4791703935952193e-05, "loss": 0.0075, "step": 68480 }, { "loss_action": 0.006442203186452389, "loss_total": 0.006442203186452389, "step": 68480 }, { "grad_norm": 0.16425232589244843, "learning_rate": 2.477742583662163e-05, "loss": 0.0064, "step": 68490 }, { "loss_action": 0.00632589403539896, "loss_total": 0.00632589403539896, "step": 68490 }, { "grad_norm": 0.16409245133399963, "learning_rate": 2.476315049559384e-05, "loss": 0.0067, "step": 68500 }, { "loss_action": 0.010516451671719551, "loss_total": 0.010516451671719551, "step": 68500 }, { "grad_norm": 0.23580726981163025, "learning_rate": 2.4748877914429987e-05, "loss": 0.0067, "step": 68510 }, { "loss_action": 0.005657404661178589, "loss_total": 0.005657404661178589, "step": 68510 }, { "grad_norm": 0.17820678651332855, "learning_rate": 2.4734608094690857e-05, "loss": 0.0069, "step": 68520 }, { "loss_action": 0.006095274351537228, "loss_total": 0.006095274351537228, "step": 68520 }, { "grad_norm": 0.16705955564975739, "learning_rate": 2.4720341037937006e-05, "loss": 0.0055, "step": 68530 }, { "loss_action": 0.005218080710619688, "loss_total": 0.005218080710619688, "step": 68530 }, { "grad_norm": 0.21946874260902405, "learning_rate": 2.4706076745728645e-05, "loss": 0.0062, "step": 68540 }, { "loss_action": 0.005825522355735302, "loss_total": 0.005825522355735302, "step": 68540 }, { "grad_norm": 0.18348529934883118, "learning_rate": 2.469181521962573e-05, "loss": 0.0071, "step": 68550 }, { "loss_action": 0.004675894044339657, "loss_total": 0.004675894044339657, "step": 68550 }, { "grad_norm": 0.15614211559295654, "learning_rate": 2.467755646118783e-05, "loss": 0.0068, "step": 68560 }, { "loss_action": 0.00670988904312253, "loss_total": 0.00670988904312253, "step": 68560 }, { "grad_norm": 0.17154057323932648, "learning_rate": 2.46633004719743e-05, "loss": 0.0064, "step": 68570 }, { "loss_action": 0.006990546360611916, "loss_total": 0.006990546360611916, "step": 68570 }, { "grad_norm": 0.19544380903244019, "learning_rate": 2.4649047253544123e-05, "loss": 0.0074, "step": 68580 }, { "loss_action": 0.008262298069894314, "loss_total": 0.008262298069894314, "step": 68580 }, { "grad_norm": 0.24945130944252014, "learning_rate": 2.4634796807456016e-05, "loss": 0.0075, "step": 68590 }, { "loss_action": 0.005851299036294222, "loss_total": 0.005851299036294222, "step": 68590 }, { "grad_norm": 0.258690744638443, "learning_rate": 2.46205491352684e-05, "loss": 0.0083, "step": 68600 }, { "loss_action": 0.010467262007296085, "loss_total": 0.010467262007296085, "step": 68600 }, { "grad_norm": 0.23425815999507904, "learning_rate": 2.4606304238539375e-05, "loss": 0.0073, "step": 68610 }, { "loss_action": 0.010607268661260605, "loss_total": 0.010607268661260605, "step": 68610 }, { "grad_norm": 0.21595706045627594, "learning_rate": 2.4592062118826753e-05, "loss": 0.0072, "step": 68620 }, { "loss_action": 0.010200697928667068, "loss_total": 0.010200697928667068, "step": 68620 }, { "grad_norm": 0.20109015703201294, "learning_rate": 2.4577822777688004e-05, "loss": 0.0067, "step": 68630 }, { "loss_action": 0.0056208777241408825, "loss_total": 0.0056208777241408825, "step": 68630 }, { "grad_norm": 0.19087101519107819, "learning_rate": 2.4563586216680347e-05, "loss": 0.0081, "step": 68640 }, { "loss_action": 0.007673441432416439, "loss_total": 0.007673441432416439, "step": 68640 }, { "grad_norm": 0.21102049946784973, "learning_rate": 2.4549352437360622e-05, "loss": 0.0072, "step": 68650 }, { "loss_action": 0.007081108167767525, "loss_total": 0.007081108167767525, "step": 68650 }, { "grad_norm": 0.19429843127727509, "learning_rate": 2.4535121441285493e-05, "loss": 0.0076, "step": 68660 }, { "loss_action": 0.007025053258985281, "loss_total": 0.007025053258985281, "step": 68660 }, { "grad_norm": 0.1552242487668991, "learning_rate": 2.4520893230011172e-05, "loss": 0.0072, "step": 68670 }, { "loss_action": 0.0051326630637049675, "loss_total": 0.0051326630637049675, "step": 68670 }, { "grad_norm": 0.2334274798631668, "learning_rate": 2.450666780509368e-05, "loss": 0.0069, "step": 68680 }, { "loss_action": 0.006501346360892057, "loss_total": 0.006501346360892057, "step": 68680 }, { "grad_norm": 0.2074543684720993, "learning_rate": 2.4492445168088656e-05, "loss": 0.0078, "step": 68690 }, { "loss_action": 0.005735656712204218, "loss_total": 0.005735656712204218, "step": 68690 }, { "grad_norm": 0.2281021624803543, "learning_rate": 2.447822532055149e-05, "loss": 0.0075, "step": 68700 }, { "loss_action": 0.006142531055957079, "loss_total": 0.006142531055957079, "step": 68700 }, { "grad_norm": 0.23047296702861786, "learning_rate": 2.4464008264037212e-05, "loss": 0.0079, "step": 68710 }, { "loss_action": 0.006675651762634516, "loss_total": 0.006675651762634516, "step": 68710 }, { "grad_norm": 0.16024403274059296, "learning_rate": 2.4449794000100605e-05, "loss": 0.0072, "step": 68720 }, { "loss_action": 0.0061667198315262794, "loss_total": 0.0061667198315262794, "step": 68720 }, { "grad_norm": 0.16451537609100342, "learning_rate": 2.4435582530296108e-05, "loss": 0.0068, "step": 68730 }, { "loss_action": 0.0066858683712780476, "loss_total": 0.0066858683712780476, "step": 68730 }, { "grad_norm": 0.1879814714193344, "learning_rate": 2.4421373856177887e-05, "loss": 0.0072, "step": 68740 }, { "loss_action": 0.006045981775969267, "loss_total": 0.006045981775969267, "step": 68740 }, { "grad_norm": 0.196966752409935, "learning_rate": 2.440716797929975e-05, "loss": 0.0078, "step": 68750 }, { "loss_action": 0.005810311529785395, "loss_total": 0.005810311529785395, "step": 68750 }, { "grad_norm": 0.1847040355205536, "learning_rate": 2.439296490121526e-05, "loss": 0.0067, "step": 68760 }, { "loss_action": 0.012609847821295261, "loss_total": 0.012609847821295261, "step": 68760 }, { "grad_norm": 0.21862797439098358, "learning_rate": 2.4378764623477608e-05, "loss": 0.0077, "step": 68770 }, { "loss_action": 0.008780183270573616, "loss_total": 0.008780183270573616, "step": 68770 }, { "grad_norm": 0.18190740048885345, "learning_rate": 2.436456714763974e-05, "loss": 0.0078, "step": 68780 }, { "loss_action": 0.007157788146287203, "loss_total": 0.007157788146287203, "step": 68780 }, { "grad_norm": 0.17789970338344574, "learning_rate": 2.4350372475254262e-05, "loss": 0.0065, "step": 68790 }, { "loss_action": 0.0049234782345592976, "loss_total": 0.0049234782345592976, "step": 68790 }, { "grad_norm": 0.17502640187740326, "learning_rate": 2.433618060787351e-05, "loss": 0.0069, "step": 68800 }, { "loss_action": 0.007182871922850609, "loss_total": 0.007182871922850609, "step": 68800 }, { "grad_norm": 0.14183059334754944, "learning_rate": 2.432199154704944e-05, "loss": 0.0078, "step": 68810 }, { "loss_action": 0.007882853038609028, "loss_total": 0.007882853038609028, "step": 68810 }, { "grad_norm": 0.1807486116886139, "learning_rate": 2.430780529433377e-05, "loss": 0.0076, "step": 68820 }, { "loss_action": 0.007625670172274113, "loss_total": 0.007625670172274113, "step": 68820 }, { "grad_norm": 0.19964680075645447, "learning_rate": 2.42936218512779e-05, "loss": 0.0072, "step": 68830 }, { "loss_action": 0.008231189101934433, "loss_total": 0.008231189101934433, "step": 68830 }, { "grad_norm": 0.21666041016578674, "learning_rate": 2.427944121943288e-05, "loss": 0.0081, "step": 68840 }, { "loss_action": 0.006828168407082558, "loss_total": 0.006828168407082558, "step": 68840 }, { "grad_norm": 0.18549706041812897, "learning_rate": 2.4265263400349497e-05, "loss": 0.0066, "step": 68850 }, { "loss_action": 0.007686412427574396, "loss_total": 0.007686412427574396, "step": 68850 }, { "grad_norm": 0.19194002449512482, "learning_rate": 2.4251088395578213e-05, "loss": 0.0072, "step": 68860 }, { "loss_action": 0.00803967285901308, "loss_total": 0.00803967285901308, "step": 68860 }, { "grad_norm": 0.12455730140209198, "learning_rate": 2.4236916206669214e-05, "loss": 0.0064, "step": 68870 }, { "loss_action": 0.004416004288941622, "loss_total": 0.004416004288941622, "step": 68870 }, { "grad_norm": 0.19744062423706055, "learning_rate": 2.4222746835172304e-05, "loss": 0.0058, "step": 68880 }, { "loss_action": 0.004413909278810024, "loss_total": 0.004413909278810024, "step": 68880 }, { "grad_norm": 0.15071125328540802, "learning_rate": 2.4208580282637065e-05, "loss": 0.0072, "step": 68890 }, { "loss_action": 0.006377633195370436, "loss_total": 0.006377633195370436, "step": 68890 }, { "grad_norm": 0.16126473248004913, "learning_rate": 2.4194416550612687e-05, "loss": 0.0062, "step": 68900 }, { "loss_action": 0.004721436649560928, "loss_total": 0.004721436649560928, "step": 68900 }, { "grad_norm": 0.18759188055992126, "learning_rate": 2.418025564064812e-05, "loss": 0.0073, "step": 68910 }, { "loss_action": 0.0053931730799376965, "loss_total": 0.0053931730799376965, "step": 68910 }, { "grad_norm": 0.206501767039299, "learning_rate": 2.4166097554291978e-05, "loss": 0.0065, "step": 68920 }, { "loss_action": 0.008528663776814938, "loss_total": 0.008528663776814938, "step": 68920 }, { "grad_norm": 0.18782544136047363, "learning_rate": 2.4151942293092583e-05, "loss": 0.0063, "step": 68930 }, { "loss_action": 0.005953522399067879, "loss_total": 0.005953522399067879, "step": 68930 }, { "grad_norm": 0.14139826595783234, "learning_rate": 2.41377898585979e-05, "loss": 0.0068, "step": 68940 }, { "loss_action": 0.011432264000177383, "loss_total": 0.011432264000177383, "step": 68940 }, { "grad_norm": 0.16240164637565613, "learning_rate": 2.4123640252355652e-05, "loss": 0.0079, "step": 68950 }, { "loss_action": 0.005475597456097603, "loss_total": 0.005475597456097603, "step": 68950 }, { "grad_norm": 0.1930711567401886, "learning_rate": 2.410949347591318e-05, "loss": 0.0067, "step": 68960 }, { "loss_action": 0.005271425470709801, "loss_total": 0.005271425470709801, "step": 68960 }, { "grad_norm": 0.16255201399326324, "learning_rate": 2.4095349530817578e-05, "loss": 0.0076, "step": 68970 }, { "loss_action": 0.009332884103059769, "loss_total": 0.009332884103059769, "step": 68970 }, { "grad_norm": 0.17317168414592743, "learning_rate": 2.4081208418615603e-05, "loss": 0.007, "step": 68980 }, { "loss_action": 0.005762219429016113, "loss_total": 0.005762219429016113, "step": 68980 }, { "grad_norm": 0.13505269587039948, "learning_rate": 2.4067070140853725e-05, "loss": 0.0063, "step": 68990 }, { "loss_action": 0.004949070978909731, "loss_total": 0.004949070978909731, "step": 68990 }, { "grad_norm": 0.1974364072084427, "learning_rate": 2.405293469907805e-05, "loss": 0.0065, "step": 69000 }, { "loss_action": 0.009797428734600544, "loss_total": 0.009797428734600544, "step": 69000 }, { "grad_norm": 0.20797912776470184, "learning_rate": 2.4038802094834446e-05, "loss": 0.0067, "step": 69010 }, { "loss_action": 0.006288568023592234, "loss_total": 0.006288568023592234, "step": 69010 }, { "grad_norm": 0.26085004210472107, "learning_rate": 2.4024672329668395e-05, "loss": 0.0071, "step": 69020 }, { "loss_action": 0.008215508423745632, "loss_total": 0.008215508423745632, "step": 69020 }, { "grad_norm": 0.3261229395866394, "learning_rate": 2.4010545405125125e-05, "loss": 0.0066, "step": 69030 }, { "loss_action": 0.007123840041458607, "loss_total": 0.007123840041458607, "step": 69030 }, { "grad_norm": 0.22389961779117584, "learning_rate": 2.3996421322749528e-05, "loss": 0.0078, "step": 69040 }, { "loss_action": 0.0064049968495965, "loss_total": 0.0064049968495965, "step": 69040 }, { "grad_norm": 0.2549476623535156, "learning_rate": 2.3982300084086224e-05, "loss": 0.0073, "step": 69050 }, { "loss_action": 0.004849051591008902, "loss_total": 0.004849051591008902, "step": 69050 }, { "grad_norm": 0.15030203759670258, "learning_rate": 2.396818169067944e-05, "loss": 0.0057, "step": 69060 }, { "loss_action": 0.007548141293227673, "loss_total": 0.007548141293227673, "step": 69060 }, { "grad_norm": 0.1596686989068985, "learning_rate": 2.3954066144073178e-05, "loss": 0.0064, "step": 69070 }, { "loss_action": 0.0074787684716284275, "loss_total": 0.0074787684716284275, "step": 69070 }, { "grad_norm": 0.14460442960262299, "learning_rate": 2.39399534458111e-05, "loss": 0.0069, "step": 69080 }, { "loss_action": 0.005523845087736845, "loss_total": 0.005523845087736845, "step": 69080 }, { "grad_norm": 0.15298421680927277, "learning_rate": 2.392584359743651e-05, "loss": 0.0068, "step": 69090 }, { "loss_action": 0.011804991401731968, "loss_total": 0.011804991401731968, "step": 69090 }, { "grad_norm": 0.1505812555551529, "learning_rate": 2.3911736600492463e-05, "loss": 0.0073, "step": 69100 }, { "loss_action": 0.006530785001814365, "loss_total": 0.006530785001814365, "step": 69100 }, { "grad_norm": 0.2267545908689499, "learning_rate": 2.3897632456521672e-05, "loss": 0.0083, "step": 69110 }, { "loss_action": 0.007319556549191475, "loss_total": 0.007319556549191475, "step": 69110 }, { "grad_norm": 0.2219635248184204, "learning_rate": 2.388353116706658e-05, "loss": 0.0073, "step": 69120 }, { "loss_action": 0.006942101754248142, "loss_total": 0.006942101754248142, "step": 69120 }, { "grad_norm": 0.19735954701900482, "learning_rate": 2.3869432733669232e-05, "loss": 0.0061, "step": 69130 }, { "loss_action": 0.007185520604252815, "loss_total": 0.007185520604252815, "step": 69130 }, { "grad_norm": 0.24176225066184998, "learning_rate": 2.385533715787145e-05, "loss": 0.0076, "step": 69140 }, { "loss_action": 0.006856812164187431, "loss_total": 0.006856812164187431, "step": 69140 }, { "grad_norm": 0.23834829032421112, "learning_rate": 2.3841244441214673e-05, "loss": 0.0065, "step": 69150 }, { "loss_action": 0.006646841764450073, "loss_total": 0.006646841764450073, "step": 69150 }, { "grad_norm": 0.1902933120727539, "learning_rate": 2.3827154585240073e-05, "loss": 0.0069, "step": 69160 }, { "loss_action": 0.008127879351377487, "loss_total": 0.008127879351377487, "step": 69160 }, { "grad_norm": 0.1578875035047531, "learning_rate": 2.3813067591488498e-05, "loss": 0.0065, "step": 69170 }, { "loss_action": 0.0058656553737819195, "loss_total": 0.0058656553737819195, "step": 69170 }, { "grad_norm": 0.1646549552679062, "learning_rate": 2.3798983461500494e-05, "loss": 0.007, "step": 69180 }, { "loss_action": 0.006320071406662464, "loss_total": 0.006320071406662464, "step": 69180 }, { "grad_norm": 0.1861567348241806, "learning_rate": 2.3784902196816256e-05, "loss": 0.006, "step": 69190 }, { "loss_action": 0.007482828572392464, "loss_total": 0.007482828572392464, "step": 69190 }, { "grad_norm": 0.15637555718421936, "learning_rate": 2.3770823798975716e-05, "loss": 0.0074, "step": 69200 }, { "loss_action": 0.008647995069622993, "loss_total": 0.008647995069622993, "step": 69200 }, { "grad_norm": 0.16263259947299957, "learning_rate": 2.3756748269518424e-05, "loss": 0.0071, "step": 69210 }, { "loss_action": 0.005996769294142723, "loss_total": 0.005996769294142723, "step": 69210 }, { "grad_norm": 0.17789018154144287, "learning_rate": 2.374267560998371e-05, "loss": 0.0068, "step": 69220 }, { "loss_action": 0.006151548121124506, "loss_total": 0.006151548121124506, "step": 69220 }, { "grad_norm": 0.17311617732048035, "learning_rate": 2.3728605821910477e-05, "loss": 0.007, "step": 69230 }, { "loss_action": 0.009977881796658039, "loss_total": 0.009977881796658039, "step": 69230 }, { "grad_norm": 0.13084830343723297, "learning_rate": 2.3714538906837453e-05, "loss": 0.0067, "step": 69240 }, { "loss_action": 0.004443482495844364, "loss_total": 0.004443482495844364, "step": 69240 }, { "grad_norm": 0.1459260731935501, "learning_rate": 2.3700474866302913e-05, "loss": 0.0071, "step": 69250 }, { "loss_action": 0.00801368709653616, "loss_total": 0.00801368709653616, "step": 69250 }, { "grad_norm": 0.17479506134986877, "learning_rate": 2.3686413701844917e-05, "loss": 0.0071, "step": 69260 }, { "loss_action": 0.009217723272740841, "loss_total": 0.009217723272740841, "step": 69260 }, { "grad_norm": 0.21931423246860504, "learning_rate": 2.367235541500114e-05, "loss": 0.0073, "step": 69270 }, { "loss_action": 0.00718327471986413, "loss_total": 0.00718327471986413, "step": 69270 }, { "grad_norm": 0.18095894157886505, "learning_rate": 2.3658300007308993e-05, "loss": 0.0066, "step": 69280 }, { "loss_action": 0.007432511541992426, "loss_total": 0.007432511541992426, "step": 69280 }, { "grad_norm": 0.21831177175045013, "learning_rate": 2.364424748030555e-05, "loss": 0.0061, "step": 69290 }, { "loss_action": 0.0056365174241364, "loss_total": 0.0056365174241364, "step": 69290 }, { "grad_norm": 0.1978246569633484, "learning_rate": 2.3630197835527595e-05, "loss": 0.0058, "step": 69300 }, { "loss_action": 0.007157274521887302, "loss_total": 0.007157274521887302, "step": 69300 }, { "grad_norm": 0.16778194904327393, "learning_rate": 2.3616151074511546e-05, "loss": 0.0078, "step": 69310 }, { "loss_action": 0.008004432544112206, "loss_total": 0.008004432544112206, "step": 69310 }, { "grad_norm": 0.21298673748970032, "learning_rate": 2.3602107198793545e-05, "loss": 0.0073, "step": 69320 }, { "loss_action": 0.004476792644709349, "loss_total": 0.004476792644709349, "step": 69320 }, { "grad_norm": 0.17132051289081573, "learning_rate": 2.3588066209909427e-05, "loss": 0.0063, "step": 69330 }, { "loss_action": 0.0091242715716362, "loss_total": 0.0091242715716362, "step": 69330 }, { "grad_norm": 0.2260856181383133, "learning_rate": 2.3574028109394662e-05, "loss": 0.0085, "step": 69340 }, { "loss_action": 0.007883595302700996, "loss_total": 0.007883595302700996, "step": 69340 }, { "grad_norm": 0.21728412806987762, "learning_rate": 2.3559992898784454e-05, "loss": 0.0072, "step": 69350 }, { "loss_action": 0.008681810460984707, "loss_total": 0.008681810460984707, "step": 69350 }, { "grad_norm": 0.24329903721809387, "learning_rate": 2.354596057961367e-05, "loss": 0.0083, "step": 69360 }, { "loss_action": 0.00505076115950942, "loss_total": 0.00505076115950942, "step": 69360 }, { "grad_norm": 0.17190589010715485, "learning_rate": 2.353193115341688e-05, "loss": 0.0065, "step": 69370 }, { "loss_action": 0.0062058293260633945, "loss_total": 0.0062058293260633945, "step": 69370 }, { "grad_norm": 0.19677497446537018, "learning_rate": 2.3517904621728294e-05, "loss": 0.0072, "step": 69380 }, { "loss_action": 0.006203481927514076, "loss_total": 0.006203481927514076, "step": 69380 }, { "grad_norm": 0.24415892362594604, "learning_rate": 2.3503880986081855e-05, "loss": 0.0068, "step": 69390 }, { "loss_action": 0.004873087164014578, "loss_total": 0.004873087164014578, "step": 69390 }, { "grad_norm": 0.1934249997138977, "learning_rate": 2.3489860248011136e-05, "loss": 0.0074, "step": 69400 }, { "loss_action": 0.0074785323813557625, "loss_total": 0.0074785323813557625, "step": 69400 }, { "grad_norm": 0.15754906833171844, "learning_rate": 2.3475842409049464e-05, "loss": 0.0065, "step": 69410 }, { "loss_action": 0.00580325722694397, "loss_total": 0.00580325722694397, "step": 69410 }, { "grad_norm": 0.13101767003536224, "learning_rate": 2.346182747072975e-05, "loss": 0.0068, "step": 69420 }, { "loss_action": 0.005650808569043875, "loss_total": 0.005650808569043875, "step": 69420 }, { "grad_norm": 0.1830710619688034, "learning_rate": 2.3447815434584718e-05, "loss": 0.0064, "step": 69430 }, { "loss_action": 0.004602877423167229, "loss_total": 0.004602877423167229, "step": 69430 }, { "grad_norm": 0.18463261425495148, "learning_rate": 2.3433806302146656e-05, "loss": 0.0064, "step": 69440 }, { "loss_action": 0.006370481103658676, "loss_total": 0.006370481103658676, "step": 69440 }, { "grad_norm": 0.15658175945281982, "learning_rate": 2.3419800074947612e-05, "loss": 0.0067, "step": 69450 }, { "loss_action": 0.005565454717725515, "loss_total": 0.005565454717725515, "step": 69450 }, { "grad_norm": 0.1990717500448227, "learning_rate": 2.3405796754519248e-05, "loss": 0.0076, "step": 69460 }, { "loss_action": 0.00942360982298851, "loss_total": 0.00942360982298851, "step": 69460 }, { "grad_norm": 0.18546004593372345, "learning_rate": 2.3391796342392992e-05, "loss": 0.0076, "step": 69470 }, { "loss_action": 0.007372406776994467, "loss_total": 0.007372406776994467, "step": 69470 }, { "grad_norm": 0.18758344650268555, "learning_rate": 2.337779884009984e-05, "loss": 0.0072, "step": 69480 }, { "loss_action": 0.0067892479710280895, "loss_total": 0.0067892479710280895, "step": 69480 }, { "grad_norm": 0.18710292875766754, "learning_rate": 2.3363804249170624e-05, "loss": 0.007, "step": 69490 }, { "loss_action": 0.005745923146605492, "loss_total": 0.005745923146605492, "step": 69490 }, { "grad_norm": 0.19479328393936157, "learning_rate": 2.3349812571135703e-05, "loss": 0.0072, "step": 69500 }, { "loss_action": 0.006591422483325005, "loss_total": 0.006591422483325005, "step": 69500 }, { "grad_norm": 0.1736171543598175, "learning_rate": 2.333582380752523e-05, "loss": 0.0065, "step": 69510 }, { "loss_action": 0.005723673850297928, "loss_total": 0.005723673850297928, "step": 69510 }, { "grad_norm": 0.16107586026191711, "learning_rate": 2.3321837959868963e-05, "loss": 0.0071, "step": 69520 }, { "loss_action": 0.006567660719156265, "loss_total": 0.006567660719156265, "step": 69520 }, { "grad_norm": 0.2108476161956787, "learning_rate": 2.3307855029696383e-05, "loss": 0.0064, "step": 69530 }, { "loss_action": 0.006006449460983276, "loss_total": 0.006006449460983276, "step": 69530 }, { "grad_norm": 0.20373106002807617, "learning_rate": 2.3293875018536648e-05, "loss": 0.0073, "step": 69540 }, { "loss_action": 0.00399111257866025, "loss_total": 0.00399111257866025, "step": 69540 }, { "grad_norm": 0.1794348955154419, "learning_rate": 2.327989792791861e-05, "loss": 0.0072, "step": 69550 }, { "loss_action": 0.0049331155605614185, "loss_total": 0.0049331155605614185, "step": 69550 }, { "grad_norm": 0.16363553702831268, "learning_rate": 2.326592375937074e-05, "loss": 0.0066, "step": 69560 }, { "loss_action": 0.006867255549877882, "loss_total": 0.006867255549877882, "step": 69560 }, { "grad_norm": 0.28647592663764954, "learning_rate": 2.3251952514421248e-05, "loss": 0.0085, "step": 69570 }, { "loss_action": 0.004846781026571989, "loss_total": 0.004846781026571989, "step": 69570 }, { "grad_norm": 0.17116641998291016, "learning_rate": 2.323798419459804e-05, "loss": 0.0074, "step": 69580 }, { "loss_action": 0.012405424378812313, "loss_total": 0.012405424378812313, "step": 69580 }, { "grad_norm": 0.2565273344516754, "learning_rate": 2.3224018801428625e-05, "loss": 0.0075, "step": 69590 }, { "loss_action": 0.009539430029690266, "loss_total": 0.009539430029690266, "step": 69590 }, { "grad_norm": 0.17194341123104095, "learning_rate": 2.3210056336440273e-05, "loss": 0.0069, "step": 69600 }, { "loss_action": 0.006761130411177874, "loss_total": 0.006761130411177874, "step": 69600 }, { "grad_norm": 0.18112771213054657, "learning_rate": 2.3196096801159844e-05, "loss": 0.0069, "step": 69610 }, { "loss_action": 0.00518676545470953, "loss_total": 0.00518676545470953, "step": 69610 }, { "grad_norm": 0.20120753347873688, "learning_rate": 2.3182140197114012e-05, "loss": 0.0078, "step": 69620 }, { "loss_action": 0.005920753348618746, "loss_total": 0.005920753348618746, "step": 69620 }, { "grad_norm": 0.2626676857471466, "learning_rate": 2.3168186525828985e-05, "loss": 0.0067, "step": 69630 }, { "loss_action": 0.0055477311834692955, "loss_total": 0.0055477311834692955, "step": 69630 }, { "grad_norm": 0.19374780356884003, "learning_rate": 2.3154235788830757e-05, "loss": 0.0074, "step": 69640 }, { "loss_action": 0.0052347141318023205, "loss_total": 0.0052347141318023205, "step": 69640 }, { "grad_norm": 0.18781743943691254, "learning_rate": 2.3140287987644927e-05, "loss": 0.0069, "step": 69650 }, { "loss_action": 0.006140945013612509, "loss_total": 0.006140945013612509, "step": 69650 }, { "grad_norm": 0.18120968341827393, "learning_rate": 2.3126343123796833e-05, "loss": 0.0061, "step": 69660 }, { "loss_action": 0.005968874786049128, "loss_total": 0.005968874786049128, "step": 69660 }, { "grad_norm": 0.1421324610710144, "learning_rate": 2.3112401198811418e-05, "loss": 0.0075, "step": 69670 }, { "loss_action": 0.00756707601249218, "loss_total": 0.00756707601249218, "step": 69670 }, { "grad_norm": 0.20919211208820343, "learning_rate": 2.3098462214213418e-05, "loss": 0.007, "step": 69680 }, { "loss_action": 0.0062656342051923275, "loss_total": 0.0062656342051923275, "step": 69680 }, { "grad_norm": 0.15776613354682922, "learning_rate": 2.308452617152712e-05, "loss": 0.0068, "step": 69690 }, { "loss_action": 0.007437606807798147, "loss_total": 0.007437606807798147, "step": 69690 }, { "grad_norm": 0.17943134903907776, "learning_rate": 2.3070593072276603e-05, "loss": 0.0066, "step": 69700 }, { "loss_action": 0.006985110696405172, "loss_total": 0.006985110696405172, "step": 69700 }, { "grad_norm": 0.21371561288833618, "learning_rate": 2.3056662917985518e-05, "loss": 0.0064, "step": 69710 }, { "loss_action": 0.004539611749351025, "loss_total": 0.004539611749351025, "step": 69710 }, { "grad_norm": 0.2514599561691284, "learning_rate": 2.3042735710177283e-05, "loss": 0.0077, "step": 69720 }, { "loss_action": 0.006045538000762463, "loss_total": 0.006045538000762463, "step": 69720 }, { "grad_norm": 0.17269933223724365, "learning_rate": 2.302881145037492e-05, "loss": 0.0069, "step": 69730 }, { "loss_action": 0.00767916115000844, "loss_total": 0.00767916115000844, "step": 69730 }, { "grad_norm": 0.22426415979862213, "learning_rate": 2.3014890140101192e-05, "loss": 0.0068, "step": 69740 }, { "loss_action": 0.009602747857570648, "loss_total": 0.009602747857570648, "step": 69740 }, { "grad_norm": 0.1559726446866989, "learning_rate": 2.30009717808785e-05, "loss": 0.007, "step": 69750 }, { "loss_action": 0.006674337200820446, "loss_total": 0.006674337200820446, "step": 69750 }, { "grad_norm": 0.13827574253082275, "learning_rate": 2.2987056374228967e-05, "loss": 0.0071, "step": 69760 }, { "loss_action": 0.006900060921907425, "loss_total": 0.006900060921907425, "step": 69760 }, { "grad_norm": 0.1704639196395874, "learning_rate": 2.297314392167431e-05, "loss": 0.0063, "step": 69770 }, { "loss_action": 0.006995946168899536, "loss_total": 0.006995946168899536, "step": 69770 }, { "grad_norm": 0.1677895188331604, "learning_rate": 2.295923442473601e-05, "loss": 0.0064, "step": 69780 }, { "loss_action": 0.006618785671889782, "loss_total": 0.006618785671889782, "step": 69780 }, { "grad_norm": 0.16921646893024445, "learning_rate": 2.294532788493519e-05, "loss": 0.0061, "step": 69790 }, { "loss_action": 0.005777318030595779, "loss_total": 0.005777318030595779, "step": 69790 }, { "grad_norm": 0.17340922355651855, "learning_rate": 2.293142430379262e-05, "loss": 0.0066, "step": 69800 }, { "loss_action": 0.005601527635008097, "loss_total": 0.005601527635008097, "step": 69800 }, { "grad_norm": 0.17644211649894714, "learning_rate": 2.291752368282879e-05, "loss": 0.0059, "step": 69810 }, { "loss_action": 0.004885862115770578, "loss_total": 0.004885862115770578, "step": 69810 }, { "grad_norm": 0.14051222801208496, "learning_rate": 2.290362602356385e-05, "loss": 0.0056, "step": 69820 }, { "loss_action": 0.0052861981093883514, "loss_total": 0.0052861981093883514, "step": 69820 }, { "grad_norm": 0.18077750504016876, "learning_rate": 2.288973132751765e-05, "loss": 0.006, "step": 69830 }, { "loss_action": 0.006606568116694689, "loss_total": 0.006606568116694689, "step": 69830 }, { "grad_norm": 0.17856039106845856, "learning_rate": 2.287583959620965e-05, "loss": 0.0071, "step": 69840 }, { "loss_action": 0.008988962508738041, "loss_total": 0.008988962508738041, "step": 69840 }, { "grad_norm": 0.15926092863082886, "learning_rate": 2.2861950831159074e-05, "loss": 0.0066, "step": 69850 }, { "loss_action": 0.0055156792514026165, "loss_total": 0.0055156792514026165, "step": 69850 }, { "grad_norm": 0.19091258943080902, "learning_rate": 2.284806503388472e-05, "loss": 0.0066, "step": 69860 }, { "loss_action": 0.011177587322890759, "loss_total": 0.011177587322890759, "step": 69860 }, { "grad_norm": 0.1719091385602951, "learning_rate": 2.283418220590518e-05, "loss": 0.0066, "step": 69870 }, { "loss_action": 0.009442192502319813, "loss_total": 0.009442192502319813, "step": 69870 }, { "grad_norm": 0.1622689962387085, "learning_rate": 2.282030234873862e-05, "loss": 0.0067, "step": 69880 }, { "loss_action": 0.005755624268203974, "loss_total": 0.005755624268203974, "step": 69880 }, { "grad_norm": 0.20599649846553802, "learning_rate": 2.2806425463902948e-05, "loss": 0.007, "step": 69890 }, { "loss_action": 0.010276692919433117, "loss_total": 0.010276692919433117, "step": 69890 }, { "grad_norm": 0.1546729952096939, "learning_rate": 2.279255155291568e-05, "loss": 0.006, "step": 69900 }, { "loss_action": 0.006746508646756411, "loss_total": 0.006746508646756411, "step": 69900 }, { "grad_norm": 0.14776578545570374, "learning_rate": 2.277868061729409e-05, "loss": 0.0067, "step": 69910 }, { "loss_action": 0.007510604802519083, "loss_total": 0.007510604802519083, "step": 69910 }, { "grad_norm": 0.19082336127758026, "learning_rate": 2.276481265855504e-05, "loss": 0.0062, "step": 69920 }, { "loss_action": 0.0073768156580626965, "loss_total": 0.0073768156580626965, "step": 69920 }, { "grad_norm": 0.13227036595344543, "learning_rate": 2.2750947678215128e-05, "loss": 0.007, "step": 69930 }, { "loss_action": 0.004526153672486544, "loss_total": 0.004526153672486544, "step": 69930 }, { "grad_norm": 0.21058061718940735, "learning_rate": 2.2737085677790616e-05, "loss": 0.0081, "step": 69940 }, { "loss_action": 0.008520442061126232, "loss_total": 0.008520442061126232, "step": 69940 }, { "grad_norm": 0.16288000345230103, "learning_rate": 2.2723226658797443e-05, "loss": 0.0065, "step": 69950 }, { "loss_action": 0.006850681267678738, "loss_total": 0.006850681267678738, "step": 69950 }, { "grad_norm": 0.21310468018054962, "learning_rate": 2.270937062275117e-05, "loss": 0.0062, "step": 69960 }, { "loss_action": 0.005422285292297602, "loss_total": 0.005422285292297602, "step": 69960 }, { "grad_norm": 0.1830102503299713, "learning_rate": 2.2695517571167113e-05, "loss": 0.0067, "step": 69970 }, { "loss_action": 0.005019169766455889, "loss_total": 0.005019169766455889, "step": 69970 }, { "grad_norm": 0.2025034874677658, "learning_rate": 2.268166750556019e-05, "loss": 0.0074, "step": 69980 }, { "loss_action": 0.005780118051916361, "loss_total": 0.005780118051916361, "step": 69980 }, { "grad_norm": 0.19214634597301483, "learning_rate": 2.266782042744503e-05, "loss": 0.0068, "step": 69990 }, { "loss_action": 0.00876359548419714, "loss_total": 0.00876359548419714, "step": 69990 }, { "grad_norm": 0.25665029883384705, "learning_rate": 2.2653976338335935e-05, "loss": 0.0066, "step": 70000 }, { "loss_action": 0.005516431760042906, "loss_total": 0.005516431760042906, "step": 70000 }, { "grad_norm": 0.23896424472332, "learning_rate": 2.2640135239746895e-05, "loss": 0.0069, "step": 70010 }, { "loss_action": 0.006339979358017445, "loss_total": 0.006339979358017445, "step": 70010 }, { "grad_norm": 0.14654406905174255, "learning_rate": 2.2626297133191515e-05, "loss": 0.007, "step": 70020 }, { "loss_action": 0.01094723865389824, "loss_total": 0.01094723865389824, "step": 70020 }, { "grad_norm": 0.19178372621536255, "learning_rate": 2.261246202018312e-05, "loss": 0.007, "step": 70030 }, { "loss_action": 0.007628764491528273, "loss_total": 0.007628764491528273, "step": 70030 }, { "grad_norm": 0.18822327256202698, "learning_rate": 2.2598629902234718e-05, "loss": 0.0069, "step": 70040 }, { "loss_action": 0.006710383575409651, "loss_total": 0.006710383575409651, "step": 70040 }, { "grad_norm": 0.16168616712093353, "learning_rate": 2.258480078085894e-05, "loss": 0.0062, "step": 70050 }, { "loss_action": 0.010431919246912003, "loss_total": 0.010431919246912003, "step": 70050 }, { "grad_norm": 0.18258409202098846, "learning_rate": 2.2570974657568126e-05, "loss": 0.0073, "step": 70060 }, { "loss_action": 0.006874134764075279, "loss_total": 0.006874134764075279, "step": 70060 }, { "grad_norm": 0.15390023589134216, "learning_rate": 2.2557151533874286e-05, "loss": 0.0061, "step": 70070 }, { "loss_action": 0.005183377768844366, "loss_total": 0.005183377768844366, "step": 70070 }, { "grad_norm": 0.1633424609899521, "learning_rate": 2.2543331411289116e-05, "loss": 0.0084, "step": 70080 }, { "loss_action": 0.008547190576791763, "loss_total": 0.008547190576791763, "step": 70080 }, { "grad_norm": 0.19526362419128418, "learning_rate": 2.252951429132392e-05, "loss": 0.007, "step": 70090 }, { "loss_action": 0.005326779559254646, "loss_total": 0.005326779559254646, "step": 70090 }, { "grad_norm": 0.18080708384513855, "learning_rate": 2.2515700175489762e-05, "loss": 0.0066, "step": 70100 }, { "loss_action": 0.005184427835047245, "loss_total": 0.005184427835047245, "step": 70100 }, { "grad_norm": 0.15348570048809052, "learning_rate": 2.2501889065297288e-05, "loss": 0.006, "step": 70110 }, { "loss_action": 0.005407927092164755, "loss_total": 0.005407927092164755, "step": 70110 }, { "grad_norm": 0.1597428321838379, "learning_rate": 2.2488080962256887e-05, "loss": 0.006, "step": 70120 }, { "loss_action": 0.008691113442182541, "loss_total": 0.008691113442182541, "step": 70120 }, { "grad_norm": 0.18282544612884521, "learning_rate": 2.2474275867878585e-05, "loss": 0.0062, "step": 70130 }, { "loss_action": 0.007041787728667259, "loss_total": 0.007041787728667259, "step": 70130 }, { "grad_norm": 0.15009614825248718, "learning_rate": 2.246047378367211e-05, "loss": 0.0061, "step": 70140 }, { "loss_action": 0.007906569167971611, "loss_total": 0.007906569167971611, "step": 70140 }, { "grad_norm": 0.16447162628173828, "learning_rate": 2.2446674711146798e-05, "loss": 0.0077, "step": 70150 }, { "loss_action": 0.004956050775945187, "loss_total": 0.004956050775945187, "step": 70150 }, { "grad_norm": 0.1658569872379303, "learning_rate": 2.2432878651811734e-05, "loss": 0.0061, "step": 70160 }, { "loss_action": 0.005238379817456007, "loss_total": 0.005238379817456007, "step": 70160 }, { "grad_norm": 0.19998614490032196, "learning_rate": 2.2419085607175594e-05, "loss": 0.0071, "step": 70170 }, { "loss_action": 0.006218988448381424, "loss_total": 0.006218988448381424, "step": 70170 }, { "grad_norm": 0.22726769745349884, "learning_rate": 2.240529557874678e-05, "loss": 0.007, "step": 70180 }, { "loss_action": 0.006918079219758511, "loss_total": 0.006918079219758511, "step": 70180 }, { "grad_norm": 0.18539360165596008, "learning_rate": 2.2391508568033358e-05, "loss": 0.0075, "step": 70190 }, { "loss_action": 0.008347539231181145, "loss_total": 0.008347539231181145, "step": 70190 }, { "grad_norm": 0.1565370410680771, "learning_rate": 2.237772457654307e-05, "loss": 0.0081, "step": 70200 }, { "loss_action": 0.006713908165693283, "loss_total": 0.006713908165693283, "step": 70200 }, { "grad_norm": 0.15056373178958893, "learning_rate": 2.236394360578327e-05, "loss": 0.0067, "step": 70210 }, { "loss_action": 0.0054765124805271626, "loss_total": 0.0054765124805271626, "step": 70210 }, { "grad_norm": 0.12472885102033615, "learning_rate": 2.2350165657261073e-05, "loss": 0.0057, "step": 70220 }, { "loss_action": 0.004544821567833424, "loss_total": 0.004544821567833424, "step": 70220 }, { "grad_norm": 0.14838017523288727, "learning_rate": 2.2336390732483164e-05, "loss": 0.0067, "step": 70230 }, { "loss_action": 0.006885274313390255, "loss_total": 0.006885274313390255, "step": 70230 }, { "grad_norm": 0.1689060628414154, "learning_rate": 2.2322618832955976e-05, "loss": 0.0067, "step": 70240 }, { "loss_action": 0.005666628945618868, "loss_total": 0.005666628945618868, "step": 70240 }, { "grad_norm": 0.18664361536502838, "learning_rate": 2.2308849960185578e-05, "loss": 0.0068, "step": 70250 }, { "loss_action": 0.006375982891768217, "loss_total": 0.006375982891768217, "step": 70250 }, { "grad_norm": 0.11307383328676224, "learning_rate": 2.229508411567774e-05, "loss": 0.0059, "step": 70260 }, { "loss_action": 0.007196434773504734, "loss_total": 0.007196434773504734, "step": 70260 }, { "grad_norm": 0.15752968192100525, "learning_rate": 2.2281321300937823e-05, "loss": 0.0067, "step": 70270 }, { "loss_action": 0.0048009552992880344, "loss_total": 0.0048009552992880344, "step": 70270 }, { "grad_norm": 0.15265204012393951, "learning_rate": 2.2267561517470937e-05, "loss": 0.0065, "step": 70280 }, { "loss_action": 0.004803653806447983, "loss_total": 0.004803653806447983, "step": 70280 }, { "grad_norm": 0.19836565852165222, "learning_rate": 2.2253804766781845e-05, "loss": 0.0074, "step": 70290 }, { "loss_action": 0.007708108983933926, "loss_total": 0.007708108983933926, "step": 70290 }, { "grad_norm": 0.1853862702846527, "learning_rate": 2.2240051050374933e-05, "loss": 0.0066, "step": 70300 }, { "loss_action": 0.005687063559889793, "loss_total": 0.005687063559889793, "step": 70300 }, { "grad_norm": 0.1947980523109436, "learning_rate": 2.22263003697543e-05, "loss": 0.0061, "step": 70310 }, { "loss_action": 0.006089935544878244, "loss_total": 0.006089935544878244, "step": 70310 }, { "grad_norm": 0.20035745203495026, "learning_rate": 2.2212552726423702e-05, "loss": 0.0064, "step": 70320 }, { "loss_action": 0.009783422574400902, "loss_total": 0.009783422574400902, "step": 70320 }, { "grad_norm": 0.1806238293647766, "learning_rate": 2.2198808121886578e-05, "loss": 0.0071, "step": 70330 }, { "loss_action": 0.004357191734015942, "loss_total": 0.004357191734015942, "step": 70330 }, { "grad_norm": 0.16596552729606628, "learning_rate": 2.218506655764598e-05, "loss": 0.0064, "step": 70340 }, { "loss_action": 0.006054707802832127, "loss_total": 0.006054707802832127, "step": 70340 }, { "grad_norm": 0.15511851012706757, "learning_rate": 2.2171328035204704e-05, "loss": 0.007, "step": 70350 }, { "loss_action": 0.005373766180127859, "loss_total": 0.005373766180127859, "step": 70350 }, { "grad_norm": 0.18429479002952576, "learning_rate": 2.2157592556065133e-05, "loss": 0.008, "step": 70360 }, { "loss_action": 0.005312483757734299, "loss_total": 0.005312483757734299, "step": 70360 }, { "grad_norm": 0.1590869426727295, "learning_rate": 2.2143860121729382e-05, "loss": 0.0066, "step": 70370 }, { "loss_action": 0.008345883339643478, "loss_total": 0.008345883339643478, "step": 70370 }, { "grad_norm": 0.3040715456008911, "learning_rate": 2.2130130733699206e-05, "loss": 0.008, "step": 70380 }, { "loss_action": 0.009054549038410187, "loss_total": 0.009054549038410187, "step": 70380 }, { "grad_norm": 0.2236061543226242, "learning_rate": 2.2116404393476052e-05, "loss": 0.0081, "step": 70390 }, { "loss_action": 0.008098962716758251, "loss_total": 0.008098962716758251, "step": 70390 }, { "grad_norm": 0.24555271863937378, "learning_rate": 2.2102681102560967e-05, "loss": 0.0069, "step": 70400 }, { "loss_action": 0.007265559397637844, "loss_total": 0.007265559397637844, "step": 70400 }, { "grad_norm": 0.2186836451292038, "learning_rate": 2.208896086245476e-05, "loss": 0.007, "step": 70410 }, { "loss_action": 0.0063684009946882725, "loss_total": 0.0063684009946882725, "step": 70410 }, { "grad_norm": 0.18676914274692535, "learning_rate": 2.2075243674657808e-05, "loss": 0.0063, "step": 70420 }, { "loss_action": 0.005514275282621384, "loss_total": 0.005514275282621384, "step": 70420 }, { "grad_norm": 0.1600288599729538, "learning_rate": 2.206152954067024e-05, "loss": 0.006, "step": 70430 }, { "loss_action": 0.004699062090367079, "loss_total": 0.004699062090367079, "step": 70430 }, { "grad_norm": 0.15004375576972961, "learning_rate": 2.2047818461991758e-05, "loss": 0.0064, "step": 70440 }, { "loss_action": 0.007773109246045351, "loss_total": 0.007773109246045351, "step": 70440 }, { "grad_norm": 0.16830624639987946, "learning_rate": 2.2034110440121864e-05, "loss": 0.0073, "step": 70450 }, { "loss_action": 0.0061831362545490265, "loss_total": 0.0061831362545490265, "step": 70450 }, { "grad_norm": 0.19708351790905, "learning_rate": 2.2020405476559585e-05, "loss": 0.0063, "step": 70460 }, { "loss_action": 0.006887303665280342, "loss_total": 0.006887303665280342, "step": 70460 }, { "grad_norm": 0.18568184971809387, "learning_rate": 2.2006703572803722e-05, "loss": 0.0074, "step": 70470 }, { "loss_action": 0.004793187137693167, "loss_total": 0.004793187137693167, "step": 70470 }, { "grad_norm": 0.1525995284318924, "learning_rate": 2.1993004730352646e-05, "loss": 0.0064, "step": 70480 }, { "loss_action": 0.005764961242675781, "loss_total": 0.005764961242675781, "step": 70480 }, { "grad_norm": 0.14720329642295837, "learning_rate": 2.1979308950704464e-05, "loss": 0.0066, "step": 70490 }, { "loss_action": 0.006648682989180088, "loss_total": 0.006648682989180088, "step": 70490 }, { "grad_norm": 0.16598787903785706, "learning_rate": 2.1965616235356923e-05, "loss": 0.0068, "step": 70500 }, { "loss_action": 0.005749177187681198, "loss_total": 0.005749177187681198, "step": 70500 }, { "grad_norm": 0.13881997764110565, "learning_rate": 2.1951926585807465e-05, "loss": 0.0071, "step": 70510 }, { "loss_action": 0.0068196821957826614, "loss_total": 0.0068196821957826614, "step": 70510 }, { "grad_norm": 0.2175537496805191, "learning_rate": 2.193824000355313e-05, "loss": 0.0071, "step": 70520 }, { "loss_action": 0.008078651502728462, "loss_total": 0.008078651502728462, "step": 70520 }, { "grad_norm": 0.1697525680065155, "learning_rate": 2.192455649009067e-05, "loss": 0.0066, "step": 70530 }, { "loss_action": 0.0063688987866044044, "loss_total": 0.0063688987866044044, "step": 70530 }, { "grad_norm": 0.1919509917497635, "learning_rate": 2.1910876046916523e-05, "loss": 0.0072, "step": 70540 }, { "loss_action": 0.0058796824887394905, "loss_total": 0.0058796824887394905, "step": 70540 }, { "grad_norm": 0.1615654081106186, "learning_rate": 2.1897198675526725e-05, "loss": 0.0068, "step": 70550 }, { "loss_action": 0.005237217526882887, "loss_total": 0.005237217526882887, "step": 70550 }, { "grad_norm": 0.33134981989860535, "learning_rate": 2.1883524377417024e-05, "loss": 0.0081, "step": 70560 }, { "loss_action": 0.005970094818621874, "loss_total": 0.005970094818621874, "step": 70560 }, { "grad_norm": 0.16633039712905884, "learning_rate": 2.1869853154082825e-05, "loss": 0.0059, "step": 70570 }, { "loss_action": 0.006915248464792967, "loss_total": 0.006915248464792967, "step": 70570 }, { "grad_norm": 0.1623745858669281, "learning_rate": 2.1856185007019215e-05, "loss": 0.0072, "step": 70580 }, { "loss_action": 0.007611494045704603, "loss_total": 0.007611494045704603, "step": 70580 }, { "grad_norm": 0.20731420814990997, "learning_rate": 2.1842519937720874e-05, "loss": 0.0076, "step": 70590 }, { "loss_action": 0.0057836780324578285, "loss_total": 0.0057836780324578285, "step": 70590 }, { "grad_norm": 0.17377258837223053, "learning_rate": 2.182885794768224e-05, "loss": 0.0071, "step": 70600 }, { "loss_action": 0.0046765184961259365, "loss_total": 0.0046765184961259365, "step": 70600 }, { "grad_norm": 0.15933412313461304, "learning_rate": 2.1815199038397326e-05, "loss": 0.0071, "step": 70610 }, { "loss_action": 0.005467414390295744, "loss_total": 0.005467414390295744, "step": 70610 }, { "grad_norm": 0.15311841666698456, "learning_rate": 2.1801543211359893e-05, "loss": 0.0067, "step": 70620 }, { "loss_action": 0.005622646305710077, "loss_total": 0.005622646305710077, "step": 70620 }, { "grad_norm": 0.21217389404773712, "learning_rate": 2.178789046806326e-05, "loss": 0.0083, "step": 70630 }, { "loss_action": 0.00794923771172762, "loss_total": 0.00794923771172762, "step": 70630 }, { "grad_norm": 0.15730488300323486, "learning_rate": 2.1774240810000547e-05, "loss": 0.0071, "step": 70640 }, { "loss_action": 0.006390779744833708, "loss_total": 0.006390779744833708, "step": 70640 }, { "grad_norm": 0.12865197658538818, "learning_rate": 2.17605942386644e-05, "loss": 0.0065, "step": 70650 }, { "loss_action": 0.0047198450192809105, "loss_total": 0.0047198450192809105, "step": 70650 }, { "grad_norm": 0.20349472761154175, "learning_rate": 2.174695075554723e-05, "loss": 0.0058, "step": 70660 }, { "loss_action": 0.007549056317657232, "loss_total": 0.007549056317657232, "step": 70660 }, { "grad_norm": 0.1802559196949005, "learning_rate": 2.173331036214103e-05, "loss": 0.0056, "step": 70670 }, { "loss_action": 0.009053495712578297, "loss_total": 0.009053495712578297, "step": 70670 }, { "grad_norm": 0.20704354345798492, "learning_rate": 2.171967305993753e-05, "loss": 0.0063, "step": 70680 }, { "loss_action": 0.0041323876939713955, "loss_total": 0.0041323876939713955, "step": 70680 }, { "grad_norm": 0.19093570113182068, "learning_rate": 2.1706038850428024e-05, "loss": 0.0065, "step": 70690 }, { "loss_action": 0.007165140472352505, "loss_total": 0.007165140472352505, "step": 70690 }, { "grad_norm": 0.1629304587841034, "learning_rate": 2.169240773510361e-05, "loss": 0.0078, "step": 70700 }, { "loss_action": 0.010478599928319454, "loss_total": 0.010478599928319454, "step": 70700 }, { "grad_norm": 0.14068062603473663, "learning_rate": 2.1678779715454906e-05, "loss": 0.0072, "step": 70710 }, { "loss_action": 0.008032881654798985, "loss_total": 0.008032881654798985, "step": 70710 }, { "grad_norm": 0.2321706861257553, "learning_rate": 2.166515479297229e-05, "loss": 0.0059, "step": 70720 }, { "loss_action": 0.0106624411419034, "loss_total": 0.0106624411419034, "step": 70720 }, { "grad_norm": 0.17582425475120544, "learning_rate": 2.1651532969145732e-05, "loss": 0.0073, "step": 70730 }, { "loss_action": 0.011109290644526482, "loss_total": 0.011109290644526482, "step": 70730 }, { "grad_norm": 0.18308895826339722, "learning_rate": 2.1637914245464903e-05, "loss": 0.008, "step": 70740 }, { "loss_action": 0.007169485092163086, "loss_total": 0.007169485092163086, "step": 70740 }, { "grad_norm": 0.2003464698791504, "learning_rate": 2.1624298623419133e-05, "loss": 0.008, "step": 70750 }, { "loss_action": 0.009042496792972088, "loss_total": 0.009042496792972088, "step": 70750 }, { "grad_norm": 0.18322493135929108, "learning_rate": 2.1610686104497413e-05, "loss": 0.0073, "step": 70760 }, { "loss_action": 0.007414236199110746, "loss_total": 0.007414236199110746, "step": 70760 }, { "grad_norm": 0.19304269552230835, "learning_rate": 2.1597076690188366e-05, "loss": 0.007, "step": 70770 }, { "loss_action": 0.008933421224355698, "loss_total": 0.008933421224355698, "step": 70770 }, { "grad_norm": 0.1762545257806778, "learning_rate": 2.1583470381980315e-05, "loss": 0.0074, "step": 70780 }, { "loss_action": 0.007590955123305321, "loss_total": 0.007590955123305321, "step": 70780 }, { "grad_norm": 0.17817507684230804, "learning_rate": 2.156986718136123e-05, "loss": 0.0074, "step": 70790 }, { "loss_action": 0.005927414633333683, "loss_total": 0.005927414633333683, "step": 70790 }, { "grad_norm": 0.18477772176265717, "learning_rate": 2.155626708981871e-05, "loss": 0.0076, "step": 70800 }, { "loss_action": 0.005529292393475771, "loss_total": 0.005529292393475771, "step": 70800 }, { "grad_norm": 0.29440635442733765, "learning_rate": 2.1542670108840075e-05, "loss": 0.0075, "step": 70810 }, { "loss_action": 0.0064715612679719925, "loss_total": 0.0064715612679719925, "step": 70810 }, { "grad_norm": 0.16442634165287018, "learning_rate": 2.152907623991221e-05, "loss": 0.0084, "step": 70820 }, { "loss_action": 0.010022508911788464, "loss_total": 0.010022508911788464, "step": 70820 }, { "grad_norm": 0.15129494667053223, "learning_rate": 2.1515485484521802e-05, "loss": 0.007, "step": 70830 }, { "loss_action": 0.004618977662175894, "loss_total": 0.004618977662175894, "step": 70830 }, { "grad_norm": 0.23404771089553833, "learning_rate": 2.150189784415506e-05, "loss": 0.0077, "step": 70840 }, { "loss_action": 0.0050374292768538, "loss_total": 0.0050374292768538, "step": 70840 }, { "grad_norm": 0.304129421710968, "learning_rate": 2.148831332029794e-05, "loss": 0.0075, "step": 70850 }, { "loss_action": 0.005998105276376009, "loss_total": 0.005998105276376009, "step": 70850 }, { "grad_norm": 0.14847815036773682, "learning_rate": 2.147473191443599e-05, "loss": 0.0063, "step": 70860 }, { "loss_action": 0.008663871325552464, "loss_total": 0.008663871325552464, "step": 70860 }, { "grad_norm": 0.15170271694660187, "learning_rate": 2.1461153628054492e-05, "loss": 0.0067, "step": 70870 }, { "loss_action": 0.0050920587964355946, "loss_total": 0.0050920587964355946, "step": 70870 }, { "grad_norm": 0.17902198433876038, "learning_rate": 2.1447578462638284e-05, "loss": 0.0071, "step": 70880 }, { "loss_action": 0.0043957894667983055, "loss_total": 0.0043957894667983055, "step": 70880 }, { "grad_norm": 0.19860108196735382, "learning_rate": 2.143400641967201e-05, "loss": 0.0078, "step": 70890 }, { "loss_action": 0.007739662192761898, "loss_total": 0.007739662192761898, "step": 70890 }, { "grad_norm": 0.17294242978096008, "learning_rate": 2.1420437500639823e-05, "loss": 0.0072, "step": 70900 }, { "loss_action": 0.005241330713033676, "loss_total": 0.005241330713033676, "step": 70900 }, { "grad_norm": 0.1737549602985382, "learning_rate": 2.1406871707025646e-05, "loss": 0.0068, "step": 70910 }, { "loss_action": 0.006480157840996981, "loss_total": 0.006480157840996981, "step": 70910 }, { "grad_norm": 0.1601056456565857, "learning_rate": 2.1393309040312963e-05, "loss": 0.0077, "step": 70920 }, { "loss_action": 0.0072467150166630745, "loss_total": 0.0072467150166630745, "step": 70920 }, { "grad_norm": 0.17292393743991852, "learning_rate": 2.137974950198502e-05, "loss": 0.0082, "step": 70930 }, { "loss_action": 0.008116994984447956, "loss_total": 0.008116994984447956, "step": 70930 }, { "grad_norm": 0.19969116151332855, "learning_rate": 2.1366193093524617e-05, "loss": 0.0076, "step": 70940 }, { "loss_action": 0.005923289805650711, "loss_total": 0.005923289805650711, "step": 70940 }, { "grad_norm": 0.13765418529510498, "learning_rate": 2.1352639816414288e-05, "loss": 0.0062, "step": 70950 }, { "loss_action": 0.005370691418647766, "loss_total": 0.005370691418647766, "step": 70950 }, { "grad_norm": 0.20172832906246185, "learning_rate": 2.1339089672136202e-05, "loss": 0.0068, "step": 70960 }, { "loss_action": 0.00850866548717022, "loss_total": 0.00850866548717022, "step": 70960 }, { "grad_norm": 0.17523454129695892, "learning_rate": 2.1325542662172193e-05, "loss": 0.0077, "step": 70970 }, { "loss_action": 0.006577644497156143, "loss_total": 0.006577644497156143, "step": 70970 }, { "grad_norm": 0.16716767847537994, "learning_rate": 2.1311998788003712e-05, "loss": 0.0067, "step": 70980 }, { "loss_action": 0.009706548415124416, "loss_total": 0.009706548415124416, "step": 70980 }, { "grad_norm": 0.26279976963996887, "learning_rate": 2.1298458051111907e-05, "loss": 0.0077, "step": 70990 }, { "loss_action": 0.007933388464152813, "loss_total": 0.007933388464152813, "step": 70990 }, { "grad_norm": 0.18125112354755402, "learning_rate": 2.1284920452977602e-05, "loss": 0.0075, "step": 71000 }, { "loss_action": 0.0052779498510062695, "loss_total": 0.0052779498510062695, "step": 71000 }, { "grad_norm": 0.2071826457977295, "learning_rate": 2.12713859950812e-05, "loss": 0.0066, "step": 71010 }, { "loss_action": 0.0071626692079007626, "loss_total": 0.0071626692079007626, "step": 71010 }, { "grad_norm": 0.21963077783584595, "learning_rate": 2.1257854678902832e-05, "loss": 0.007, "step": 71020 }, { "loss_action": 0.01639873906970024, "loss_total": 0.01639873906970024, "step": 71020 }, { "grad_norm": 0.2580263614654541, "learning_rate": 2.124432650592227e-05, "loss": 0.0071, "step": 71030 }, { "loss_action": 0.0048734527081251144, "loss_total": 0.0048734527081251144, "step": 71030 }, { "grad_norm": 0.144748255610466, "learning_rate": 2.1230801477618937e-05, "loss": 0.0069, "step": 71040 }, { "loss_action": 0.004521009046584368, "loss_total": 0.004521009046584368, "step": 71040 }, { "grad_norm": 0.17161914706230164, "learning_rate": 2.121727959547189e-05, "loss": 0.0061, "step": 71050 }, { "loss_action": 0.004982667975127697, "loss_total": 0.004982667975127697, "step": 71050 }, { "grad_norm": 0.16362659633159637, "learning_rate": 2.1203760860959886e-05, "loss": 0.0067, "step": 71060 }, { "loss_action": 0.0066786883398890495, "loss_total": 0.0066786883398890495, "step": 71060 }, { "grad_norm": 0.15323412418365479, "learning_rate": 2.119024527556127e-05, "loss": 0.0076, "step": 71070 }, { "loss_action": 0.008722133003175259, "loss_total": 0.008722133003175259, "step": 71070 }, { "grad_norm": 0.19838818907737732, "learning_rate": 2.117673284075415e-05, "loss": 0.0073, "step": 71080 }, { "loss_action": 0.006752267014235258, "loss_total": 0.006752267014235258, "step": 71080 }, { "grad_norm": 0.17799794673919678, "learning_rate": 2.1163223558016165e-05, "loss": 0.0073, "step": 71090 }, { "loss_action": 0.006000347901135683, "loss_total": 0.006000347901135683, "step": 71090 }, { "grad_norm": 0.20630806684494019, "learning_rate": 2.1149717428824722e-05, "loss": 0.0068, "step": 71100 }, { "loss_action": 0.007319344207644463, "loss_total": 0.007319344207644463, "step": 71100 }, { "grad_norm": 0.23727287352085114, "learning_rate": 2.1136214454656784e-05, "loss": 0.0067, "step": 71110 }, { "loss_action": 0.00704059237614274, "loss_total": 0.00704059237614274, "step": 71110 }, { "grad_norm": 0.20565339922904968, "learning_rate": 2.1122714636989056e-05, "loss": 0.0061, "step": 71120 }, { "loss_action": 0.006423368584364653, "loss_total": 0.006423368584364653, "step": 71120 }, { "grad_norm": 0.22149908542633057, "learning_rate": 2.1109217977297823e-05, "loss": 0.0064, "step": 71130 }, { "loss_action": 0.0065757534466683865, "loss_total": 0.0065757534466683865, "step": 71130 }, { "grad_norm": 0.2048281729221344, "learning_rate": 2.1095724477059077e-05, "loss": 0.0069, "step": 71140 }, { "loss_action": 0.005926419049501419, "loss_total": 0.005926419049501419, "step": 71140 }, { "grad_norm": 0.2052057981491089, "learning_rate": 2.1082234137748434e-05, "loss": 0.0062, "step": 71150 }, { "loss_action": 0.005989000666886568, "loss_total": 0.005989000666886568, "step": 71150 }, { "grad_norm": 0.17904874682426453, "learning_rate": 2.106874696084122e-05, "loss": 0.0069, "step": 71160 }, { "loss_action": 0.006862067151814699, "loss_total": 0.006862067151814699, "step": 71160 }, { "grad_norm": 0.18353453278541565, "learning_rate": 2.1055262947812315e-05, "loss": 0.0076, "step": 71170 }, { "loss_action": 0.007515168748795986, "loss_total": 0.007515168748795986, "step": 71170 }, { "grad_norm": 0.19375716149806976, "learning_rate": 2.104178210013636e-05, "loss": 0.0067, "step": 71180 }, { "loss_action": 0.007606554310768843, "loss_total": 0.007606554310768843, "step": 71180 }, { "grad_norm": 0.1721189022064209, "learning_rate": 2.1028304419287554e-05, "loss": 0.0068, "step": 71190 }, { "loss_action": 0.006190345156937838, "loss_total": 0.006190345156937838, "step": 71190 }, { "grad_norm": 0.14691834151744843, "learning_rate": 2.101482990673982e-05, "loss": 0.0058, "step": 71200 }, { "loss_action": 0.005276208743453026, "loss_total": 0.005276208743453026, "step": 71200 }, { "grad_norm": 0.14384037256240845, "learning_rate": 2.1001358563966707e-05, "loss": 0.0057, "step": 71210 }, { "loss_action": 0.004953447263687849, "loss_total": 0.004953447263687849, "step": 71210 }, { "grad_norm": 0.17943379282951355, "learning_rate": 2.098789039244144e-05, "loss": 0.0065, "step": 71220 }, { "loss_action": 0.005095603410154581, "loss_total": 0.005095603410154581, "step": 71220 }, { "grad_norm": 0.1949928253889084, "learning_rate": 2.097442539363685e-05, "loss": 0.007, "step": 71230 }, { "loss_action": 0.009338741190731525, "loss_total": 0.009338741190731525, "step": 71230 }, { "grad_norm": 0.16055116057395935, "learning_rate": 2.0960963569025448e-05, "loss": 0.0066, "step": 71240 }, { "loss_action": 0.006566223222762346, "loss_total": 0.006566223222762346, "step": 71240 }, { "grad_norm": 0.18178598582744598, "learning_rate": 2.0947504920079435e-05, "loss": 0.0079, "step": 71250 }, { "loss_action": 0.004120614379644394, "loss_total": 0.004120614379644394, "step": 71250 }, { "grad_norm": 0.18395058810710907, "learning_rate": 2.093404944827059e-05, "loss": 0.0061, "step": 71260 }, { "loss_action": 0.008563380688428879, "loss_total": 0.008563380688428879, "step": 71260 }, { "grad_norm": 0.1825716495513916, "learning_rate": 2.0920597155070394e-05, "loss": 0.0064, "step": 71270 }, { "loss_action": 0.010829852893948555, "loss_total": 0.010829852893948555, "step": 71270 }, { "grad_norm": 0.17926976084709167, "learning_rate": 2.090714804194997e-05, "loss": 0.0072, "step": 71280 }, { "loss_action": 0.0073774997144937515, "loss_total": 0.0073774997144937515, "step": 71280 }, { "grad_norm": 0.196344256401062, "learning_rate": 2.0893702110380114e-05, "loss": 0.0063, "step": 71290 }, { "loss_action": 0.005606959108263254, "loss_total": 0.005606959108263254, "step": 71290 }, { "grad_norm": 0.15581201016902924, "learning_rate": 2.0880259361831216e-05, "loss": 0.0063, "step": 71300 }, { "loss_action": 0.006697770208120346, "loss_total": 0.006697770208120346, "step": 71300 }, { "grad_norm": 0.1586935669183731, "learning_rate": 2.0866819797773397e-05, "loss": 0.0058, "step": 71310 }, { "loss_action": 0.008846379816532135, "loss_total": 0.008846379816532135, "step": 71310 }, { "grad_norm": 0.27249640226364136, "learning_rate": 2.085338341967634e-05, "loss": 0.0064, "step": 71320 }, { "loss_action": 0.006961497478187084, "loss_total": 0.006961497478187084, "step": 71320 }, { "grad_norm": 0.17718705534934998, "learning_rate": 2.083995022900946e-05, "loss": 0.0065, "step": 71330 }, { "loss_action": 0.005856149364262819, "loss_total": 0.005856149364262819, "step": 71330 }, { "grad_norm": 0.1596313714981079, "learning_rate": 2.0826520227241768e-05, "loss": 0.0069, "step": 71340 }, { "loss_action": 0.009423785842955112, "loss_total": 0.009423785842955112, "step": 71340 }, { "grad_norm": 0.18087054789066315, "learning_rate": 2.081309341584199e-05, "loss": 0.007, "step": 71350 }, { "loss_action": 0.006037082057446241, "loss_total": 0.006037082057446241, "step": 71350 }, { "grad_norm": 0.24450328946113586, "learning_rate": 2.0799669796278413e-05, "loss": 0.0081, "step": 71360 }, { "loss_action": 0.005517615005373955, "loss_total": 0.005517615005373955, "step": 71360 }, { "grad_norm": 0.19114628434181213, "learning_rate": 2.078624937001906e-05, "loss": 0.0062, "step": 71370 }, { "loss_action": 0.005372792482376099, "loss_total": 0.005372792482376099, "step": 71370 }, { "grad_norm": 0.16889989376068115, "learning_rate": 2.0772832138531544e-05, "loss": 0.0063, "step": 71380 }, { "loss_action": 0.005350178107619286, "loss_total": 0.005350178107619286, "step": 71380 }, { "grad_norm": 0.1825370490550995, "learning_rate": 2.0759418103283158e-05, "loss": 0.0067, "step": 71390 }, { "loss_action": 0.004743795841932297, "loss_total": 0.004743795841932297, "step": 71390 }, { "grad_norm": 0.13736604154109955, "learning_rate": 2.0746007265740846e-05, "loss": 0.0064, "step": 71400 }, { "loss_action": 0.011702809482812881, "loss_total": 0.011702809482812881, "step": 71400 }, { "grad_norm": 0.1841229945421219, "learning_rate": 2.0732599627371215e-05, "loss": 0.0081, "step": 71410 }, { "loss_action": 0.007769135292619467, "loss_total": 0.007769135292619467, "step": 71410 }, { "grad_norm": 0.16886921226978302, "learning_rate": 2.0719195189640468e-05, "loss": 0.0071, "step": 71420 }, { "loss_action": 0.009092077612876892, "loss_total": 0.009092077612876892, "step": 71420 }, { "grad_norm": 0.1649385690689087, "learning_rate": 2.0705793954014528e-05, "loss": 0.0069, "step": 71430 }, { "loss_action": 0.008408583700656891, "loss_total": 0.008408583700656891, "step": 71430 }, { "grad_norm": 0.18409550189971924, "learning_rate": 2.06923959219589e-05, "loss": 0.007, "step": 71440 }, { "loss_action": 0.007392358034849167, "loss_total": 0.007392358034849167, "step": 71440 }, { "grad_norm": 0.18932464718818665, "learning_rate": 2.0679001094938793e-05, "loss": 0.007, "step": 71450 }, { "loss_action": 0.006509730126708746, "loss_total": 0.006509730126708746, "step": 71450 }, { "grad_norm": 0.17553573846817017, "learning_rate": 2.066560947441904e-05, "loss": 0.0056, "step": 71460 }, { "loss_action": 0.007696556858718395, "loss_total": 0.007696556858718395, "step": 71460 }, { "grad_norm": 0.17612318694591522, "learning_rate": 2.0652221061864152e-05, "loss": 0.0068, "step": 71470 }, { "loss_action": 0.0070437658578157425, "loss_total": 0.0070437658578157425, "step": 71470 }, { "grad_norm": 0.20528773963451385, "learning_rate": 2.0638835858738226e-05, "loss": 0.006, "step": 71480 }, { "loss_action": 0.005817354191094637, "loss_total": 0.005817354191094637, "step": 71480 }, { "grad_norm": 0.12855304777622223, "learning_rate": 2.0625453866505068e-05, "loss": 0.0062, "step": 71490 }, { "loss_action": 0.004414084367454052, "loss_total": 0.004414084367454052, "step": 71490 }, { "grad_norm": 0.13390417397022247, "learning_rate": 2.0612075086628123e-05, "loss": 0.007, "step": 71500 }, { "loss_action": 0.005560722667723894, "loss_total": 0.005560722667723894, "step": 71500 }, { "grad_norm": 0.12873654067516327, "learning_rate": 2.059869952057045e-05, "loss": 0.0071, "step": 71510 }, { "loss_action": 0.005404267925769091, "loss_total": 0.005404267925769091, "step": 71510 }, { "grad_norm": 0.16489669680595398, "learning_rate": 2.0585327169794793e-05, "loss": 0.0052, "step": 71520 }, { "loss_action": 0.009343135170638561, "loss_total": 0.009343135170638561, "step": 71520 }, { "grad_norm": 0.18606239557266235, "learning_rate": 2.0571958035763534e-05, "loss": 0.0068, "step": 71530 }, { "loss_action": 0.004827370401471853, "loss_total": 0.004827370401471853, "step": 71530 }, { "grad_norm": 0.17030109465122223, "learning_rate": 2.0558592119938715e-05, "loss": 0.0074, "step": 71540 }, { "loss_action": 0.006134644616395235, "loss_total": 0.006134644616395235, "step": 71540 }, { "grad_norm": 0.14610454440116882, "learning_rate": 2.054522942378198e-05, "loss": 0.0064, "step": 71550 }, { "loss_action": 0.004297822248190641, "loss_total": 0.004297822248190641, "step": 71550 }, { "grad_norm": 0.17322739958763123, "learning_rate": 2.053186994875469e-05, "loss": 0.0072, "step": 71560 }, { "loss_action": 0.0058822305873036385, "loss_total": 0.0058822305873036385, "step": 71560 }, { "grad_norm": 0.17284941673278809, "learning_rate": 2.0518513696317775e-05, "loss": 0.0066, "step": 71570 }, { "loss_action": 0.008392644114792347, "loss_total": 0.008392644114792347, "step": 71570 }, { "grad_norm": 0.1639377474784851, "learning_rate": 2.050516066793188e-05, "loss": 0.006, "step": 71580 }, { "loss_action": 0.0066851223818957806, "loss_total": 0.0066851223818957806, "step": 71580 }, { "grad_norm": 0.1467718482017517, "learning_rate": 2.0491810865057276e-05, "loss": 0.0054, "step": 71590 }, { "loss_action": 0.00595086719840765, "loss_total": 0.00595086719840765, "step": 71590 }, { "grad_norm": 0.18152561783790588, "learning_rate": 2.0478464289153882e-05, "loss": 0.0079, "step": 71600 }, { "loss_action": 0.006786698941141367, "loss_total": 0.006786698941141367, "step": 71600 }, { "grad_norm": 0.1777302622795105, "learning_rate": 2.0465120941681232e-05, "loss": 0.0067, "step": 71610 }, { "loss_action": 0.007991730235517025, "loss_total": 0.007991730235517025, "step": 71610 }, { "grad_norm": 0.14818540215492249, "learning_rate": 2.0451780824098566e-05, "loss": 0.0058, "step": 71620 }, { "loss_action": 0.005399626679718494, "loss_total": 0.005399626679718494, "step": 71620 }, { "grad_norm": 0.174923375248909, "learning_rate": 2.043844393786471e-05, "loss": 0.007, "step": 71630 }, { "loss_action": 0.005087966099381447, "loss_total": 0.005087966099381447, "step": 71630 }, { "grad_norm": 0.21947330236434937, "learning_rate": 2.0425110284438193e-05, "loss": 0.0063, "step": 71640 }, { "loss_action": 0.005397334229201078, "loss_total": 0.005397334229201078, "step": 71640 }, { "grad_norm": 0.15802036225795746, "learning_rate": 2.041177986527712e-05, "loss": 0.0058, "step": 71650 }, { "loss_action": 0.004176636692136526, "loss_total": 0.004176636692136526, "step": 71650 }, { "grad_norm": 0.16786281764507294, "learning_rate": 2.0398452681839347e-05, "loss": 0.0076, "step": 71660 }, { "loss_action": 0.008380603045225143, "loss_total": 0.008380603045225143, "step": 71660 }, { "grad_norm": 0.230376198887825, "learning_rate": 2.0385128735582272e-05, "loss": 0.0072, "step": 71670 }, { "loss_action": 0.007237755693495274, "loss_total": 0.007237755693495274, "step": 71670 }, { "grad_norm": 0.17247402667999268, "learning_rate": 2.0371808027963003e-05, "loss": 0.0075, "step": 71680 }, { "loss_action": 0.009585493244230747, "loss_total": 0.009585493244230747, "step": 71680 }, { "grad_norm": 0.22009392082691193, "learning_rate": 2.035849056043825e-05, "loss": 0.0075, "step": 71690 }, { "loss_action": 0.006314181722700596, "loss_total": 0.006314181722700596, "step": 71690 }, { "grad_norm": 0.21022383868694305, "learning_rate": 2.03451763344644e-05, "loss": 0.0068, "step": 71700 }, { "loss_action": 0.007815987803041935, "loss_total": 0.007815987803041935, "step": 71700 }, { "grad_norm": 0.1608666032552719, "learning_rate": 2.0331865351497482e-05, "loss": 0.0061, "step": 71710 }, { "loss_action": 0.003940405789762735, "loss_total": 0.003940405789762735, "step": 71710 }, { "grad_norm": 0.14923958480358124, "learning_rate": 2.0318557612993185e-05, "loss": 0.0065, "step": 71720 }, { "loss_action": 0.005179417785257101, "loss_total": 0.005179417785257101, "step": 71720 }, { "grad_norm": 0.12466178089380264, "learning_rate": 2.0305253120406782e-05, "loss": 0.0058, "step": 71730 }, { "loss_action": 0.007395436521619558, "loss_total": 0.007395436521619558, "step": 71730 }, { "grad_norm": 0.15361280739307404, "learning_rate": 2.029195187519325e-05, "loss": 0.0058, "step": 71740 }, { "loss_action": 0.008915684185922146, "loss_total": 0.008915684185922146, "step": 71740 }, { "grad_norm": 0.2783636152744293, "learning_rate": 2.0278653878807217e-05, "loss": 0.0068, "step": 71750 }, { "loss_action": 0.006267446558922529, "loss_total": 0.006267446558922529, "step": 71750 }, { "grad_norm": 0.22077134251594543, "learning_rate": 2.0265359132702892e-05, "loss": 0.0055, "step": 71760 }, { "loss_action": 0.00943057332187891, "loss_total": 0.00943057332187891, "step": 71760 }, { "grad_norm": 0.19773192703723907, "learning_rate": 2.0252067638334182e-05, "loss": 0.0069, "step": 71770 }, { "loss_action": 0.005237051285803318, "loss_total": 0.005237051285803318, "step": 71770 }, { "grad_norm": 0.13410496711730957, "learning_rate": 2.023877939715464e-05, "loss": 0.0063, "step": 71780 }, { "loss_action": 0.0049289255402982235, "loss_total": 0.0049289255402982235, "step": 71780 }, { "grad_norm": 0.12605278193950653, "learning_rate": 2.0225494410617448e-05, "loss": 0.006, "step": 71790 }, { "loss_action": 0.0062394882552325726, "loss_total": 0.0062394882552325726, "step": 71790 }, { "grad_norm": 0.17587055265903473, "learning_rate": 2.02122126801754e-05, "loss": 0.0071, "step": 71800 }, { "loss_action": 0.006631252355873585, "loss_total": 0.006631252355873585, "step": 71800 }, { "grad_norm": 0.16523897647857666, "learning_rate": 2.0198934207281018e-05, "loss": 0.0069, "step": 71810 }, { "loss_action": 0.005569335538893938, "loss_total": 0.005569335538893938, "step": 71810 }, { "grad_norm": 0.16212619841098785, "learning_rate": 2.0185658993386357e-05, "loss": 0.0062, "step": 71820 }, { "loss_action": 0.006167551036924124, "loss_total": 0.006167551036924124, "step": 71820 }, { "grad_norm": 0.20769934356212616, "learning_rate": 2.0172387039943226e-05, "loss": 0.0067, "step": 71830 }, { "loss_action": 0.005730749107897282, "loss_total": 0.005730749107897282, "step": 71830 }, { "grad_norm": 0.17430859804153442, "learning_rate": 2.0159118348402968e-05, "loss": 0.0061, "step": 71840 }, { "loss_action": 0.005488441325724125, "loss_total": 0.005488441325724125, "step": 71840 }, { "grad_norm": 0.17535755038261414, "learning_rate": 2.0145852920216697e-05, "loss": 0.0066, "step": 71850 }, { "loss_action": 0.006408874411135912, "loss_total": 0.006408874411135912, "step": 71850 }, { "grad_norm": 0.19708925485610962, "learning_rate": 2.0132590756835045e-05, "loss": 0.0071, "step": 71860 }, { "loss_action": 0.005906537640839815, "loss_total": 0.005906537640839815, "step": 71860 }, { "grad_norm": 0.15570025146007538, "learning_rate": 2.0119331859708386e-05, "loss": 0.0064, "step": 71870 }, { "loss_action": 0.009331334382295609, "loss_total": 0.009331334382295609, "step": 71870 }, { "grad_norm": 0.1750156283378601, "learning_rate": 2.0106076230286654e-05, "loss": 0.0074, "step": 71880 }, { "loss_action": 0.00853816419839859, "loss_total": 0.00853816419839859, "step": 71880 }, { "grad_norm": 0.15144909918308258, "learning_rate": 2.0092823870019488e-05, "loss": 0.0074, "step": 71890 }, { "loss_action": 0.0055899848230183125, "loss_total": 0.0055899848230183125, "step": 71890 }, { "grad_norm": 0.1823657900094986, "learning_rate": 2.0079574780356115e-05, "loss": 0.0061, "step": 71900 }, { "loss_action": 0.0060367342084646225, "loss_total": 0.0060367342084646225, "step": 71900 }, { "grad_norm": 0.21171049773693085, "learning_rate": 2.0066328962745486e-05, "loss": 0.007, "step": 71910 }, { "loss_action": 0.005809539929032326, "loss_total": 0.005809539929032326, "step": 71910 }, { "grad_norm": 0.21909445524215698, "learning_rate": 2.00530864186361e-05, "loss": 0.0065, "step": 71920 }, { "loss_action": 0.005745772272348404, "loss_total": 0.005745772272348404, "step": 71920 }, { "grad_norm": 0.14024709165096283, "learning_rate": 2.003984714947618e-05, "loss": 0.0061, "step": 71930 }, { "loss_action": 0.0067170532420277596, "loss_total": 0.0067170532420277596, "step": 71930 }, { "grad_norm": 0.16682499647140503, "learning_rate": 2.0026611156713515e-05, "loss": 0.0053, "step": 71940 }, { "loss_action": 0.005858757067471743, "loss_total": 0.005858757067471743, "step": 71940 }, { "grad_norm": 0.18193702399730682, "learning_rate": 2.0013378441795584e-05, "loss": 0.0059, "step": 71950 }, { "loss_action": 0.007915210910141468, "loss_total": 0.007915210910141468, "step": 71950 }, { "grad_norm": 0.17283858358860016, "learning_rate": 2.0000149006169506e-05, "loss": 0.0063, "step": 71960 }, { "loss_action": 0.005126699339598417, "loss_total": 0.005126699339598417, "step": 71960 }, { "grad_norm": 0.16660365462303162, "learning_rate": 1.9986922851282048e-05, "loss": 0.0057, "step": 71970 }, { "loss_action": 0.006894666701555252, "loss_total": 0.006894666701555252, "step": 71970 }, { "grad_norm": 0.13749836385250092, "learning_rate": 1.997369997857956e-05, "loss": 0.0068, "step": 71980 }, { "loss_action": 0.008709913119673729, "loss_total": 0.008709913119673729, "step": 71980 }, { "grad_norm": 0.15200555324554443, "learning_rate": 1.9960480389508103e-05, "loss": 0.0063, "step": 71990 }, { "loss_action": 0.006026696413755417, "loss_total": 0.006026696413755417, "step": 71990 }, { "grad_norm": 0.14761395752429962, "learning_rate": 1.9947264085513363e-05, "loss": 0.0057, "step": 72000 }, { "loss_action": 0.007547035347670317, "loss_total": 0.007547035347670317, "step": 72000 }, { "grad_norm": 0.14181657135486603, "learning_rate": 1.993405106804062e-05, "loss": 0.0069, "step": 72010 }, { "loss_action": 0.0072339363396167755, "loss_total": 0.0072339363396167755, "step": 72010 }, { "grad_norm": 0.16792580485343933, "learning_rate": 1.9920841338534867e-05, "loss": 0.0063, "step": 72020 }, { "loss_action": 0.006526402197778225, "loss_total": 0.006526402197778225, "step": 72020 }, { "grad_norm": 0.1994287371635437, "learning_rate": 1.9907634898440646e-05, "loss": 0.0069, "step": 72030 }, { "loss_action": 0.0034775177482515574, "loss_total": 0.0034775177482515574, "step": 72030 }, { "grad_norm": 0.16522489488124847, "learning_rate": 1.989443174920227e-05, "loss": 0.0069, "step": 72040 }, { "loss_action": 0.008801900781691074, "loss_total": 0.008801900781691074, "step": 72040 }, { "grad_norm": 0.15141455829143524, "learning_rate": 1.988123189226355e-05, "loss": 0.0067, "step": 72050 }, { "loss_action": 0.00940697081387043, "loss_total": 0.00940697081387043, "step": 72050 }, { "grad_norm": 0.1656104326248169, "learning_rate": 1.986803532906805e-05, "loss": 0.0069, "step": 72060 }, { "loss_action": 0.0042235879227519035, "loss_total": 0.0042235879227519035, "step": 72060 }, { "grad_norm": 0.16510522365570068, "learning_rate": 1.985484206105889e-05, "loss": 0.0068, "step": 72070 }, { "loss_action": 0.01020188257098198, "loss_total": 0.01020188257098198, "step": 72070 }, { "grad_norm": 0.18704386055469513, "learning_rate": 1.9841652089678887e-05, "loss": 0.007, "step": 72080 }, { "loss_action": 0.005279657896608114, "loss_total": 0.005279657896608114, "step": 72080 }, { "grad_norm": 0.15608616173267365, "learning_rate": 1.9828465416370435e-05, "loss": 0.007, "step": 72090 }, { "loss_action": 0.006866454146802425, "loss_total": 0.006866454146802425, "step": 72090 }, { "grad_norm": 0.16778770089149475, "learning_rate": 1.9815282042575685e-05, "loss": 0.007, "step": 72100 }, { "loss_action": 0.009999343194067478, "loss_total": 0.009999343194067478, "step": 72100 }, { "grad_norm": 0.1635924130678177, "learning_rate": 1.9802101969736285e-05, "loss": 0.0066, "step": 72110 }, { "loss_action": 0.005751434713602066, "loss_total": 0.005751434713602066, "step": 72110 }, { "grad_norm": 0.16041713953018188, "learning_rate": 1.9788925199293633e-05, "loss": 0.0065, "step": 72120 }, { "loss_action": 0.004080590792000294, "loss_total": 0.004080590792000294, "step": 72120 }, { "grad_norm": 0.19773007929325104, "learning_rate": 1.977575173268868e-05, "loss": 0.0054, "step": 72130 }, { "loss_action": 0.008013177663087845, "loss_total": 0.008013177663087845, "step": 72130 }, { "grad_norm": 0.15795406699180603, "learning_rate": 1.9762581571362094e-05, "loss": 0.0069, "step": 72140 }, { "loss_action": 0.004591319244354963, "loss_total": 0.004591319244354963, "step": 72140 }, { "grad_norm": 0.1563253253698349, "learning_rate": 1.9749414716754112e-05, "loss": 0.0067, "step": 72150 }, { "loss_action": 0.006309840362519026, "loss_total": 0.006309840362519026, "step": 72150 }, { "grad_norm": 0.14672306180000305, "learning_rate": 1.973625117030465e-05, "loss": 0.006, "step": 72160 }, { "loss_action": 0.007643919438123703, "loss_total": 0.007643919438123703, "step": 72160 }, { "grad_norm": 0.17042620480060577, "learning_rate": 1.972309093345326e-05, "loss": 0.0061, "step": 72170 }, { "loss_action": 0.006134438328444958, "loss_total": 0.006134438328444958, "step": 72170 }, { "grad_norm": 0.11656391620635986, "learning_rate": 1.970993400763915e-05, "loss": 0.0059, "step": 72180 }, { "loss_action": 0.006167667917907238, "loss_total": 0.006167667917907238, "step": 72180 }, { "grad_norm": 0.1440829336643219, "learning_rate": 1.969678039430109e-05, "loss": 0.0066, "step": 72190 }, { "loss_action": 0.005871884059160948, "loss_total": 0.005871884059160948, "step": 72190 }, { "grad_norm": 0.1674366146326065, "learning_rate": 1.9683630094877564e-05, "loss": 0.0055, "step": 72200 }, { "loss_action": 0.006491806358098984, "loss_total": 0.006491806358098984, "step": 72200 }, { "grad_norm": 0.1414673924446106, "learning_rate": 1.9670483110806696e-05, "loss": 0.0061, "step": 72210 }, { "loss_action": 0.007452969904989004, "loss_total": 0.007452969904989004, "step": 72210 }, { "grad_norm": 0.15615953505039215, "learning_rate": 1.9657339443526172e-05, "loss": 0.0065, "step": 72220 }, { "loss_action": 0.009284424595534801, "loss_total": 0.009284424595534801, "step": 72220 }, { "grad_norm": 0.19847583770751953, "learning_rate": 1.964419909447339e-05, "loss": 0.0064, "step": 72230 }, { "loss_action": 0.005973184481263161, "loss_total": 0.005973184481263161, "step": 72230 }, { "grad_norm": 0.17547832429409027, "learning_rate": 1.963106206508536e-05, "loss": 0.0068, "step": 72240 }, { "loss_action": 0.0045653353445231915, "loss_total": 0.0045653353445231915, "step": 72240 }, { "grad_norm": 0.20413170754909515, "learning_rate": 1.9617928356798738e-05, "loss": 0.0062, "step": 72250 }, { "loss_action": 0.005616249982267618, "loss_total": 0.005616249982267618, "step": 72250 }, { "grad_norm": 0.14336815476417542, "learning_rate": 1.960479797104977e-05, "loss": 0.0074, "step": 72260 }, { "loss_action": 0.006696101278066635, "loss_total": 0.006696101278066635, "step": 72260 }, { "grad_norm": 0.16773615777492523, "learning_rate": 1.9591670909274418e-05, "loss": 0.0068, "step": 72270 }, { "loss_action": 0.007611924782395363, "loss_total": 0.007611924782395363, "step": 72270 }, { "grad_norm": 0.17761030793190002, "learning_rate": 1.9578547172908184e-05, "loss": 0.006, "step": 72280 }, { "loss_action": 0.009334510192275047, "loss_total": 0.009334510192275047, "step": 72280 }, { "grad_norm": 0.1685950756072998, "learning_rate": 1.9565426763386325e-05, "loss": 0.0071, "step": 72290 }, { "loss_action": 0.006382495164871216, "loss_total": 0.006382495164871216, "step": 72290 }, { "grad_norm": 0.16407525539398193, "learning_rate": 1.9552309682143622e-05, "loss": 0.0069, "step": 72300 }, { "loss_action": 0.007018267177045345, "loss_total": 0.007018267177045345, "step": 72300 }, { "grad_norm": 0.17976830899715424, "learning_rate": 1.9539195930614574e-05, "loss": 0.006, "step": 72310 }, { "loss_action": 0.005141569301486015, "loss_total": 0.005141569301486015, "step": 72310 }, { "grad_norm": 0.18008562922477722, "learning_rate": 1.952608551023324e-05, "loss": 0.0059, "step": 72320 }, { "loss_action": 0.0072375512681901455, "loss_total": 0.0072375512681901455, "step": 72320 }, { "grad_norm": 0.16887997090816498, "learning_rate": 1.9512978422433397e-05, "loss": 0.0054, "step": 72330 }, { "loss_action": 0.005396666936576366, "loss_total": 0.005396666936576366, "step": 72330 }, { "grad_norm": 0.14818981289863586, "learning_rate": 1.9499874668648376e-05, "loss": 0.0067, "step": 72340 }, { "loss_action": 0.0058578914031386375, "loss_total": 0.0058578914031386375, "step": 72340 }, { "grad_norm": 0.14245004951953888, "learning_rate": 1.9486774250311213e-05, "loss": 0.0061, "step": 72350 }, { "loss_action": 0.015320866368710995, "loss_total": 0.015320866368710995, "step": 72350 }, { "grad_norm": 0.18257218599319458, "learning_rate": 1.9473677168854537e-05, "loss": 0.0075, "step": 72360 }, { "loss_action": 0.007776577025651932, "loss_total": 0.007776577025651932, "step": 72360 }, { "grad_norm": 0.14681558310985565, "learning_rate": 1.946058342571065e-05, "loss": 0.0063, "step": 72370 }, { "loss_action": 0.007660359144210815, "loss_total": 0.007660359144210815, "step": 72370 }, { "grad_norm": 0.16854164004325867, "learning_rate": 1.9447493022311424e-05, "loss": 0.0067, "step": 72380 }, { "loss_action": 0.013137590140104294, "loss_total": 0.013137590140104294, "step": 72380 }, { "grad_norm": 0.20693787932395935, "learning_rate": 1.9434405960088442e-05, "loss": 0.0066, "step": 72390 }, { "loss_action": 0.011254878714680672, "loss_total": 0.011254878714680672, "step": 72390 }, { "grad_norm": 0.18923254311084747, "learning_rate": 1.9421322240472857e-05, "loss": 0.007, "step": 72400 }, { "loss_action": 0.006267654709517956, "loss_total": 0.006267654709517956, "step": 72400 }, { "grad_norm": 0.15529704093933105, "learning_rate": 1.9408241864895494e-05, "loss": 0.0065, "step": 72410 }, { "loss_action": 0.007478467654436827, "loss_total": 0.007478467654436827, "step": 72410 }, { "grad_norm": 0.17008118331432343, "learning_rate": 1.939516483478681e-05, "loss": 0.0063, "step": 72420 }, { "loss_action": 0.0053776768036186695, "loss_total": 0.0053776768036186695, "step": 72420 }, { "grad_norm": 0.1729304939508438, "learning_rate": 1.9382091151576902e-05, "loss": 0.0062, "step": 72430 }, { "loss_action": 0.004671998787671328, "loss_total": 0.004671998787671328, "step": 72430 }, { "grad_norm": 0.16101951897144318, "learning_rate": 1.9369020816695454e-05, "loss": 0.0064, "step": 72440 }, { "loss_action": 0.007313117850571871, "loss_total": 0.007313117850571871, "step": 72440 }, { "grad_norm": 0.22591657936573029, "learning_rate": 1.935595383157184e-05, "loss": 0.0072, "step": 72450 }, { "loss_action": 0.005388698074966669, "loss_total": 0.005388698074966669, "step": 72450 }, { "grad_norm": 0.18123650550842285, "learning_rate": 1.9342890197635057e-05, "loss": 0.0061, "step": 72460 }, { "loss_action": 0.0061787511222064495, "loss_total": 0.0061787511222064495, "step": 72460 }, { "grad_norm": 0.26231539249420166, "learning_rate": 1.9329829916313685e-05, "loss": 0.0066, "step": 72470 }, { "loss_action": 0.005955524276942015, "loss_total": 0.005955524276942015, "step": 72470 }, { "grad_norm": 0.16238097846508026, "learning_rate": 1.9316772989036013e-05, "loss": 0.0067, "step": 72480 }, { "loss_action": 0.008234303444623947, "loss_total": 0.008234303444623947, "step": 72480 }, { "grad_norm": 0.16490891575813293, "learning_rate": 1.930371941722991e-05, "loss": 0.0065, "step": 72490 }, { "loss_action": 0.006567689124494791, "loss_total": 0.006567689124494791, "step": 72490 }, { "grad_norm": 0.1806119829416275, "learning_rate": 1.929066920232292e-05, "loss": 0.0063, "step": 72500 }, { "loss_action": 0.005857772193849087, "loss_total": 0.005857772193849087, "step": 72500 }, { "grad_norm": 0.16930794715881348, "learning_rate": 1.9277622345742152e-05, "loss": 0.007, "step": 72510 }, { "loss_action": 0.0085628442466259, "loss_total": 0.0085628442466259, "step": 72510 }, { "grad_norm": 0.21312594413757324, "learning_rate": 1.926457884891444e-05, "loss": 0.0079, "step": 72520 }, { "loss_action": 0.011183328926563263, "loss_total": 0.011183328926563263, "step": 72520 }, { "grad_norm": 0.19236740469932556, "learning_rate": 1.9251538713266147e-05, "loss": 0.0076, "step": 72530 }, { "loss_action": 0.006379767786711454, "loss_total": 0.006379767786711454, "step": 72530 }, { "grad_norm": 0.17362062633037567, "learning_rate": 1.9238501940223358e-05, "loss": 0.0061, "step": 72540 }, { "loss_action": 0.005593248177319765, "loss_total": 0.005593248177319765, "step": 72540 }, { "grad_norm": 0.14490380883216858, "learning_rate": 1.922546853121175e-05, "loss": 0.0061, "step": 72550 }, { "loss_action": 0.006540250964462757, "loss_total": 0.006540250964462757, "step": 72550 }, { "grad_norm": 0.2041451632976532, "learning_rate": 1.9212438487656647e-05, "loss": 0.0059, "step": 72560 }, { "loss_action": 0.008864788338541985, "loss_total": 0.008864788338541985, "step": 72560 }, { "grad_norm": 0.16983704268932343, "learning_rate": 1.9199411810982965e-05, "loss": 0.0063, "step": 72570 }, { "loss_action": 0.007083166856318712, "loss_total": 0.007083166856318712, "step": 72570 }, { "grad_norm": 0.20471814274787903, "learning_rate": 1.918638850261532e-05, "loss": 0.0074, "step": 72580 }, { "loss_action": 0.006786517333239317, "loss_total": 0.006786517333239317, "step": 72580 }, { "grad_norm": 0.18116217851638794, "learning_rate": 1.9173368563977885e-05, "loss": 0.0065, "step": 72590 }, { "loss_action": 0.004878228064626455, "loss_total": 0.004878228064626455, "step": 72590 }, { "grad_norm": 0.1693989485502243, "learning_rate": 1.9160351996494513e-05, "loss": 0.0059, "step": 72600 }, { "loss_action": 0.0068414220586419106, "loss_total": 0.0068414220586419106, "step": 72600 }, { "grad_norm": 0.20116639137268066, "learning_rate": 1.9147338801588677e-05, "loss": 0.0073, "step": 72610 }, { "loss_action": 0.0049156066961586475, "loss_total": 0.0049156066961586475, "step": 72610 }, { "grad_norm": 0.18521714210510254, "learning_rate": 1.913432898068351e-05, "loss": 0.0059, "step": 72620 }, { "loss_action": 0.006230659317225218, "loss_total": 0.006230659317225218, "step": 72620 }, { "grad_norm": 0.17539450526237488, "learning_rate": 1.912132253520169e-05, "loss": 0.0068, "step": 72630 }, { "loss_action": 0.00968767050653696, "loss_total": 0.00968767050653696, "step": 72630 }, { "grad_norm": 0.17252813279628754, "learning_rate": 1.910831946656564e-05, "loss": 0.0073, "step": 72640 }, { "loss_action": 0.006314546335488558, "loss_total": 0.006314546335488558, "step": 72640 }, { "grad_norm": 0.14856530725955963, "learning_rate": 1.909531977619731e-05, "loss": 0.0059, "step": 72650 }, { "loss_action": 0.004424648825079203, "loss_total": 0.004424648825079203, "step": 72650 }, { "grad_norm": 0.11754318326711655, "learning_rate": 1.908232346551834e-05, "loss": 0.0069, "step": 72660 }, { "loss_action": 0.00616565253585577, "loss_total": 0.00616565253585577, "step": 72660 }, { "grad_norm": 0.18774251639842987, "learning_rate": 1.9069330535949993e-05, "loss": 0.0063, "step": 72670 }, { "loss_action": 0.006842254661023617, "loss_total": 0.006842254661023617, "step": 72670 }, { "grad_norm": 0.12531624734401703, "learning_rate": 1.9056340988913167e-05, "loss": 0.0065, "step": 72680 }, { "loss_action": 0.00469600223004818, "loss_total": 0.00469600223004818, "step": 72680 }, { "grad_norm": 0.1827605962753296, "learning_rate": 1.9043354825828357e-05, "loss": 0.0055, "step": 72690 }, { "loss_action": 0.0047229621559381485, "loss_total": 0.0047229621559381485, "step": 72690 }, { "grad_norm": 0.13229703903198242, "learning_rate": 1.9030372048115724e-05, "loss": 0.0063, "step": 72700 }, { "loss_action": 0.00448206253349781, "loss_total": 0.00448206253349781, "step": 72700 }, { "grad_norm": 0.1651035100221634, "learning_rate": 1.9017392657195056e-05, "loss": 0.0058, "step": 72710 }, { "loss_action": 0.004648194182664156, "loss_total": 0.004648194182664156, "step": 72710 }, { "grad_norm": 0.15029558539390564, "learning_rate": 1.9004416654485724e-05, "loss": 0.0052, "step": 72720 }, { "loss_action": 0.005246124695986509, "loss_total": 0.005246124695986509, "step": 72720 }, { "grad_norm": 0.15534880757331848, "learning_rate": 1.8991444041406785e-05, "loss": 0.006, "step": 72730 }, { "loss_action": 0.004748883657157421, "loss_total": 0.004748883657157421, "step": 72730 }, { "grad_norm": 0.17327989637851715, "learning_rate": 1.8978474819376912e-05, "loss": 0.0062, "step": 72740 }, { "loss_action": 0.006304526701569557, "loss_total": 0.006304526701569557, "step": 72740 }, { "grad_norm": 0.15137679874897003, "learning_rate": 1.8965508989814406e-05, "loss": 0.0061, "step": 72750 }, { "loss_action": 0.007898831740021706, "loss_total": 0.007898831740021706, "step": 72750 }, { "grad_norm": 0.14900489151477814, "learning_rate": 1.8952546554137158e-05, "loss": 0.0065, "step": 72760 }, { "loss_action": 0.005748807452619076, "loss_total": 0.005748807452619076, "step": 72760 }, { "grad_norm": 0.19911955296993256, "learning_rate": 1.8939587513762757e-05, "loss": 0.0068, "step": 72770 }, { "loss_action": 0.00536692701280117, "loss_total": 0.00536692701280117, "step": 72770 }, { "grad_norm": 0.1244916319847107, "learning_rate": 1.892663187010835e-05, "loss": 0.0053, "step": 72780 }, { "loss_action": 0.005463749170303345, "loss_total": 0.005463749170303345, "step": 72780 }, { "grad_norm": 0.18794004619121552, "learning_rate": 1.891367962459077e-05, "loss": 0.0061, "step": 72790 }, { "loss_action": 0.0052833533845841885, "loss_total": 0.0052833533845841885, "step": 72790 }, { "grad_norm": 0.1668912023305893, "learning_rate": 1.890073077862644e-05, "loss": 0.0058, "step": 72800 }, { "loss_action": 0.00518459640443325, "loss_total": 0.00518459640443325, "step": 72800 }, { "grad_norm": 0.2137114703655243, "learning_rate": 1.888778533363146e-05, "loss": 0.0065, "step": 72810 }, { "loss_action": 0.006372945383191109, "loss_total": 0.006372945383191109, "step": 72810 }, { "grad_norm": 0.20323121547698975, "learning_rate": 1.8874843291021478e-05, "loss": 0.0067, "step": 72820 }, { "loss_action": 0.006351349875330925, "loss_total": 0.006351349875330925, "step": 72820 }, { "grad_norm": 0.17433679103851318, "learning_rate": 1.8861904652211853e-05, "loss": 0.0067, "step": 72830 }, { "loss_action": 0.004318377003073692, "loss_total": 0.004318377003073692, "step": 72830 }, { "grad_norm": 0.15177679061889648, "learning_rate": 1.8848969418617507e-05, "loss": 0.0061, "step": 72840 }, { "loss_action": 0.005473767872899771, "loss_total": 0.005473767872899771, "step": 72840 }, { "grad_norm": 0.14384475350379944, "learning_rate": 1.8836037591653044e-05, "loss": 0.006, "step": 72850 }, { "loss_action": 0.004740834701806307, "loss_total": 0.004740834701806307, "step": 72850 }, { "grad_norm": 0.20503950119018555, "learning_rate": 1.882310917273262e-05, "loss": 0.0068, "step": 72860 }, { "loss_action": 0.006834885571151972, "loss_total": 0.006834885571151972, "step": 72860 }, { "grad_norm": 0.1867683380842209, "learning_rate": 1.881018416327014e-05, "loss": 0.0061, "step": 72870 }, { "loss_action": 0.004565411247313023, "loss_total": 0.004565411247313023, "step": 72870 }, { "grad_norm": 0.1339656412601471, "learning_rate": 1.8797262564679014e-05, "loss": 0.0055, "step": 72880 }, { "loss_action": 0.007357018534094095, "loss_total": 0.007357018534094095, "step": 72880 }, { "grad_norm": 0.20922790467739105, "learning_rate": 1.8784344378372355e-05, "loss": 0.0065, "step": 72890 }, { "loss_action": 0.0046409498900175095, "loss_total": 0.0046409498900175095, "step": 72890 }, { "grad_norm": 0.15780334174633026, "learning_rate": 1.8771429605762843e-05, "loss": 0.0055, "step": 72900 }, { "loss_action": 0.008086026646196842, "loss_total": 0.008086026646196842, "step": 72900 }, { "grad_norm": 0.16005784273147583, "learning_rate": 1.8758518248262835e-05, "loss": 0.0065, "step": 72910 }, { "loss_action": 0.007771665696054697, "loss_total": 0.007771665696054697, "step": 72910 }, { "grad_norm": 0.153534933924675, "learning_rate": 1.8745610307284305e-05, "loss": 0.0061, "step": 72920 }, { "loss_action": 0.006449531763792038, "loss_total": 0.006449531763792038, "step": 72920 }, { "grad_norm": 0.15833880007266998, "learning_rate": 1.8732705784238862e-05, "loss": 0.0057, "step": 72930 }, { "loss_action": 0.004679680336266756, "loss_total": 0.004679680336266756, "step": 72930 }, { "grad_norm": 0.2047380954027176, "learning_rate": 1.8719804680537682e-05, "loss": 0.007, "step": 72940 }, { "loss_action": 0.005365441087633371, "loss_total": 0.005365441087633371, "step": 72940 }, { "grad_norm": 0.18624170124530792, "learning_rate": 1.870690699759164e-05, "loss": 0.006, "step": 72950 }, { "loss_action": 0.004671918228268623, "loss_total": 0.004671918228268623, "step": 72950 }, { "grad_norm": 0.26441246271133423, "learning_rate": 1.8694012736811213e-05, "loss": 0.0057, "step": 72960 }, { "loss_action": 0.006058460101485252, "loss_total": 0.006058460101485252, "step": 72960 }, { "grad_norm": 0.16038639843463898, "learning_rate": 1.8681121899606463e-05, "loss": 0.0069, "step": 72970 }, { "loss_action": 0.00817442312836647, "loss_total": 0.00817442312836647, "step": 72970 }, { "grad_norm": 0.1644279509782791, "learning_rate": 1.8668234487387144e-05, "loss": 0.0072, "step": 72980 }, { "loss_action": 0.0055261473171412945, "loss_total": 0.0055261473171412945, "step": 72980 }, { "grad_norm": 0.2031273990869522, "learning_rate": 1.8655350501562592e-05, "loss": 0.0059, "step": 72990 }, { "loss_action": 0.0058936444111168385, "loss_total": 0.0058936444111168385, "step": 72990 }, { "grad_norm": 0.16302821040153503, "learning_rate": 1.8642469943541796e-05, "loss": 0.0068, "step": 73000 }, { "loss_action": 0.0060313004069030285, "loss_total": 0.0060313004069030285, "step": 73000 }, { "grad_norm": 0.16381694376468658, "learning_rate": 1.8629592814733328e-05, "loss": 0.0056, "step": 73010 }, { "loss_action": 0.007263779640197754, "loss_total": 0.007263779640197754, "step": 73010 }, { "grad_norm": 0.16963303089141846, "learning_rate": 1.8616719116545438e-05, "loss": 0.006, "step": 73020 }, { "loss_action": 0.005612974986433983, "loss_total": 0.005612974986433983, "step": 73020 }, { "grad_norm": 0.15173690021038055, "learning_rate": 1.8603848850385952e-05, "loss": 0.0061, "step": 73030 }, { "loss_action": 0.00511958496645093, "loss_total": 0.00511958496645093, "step": 73030 }, { "grad_norm": 0.13650618493556976, "learning_rate": 1.859098201766236e-05, "loss": 0.006, "step": 73040 }, { "loss_action": 0.006646359339356422, "loss_total": 0.006646359339356422, "step": 73040 }, { "grad_norm": 0.16877664625644684, "learning_rate": 1.8578118619781726e-05, "loss": 0.0065, "step": 73050 }, { "loss_action": 0.005916897673159838, "loss_total": 0.005916897673159838, "step": 73050 }, { "grad_norm": 0.24844300746917725, "learning_rate": 1.856525865815083e-05, "loss": 0.007, "step": 73060 }, { "loss_action": 0.005281899590045214, "loss_total": 0.005281899590045214, "step": 73060 }, { "grad_norm": 0.23747703433036804, "learning_rate": 1.8552402134175966e-05, "loss": 0.0064, "step": 73070 }, { "loss_action": 0.006016651634126902, "loss_total": 0.006016651634126902, "step": 73070 }, { "grad_norm": 0.1857304871082306, "learning_rate": 1.8539549049263143e-05, "loss": 0.0062, "step": 73080 }, { "loss_action": 0.004555713851004839, "loss_total": 0.004555713851004839, "step": 73080 }, { "grad_norm": 0.16306275129318237, "learning_rate": 1.8526699404817917e-05, "loss": 0.0066, "step": 73090 }, { "loss_action": 0.007798852864652872, "loss_total": 0.007798852864652872, "step": 73090 }, { "grad_norm": 0.17705987393856049, "learning_rate": 1.8513853202245546e-05, "loss": 0.0059, "step": 73100 }, { "loss_action": 0.008074321784079075, "loss_total": 0.008074321784079075, "step": 73100 }, { "grad_norm": 0.19132880866527557, "learning_rate": 1.850101044295081e-05, "loss": 0.0076, "step": 73110 }, { "loss_action": 0.005080299451947212, "loss_total": 0.005080299451947212, "step": 73110 }, { "grad_norm": 0.15948908030986786, "learning_rate": 1.848817112833825e-05, "loss": 0.0063, "step": 73120 }, { "loss_action": 0.005931576248258352, "loss_total": 0.005931576248258352, "step": 73120 }, { "grad_norm": 0.13437040150165558, "learning_rate": 1.8475335259811905e-05, "loss": 0.0068, "step": 73130 }, { "loss_action": 0.005898952484130859, "loss_total": 0.005898952484130859, "step": 73130 }, { "grad_norm": 0.21725501120090485, "learning_rate": 1.8462502838775508e-05, "loss": 0.0066, "step": 73140 }, { "loss_action": 0.008319984190165997, "loss_total": 0.008319984190165997, "step": 73140 }, { "grad_norm": 0.1529514044523239, "learning_rate": 1.8449673866632378e-05, "loss": 0.0064, "step": 73150 }, { "loss_action": 0.006006884388625622, "loss_total": 0.006006884388625622, "step": 73150 }, { "grad_norm": 0.1791299432516098, "learning_rate": 1.8436848344785473e-05, "loss": 0.0068, "step": 73160 }, { "loss_action": 0.008083470165729523, "loss_total": 0.008083470165729523, "step": 73160 }, { "grad_norm": 0.17094337940216064, "learning_rate": 1.8424026274637378e-05, "loss": 0.0059, "step": 73170 }, { "loss_action": 0.005492668133229017, "loss_total": 0.005492668133229017, "step": 73170 }, { "grad_norm": 0.1419486254453659, "learning_rate": 1.8411207657590312e-05, "loss": 0.0069, "step": 73180 }, { "loss_action": 0.007068592123687267, "loss_total": 0.007068592123687267, "step": 73180 }, { "grad_norm": 0.1681762933731079, "learning_rate": 1.839839249504607e-05, "loss": 0.0067, "step": 73190 }, { "loss_action": 0.005030903499573469, "loss_total": 0.005030903499573469, "step": 73190 }, { "grad_norm": 0.18621322512626648, "learning_rate": 1.8385580788406108e-05, "loss": 0.0063, "step": 73200 }, { "loss_action": 0.0039681922644376755, "loss_total": 0.0039681922644376755, "step": 73200 }, { "grad_norm": 0.20831423997879028, "learning_rate": 1.837277253907152e-05, "loss": 0.0069, "step": 73210 }, { "loss_action": 0.0061975750140845776, "loss_total": 0.0061975750140845776, "step": 73210 }, { "grad_norm": 0.18101359903812408, "learning_rate": 1.8359967748442957e-05, "loss": 0.0077, "step": 73220 }, { "loss_action": 0.00807354599237442, "loss_total": 0.00807354599237442, "step": 73220 }, { "grad_norm": 0.21773599088191986, "learning_rate": 1.8347166417920774e-05, "loss": 0.0075, "step": 73230 }, { "loss_action": 0.004928758833557367, "loss_total": 0.004928758833557367, "step": 73230 }, { "grad_norm": 0.15449929237365723, "learning_rate": 1.833436854890484e-05, "loss": 0.0056, "step": 73240 }, { "loss_action": 0.004838136490434408, "loss_total": 0.004838136490434408, "step": 73240 }, { "grad_norm": 0.18125225603580475, "learning_rate": 1.8321574142794796e-05, "loss": 0.0052, "step": 73250 }, { "loss_action": 0.005450856871902943, "loss_total": 0.005450856871902943, "step": 73250 }, { "grad_norm": 0.17135100066661835, "learning_rate": 1.8308783200989748e-05, "loss": 0.0054, "step": 73260 }, { "loss_action": 0.005229926202446222, "loss_total": 0.005229926202446222, "step": 73260 }, { "grad_norm": 0.22389774024486542, "learning_rate": 1.829599572488855e-05, "loss": 0.0077, "step": 73270 }, { "loss_action": 0.005204949993640184, "loss_total": 0.005204949993640184, "step": 73270 }, { "grad_norm": 0.19051937758922577, "learning_rate": 1.828321171588957e-05, "loss": 0.0065, "step": 73280 }, { "loss_action": 0.008593117818236351, "loss_total": 0.008593117818236351, "step": 73280 }, { "grad_norm": 0.18850818276405334, "learning_rate": 1.827043117539089e-05, "loss": 0.0065, "step": 73290 }, { "loss_action": 0.007647886406630278, "loss_total": 0.007647886406630278, "step": 73290 }, { "grad_norm": 0.15580956637859344, "learning_rate": 1.8257654104790116e-05, "loss": 0.0071, "step": 73300 }, { "loss_action": 0.0068775056861341, "loss_total": 0.0068775056861341, "step": 73300 }, { "grad_norm": 0.19971805810928345, "learning_rate": 1.82448805054846e-05, "loss": 0.0063, "step": 73310 }, { "loss_action": 0.008968359790742397, "loss_total": 0.008968359790742397, "step": 73310 }, { "grad_norm": 0.17790524661540985, "learning_rate": 1.823211037887119e-05, "loss": 0.0078, "step": 73320 }, { "loss_action": 0.006665010005235672, "loss_total": 0.006665010005235672, "step": 73320 }, { "grad_norm": 0.14321443438529968, "learning_rate": 1.821934372634645e-05, "loss": 0.0068, "step": 73330 }, { "loss_action": 0.006894346326589584, "loss_total": 0.006894346326589584, "step": 73330 }, { "grad_norm": 0.2004057914018631, "learning_rate": 1.8206580549306472e-05, "loss": 0.0067, "step": 73340 }, { "loss_action": 0.009838108904659748, "loss_total": 0.009838108904659748, "step": 73340 }, { "grad_norm": 0.13176539540290833, "learning_rate": 1.819382084914707e-05, "loss": 0.0065, "step": 73350 }, { "loss_action": 0.006587190553545952, "loss_total": 0.006587190553545952, "step": 73350 }, { "grad_norm": 0.17477957904338837, "learning_rate": 1.8181064627263577e-05, "loss": 0.0068, "step": 73360 }, { "loss_action": 0.005310770124197006, "loss_total": 0.005310770124197006, "step": 73360 }, { "grad_norm": 0.13118626177310944, "learning_rate": 1.8168311885051022e-05, "loss": 0.0062, "step": 73370 }, { "loss_action": 0.005736967548727989, "loss_total": 0.005736967548727989, "step": 73370 }, { "grad_norm": 0.21349474787712097, "learning_rate": 1.815556262390402e-05, "loss": 0.0069, "step": 73380 }, { "loss_action": 0.0059817079454660416, "loss_total": 0.0059817079454660416, "step": 73380 }, { "grad_norm": 0.15388791263103485, "learning_rate": 1.8142816845216826e-05, "loss": 0.0079, "step": 73390 }, { "loss_action": 0.004425601102411747, "loss_total": 0.004425601102411747, "step": 73390 }, { "grad_norm": 0.1743585765361786, "learning_rate": 1.8130074550383276e-05, "loss": 0.0079, "step": 73400 }, { "loss_action": 0.005900482181459665, "loss_total": 0.005900482181459665, "step": 73400 }, { "grad_norm": 0.1809115707874298, "learning_rate": 1.8117335740796848e-05, "loss": 0.0068, "step": 73410 }, { "loss_action": 0.0064168148674070835, "loss_total": 0.0064168148674070835, "step": 73410 }, { "grad_norm": 0.13964252173900604, "learning_rate": 1.810460041785067e-05, "loss": 0.0065, "step": 73420 }, { "loss_action": 0.006707795429974794, "loss_total": 0.006707795429974794, "step": 73420 }, { "grad_norm": 0.1649511158466339, "learning_rate": 1.809186858293742e-05, "loss": 0.0061, "step": 73430 }, { "loss_action": 0.006454421207308769, "loss_total": 0.006454421207308769, "step": 73430 }, { "grad_norm": 0.17747682332992554, "learning_rate": 1.8079140237449448e-05, "loss": 0.0066, "step": 73440 }, { "loss_action": 0.006949123460799456, "loss_total": 0.006949123460799456, "step": 73440 }, { "grad_norm": 0.16433748602867126, "learning_rate": 1.8066415382778707e-05, "loss": 0.0057, "step": 73450 }, { "loss_action": 0.006942985579371452, "loss_total": 0.006942985579371452, "step": 73450 }, { "grad_norm": 0.13636451959609985, "learning_rate": 1.8053694020316786e-05, "loss": 0.0057, "step": 73460 }, { "loss_action": 0.006852664519101381, "loss_total": 0.006852664519101381, "step": 73460 }, { "grad_norm": 0.17827041447162628, "learning_rate": 1.8040976151454837e-05, "loss": 0.0069, "step": 73470 }, { "loss_action": 0.005307676736265421, "loss_total": 0.005307676736265421, "step": 73470 }, { "grad_norm": 0.14046013355255127, "learning_rate": 1.8028261777583704e-05, "loss": 0.0062, "step": 73480 }, { "loss_action": 0.004731143359094858, "loss_total": 0.004731143359094858, "step": 73480 }, { "grad_norm": 0.15028826892375946, "learning_rate": 1.8015550900093758e-05, "loss": 0.0054, "step": 73490 }, { "loss_action": 0.008105399087071419, "loss_total": 0.008105399087071419, "step": 73490 }, { "grad_norm": 0.1792551875114441, "learning_rate": 1.800284352037512e-05, "loss": 0.0062, "step": 73500 }, { "loss_action": 0.00503507349640131, "loss_total": 0.00503507349640131, "step": 73500 }, { "grad_norm": 0.19356533885002136, "learning_rate": 1.799013963981738e-05, "loss": 0.006, "step": 73510 }, { "loss_action": 0.006271090358495712, "loss_total": 0.006271090358495712, "step": 73510 }, { "grad_norm": 0.20522312819957733, "learning_rate": 1.797743925980987e-05, "loss": 0.0074, "step": 73520 }, { "loss_action": 0.004859717562794685, "loss_total": 0.004859717562794685, "step": 73520 }, { "grad_norm": 0.14269748330116272, "learning_rate": 1.7964742381741435e-05, "loss": 0.0064, "step": 73530 }, { "loss_action": 0.004424700979143381, "loss_total": 0.004424700979143381, "step": 73530 }, { "grad_norm": 0.13712173700332642, "learning_rate": 1.7952049007000627e-05, "loss": 0.0053, "step": 73540 }, { "loss_action": 0.004104142542928457, "loss_total": 0.004104142542928457, "step": 73540 }, { "grad_norm": 0.11554711312055588, "learning_rate": 1.7939359136975535e-05, "loss": 0.0063, "step": 73550 }, { "loss_action": 0.007266660686582327, "loss_total": 0.007266660686582327, "step": 73550 }, { "grad_norm": 0.16319367289543152, "learning_rate": 1.7926672773053932e-05, "loss": 0.0063, "step": 73560 }, { "loss_action": 0.0062193660996854305, "loss_total": 0.0062193660996854305, "step": 73560 }, { "grad_norm": 0.15039853751659393, "learning_rate": 1.791398991662317e-05, "loss": 0.0066, "step": 73570 }, { "loss_action": 0.004773980937898159, "loss_total": 0.004773980937898159, "step": 73570 }, { "grad_norm": 0.15709704160690308, "learning_rate": 1.7901310569070244e-05, "loss": 0.0065, "step": 73580 }, { "loss_action": 0.004830646328628063, "loss_total": 0.004830646328628063, "step": 73580 }, { "grad_norm": 0.15365076065063477, "learning_rate": 1.7888634731781724e-05, "loss": 0.0059, "step": 73590 }, { "loss_action": 0.003953707404434681, "loss_total": 0.003953707404434681, "step": 73590 }, { "grad_norm": 0.15953728556632996, "learning_rate": 1.7875962406143844e-05, "loss": 0.0057, "step": 73600 }, { "loss_action": 0.006572070997208357, "loss_total": 0.006572070997208357, "step": 73600 }, { "grad_norm": 0.1796007752418518, "learning_rate": 1.7863293593542403e-05, "loss": 0.0067, "step": 73610 }, { "loss_action": 0.005590380169451237, "loss_total": 0.005590380169451237, "step": 73610 }, { "grad_norm": 0.17992626130580902, "learning_rate": 1.7850628295362853e-05, "loss": 0.0064, "step": 73620 }, { "loss_action": 0.00714851962402463, "loss_total": 0.00714851962402463, "step": 73620 }, { "grad_norm": 0.13657891750335693, "learning_rate": 1.7837966512990263e-05, "loss": 0.0058, "step": 73630 }, { "loss_action": 0.005638831295073032, "loss_total": 0.005638831295073032, "step": 73630 }, { "grad_norm": 0.15107779204845428, "learning_rate": 1.782530824780931e-05, "loss": 0.0068, "step": 73640 }, { "loss_action": 0.00920894742012024, "loss_total": 0.00920894742012024, "step": 73640 }, { "grad_norm": 0.17249231040477753, "learning_rate": 1.7812653501204263e-05, "loss": 0.0066, "step": 73650 }, { "loss_action": 0.007010064087808132, "loss_total": 0.007010064087808132, "step": 73650 }, { "grad_norm": 0.19422392547130585, "learning_rate": 1.780000227455903e-05, "loss": 0.0064, "step": 73660 }, { "loss_action": 0.008218691684305668, "loss_total": 0.008218691684305668, "step": 73660 }, { "grad_norm": 0.18157348036766052, "learning_rate": 1.778735456925716e-05, "loss": 0.0075, "step": 73670 }, { "loss_action": 0.0057531255297362804, "loss_total": 0.0057531255297362804, "step": 73670 }, { "grad_norm": 0.17802119255065918, "learning_rate": 1.7774710386681737e-05, "loss": 0.0056, "step": 73680 }, { "loss_action": 0.005762783344835043, "loss_total": 0.005762783344835043, "step": 73680 }, { "grad_norm": 0.18440698087215424, "learning_rate": 1.7762069728215545e-05, "loss": 0.0064, "step": 73690 }, { "loss_action": 0.007182466797530651, "loss_total": 0.007182466797530651, "step": 73690 }, { "grad_norm": 0.15600547194480896, "learning_rate": 1.7749432595240932e-05, "loss": 0.0064, "step": 73700 }, { "loss_action": 0.0036875575315207243, "loss_total": 0.0036875575315207243, "step": 73700 }, { "grad_norm": 0.13374502956867218, "learning_rate": 1.773679898913991e-05, "loss": 0.0059, "step": 73710 }, { "loss_action": 0.006488759070634842, "loss_total": 0.006488759070634842, "step": 73710 }, { "grad_norm": 0.15314190089702606, "learning_rate": 1.7724168911294015e-05, "loss": 0.0059, "step": 73720 }, { "loss_action": 0.004136957228183746, "loss_total": 0.004136957228183746, "step": 73720 }, { "grad_norm": 0.15860968828201294, "learning_rate": 1.7711542363084504e-05, "loss": 0.0067, "step": 73730 }, { "loss_action": 0.004488782491534948, "loss_total": 0.004488782491534948, "step": 73730 }, { "grad_norm": 0.2836308479309082, "learning_rate": 1.7698919345892158e-05, "loss": 0.0065, "step": 73740 }, { "loss_action": 0.006374023389071226, "loss_total": 0.006374023389071226, "step": 73740 }, { "grad_norm": 0.1714240163564682, "learning_rate": 1.768629986109743e-05, "loss": 0.0065, "step": 73750 }, { "loss_action": 0.00505963945761323, "loss_total": 0.00505963945761323, "step": 73750 }, { "grad_norm": 0.1555999368429184, "learning_rate": 1.7673683910080357e-05, "loss": 0.0051, "step": 73760 }, { "loss_action": 0.004000220913439989, "loss_total": 0.004000220913439989, "step": 73760 }, { "grad_norm": 0.16440361738204956, "learning_rate": 1.7661071494220638e-05, "loss": 0.0052, "step": 73770 }, { "loss_action": 0.004390730056911707, "loss_total": 0.004390730056911707, "step": 73770 }, { "grad_norm": 0.1933213472366333, "learning_rate": 1.7648462614897498e-05, "loss": 0.0066, "step": 73780 }, { "loss_action": 0.004402459599077702, "loss_total": 0.004402459599077702, "step": 73780 }, { "grad_norm": 0.15807467699050903, "learning_rate": 1.7635857273489863e-05, "loss": 0.0059, "step": 73790 }, { "loss_action": 0.006673053372651339, "loss_total": 0.006673053372651339, "step": 73790 }, { "grad_norm": 0.14281493425369263, "learning_rate": 1.7623255471376198e-05, "loss": 0.0069, "step": 73800 }, { "loss_action": 0.005101088900119066, "loss_total": 0.005101088900119066, "step": 73800 }, { "grad_norm": 0.16335277259349823, "learning_rate": 1.7610657209934646e-05, "loss": 0.0053, "step": 73810 }, { "loss_action": 0.004016068298369646, "loss_total": 0.004016068298369646, "step": 73810 }, { "grad_norm": 0.1430625170469284, "learning_rate": 1.7598062490542915e-05, "loss": 0.0062, "step": 73820 }, { "loss_action": 0.005365101620554924, "loss_total": 0.005365101620554924, "step": 73820 }, { "grad_norm": 0.16375598311424255, "learning_rate": 1.7585471314578377e-05, "loss": 0.0062, "step": 73830 }, { "loss_action": 0.00823606550693512, "loss_total": 0.00823606550693512, "step": 73830 }, { "grad_norm": 0.14272670447826385, "learning_rate": 1.7572883683417945e-05, "loss": 0.006, "step": 73840 }, { "loss_action": 0.007267995737493038, "loss_total": 0.007267995737493038, "step": 73840 }, { "grad_norm": 0.1965859979391098, "learning_rate": 1.7560299598438212e-05, "loss": 0.0071, "step": 73850 }, { "loss_action": 0.006505270954221487, "loss_total": 0.006505270954221487, "step": 73850 }, { "grad_norm": 0.16566257178783417, "learning_rate": 1.7547719061015334e-05, "loss": 0.0067, "step": 73860 }, { "loss_action": 0.005642840173095465, "loss_total": 0.005642840173095465, "step": 73860 }, { "grad_norm": 0.14180661737918854, "learning_rate": 1.75351420725251e-05, "loss": 0.0061, "step": 73870 }, { "loss_action": 0.005551546812057495, "loss_total": 0.005551546812057495, "step": 73870 }, { "grad_norm": 0.13050495088100433, "learning_rate": 1.7522568634342923e-05, "loss": 0.0071, "step": 73880 }, { "loss_action": 0.010369461961090565, "loss_total": 0.010369461961090565, "step": 73880 }, { "grad_norm": 0.12394960224628448, "learning_rate": 1.7509998747843825e-05, "loss": 0.0064, "step": 73890 }, { "loss_action": 0.005542776081711054, "loss_total": 0.005542776081711054, "step": 73890 }, { "grad_norm": 0.12698963284492493, "learning_rate": 1.7497432414402403e-05, "loss": 0.0057, "step": 73900 }, { "loss_action": 0.004523694980889559, "loss_total": 0.004523694980889559, "step": 73900 }, { "grad_norm": 0.13441318273544312, "learning_rate": 1.7484869635392903e-05, "loss": 0.0051, "step": 73910 }, { "loss_action": 0.007754741236567497, "loss_total": 0.007754741236567497, "step": 73910 }, { "grad_norm": 0.1482032984495163, "learning_rate": 1.747231041218919e-05, "loss": 0.0065, "step": 73920 }, { "loss_action": 0.006414405070245266, "loss_total": 0.006414405070245266, "step": 73920 }, { "grad_norm": 0.1011262759566307, "learning_rate": 1.7459754746164692e-05, "loss": 0.0056, "step": 73930 }, { "loss_action": 0.006150240544229746, "loss_total": 0.006150240544229746, "step": 73930 }, { "grad_norm": 0.16672396659851074, "learning_rate": 1.744720263869249e-05, "loss": 0.0061, "step": 73940 }, { "loss_action": 0.0059137847274541855, "loss_total": 0.0059137847274541855, "step": 73940 }, { "grad_norm": 0.15968865156173706, "learning_rate": 1.7434654091145263e-05, "loss": 0.0067, "step": 73950 }, { "loss_action": 0.006048908457159996, "loss_total": 0.006048908457159996, "step": 73950 }, { "grad_norm": 0.17297083139419556, "learning_rate": 1.742210910489532e-05, "loss": 0.0058, "step": 73960 }, { "loss_action": 0.0052717216312885284, "loss_total": 0.0052717216312885284, "step": 73960 }, { "grad_norm": 0.1651473492383957, "learning_rate": 1.7409567681314532e-05, "loss": 0.0058, "step": 73970 }, { "loss_action": 0.007230732124298811, "loss_total": 0.007230732124298811, "step": 73970 }, { "grad_norm": 0.16267138719558716, "learning_rate": 1.7397029821774434e-05, "loss": 0.0062, "step": 73980 }, { "loss_action": 0.004524067044258118, "loss_total": 0.004524067044258118, "step": 73980 }, { "grad_norm": 0.14673906564712524, "learning_rate": 1.7384495527646126e-05, "loss": 0.0062, "step": 73990 }, { "loss_action": 0.006358661223202944, "loss_total": 0.006358661223202944, "step": 73990 }, { "grad_norm": 0.16563989222049713, "learning_rate": 1.737196480030035e-05, "loss": 0.0056, "step": 74000 }, { "loss_action": 0.006452040746808052, "loss_total": 0.006452040746808052, "step": 74000 }, { "grad_norm": 0.16665197908878326, "learning_rate": 1.7359437641107447e-05, "loss": 0.0061, "step": 74010 }, { "loss_action": 0.006050216034054756, "loss_total": 0.006050216034054756, "step": 74010 }, { "grad_norm": 0.16390575468540192, "learning_rate": 1.7346914051437387e-05, "loss": 0.0061, "step": 74020 }, { "loss_action": 0.004039269406348467, "loss_total": 0.004039269406348467, "step": 74020 }, { "grad_norm": 0.21445244550704956, "learning_rate": 1.733439403265969e-05, "loss": 0.0072, "step": 74030 }, { "loss_action": 0.0047455220483243465, "loss_total": 0.0047455220483243465, "step": 74030 }, { "grad_norm": 0.1815589964389801, "learning_rate": 1.732187758614357e-05, "loss": 0.0059, "step": 74040 }, { "loss_action": 0.0068861995823681355, "loss_total": 0.0068861995823681355, "step": 74040 }, { "grad_norm": 0.1656610518693924, "learning_rate": 1.730936471325777e-05, "loss": 0.0074, "step": 74050 }, { "loss_action": 0.0030602901242673397, "loss_total": 0.0030602901242673397, "step": 74050 }, { "grad_norm": 0.19229304790496826, "learning_rate": 1.7296855415370718e-05, "loss": 0.0058, "step": 74060 }, { "loss_action": 0.0061001828871667385, "loss_total": 0.0061001828871667385, "step": 74060 }, { "grad_norm": 0.1777242124080658, "learning_rate": 1.728434969385035e-05, "loss": 0.0065, "step": 74070 }, { "loss_action": 0.007818951271474361, "loss_total": 0.007818951271474361, "step": 74070 }, { "grad_norm": 0.1596679836511612, "learning_rate": 1.7271847550064346e-05, "loss": 0.0058, "step": 74080 }, { "loss_action": 0.004744235891848803, "loss_total": 0.004744235891848803, "step": 74080 }, { "grad_norm": 0.15776237845420837, "learning_rate": 1.725934898537987e-05, "loss": 0.0057, "step": 74090 }, { "loss_action": 0.006120316218584776, "loss_total": 0.006120316218584776, "step": 74090 }, { "grad_norm": 0.08939105272293091, "learning_rate": 1.7246854001163783e-05, "loss": 0.0064, "step": 74100 }, { "loss_action": 0.006615241523832083, "loss_total": 0.006615241523832083, "step": 74100 }, { "grad_norm": 0.1569090038537979, "learning_rate": 1.7234362598782476e-05, "loss": 0.0064, "step": 74110 }, { "loss_action": 0.008861071430146694, "loss_total": 0.008861071430146694, "step": 74110 }, { "grad_norm": 0.22761288285255432, "learning_rate": 1.722187477960202e-05, "loss": 0.0064, "step": 74120 }, { "loss_action": 0.005770016927272081, "loss_total": 0.005770016927272081, "step": 74120 }, { "grad_norm": 0.2619350254535675, "learning_rate": 1.7209390544988057e-05, "loss": 0.0067, "step": 74130 }, { "loss_action": 0.0072612217627465725, "loss_total": 0.0072612217627465725, "step": 74130 }, { "grad_norm": 0.14486514031887054, "learning_rate": 1.7196909896305856e-05, "loss": 0.0063, "step": 74140 }, { "loss_action": 0.006710107903927565, "loss_total": 0.006710107903927565, "step": 74140 }, { "grad_norm": 0.1413331776857376, "learning_rate": 1.718443283492026e-05, "loss": 0.0064, "step": 74150 }, { "loss_action": 0.004107790067791939, "loss_total": 0.004107790067791939, "step": 74150 }, { "grad_norm": 0.13917215168476105, "learning_rate": 1.7171959362195746e-05, "loss": 0.0058, "step": 74160 }, { "loss_action": 0.005921248346567154, "loss_total": 0.005921248346567154, "step": 74160 }, { "grad_norm": 0.13185656070709229, "learning_rate": 1.715948947949642e-05, "loss": 0.0061, "step": 74170 }, { "loss_action": 0.0046336716040968895, "loss_total": 0.0046336716040968895, "step": 74170 }, { "grad_norm": 0.20130956172943115, "learning_rate": 1.714702318818593e-05, "loss": 0.0064, "step": 74180 }, { "loss_action": 0.010389511473476887, "loss_total": 0.010389511473476887, "step": 74180 }, { "grad_norm": 0.18688304722309113, "learning_rate": 1.7134560489627592e-05, "loss": 0.0074, "step": 74190 }, { "loss_action": 0.0051766070537269115, "loss_total": 0.0051766070537269115, "step": 74190 }, { "grad_norm": 0.18679045140743256, "learning_rate": 1.712210138518431e-05, "loss": 0.0061, "step": 74200 }, { "loss_action": 0.005003861617296934, "loss_total": 0.005003861617296934, "step": 74200 }, { "grad_norm": 0.17985200881958008, "learning_rate": 1.71096458762186e-05, "loss": 0.0052, "step": 74210 }, { "loss_action": 0.00452521163970232, "loss_total": 0.00452521163970232, "step": 74210 }, { "grad_norm": 0.11741334944963455, "learning_rate": 1.7097193964092552e-05, "loss": 0.0057, "step": 74220 }, { "loss_action": 0.004553344566375017, "loss_total": 0.004553344566375017, "step": 74220 }, { "grad_norm": 0.14846307039260864, "learning_rate": 1.708474565016792e-05, "loss": 0.0058, "step": 74230 }, { "loss_action": 0.005773783195763826, "loss_total": 0.005773783195763826, "step": 74230 }, { "grad_norm": 0.13091067969799042, "learning_rate": 1.7072300935806e-05, "loss": 0.0066, "step": 74240 }, { "loss_action": 0.005136186257004738, "loss_total": 0.005136186257004738, "step": 74240 }, { "grad_norm": 0.1890266388654709, "learning_rate": 1.705985982236776e-05, "loss": 0.0062, "step": 74250 }, { "loss_action": 0.013417716138064861, "loss_total": 0.013417716138064861, "step": 74250 }, { "grad_norm": 0.14791877567768097, "learning_rate": 1.7047422311213697e-05, "loss": 0.0069, "step": 74260 }, { "loss_action": 0.008157466538250446, "loss_total": 0.008157466538250446, "step": 74260 }, { "grad_norm": 0.20523755252361298, "learning_rate": 1.703498840370401e-05, "loss": 0.006, "step": 74270 }, { "loss_action": 0.006334211211651564, "loss_total": 0.006334211211651564, "step": 74270 }, { "grad_norm": 0.1665702760219574, "learning_rate": 1.702255810119842e-05, "loss": 0.0063, "step": 74280 }, { "loss_action": 0.011621193028986454, "loss_total": 0.011621193028986454, "step": 74280 }, { "grad_norm": 0.1983582079410553, "learning_rate": 1.7010131405056305e-05, "loss": 0.0076, "step": 74290 }, { "loss_action": 0.004653220996260643, "loss_total": 0.004653220996260643, "step": 74290 }, { "grad_norm": 0.18821857869625092, "learning_rate": 1.6997708316636613e-05, "loss": 0.0071, "step": 74300 }, { "loss_action": 0.0052374908700585365, "loss_total": 0.0052374908700585365, "step": 74300 }, { "grad_norm": 0.19969233870506287, "learning_rate": 1.6985288837297932e-05, "loss": 0.0063, "step": 74310 }, { "loss_action": 0.008011053316295147, "loss_total": 0.008011053316295147, "step": 74310 }, { "grad_norm": 0.19659964740276337, "learning_rate": 1.6972872968398394e-05, "loss": 0.0068, "step": 74320 }, { "loss_action": 0.005609833635389805, "loss_total": 0.005609833635389805, "step": 74320 }, { "grad_norm": 0.14142084121704102, "learning_rate": 1.6960460711295845e-05, "loss": 0.0073, "step": 74330 }, { "loss_action": 0.004758796188980341, "loss_total": 0.004758796188980341, "step": 74330 }, { "grad_norm": 0.1919616311788559, "learning_rate": 1.6948052067347623e-05, "loss": 0.0064, "step": 74340 }, { "loss_action": 0.005266457796096802, "loss_total": 0.005266457796096802, "step": 74340 }, { "grad_norm": 0.22212164103984833, "learning_rate": 1.693564703791075e-05, "loss": 0.0068, "step": 74350 }, { "loss_action": 0.005316462833434343, "loss_total": 0.005316462833434343, "step": 74350 }, { "grad_norm": 0.16994990408420563, "learning_rate": 1.6923245624341793e-05, "loss": 0.0063, "step": 74360 }, { "loss_action": 0.00605796230956912, "loss_total": 0.00605796230956912, "step": 74360 }, { "grad_norm": 0.1986578106880188, "learning_rate": 1.6910847827996962e-05, "loss": 0.0066, "step": 74370 }, { "loss_action": 0.0059716892428696156, "loss_total": 0.0059716892428696156, "step": 74370 }, { "grad_norm": 0.16234032809734344, "learning_rate": 1.689845365023206e-05, "loss": 0.0059, "step": 74380 }, { "loss_action": 0.005231346469372511, "loss_total": 0.005231346469372511, "step": 74380 }, { "grad_norm": 0.28973057866096497, "learning_rate": 1.6886063092402505e-05, "loss": 0.006, "step": 74390 }, { "loss_action": 0.008138359524309635, "loss_total": 0.008138359524309635, "step": 74390 }, { "grad_norm": 0.19446824491024017, "learning_rate": 1.6873676155863317e-05, "loss": 0.0075, "step": 74400 }, { "loss_action": 0.009189463220536709, "loss_total": 0.009189463220536709, "step": 74400 }, { "grad_norm": 0.2237558811903, "learning_rate": 1.6861292841969085e-05, "loss": 0.0065, "step": 74410 }, { "loss_action": 0.006140542216598988, "loss_total": 0.006140542216598988, "step": 74410 }, { "grad_norm": 0.12459315359592438, "learning_rate": 1.684891315207406e-05, "loss": 0.006, "step": 74420 }, { "loss_action": 0.0062011657282710075, "loss_total": 0.0062011657282710075, "step": 74420 }, { "grad_norm": 0.162443146109581, "learning_rate": 1.6836537087532034e-05, "loss": 0.0061, "step": 74430 }, { "loss_action": 0.008035804145038128, "loss_total": 0.008035804145038128, "step": 74430 }, { "grad_norm": 0.2108697146177292, "learning_rate": 1.6824164649696465e-05, "loss": 0.0066, "step": 74440 }, { "loss_action": 0.005026543978601694, "loss_total": 0.005026543978601694, "step": 74440 }, { "grad_norm": 0.1731988489627838, "learning_rate": 1.681179583992034e-05, "loss": 0.0067, "step": 74450 }, { "loss_action": 0.008485033176839352, "loss_total": 0.008485033176839352, "step": 74450 }, { "grad_norm": 0.18715840578079224, "learning_rate": 1.679943065955636e-05, "loss": 0.007, "step": 74460 }, { "loss_action": 0.007115222048014402, "loss_total": 0.007115222048014402, "step": 74460 }, { "grad_norm": 0.21863161027431488, "learning_rate": 1.678706910995671e-05, "loss": 0.0074, "step": 74470 }, { "loss_action": 0.00425938842818141, "loss_total": 0.00425938842818141, "step": 74470 }, { "grad_norm": 0.18789531290531158, "learning_rate": 1.6774711192473262e-05, "loss": 0.0064, "step": 74480 }, { "loss_action": 0.006436789408326149, "loss_total": 0.006436789408326149, "step": 74480 }, { "grad_norm": 0.19124966859817505, "learning_rate": 1.676235690845743e-05, "loss": 0.0067, "step": 74490 }, { "loss_action": 0.004867530893534422, "loss_total": 0.004867530893534422, "step": 74490 }, { "grad_norm": 0.16536852717399597, "learning_rate": 1.6750006259260285e-05, "loss": 0.007, "step": 74500 }, { "loss_action": 0.007717248983681202, "loss_total": 0.007717248983681202, "step": 74500 }, { "grad_norm": 0.1792084127664566, "learning_rate": 1.673765924623244e-05, "loss": 0.0061, "step": 74510 }, { "loss_action": 0.007004887796938419, "loss_total": 0.007004887796938419, "step": 74510 }, { "grad_norm": 0.14783357083797455, "learning_rate": 1.67253158707242e-05, "loss": 0.0061, "step": 74520 }, { "loss_action": 0.00522583769634366, "loss_total": 0.00522583769634366, "step": 74520 }, { "grad_norm": 0.16254402697086334, "learning_rate": 1.671297613408537e-05, "loss": 0.0069, "step": 74530 }, { "loss_action": 0.0047564031556248665, "loss_total": 0.0047564031556248665, "step": 74530 }, { "grad_norm": 0.11119957268238068, "learning_rate": 1.6700640037665444e-05, "loss": 0.006, "step": 74540 }, { "loss_action": 0.005431656260043383, "loss_total": 0.005431656260043383, "step": 74540 }, { "grad_norm": 0.15256957709789276, "learning_rate": 1.668830758281344e-05, "loss": 0.0067, "step": 74550 }, { "loss_action": 0.010139383375644684, "loss_total": 0.010139383375644684, "step": 74550 }, { "grad_norm": 0.1651466339826584, "learning_rate": 1.6675978770878052e-05, "loss": 0.0069, "step": 74560 }, { "loss_action": 0.006042405962944031, "loss_total": 0.006042405962944031, "step": 74560 }, { "grad_norm": 0.20204156637191772, "learning_rate": 1.6663653603207506e-05, "loss": 0.0066, "step": 74570 }, { "loss_action": 0.011303817853331566, "loss_total": 0.011303817853331566, "step": 74570 }, { "grad_norm": 0.1373647004365921, "learning_rate": 1.6651332081149685e-05, "loss": 0.0066, "step": 74580 }, { "loss_action": 0.004721681121736765, "loss_total": 0.004721681121736765, "step": 74580 }, { "grad_norm": 0.15433987975120544, "learning_rate": 1.6639014206052046e-05, "loss": 0.006, "step": 74590 }, { "loss_action": 0.004733019508421421, "loss_total": 0.004733019508421421, "step": 74590 }, { "grad_norm": 0.14619147777557373, "learning_rate": 1.6626699979261657e-05, "loss": 0.006, "step": 74600 }, { "loss_action": 0.004586547147482634, "loss_total": 0.004586547147482634, "step": 74600 }, { "grad_norm": 0.1358705759048462, "learning_rate": 1.6614389402125197e-05, "loss": 0.0053, "step": 74610 }, { "loss_action": 0.004881704691797495, "loss_total": 0.004881704691797495, "step": 74610 }, { "grad_norm": 0.1607079952955246, "learning_rate": 1.66020824759889e-05, "loss": 0.007, "step": 74620 }, { "loss_action": 0.00610016193240881, "loss_total": 0.00610016193240881, "step": 74620 }, { "grad_norm": 0.1506018489599228, "learning_rate": 1.6589779202198675e-05, "loss": 0.0059, "step": 74630 }, { "loss_action": 0.007808398921042681, "loss_total": 0.007808398921042681, "step": 74630 }, { "grad_norm": 0.1610053926706314, "learning_rate": 1.6577479582099924e-05, "loss": 0.0058, "step": 74640 }, { "loss_action": 0.011187892407178879, "loss_total": 0.011187892407178879, "step": 74640 }, { "grad_norm": 0.22637902200222015, "learning_rate": 1.6565183617037788e-05, "loss": 0.0072, "step": 74650 }, { "loss_action": 0.005807127337902784, "loss_total": 0.005807127337902784, "step": 74650 }, { "grad_norm": 0.13352036476135254, "learning_rate": 1.6552891308356894e-05, "loss": 0.0066, "step": 74660 }, { "loss_action": 0.0060305604711174965, "loss_total": 0.0060305604711174965, "step": 74660 }, { "grad_norm": 0.16093657910823822, "learning_rate": 1.6540602657401526e-05, "loss": 0.0068, "step": 74670 }, { "loss_action": 0.005863646510988474, "loss_total": 0.005863646510988474, "step": 74670 }, { "grad_norm": 0.19606435298919678, "learning_rate": 1.6528317665515537e-05, "loss": 0.0062, "step": 74680 }, { "loss_action": 0.004819950088858604, "loss_total": 0.004819950088858604, "step": 74680 }, { "grad_norm": 0.17955783009529114, "learning_rate": 1.6516036334042416e-05, "loss": 0.0056, "step": 74690 }, { "loss_action": 0.005876394920051098, "loss_total": 0.005876394920051098, "step": 74690 }, { "grad_norm": 0.17560093104839325, "learning_rate": 1.650375866432519e-05, "loss": 0.0069, "step": 74700 }, { "loss_action": 0.004347181413322687, "loss_total": 0.004347181413322687, "step": 74700 }, { "grad_norm": 0.18214450776576996, "learning_rate": 1.649148465770659e-05, "loss": 0.0064, "step": 74710 }, { "loss_action": 0.005521649494767189, "loss_total": 0.005521649494767189, "step": 74710 }, { "grad_norm": 0.14823804795742035, "learning_rate": 1.647921431552883e-05, "loss": 0.0052, "step": 74720 }, { "loss_action": 0.0037647332064807415, "loss_total": 0.0037647332064807415, "step": 74720 }, { "grad_norm": 0.13637487590312958, "learning_rate": 1.646694763913381e-05, "loss": 0.0057, "step": 74730 }, { "loss_action": 0.007484877482056618, "loss_total": 0.007484877482056618, "step": 74730 }, { "grad_norm": 0.1513959914445877, "learning_rate": 1.6454684629862966e-05, "loss": 0.0061, "step": 74740 }, { "loss_action": 0.004935515113174915, "loss_total": 0.004935515113174915, "step": 74740 }, { "grad_norm": 0.17957273125648499, "learning_rate": 1.6442425289057388e-05, "loss": 0.0057, "step": 74750 }, { "loss_action": 0.006778267677873373, "loss_total": 0.006778267677873373, "step": 74750 }, { "grad_norm": 0.13866208493709564, "learning_rate": 1.6430169618057718e-05, "loss": 0.0055, "step": 74760 }, { "loss_action": 0.004688804503530264, "loss_total": 0.004688804503530264, "step": 74760 }, { "grad_norm": 0.180710107088089, "learning_rate": 1.641791761820422e-05, "loss": 0.0063, "step": 74770 }, { "loss_action": 0.0049409461207687855, "loss_total": 0.0049409461207687855, "step": 74770 }, { "grad_norm": 0.15465421974658966, "learning_rate": 1.640566929083676e-05, "loss": 0.0051, "step": 74780 }, { "loss_action": 0.0056592305190861225, "loss_total": 0.0056592305190861225, "step": 74780 }, { "grad_norm": 0.15190386772155762, "learning_rate": 1.6393424637294823e-05, "loss": 0.0058, "step": 74790 }, { "loss_action": 0.005984991788864136, "loss_total": 0.005984991788864136, "step": 74790 }, { "grad_norm": 0.180064857006073, "learning_rate": 1.638118365891742e-05, "loss": 0.0068, "step": 74800 }, { "loss_action": 0.009936559945344925, "loss_total": 0.009936559945344925, "step": 74800 }, { "grad_norm": 0.21887293457984924, "learning_rate": 1.636894635704323e-05, "loss": 0.0076, "step": 74810 }, { "loss_action": 0.006161880679428577, "loss_total": 0.006161880679428577, "step": 74810 }, { "grad_norm": 0.23932747542858124, "learning_rate": 1.6356712733010517e-05, "loss": 0.0071, "step": 74820 }, { "loss_action": 0.004697571042925119, "loss_total": 0.004697571042925119, "step": 74820 }, { "grad_norm": 0.1523130089044571, "learning_rate": 1.6344482788157096e-05, "loss": 0.0057, "step": 74830 }, { "loss_action": 0.005708116572350264, "loss_total": 0.005708116572350264, "step": 74830 }, { "grad_norm": 0.1556694358587265, "learning_rate": 1.6332256523820444e-05, "loss": 0.007, "step": 74840 }, { "loss_action": 0.013703001663088799, "loss_total": 0.013703001663088799, "step": 74840 }, { "grad_norm": 0.19557660818099976, "learning_rate": 1.6320033941337597e-05, "loss": 0.0072, "step": 74850 }, { "loss_action": 0.01021630223840475, "loss_total": 0.01021630223840475, "step": 74850 }, { "grad_norm": 0.13848137855529785, "learning_rate": 1.6307815042045216e-05, "loss": 0.006, "step": 74860 }, { "loss_action": 0.005416714586317539, "loss_total": 0.005416714586317539, "step": 74860 }, { "grad_norm": 0.1633567363023758, "learning_rate": 1.6295599827279513e-05, "loss": 0.0057, "step": 74870 }, { "loss_action": 0.004759875126183033, "loss_total": 0.004759875126183033, "step": 74870 }, { "grad_norm": 0.1862124353647232, "learning_rate": 1.6283388298376356e-05, "loss": 0.0064, "step": 74880 }, { "loss_action": 0.008670371025800705, "loss_total": 0.008670371025800705, "step": 74880 }, { "grad_norm": 0.14447762072086334, "learning_rate": 1.6271180456671125e-05, "loss": 0.0067, "step": 74890 }, { "loss_action": 0.00465434230864048, "loss_total": 0.00465434230864048, "step": 74890 }, { "grad_norm": 0.14606580138206482, "learning_rate": 1.625897630349893e-05, "loss": 0.0054, "step": 74900 }, { "loss_action": 0.006330821663141251, "loss_total": 0.006330821663141251, "step": 74900 }, { "grad_norm": 0.21171852946281433, "learning_rate": 1.6246775840194335e-05, "loss": 0.0063, "step": 74910 }, { "loss_action": 0.004862491507083178, "loss_total": 0.004862491507083178, "step": 74910 }, { "grad_norm": 0.12674756348133087, "learning_rate": 1.6234579068091604e-05, "loss": 0.0068, "step": 74920 }, { "loss_action": 0.005182221066206694, "loss_total": 0.005182221066206694, "step": 74920 }, { "grad_norm": 0.17968472838401794, "learning_rate": 1.6222385988524524e-05, "loss": 0.0064, "step": 74930 }, { "loss_action": 0.006273300386965275, "loss_total": 0.006273300386965275, "step": 74930 }, { "grad_norm": 0.22913743555545807, "learning_rate": 1.6210196602826544e-05, "loss": 0.007, "step": 74940 }, { "loss_action": 0.00925750844180584, "loss_total": 0.00925750844180584, "step": 74940 }, { "grad_norm": 0.19691617786884308, "learning_rate": 1.6198010912330646e-05, "loss": 0.0069, "step": 74950 }, { "loss_action": 0.007743752561509609, "loss_total": 0.007743752561509609, "step": 74950 }, { "grad_norm": 0.15183475613594055, "learning_rate": 1.6185828918369456e-05, "loss": 0.0061, "step": 74960 }, { "loss_action": 0.0078077358193695545, "loss_total": 0.0078077358193695545, "step": 74960 }, { "grad_norm": 0.14877597987651825, "learning_rate": 1.617365062227517e-05, "loss": 0.0055, "step": 74970 }, { "loss_action": 0.004956353455781937, "loss_total": 0.004956353455781937, "step": 74970 }, { "grad_norm": 0.144554004073143, "learning_rate": 1.616147602537962e-05, "loss": 0.0059, "step": 74980 }, { "loss_action": 0.00449436716735363, "loss_total": 0.00449436716735363, "step": 74980 }, { "grad_norm": 0.16705037653446198, "learning_rate": 1.614930512901415e-05, "loss": 0.0064, "step": 74990 }, { "loss_action": 0.006452586036175489, "loss_total": 0.006452586036175489, "step": 74990 }, { "grad_norm": 0.17153842747211456, "learning_rate": 1.6137137934509804e-05, "loss": 0.0068, "step": 75000 }, { "loss_action": 0.0047979895025491714, "loss_total": 0.0047979895025491714, "step": 75000 }, { "grad_norm": 0.14179210364818573, "learning_rate": 1.6124974443197123e-05, "loss": 0.0061, "step": 75010 }, { "loss_action": 0.007048062514513731, "loss_total": 0.007048062514513731, "step": 75010 }, { "grad_norm": 0.1577550619840622, "learning_rate": 1.6112814656406306e-05, "loss": 0.0065, "step": 75020 }, { "loss_action": 0.006649447605013847, "loss_total": 0.006649447605013847, "step": 75020 }, { "grad_norm": 0.17474251985549927, "learning_rate": 1.6100658575467125e-05, "loss": 0.0074, "step": 75030 }, { "loss_action": 0.005958687048405409, "loss_total": 0.005958687048405409, "step": 75030 }, { "grad_norm": 0.1665535271167755, "learning_rate": 1.6088506201708974e-05, "loss": 0.0063, "step": 75040 }, { "loss_action": 0.004104414489120245, "loss_total": 0.004104414489120245, "step": 75040 }, { "grad_norm": 0.13181501626968384, "learning_rate": 1.6076357536460785e-05, "loss": 0.0059, "step": 75050 }, { "loss_action": 0.0050803543999791145, "loss_total": 0.0050803543999791145, "step": 75050 }, { "grad_norm": 0.1939498335123062, "learning_rate": 1.606421258105113e-05, "loss": 0.0062, "step": 75060 }, { "loss_action": 0.006046957336366177, "loss_total": 0.006046957336366177, "step": 75060 }, { "grad_norm": 0.21261613070964813, "learning_rate": 1.6052071336808183e-05, "loss": 0.0061, "step": 75070 }, { "loss_action": 0.005280286073684692, "loss_total": 0.005280286073684692, "step": 75070 }, { "grad_norm": 0.13933122158050537, "learning_rate": 1.6039933805059658e-05, "loss": 0.0054, "step": 75080 }, { "loss_action": 0.010189156047999859, "loss_total": 0.010189156047999859, "step": 75080 }, { "grad_norm": 0.16907325387001038, "learning_rate": 1.6027799987132915e-05, "loss": 0.006, "step": 75090 }, { "loss_action": 0.005977477412670851, "loss_total": 0.005977477412670851, "step": 75090 }, { "grad_norm": 0.17167726159095764, "learning_rate": 1.6015669884354888e-05, "loss": 0.0076, "step": 75100 }, { "loss_action": 0.006359954830259085, "loss_total": 0.006359954830259085, "step": 75100 }, { "grad_norm": 0.1333753764629364, "learning_rate": 1.6003543498052125e-05, "loss": 0.0058, "step": 75110 }, { "loss_action": 0.005057675763964653, "loss_total": 0.005057675763964653, "step": 75110 }, { "grad_norm": 0.1254291534423828, "learning_rate": 1.5991420829550715e-05, "loss": 0.0062, "step": 75120 }, { "loss_action": 0.004007659386843443, "loss_total": 0.004007659386843443, "step": 75120 }, { "grad_norm": 0.1544337421655655, "learning_rate": 1.5979301880176405e-05, "loss": 0.0065, "step": 75130 }, { "loss_action": 0.008455566130578518, "loss_total": 0.008455566130578518, "step": 75130 }, { "grad_norm": 0.15688785910606384, "learning_rate": 1.5967186651254485e-05, "loss": 0.006, "step": 75140 }, { "loss_action": 0.005659748334437609, "loss_total": 0.005659748334437609, "step": 75140 }, { "grad_norm": 0.15164394676685333, "learning_rate": 1.5955075144109853e-05, "loss": 0.0059, "step": 75150 }, { "loss_action": 0.010117912665009499, "loss_total": 0.010117912665009499, "step": 75150 }, { "grad_norm": 0.2093980312347412, "learning_rate": 1.594296736006703e-05, "loss": 0.0056, "step": 75160 }, { "loss_action": 0.006710839457809925, "loss_total": 0.006710839457809925, "step": 75160 }, { "grad_norm": 0.13008926808834076, "learning_rate": 1.59308633004501e-05, "loss": 0.0068, "step": 75170 }, { "loss_action": 0.01337044034153223, "loss_total": 0.01337044034153223, "step": 75170 }, { "grad_norm": 0.1253296434879303, "learning_rate": 1.5918762966582724e-05, "loss": 0.0063, "step": 75180 }, { "loss_action": 0.004585488699376583, "loss_total": 0.004585488699376583, "step": 75180 }, { "grad_norm": 0.20028068125247955, "learning_rate": 1.5906666359788203e-05, "loss": 0.0066, "step": 75190 }, { "loss_action": 0.005758584011346102, "loss_total": 0.005758584011346102, "step": 75190 }, { "grad_norm": 0.17960557341575623, "learning_rate": 1.589457348138938e-05, "loss": 0.0058, "step": 75200 }, { "loss_action": 0.005837244912981987, "loss_total": 0.005837244912981987, "step": 75200 }, { "grad_norm": 0.13379961252212524, "learning_rate": 1.588248433270872e-05, "loss": 0.0053, "step": 75210 }, { "loss_action": 0.006610558368265629, "loss_total": 0.006610558368265629, "step": 75210 }, { "grad_norm": 0.21902896463871002, "learning_rate": 1.587039891506828e-05, "loss": 0.0068, "step": 75220 }, { "loss_action": 0.005184142850339413, "loss_total": 0.005184142850339413, "step": 75220 }, { "grad_norm": 0.181023508310318, "learning_rate": 1.5858317229789715e-05, "loss": 0.0065, "step": 75230 }, { "loss_action": 0.0042618997395038605, "loss_total": 0.0042618997395038605, "step": 75230 }, { "grad_norm": 0.16650834679603577, "learning_rate": 1.584623927819423e-05, "loss": 0.0073, "step": 75240 }, { "loss_action": 0.006302114110440016, "loss_total": 0.006302114110440016, "step": 75240 }, { "grad_norm": 0.1770850270986557, "learning_rate": 1.583416506160269e-05, "loss": 0.007, "step": 75250 }, { "loss_action": 0.0072272177785634995, "loss_total": 0.0072272177785634995, "step": 75250 }, { "grad_norm": 0.2132892608642578, "learning_rate": 1.5822094581335472e-05, "loss": 0.0069, "step": 75260 }, { "loss_action": 0.004709577653557062, "loss_total": 0.004709577653557062, "step": 75260 }, { "grad_norm": 0.1826879233121872, "learning_rate": 1.5810027838712604e-05, "loss": 0.0058, "step": 75270 }, { "loss_action": 0.005483212415128946, "loss_total": 0.005483212415128946, "step": 75270 }, { "grad_norm": 0.1461821049451828, "learning_rate": 1.5797964835053687e-05, "loss": 0.0068, "step": 75280 }, { "loss_action": 0.0037918458692729473, "loss_total": 0.0037918458692729473, "step": 75280 }, { "grad_norm": 0.12888765335083008, "learning_rate": 1.5785905571677933e-05, "loss": 0.0056, "step": 75290 }, { "loss_action": 0.006833836901932955, "loss_total": 0.006833836901932955, "step": 75290 }, { "grad_norm": 0.17646105587482452, "learning_rate": 1.5773850049904086e-05, "loss": 0.0055, "step": 75300 }, { "loss_action": 0.0059833647683262825, "loss_total": 0.0059833647683262825, "step": 75300 }, { "grad_norm": 0.16697673499584198, "learning_rate": 1.5761798271050543e-05, "loss": 0.0058, "step": 75310 }, { "loss_action": 0.004898198880255222, "loss_total": 0.004898198880255222, "step": 75310 }, { "grad_norm": 0.16800300776958466, "learning_rate": 1.5749750236435277e-05, "loss": 0.0058, "step": 75320 }, { "loss_action": 0.008037948980927467, "loss_total": 0.008037948980927467, "step": 75320 }, { "grad_norm": 0.14343468844890594, "learning_rate": 1.5737705947375815e-05, "loss": 0.0065, "step": 75330 }, { "loss_action": 0.006996467709541321, "loss_total": 0.006996467709541321, "step": 75330 }, { "grad_norm": 0.15723444521427155, "learning_rate": 1.5725665405189322e-05, "loss": 0.0056, "step": 75340 }, { "loss_action": 0.0057689109817147255, "loss_total": 0.0057689109817147255, "step": 75340 }, { "grad_norm": 0.13757407665252686, "learning_rate": 1.571362861119253e-05, "loss": 0.0061, "step": 75350 }, { "loss_action": 0.009519926272332668, "loss_total": 0.009519926272332668, "step": 75350 }, { "grad_norm": 0.13819272816181183, "learning_rate": 1.570159556670177e-05, "loss": 0.0066, "step": 75360 }, { "loss_action": 0.005656467750668526, "loss_total": 0.005656467750668526, "step": 75360 }, { "grad_norm": 0.18799912929534912, "learning_rate": 1.5689566273032946e-05, "loss": 0.0056, "step": 75370 }, { "loss_action": 0.005716115236282349, "loss_total": 0.005716115236282349, "step": 75370 }, { "grad_norm": 0.13548599183559418, "learning_rate": 1.5677540731501583e-05, "loss": 0.0056, "step": 75380 }, { "loss_action": 0.0082953330129385, "loss_total": 0.0082953330129385, "step": 75380 }, { "grad_norm": 0.21409082412719727, "learning_rate": 1.5665518943422746e-05, "loss": 0.0083, "step": 75390 }, { "loss_action": 0.00589956296607852, "loss_total": 0.00589956296607852, "step": 75390 }, { "grad_norm": 0.140824094414711, "learning_rate": 1.5653500910111134e-05, "loss": 0.006, "step": 75400 }, { "loss_action": 0.008007675409317017, "loss_total": 0.008007675409317017, "step": 75400 }, { "grad_norm": 0.14913460612297058, "learning_rate": 1.5641486632881023e-05, "loss": 0.0059, "step": 75410 }, { "loss_action": 0.006647828035056591, "loss_total": 0.006647828035056591, "step": 75410 }, { "grad_norm": 0.1525294929742813, "learning_rate": 1.56294761130463e-05, "loss": 0.0072, "step": 75420 }, { "loss_action": 0.006136212032288313, "loss_total": 0.006136212032288313, "step": 75420 }, { "grad_norm": 0.13623563945293427, "learning_rate": 1.5617469351920373e-05, "loss": 0.005, "step": 75430 }, { "loss_action": 0.004390668123960495, "loss_total": 0.004390668123960495, "step": 75430 }, { "grad_norm": 0.156296044588089, "learning_rate": 1.5605466350816315e-05, "loss": 0.0059, "step": 75440 }, { "loss_action": 0.0084186140447855, "loss_total": 0.0084186140447855, "step": 75440 }, { "grad_norm": 0.1603047251701355, "learning_rate": 1.559346711104674e-05, "loss": 0.0073, "step": 75450 }, { "loss_action": 0.005644380114972591, "loss_total": 0.005644380114972591, "step": 75450 }, { "grad_norm": 0.20289021730422974, "learning_rate": 1.5581471633923883e-05, "loss": 0.0067, "step": 75460 }, { "loss_action": 0.005395951215177774, "loss_total": 0.005395951215177774, "step": 75460 }, { "grad_norm": 0.1648905873298645, "learning_rate": 1.5569479920759505e-05, "loss": 0.0058, "step": 75470 }, { "loss_action": 0.00627160957083106, "loss_total": 0.00627160957083106, "step": 75470 }, { "grad_norm": 0.14817237854003906, "learning_rate": 1.5557491972865072e-05, "loss": 0.0055, "step": 75480 }, { "loss_action": 0.0054511213675141335, "loss_total": 0.0054511213675141335, "step": 75480 }, { "grad_norm": 0.17289021611213684, "learning_rate": 1.554550779155152e-05, "loss": 0.0057, "step": 75490 }, { "loss_action": 0.007063682656735182, "loss_total": 0.007063682656735182, "step": 75490 }, { "grad_norm": 0.18991945683956146, "learning_rate": 1.5533527378129453e-05, "loss": 0.0063, "step": 75500 }, { "loss_action": 0.008008003234863281, "loss_total": 0.008008003234863281, "step": 75500 }, { "grad_norm": 0.18294398486614227, "learning_rate": 1.552155073390899e-05, "loss": 0.0072, "step": 75510 }, { "loss_action": 0.005441552959382534, "loss_total": 0.005441552959382534, "step": 75510 }, { "grad_norm": 0.2011352926492691, "learning_rate": 1.5509577860199903e-05, "loss": 0.006, "step": 75520 }, { "loss_action": 0.0066003212705254555, "loss_total": 0.0066003212705254555, "step": 75520 }, { "grad_norm": 0.16739967465400696, "learning_rate": 1.5497608758311525e-05, "loss": 0.0067, "step": 75530 }, { "loss_action": 0.005274921655654907, "loss_total": 0.005274921655654907, "step": 75530 }, { "grad_norm": 0.17301902174949646, "learning_rate": 1.5485643429552797e-05, "loss": 0.0057, "step": 75540 }, { "loss_action": 0.004529227968305349, "loss_total": 0.004529227968305349, "step": 75540 }, { "grad_norm": 0.14591588079929352, "learning_rate": 1.5473681875232197e-05, "loss": 0.0064, "step": 75550 }, { "loss_action": 0.005952608305960894, "loss_total": 0.005952608305960894, "step": 75550 }, { "grad_norm": 0.15174946188926697, "learning_rate": 1.5461724096657837e-05, "loss": 0.0068, "step": 75560 }, { "loss_action": 0.007407056633383036, "loss_total": 0.007407056633383036, "step": 75560 }, { "grad_norm": 0.181441992521286, "learning_rate": 1.5449770095137416e-05, "loss": 0.0065, "step": 75570 }, { "loss_action": 0.0061217718757689, "loss_total": 0.0061217718757689, "step": 75570 }, { "grad_norm": 0.2623783349990845, "learning_rate": 1.5437819871978178e-05, "loss": 0.0067, "step": 75580 }, { "loss_action": 0.0062615047208964825, "loss_total": 0.0062615047208964825, "step": 75580 }, { "grad_norm": 0.17582321166992188, "learning_rate": 1.5425873428486992e-05, "loss": 0.0061, "step": 75590 }, { "loss_action": 0.006508993916213512, "loss_total": 0.006508993916213512, "step": 75590 }, { "grad_norm": 0.11000459641218185, "learning_rate": 1.5413930765970312e-05, "loss": 0.0061, "step": 75600 }, { "loss_action": 0.0070809898898005486, "loss_total": 0.0070809898898005486, "step": 75600 }, { "grad_norm": 0.17327623069286346, "learning_rate": 1.5401991885734175e-05, "loss": 0.0063, "step": 75610 }, { "loss_action": 0.005265358369797468, "loss_total": 0.005265358369797468, "step": 75610 }, { "grad_norm": 0.14981609582901, "learning_rate": 1.5390056789084174e-05, "loss": 0.0069, "step": 75620 }, { "loss_action": 0.006009408738464117, "loss_total": 0.006009408738464117, "step": 75620 }, { "grad_norm": 0.15439893305301666, "learning_rate": 1.5378125477325545e-05, "loss": 0.0061, "step": 75630 }, { "loss_action": 0.006674980279058218, "loss_total": 0.006674980279058218, "step": 75630 }, { "grad_norm": 0.13815170526504517, "learning_rate": 1.5366197951763046e-05, "loss": 0.0057, "step": 75640 }, { "loss_action": 0.005457955412566662, "loss_total": 0.005457955412566662, "step": 75640 }, { "grad_norm": 0.21561478078365326, "learning_rate": 1.5354274213701075e-05, "loss": 0.0061, "step": 75650 }, { "loss_action": 0.00833828840404749, "loss_total": 0.00833828840404749, "step": 75650 }, { "grad_norm": 0.1966821253299713, "learning_rate": 1.5342354264443566e-05, "loss": 0.0071, "step": 75660 }, { "loss_action": 0.006916037295013666, "loss_total": 0.006916037295013666, "step": 75660 }, { "grad_norm": 0.17042407393455505, "learning_rate": 1.533043810529411e-05, "loss": 0.0063, "step": 75670 }, { "loss_action": 0.008849729783833027, "loss_total": 0.008849729783833027, "step": 75670 }, { "grad_norm": 0.1746603399515152, "learning_rate": 1.5318525737555807e-05, "loss": 0.0063, "step": 75680 }, { "loss_action": 0.005144351162016392, "loss_total": 0.005144351162016392, "step": 75680 }, { "grad_norm": 0.1482386291027069, "learning_rate": 1.53066171625314e-05, "loss": 0.0055, "step": 75690 }, { "loss_action": 0.010081764310598373, "loss_total": 0.010081764310598373, "step": 75690 }, { "grad_norm": 0.10521207004785538, "learning_rate": 1.529471238152317e-05, "loss": 0.0054, "step": 75700 }, { "loss_action": 0.005305746104568243, "loss_total": 0.005305746104568243, "step": 75700 }, { "grad_norm": 0.23472723364830017, "learning_rate": 1.5282811395833023e-05, "loss": 0.0069, "step": 75710 }, { "loss_action": 0.006302759516984224, "loss_total": 0.006302759516984224, "step": 75710 }, { "grad_norm": 0.1597975641489029, "learning_rate": 1.5270914206762397e-05, "loss": 0.0065, "step": 75720 }, { "loss_action": 0.004794046748429537, "loss_total": 0.004794046748429537, "step": 75720 }, { "grad_norm": 0.16840851306915283, "learning_rate": 1.525902081561241e-05, "loss": 0.0063, "step": 75730 }, { "loss_action": 0.005706011783331633, "loss_total": 0.005706011783331633, "step": 75730 }, { "grad_norm": 0.16570129990577698, "learning_rate": 1.5247131223683664e-05, "loss": 0.0061, "step": 75740 }, { "loss_action": 0.004923906642943621, "loss_total": 0.004923906642943621, "step": 75740 }, { "grad_norm": 0.16490323841571808, "learning_rate": 1.5235245432276408e-05, "loss": 0.0062, "step": 75750 }, { "loss_action": 0.015165061689913273, "loss_total": 0.015165061689913273, "step": 75750 }, { "grad_norm": 0.18308568000793457, "learning_rate": 1.5223363442690424e-05, "loss": 0.007, "step": 75760 }, { "loss_action": 0.005368692800402641, "loss_total": 0.005368692800402641, "step": 75760 }, { "grad_norm": 0.2650614380836487, "learning_rate": 1.5211485256225133e-05, "loss": 0.0058, "step": 75770 }, { "loss_action": 0.00566114392131567, "loss_total": 0.00566114392131567, "step": 75770 }, { "grad_norm": 0.23419973254203796, "learning_rate": 1.519961087417951e-05, "loss": 0.007, "step": 75780 }, { "loss_action": 0.00646598357707262, "loss_total": 0.00646598357707262, "step": 75780 }, { "grad_norm": 0.23993046581745148, "learning_rate": 1.5187740297852137e-05, "loss": 0.0078, "step": 75790 }, { "loss_action": 0.006377298850566149, "loss_total": 0.006377298850566149, "step": 75790 }, { "grad_norm": 0.27838554978370667, "learning_rate": 1.517587352854113e-05, "loss": 0.0069, "step": 75800 }, { "loss_action": 0.005708805751055479, "loss_total": 0.005708805751055479, "step": 75800 }, { "grad_norm": 0.1245025172829628, "learning_rate": 1.516401056754423e-05, "loss": 0.0069, "step": 75810 }, { "loss_action": 0.008241555653512478, "loss_total": 0.008241555653512478, "step": 75810 }, { "grad_norm": 0.17812217772006989, "learning_rate": 1.5152151416158783e-05, "loss": 0.0064, "step": 75820 }, { "loss_action": 0.007585514336824417, "loss_total": 0.007585514336824417, "step": 75820 }, { "grad_norm": 0.13651245832443237, "learning_rate": 1.5140296075681642e-05, "loss": 0.0064, "step": 75830 }, { "loss_action": 0.005026238039135933, "loss_total": 0.005026238039135933, "step": 75830 }, { "grad_norm": 0.20617032051086426, "learning_rate": 1.5128444547409331e-05, "loss": 0.0065, "step": 75840 }, { "loss_action": 0.006150775123387575, "loss_total": 0.006150775123387575, "step": 75840 }, { "grad_norm": 0.18517200648784637, "learning_rate": 1.5116596832637864e-05, "loss": 0.0066, "step": 75850 }, { "loss_action": 0.005703159142285585, "loss_total": 0.005703159142285585, "step": 75850 }, { "grad_norm": 0.16612179577350616, "learning_rate": 1.5104752932662952e-05, "loss": 0.006, "step": 75860 }, { "loss_action": 0.007791753858327866, "loss_total": 0.007791753858327866, "step": 75860 }, { "grad_norm": 0.15805630385875702, "learning_rate": 1.5092912848779778e-05, "loss": 0.0062, "step": 75870 }, { "loss_action": 0.004809364210814238, "loss_total": 0.004809364210814238, "step": 75870 }, { "grad_norm": 0.20406851172447205, "learning_rate": 1.5081076582283194e-05, "loss": 0.0055, "step": 75880 }, { "loss_action": 0.007626914419233799, "loss_total": 0.007626914419233799, "step": 75880 }, { "grad_norm": 0.12563835084438324, "learning_rate": 1.5069244134467553e-05, "loss": 0.0063, "step": 75890 }, { "loss_action": 0.004672870505601168, "loss_total": 0.004672870505601168, "step": 75890 }, { "grad_norm": 0.19486922025680542, "learning_rate": 1.5057415506626876e-05, "loss": 0.0058, "step": 75900 }, { "loss_action": 0.005166512914001942, "loss_total": 0.005166512914001942, "step": 75900 }, { "grad_norm": 0.139487162232399, "learning_rate": 1.5045590700054668e-05, "loss": 0.0055, "step": 75910 }, { "loss_action": 0.004354272037744522, "loss_total": 0.004354272037744522, "step": 75910 }, { "grad_norm": 0.21951426565647125, "learning_rate": 1.5033769716044144e-05, "loss": 0.0072, "step": 75920 }, { "loss_action": 0.007029404863715172, "loss_total": 0.007029404863715172, "step": 75920 }, { "grad_norm": 0.159625843167305, "learning_rate": 1.5021952555887975e-05, "loss": 0.0068, "step": 75930 }, { "loss_action": 0.005196650978177786, "loss_total": 0.005196650978177786, "step": 75930 }, { "grad_norm": 0.15768493711948395, "learning_rate": 1.50101392208785e-05, "loss": 0.006, "step": 75940 }, { "loss_action": 0.004009629134088755, "loss_total": 0.004009629134088755, "step": 75940 }, { "grad_norm": 0.1462797224521637, "learning_rate": 1.4998329712307579e-05, "loss": 0.0064, "step": 75950 }, { "loss_action": 0.008267299272119999, "loss_total": 0.008267299272119999, "step": 75950 }, { "grad_norm": 0.14614760875701904, "learning_rate": 1.4986524031466708e-05, "loss": 0.006, "step": 75960 }, { "loss_action": 0.006351163145154715, "loss_total": 0.006351163145154715, "step": 75960 }, { "grad_norm": 0.1521519422531128, "learning_rate": 1.4974722179646916e-05, "loss": 0.0061, "step": 75970 }, { "loss_action": 0.00506154028698802, "loss_total": 0.00506154028698802, "step": 75970 }, { "grad_norm": 0.12091206759214401, "learning_rate": 1.4962924158138847e-05, "loss": 0.006, "step": 75980 }, { "loss_action": 0.005576819181442261, "loss_total": 0.005576819181442261, "step": 75980 }, { "grad_norm": 0.12056957185268402, "learning_rate": 1.4951129968232714e-05, "loss": 0.0053, "step": 75990 }, { "loss_action": 0.00452009029686451, "loss_total": 0.00452009029686451, "step": 75990 }, { "grad_norm": 0.14632156491279602, "learning_rate": 1.4939339611218329e-05, "loss": 0.0052, "step": 76000 }, { "loss_action": 0.00580045348033309, "loss_total": 0.00580045348033309, "step": 76000 }, { "grad_norm": 0.17004549503326416, "learning_rate": 1.4927553088385032e-05, "loss": 0.0057, "step": 76010 }, { "loss_action": 0.0067022317089140415, "loss_total": 0.0067022317089140415, "step": 76010 }, { "grad_norm": 0.14132875204086304, "learning_rate": 1.4915770401021801e-05, "loss": 0.0072, "step": 76020 }, { "loss_action": 0.0069674961268901825, "loss_total": 0.0069674961268901825, "step": 76020 }, { "grad_norm": 0.14083223044872284, "learning_rate": 1.4903991550417185e-05, "loss": 0.0062, "step": 76030 }, { "loss_action": 0.006356621626764536, "loss_total": 0.006356621626764536, "step": 76030 }, { "grad_norm": 0.18828552961349487, "learning_rate": 1.4892216537859277e-05, "loss": 0.007, "step": 76040 }, { "loss_action": 0.010523839853703976, "loss_total": 0.010523839853703976, "step": 76040 }, { "grad_norm": 0.14882592856884003, "learning_rate": 1.4880445364635775e-05, "loss": 0.0065, "step": 76050 }, { "loss_action": 0.007783580105751753, "loss_total": 0.007783580105751753, "step": 76050 }, { "grad_norm": 0.16242031753063202, "learning_rate": 1.4868678032033973e-05, "loss": 0.0067, "step": 76060 }, { "loss_action": 0.008715257979929447, "loss_total": 0.008715257979929447, "step": 76060 }, { "grad_norm": 0.12141326069831848, "learning_rate": 1.4856914541340739e-05, "loss": 0.006, "step": 76070 }, { "loss_action": 0.005493429489433765, "loss_total": 0.005493429489433765, "step": 76070 }, { "grad_norm": 0.1713855266571045, "learning_rate": 1.4845154893842472e-05, "loss": 0.0057, "step": 76080 }, { "loss_action": 0.007421379443258047, "loss_total": 0.007421379443258047, "step": 76080 }, { "grad_norm": 0.17763973772525787, "learning_rate": 1.4833399090825234e-05, "loss": 0.0064, "step": 76090 }, { "loss_action": 0.004666210152208805, "loss_total": 0.004666210152208805, "step": 76090 }, { "grad_norm": 0.18765003979206085, "learning_rate": 1.4821647133574562e-05, "loss": 0.006, "step": 76100 }, { "loss_action": 0.00838380679488182, "loss_total": 0.00838380679488182, "step": 76100 }, { "grad_norm": 0.2037643939256668, "learning_rate": 1.4809899023375706e-05, "loss": 0.0061, "step": 76110 }, { "loss_action": 0.004869803320616484, "loss_total": 0.004869803320616484, "step": 76110 }, { "grad_norm": 0.15867026150226593, "learning_rate": 1.4798154761513366e-05, "loss": 0.0064, "step": 76120 }, { "loss_action": 0.005559034179896116, "loss_total": 0.005559034179896116, "step": 76120 }, { "grad_norm": 0.2228948175907135, "learning_rate": 1.4786414349271916e-05, "loss": 0.0054, "step": 76130 }, { "loss_action": 0.006571606732904911, "loss_total": 0.006571606732904911, "step": 76130 }, { "grad_norm": 0.138912171125412, "learning_rate": 1.4774677787935226e-05, "loss": 0.0062, "step": 76140 }, { "loss_action": 0.005269919987767935, "loss_total": 0.005269919987767935, "step": 76140 }, { "grad_norm": 0.15365244448184967, "learning_rate": 1.4762945078786838e-05, "loss": 0.0062, "step": 76150 }, { "loss_action": 0.004135806113481522, "loss_total": 0.004135806113481522, "step": 76150 }, { "grad_norm": 0.14115333557128906, "learning_rate": 1.4751216223109777e-05, "loss": 0.0056, "step": 76160 }, { "loss_action": 0.006659922190010548, "loss_total": 0.006659922190010548, "step": 76160 }, { "grad_norm": 0.1471654176712036, "learning_rate": 1.4739491222186714e-05, "loss": 0.0067, "step": 76170 }, { "loss_action": 0.00507228123024106, "loss_total": 0.00507228123024106, "step": 76170 }, { "grad_norm": 0.14730031788349152, "learning_rate": 1.4727770077299879e-05, "loss": 0.0058, "step": 76180 }, { "loss_action": 0.006589686963707209, "loss_total": 0.006589686963707209, "step": 76180 }, { "grad_norm": 0.16689521074295044, "learning_rate": 1.4716052789731094e-05, "loss": 0.0056, "step": 76190 }, { "loss_action": 0.004834440071135759, "loss_total": 0.004834440071135759, "step": 76190 }, { "grad_norm": 0.2007422000169754, "learning_rate": 1.470433936076171e-05, "loss": 0.0067, "step": 76200 }, { "loss_action": 0.0041182334534823895, "loss_total": 0.0041182334534823895, "step": 76200 }, { "grad_norm": 0.18979936838150024, "learning_rate": 1.4692629791672719e-05, "loss": 0.0073, "step": 76210 }, { "loss_action": 0.00626287842169404, "loss_total": 0.00626287842169404, "step": 76210 }, { "grad_norm": 0.17778468132019043, "learning_rate": 1.468092408374464e-05, "loss": 0.0065, "step": 76220 }, { "loss_action": 0.007262197323143482, "loss_total": 0.007262197323143482, "step": 76220 }, { "grad_norm": 0.13995149731636047, "learning_rate": 1.4669222238257602e-05, "loss": 0.0055, "step": 76230 }, { "loss_action": 0.004880422260612249, "loss_total": 0.004880422260612249, "step": 76230 }, { "grad_norm": 0.15675312280654907, "learning_rate": 1.4657524256491301e-05, "loss": 0.0063, "step": 76240 }, { "loss_action": 0.004366616252809763, "loss_total": 0.004366616252809763, "step": 76240 }, { "grad_norm": 0.21973931789398193, "learning_rate": 1.464583013972502e-05, "loss": 0.0058, "step": 76250 }, { "loss_action": 0.008294367231428623, "loss_total": 0.008294367231428623, "step": 76250 }, { "grad_norm": 0.16754767298698425, "learning_rate": 1.4634139889237591e-05, "loss": 0.0062, "step": 76260 }, { "loss_action": 0.007755948230624199, "loss_total": 0.007755948230624199, "step": 76260 }, { "grad_norm": 0.15717817842960358, "learning_rate": 1.4622453506307448e-05, "loss": 0.0071, "step": 76270 }, { "loss_action": 0.008388330228626728, "loss_total": 0.008388330228626728, "step": 76270 }, { "grad_norm": 0.1513555943965912, "learning_rate": 1.461077099221262e-05, "loss": 0.0061, "step": 76280 }, { "loss_action": 0.0061489734798669815, "loss_total": 0.0061489734798669815, "step": 76280 }, { "grad_norm": 0.15777850151062012, "learning_rate": 1.4599092348230652e-05, "loss": 0.0053, "step": 76290 }, { "loss_action": 0.00402452889829874, "loss_total": 0.00402452889829874, "step": 76290 }, { "grad_norm": 0.14100292325019836, "learning_rate": 1.4587417575638724e-05, "loss": 0.0056, "step": 76300 }, { "loss_action": 0.00937753077596426, "loss_total": 0.00937753077596426, "step": 76300 }, { "grad_norm": 0.15489768981933594, "learning_rate": 1.4575746675713563e-05, "loss": 0.0064, "step": 76310 }, { "loss_action": 0.004241445101797581, "loss_total": 0.004241445101797581, "step": 76310 }, { "grad_norm": 0.14987465739250183, "learning_rate": 1.4564079649731504e-05, "loss": 0.0051, "step": 76320 }, { "loss_action": 0.005085556767880917, "loss_total": 0.005085556767880917, "step": 76320 }, { "grad_norm": 0.14587241411209106, "learning_rate": 1.4552416498968402e-05, "loss": 0.0053, "step": 76330 }, { "loss_action": 0.008096301928162575, "loss_total": 0.008096301928162575, "step": 76330 }, { "grad_norm": 0.18677224218845367, "learning_rate": 1.4540757224699747e-05, "loss": 0.0065, "step": 76340 }, { "loss_action": 0.006413282826542854, "loss_total": 0.006413282826542854, "step": 76340 }, { "grad_norm": 0.2534746527671814, "learning_rate": 1.452910182820056e-05, "loss": 0.0069, "step": 76350 }, { "loss_action": 0.00630720891058445, "loss_total": 0.00630720891058445, "step": 76350 }, { "grad_norm": 0.18519629538059235, "learning_rate": 1.4517450310745468e-05, "loss": 0.0061, "step": 76360 }, { "loss_action": 0.0051558613777160645, "loss_total": 0.0051558613777160645, "step": 76360 }, { "grad_norm": 0.17039723694324493, "learning_rate": 1.450580267360866e-05, "loss": 0.0055, "step": 76370 }, { "loss_action": 0.00914050918072462, "loss_total": 0.00914050918072462, "step": 76370 }, { "grad_norm": 0.15815195441246033, "learning_rate": 1.4494158918063922e-05, "loss": 0.0081, "step": 76380 }, { "loss_action": 0.00581997400149703, "loss_total": 0.00581997400149703, "step": 76380 }, { "grad_norm": 0.21775692701339722, "learning_rate": 1.4482519045384568e-05, "loss": 0.0063, "step": 76390 }, { "loss_action": 0.008770601823925972, "loss_total": 0.008770601823925972, "step": 76390 }, { "grad_norm": 0.20661218464374542, "learning_rate": 1.4470883056843548e-05, "loss": 0.0069, "step": 76400 }, { "loss_action": 0.004297028761357069, "loss_total": 0.004297028761357069, "step": 76400 }, { "grad_norm": 0.18943707644939423, "learning_rate": 1.4459250953713322e-05, "loss": 0.0062, "step": 76410 }, { "loss_action": 0.004049492999911308, "loss_total": 0.004049492999911308, "step": 76410 }, { "grad_norm": 0.1840454339981079, "learning_rate": 1.444762273726598e-05, "loss": 0.0052, "step": 76420 }, { "loss_action": 0.01322602853178978, "loss_total": 0.01322602853178978, "step": 76420 }, { "grad_norm": 0.20268458127975464, "learning_rate": 1.443599840877316e-05, "loss": 0.0065, "step": 76430 }, { "loss_action": 0.004984620492905378, "loss_total": 0.004984620492905378, "step": 76430 }, { "grad_norm": 0.1640748679637909, "learning_rate": 1.4424377969506103e-05, "loss": 0.0059, "step": 76440 }, { "loss_action": 0.0074995821341872215, "loss_total": 0.0074995821341872215, "step": 76440 }, { "grad_norm": 0.18636812269687653, "learning_rate": 1.4412761420735565e-05, "loss": 0.0059, "step": 76450 }, { "loss_action": 0.006427408196032047, "loss_total": 0.006427408196032047, "step": 76450 }, { "grad_norm": 0.14406943321228027, "learning_rate": 1.4401148763731953e-05, "loss": 0.006, "step": 76460 }, { "loss_action": 0.005698154214769602, "loss_total": 0.005698154214769602, "step": 76460 }, { "grad_norm": 0.17170274257659912, "learning_rate": 1.4389539999765173e-05, "loss": 0.0057, "step": 76470 }, { "loss_action": 0.00600948603823781, "loss_total": 0.00600948603823781, "step": 76470 }, { "grad_norm": 0.1334231197834015, "learning_rate": 1.4377935130104758e-05, "loss": 0.0057, "step": 76480 }, { "loss_action": 0.0063887666910886765, "loss_total": 0.0063887666910886765, "step": 76480 }, { "grad_norm": 0.14815911650657654, "learning_rate": 1.4366334156019801e-05, "loss": 0.0061, "step": 76490 }, { "loss_action": 0.008014010265469551, "loss_total": 0.008014010265469551, "step": 76490 }, { "grad_norm": 0.18185953795909882, "learning_rate": 1.435473707877898e-05, "loss": 0.0062, "step": 76500 }, { "loss_action": 0.0052270242013037205, "loss_total": 0.0052270242013037205, "step": 76500 }, { "grad_norm": 0.16620253026485443, "learning_rate": 1.4343143899650508e-05, "loss": 0.0061, "step": 76510 }, { "loss_action": 0.0073713986203074455, "loss_total": 0.0073713986203074455, "step": 76510 }, { "grad_norm": 0.11311282962560654, "learning_rate": 1.4331554619902204e-05, "loss": 0.0062, "step": 76520 }, { "loss_action": 0.006043151952326298, "loss_total": 0.006043151952326298, "step": 76520 }, { "grad_norm": 0.1688249409198761, "learning_rate": 1.4319969240801484e-05, "loss": 0.0056, "step": 76530 }, { "loss_action": 0.004446723498404026, "loss_total": 0.004446723498404026, "step": 76530 }, { "grad_norm": 0.13463403284549713, "learning_rate": 1.430838776361526e-05, "loss": 0.0057, "step": 76540 }, { "loss_action": 0.004143198486417532, "loss_total": 0.004143198486417532, "step": 76540 }, { "grad_norm": 0.2040625661611557, "learning_rate": 1.4296810189610093e-05, "loss": 0.0061, "step": 76550 }, { "loss_action": 0.005209337454289198, "loss_total": 0.005209337454289198, "step": 76550 }, { "grad_norm": 0.12483885884284973, "learning_rate": 1.4285236520052087e-05, "loss": 0.0055, "step": 76560 }, { "loss_action": 0.0053755431436002254, "loss_total": 0.0053755431436002254, "step": 76560 }, { "grad_norm": 0.1750435084104538, "learning_rate": 1.4273666756206933e-05, "loss": 0.0062, "step": 76570 }, { "loss_action": 0.0055021499283611774, "loss_total": 0.0055021499283611774, "step": 76570 }, { "grad_norm": 0.1925525665283203, "learning_rate": 1.4262100899339848e-05, "loss": 0.0063, "step": 76580 }, { "loss_action": 0.003727721283212304, "loss_total": 0.003727721283212304, "step": 76580 }, { "grad_norm": 0.18222646415233612, "learning_rate": 1.4250538950715696e-05, "loss": 0.0064, "step": 76590 }, { "loss_action": 0.007960540242493153, "loss_total": 0.007960540242493153, "step": 76590 }, { "grad_norm": 0.18861213326454163, "learning_rate": 1.4238980911598842e-05, "loss": 0.0057, "step": 76600 }, { "loss_action": 0.0070034111849963665, "loss_total": 0.0070034111849963665, "step": 76600 }, { "grad_norm": 0.14916911721229553, "learning_rate": 1.4227426783253267e-05, "loss": 0.0055, "step": 76610 }, { "loss_action": 0.00393056683242321, "loss_total": 0.00393056683242321, "step": 76610 }, { "grad_norm": 0.218728169798851, "learning_rate": 1.4215876566942521e-05, "loss": 0.0062, "step": 76620 }, { "loss_action": 0.0057540894486010075, "loss_total": 0.0057540894486010075, "step": 76620 }, { "grad_norm": 0.16259156167507172, "learning_rate": 1.4204330263929721e-05, "loss": 0.0054, "step": 76630 }, { "loss_action": 0.005894615780562162, "loss_total": 0.005894615780562162, "step": 76630 }, { "grad_norm": 0.13634926080703735, "learning_rate": 1.4192787875477537e-05, "loss": 0.0059, "step": 76640 }, { "loss_action": 0.00526002049446106, "loss_total": 0.00526002049446106, "step": 76640 }, { "grad_norm": 0.17702005803585052, "learning_rate": 1.4181249402848246e-05, "loss": 0.0057, "step": 76650 }, { "loss_action": 0.005402084905654192, "loss_total": 0.005402084905654192, "step": 76650 }, { "grad_norm": 0.19813624024391174, "learning_rate": 1.4169714847303656e-05, "loss": 0.0068, "step": 76660 }, { "loss_action": 0.00630386546254158, "loss_total": 0.00630386546254158, "step": 76660 }, { "grad_norm": 0.1627708077430725, "learning_rate": 1.4158184210105197e-05, "loss": 0.0064, "step": 76670 }, { "loss_action": 0.01241741981357336, "loss_total": 0.01241741981357336, "step": 76670 }, { "grad_norm": 0.17089129984378815, "learning_rate": 1.4146657492513787e-05, "loss": 0.0066, "step": 76680 }, { "loss_action": 0.005609374959021807, "loss_total": 0.005609374959021807, "step": 76680 }, { "grad_norm": 0.17518161237239838, "learning_rate": 1.4135134695790047e-05, "loss": 0.0056, "step": 76690 }, { "loss_action": 0.008336673490703106, "loss_total": 0.008336673490703106, "step": 76690 }, { "grad_norm": 0.12677817046642303, "learning_rate": 1.4123615821194037e-05, "loss": 0.0058, "step": 76700 }, { "loss_action": 0.006212207954376936, "loss_total": 0.006212207954376936, "step": 76700 }, { "grad_norm": 0.16700080037117004, "learning_rate": 1.4112100869985473e-05, "loss": 0.0057, "step": 76710 }, { "loss_action": 0.0054008145816624165, "loss_total": 0.0054008145816624165, "step": 76710 }, { "grad_norm": 0.15321388840675354, "learning_rate": 1.4100589843423589e-05, "loss": 0.0059, "step": 76720 }, { "loss_action": 0.004840395413339138, "loss_total": 0.004840395413339138, "step": 76720 }, { "grad_norm": 0.12882021069526672, "learning_rate": 1.408908274276723e-05, "loss": 0.0049, "step": 76730 }, { "loss_action": 0.005063997581601143, "loss_total": 0.005063997581601143, "step": 76730 }, { "grad_norm": 0.17916859686374664, "learning_rate": 1.4077579569274786e-05, "loss": 0.0055, "step": 76740 }, { "loss_action": 0.0033922065049409866, "loss_total": 0.0033922065049409866, "step": 76740 }, { "grad_norm": 0.17841055989265442, "learning_rate": 1.4066080324204245e-05, "loss": 0.0067, "step": 76750 }, { "loss_action": 0.0036166091449558735, "loss_total": 0.0036166091449558735, "step": 76750 }, { "grad_norm": 0.12803399562835693, "learning_rate": 1.405458500881312e-05, "loss": 0.0063, "step": 76760 }, { "loss_action": 0.004843970760703087, "loss_total": 0.004843970760703087, "step": 76760 }, { "grad_norm": 0.15584491193294525, "learning_rate": 1.4043093624358538e-05, "loss": 0.0066, "step": 76770 }, { "loss_action": 0.008349903859198093, "loss_total": 0.008349903859198093, "step": 76770 }, { "grad_norm": 0.14041787385940552, "learning_rate": 1.4031606172097189e-05, "loss": 0.0056, "step": 76780 }, { "loss_action": 0.007398716174066067, "loss_total": 0.007398716174066067, "step": 76780 }, { "grad_norm": 0.14894236624240875, "learning_rate": 1.40201226532853e-05, "loss": 0.006, "step": 76790 }, { "loss_action": 0.0055038114078342915, "loss_total": 0.0055038114078342915, "step": 76790 }, { "grad_norm": 0.1949673891067505, "learning_rate": 1.4008643069178701e-05, "loss": 0.0062, "step": 76800 }, { "loss_action": 0.004205511417239904, "loss_total": 0.004205511417239904, "step": 76800 }, { "grad_norm": 0.11493230611085892, "learning_rate": 1.399716742103278e-05, "loss": 0.0053, "step": 76810 }, { "loss_action": 0.005193021614104509, "loss_total": 0.005193021614104509, "step": 76810 }, { "grad_norm": 0.12197130173444748, "learning_rate": 1.398569571010252e-05, "loss": 0.0059, "step": 76820 }, { "loss_action": 0.006210929248481989, "loss_total": 0.006210929248481989, "step": 76820 }, { "grad_norm": 0.17196115851402283, "learning_rate": 1.3974227937642414e-05, "loss": 0.0063, "step": 76830 }, { "loss_action": 0.005108284763991833, "loss_total": 0.005108284763991833, "step": 76830 }, { "grad_norm": 0.11134078353643417, "learning_rate": 1.3962764104906595e-05, "loss": 0.0055, "step": 76840 }, { "loss_action": 0.004015885293483734, "loss_total": 0.004015885293483734, "step": 76840 }, { "grad_norm": 0.1140407919883728, "learning_rate": 1.3951304213148696e-05, "loss": 0.0051, "step": 76850 }, { "loss_action": 0.008349963463842869, "loss_total": 0.008349963463842869, "step": 76850 }, { "grad_norm": 0.15566344559192657, "learning_rate": 1.3939848263621979e-05, "loss": 0.006, "step": 76860 }, { "loss_action": 0.009973201900720596, "loss_total": 0.009973201900720596, "step": 76860 }, { "grad_norm": 0.19387386739253998, "learning_rate": 1.3928396257579219e-05, "loss": 0.0057, "step": 76870 }, { "loss_action": 0.007429688237607479, "loss_total": 0.007429688237607479, "step": 76870 }, { "grad_norm": 0.12850670516490936, "learning_rate": 1.3916948196272833e-05, "loss": 0.005, "step": 76880 }, { "loss_action": 0.003226241562515497, "loss_total": 0.003226241562515497, "step": 76880 }, { "grad_norm": 0.20504553616046906, "learning_rate": 1.3905504080954734e-05, "loss": 0.0057, "step": 76890 }, { "loss_action": 0.004198369570076466, "loss_total": 0.004198369570076466, "step": 76890 }, { "grad_norm": 0.15277262032032013, "learning_rate": 1.3894063912876454e-05, "loss": 0.0057, "step": 76900 }, { "loss_action": 0.005604294594377279, "loss_total": 0.005604294594377279, "step": 76900 }, { "grad_norm": 0.1781567633152008, "learning_rate": 1.3882627693289046e-05, "loss": 0.0052, "step": 76910 }, { "loss_action": 0.007044515106827021, "loss_total": 0.007044515106827021, "step": 76910 }, { "grad_norm": 0.15683665871620178, "learning_rate": 1.3871195423443183e-05, "loss": 0.0064, "step": 76920 }, { "loss_action": 0.008311865851283073, "loss_total": 0.008311865851283073, "step": 76920 }, { "grad_norm": 0.15396180748939514, "learning_rate": 1.3859767104589044e-05, "loss": 0.0056, "step": 76930 }, { "loss_action": 0.005224599968641996, "loss_total": 0.005224599968641996, "step": 76930 }, { "grad_norm": 0.1710079163312912, "learning_rate": 1.3848342737976467e-05, "loss": 0.0064, "step": 76940 }, { "loss_action": 0.006503968499600887, "loss_total": 0.006503968499600887, "step": 76940 }, { "grad_norm": 0.20617473125457764, "learning_rate": 1.3836922324854757e-05, "loss": 0.0065, "step": 76950 }, { "loss_action": 0.010301412083208561, "loss_total": 0.010301412083208561, "step": 76950 }, { "grad_norm": 0.16378933191299438, "learning_rate": 1.382550586647287e-05, "loss": 0.0069, "step": 76960 }, { "loss_action": 0.004983797203749418, "loss_total": 0.004983797203749418, "step": 76960 }, { "grad_norm": 0.13777844607830048, "learning_rate": 1.3814093364079257e-05, "loss": 0.0059, "step": 76970 }, { "loss_action": 0.00449546379968524, "loss_total": 0.00449546379968524, "step": 76970 }, { "grad_norm": 0.13406822085380554, "learning_rate": 1.3802684818921991e-05, "loss": 0.0064, "step": 76980 }, { "loss_action": 0.0044305878691375256, "loss_total": 0.0044305878691375256, "step": 76980 }, { "grad_norm": 0.18600055575370789, "learning_rate": 1.3791280232248687e-05, "loss": 0.0061, "step": 76990 }, { "loss_action": 0.008848832920193672, "loss_total": 0.008848832920193672, "step": 76990 }, { "grad_norm": 0.15024863183498383, "learning_rate": 1.3779879605306555e-05, "loss": 0.0057, "step": 77000 }, { "loss_action": 0.00562122231349349, "loss_total": 0.00562122231349349, "step": 77000 }, { "grad_norm": 0.1678277552127838, "learning_rate": 1.376848293934232e-05, "loss": 0.0068, "step": 77010 }, { "loss_action": 0.010126871056854725, "loss_total": 0.010126871056854725, "step": 77010 }, { "grad_norm": 0.1408001184463501, "learning_rate": 1.3757090235602316e-05, "loss": 0.0062, "step": 77020 }, { "loss_action": 0.005157175939530134, "loss_total": 0.005157175939530134, "step": 77020 }, { "grad_norm": 0.17191939055919647, "learning_rate": 1.3745701495332447e-05, "loss": 0.0058, "step": 77030 }, { "loss_action": 0.006819600239396095, "loss_total": 0.006819600239396095, "step": 77030 }, { "grad_norm": 0.14913800358772278, "learning_rate": 1.3734316719778145e-05, "loss": 0.0066, "step": 77040 }, { "loss_action": 0.0064688790589571, "loss_total": 0.0064688790589571, "step": 77040 }, { "grad_norm": 0.14444147050380707, "learning_rate": 1.3722935910184454e-05, "loss": 0.0068, "step": 77050 }, { "loss_action": 0.007876158691942692, "loss_total": 0.007876158691942692, "step": 77050 }, { "grad_norm": 0.1725362092256546, "learning_rate": 1.3711559067795921e-05, "loss": 0.0058, "step": 77060 }, { "loss_action": 0.003960432019084692, "loss_total": 0.003960432019084692, "step": 77060 }, { "grad_norm": 0.23317208886146545, "learning_rate": 1.3700186193856756e-05, "loss": 0.0072, "step": 77070 }, { "loss_action": 0.0071667456068098545, "loss_total": 0.0071667456068098545, "step": 77070 }, { "grad_norm": 0.12245599925518036, "learning_rate": 1.368881728961064e-05, "loss": 0.0056, "step": 77080 }, { "loss_action": 0.008034181781113148, "loss_total": 0.008034181781113148, "step": 77080 }, { "grad_norm": 0.13851532340049744, "learning_rate": 1.3677452356300885e-05, "loss": 0.0058, "step": 77090 }, { "loss_action": 0.005997541360557079, "loss_total": 0.005997541360557079, "step": 77090 }, { "grad_norm": 0.17666974663734436, "learning_rate": 1.3666091395170321e-05, "loss": 0.0062, "step": 77100 }, { "loss_action": 0.005243295803666115, "loss_total": 0.005243295803666115, "step": 77100 }, { "grad_norm": 0.11265897750854492, "learning_rate": 1.3654734407461384e-05, "loss": 0.0056, "step": 77110 }, { "loss_action": 0.00373226311057806, "loss_total": 0.00373226311057806, "step": 77110 }, { "grad_norm": 0.1221744641661644, "learning_rate": 1.3643381394416022e-05, "loss": 0.0056, "step": 77120 }, { "loss_action": 0.005187101196497679, "loss_total": 0.005187101196497679, "step": 77120 }, { "grad_norm": 0.17160220444202423, "learning_rate": 1.3632032357275838e-05, "loss": 0.0065, "step": 77130 }, { "loss_action": 0.005072346888482571, "loss_total": 0.005072346888482571, "step": 77130 }, { "grad_norm": 0.1327315717935562, "learning_rate": 1.3620687297281898e-05, "loss": 0.0072, "step": 77140 }, { "loss_action": 0.006826366763561964, "loss_total": 0.006826366763561964, "step": 77140 }, { "grad_norm": 0.16825053095817566, "learning_rate": 1.3609346215674917e-05, "loss": 0.0049, "step": 77150 }, { "loss_action": 0.010027764365077019, "loss_total": 0.010027764365077019, "step": 77150 }, { "grad_norm": 0.16332820057868958, "learning_rate": 1.3598009113695109e-05, "loss": 0.0073, "step": 77160 }, { "loss_action": 0.0074480571784079075, "loss_total": 0.0074480571784079075, "step": 77160 }, { "grad_norm": 0.15088559687137604, "learning_rate": 1.358667599258231e-05, "loss": 0.0057, "step": 77170 }, { "loss_action": 0.008815520443022251, "loss_total": 0.008815520443022251, "step": 77170 }, { "grad_norm": 0.12190453708171844, "learning_rate": 1.357534685357586e-05, "loss": 0.0056, "step": 77180 }, { "loss_action": 0.00883446354418993, "loss_total": 0.00883446354418993, "step": 77180 }, { "grad_norm": 0.19670069217681885, "learning_rate": 1.3564021697914715e-05, "loss": 0.007, "step": 77190 }, { "loss_action": 0.007730285171419382, "loss_total": 0.007730285171419382, "step": 77190 }, { "grad_norm": 0.17538127303123474, "learning_rate": 1.3552700526837381e-05, "loss": 0.0067, "step": 77200 }, { "loss_action": 0.008836151100695133, "loss_total": 0.008836151100695133, "step": 77200 }, { "grad_norm": 0.21016865968704224, "learning_rate": 1.3541383341581925e-05, "loss": 0.0072, "step": 77210 }, { "loss_action": 0.005912354681640863, "loss_total": 0.005912354681640863, "step": 77210 }, { "grad_norm": 0.19218844175338745, "learning_rate": 1.3530070143385965e-05, "loss": 0.0062, "step": 77220 }, { "loss_action": 0.010708741843700409, "loss_total": 0.010708741843700409, "step": 77220 }, { "grad_norm": 0.13113975524902344, "learning_rate": 1.3518760933486702e-05, "loss": 0.0062, "step": 77230 }, { "loss_action": 0.007948054932057858, "loss_total": 0.007948054932057858, "step": 77230 }, { "grad_norm": 0.15510724484920502, "learning_rate": 1.3507455713120908e-05, "loss": 0.0074, "step": 77240 }, { "loss_action": 0.007999284192919731, "loss_total": 0.007999284192919731, "step": 77240 }, { "grad_norm": 0.17084284126758575, "learning_rate": 1.3496154483524876e-05, "loss": 0.006, "step": 77250 }, { "loss_action": 0.005531240254640579, "loss_total": 0.005531240254640579, "step": 77250 }, { "grad_norm": 0.16345304250717163, "learning_rate": 1.3484857245934506e-05, "loss": 0.007, "step": 77260 }, { "loss_action": 0.0035489785950630903, "loss_total": 0.0035489785950630903, "step": 77260 }, { "grad_norm": 0.19275203347206116, "learning_rate": 1.3473564001585248e-05, "loss": 0.005, "step": 77270 }, { "loss_action": 0.0045837038196623325, "loss_total": 0.0045837038196623325, "step": 77270 }, { "grad_norm": 0.146567702293396, "learning_rate": 1.3462274751712129e-05, "loss": 0.007, "step": 77280 }, { "loss_action": 0.009677238762378693, "loss_total": 0.009677238762378693, "step": 77280 }, { "grad_norm": 0.18662770092487335, "learning_rate": 1.3450989497549698e-05, "loss": 0.0065, "step": 77290 }, { "loss_action": 0.004414484836161137, "loss_total": 0.004414484836161137, "step": 77290 }, { "grad_norm": 0.1990504115819931, "learning_rate": 1.3439708240332115e-05, "loss": 0.0061, "step": 77300 }, { "loss_action": 0.0044603245332837105, "loss_total": 0.0044603245332837105, "step": 77300 }, { "grad_norm": 0.21231047809123993, "learning_rate": 1.3428430981293043e-05, "loss": 0.0057, "step": 77310 }, { "loss_action": 0.0059979697689414024, "loss_total": 0.0059979697689414024, "step": 77310 }, { "grad_norm": 0.17449384927749634, "learning_rate": 1.3417157721665808e-05, "loss": 0.0067, "step": 77320 }, { "loss_action": 0.004499509464949369, "loss_total": 0.004499509464949369, "step": 77320 }, { "grad_norm": 0.15342256426811218, "learning_rate": 1.3405888462683186e-05, "loss": 0.0053, "step": 77330 }, { "loss_action": 0.006457889452576637, "loss_total": 0.006457889452576637, "step": 77330 }, { "grad_norm": 0.12652701139450073, "learning_rate": 1.3394623205577595e-05, "loss": 0.0066, "step": 77340 }, { "loss_action": 0.005238375160843134, "loss_total": 0.005238375160843134, "step": 77340 }, { "grad_norm": 0.1560906320810318, "learning_rate": 1.3383361951580963e-05, "loss": 0.0063, "step": 77350 }, { "loss_action": 0.005070519167929888, "loss_total": 0.005070519167929888, "step": 77350 }, { "grad_norm": 0.12561403214931488, "learning_rate": 1.337210470192483e-05, "loss": 0.0058, "step": 77360 }, { "loss_action": 0.008277513086795807, "loss_total": 0.008277513086795807, "step": 77360 }, { "grad_norm": 0.1381331980228424, "learning_rate": 1.3360851457840245e-05, "loss": 0.0064, "step": 77370 }, { "loss_action": 0.0034520362969487906, "loss_total": 0.0034520362969487906, "step": 77370 }, { "grad_norm": 0.1482233852148056, "learning_rate": 1.3349602220557856e-05, "loss": 0.006, "step": 77380 }, { "loss_action": 0.005903414450585842, "loss_total": 0.005903414450585842, "step": 77380 }, { "grad_norm": 0.15227103233337402, "learning_rate": 1.3338356991307865e-05, "loss": 0.006, "step": 77390 }, { "loss_action": 0.005841346457600594, "loss_total": 0.005841346457600594, "step": 77390 }, { "grad_norm": 0.12566380202770233, "learning_rate": 1.3327115771320048e-05, "loss": 0.0058, "step": 77400 }, { "loss_action": 0.007592980284243822, "loss_total": 0.007592980284243822, "step": 77400 }, { "grad_norm": 0.14802302420139313, "learning_rate": 1.3315878561823697e-05, "loss": 0.0059, "step": 77410 }, { "loss_action": 0.00403360091149807, "loss_total": 0.00403360091149807, "step": 77410 }, { "grad_norm": 0.12295524030923843, "learning_rate": 1.330464536404773e-05, "loss": 0.0052, "step": 77420 }, { "loss_action": 0.01079592015594244, "loss_total": 0.01079592015594244, "step": 77420 }, { "grad_norm": 0.15608398616313934, "learning_rate": 1.3293416179220563e-05, "loss": 0.006, "step": 77430 }, { "loss_action": 0.009401988238096237, "loss_total": 0.009401988238096237, "step": 77430 }, { "grad_norm": 0.13951091468334198, "learning_rate": 1.328219100857021e-05, "loss": 0.0073, "step": 77440 }, { "loss_action": 0.004982606042176485, "loss_total": 0.004982606042176485, "step": 77440 }, { "grad_norm": 0.15242333710193634, "learning_rate": 1.327096985332425e-05, "loss": 0.0064, "step": 77450 }, { "loss_action": 0.0065568117424845695, "loss_total": 0.0065568117424845695, "step": 77450 }, { "grad_norm": 0.15451769530773163, "learning_rate": 1.3259752714709816e-05, "loss": 0.0055, "step": 77460 }, { "loss_action": 0.00634315051138401, "loss_total": 0.00634315051138401, "step": 77460 }, { "grad_norm": 0.14057594537734985, "learning_rate": 1.3248539593953569e-05, "loss": 0.0056, "step": 77470 }, { "loss_action": 0.004356739576905966, "loss_total": 0.004356739576905966, "step": 77470 }, { "grad_norm": 0.12030977010726929, "learning_rate": 1.323733049228178e-05, "loss": 0.0047, "step": 77480 }, { "loss_action": 0.005357531365007162, "loss_total": 0.005357531365007162, "step": 77480 }, { "grad_norm": 0.1336912363767624, "learning_rate": 1.3226125410920276e-05, "loss": 0.0056, "step": 77490 }, { "loss_action": 0.005790266674011946, "loss_total": 0.005790266674011946, "step": 77490 }, { "grad_norm": 0.1215607151389122, "learning_rate": 1.3214924351094388e-05, "loss": 0.0052, "step": 77500 }, { "loss_action": 0.005727858282625675, "loss_total": 0.005727858282625675, "step": 77500 }, { "grad_norm": 0.13966436684131622, "learning_rate": 1.3203727314029069e-05, "loss": 0.0054, "step": 77510 }, { "loss_action": 0.005342166405171156, "loss_total": 0.005342166405171156, "step": 77510 }, { "grad_norm": 0.14822910726070404, "learning_rate": 1.3192534300948811e-05, "loss": 0.0071, "step": 77520 }, { "loss_action": 0.006895596627146006, "loss_total": 0.006895596627146006, "step": 77520 }, { "grad_norm": 0.1849754899740219, "learning_rate": 1.3181345313077675e-05, "loss": 0.0061, "step": 77530 }, { "loss_action": 0.005026583094149828, "loss_total": 0.005026583094149828, "step": 77530 }, { "grad_norm": 0.1339840441942215, "learning_rate": 1.3170160351639243e-05, "loss": 0.0051, "step": 77540 }, { "loss_action": 0.004110970068722963, "loss_total": 0.004110970068722963, "step": 77540 }, { "grad_norm": 0.14084696769714355, "learning_rate": 1.3158979417856721e-05, "loss": 0.0062, "step": 77550 }, { "loss_action": 0.004898184444755316, "loss_total": 0.004898184444755316, "step": 77550 }, { "grad_norm": 0.1889594942331314, "learning_rate": 1.31478025129528e-05, "loss": 0.0069, "step": 77560 }, { "loss_action": 0.008484750986099243, "loss_total": 0.008484750986099243, "step": 77560 }, { "grad_norm": 0.16882139444351196, "learning_rate": 1.3136629638149794e-05, "loss": 0.0059, "step": 77570 }, { "loss_action": 0.006487906910479069, "loss_total": 0.006487906910479069, "step": 77570 }, { "grad_norm": 0.1409337967634201, "learning_rate": 1.3125460794669547e-05, "loss": 0.0064, "step": 77580 }, { "loss_action": 0.009158174507319927, "loss_total": 0.009158174507319927, "step": 77580 }, { "grad_norm": 0.12326069921255112, "learning_rate": 1.3114295983733483e-05, "loss": 0.006, "step": 77590 }, { "loss_action": 0.005328429397195578, "loss_total": 0.005328429397195578, "step": 77590 }, { "grad_norm": 0.11515387147665024, "learning_rate": 1.3103135206562534e-05, "loss": 0.0055, "step": 77600 }, { "loss_action": 0.003952207043766975, "loss_total": 0.003952207043766975, "step": 77600 }, { "grad_norm": 0.12642814218997955, "learning_rate": 1.3091978464377264e-05, "loss": 0.0055, "step": 77610 }, { "loss_action": 0.005481469910591841, "loss_total": 0.005481469910591841, "step": 77610 }, { "grad_norm": 0.16880150139331818, "learning_rate": 1.3080825758397724e-05, "loss": 0.0064, "step": 77620 }, { "loss_action": 0.008084993809461594, "loss_total": 0.008084993809461594, "step": 77620 }, { "grad_norm": 0.14683711528778076, "learning_rate": 1.3069677089843568e-05, "loss": 0.0068, "step": 77630 }, { "loss_action": 0.00855968240648508, "loss_total": 0.00855968240648508, "step": 77630 }, { "grad_norm": 0.16192491352558136, "learning_rate": 1.305853245993401e-05, "loss": 0.0057, "step": 77640 }, { "loss_action": 0.005019265227019787, "loss_total": 0.005019265227019787, "step": 77640 }, { "grad_norm": 0.21670463681221008, "learning_rate": 1.3047391869887809e-05, "loss": 0.006, "step": 77650 }, { "loss_action": 0.008280589245259762, "loss_total": 0.008280589245259762, "step": 77650 }, { "grad_norm": 0.17554828524589539, "learning_rate": 1.3036255320923263e-05, "loss": 0.0062, "step": 77660 }, { "loss_action": 0.0067831543274223804, "loss_total": 0.0067831543274223804, "step": 77660 }, { "grad_norm": 0.181810662150383, "learning_rate": 1.3025122814258273e-05, "loss": 0.0059, "step": 77670 }, { "loss_action": 0.006204735953360796, "loss_total": 0.006204735953360796, "step": 77670 }, { "grad_norm": 0.17382746934890747, "learning_rate": 1.3013994351110249e-05, "loss": 0.0059, "step": 77680 }, { "loss_action": 0.003364808391779661, "loss_total": 0.003364808391779661, "step": 77680 }, { "grad_norm": 0.1564818024635315, "learning_rate": 1.3002869932696194e-05, "loss": 0.0069, "step": 77690 }, { "loss_action": 0.004575985483825207, "loss_total": 0.004575985483825207, "step": 77690 }, { "grad_norm": 0.11777979135513306, "learning_rate": 1.2991749560232664e-05, "loss": 0.0057, "step": 77700 }, { "loss_action": 0.00471129035577178, "loss_total": 0.00471129035577178, "step": 77700 }, { "grad_norm": 0.1200878843665123, "learning_rate": 1.2980633234935768e-05, "loss": 0.0051, "step": 77710 }, { "loss_action": 0.0039182729087769985, "loss_total": 0.0039182729087769985, "step": 77710 }, { "grad_norm": 0.11563804745674133, "learning_rate": 1.2969520958021153e-05, "loss": 0.0057, "step": 77720 }, { "loss_action": 0.005237341858446598, "loss_total": 0.005237341858446598, "step": 77720 }, { "grad_norm": 0.10889609158039093, "learning_rate": 1.295841273070405e-05, "loss": 0.0049, "step": 77730 }, { "loss_action": 0.005419938825070858, "loss_total": 0.005419938825070858, "step": 77730 }, { "grad_norm": 0.141768679022789, "learning_rate": 1.2947308554199255e-05, "loss": 0.0053, "step": 77740 }, { "loss_action": 0.004937347024679184, "loss_total": 0.004937347024679184, "step": 77740 }, { "grad_norm": 0.20223468542099, "learning_rate": 1.2936208429721075e-05, "loss": 0.0053, "step": 77750 }, { "loss_action": 0.006822874303907156, "loss_total": 0.006822874303907156, "step": 77750 }, { "grad_norm": 0.13440771400928497, "learning_rate": 1.2925112358483416e-05, "loss": 0.0054, "step": 77760 }, { "loss_action": 0.006193745881319046, "loss_total": 0.006193745881319046, "step": 77760 }, { "grad_norm": 0.15831640362739563, "learning_rate": 1.2914020341699728e-05, "loss": 0.0062, "step": 77770 }, { "loss_action": 0.005422721151262522, "loss_total": 0.005422721151262522, "step": 77770 }, { "grad_norm": 0.17179477214813232, "learning_rate": 1.2902932380583032e-05, "loss": 0.0057, "step": 77780 }, { "loss_action": 0.0042426735162734985, "loss_total": 0.0042426735162734985, "step": 77780 }, { "grad_norm": 0.15423262119293213, "learning_rate": 1.2891848476345863e-05, "loss": 0.0051, "step": 77790 }, { "loss_action": 0.005671616178005934, "loss_total": 0.005671616178005934, "step": 77790 }, { "grad_norm": 0.11578977853059769, "learning_rate": 1.2880768630200368e-05, "loss": 0.0055, "step": 77800 }, { "loss_action": 0.005249921698123217, "loss_total": 0.005249921698123217, "step": 77800 }, { "grad_norm": 0.1294509619474411, "learning_rate": 1.286969284335819e-05, "loss": 0.0049, "step": 77810 }, { "loss_action": 0.004435282666236162, "loss_total": 0.004435282666236162, "step": 77810 }, { "grad_norm": 0.12433281540870667, "learning_rate": 1.2858621117030578e-05, "loss": 0.0055, "step": 77820 }, { "loss_action": 0.01409081369638443, "loss_total": 0.01409081369638443, "step": 77820 }, { "grad_norm": 0.18365350365638733, "learning_rate": 1.2847553452428324e-05, "loss": 0.0065, "step": 77830 }, { "loss_action": 0.004101904574781656, "loss_total": 0.004101904574781656, "step": 77830 }, { "grad_norm": 0.16476844251155853, "learning_rate": 1.283648985076178e-05, "loss": 0.0054, "step": 77840 }, { "loss_action": 0.009111685678362846, "loss_total": 0.009111685678362846, "step": 77840 }, { "grad_norm": 0.17392019927501678, "learning_rate": 1.2825430313240817e-05, "loss": 0.0065, "step": 77850 }, { "loss_action": 0.00775862718001008, "loss_total": 0.00775862718001008, "step": 77850 }, { "grad_norm": 0.1344592571258545, "learning_rate": 1.281437484107491e-05, "loss": 0.0061, "step": 77860 }, { "loss_action": 0.005748224910348654, "loss_total": 0.005748224910348654, "step": 77860 }, { "grad_norm": 0.16032902896404266, "learning_rate": 1.2803323435473058e-05, "loss": 0.0059, "step": 77870 }, { "loss_action": 0.005843583028763533, "loss_total": 0.005843583028763533, "step": 77870 }, { "grad_norm": 0.17552398145198822, "learning_rate": 1.2792276097643841e-05, "loss": 0.0056, "step": 77880 }, { "loss_action": 0.0029569619800895452, "loss_total": 0.0029569619800895452, "step": 77880 }, { "grad_norm": 0.18731462955474854, "learning_rate": 1.2781232828795342e-05, "loss": 0.0056, "step": 77890 }, { "loss_action": 0.005641608498990536, "loss_total": 0.005641608498990536, "step": 77890 }, { "grad_norm": 0.14443211257457733, "learning_rate": 1.2770193630135292e-05, "loss": 0.006, "step": 77900 }, { "loss_action": 0.005690511781722307, "loss_total": 0.005690511781722307, "step": 77900 }, { "grad_norm": 0.14354842901229858, "learning_rate": 1.2759158502870877e-05, "loss": 0.0069, "step": 77910 }, { "loss_action": 0.005576827097684145, "loss_total": 0.005576827097684145, "step": 77910 }, { "grad_norm": 0.1423214226961136, "learning_rate": 1.2748127448208913e-05, "loss": 0.0061, "step": 77920 }, { "loss_action": 0.0036940646823495626, "loss_total": 0.0036940646823495626, "step": 77920 }, { "grad_norm": 0.12061173468828201, "learning_rate": 1.2737100467355706e-05, "loss": 0.005, "step": 77930 }, { "loss_action": 0.005808946210891008, "loss_total": 0.005808946210891008, "step": 77930 }, { "grad_norm": 0.1853620558977127, "learning_rate": 1.2726077561517169e-05, "loss": 0.006, "step": 77940 }, { "loss_action": 0.005159955937415361, "loss_total": 0.005159955937415361, "step": 77940 }, { "grad_norm": 0.13666246831417084, "learning_rate": 1.2715058731898755e-05, "loss": 0.0058, "step": 77950 }, { "loss_action": 0.008244003169238567, "loss_total": 0.008244003169238567, "step": 77950 }, { "grad_norm": 0.16896867752075195, "learning_rate": 1.2704043979705471e-05, "loss": 0.0056, "step": 77960 }, { "loss_action": 0.007097902242094278, "loss_total": 0.007097902242094278, "step": 77960 }, { "grad_norm": 0.1390240490436554, "learning_rate": 1.269303330614185e-05, "loss": 0.0067, "step": 77970 }, { "loss_action": 0.003912033978849649, "loss_total": 0.003912033978849649, "step": 77970 }, { "grad_norm": 0.15332147479057312, "learning_rate": 1.2682026712412015e-05, "loss": 0.0052, "step": 77980 }, { "loss_action": 0.005687656346708536, "loss_total": 0.005687656346708536, "step": 77980 }, { "grad_norm": 0.2007354199886322, "learning_rate": 1.2671024199719644e-05, "loss": 0.0055, "step": 77990 }, { "loss_action": 0.00980452448129654, "loss_total": 0.00980452448129654, "step": 77990 }, { "grad_norm": 0.1492786407470703, "learning_rate": 1.2660025769267936e-05, "loss": 0.0056, "step": 78000 }, { "loss_action": 0.006616636645048857, "loss_total": 0.006616636645048857, "step": 78000 }, { "grad_norm": 0.12177874147891998, "learning_rate": 1.2649031422259667e-05, "loss": 0.005, "step": 78010 }, { "loss_action": 0.005289384163916111, "loss_total": 0.005289384163916111, "step": 78010 }, { "grad_norm": 0.19490936398506165, "learning_rate": 1.2638041159897163e-05, "loss": 0.0065, "step": 78020 }, { "loss_action": 0.005054678302258253, "loss_total": 0.005054678302258253, "step": 78020 }, { "grad_norm": 0.17011822760105133, "learning_rate": 1.262705498338232e-05, "loss": 0.0059, "step": 78030 }, { "loss_action": 0.007031058426946402, "loss_total": 0.007031058426946402, "step": 78030 }, { "grad_norm": 0.15798285603523254, "learning_rate": 1.2616072893916542e-05, "loss": 0.0052, "step": 78040 }, { "loss_action": 0.0052408785559237, "loss_total": 0.0052408785559237, "step": 78040 }, { "grad_norm": 0.12587572634220123, "learning_rate": 1.2605094892700836e-05, "loss": 0.0058, "step": 78050 }, { "loss_action": 0.006968036759644747, "loss_total": 0.006968036759644747, "step": 78050 }, { "grad_norm": 0.14070968329906464, "learning_rate": 1.259412098093572e-05, "loss": 0.0067, "step": 78060 }, { "loss_action": 0.005328969098627567, "loss_total": 0.005328969098627567, "step": 78060 }, { "grad_norm": 0.13047559559345245, "learning_rate": 1.258315115982131e-05, "loss": 0.0057, "step": 78070 }, { "loss_action": 0.0054966602474451065, "loss_total": 0.0054966602474451065, "step": 78070 }, { "grad_norm": 0.13525712490081787, "learning_rate": 1.2572185430557203e-05, "loss": 0.005, "step": 78080 }, { "loss_action": 0.007510087918490171, "loss_total": 0.007510087918490171, "step": 78080 }, { "grad_norm": 0.13931280374526978, "learning_rate": 1.2561223794342659e-05, "loss": 0.006, "step": 78090 }, { "loss_action": 0.006230364087969065, "loss_total": 0.006230364087969065, "step": 78090 }, { "grad_norm": 0.1879757195711136, "learning_rate": 1.255026625237637e-05, "loss": 0.0063, "step": 78100 }, { "loss_action": 0.0055632623843848705, "loss_total": 0.0055632623843848705, "step": 78100 }, { "grad_norm": 0.12992359697818756, "learning_rate": 1.2539312805856678e-05, "loss": 0.0055, "step": 78110 }, { "loss_action": 0.005049539729952812, "loss_total": 0.005049539729952812, "step": 78110 }, { "grad_norm": 0.16506434977054596, "learning_rate": 1.25283634559814e-05, "loss": 0.0057, "step": 78120 }, { "loss_action": 0.004718753043562174, "loss_total": 0.004718753043562174, "step": 78120 }, { "grad_norm": 0.13936324417591095, "learning_rate": 1.2517418203947972e-05, "loss": 0.0056, "step": 78130 }, { "loss_action": 0.0058721560053527355, "loss_total": 0.0058721560053527355, "step": 78130 }, { "grad_norm": 0.16507038474082947, "learning_rate": 1.2506477050953308e-05, "loss": 0.0062, "step": 78140 }, { "loss_action": 0.004733061883598566, "loss_total": 0.004733061883598566, "step": 78140 }, { "grad_norm": 0.1615828424692154, "learning_rate": 1.2495539998193972e-05, "loss": 0.0058, "step": 78150 }, { "loss_action": 0.006090700160712004, "loss_total": 0.006090700160712004, "step": 78150 }, { "grad_norm": 0.22573713958263397, "learning_rate": 1.2484607046865975e-05, "loss": 0.0057, "step": 78160 }, { "loss_action": 0.010674893856048584, "loss_total": 0.010674893856048584, "step": 78160 }, { "grad_norm": 0.15266403555870056, "learning_rate": 1.2473678198164968e-05, "loss": 0.0061, "step": 78170 }, { "loss_action": 0.008202663622796535, "loss_total": 0.008202663622796535, "step": 78170 }, { "grad_norm": 0.1373363882303238, "learning_rate": 1.2462753453286075e-05, "loss": 0.0058, "step": 78180 }, { "loss_action": 0.009659769013524055, "loss_total": 0.009659769013524055, "step": 78180 }, { "grad_norm": 0.1603127270936966, "learning_rate": 1.2451832813424031e-05, "loss": 0.0066, "step": 78190 }, { "loss_action": 0.004257558844983578, "loss_total": 0.004257558844983578, "step": 78190 }, { "grad_norm": 0.16535452008247375, "learning_rate": 1.2440916279773095e-05, "loss": 0.0062, "step": 78200 }, { "loss_action": 0.0038323283661156893, "loss_total": 0.0038323283661156893, "step": 78200 }, { "grad_norm": 0.13342879712581635, "learning_rate": 1.2430003853527101e-05, "loss": 0.0053, "step": 78210 }, { "loss_action": 0.007710238453000784, "loss_total": 0.007710238453000784, "step": 78210 }, { "grad_norm": 0.1348450630903244, "learning_rate": 1.2419095535879383e-05, "loss": 0.0055, "step": 78220 }, { "loss_action": 0.004683957435190678, "loss_total": 0.004683957435190678, "step": 78220 }, { "grad_norm": 0.15621620416641235, "learning_rate": 1.2408191328022878e-05, "loss": 0.0057, "step": 78230 }, { "loss_action": 0.0036357019562274218, "loss_total": 0.0036357019562274218, "step": 78230 }, { "grad_norm": 0.09775499999523163, "learning_rate": 1.2397291231150066e-05, "loss": 0.0049, "step": 78240 }, { "loss_action": 0.004860322922468185, "loss_total": 0.004860322922468185, "step": 78240 }, { "grad_norm": 0.12663380801677704, "learning_rate": 1.2386395246452937e-05, "loss": 0.0049, "step": 78250 }, { "loss_action": 0.005602418445050716, "loss_total": 0.005602418445050716, "step": 78250 }, { "grad_norm": 0.18313874304294586, "learning_rate": 1.2375503375123083e-05, "loss": 0.0062, "step": 78260 }, { "loss_action": 0.006402816157788038, "loss_total": 0.006402816157788038, "step": 78260 }, { "grad_norm": 0.12157838046550751, "learning_rate": 1.2364615618351583e-05, "loss": 0.0055, "step": 78270 }, { "loss_action": 0.0076221888884902, "loss_total": 0.0076221888884902, "step": 78270 }, { "grad_norm": 0.18037530779838562, "learning_rate": 1.2353731977329169e-05, "loss": 0.0067, "step": 78280 }, { "loss_action": 0.00446794368326664, "loss_total": 0.00446794368326664, "step": 78280 }, { "grad_norm": 0.16376835107803345, "learning_rate": 1.2342852453246007e-05, "loss": 0.0057, "step": 78290 }, { "loss_action": 0.005765574052929878, "loss_total": 0.005765574052929878, "step": 78290 }, { "grad_norm": 0.2001468986272812, "learning_rate": 1.2331977047291898e-05, "loss": 0.0055, "step": 78300 }, { "loss_action": 0.005219075828790665, "loss_total": 0.005219075828790665, "step": 78300 }, { "grad_norm": 0.1622590571641922, "learning_rate": 1.2321105760656137e-05, "loss": 0.0059, "step": 78310 }, { "loss_action": 0.014007568359375, "loss_total": 0.014007568359375, "step": 78310 }, { "grad_norm": 0.1639108806848526, "learning_rate": 1.2310238594527613e-05, "loss": 0.0065, "step": 78320 }, { "loss_action": 0.007441684138029814, "loss_total": 0.007441684138029814, "step": 78320 }, { "grad_norm": 0.13921517133712769, "learning_rate": 1.2299375550094693e-05, "loss": 0.0057, "step": 78330 }, { "loss_action": 0.006870461627840996, "loss_total": 0.006870461627840996, "step": 78330 }, { "grad_norm": 0.16930924355983734, "learning_rate": 1.2288516628545421e-05, "loss": 0.0062, "step": 78340 }, { "loss_action": 0.004478602670133114, "loss_total": 0.004478602670133114, "step": 78340 }, { "grad_norm": 0.14325447380542755, "learning_rate": 1.2277661831067255e-05, "loss": 0.0049, "step": 78350 }, { "loss_action": 0.006306180264800787, "loss_total": 0.006306180264800787, "step": 78350 }, { "grad_norm": 0.13036230206489563, "learning_rate": 1.2266811158847286e-05, "loss": 0.0063, "step": 78360 }, { "loss_action": 0.004790268372744322, "loss_total": 0.004790268372744322, "step": 78360 }, { "grad_norm": 0.140047088265419, "learning_rate": 1.2255964613072107e-05, "loss": 0.0063, "step": 78370 }, { "loss_action": 0.004304947797209024, "loss_total": 0.004304947797209024, "step": 78370 }, { "grad_norm": 0.18818071484565735, "learning_rate": 1.2245122194927905e-05, "loss": 0.0061, "step": 78380 }, { "loss_action": 0.0053072343580424786, "loss_total": 0.0053072343580424786, "step": 78380 }, { "grad_norm": 0.14755642414093018, "learning_rate": 1.2234283905600364e-05, "loss": 0.0058, "step": 78390 }, { "loss_action": 0.004989338107407093, "loss_total": 0.004989338107407093, "step": 78390 }, { "grad_norm": 0.1561041623353958, "learning_rate": 1.222344974627475e-05, "loss": 0.0058, "step": 78400 }, { "loss_action": 0.006637164391577244, "loss_total": 0.006637164391577244, "step": 78400 }, { "grad_norm": 0.15925636887550354, "learning_rate": 1.2212619718135875e-05, "loss": 0.0053, "step": 78410 }, { "loss_action": 0.005159552674740553, "loss_total": 0.005159552674740553, "step": 78410 }, { "grad_norm": 0.24523302912712097, "learning_rate": 1.2201793822368118e-05, "loss": 0.0069, "step": 78420 }, { "loss_action": 0.005684432573616505, "loss_total": 0.005684432573616505, "step": 78420 }, { "grad_norm": 0.17712463438510895, "learning_rate": 1.2190972060155337e-05, "loss": 0.0068, "step": 78430 }, { "loss_action": 0.007477637846022844, "loss_total": 0.007477637846022844, "step": 78430 }, { "grad_norm": 0.13727758824825287, "learning_rate": 1.2180154432681013e-05, "loss": 0.0062, "step": 78440 }, { "loss_action": 0.004546547308564186, "loss_total": 0.004546547308564186, "step": 78440 }, { "grad_norm": 0.4362536668777466, "learning_rate": 1.2169340941128148e-05, "loss": 0.0068, "step": 78450 }, { "loss_action": 0.003993883263319731, "loss_total": 0.003993883263319731, "step": 78450 }, { "grad_norm": 0.16340214014053345, "learning_rate": 1.2158531586679267e-05, "loss": 0.0056, "step": 78460 }, { "loss_action": 0.009149138815701008, "loss_total": 0.009149138815701008, "step": 78460 }, { "grad_norm": 0.12427660822868347, "learning_rate": 1.2147726370516477e-05, "loss": 0.0068, "step": 78470 }, { "loss_action": 0.004719467833638191, "loss_total": 0.004719467833638191, "step": 78470 }, { "grad_norm": 0.12590959668159485, "learning_rate": 1.2136925293821422e-05, "loss": 0.0053, "step": 78480 }, { "loss_action": 0.004943392239511013, "loss_total": 0.004943392239511013, "step": 78480 }, { "grad_norm": 0.1356634944677353, "learning_rate": 1.2126128357775306e-05, "loss": 0.0055, "step": 78490 }, { "loss_action": 0.004343142732977867, "loss_total": 0.004343142732977867, "step": 78490 }, { "grad_norm": 0.1442410796880722, "learning_rate": 1.2115335563558838e-05, "loss": 0.0062, "step": 78500 }, { "loss_action": 0.006097028497606516, "loss_total": 0.006097028497606516, "step": 78500 }, { "grad_norm": 0.14355553686618805, "learning_rate": 1.2104546912352327e-05, "loss": 0.0057, "step": 78510 }, { "loss_action": 0.007425791583955288, "loss_total": 0.007425791583955288, "step": 78510 }, { "grad_norm": 0.16212591528892517, "learning_rate": 1.2093762405335557e-05, "loss": 0.0063, "step": 78520 }, { "loss_action": 0.005365999415516853, "loss_total": 0.005365999415516853, "step": 78520 }, { "grad_norm": 0.1526017040014267, "learning_rate": 1.2082982043687974e-05, "loss": 0.0064, "step": 78530 }, { "loss_action": 0.003627372207120061, "loss_total": 0.003627372207120061, "step": 78530 }, { "grad_norm": 0.15885601937770844, "learning_rate": 1.207220582858845e-05, "loss": 0.0058, "step": 78540 }, { "loss_action": 0.005566389299929142, "loss_total": 0.005566389299929142, "step": 78540 }, { "grad_norm": 0.2041444629430771, "learning_rate": 1.206143376121549e-05, "loss": 0.0057, "step": 78550 }, { "loss_action": 0.004822262097150087, "loss_total": 0.004822262097150087, "step": 78550 }, { "grad_norm": 0.1424316018819809, "learning_rate": 1.2050665842747078e-05, "loss": 0.0052, "step": 78560 }, { "loss_action": 0.004081358667463064, "loss_total": 0.004081358667463064, "step": 78560 }, { "grad_norm": 0.11929091811180115, "learning_rate": 1.2039902074360804e-05, "loss": 0.0053, "step": 78570 }, { "loss_action": 0.004082727711647749, "loss_total": 0.004082727711647749, "step": 78570 }, { "grad_norm": 0.11654102802276611, "learning_rate": 1.2029142457233755e-05, "loss": 0.0055, "step": 78580 }, { "loss_action": 0.00352481659501791, "loss_total": 0.00352481659501791, "step": 78580 }, { "grad_norm": 0.17361903190612793, "learning_rate": 1.2018386992542601e-05, "loss": 0.0055, "step": 78590 }, { "loss_action": 0.0038959698285907507, "loss_total": 0.0038959698285907507, "step": 78590 }, { "grad_norm": 0.13064362108707428, "learning_rate": 1.2007635681463542e-05, "loss": 0.0046, "step": 78600 }, { "loss_action": 0.00847944151610136, "loss_total": 0.00847944151610136, "step": 78600 }, { "grad_norm": 0.13350048661231995, "learning_rate": 1.1996888525172334e-05, "loss": 0.0059, "step": 78610 }, { "loss_action": 0.006328854244202375, "loss_total": 0.006328854244202375, "step": 78610 }, { "grad_norm": 0.15217074751853943, "learning_rate": 1.198614552484425e-05, "loss": 0.0059, "step": 78620 }, { "loss_action": 0.005599183030426502, "loss_total": 0.005599183030426502, "step": 78620 }, { "grad_norm": 0.11957979202270508, "learning_rate": 1.197540668165415e-05, "loss": 0.0051, "step": 78630 }, { "loss_action": 0.006489407271146774, "loss_total": 0.006489407271146774, "step": 78630 }, { "grad_norm": 0.11714497208595276, "learning_rate": 1.1964671996776395e-05, "loss": 0.0054, "step": 78640 }, { "loss_action": 0.0052807568572461605, "loss_total": 0.0052807568572461605, "step": 78640 }, { "grad_norm": 0.13098491728305817, "learning_rate": 1.1953941471384922e-05, "loss": 0.0049, "step": 78650 }, { "loss_action": 0.004195473622530699, "loss_total": 0.004195473622530699, "step": 78650 }, { "grad_norm": 0.1368018239736557, "learning_rate": 1.1943215106653205e-05, "loss": 0.0067, "step": 78660 }, { "loss_action": 0.006762522738426924, "loss_total": 0.006762522738426924, "step": 78660 }, { "grad_norm": 0.13302266597747803, "learning_rate": 1.193249290375429e-05, "loss": 0.0065, "step": 78670 }, { "loss_action": 0.004372992552816868, "loss_total": 0.004372992552816868, "step": 78670 }, { "grad_norm": 0.14520666003227234, "learning_rate": 1.1921774863860696e-05, "loss": 0.0052, "step": 78680 }, { "loss_action": 0.0035312594845891, "loss_total": 0.0035312594845891, "step": 78680 }, { "grad_norm": 0.16962413489818573, "learning_rate": 1.1911060988144556e-05, "loss": 0.0055, "step": 78690 }, { "loss_action": 0.008172404021024704, "loss_total": 0.008172404021024704, "step": 78690 }, { "grad_norm": 0.19065222144126892, "learning_rate": 1.1900351277777533e-05, "loss": 0.0057, "step": 78700 }, { "loss_action": 0.006450607441365719, "loss_total": 0.006450607441365719, "step": 78700 }, { "grad_norm": 0.17526604235172272, "learning_rate": 1.1889645733930798e-05, "loss": 0.0064, "step": 78710 }, { "loss_action": 0.00771102961152792, "loss_total": 0.00771102961152792, "step": 78710 }, { "grad_norm": 0.16381913423538208, "learning_rate": 1.1878944357775107e-05, "loss": 0.0065, "step": 78720 }, { "loss_action": 0.005740226246416569, "loss_total": 0.005740226246416569, "step": 78720 }, { "grad_norm": 0.18957094848155975, "learning_rate": 1.1868247150480749e-05, "loss": 0.0063, "step": 78730 }, { "loss_action": 0.004985871259123087, "loss_total": 0.004985871259123087, "step": 78730 }, { "grad_norm": 0.16876843571662903, "learning_rate": 1.1857554113217567e-05, "loss": 0.0064, "step": 78740 }, { "loss_action": 0.0035276308190077543, "loss_total": 0.0035276308190077543, "step": 78740 }, { "grad_norm": 0.13119831681251526, "learning_rate": 1.1846865247154903e-05, "loss": 0.005, "step": 78750 }, { "loss_action": 0.00788787379860878, "loss_total": 0.00788787379860878, "step": 78750 }, { "grad_norm": 0.11842550337314606, "learning_rate": 1.1836180553461711e-05, "loss": 0.0061, "step": 78760 }, { "loss_action": 0.007927127182483673, "loss_total": 0.007927127182483673, "step": 78760 }, { "grad_norm": 0.12920346856117249, "learning_rate": 1.1825500033306419e-05, "loss": 0.0059, "step": 78770 }, { "loss_action": 0.005343257915228605, "loss_total": 0.005343257915228605, "step": 78770 }, { "grad_norm": 0.1756259948015213, "learning_rate": 1.1814823687857052e-05, "loss": 0.0063, "step": 78780 }, { "loss_action": 0.003467605682089925, "loss_total": 0.003467605682089925, "step": 78780 }, { "grad_norm": 0.11902633309364319, "learning_rate": 1.1804151518281153e-05, "loss": 0.0049, "step": 78790 }, { "loss_action": 0.005143305286765099, "loss_total": 0.005143305286765099, "step": 78790 }, { "grad_norm": 0.12455886602401733, "learning_rate": 1.179348352574583e-05, "loss": 0.0054, "step": 78800 }, { "loss_action": 0.010840298607945442, "loss_total": 0.010840298607945442, "step": 78800 }, { "grad_norm": 0.16664059460163116, "learning_rate": 1.1782819711417697e-05, "loss": 0.0058, "step": 78810 }, { "loss_action": 0.005738509353250265, "loss_total": 0.005738509353250265, "step": 78810 }, { "grad_norm": 0.13137789070606232, "learning_rate": 1.1772160076462951e-05, "loss": 0.0052, "step": 78820 }, { "loss_action": 0.006513519212603569, "loss_total": 0.006513519212603569, "step": 78820 }, { "grad_norm": 0.11522503942251205, "learning_rate": 1.1761504622047293e-05, "loss": 0.0065, "step": 78830 }, { "loss_action": 0.006609563250094652, "loss_total": 0.006609563250094652, "step": 78830 }, { "grad_norm": 0.2713662087917328, "learning_rate": 1.1750853349335999e-05, "loss": 0.0059, "step": 78840 }, { "loss_action": 0.005566680338233709, "loss_total": 0.005566680338233709, "step": 78840 }, { "grad_norm": 0.17650924623012543, "learning_rate": 1.1740206259493874e-05, "loss": 0.0054, "step": 78850 }, { "loss_action": 0.004424120765179396, "loss_total": 0.004424120765179396, "step": 78850 }, { "grad_norm": 0.13879232108592987, "learning_rate": 1.1729563353685286e-05, "loss": 0.0052, "step": 78860 }, { "loss_action": 0.004725737497210503, "loss_total": 0.004725737497210503, "step": 78860 }, { "grad_norm": 0.11723493784666061, "learning_rate": 1.1718924633074091e-05, "loss": 0.0051, "step": 78870 }, { "loss_action": 0.007731706835329533, "loss_total": 0.007731706835329533, "step": 78870 }, { "grad_norm": 0.13762131333351135, "learning_rate": 1.1708290098823765e-05, "loss": 0.0069, "step": 78880 }, { "loss_action": 0.007077767979353666, "loss_total": 0.007077767979353666, "step": 78880 }, { "grad_norm": 0.1232549175620079, "learning_rate": 1.1697659752097245e-05, "loss": 0.0058, "step": 78890 }, { "loss_action": 0.009048199281096458, "loss_total": 0.009048199281096458, "step": 78890 }, { "grad_norm": 0.1429532766342163, "learning_rate": 1.1687033594057068e-05, "loss": 0.0068, "step": 78900 }, { "loss_action": 0.005055961664766073, "loss_total": 0.005055961664766073, "step": 78900 }, { "grad_norm": 0.09476055204868317, "learning_rate": 1.1676411625865297e-05, "loss": 0.005, "step": 78910 }, { "loss_action": 0.00553707592189312, "loss_total": 0.00553707592189312, "step": 78910 }, { "grad_norm": 0.1537560075521469, "learning_rate": 1.1665793848683542e-05, "loss": 0.0064, "step": 78920 }, { "loss_action": 0.00490396935492754, "loss_total": 0.00490396935492754, "step": 78920 }, { "grad_norm": 0.14303040504455566, "learning_rate": 1.1655180263672927e-05, "loss": 0.0057, "step": 78930 }, { "loss_action": 0.0031865774653851986, "loss_total": 0.0031865774653851986, "step": 78930 }, { "grad_norm": 0.14353741705417633, "learning_rate": 1.1644570871994142e-05, "loss": 0.0058, "step": 78940 }, { "loss_action": 0.006098567508161068, "loss_total": 0.006098567508161068, "step": 78940 }, { "grad_norm": 0.16593830287456512, "learning_rate": 1.163396567480744e-05, "loss": 0.0052, "step": 78950 }, { "loss_action": 0.006965468171983957, "loss_total": 0.006965468171983957, "step": 78950 }, { "grad_norm": 0.14131206274032593, "learning_rate": 1.1623364673272552e-05, "loss": 0.0075, "step": 78960 }, { "loss_action": 0.00474855862557888, "loss_total": 0.00474855862557888, "step": 78960 }, { "grad_norm": 0.08960510045289993, "learning_rate": 1.1612767868548807e-05, "loss": 0.0047, "step": 78970 }, { "loss_action": 0.0048662275075912476, "loss_total": 0.0048662275075912476, "step": 78970 }, { "grad_norm": 0.15712079405784607, "learning_rate": 1.1602175261795057e-05, "loss": 0.0063, "step": 78980 }, { "loss_action": 0.005710018798708916, "loss_total": 0.005710018798708916, "step": 78980 }, { "grad_norm": 0.0990896075963974, "learning_rate": 1.1591586854169696e-05, "loss": 0.0057, "step": 78990 }, { "loss_action": 0.0037887925282120705, "loss_total": 0.0037887925282120705, "step": 78990 }, { "grad_norm": 0.16874563694000244, "learning_rate": 1.158100264683064e-05, "loss": 0.0057, "step": 79000 }, { "loss_action": 0.006473625544458628, "loss_total": 0.006473625544458628, "step": 79000 }, { "grad_norm": 0.1523822546005249, "learning_rate": 1.1570422640935386e-05, "loss": 0.0056, "step": 79010 }, { "loss_action": 0.0056948233395814896, "loss_total": 0.0056948233395814896, "step": 79010 }, { "grad_norm": 0.1817711442708969, "learning_rate": 1.155984683764092e-05, "loss": 0.0058, "step": 79020 }, { "loss_action": 0.005718940403312445, "loss_total": 0.005718940403312445, "step": 79020 }, { "grad_norm": 0.18753959238529205, "learning_rate": 1.1549275238103812e-05, "loss": 0.0052, "step": 79030 }, { "loss_action": 0.0053186300210654736, "loss_total": 0.0053186300210654736, "step": 79030 }, { "grad_norm": 0.15920589864253998, "learning_rate": 1.1538707843480152e-05, "loss": 0.0062, "step": 79040 }, { "loss_action": 0.0065290844067931175, "loss_total": 0.0065290844067931175, "step": 79040 }, { "grad_norm": 0.14899194240570068, "learning_rate": 1.1528144654925593e-05, "loss": 0.006, "step": 79050 }, { "loss_action": 0.00560473557561636, "loss_total": 0.00560473557561636, "step": 79050 }, { "grad_norm": 0.16898395121097565, "learning_rate": 1.1517585673595277e-05, "loss": 0.0055, "step": 79060 }, { "loss_action": 0.005723326466977596, "loss_total": 0.005723326466977596, "step": 79060 }, { "grad_norm": 0.1431690752506256, "learning_rate": 1.150703090064395e-05, "loss": 0.0061, "step": 79070 }, { "loss_action": 0.004228911362588406, "loss_total": 0.004228911362588406, "step": 79070 }, { "grad_norm": 0.10179848223924637, "learning_rate": 1.1496480337225835e-05, "loss": 0.0052, "step": 79080 }, { "loss_action": 0.003662580158561468, "loss_total": 0.003662580158561468, "step": 79080 }, { "grad_norm": 0.13082407414913177, "learning_rate": 1.1485933984494751e-05, "loss": 0.0062, "step": 79090 }, { "loss_action": 0.006395068485289812, "loss_total": 0.006395068485289812, "step": 79090 }, { "grad_norm": 0.12975424528121948, "learning_rate": 1.1475391843604e-05, "loss": 0.0059, "step": 79100 }, { "loss_action": 0.00837870966643095, "loss_total": 0.00837870966643095, "step": 79100 }, { "grad_norm": 0.17393222451210022, "learning_rate": 1.1464853915706503e-05, "loss": 0.0061, "step": 79110 }, { "loss_action": 0.004720143508166075, "loss_total": 0.004720143508166075, "step": 79110 }, { "grad_norm": 0.18046900629997253, "learning_rate": 1.1454320201954626e-05, "loss": 0.006, "step": 79120 }, { "loss_action": 0.00740948598831892, "loss_total": 0.00740948598831892, "step": 79120 }, { "grad_norm": 0.1290157586336136, "learning_rate": 1.1443790703500356e-05, "loss": 0.0055, "step": 79130 }, { "loss_action": 0.008241189643740654, "loss_total": 0.008241189643740654, "step": 79130 }, { "grad_norm": 0.20490285754203796, "learning_rate": 1.1433265421495154e-05, "loss": 0.006, "step": 79140 }, { "loss_action": 0.006007207557559013, "loss_total": 0.006007207557559013, "step": 79140 }, { "grad_norm": 0.1712045967578888, "learning_rate": 1.1422744357090065e-05, "loss": 0.0055, "step": 79150 }, { "loss_action": 0.005215666256844997, "loss_total": 0.005215666256844997, "step": 79150 }, { "grad_norm": 0.17071276903152466, "learning_rate": 1.1412227511435647e-05, "loss": 0.0053, "step": 79160 }, { "loss_action": 0.006079406011849642, "loss_total": 0.006079406011849642, "step": 79160 }, { "grad_norm": 0.19737522304058075, "learning_rate": 1.1401714885682025e-05, "loss": 0.0058, "step": 79170 }, { "loss_action": 0.009793036617338657, "loss_total": 0.009793036617338657, "step": 79170 }, { "grad_norm": 0.1506909281015396, "learning_rate": 1.1391206480978823e-05, "loss": 0.0071, "step": 79180 }, { "loss_action": 0.007572177331894636, "loss_total": 0.007572177331894636, "step": 79180 }, { "grad_norm": 0.13854862749576569, "learning_rate": 1.1380702298475227e-05, "loss": 0.0052, "step": 79190 }, { "loss_action": 0.004721058066934347, "loss_total": 0.004721058066934347, "step": 79190 }, { "grad_norm": 0.13333022594451904, "learning_rate": 1.1370202339319985e-05, "loss": 0.0058, "step": 79200 }, { "loss_action": 0.006455730646848679, "loss_total": 0.006455730646848679, "step": 79200 }, { "grad_norm": 0.13299427926540375, "learning_rate": 1.1359706604661319e-05, "loss": 0.0054, "step": 79210 }, { "loss_action": 0.004233954474329948, "loss_total": 0.004233954474329948, "step": 79210 }, { "grad_norm": 0.11796911805868149, "learning_rate": 1.1349215095647042e-05, "loss": 0.0054, "step": 79220 }, { "loss_action": 0.005091767758131027, "loss_total": 0.005091767758131027, "step": 79220 }, { "grad_norm": 0.14320601522922516, "learning_rate": 1.1338727813424493e-05, "loss": 0.006, "step": 79230 }, { "loss_action": 0.004817609209567308, "loss_total": 0.004817609209567308, "step": 79230 }, { "grad_norm": 0.0919872596859932, "learning_rate": 1.132824475914056e-05, "loss": 0.0048, "step": 79240 }, { "loss_action": 0.004443951416760683, "loss_total": 0.004443951416760683, "step": 79240 }, { "grad_norm": 0.14343348145484924, "learning_rate": 1.131776593394162e-05, "loss": 0.006, "step": 79250 }, { "loss_action": 0.004912253934890032, "loss_total": 0.004912253934890032, "step": 79250 }, { "grad_norm": 0.13813991844654083, "learning_rate": 1.1307291338973657e-05, "loss": 0.0057, "step": 79260 }, { "loss_action": 0.006010044366121292, "loss_total": 0.006010044366121292, "step": 79260 }, { "grad_norm": 0.1673693060874939, "learning_rate": 1.1296820975382121e-05, "loss": 0.0054, "step": 79270 }, { "loss_action": 0.0038371754344552755, "loss_total": 0.0038371754344552755, "step": 79270 }, { "grad_norm": 0.22951392829418182, "learning_rate": 1.1286354844312074e-05, "loss": 0.006, "step": 79280 }, { "loss_action": 0.004897844512015581, "loss_total": 0.004897844512015581, "step": 79280 }, { "grad_norm": 0.11679710447788239, "learning_rate": 1.1275892946908023e-05, "loss": 0.0061, "step": 79290 }, { "loss_action": 0.00473235035315156, "loss_total": 0.00473235035315156, "step": 79290 }, { "grad_norm": 0.15342475473880768, "learning_rate": 1.126543528431413e-05, "loss": 0.0056, "step": 79300 }, { "loss_action": 0.007331482134759426, "loss_total": 0.007331482134759426, "step": 79300 }, { "grad_norm": 0.13473615050315857, "learning_rate": 1.125498185767398e-05, "loss": 0.0072, "step": 79310 }, { "loss_action": 0.004933573771268129, "loss_total": 0.004933573771268129, "step": 79310 }, { "grad_norm": 0.14946946501731873, "learning_rate": 1.1244532668130781e-05, "loss": 0.0051, "step": 79320 }, { "loss_action": 0.005118257831782103, "loss_total": 0.005118257831782103, "step": 79320 }, { "grad_norm": 0.19109930098056793, "learning_rate": 1.1234087716827203e-05, "loss": 0.006, "step": 79330 }, { "loss_action": 0.004899131134152412, "loss_total": 0.004899131134152412, "step": 79330 }, { "grad_norm": 0.24292559921741486, "learning_rate": 1.1223647004905524e-05, "loss": 0.0069, "step": 79340 }, { "loss_action": 0.003767853369936347, "loss_total": 0.003767853369936347, "step": 79340 }, { "grad_norm": 0.14722158014774323, "learning_rate": 1.1213210533507485e-05, "loss": 0.0051, "step": 79350 }, { "loss_action": 0.00960080511868, "loss_total": 0.00960080511868, "step": 79350 }, { "grad_norm": 0.1694888025522232, "learning_rate": 1.1202778303774447e-05, "loss": 0.0058, "step": 79360 }, { "loss_action": 0.005733305588364601, "loss_total": 0.005733305588364601, "step": 79360 }, { "grad_norm": 0.1408425271511078, "learning_rate": 1.1192350316847234e-05, "loss": 0.0052, "step": 79370 }, { "loss_action": 0.004053283482789993, "loss_total": 0.004053283482789993, "step": 79370 }, { "grad_norm": 0.170189768075943, "learning_rate": 1.1181926573866258e-05, "loss": 0.0054, "step": 79380 }, { "loss_action": 0.008691019378602505, "loss_total": 0.008691019378602505, "step": 79380 }, { "grad_norm": 0.11462544649839401, "learning_rate": 1.1171507075971416e-05, "loss": 0.0051, "step": 79390 }, { "loss_action": 0.0036077979020774364, "loss_total": 0.0036077979020774364, "step": 79390 }, { "grad_norm": 0.1406179517507553, "learning_rate": 1.1161091824302177e-05, "loss": 0.0054, "step": 79400 }, { "loss_action": 0.006638817023485899, "loss_total": 0.006638817023485899, "step": 79400 }, { "grad_norm": 0.224302276968956, "learning_rate": 1.115068081999755e-05, "loss": 0.0054, "step": 79410 }, { "loss_action": 0.003959766589105129, "loss_total": 0.003959766589105129, "step": 79410 }, { "grad_norm": 0.1991429626941681, "learning_rate": 1.1140274064196071e-05, "loss": 0.0076, "step": 79420 }, { "loss_action": 0.005050917621701956, "loss_total": 0.005050917621701956, "step": 79420 }, { "grad_norm": 0.12427864968776703, "learning_rate": 1.112987155803578e-05, "loss": 0.0053, "step": 79430 }, { "loss_action": 0.004582714289426804, "loss_total": 0.004582714289426804, "step": 79430 }, { "grad_norm": 0.13772225379943848, "learning_rate": 1.1119473302654298e-05, "loss": 0.0057, "step": 79440 }, { "loss_action": 0.004160661716014147, "loss_total": 0.004160661716014147, "step": 79440 }, { "grad_norm": 0.13060423731803894, "learning_rate": 1.1109079299188769e-05, "loss": 0.0052, "step": 79450 }, { "loss_action": 0.003406343050301075, "loss_total": 0.003406343050301075, "step": 79450 }, { "grad_norm": 0.17669938504695892, "learning_rate": 1.1098689548775847e-05, "loss": 0.0067, "step": 79460 }, { "loss_action": 0.005052667111158371, "loss_total": 0.005052667111158371, "step": 79460 }, { "grad_norm": 0.13980847597122192, "learning_rate": 1.1088304052551762e-05, "loss": 0.0058, "step": 79470 }, { "loss_action": 0.005667506717145443, "loss_total": 0.005667506717145443, "step": 79470 }, { "grad_norm": 0.14947813749313354, "learning_rate": 1.1077922811652215e-05, "loss": 0.0061, "step": 79480 }, { "loss_action": 0.004569333512336016, "loss_total": 0.004569333512336016, "step": 79480 }, { "grad_norm": 0.18253549933433533, "learning_rate": 1.1067545827212534e-05, "loss": 0.0059, "step": 79490 }, { "loss_action": 0.005852083209902048, "loss_total": 0.005852083209902048, "step": 79490 }, { "grad_norm": 0.10231391340494156, "learning_rate": 1.1057173100367496e-05, "loss": 0.0055, "step": 79500 }, { "loss_action": 0.004245060496032238, "loss_total": 0.004245060496032238, "step": 79500 }, { "grad_norm": 0.1240304484963417, "learning_rate": 1.1046804632251474e-05, "loss": 0.0057, "step": 79510 }, { "loss_action": 0.005144852679222822, "loss_total": 0.005144852679222822, "step": 79510 }, { "grad_norm": 0.16841351985931396, "learning_rate": 1.1036440423998318e-05, "loss": 0.0051, "step": 79520 }, { "loss_action": 0.009592006914317608, "loss_total": 0.009592006914317608, "step": 79520 }, { "grad_norm": 0.1227056235074997, "learning_rate": 1.1026080476741469e-05, "loss": 0.006, "step": 79530 }, { "loss_action": 0.005657791625708342, "loss_total": 0.005657791625708342, "step": 79530 }, { "grad_norm": 0.21594691276550293, "learning_rate": 1.1015724791613836e-05, "loss": 0.0061, "step": 79540 }, { "loss_action": 0.004083652049303055, "loss_total": 0.004083652049303055, "step": 79540 }, { "grad_norm": 0.14677882194519043, "learning_rate": 1.1005373369747951e-05, "loss": 0.0068, "step": 79550 }, { "loss_action": 0.0067172725684940815, "loss_total": 0.0067172725684940815, "step": 79550 }, { "grad_norm": 0.20673777163028717, "learning_rate": 1.09950262122758e-05, "loss": 0.0054, "step": 79560 }, { "loss_action": 0.007178767584264278, "loss_total": 0.007178767584264278, "step": 79560 }, { "grad_norm": 0.09462433308362961, "learning_rate": 1.0984683320328948e-05, "loss": 0.0053, "step": 79570 }, { "loss_action": 0.004485514480620623, "loss_total": 0.004485514480620623, "step": 79570 }, { "grad_norm": 0.16506266593933105, "learning_rate": 1.0974344695038458e-05, "loss": 0.0051, "step": 79580 }, { "loss_action": 0.004944413900375366, "loss_total": 0.004944413900375366, "step": 79580 }, { "grad_norm": 0.09096764028072357, "learning_rate": 1.0964010337534968e-05, "loss": 0.0052, "step": 79590 }, { "loss_action": 0.005298285745084286, "loss_total": 0.005298285745084286, "step": 79590 }, { "grad_norm": 0.10238523036241531, "learning_rate": 1.0953680248948611e-05, "loss": 0.0065, "step": 79600 }, { "loss_action": 0.004931735806167126, "loss_total": 0.004931735806167126, "step": 79600 }, { "grad_norm": 0.1754692643880844, "learning_rate": 1.0943354430409069e-05, "loss": 0.005, "step": 79610 }, { "loss_action": 0.00593367125838995, "loss_total": 0.00593367125838995, "step": 79610 }, { "grad_norm": 0.1464998722076416, "learning_rate": 1.0933032883045574e-05, "loss": 0.0055, "step": 79620 }, { "loss_action": 0.004438518546521664, "loss_total": 0.004438518546521664, "step": 79620 }, { "grad_norm": 0.17655882239341736, "learning_rate": 1.0922715607986872e-05, "loss": 0.0052, "step": 79630 }, { "loss_action": 0.006908225826919079, "loss_total": 0.006908225826919079, "step": 79630 }, { "grad_norm": 0.19714617729187012, "learning_rate": 1.0912402606361234e-05, "loss": 0.0062, "step": 79640 }, { "loss_action": 0.006946036126464605, "loss_total": 0.006946036126464605, "step": 79640 }, { "grad_norm": 0.14107491075992584, "learning_rate": 1.090209387929647e-05, "loss": 0.0062, "step": 79650 }, { "loss_action": 0.008739331737160683, "loss_total": 0.008739331737160683, "step": 79650 }, { "grad_norm": 0.17409545183181763, "learning_rate": 1.0891789427919957e-05, "loss": 0.0063, "step": 79660 }, { "loss_action": 0.006211965344846249, "loss_total": 0.006211965344846249, "step": 79660 }, { "grad_norm": 0.19871748983860016, "learning_rate": 1.088148925335854e-05, "loss": 0.0066, "step": 79670 }, { "loss_action": 0.007475140038877726, "loss_total": 0.007475140038877726, "step": 79670 }, { "grad_norm": 0.1329895406961441, "learning_rate": 1.087119335673864e-05, "loss": 0.0055, "step": 79680 }, { "loss_action": 0.006128606852144003, "loss_total": 0.006128606852144003, "step": 79680 }, { "grad_norm": 0.14325512945652008, "learning_rate": 1.0860901739186208e-05, "loss": 0.0052, "step": 79690 }, { "loss_action": 0.005279428791254759, "loss_total": 0.005279428791254759, "step": 79690 }, { "grad_norm": 0.17032575607299805, "learning_rate": 1.085061440182673e-05, "loss": 0.0054, "step": 79700 }, { "loss_action": 0.004287004005163908, "loss_total": 0.004287004005163908, "step": 79700 }, { "grad_norm": 0.13045737147331238, "learning_rate": 1.0840331345785193e-05, "loss": 0.0049, "step": 79710 }, { "loss_action": 0.005659862887114286, "loss_total": 0.005659862887114286, "step": 79710 }, { "grad_norm": 0.1388576328754425, "learning_rate": 1.083005257218615e-05, "loss": 0.006, "step": 79720 }, { "loss_action": 0.0047612604685127735, "loss_total": 0.0047612604685127735, "step": 79720 }, { "grad_norm": 0.11173997074365616, "learning_rate": 1.0819778082153642e-05, "loss": 0.006, "step": 79730 }, { "loss_action": 0.004980663303285837, "loss_total": 0.004980663303285837, "step": 79730 }, { "grad_norm": 0.1267140805721283, "learning_rate": 1.0809507876811325e-05, "loss": 0.0064, "step": 79740 }, { "loss_action": 0.0030899110715836287, "loss_total": 0.0030899110715836287, "step": 79740 }, { "grad_norm": 0.17487893998622894, "learning_rate": 1.0799241957282292e-05, "loss": 0.0055, "step": 79750 }, { "loss_action": 0.006546834949404001, "loss_total": 0.006546834949404001, "step": 79750 }, { "grad_norm": 0.1370803564786911, "learning_rate": 1.078898032468923e-05, "loss": 0.0058, "step": 79760 }, { "loss_action": 0.004116807132959366, "loss_total": 0.004116807132959366, "step": 79760 }, { "grad_norm": 0.25394535064697266, "learning_rate": 1.0778722980154315e-05, "loss": 0.0064, "step": 79770 }, { "loss_action": 0.00492652365937829, "loss_total": 0.00492652365937829, "step": 79770 }, { "grad_norm": 0.12159271538257599, "learning_rate": 1.0768469924799302e-05, "loss": 0.0062, "step": 79780 }, { "loss_action": 0.005383790470659733, "loss_total": 0.005383790470659733, "step": 79780 }, { "grad_norm": 0.15855617821216583, "learning_rate": 1.0758221159745419e-05, "loss": 0.0063, "step": 79790 }, { "loss_action": 0.003628604346886277, "loss_total": 0.003628604346886277, "step": 79790 }, { "grad_norm": 0.14901669323444366, "learning_rate": 1.074797668611347e-05, "loss": 0.006, "step": 79800 }, { "loss_action": 0.0072044553235173225, "loss_total": 0.0072044553235173225, "step": 79800 }, { "grad_norm": 0.14574429392814636, "learning_rate": 1.0737736505023777e-05, "loss": 0.0049, "step": 79810 }, { "loss_action": 0.006549254525452852, "loss_total": 0.006549254525452852, "step": 79810 }, { "grad_norm": 0.5497328639030457, "learning_rate": 1.0727500617596203e-05, "loss": 0.0062, "step": 79820 }, { "loss_action": 0.005197318736463785, "loss_total": 0.005197318736463785, "step": 79820 }, { "grad_norm": 0.14941494166851044, "learning_rate": 1.0717269024950104e-05, "loss": 0.0054, "step": 79830 }, { "loss_action": 0.004077089950442314, "loss_total": 0.004077089950442314, "step": 79830 }, { "grad_norm": 0.13605563342571259, "learning_rate": 1.070704172820442e-05, "loss": 0.0054, "step": 79840 }, { "loss_action": 0.004619698040187359, "loss_total": 0.004619698040187359, "step": 79840 }, { "grad_norm": 0.13154855370521545, "learning_rate": 1.0696818728477559e-05, "loss": 0.0051, "step": 79850 }, { "loss_action": 0.003995160106569529, "loss_total": 0.003995160106569529, "step": 79850 }, { "grad_norm": 0.13001354038715363, "learning_rate": 1.0686600026887511e-05, "loss": 0.0057, "step": 79860 }, { "loss_action": 0.009272748604416847, "loss_total": 0.009272748604416847, "step": 79860 }, { "grad_norm": 0.3729470670223236, "learning_rate": 1.0676385624551777e-05, "loss": 0.0066, "step": 79870 }, { "loss_action": 0.0077764419838786125, "loss_total": 0.0077764419838786125, "step": 79870 }, { "grad_norm": 0.1617812216281891, "learning_rate": 1.0666175522587402e-05, "loss": 0.0053, "step": 79880 }, { "loss_action": 0.008891395293176174, "loss_total": 0.008891395293176174, "step": 79880 }, { "grad_norm": 0.13948212563991547, "learning_rate": 1.0655969722110925e-05, "loss": 0.006, "step": 79890 }, { "loss_action": 0.004755237139761448, "loss_total": 0.004755237139761448, "step": 79890 }, { "grad_norm": 0.13912324607372284, "learning_rate": 1.0645768224238439e-05, "loss": 0.0063, "step": 79900 }, { "loss_action": 0.00653443019837141, "loss_total": 0.00653443019837141, "step": 79900 }, { "grad_norm": 0.15604083240032196, "learning_rate": 1.063557103008559e-05, "loss": 0.0061, "step": 79910 }, { "loss_action": 0.004996504168957472, "loss_total": 0.004996504168957472, "step": 79910 }, { "grad_norm": 0.15593315660953522, "learning_rate": 1.0625378140767494e-05, "loss": 0.0051, "step": 79920 }, { "loss_action": 0.004976499360054731, "loss_total": 0.004976499360054731, "step": 79920 }, { "grad_norm": 0.19987505674362183, "learning_rate": 1.0615189557398846e-05, "loss": 0.0051, "step": 79930 }, { "loss_action": 0.006234232801944017, "loss_total": 0.006234232801944017, "step": 79930 }, { "grad_norm": 0.1418926864862442, "learning_rate": 1.060500528109386e-05, "loss": 0.0049, "step": 79940 }, { "loss_action": 0.008304758928716183, "loss_total": 0.008304758928716183, "step": 79940 }, { "grad_norm": 0.16752980649471283, "learning_rate": 1.0594825312966272e-05, "loss": 0.0053, "step": 79950 }, { "loss_action": 0.004679067060351372, "loss_total": 0.004679067060351372, "step": 79950 }, { "grad_norm": 0.13653092086315155, "learning_rate": 1.0584649654129336e-05, "loss": 0.0058, "step": 79960 }, { "loss_action": 0.004806345794349909, "loss_total": 0.004806345794349909, "step": 79960 }, { "grad_norm": 0.1500166356563568, "learning_rate": 1.0574478305695863e-05, "loss": 0.0058, "step": 79970 }, { "loss_action": 0.004151121713221073, "loss_total": 0.004151121713221073, "step": 79970 }, { "grad_norm": 0.13129912316799164, "learning_rate": 1.0564311268778154e-05, "loss": 0.0058, "step": 79980 }, { "loss_action": 0.004908183589577675, "loss_total": 0.004908183589577675, "step": 79980 }, { "grad_norm": 0.2017778903245926, "learning_rate": 1.0554148544488073e-05, "loss": 0.0053, "step": 79990 }, { "loss_action": 0.004115861840546131, "loss_total": 0.004115861840546131, "step": 79990 }, { "grad_norm": 0.18314601480960846, "learning_rate": 1.0543990133937004e-05, "loss": 0.0062, "step": 80000 } ], "logging_steps": 10, "max_steps": 100000, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 10000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }